diff options
Diffstat (limited to 'isuifang_solr/solr/conf')
81 files changed, 15659 insertions, 0 deletions
diff --git a/isuifang_solr/solr/conf/admin-extra.html b/isuifang_solr/solr/conf/admin-extra.html new file mode 100644 index 0000000..aa739da --- /dev/null +++ b/isuifang_solr/solr/conf/admin-extra.html @@ -0,0 +1,31 @@ +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<!-- The content of this page will be statically included into the top +of the admin page. Uncomment this as an example to see there the content +will show up. + +<hr> +<i>This line will appear before the first table</i> +<tr> +<td colspan="2"> +This row will be appended to the end of the first table +</td> +</tr> +<hr> + +--> diff --git a/isuifang_solr/solr/conf/currency.xml b/isuifang_solr/solr/conf/currency.xml new file mode 100644 index 0000000..3a9c58a --- /dev/null +++ b/isuifang_solr/solr/conf/currency.xml @@ -0,0 +1,67 @@ +<?xml version="1.0" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<!-- Example exchange rates file for CurrencyField type named "currency" in example schema --> + +<currencyConfig version="1.0"> + <rates> + <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 --> + <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" /> + <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" /> + <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" /> + <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" /> + <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" /> + <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" /> + <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" /> + <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" /> + <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" /> + <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" /> + <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" /> + <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" /> + <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" /> + <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" /> + <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" /> + <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" /> + <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" /> + <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" /> + <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" /> + <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" /> + <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" /> + <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" /> + <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" /> + <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" /> + <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" /> + <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" /> + <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" /> + <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" /> + <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" /> + <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" /> + <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" /> + <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" /> + <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" /> + <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" /> + <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" /> + <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" /> + <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" /> + + <!-- Cross-rates for some common currencies --> + <rate from="EUR" to="GBP" rate="0.869914" /> + <rate from="EUR" to="NOK" rate="7.800095" /> + <rate from="GBP" to="NOK" rate="8.966508" /> + </rates> +</currencyConfig> diff --git a/isuifang_solr/solr/conf/elevate.xml b/isuifang_solr/solr/conf/elevate.xml new file mode 100644 index 0000000..7630ebe --- /dev/null +++ b/isuifang_solr/solr/conf/elevate.xml @@ -0,0 +1,36 @@ +<?xml version="1.0" encoding="UTF-8" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<!-- If this file is found in the config directory, it will only be + loaded once at startup. If it is found in Solr's data + directory, it will be re-loaded every commit. +--> + +<elevate> + <query text="foo bar"> + <doc id="1" /> + <doc id="2" /> + <doc id="3" /> + </query> + + <query text="ipod"> + <doc id="MA147LL/A" /> <!-- put the actual ipod at the top --> + <doc id="IW-02" exclude="true" /> <!-- exclude this cable --> + </query> + +</elevate> diff --git a/isuifang_solr/solr/conf/lang/contractions_ca.txt b/isuifang_solr/solr/conf/lang/contractions_ca.txt new file mode 100644 index 0000000..307a85f --- /dev/null +++ b/isuifang_solr/solr/conf/lang/contractions_ca.txt @@ -0,0 +1,8 @@ +# Set of Catalan contractions for ElisionFilter +# TODO: load this as a resource from the analyzer and sync it in build.xml +d +l +m +n +s +t diff --git a/isuifang_solr/solr/conf/lang/contractions_fr.txt b/isuifang_solr/solr/conf/lang/contractions_fr.txt new file mode 100644 index 0000000..722db58 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/contractions_fr.txt @@ -0,0 +1,9 @@ +# Set of French contractions for ElisionFilter +# TODO: load this as a resource from the analyzer and sync it in build.xml +l +m +t +qu +n +s +j diff --git a/isuifang_solr/solr/conf/lang/contractions_ga.txt b/isuifang_solr/solr/conf/lang/contractions_ga.txt new file mode 100644 index 0000000..9ebe7fa --- /dev/null +++ b/isuifang_solr/solr/conf/lang/contractions_ga.txt @@ -0,0 +1,5 @@ +# Set of Irish contractions for ElisionFilter +# TODO: load this as a resource from the analyzer and sync it in build.xml +d +m +b diff --git a/isuifang_solr/solr/conf/lang/contractions_it.txt b/isuifang_solr/solr/conf/lang/contractions_it.txt new file mode 100644 index 0000000..cac0409 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/contractions_it.txt @@ -0,0 +1,23 @@ +# Set of Italian contractions for ElisionFilter +# TODO: load this as a resource from the analyzer and sync it in build.xml +c +l +all +dall +dell +nell +sull +coll +pell +gl +agl +dagl +degl +negl +sugl +un +m +t +s +v +d diff --git a/isuifang_solr/solr/conf/lang/hyphenations_ga.txt b/isuifang_solr/solr/conf/lang/hyphenations_ga.txt new file mode 100644 index 0000000..4d2642c --- /dev/null +++ b/isuifang_solr/solr/conf/lang/hyphenations_ga.txt @@ -0,0 +1,5 @@ +# Set of Irish hyphenations for StopFilter +# TODO: load this as a resource from the analyzer and sync it in build.xml +h +n +t diff --git a/isuifang_solr/solr/conf/lang/stemdict_nl.txt b/isuifang_solr/solr/conf/lang/stemdict_nl.txt new file mode 100644 index 0000000..4410729 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stemdict_nl.txt @@ -0,0 +1,6 @@ +# Set of overrides for the dutch stemmer +# TODO: load this as a resource from the analyzer and sync it in build.xml +fiets fiets +bromfiets bromfiets +ei eier +kind kinder diff --git a/isuifang_solr/solr/conf/lang/stoptags_ja.txt b/isuifang_solr/solr/conf/lang/stoptags_ja.txt new file mode 100644 index 0000000..71b7508 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stoptags_ja.txt @@ -0,0 +1,420 @@ +# +# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter. +# +# Any token with a part-of-speech tag that exactly matches those defined in this +# file are removed from the token stream. +# +# Set your own stoptags by uncommenting the lines below. Note that comments are +# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists, +# etc. that can be useful for building you own stoptag set. +# +# The entire possible tagset is provided below for convenience. +# +##### +# noun: unclassified nouns +#名詞 +# +# noun-common: Common nouns or nouns where the sub-classification is undefined +#名詞-一般 +# +# noun-proper: Proper nouns where the sub-classification is undefined +#名詞-固有名詞 +# +# noun-proper-misc: miscellaneous proper nouns +#名詞-固有名詞-一般 +# +# noun-proper-person: Personal names where the sub-classification is undefined +#名詞-固有名詞-人名 +# +# noun-proper-person-misc: names that cannot be divided into surname and +# given name; foreign names; names where the surname or given name is unknown. +# e.g. お市の方 +#名詞-固有名詞-人名-一般 +# +# noun-proper-person-surname: Mainly Japanese surnames. +# e.g. 山田 +#名詞-固有名詞-人名-姓 +# +# noun-proper-person-given_name: Mainly Japanese given names. +# e.g. 太郎 +#名詞-固有名詞-人名-名 +# +# noun-proper-organization: Names representing organizations. +# e.g. 通産省, NHK +#名詞-固有名詞-組織 +# +# noun-proper-place: Place names where the sub-classification is undefined +#名詞-固有名詞-地域 +# +# noun-proper-place-misc: Place names excluding countries. +# e.g. アジア, バルセロナ, 京都 +#名詞-固有名詞-地域-一般 +# +# noun-proper-place-country: Country names. +# e.g. 日本, オーストラリア +#名詞-固有名詞-地域-国 +# +# noun-pronoun: Pronouns where the sub-classification is undefined +#名詞-代名詞 +# +# noun-pronoun-misc: miscellaneous pronouns: +# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ +#名詞-代名詞-一般 +# +# noun-pronoun-contraction: Spoken language contraction made by combining a +# pronoun and the particle 'wa'. +# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ +#名詞-代名詞-縮約 +# +# noun-adverbial: Temporal nouns such as names of days or months that behave +# like adverbs. Nouns that represent amount or ratios and can be used adverbially, +# e.g. 金曜, 一月, 午後, 少量 +#名詞-副詞可能 +# +# noun-verbal: Nouns that take arguments with case and can appear followed by +# 'suru' and related verbs (する, できる, なさる, くださる) +# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り +#名詞-サ変接続 +# +# noun-adjective-base: The base form of adjectives, words that appear before な ("na") +# e.g. 健康, 安易, 駄目, だめ +#名詞-形容動詞語幹 +# +# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数. +# e.g. 0, 1, 2, 何, 数, 幾 +#名詞-数 +# +# noun-affix: noun affixes where the sub-classification is undefined +#名詞-非自立 +# +# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that +# attach to the base form of inflectional words, words that cannot be classified +# into any of the other categories below. This category includes indefinite nouns. +# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第, +# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み, +# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳, +# わり, 割り, 割, ん-口語/, もん-口語/ +#名詞-非自立-一般 +# +# noun-affix-adverbial: noun affixes that that can behave as adverbs. +# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ, +# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか, +# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所, +# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま, +# 儘, 侭, みぎり, 矢先 +#名詞-非自立-副詞可能 +# +# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars +# with the stem よう(だ) ("you(da)"). +# e.g. よう, やう, 様 (よう) +#名詞-非自立-助動詞語幹 +# +# noun-affix-adjective-base: noun affixes that can connect to the indeclinable +# connection form な (aux "da"). +# e.g. みたい, ふう +#名詞-非自立-形容動詞語幹 +# +# noun-special: special nouns where the sub-classification is undefined. +#名詞-特殊 +# +# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is +# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base +# form of inflectional words. +# e.g. そう +#名詞-特殊-助動詞語幹 +# +# noun-suffix: noun suffixes where the sub-classification is undefined. +#名詞-接尾 +# +# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect +# to ガル or タイ and can combine into compound nouns, words that cannot be classified into +# any of the other categories below. In general, this category is more inclusive than +# 接尾語 ("suffix") and is usually the last element in a compound noun. +# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み, +# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用 +#名詞-接尾-一般 +# +# noun-suffix-person: Suffixes that form nouns and attach to person names more often +# than other nouns. +# e.g. 君, 様, 著 +#名詞-接尾-人名 +# +# noun-suffix-place: Suffixes that form nouns and attach to place names more often +# than other nouns. +# e.g. 町, 市, 県 +#名詞-接尾-地域 +# +# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that +# can appear before スル ("suru"). +# e.g. 化, 視, 分け, 入り, 落ち, 買い +#名詞-接尾-サ変接続 +# +# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions, +# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the +# conjunctive form of inflectional words. +# e.g. そう +#名詞-接尾-助動詞語幹 +# +# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive +# form of inflectional words and appear before the copula だ ("da"). +# e.g. 的, げ, がち +#名詞-接尾-形容動詞語幹 +# +# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs. +# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ) +#名詞-接尾-副詞可能 +# +# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category +# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach +# to numbers. +# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半 +#名詞-接尾-助数詞 +# +# noun-suffix-special: Special suffixes that mainly attach to inflecting words. +# e.g. (楽し) さ, (考え) 方 +#名詞-接尾-特殊 +# +# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words +# together. +# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦) +#名詞-接続詞的 +# +# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are +# semantically verb-like. +# e.g. ごらん, ご覧, 御覧, 頂戴 +#名詞-動詞非自立的 +# +# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry, +# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation") +# is いわく ("iwaku"). +#名詞-引用文字列 +# +# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and +# behave like an adjective. +# e.g. 申し訳, 仕方, とんでも, 違い +#名詞-ナイ形容詞語幹 +# +##### +# prefix: unclassified prefixes +#接頭詞 +# +# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms) +# excluding numerical expressions. +# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派) +#接頭詞-名詞接続 +# +# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb +# in conjunctive form followed by なる/なさる/くださる. +# e.g. お (読みなさい), お (座り) +#接頭詞-動詞接続 +# +# prefix-adjectival: Prefixes that attach to adjectives. +# e.g. お (寒いですねえ), バカ (でかい) +#接頭詞-形容詞接続 +# +# prefix-numerical: Prefixes that attach to numerical expressions. +# e.g. 約, およそ, 毎時 +#接頭詞-数接続 +# +##### +# verb: unclassified verbs +#動詞 +# +# verb-main: +#動詞-自立 +# +# verb-auxiliary: +#動詞-非自立 +# +# verb-suffix: +#動詞-接尾 +# +##### +# adjective: unclassified adjectives +#形容詞 +# +# adjective-main: +#形容詞-自立 +# +# adjective-auxiliary: +#形容詞-非自立 +# +# adjective-suffix: +#形容詞-接尾 +# +##### +# adverb: unclassified adverbs +#副詞 +# +# adverb-misc: Words that can be segmented into one unit and where adnominal +# modification is not possible. +# e.g. あいかわらず, 多分 +#副詞-一般 +# +# adverb-particle_conjunction: Adverbs that can be followed by の, は, に, +# な, する, だ, etc. +# e.g. こんなに, そんなに, あんなに, なにか, なんでも +#副詞-助詞類接続 +# +##### +# adnominal: Words that only have noun-modifying forms. +# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう, +# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした, +# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き +#連体詞 +# +##### +# conjunction: Conjunctions that can occur independently. +# e.g. が, けれども, そして, じゃあ, それどころか +接続詞 +# +##### +# particle: unclassified particles. +助詞 +# +# particle-case: case particles where the subclassification is undefined. +助詞-格助詞 +# +# particle-case-misc: Case particles. +# e.g. から, が, で, と, に, へ, より, を, の, にて +助詞-格助詞-一般 +# +# particle-case-quote: the "to" that appears after nouns, a person’s speech, +# quotation marks, expressions of decisions from a meeting, reasons, judgements, +# conjectures, etc. +# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...) +助詞-格助詞-引用 +# +# particle-case-compound: Compounds of particles and verbs that mainly behave +# like case particles. +# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って, +# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける, +# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し, +# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして, +# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって, +# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る, +# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる, +# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ +助詞-格助詞-連語 +# +# particle-conjunctive: +# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども, +# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/, +# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/ +助詞-接続助詞 +# +# particle-dependency: +# e.g. こそ, さえ, しか, すら, は, も, ぞ +助詞-係助詞 +# +# particle-adverbial: +# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/, +# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/, +# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに, +# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/, +# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」) +助詞-副助詞 +# +# particle-interjective: particles with interjective grammatical roles. +# e.g. (松島) や +助詞-間投助詞 +# +# particle-coordinate: +# e.g. と, たり, だの, だり, とか, なり, や, やら +助詞-並立助詞 +# +# particle-final: +# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ, +# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/ +助詞-終助詞 +# +# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is +# adverbial, conjunctive, or sentence final. For example: +# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」 +# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」 +# 「(祈りが届いたせい) か (, 試験に合格した.)」 +# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」 +# e.g. か +助詞-副助詞／並立助詞／終助詞 +# +# particle-adnominalizer: The "no" that attaches to nouns and modifies +# non-inflectional words. +助詞-連体化 +# +# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs +# that are giongo, giseigo, or gitaigo. +# e.g. に, と +助詞-副詞化 +# +# particle-special: A particle that does not fit into one of the above classifications. +# This includes particles that are used in Tanka, Haiku, and other poetry. +# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家) +助詞-特殊 +# +##### +# auxiliary-verb: +助動詞 +# +##### +# interjection: Greetings and other exclamations. +# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます, +# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい +#感動詞 +# +##### +# symbol: unclassified Symbols. +記号 +# +# symbol-misc: A general symbol not in one of the categories below. +# e.g. [○◎@$〒→+] +記号-一般 +# +# symbol-comma: Commas +# e.g. [,、] +記号-読点 +# +# symbol-period: Periods and full stops. +# e.g. [.．。] +記号-句点 +# +# symbol-space: Full-width whitespace. +記号-空白 +# +# symbol-open_bracket: +# e.g. [({‘“『【] +記号-括弧開 +# +# symbol-close_bracket: +# e.g. [)}’”』」】] +記号-括弧閉 +# +# symbol-alphabetic: +#記号-アルファベット +# +##### +# other: unclassified other +#その他 +# +# other-interjection: Words that are hard to classify as noun-suffixes or +# sentence-final particles. +# e.g. (だ)ァ +その他-間投 +# +##### +# filler: Aizuchi that occurs during a conversation or sounds inserted as filler. +# e.g. あの, うんと, えと +フィラー +# +##### +# non-verbal: non-verbal sound. +非言語音 +# +##### +# fragment: +#語断片 +# +##### +# unknown: unknown part of speech. +#未知語 +# +##### End of file diff --git a/isuifang_solr/solr/conf/lang/stopwords_ar.txt b/isuifang_solr/solr/conf/lang/stopwords_ar.txt new file mode 100644 index 0000000..046829d --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ar.txt @@ -0,0 +1,125 @@ +# This file was created by Jacques Savoy and is distributed under the BSD license. +# See http://members.unine.ch/jacques.savoy/clef/index.html. +# Also see http://www.opensource.org/licenses/bsd-license.html +# Cleaned on October 11, 2009 (not normalized, so use before normalization) +# This means that when modifying this list, you might need to add some +# redundant entries, for example containing forms with both أ and ا +من +ومن +منها +منه +في +وفي +فيها +فيه +و +ف +ثم +او +أو +ب +بها +به +ا +أ +اى +اي +أي +أى +لا +ولا +الا +ألا +إلا +لكن +ما +وما +كما +فما +عن +مع +اذا +إذا +ان +أن +إن +انها +أنها +إنها +انه +أنه +إنه +بان +بأن +فان +فأن +وان +وأن +وإن +التى +التي +الذى +الذي +الذين +الى +الي +إلى +إلي +على +عليها +عليه +اما +أما +إما +ايضا +أيضا +كل +وكل +لم +ولم +لن +ولن +هى +هي +هو +وهى +وهي +وهو +فهى +فهي +فهو +انت +أنت +لك +لها +له +هذه +هذا +تلك +ذلك +هناك +كانت +كان +يكون +تكون +وكانت +وكان +غير +بعض +قد +نحو +بين +بينما +منذ +ضمن +حيث +الان +الآن +خلال +بعد +قبل +حتى +عند +عندما +لدى +جميع diff --git a/isuifang_solr/solr/conf/lang/stopwords_bg.txt b/isuifang_solr/solr/conf/lang/stopwords_bg.txt new file mode 100644 index 0000000..1ae4ba2 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_bg.txt @@ -0,0 +1,193 @@ +# This file was created by Jacques Savoy and is distributed under the BSD license. +# See http://members.unine.ch/jacques.savoy/clef/index.html. +# Also see http://www.opensource.org/licenses/bsd-license.html +а +аз +ако +ала +бе +без +беше +би +бил +била +били +било +близо +бъдат +бъде +бяха +в +вас +ваш +ваша +вероятно +вече +взема +ви +вие +винаги +все +всеки +всички +всичко +всяка +във +въпреки +върху +г +ги +главно +го +д +да +дали +до +докато +докога +дори +досега +доста +е +едва +един +ето +за +зад +заедно +заради +засега +затова +защо +защото +и +из +или +им +има +имат +иска +й +каза +как +каква +какво +както +какъв +като +кога +когато +което +които +кой +който +колко +която +къде +където +към +ли +м +ме +между +мен +ми +мнозина +мога +могат +може +моля +момента +му +н +на +над +назад +най +направи +напред +например +нас +не +него +нея +ни +ние +никой +нито +но +някои +някой +няма +обаче +около +освен +особено +от +отгоре +отново +още +пак +по +повече +повечето +под +поне +поради +после +почти +прави +пред +преди +през +при +пък +първо +с +са +само +се +сега +си +скоро +след +сме +според +сред +срещу +сте +съм +със +също +т +тази +така +такива +такъв +там +твой +те +тези +ти +тн +то +това +тогава +този +той +толкова +точно +трябва +тук +тъй +тя +тях +у +харесва +ч +че +често +чрез +ще +щом +я diff --git a/isuifang_solr/solr/conf/lang/stopwords_ca.txt b/isuifang_solr/solr/conf/lang/stopwords_ca.txt new file mode 100644 index 0000000..3da65de --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ca.txt @@ -0,0 +1,220 @@ +# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed) +a +abans +ací +ah +així +això +al +als +aleshores +algun +alguna +algunes +alguns +alhora +allà +allí +allò +altra +altre +altres +amb +ambdós +ambdues +apa +aquell +aquella +aquelles +aquells +aquest +aquesta +aquestes +aquests +aquí +baix +cada +cadascú +cadascuna +cadascunes +cadascuns +com +contra +d'un +d'una +d'unes +d'uns +dalt +de +del +dels +des +després +dins +dintre +donat +doncs +durant +e +eh +el +els +em +en +encara +ens +entre +érem +eren +éreu +es +és +esta +està +estàvem +estaven +estàveu +esteu +et +etc +ets +fins +fora +gairebé +ha +han +has +havia +he +hem +heu +hi +ho +i +igual +iguals +ja +l'hi +la +les +li +li'n +llavors +m'he +ma +mal +malgrat +mateix +mateixa +mateixes +mateixos +me +mentre +més +meu +meus +meva +meves +molt +molta +moltes +molts +mon +mons +n'he +n'hi +ne +ni +no +nogensmenys +només +nosaltres +nostra +nostre +nostres +o +oh +oi +on +pas +pel +pels +per +però +perquè +poc +poca +pocs +poques +potser +propi +qual +quals +quan +quant +que +què +quelcom +qui +quin +quina +quines +quins +s'ha +s'han +sa +semblant +semblants +ses +seu +seus +seva +seva +seves +si +sobre +sobretot +sóc +solament +sols +son +són +sons +sota +sou +t'ha +t'han +t'he +ta +tal +també +tampoc +tan +tant +tanta +tantes +teu +teus +teva +teves +ton +tons +tot +tota +totes +tots +un +una +unes +uns +us +va +vaig +vam +van +vas +veu +vosaltres +vostra +vostre +vostres diff --git a/isuifang_solr/solr/conf/lang/stopwords_cz.txt b/isuifang_solr/solr/conf/lang/stopwords_cz.txt new file mode 100644 index 0000000..53c6097 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_cz.txt @@ -0,0 +1,172 @@ +a +s +k +o +i +u +v +z +dnes +cz +tímto +budeš +budem +byli +jseš +můj +svým +ta +tomto +tohle +tuto +tyto +jej +zda +proč +máte +tato +kam +tohoto +kdo +kteří +mi +nám +tom +tomuto +mít +nic +proto +kterou +byla +toho +protože +asi +ho +naši +napište +re +což +tím +takže +svých +její +svými +jste +aj +tu +tedy +teto +bylo +kde +ke +pravé +ji +nad +nejsou +či +pod +téma +mezi +přes +ty +pak +vám +ani +když +však +neg +jsem +tento +článku +články +aby +jsme +před +pta +jejich +byl +ještě +až +bez +také +pouze +první +vaše +která +nás +nový +tipy +pokud +může +strana +jeho +své +jiné +zprávy +nové +není +vás +jen +podle +zde +už +být +více +bude +již +než +který +by +které +co +nebo +ten +tak +má +při +od +po +jsou +jak +další +ale +si +se +ve +to +jako +za +zpět +ze +do +pro +je +na +atd +atp +jakmile +přičemž +já +on +ona +ono +oni +ony +my +vy +jí +ji +mě +mne +jemu +tomu +těm +těmu +němu +němuž +jehož +jíž +jelikož +jež +jakož +načež diff --git a/isuifang_solr/solr/conf/lang/stopwords_da.txt b/isuifang_solr/solr/conf/lang/stopwords_da.txt new file mode 100644 index 0000000..a3ff5fe --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_da.txt @@ -0,0 +1,108 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Danish stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + | This is a ranked list (commonest to rarest) of stopwords derived from + | a large text sample. + + +og | and +i | in +jeg | I +det | that (dem. pronoun)/it (pers. pronoun) +at | that (in front of a sentence)/to (with infinitive) +en | a/an +den | it (pers. pronoun)/that (dem. pronoun) +til | to/at/for/until/against/by/of/into, more +er | present tense of "to be" +som | who, as +på | on/upon/in/on/at/to/after/of/with/for, on +de | they +med | with/by/in, along +han | he +af | of/by/from/off/for/in/with/on, off +for | at/for/to/from/by/of/ago, in front/before, because +ikke | not +der | who/which, there/those +var | past tense of "to be" +mig | me/myself +sig | oneself/himself/herself/itself/themselves +men | but +et | a/an/one, one (number), someone/somebody/one +har | present tense of "to have" +om | round/about/for/in/a, about/around/down, if +vi | we +min | my +havde | past tense of "to have" +ham | him +hun | she +nu | now +over | over/above/across/by/beyond/past/on/about, over/past +da | then, when/as/since +fra | from/off/since, off, since +du | you +ud | out +sin | his/her/its/one's +dem | them +os | us/ourselves +op | up +man | you/one +hans | his +hvor | where +eller | or +hvad | what +skal | must/shall etc. +selv | myself/youself/herself/ourselves etc., even +her | here +alle | all/everyone/everybody etc. +vil | will (verb) +blev | past tense of "to stay/to remain/to get/to become" +kunne | could +ind | in +når | when +være | present tense of "to be" +dog | however/yet/after all +noget | something +ville | would +jo | you know/you see (adv), yes +deres | their/theirs +efter | after/behind/according to/for/by/from, later/afterwards +ned | down +skulle | should +denne | this +end | than +dette | this +mit | my/mine +også | also +under | under/beneath/below/during, below/underneath +have | have +dig | you +anden | other +hende | her +mine | my +alt | everything +meget | much/very, plenty of +sit | his, her, its, one's +sine | his, her, its, one's +vor | our +mod | against +disse | these +hvis | if +din | your/yours +nogle | some +hos | by/at +blive | be/become +mange | many +ad | by/through +bliver | present tense of "to be/to become" +hendes | her/hers +været | be +thi | for (conj) +jer | you +sådan | such, like this/like that diff --git a/isuifang_solr/solr/conf/lang/stopwords_de.txt b/isuifang_solr/solr/conf/lang/stopwords_de.txt new file mode 100644 index 0000000..f770384 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_de.txt @@ -0,0 +1,292 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A German stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + | The number of forms in this list is reduced significantly by passing it + | through the German stemmer. + + +aber | but + +alle | all +allem +allen +aller +alles + +als | than, as +also | so +am | an + dem +an | at + +ander | other +andere +anderem +anderen +anderer +anderes +anderm +andern +anderr +anders + +auch | also +auf | on +aus | out of +bei | by +bin | am +bis | until +bist | art +da | there +damit | with it +dann | then + +der | the +den +des +dem +die +das + +daß | that + +derselbe | the same +derselben +denselben +desselben +demselben +dieselbe +dieselben +dasselbe + +dazu | to that + +dein | thy +deine +deinem +deinen +deiner +deines + +denn | because + +derer | of those +dessen | of him + +dich | thee +dir | to thee +du | thou + +dies | this +diese +diesem +diesen +dieser +dieses + + +doch | (several meanings) +dort | (over) there + + +durch | through + +ein | a +eine +einem +einen +einer +eines + +einig | some +einige +einigem +einigen +einiger +einiges + +einmal | once + +er | he +ihn | him +ihm | to him + +es | it +etwas | something + +euer | your +eure +eurem +euren +eurer +eures + +für | for +gegen | towards +gewesen | p.p. of sein +hab | have +habe | have +haben | have +hat | has +hatte | had +hatten | had +hier | here +hin | there +hinter | behind + +ich | I +mich | me +mir | to me + + +ihr | you, to her +ihre +ihrem +ihren +ihrer +ihres +euch | to you + +im | in + dem +in | in +indem | while +ins | in + das +ist | is + +jede | each, every +jedem +jeden +jeder +jedes + +jene | that +jenem +jenen +jener +jenes + +jetzt | now +kann | can + +kein | no +keine +keinem +keinen +keiner +keines + +können | can +könnte | could +machen | do +man | one + +manche | some, many a +manchem +manchen +mancher +manches + +mein | my +meine +meinem +meinen +meiner +meines + +mit | with +muss | must +musste | had to +nach | to(wards) +nicht | not +nichts | nothing +noch | still, yet +nun | now +nur | only +ob | whether +oder | or +ohne | without +sehr | very + +sein | his +seine +seinem +seinen +seiner +seines + +selbst | self +sich | herself + +sie | they, she +ihnen | to them + +sind | are +so | so + +solche | such +solchem +solchen +solcher +solches + +soll | shall +sollte | should +sondern | but +sonst | else +über | over +um | about, around +und | and + +uns | us +unse +unsem +unsen +unser +unses + +unter | under +viel | much +vom | von + dem +von | from +vor | before +während | while +war | was +waren | were +warst | wast +was | what +weg | away, off +weil | because +weiter | further + +welche | which +welchem +welchen +welcher +welches + +wenn | when +werde | will +werden | will +wie | how +wieder | again +will | want +wir | we +wird | will +wirst | willst +wo | where +wollen | want +wollte | wanted +würde | would +würden | would +zu | to +zum | zu + dem +zur | zu + der +zwar | indeed +zwischen | between + diff --git a/isuifang_solr/solr/conf/lang/stopwords_el.txt b/isuifang_solr/solr/conf/lang/stopwords_el.txt new file mode 100644 index 0000000..232681f --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_el.txt @@ -0,0 +1,78 @@ +# Lucene Greek Stopwords list +# Note: by default this file is used after GreekLowerCaseFilter, +# so when modifying this file use 'σ' instead of 'ς' +ο +η +το +οι +τα +του +τησ +των +τον +την +και +κι +κ +ειμαι +εισαι +ειναι +ειμαστε +ειστε +στο +στον +στη +στην +μα +αλλα +απο +για +προσ +με +σε +ωσ +παρα +αντι +κατα +μετα +θα +να +δε +δεν +μη +μην +επι +ενω +εαν +αν +τοτε +που +πωσ +ποιοσ +ποια +ποιο +ποιοι +ποιεσ +ποιων +ποιουσ +αυτοσ +αυτη +αυτο +αυτοι +αυτων +αυτουσ +αυτεσ +αυτα +εκεινοσ +εκεινη +εκεινο +εκεινοι +εκεινεσ +εκεινα +εκεινων +εκεινουσ +οπωσ +ομωσ +ισωσ +οσο +οτι diff --git a/isuifang_solr/solr/conf/lang/stopwords_en.txt b/isuifang_solr/solr/conf/lang/stopwords_en.txt new file mode 100644 index 0000000..2c164c0 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_en.txt @@ -0,0 +1,54 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# a couple of test stopwords to test that the words are really being +# configured from this file: +stopworda +stopwordb + +# Standard english stop words taken from Lucene's StopAnalyzer +a +an +and +are +as +at +be +but +by +for +if +in +into +is +it +no +not +of +on +or +such +that +the +their +then +there +these +they +this +to +was +will +with diff --git a/isuifang_solr/solr/conf/lang/stopwords_es.txt b/isuifang_solr/solr/conf/lang/stopwords_es.txt new file mode 100644 index 0000000..2db1476 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_es.txt @@ -0,0 +1,354 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Spanish stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + + | The following is a ranked list (commonest to rarest) of stopwords + | deriving from a large sample of text. + + | Extra words have been added at the end. + +de | from, of +la | the, her +que | who, that +el | the +en | in +y | and +a | to +los | the, them +del | de + el +se | himself, from him etc +las | the, them +por | for, by, etc +un | a +para | for +con | with +no | no +una | a +su | his, her +al | a + el + | es from SER +lo | him +como | how +más | more +pero | pero +sus | su plural +le | to him, her +ya | already +o | or + | fue from SER +este | this + | ha from HABER +sí | himself etc +porque | because +esta | this + | son from SER +entre | between + | está from ESTAR +cuando | when +muy | very +sin | without +sobre | on + | ser from SER + | tiene from TENER +también | also +me | me +hasta | until +hay | there is/are +donde | where + | han from HABER +quien | whom, that + | están from ESTAR + | estado from ESTAR +desde | from +todo | all +nos | us +durante | during + | estados from ESTAR +todos | all +uno | a +les | to them +ni | nor +contra | against +otros | other + | fueron from SER +ese | that +eso | that + | había from HABER +ante | before +ellos | they +e | and (variant of y) +esto | this +mí | me +antes | before +algunos | some +qué | what? +unos | a +yo | I +otro | other +otras | other +otra | other +él | he +tanto | so much, many +esa | that +estos | these +mucho | much, many +quienes | who +nada | nothing +muchos | many +cual | who + | sea from SER +poco | few +ella | she +estar | to be + | haber from HABER +estas | these + | estaba from ESTAR + | estamos from ESTAR +algunas | some +algo | something +nosotros | we + + | other forms + +mi | me +mis | mi plural +tú | thou +te | thee +ti | thee +tu | thy +tus | tu plural +ellas | they +nosotras | we +vosotros | you +vosotras | you +os | you +mío | mine +mía | +míos | +mías | +tuyo | thine +tuya | +tuyos | +tuyas | +suyo | his, hers, theirs +suya | +suyos | +suyas | +nuestro | ours +nuestra | +nuestros | +nuestras | +vuestro | yours +vuestra | +vuestros | +vuestras | +esos | those +esas | those + + | forms of estar, to be (not including the infinitive): +estoy +estás +está +estamos +estáis +están +esté +estés +estemos +estéis +estén +estaré +estarás +estará +estaremos +estaréis +estarán +estaría +estarías +estaríamos +estaríais +estarían +estaba +estabas +estábamos +estabais +estaban +estuve +estuviste +estuvo +estuvimos +estuvisteis +estuvieron +estuviera +estuvieras +estuviéramos +estuvierais +estuvieran +estuviese +estuvieses +estuviésemos +estuvieseis +estuviesen +estando +estado +estada +estados +estadas +estad + + | forms of haber, to have (not including the infinitive): +he +has +ha +hemos +habéis +han +haya +hayas +hayamos +hayáis +hayan +habré +habrás +habrá +habremos +habréis +habrán +habría +habrías +habríamos +habríais +habrían +había +habías +habíamos +habíais +habían +hube +hubiste +hubo +hubimos +hubisteis +hubieron +hubiera +hubieras +hubiéramos +hubierais +hubieran +hubiese +hubieses +hubiésemos +hubieseis +hubiesen +habiendo +habido +habida +habidos +habidas + + | forms of ser, to be (not including the infinitive): +soy +eres +es +somos +sois +son +sea +seas +seamos +seáis +sean +seré +serás +será +seremos +seréis +serán +sería +serías +seríamos +seríais +serían +era +eras +éramos +erais +eran +fui +fuiste +fue +fuimos +fuisteis +fueron +fuera +fueras +fuéramos +fuerais +fueran +fuese +fueses +fuésemos +fueseis +fuesen +siendo +sido + | sed also means 'thirst' + + | forms of tener, to have (not including the infinitive): +tengo +tienes +tiene +tenemos +tenéis +tienen +tenga +tengas +tengamos +tengáis +tengan +tendré +tendrás +tendrá +tendremos +tendréis +tendrán +tendría +tendrías +tendríamos +tendríais +tendrían +tenía +tenías +teníamos +teníais +tenían +tuve +tuviste +tuvo +tuvimos +tuvisteis +tuvieron +tuviera +tuvieras +tuviéramos +tuvierais +tuvieran +tuviese +tuvieses +tuviésemos +tuvieseis +tuviesen +teniendo +tenido +tenida +tenidos +tenidas +tened + diff --git a/isuifang_solr/solr/conf/lang/stopwords_eu.txt b/isuifang_solr/solr/conf/lang/stopwords_eu.txt new file mode 100644 index 0000000..25f1db9 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_eu.txt @@ -0,0 +1,99 @@ +# example set of basque stopwords +al +anitz +arabera +asko +baina +bat +batean +batek +bati +batzuei +batzuek +batzuetan +batzuk +bera +beraiek +berau +berauek +bere +berori +beroriek +beste +bezala +da +dago +dira +ditu +du +dute +edo +egin +ere +eta +eurak +ez +gainera +gu +gutxi +guzti +haiei +haiek +haietan +hainbeste +hala +han +handik +hango +hara +hari +hark +hartan +hau +hauei +hauek +hauetan +hemen +hemendik +hemengo +hi +hona +honek +honela +honetan +honi +hor +hori +horiei +horiek +horietan +horko +horra +horrek +horrela +horretan +horri +hortik +hura +izan +ni +noiz +nola +non +nondik +nongo +nor +nora +ze +zein +zen +zenbait +zenbat +zer +zergatik +ziren +zituen +zu +zuek +zuen +zuten diff --git a/isuifang_solr/solr/conf/lang/stopwords_fa.txt b/isuifang_solr/solr/conf/lang/stopwords_fa.txt new file mode 100644 index 0000000..723641c --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_fa.txt @@ -0,0 +1,313 @@ +# This file was created by Jacques Savoy and is distributed under the BSD license. +# See http://members.unine.ch/jacques.savoy/clef/index.html. +# Also see http://www.opensource.org/licenses/bsd-license.html +# Note: by default this file is used after normalization, so when adding entries +# to this file, use the arabic 'ي' instead of 'ی' +انان +نداشته +سراسر +خياه +ايشان +وي +تاكنون +بيشتري +دوم +پس +ناشي +وگو +يا +داشتند +سپس +هنگام +هرگز +پنج +نشان +امسال +ديگر +گروهي +شدند +چطور +ده +و +دو +نخستين +ولي +چرا +چه +وسط +ه +كدام +قابل +يك +رفت +هفت +همچنين +در +هزار +بله +بلي +شايد +اما +شناسي +گرفته +دهد +داشته +دانست +داشتن +خواهيم +ميليارد +وقتيكه +امد +خواهد +جز +اورده +شده +بلكه +خدمات +شدن +برخي +نبود +بسياري +جلوگيري +حق +كردند +نوعي +بعري +نكرده +نظير +نبايد +بوده +بودن +داد +اورد +هست +جايي +شود +دنبال +داده +بايد +سابق +هيچ +همان +انجا +كمتر +كجاست +گردد +كسي +تر +مردم +تان +دادن +بودند +سري +جدا +ندارند +مگر +يكديگر +دارد +دهند +بنابراين +هنگامي +سمت +جا +انچه +خود +دادند +زياد +دارند +اثر +بدون +بهترين +بيشتر +البته +به +براساس +بيرون +كرد +بعضي +گرفت +توي +اي +ميليون +او +جريان +تول +بر +مانند +برابر +باشيم +مدتي +گويند +اكنون +تا +تنها +جديد +چند +بي +نشده +كردن +كردم +گويد +كرده +كنيم +نمي +نزد +روي +قصد +فقط +بالاي +ديگران +اين +ديروز +توسط +سوم +ايم +دانند +سوي +استفاده +شما +كنار +داريم +ساخته +طور +امده +رفته +نخست +بيست +نزديك +طي +كنيد +از +انها +تمامي +داشت +يكي +طريق +اش +چيست +روب +نمايد +گفت +چندين +چيزي +تواند +ام +ايا +با +ان +ايد +ترين +اينكه +ديگري +راه +هايي +بروز +همچنان +پاعين +كس +حدود +مختلف +مقابل +چيز +گيرد +ندارد +ضد +همچون +سازي +شان +مورد +باره +مرسي +خويش +برخوردار +چون +خارج +شش +هنوز +تحت +ضمن +هستيم +گفته +فكر +بسيار +پيش +براي +روزهاي +انكه +نخواهد +بالا +كل +وقتي +كي +چنين +كه +گيري +نيست +است +كجا +كند +نيز +يابد +بندي +حتي +توانند +عقب +خواست +كنند +بين +تمام +همه +ما +باشند +مثل +شد +اري +باشد +اره +طبق +بعد +اگر +صورت +غير +جاي +بيش +ريزي +اند +زيرا +چگونه +بار +لطفا +مي +درباره +من +ديده +همين +گذاري +برداري +علت +گذاشته +هم +فوق +نه +ها +شوند +اباد +همواره +هر +اول +خواهند +چهار +نام +امروز +مان +هاي +قبل +كنم +سعي +تازه +را +هستند +زير +جلوي +عنوان +بود diff --git a/isuifang_solr/solr/conf/lang/stopwords_fi.txt b/isuifang_solr/solr/conf/lang/stopwords_fi.txt new file mode 100644 index 0000000..addad79 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_fi.txt @@ -0,0 +1,95 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + +| forms of BE + +olla +olen +olet +on +olemme +olette +ovat +ole | negative form + +oli +olisi +olisit +olisin +olisimme +olisitte +olisivat +olit +olin +olimme +olitte +olivat +ollut +olleet + +en | negation +et +ei +emme +ette +eivät + +|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans +minä minun minut minua minussa minusta minuun minulla minulta minulle | I +sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you +hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she +me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we +te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you +he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they + +tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this +tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that +se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it +nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these +nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those +ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they + +kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who +ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl) +mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what +mitkä | (pl) + +joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which +jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl) + +| conjunctions + +että | that +ja | and +jos | if +koska | because +kuin | than +mutta | but +niin | so +sekä | and +sillä | for +tai | or +vaan | but +vai | or +vaikka | although + + +| prepositions + +kanssa | with +mukaan | according to +noin | about +poikki | across +yli | over, across + +| other + +kun | when +niin | so +nyt | now +itse | self + diff --git a/isuifang_solr/solr/conf/lang/stopwords_fr.txt b/isuifang_solr/solr/conf/lang/stopwords_fr.txt new file mode 100644 index 0000000..c00837e --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_fr.txt @@ -0,0 +1,183 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A French stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + +au | a + le +aux | a + les +avec | with +ce | this +ces | these +dans | with +de | of +des | de + les +du | de + le +elle | she +en | `of them' etc +et | and +eux | them +il | he +je | I +la | the +le | the +leur | their +lui | him +ma | my (fem) +mais | but +me | me +même | same; as in moi-même (myself) etc +mes | me (pl) +moi | me +mon | my (masc) +ne | not +nos | our (pl) +notre | our +nous | we +on | one +ou | where +par | by +pas | not +pour | for +qu | que before vowel +que | that +qui | who +sa | his, her (fem) +se | oneself +ses | his (pl) +son | his, her (masc) +sur | on +ta | thy (fem) +te | thee +tes | thy (pl) +toi | thee +ton | thy (masc) +tu | thou +un | a +une | a +vos | your (pl) +votre | your +vous | you + + | single letter forms + +c | c' +d | d' +j | j' +l | l' +à | to, at +m | m' +n | n' +s | s' +t | t' +y | there + + | forms of être (not including the infinitive): +été +étée +étées +étés +étant +suis +es +est +sommes +êtes +sont +serai +seras +sera +serons +serez +seront +serais +serait +serions +seriez +seraient +étais +était +étions +étiez +étaient +fus +fut +fûmes +fûtes +furent +sois +soit +soyons +soyez +soient +fusse +fusses +fût +fussions +fussiez +fussent + + | forms of avoir (not including the infinitive): +ayant +eu +eue +eues +eus +ai +as +avons +avez +ont +aurai +auras +aura +aurons +aurez +auront +aurais +aurait +aurions +auriez +auraient +avais +avait +avions +aviez +avaient +eut +eûmes +eûtes +eurent +aie +aies +ait +ayons +ayez +aient +eusse +eusses +eût +eussions +eussiez +eussent + + | Later additions (from Jean-Christophe Deschamps) +ceci | this +celà | that +cet | this +cette | this +ici | here +ils | they +les | the (pl) +leurs | their (pl) +quel | which +quels | which +quelle | which +quelles | which +sans | without +soi | oneself + diff --git a/isuifang_solr/solr/conf/lang/stopwords_ga.txt b/isuifang_solr/solr/conf/lang/stopwords_ga.txt new file mode 100644 index 0000000..9ff88d7 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ga.txt @@ -0,0 +1,110 @@ + +a +ach +ag +agus +an +aon +ar +arna +as +b' +ba +beirt +bhúr +caoga +ceathair +ceathrar +chomh +chtó +chuig +chun +cois +céad +cúig +cúigear +d' +daichead +dar +de +deich +deichniúr +den +dhá +do +don +dtí +dá +dár +dó +faoi +faoin +faoina +faoinár +fara +fiche +gach +gan +go +gur +haon +hocht +i +iad +idir +in +ina +ins +inár +is +le +leis +lena +lenár +m' +mar +mo +mé +na +nach +naoi +naonúr +ná +ní +níor +nó +nócha +ocht +ochtar +os +roimh +sa +seacht +seachtar +seachtó +seasca +seisear +siad +sibh +sinn +sna +sé +sí +tar +thar +thú +triúr +trí +trína +trínár +tríocha +tú +um +ár +é +éis +í +ó +ón +óna +ónár diff --git a/isuifang_solr/solr/conf/lang/stopwords_gl.txt b/isuifang_solr/solr/conf/lang/stopwords_gl.txt new file mode 100644 index 0000000..d8760b1 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_gl.txt @@ -0,0 +1,161 @@ +# galican stopwords +a +aínda +alí +aquel +aquela +aquelas +aqueles +aquilo +aquí +ao +aos +as +así +á +ben +cando +che +co +coa +comigo +con +connosco +contigo +convosco +coas +cos +cun +cuns +cunha +cunhas +da +dalgunha +dalgunhas +dalgún +dalgúns +das +de +del +dela +delas +deles +desde +deste +do +dos +dun +duns +dunha +dunhas +e +el +ela +elas +eles +en +era +eran +esa +esas +ese +eses +esta +estar +estaba +está +están +este +estes +estiven +estou +eu +é +facer +foi +foron +fun +había +hai +iso +isto +la +las +lle +lles +lo +los +mais +me +meu +meus +min +miña +miñas +moi +na +nas +neste +nin +no +non +nos +nosa +nosas +noso +nosos +nós +nun +nunha +nuns +nunhas +o +os +ou +ó +ós +para +pero +pode +pois +pola +polas +polo +polos +por +que +se +senón +ser +seu +seus +sexa +sido +sobre +súa +súas +tamén +tan +te +ten +teñen +teño +ter +teu +teus +ti +tido +tiña +tiven +túa +túas +un +unha +unhas +uns +vos +vosa +vosas +voso +vosos +vós diff --git a/isuifang_solr/solr/conf/lang/stopwords_hi.txt b/isuifang_solr/solr/conf/lang/stopwords_hi.txt new file mode 100644 index 0000000..86286bb --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_hi.txt @@ -0,0 +1,235 @@ +# Also see http://www.opensource.org/licenses/bsd-license.html +# See http://members.unine.ch/jacques.savoy/clef/index.html. +# This file was created by Jacques Savoy and is distributed under the BSD license. +# Note: by default this file also contains forms normalized by HindiNormalizer +# for spelling variation (see section below), such that it can be used whether or +# not you enable that feature. When adding additional entries to this list, +# please add the normalized form as well. +अंदर +अत +अपना +अपनी +अपने +अभी +आदि +आप +इत्यादि +इन +इनका +इन्हीं +इन्हें +इन्हों +इस +इसका +इसकी +इसके +इसमें +इसी +इसे +उन +उनका +उनकी +उनके +उनको +उन्हीं +उन्हें +उन्हों +उस +उसके +उसी +उसे +एक +एवं +एस +ऐसे +और +कई +कर +करता +करते +करना +करने +करें +कहते +कहा +का +काफ़ी +कि +कितना +किन्हें +किन्हों +किया +किर +किस +किसी +किसे +की +कुछ +कुल +के +को +कोई +कौन +कौनसा +गया +घर +जब +जहाँ +जा +जितना +जिन +जिन्हें +जिन्हों +जिस +जिसे +जीधर +जैसा +जैसे +जो +तक +तब +तरह +तिन +तिन्हें +तिन्हों +तिस +तिसे +तो +था +थी +थे +दबारा +दिया +दुसरा +दूसरे +दो +द्वारा +न +नहीं +ना +निहायत +नीचे +ने +पर +पर +पहले +पूरा +पे +फिर +बनी +बही +बहुत +बाद +बाला +बिलकुल +भी +भीतर +मगर +मानो +मे +में +यदि +यह +यहाँ +यही +या +यिह +ये +रखें +रहा +रहे +ऱ्वासा +लिए +लिये +लेकिन +व +वर्ग +वह +वह +वहाँ +वहीं +वाले +वुह +वे +वग़ैरह +संग +सकता +सकते +सबसे +सभी +साथ +साबुत +साभ +सारा +से +सो +ही +हुआ +हुई +हुए +है +हैं +हो +होता +होती +होते +होना +होने +# additional normalized forms of the above +अपनि +जेसे +होति +सभि +तिंहों +इंहों +दवारा +इसि +किंहें +थि +उंहों +ओर +जिंहें +वहिं +अभि +बनि +हि +उंहिं +उंहें +हें +वगेरह +एसे +रवासा +कोन +निचे +काफि +उसि +पुरा +भितर +हे +बहि +वहां +कोइ +यहां +जिंहों +तिंहें +किसि +कइ +यहि +इंहिं +जिधर +इंहें +अदि +इतयादि +हुइ +कोनसा +इसकि +दुसरे +जहां +अप +किंहों +उनकि +भि +वरग +हुअ +जेसा +नहिं diff --git a/isuifang_solr/solr/conf/lang/stopwords_hu.txt b/isuifang_solr/solr/conf/lang/stopwords_hu.txt new file mode 100644 index 0000000..1a96f1d --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_hu.txt @@ -0,0 +1,209 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + +| Hungarian stop word list +| prepared by Anna Tordai + +a +ahogy +ahol +aki +akik +akkor +alatt +által +általában +amely +amelyek +amelyekben +amelyeket +amelyet +amelynek +ami +amit +amolyan +amíg +amikor +át +abban +ahhoz +annak +arra +arról +az +azok +azon +azt +azzal +azért +aztán +azután +azonban +bár +be +belül +benne +cikk +cikkek +cikkeket +csak +de +e +eddig +egész +egy +egyes +egyetlen +egyéb +egyik +egyre +ekkor +el +elég +ellen +elő +először +előtt +első +én +éppen +ebben +ehhez +emilyen +ennek +erre +ez +ezt +ezek +ezen +ezzel +ezért +és +fel +felé +hanem +hiszen +hogy +hogyan +igen +így +illetve +ill. +ill +ilyen +ilyenkor +ison +ismét +itt +jó +jól +jobban +kell +kellett +keresztül +keressünk +ki +kívül +között +közül +legalább +lehet +lehetett +legyen +lenne +lenni +lesz +lett +maga +magát +majd +majd +már +más +másik +meg +még +mellett +mert +mely +melyek +mi +mit +míg +miért +milyen +mikor +minden +mindent +mindenki +mindig +mint +mintha +mivel +most +nagy +nagyobb +nagyon +ne +néha +nekem +neki +nem +néhány +nélkül +nincs +olyan +ott +össze +ő +ők +őket +pedig +persze +rá +s +saját +sem +semmi +sok +sokat +sokkal +számára +szemben +szerint +szinte +talán +tehát +teljes +tovább +továbbá +több +úgy +ugyanis +új +újabb +újra +után +utána +utolsó +vagy +vagyis +valaki +valami +valamint +való +vagyok +van +vannak +volt +voltam +voltak +voltunk +vissza +vele +viszont +volna diff --git a/isuifang_solr/solr/conf/lang/stopwords_hy.txt b/isuifang_solr/solr/conf/lang/stopwords_hy.txt new file mode 100644 index 0000000..60c1c50 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_hy.txt @@ -0,0 +1,46 @@ +# example set of Armenian stopwords. +այդ +այլ +այն +այս +դու +դուք +եմ +են +ենք +ես +եք +է +էի +էին +էինք +էիր +էիք +էր +ըստ +թ +ի +ին +իսկ +իր +կամ +համար +հետ +հետո +մենք +մեջ +մի +ն +նա +նաև +նրա +նրանք +որ +որը +որոնք +որպես +ու +ում +պիտի +վրա +և diff --git a/isuifang_solr/solr/conf/lang/stopwords_id.txt b/isuifang_solr/solr/conf/lang/stopwords_id.txt new file mode 100644 index 0000000..4617f83 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_id.txt @@ -0,0 +1,359 @@ +# from appendix D of: A Study of Stemming Effects on Information +# Retrieval in Bahasa Indonesia +ada +adanya +adalah +adapun +agak +agaknya +agar +akan +akankah +akhirnya +aku +akulah +amat +amatlah +anda +andalah +antar +diantaranya +antara +antaranya +diantara +apa +apaan +mengapa +apabila +apakah +apalagi +apatah +atau +ataukah +ataupun +bagai +bagaikan +sebagai +sebagainya +bagaimana +bagaimanapun +sebagaimana +bagaimanakah +bagi +bahkan +bahwa +bahwasanya +sebaliknya +banyak +sebanyak +beberapa +seberapa +begini +beginian +beginikah +beginilah +sebegini +begitu +begitukah +begitulah +begitupun +sebegitu +belum +belumlah +sebelum +sebelumnya +sebenarnya +berapa +berapakah +berapalah +berapapun +betulkah +sebetulnya +biasa +biasanya +bila +bilakah +bisa +bisakah +sebisanya +boleh +bolehkah +bolehlah +buat +bukan +bukankah +bukanlah +bukannya +cuma +percuma +dahulu +dalam +dan +dapat +dari +daripada +dekat +demi +demikian +demikianlah +sedemikian +dengan +depan +di +dia +dialah +dini +diri +dirinya +terdiri +dong +dulu +enggak +enggaknya +entah +entahlah +terhadap +terhadapnya +hal +hampir +hanya +hanyalah +harus +haruslah +harusnya +seharusnya +hendak +hendaklah +hendaknya +hingga +sehingga +ia +ialah +ibarat +ingin +inginkah +inginkan +ini +inikah +inilah +itu +itukah +itulah +jangan +jangankan +janganlah +jika +jikalau +juga +justru +kala +kalau +kalaulah +kalaupun +kalian +kami +kamilah +kamu +kamulah +kan +kapan +kapankah +kapanpun +dikarenakan +karena +karenanya +ke +kecil +kemudian +kenapa +kepada +kepadanya +ketika +seketika +khususnya +kini +kinilah +kiranya +sekiranya +kita +kitalah +kok +lagi +lagian +selagi +lah +lain +lainnya +melainkan +selaku +lalu +melalui +terlalu +lama +lamanya +selama +selama +selamanya +lebih +terlebih +bermacam +macam +semacam +maka +makanya +makin +malah +malahan +mampu +mampukah +mana +manakala +manalagi +masih +masihkah +semasih +masing +mau +maupun +semaunya +memang +mereka +merekalah +meski +meskipun +semula +mungkin +mungkinkah +nah +namun +nanti +nantinya +nyaris +oleh +olehnya +seorang +seseorang +pada +padanya +padahal +paling +sepanjang +pantas +sepantasnya +sepantasnyalah +para +pasti +pastilah +per +pernah +pula +pun +merupakan +rupanya +serupa +saat +saatnya +sesaat +saja +sajalah +saling +bersama +sama +sesama +sambil +sampai +sana +sangat +sangatlah +saya +sayalah +se +sebab +sebabnya +sebuah +tersebut +tersebutlah +sedang +sedangkan +sedikit +sedikitnya +segala +segalanya +segera +sesegera +sejak +sejenak +sekali +sekalian +sekalipun +sesekali +sekaligus +sekarang +sekarang +sekitar +sekitarnya +sela +selain +selalu +seluruh +seluruhnya +semakin +sementara +sempat +semua +semuanya +sendiri +sendirinya +seolah +seperti +sepertinya +sering +seringnya +serta +siapa +siapakah +siapapun +disini +disinilah +sini +sinilah +sesuatu +sesuatunya +suatu +sesudah +sesudahnya +sudah +sudahkah +sudahlah +supaya +tadi +tadinya +tak +tanpa +setelah +telah +tentang +tentu +tentulah +tentunya +tertentu +seterusnya +tapi +tetapi +setiap +tiap +setidaknya +tidak +tidakkah +tidaklah +toh +waduh +wah +wahai +sewaktu +walau +walaupun +wong +yaitu +yakni +yang diff --git a/isuifang_solr/solr/conf/lang/stopwords_it.txt b/isuifang_solr/solr/conf/lang/stopwords_it.txt new file mode 100644 index 0000000..4cb5b08 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_it.txt @@ -0,0 +1,301 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | An Italian stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + +ad | a (to) before vowel +al | a + il +allo | a + lo +ai | a + i +agli | a + gli +all | a + l' +agl | a + gl' +alla | a + la +alle | a + le +con | with +col | con + il +coi | con + i (forms collo, cogli etc are now very rare) +da | from +dal | da + il +dallo | da + lo +dai | da + i +dagli | da + gli +dall | da + l' +dagl | da + gll' +dalla | da + la +dalle | da + le +di | of +del | di + il +dello | di + lo +dei | di + i +degli | di + gli +dell | di + l' +degl | di + gl' +della | di + la +delle | di + le +in | in +nel | in + el +nello | in + lo +nei | in + i +negli | in + gli +nell | in + l' +negl | in + gl' +nella | in + la +nelle | in + le +su | on +sul | su + il +sullo | su + lo +sui | su + i +sugli | su + gli +sull | su + l' +sugl | su + gl' +sulla | su + la +sulle | su + le +per | through, by +tra | among +contro | against +io | I +tu | thou +lui | he +lei | she +noi | we +voi | you +loro | they +mio | my +mia | +miei | +mie | +tuo | +tua | +tuoi | thy +tue | +suo | +sua | +suoi | his, her +sue | +nostro | our +nostra | +nostri | +nostre | +vostro | your +vostra | +vostri | +vostre | +mi | me +ti | thee +ci | us, there +vi | you, there +lo | him, the +la | her, the +li | them +le | them, the +gli | to him, the +ne | from there etc +il | the +un | a +uno | a +una | a +ma | but +ed | and +se | if +perché | why, because +anche | also +come | how +dov | where (as dov') +dove | where +che | who, that +chi | who +cui | whom +non | not +più | more +quale | who, that +quanto | how much +quanti | +quanta | +quante | +quello | that +quelli | +quella | +quelle | +questo | this +questi | +questa | +queste | +si | yes +tutto | all +tutti | all + + | single letter forms: + +a | at +c | as c' for ce or ci +e | and +i | the +l | as l' +o | or + + | forms of avere, to have (not including the infinitive): + +ho +hai +ha +abbiamo +avete +hanno +abbia +abbiate +abbiano +avrò +avrai +avrà +avremo +avrete +avranno +avrei +avresti +avrebbe +avremmo +avreste +avrebbero +avevo +avevi +aveva +avevamo +avevate +avevano +ebbi +avesti +ebbe +avemmo +aveste +ebbero +avessi +avesse +avessimo +avessero +avendo +avuto +avuta +avuti +avute + + | forms of essere, to be (not including the infinitive): +sono +sei +è +siamo +siete +sia +siate +siano +sarò +sarai +sarà +saremo +sarete +saranno +sarei +saresti +sarebbe +saremmo +sareste +sarebbero +ero +eri +era +eravamo +eravate +erano +fui +fosti +fu +fummo +foste +furono +fossi +fosse +fossimo +fossero +essendo + + | forms of fare, to do (not including the infinitive, fa, fat-): +faccio +fai +facciamo +fanno +faccia +facciate +facciano +farò +farai +farà +faremo +farete +faranno +farei +faresti +farebbe +faremmo +fareste +farebbero +facevo +facevi +faceva +facevamo +facevate +facevano +feci +facesti +fece +facemmo +faceste +fecero +facessi +facesse +facessimo +facessero +facendo + + | forms of stare, to be (not including the infinitive): +sto +stai +sta +stiamo +stanno +stia +stiate +stiano +starò +starai +starà +staremo +starete +staranno +starei +staresti +starebbe +staremmo +stareste +starebbero +stavo +stavi +stava +stavamo +stavate +stavano +stetti +stesti +stette +stemmo +steste +stettero +stessi +stesse +stessimo +stessero +stando diff --git a/isuifang_solr/solr/conf/lang/stopwords_ja.txt b/isuifang_solr/solr/conf/lang/stopwords_ja.txt new file mode 100644 index 0000000..d4321be --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ja.txt @@ -0,0 +1,127 @@ +# +# This file defines a stopword set for Japanese. +# +# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia. +# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745 +# for frequency lists, etc. that can be useful for making your own set (if desired) +# +# Note that there is an overlap between these stopwords and the terms stopped when used +# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note +# that comments are not allowed on the same line as stopwords. +# +# Also note that stopping is done in a case-insensitive manner. Change your StopFilter +# configuration if you need case-sensitive stopping. Lastly, note that stopping is done +# using the same character width as the entries in this file. Since this StopFilter is +# normally done after a CJKWidthFilter in your chain, you would usually want your romaji +# entries to be in half-width and your kana entries to be in full-width. +# +の +に +は +を +た +が +で +て +と +し +れ +さ +ある +いる +も +する +から +な +こと +として +い +や +れる +など +なっ +ない +この +ため +その +あっ +よう +また +もの +という +あり +まで +られ +なる +へ +か +だ +これ +によって +により +おり +より +による +ず +なり +られる +において +ば +なかっ +なく +しかし +について +せ +だっ +その後 +できる +それ +う +ので +なお +のみ +でき +き +つ +における +および +いう +さらに +でも +ら +たり +その他 +に関する +たち +ます +ん +なら +に対して +特に +せる +及び +これら +とき +では +にて +ほか +ながら +うち +そして +とともに +ただし +かつて +それぞれ +または +お +ほど +ものの +に対する +ほとんど +と共に +といった +です +とも +ところ +ここ +##### End of file diff --git a/isuifang_solr/solr/conf/lang/stopwords_lv.txt b/isuifang_solr/solr/conf/lang/stopwords_lv.txt new file mode 100644 index 0000000..e21a23c --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_lv.txt @@ -0,0 +1,172 @@ +# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins +# the original list of over 800 forms was refined: +# pronouns, adverbs, interjections were removed +# +# prepositions +aiz +ap +ar +apakš +ārpus +augšpus +bez +caur +dēļ +gar +iekš +iz +kopš +labad +lejpus +līdz +no +otrpus +pa +par +pār +pēc +pie +pirms +pret +priekš +starp +šaipus +uz +viņpus +virs +virspus +zem +apakšpus +# Conjunctions +un +bet +jo +ja +ka +lai +tomēr +tikko +turpretī +arī +kaut +gan +tādēļ +tā +ne +tikvien +vien +kā +ir +te +vai +kamēr +# Particles +ar +diezin +droši +diemžēl +nebūt +ik +it +taču +nu +pat +tiklab +iekšpus +nedz +tik +nevis +turpretim +jeb +iekam +iekām +iekāms +kolīdz +līdzko +tiklīdz +jebšu +tālab +tāpēc +nekā +itin +jā +jau +jel +nē +nezin +tad +tikai +vis +tak +iekams +vien +# modal verbs +būt +biju +biji +bija +bijām +bijāt +esmu +esi +esam +esat +būšu +būsi +būs +būsim +būsiet +tikt +tiku +tiki +tika +tikām +tikāt +tieku +tiec +tiek +tiekam +tiekat +tikšu +tiks +tiksim +tiksiet +tapt +tapi +tapāt +topat +tapšu +tapsi +taps +tapsim +tapsiet +kļūt +kļuvu +kļuvi +kļuva +kļuvām +kļuvāt +kļūstu +kļūsti +kļūst +kļūstam +kļūstat +kļūšu +kļūsi +kļūs +kļūsim +kļūsiet +# verbs +varēt +varēju +varējām +varēšu +varēsim +var +varēji +varējāt +varēsi +varēsiet +varat +varēja +varēs diff --git a/isuifang_solr/solr/conf/lang/stopwords_nl.txt b/isuifang_solr/solr/conf/lang/stopwords_nl.txt new file mode 100644 index 0000000..f4d61f5 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_nl.txt @@ -0,0 +1,117 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Dutch stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + | This is a ranked list (commonest to rarest) of stopwords derived from + | a large sample of Dutch text. + + | Dutch stop words frequently exhibit homonym clashes. These are indicated + | clearly below. + +de | the +en | and +van | of, from +ik | I, the ego +te | (1) chez, at etc, (2) to, (3) too +dat | that, which +die | that, those, who, which +in | in, inside +een | a, an, one +hij | he +het | the, it +niet | not, nothing, naught +zijn | (1) to be, being, (2) his, one's, its +is | is +was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river +op | on, upon, at, in, up, used up +aan | on, upon, to (as dative) +met | with, by +als | like, such as, when +voor | (1) before, in front of, (2) furrow +had | had, past tense all persons sing. of 'hebben' (have) +er | there +maar | but, only +om | round, about, for etc +hem | him +dan | then +zou | should/would, past tense all persons sing. of 'zullen' +of | or, whether, if +wat | what, something, anything +mijn | possessive and noun 'mine' +men | people, 'one' +dit | this +zo | so, thus, in this way +door | through by +over | over, across +ze | she, her, they, them +zich | oneself +bij | (1) a bee, (2) by, near, at +ook | also, too +tot | till, until +je | you +mij | me +uit | out of, from +der | Old Dutch form of 'van der' still found in surnames +daar | (1) there, (2) because +haar | (1) her, their, them, (2) hair +naar | (1) unpleasant, unwell etc, (2) towards, (3) as +heb | present first person sing. of 'to have' +hoe | how, why +heeft | present third person sing. of 'to have' +hebben | 'to have' and various parts thereof +deze | this +u | you +want | (1) for, (2) mitten, (3) rigging +nog | yet, still +zal | 'shall', first and third person sing. of verb 'zullen' (will) +me | me +zij | she, they +nu | now +ge | 'thou', still used in Belgium and south Netherlands +geen | none +omdat | because +iets | something, somewhat +worden | to become, grow, get +toch | yet, still +al | all, every, each +waren | (1) 'were' (2) to wander, (3) wares, (3) +veel | much, many +meer | (1) more, (2) lake +doen | to do, to make +toen | then, when +moet | noun 'spot/mote' and present form of 'to must' +ben | (1) am, (2) 'are' in interrogative second person singular of 'to be' +zonder | without +kan | noun 'can' and present form of 'to be able' +hun | their, them +dus | so, consequently +alles | all, everything, anything +onder | under, beneath +ja | yes, of course +eens | once, one day +hier | here +wie | who +werd | imperfect third person sing. of 'become' +altijd | always +doch | yet, but etc +wordt | present third person sing. of 'become' +wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans +kunnen | to be able +ons | us/our +zelf | self +tegen | against, towards, at +na | after, near +reeds | already +wil | (1) present tense of 'want', (2) 'will', noun, (3) fender +kon | could; past tense of 'to be able' +niets | nothing +uw | your +iemand | somebody +geweest | been; past participle of 'be' +andere | other diff --git a/isuifang_solr/solr/conf/lang/stopwords_no.txt b/isuifang_solr/solr/conf/lang/stopwords_no.txt new file mode 100644 index 0000000..e76f36e --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_no.txt @@ -0,0 +1,192 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Norwegian stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + | This stop word list is for the dominant bokmål dialect. Words unique + | to nynorsk are marked *. + + | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005 + +og | and +i | in +jeg | I +det | it/this/that +at | to (w. inf.) +en | a/an +et | a/an +den | it/this/that +til | to +er | is/am/are +som | who/that +på | on +de | they / you(formal) +med | with +han | he +av | of +ikke | not +ikkje | not * +der | there +så | so +var | was/were +meg | me +seg | you +men | but +ett | one +har | have +om | about +vi | we +min | my +mitt | my +ha | have +hadde | had +hun | she +nå | now +over | over +da | when/as +ved | by/know +fra | from +du | you +ut | out +sin | your +dem | them +oss | us +opp | up +man | you/one +kan | can +hans | his +hvor | where +eller | or +hva | what +skal | shall/must +selv | self (reflective) +sjøl | self (reflective) +her | here +alle | all +vil | will +bli | become +ble | became +blei | became * +blitt | have become +kunne | could +inn | in +når | when +være | be +kom | come +noen | some +noe | some +ville | would +dere | you +som | who/which/that +deres | their/theirs +kun | only/just +ja | yes +etter | after +ned | down +skulle | should +denne | this +for | for/because +deg | you +si | hers/his +sine | hers/his +sitt | hers/his +mot | against +å | to +meget | much +hvorfor | why +dette | this +disse | these/those +uten | without +hvordan | how +ingen | none +din | your +ditt | your +blir | become +samme | same +hvilken | which +hvilke | which (plural) +sånn | such a +inni | inside/within +mellom | between +vår | our +hver | each +hvem | who +vors | us/ours +hvis | whose +både | both +bare | only/just +enn | than +fordi | as/because +før | before +mange | many +også | also +slik | just +vært | been +være | to be +båe | both * +begge | both +siden | since +dykk | your * +dykkar | yours * +dei | they * +deira | them * +deires | theirs * +deim | them * +di | your (fem.) * +då | as/when * +eg | I * +ein | a/an * +eit | a/an * +eitt | a/an * +elles | or * +honom | he * +hjå | at * +ho | she * +hoe | she * +henne | her +hennar | her/hers +hennes | hers +hoss | how * +hossen | how * +ikkje | not * +ingi | noone * +inkje | noone * +korleis | how * +korso | how * +kva | what/which * +kvar | where * +kvarhelst | where * +kven | who/whom * +kvi | why * +kvifor | why * +me | we * +medan | while * +mi | my * +mine | my * +mykje | much * +no | now * +nokon | some (masc./neut.) * +noka | some (fem.) * +nokor | some * +noko | some * +nokre | some * +si | his/hers * +sia | since * +sidan | since * +so | so * +somt | some * +somme | some * +um | about* +upp | up * +vere | be * +vore | was * +verte | become * +vort | become * +varte | became * +vart | became * + diff --git a/isuifang_solr/solr/conf/lang/stopwords_pt.txt b/isuifang_solr/solr/conf/lang/stopwords_pt.txt new file mode 100644 index 0000000..276c1b4 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_pt.txt @@ -0,0 +1,251 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Portuguese stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + + | The following is a ranked list (commonest to rarest) of stopwords + | deriving from a large sample of text. + + | Extra words have been added at the end. + +de | of, from +a | the; to, at; her +o | the; him +que | who, that +e | and +do | de + o +da | de + a +em | in +um | a +para | for + | é from SER +com | with +não | not, no +uma | a +os | the; them +no | em + o +se | himself etc +na | em + a +por | for +mais | more +as | the; them +dos | de + os +como | as, like +mas | but + | foi from SER +ao | a + o +ele | he +das | de + as + | tem from TER +à | a + a +seu | his +sua | her +ou | or + | ser from SER +quando | when +muito | much + | há from HAV +nos | em + os; us +já | already, now + | está from EST +eu | I +também | also +só | only, just +pelo | per + o +pela | per + a +até | up to +isso | that +ela | he +entre | between + | era from SER +depois | after +sem | without +mesmo | same +aos | a + os + | ter from TER +seus | his +quem | whom +nas | em + as +me | me +esse | that +eles | they + | estão from EST +você | you + | tinha from TER + | foram from SER +essa | that +num | em + um +nem | nor +suas | her +meu | my +às | a + as +minha | my + | têm from TER +numa | em + uma +pelos | per + os +elas | they + | havia from HAV + | seja from SER +qual | which + | será from SER +nós | we + | tenho from TER +lhe | to him, her +deles | of them +essas | those +esses | those +pelas | per + as +este | this + | fosse from SER +dele | of him + + | other words. There are many contractions such as naquele = em+aquele, + | mo = me+o, but they are rare. + | Indefinite article plural forms are also rare. + +tu | thou +te | thee +vocês | you (plural) +vos | you +lhes | to them +meus | my +minhas +teu | thy +tua +teus +tuas +nosso | our +nossa +nossos +nossas + +dela | of her +delas | of them + +esta | this +estes | these +estas | these +aquele | that +aquela | that +aqueles | those +aquelas | those +isto | this +aquilo | that + + | forms of estar, to be (not including the infinitive): +estou +está +estamos +estão +estive +esteve +estivemos +estiveram +estava +estávamos +estavam +estivera +estivéramos +esteja +estejamos +estejam +estivesse +estivéssemos +estivessem +estiver +estivermos +estiverem + + | forms of haver, to have (not including the infinitive): +hei +há +havemos +hão +houve +houvemos +houveram +houvera +houvéramos +haja +hajamos +hajam +houvesse +houvéssemos +houvessem +houver +houvermos +houverem +houverei +houverá +houveremos +houverão +houveria +houveríamos +houveriam + + | forms of ser, to be (not including the infinitive): +sou +somos +são +era +éramos +eram +fui +foi +fomos +foram +fora +fôramos +seja +sejamos +sejam +fosse +fôssemos +fossem +for +formos +forem +serei +será +seremos +serão +seria +seríamos +seriam + + | forms of ter, to have (not including the infinitive): +tenho +tem +temos +tém +tinha +tínhamos +tinham +tive +teve +tivemos +tiveram +tivera +tivéramos +tenha +tenhamos +tenham +tivesse +tivéssemos +tivessem +tiver +tivermos +tiverem +terei +terá +teremos +terão +teria +teríamos +teriam diff --git a/isuifang_solr/solr/conf/lang/stopwords_ro.txt b/isuifang_solr/solr/conf/lang/stopwords_ro.txt new file mode 100644 index 0000000..4fdee90 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ro.txt @@ -0,0 +1,233 @@ +# This file was created by Jacques Savoy and is distributed under the BSD license. +# See http://members.unine.ch/jacques.savoy/clef/index.html. +# Also see http://www.opensource.org/licenses/bsd-license.html +acea +aceasta +această +aceea +acei +aceia +acel +acela +acele +acelea +acest +acesta +aceste +acestea +aceşti +aceştia +acolo +acum +ai +aia +aibă +aici +al +ăla +ale +alea +ălea +altceva +altcineva +am +ar +are +aş +aşadar +asemenea +asta +ăsta +astăzi +astea +ăstea +ăştia +asupra +aţi +au +avea +avem +aveţi +azi +bine +bucur +bună +ca +că +căci +când +care +cărei +căror +cărui +cât +câte +câţi +către +câtva +ce +cel +ceva +chiar +cînd +cine +cineva +cît +cîte +cîţi +cîtva +contra +cu +cum +cumva +curând +curînd +da +dă +dacă +dar +datorită +de +deci +deja +deoarece +departe +deşi +din +dinaintea +dintr +dintre +drept +după +ea +ei +el +ele +eram +este +eşti +eu +face +fără +fi +fie +fiecare +fii +fim +fiţi +iar +ieri +îi +îl +îmi +împotriva +în +înainte +înaintea +încât +încît +încotro +între +întrucât +întrucît +îţi +la +lângă +le +li +lîngă +lor +lui +mă +mâine +mea +mei +mele +mereu +meu +mi +mine +mult +multă +mulţi +ne +nicăieri +nici +nimeni +nişte +noastră +noastre +noi +noştri +nostru +nu +ori +oricând +oricare +oricât +orice +oricînd +oricine +oricît +oricum +oriunde +până +pe +pentru +peste +pînă +poate +pot +prea +prima +primul +prin +printr +sa +să +săi +sale +sau +său +se +şi +sînt +sîntem +sînteţi +spre +sub +sunt +suntem +sunteţi +ta +tăi +tale +tău +te +ţi +ţie +tine +toată +toate +tot +toţi +totuşi +tu +un +una +unde +undeva +unei +unele +uneori +unor +vă +vi +voastră +voastre +voi +voştri +vostru +vouă +vreo +vreun diff --git a/isuifang_solr/solr/conf/lang/stopwords_ru.txt b/isuifang_solr/solr/conf/lang/stopwords_ru.txt new file mode 100644 index 0000000..6430769 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_ru.txt @@ -0,0 +1,241 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | a russian stop word list. comments begin with vertical bar. each stop + | word is at the start of a line. + + | this is a ranked list (commonest to rarest) of stopwords derived from + | a large text sample. + + | letter `ё' is translated to `е'. + +и | and +в | in/into +во | alternative form +не | not +что | what/that +он | he +на | on/onto +я | i +с | from +со | alternative form +как | how +а | milder form of `no' (but) +то | conjunction and form of `that' +все | all +она | she +так | so, thus +его | him +но | but +да | yes/and +ты | thou +к | towards, by +у | around, chez +же | intensifier particle +вы | you +за | beyond, behind +бы | conditional/subj. particle +по | up to, along +только | only +ее | her +мне | to me +было | it was +вот | here is/are, particle +от | away from +меня | me +еще | still, yet, more +нет | no, there isnt/arent +о | about +из | out of +ему | to him +теперь | now +когда | when +даже | even +ну | so, well +вдруг | suddenly +ли | interrogative particle +если | if +уже | already, but homonym of `narrower' +или | or +ни | neither +быть | to be +был | he was +него | prepositional form of его +до | up to +вас | you accusative +нибудь | indef. suffix preceded by hyphen +опять | again +уж | already, but homonym of `adder' +вам | to you +сказал | he said +ведь | particle `after all' +там | there +потом | then +себя | oneself +ничего | nothing +ей | to her +может | usually with `быть' as `maybe' +они | they +тут | here +где | where +есть | there is/are +надо | got to, must +ней | prepositional form of ей +для | for +мы | we +тебя | thee +их | them, their +чем | than +была | she was +сам | self +чтоб | in order to +без | without +будто | as if +человек | man, person, one +чего | genitive form of `what' +раз | once +тоже | also +себе | to oneself +под | beneath +жизнь | life +будет | will be +ж | short form of intensifer particle `же' +тогда | then +кто | who +этот | this +говорил | was saying +того | genitive form of `that' +потому | for that reason +этого | genitive form of `this' +какой | which +совсем | altogether +ним | prepositional form of `его', `они' +здесь | here +этом | prepositional form of `этот' +один | one +почти | almost +мой | my +тем | instrumental/dative plural of `тот', `то' +чтобы | full form of `in order that' +нее | her (acc.) +кажется | it seems +сейчас | now +были | they were +куда | where to +зачем | why +сказать | to say +всех | all (acc., gen. preposn. plural) +никогда | never +сегодня | today +можно | possible, one can +при | by +наконец | finally +два | two +об | alternative form of `о', about +другой | another +хоть | even +после | after +над | above +больше | more +тот | that one (masc.) +через | across, in +эти | these +нас | us +про | about +всего | in all, only, of all +них | prepositional form of `они' (they) +какая | which, feminine +много | lots +разве | interrogative particle +сказала | she said +три | three +эту | this, acc. fem. sing. +моя | my, feminine +впрочем | moreover, besides +хорошо | good +свою | ones own, acc. fem. sing. +этой | oblique form of `эта', fem. `this' +перед | in front of +иногда | sometimes +лучше | better +чуть | a little +том | preposn. form of `that one' +нельзя | one must not +такой | such a one +им | to them +более | more +всегда | always +конечно | of course +всю | acc. fem. sing of `all' +между | between + + + | b: some paradigms + | + | personal pronouns + | + | я меня мне мной [мною] + | ты тебя тебе тобой [тобою] + | он его ему им [него, нему, ним] + | она ее эи ею [нее, нэи, нею] + | оно его ему им [него, нему, ним] + | + | мы нас нам нами + | вы вас вам вами + | они их им ими [них, ним, ними] + | + | себя себе собой [собою] + | + | demonstrative pronouns: этот (this), тот (that) + | + | этот эта это эти + | этого эты это эти + | этого этой этого этих + | этому этой этому этим + | этим этой этим [этою] этими + | этом этой этом этих + | + | тот та то те + | того ту то те + | того той того тех + | тому той тому тем + | тем той тем [тою] теми + | том той том тех + | + | determinative pronouns + | + | (a) весь (all) + | + | весь вся все все + | всего всю все все + | всего всей всего всех + | всему всей всему всем + | всем всей всем [всею] всеми + | всем всей всем всех + | + | (b) сам (himself etc) + | + | сам сама само сами + | самого саму само самих + | самого самой самого самих + | самому самой самому самим + | самим самой самим [самою] самими + | самом самой самом самих + | + | stems of verbs `to be', `to have', `to do' and modal + | + | быть бы буд быв есть суть + | име + | дел + | мог мож мочь + | уме + | хоч хот + | долж + | можн + | нужн + | нельзя + diff --git a/isuifang_solr/solr/conf/lang/stopwords_sv.txt b/isuifang_solr/solr/conf/lang/stopwords_sv.txt new file mode 100644 index 0000000..22bddfd --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_sv.txt @@ -0,0 +1,131 @@ + | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt + | This file is distributed under the BSD License. + | See http://snowball.tartarus.org/license.php + | Also see http://www.opensource.org/licenses/bsd-license.html + | - Encoding was converted to UTF-8. + | - This notice was added. + + | A Swedish stop word list. Comments begin with vertical bar. Each stop + | word is at the start of a line. + + | This is a ranked list (commonest to rarest) of stopwords derived from + | a large text sample. + + | Swedish stop words occasionally exhibit homonym clashes. For example + | så = so, but also seed. These are indicated clearly below. + +och | and +det | it, this/that +att | to (with infinitive) +i | in, at +en | a +jag | I +hon | she +som | who, that +han | he +på | on +den | it, this/that +med | with +var | where, each +sig | him(self) etc +för | for +så | so (also: seed) +till | to +är | is +men | but +ett | a +om | if; around, about +hade | had +de | they, these/those +av | of +icke | not, no +mig | me +du | you +henne | her +då | then, when +sin | his +nu | now +har | have +inte | inte någon = no one +hans | his +honom | him +skulle | 'sake' +hennes | her +där | there +min | my +man | one (pronoun) +ej | nor +vid | at, by, on (also: vast) +kunde | could +något | some etc +från | from, off +ut | out +när | when +efter | after, behind +upp | up +vi | we +dem | them +vara | be +vad | what +över | over +än | than +dig | you +kan | can +sina | his +här | here +ha | have +mot | towards +alla | all +under | under (also: wonder) +någon | some etc +eller | or (else) +allt | all +mycket | much +sedan | since +ju | why +denna | this/that +själv | myself, yourself etc +detta | this/that +åt | to +utan | without +varit | was +hur | how +ingen | no +mitt | my +ni | you +bli | to be, become +blev | from bli +oss | us +din | thy +dessa | these/those +några | some etc +deras | their +blir | from bli +mina | my +samma | (the) same +vilken | who, that +er | you, your +sådan | such a +vår | our +blivit | from bli +dess | its +inom | within +mellan | between +sådant | such a +varför | why +varje | each +vilka | who, that +ditt | thy +vem | who +vilket | who, that +sitta | his +sådana | such a +vart | each +dina | thy +vars | whose +vårt | our +våra | our +ert | your +era | your +vilkas | whose + diff --git a/isuifang_solr/solr/conf/lang/stopwords_th.txt b/isuifang_solr/solr/conf/lang/stopwords_th.txt new file mode 100644 index 0000000..07f0fab --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_th.txt @@ -0,0 +1,119 @@ +# Thai stopwords from: +# "Opinion Detection in Thai Political News Columns +# Based on Subjectivity Analysis" +# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak +ไว้ +ไม่ +ไป +ได้ +ให้ +ใน +โดย +แห่ง +แล้ว +และ +แรก +แบบ +แต่ +เอง +เห็น +เลย +เริ่ม +เรา +เมื่อ +เพื่อ +เพราะ +เป็นการ +เป็น +เปิดเผย +เปิด +เนื่องจาก +เดียวกัน +เดียว +เช่น +เฉพาะ +เคย +เข้า +เขา +อีก +อาจ +อะไร +ออก +อย่าง +อยู่ +อยาก +หาก +หลาย +หลังจาก +หลัง +หรือ +หนึ่ง +ส่วน +ส่ง +สุด +สําหรับ +ว่า +วัน +ลง +ร่วม +ราย +รับ +ระหว่าง +รวม +ยัง +มี +มาก +มา +พร้อม +พบ +ผ่าน +ผล +บาง +น่า +นี้ +นํา +นั้น +นัก +นอกจาก +ทุก +ที่สุด +ที่ +ทําให้ +ทํา +ทาง +ทั้งนี้ +ทั้ง +ถ้า +ถูก +ถึง +ต้อง +ต่างๆ +ต่าง +ต่อ +ตาม +ตั้งแต่ +ตั้ง +ด้าน +ด้วย +ดัง +ซึ่ง +ช่วง +จึง +จาก +จัด +จะ +คือ +ความ +ครั้ง +คง +ขึ้น +ของ +ขอ +ขณะ +ก่อน +ก็ +การ +กับ +กัน +กว่า +กล่าว diff --git a/isuifang_solr/solr/conf/lang/stopwords_tr.txt b/isuifang_solr/solr/conf/lang/stopwords_tr.txt new file mode 100644 index 0000000..84d9408 --- /dev/null +++ b/isuifang_solr/solr/conf/lang/stopwords_tr.txt @@ -0,0 +1,212 @@ +# Turkish stopwords from LUCENE-559 +# merged with the list from "Information Retrieval on Turkish Texts" +# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf) +acaba +altmış +altı +ama +ancak +arada +aslında +ayrıca +bana +bazı +belki +ben +benden +beni +benim +beri +beş +bile +bin +bir +birçok +biri +birkaç +birkez +birşey +birşeyi +biz +bize +bizden +bizi +bizim +böyle +böylece +bu +buna +bunda +bundan +bunlar +bunları +bunların +bunu +bunun +burada +çok +çünkü +da +daha +dahi +de +defa +değil +diğer +diye +doksan +dokuz +dolayı +dolayısıyla +dört +edecek +eden +ederek +edilecek +ediliyor +edilmesi +ediyor +eğer +elli +en +etmesi +etti +ettiği +ettiğini +gibi +göre +halen +hangi +hatta +hem +henüz +hep +hepsi +her +herhangi +herkesin +hiç +hiçbir +için +iki +ile +ilgili +ise +işte +itibaren +itibariyle +kadar +karşın +katrilyon +kendi +kendilerine +kendini +kendisi +kendisine +kendisini +kez +ki +kim +kimden +kime +kimi +kimse +kırk +milyar +milyon +mu +mü +mı +nasıl +ne +neden +nedenle +nerde +nerede +nereye +niye +niçin +o +olan +olarak +oldu +olduğu +olduğunu +olduklarını +olmadı +olmadığı +olmak +olması +olmayan +olmaz +olsa +olsun +olup +olur +olursa +oluyor +on +ona +ondan +onlar +onlardan +onları +onların +onu +onun +otuz +oysa +öyle +pek +rağmen +sadece +sanki +sekiz +seksen +sen +senden +seni +senin +siz +sizden +sizi +sizin +şey +şeyden +şeyi +şeyler +şöyle +şu +şuna +şunda +şundan +şunları +şunu +tarafından +trilyon +tüm +üç +üzere +var +vardı +ve +veya +ya +yani +yapacak +yapılan +yapılması +yapıyor +yapmak +yaptı +yaptığı +yaptığını +yaptıkları +yedi +yerine +yetmiş +yine +yirmi +yoksa +yüz +zaten diff --git a/isuifang_solr/solr/conf/lang/userdict_ja.txt b/isuifang_solr/solr/conf/lang/userdict_ja.txt new file mode 100644 index 0000000..6f0368e --- /dev/null +++ b/isuifang_solr/solr/conf/lang/userdict_ja.txt @@ -0,0 +1,29 @@ +# +# This is a sample user dictionary for Kuromoji (JapaneseTokenizer) +# +# Add entries to this file in order to override the statistical model in terms +# of segmentation, readings and part-of-speech tags. Notice that entries do +# not have weights since they are always used when found. This is by-design +# in order to maximize ease-of-use. +# +# Entries are defined using the following CSV format: +# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag> +# +# Notice that a single half-width space separates tokens and readings, and +# that the number tokens and readings must match exactly. +# +# Also notice that multiple entries with the same <text> is undefined. +# +# Whitespace only lines are ignored. Comments are not allowed on entry lines. +# + +# Custom segmentation for kanji compounds +日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞 +関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞 + +# Custom segmentation for compound katakana +トートバッグ,トート バッグ,トート バッグ,かずカナ名詞 +ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞 + +# Custom reading for former sumo wrestler +朝青龍,朝青龍,アサショウリュウ,カスタム人名 diff --git a/isuifang_solr/solr/conf/mapping-FoldToASCII.txt b/isuifang_solr/solr/conf/mapping-FoldToASCII.txt new file mode 100644 index 0000000..9a84b6e --- /dev/null +++ b/isuifang_solr/solr/conf/mapping-FoldToASCII.txt @@ -0,0 +1,3813 @@ +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + + +# This map converts alphabetic, numeric, and symbolic Unicode characters +# which are not in the first 127 ASCII characters (the "Basic Latin" Unicode +# block) into their ASCII equivalents, if one exists. +# +# Characters from the following Unicode blocks are converted; however, only +# those characters with reasonable ASCII alternatives are converted: +# +# - C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf +# - Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf +# - Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf +# - Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf +# - Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf +# - Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf +# - IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf +# - Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf +# - Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf +# - General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf +# - Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf +# - Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf +# - Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf +# - Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf +# - Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf +# - Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf +# +# See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode +# +# The set of character conversions supported by this map is a superset of +# those supported by the map represented by mapping-ISOLatin1Accent.txt. +# +# See the bottom of this file for the Perl script used to generate the contents +# of this file (without this header) from ASCIIFoldingFilter.java. + + +# Syntax: +# "source" => "target" +# "source".length() > 0 (source cannot be empty.) +# "target".length() >= 0 (target can be empty.) + + +# À [LATIN CAPITAL LETTER A WITH GRAVE] +"\u00C0" => "A" + +# Á [LATIN CAPITAL LETTER A WITH ACUTE] +"\u00C1" => "A" + +#  [LATIN CAPITAL LETTER A WITH CIRCUMFLEX] +"\u00C2" => "A" + +# à [LATIN CAPITAL LETTER A WITH TILDE] +"\u00C3" => "A" + +# Ä [LATIN CAPITAL LETTER A WITH DIAERESIS] +"\u00C4" => "A" + +# Å [LATIN CAPITAL LETTER A WITH RING ABOVE] +"\u00C5" => "A" + +# Ā [LATIN CAPITAL LETTER A WITH MACRON] +"\u0100" => "A" + +# Ă [LATIN CAPITAL LETTER A WITH BREVE] +"\u0102" => "A" + +# Ą [LATIN CAPITAL LETTER A WITH OGONEK] +"\u0104" => "A" + +# Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA] +"\u018F" => "A" + +# Ǎ [LATIN CAPITAL LETTER A WITH CARON] +"\u01CD" => "A" + +# Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON] +"\u01DE" => "A" + +# Ǡ [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON] +"\u01E0" => "A" + +# Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE] +"\u01FA" => "A" + +# Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE] +"\u0200" => "A" + +# Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE] +"\u0202" => "A" + +# Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE] +"\u0226" => "A" + +# Ⱥ [LATIN CAPITAL LETTER A WITH STROKE] +"\u023A" => "A" + +# ᴀ [LATIN LETTER SMALL CAPITAL A] +"\u1D00" => "A" + +# Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW] +"\u1E00" => "A" + +# Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW] +"\u1EA0" => "A" + +# Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE] +"\u1EA2" => "A" + +# Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE] +"\u1EA4" => "A" + +# Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE] +"\u1EA6" => "A" + +# Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1EA8" => "A" + +# Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE] +"\u1EAA" => "A" + +# Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW] +"\u1EAC" => "A" + +# Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE] +"\u1EAE" => "A" + +# Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE] +"\u1EB0" => "A" + +# Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE] +"\u1EB2" => "A" + +# Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE] +"\u1EB4" => "A" + +# Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW] +"\u1EB6" => "A" + +# Ⓐ [CIRCLED LATIN CAPITAL LETTER A] +"\u24B6" => "A" + +# Ａ [FULLWIDTH LATIN CAPITAL LETTER A] +"\uFF21" => "A" + +# à [LATIN SMALL LETTER A WITH GRAVE] +"\u00E0" => "a" + +# á [LATIN SMALL LETTER A WITH ACUTE] +"\u00E1" => "a" + +# â [LATIN SMALL LETTER A WITH CIRCUMFLEX] +"\u00E2" => "a" + +# ã [LATIN SMALL LETTER A WITH TILDE] +"\u00E3" => "a" + +# ä [LATIN SMALL LETTER A WITH DIAERESIS] +"\u00E4" => "a" + +# å [LATIN SMALL LETTER A WITH RING ABOVE] +"\u00E5" => "a" + +# ā [LATIN SMALL LETTER A WITH MACRON] +"\u0101" => "a" + +# ă [LATIN SMALL LETTER A WITH BREVE] +"\u0103" => "a" + +# ą [LATIN SMALL LETTER A WITH OGONEK] +"\u0105" => "a" + +# ǎ [LATIN SMALL LETTER A WITH CARON] +"\u01CE" => "a" + +# ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON] +"\u01DF" => "a" + +# ǡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON] +"\u01E1" => "a" + +# ǻ [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE] +"\u01FB" => "a" + +# ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE] +"\u0201" => "a" + +# ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE] +"\u0203" => "a" + +# ȧ [LATIN SMALL LETTER A WITH DOT ABOVE] +"\u0227" => "a" + +# ɐ [LATIN SMALL LETTER TURNED A] +"\u0250" => "a" + +# ə [LATIN SMALL LETTER SCHWA] +"\u0259" => "a" + +# ɚ [LATIN SMALL LETTER SCHWA WITH HOOK] +"\u025A" => "a" + +# ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK] +"\u1D8F" => "a" + +# ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK] +"\u1D95" => "a" + +# ạ [LATIN SMALL LETTER A WITH RING BELOW] +"\u1E01" => "a" + +# ả [LATIN SMALL LETTER A WITH RIGHT HALF RING] +"\u1E9A" => "a" + +# ạ [LATIN SMALL LETTER A WITH DOT BELOW] +"\u1EA1" => "a" + +# ả [LATIN SMALL LETTER A WITH HOOK ABOVE] +"\u1EA3" => "a" + +# ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE] +"\u1EA5" => "a" + +# ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE] +"\u1EA7" => "a" + +# ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1EA9" => "a" + +# ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE] +"\u1EAB" => "a" + +# ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW] +"\u1EAD" => "a" + +# ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE] +"\u1EAF" => "a" + +# ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE] +"\u1EB1" => "a" + +# ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE] +"\u1EB3" => "a" + +# ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE] +"\u1EB5" => "a" + +# ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW] +"\u1EB7" => "a" + +# ₐ [LATIN SUBSCRIPT SMALL LETTER A] +"\u2090" => "a" + +# ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA] +"\u2094" => "a" + +# ⓐ [CIRCLED LATIN SMALL LETTER A] +"\u24D0" => "a" + +# ⱥ [LATIN SMALL LETTER A WITH STROKE] +"\u2C65" => "a" + +# Ɐ [LATIN CAPITAL LETTER TURNED A] +"\u2C6F" => "a" + +# ａ [FULLWIDTH LATIN SMALL LETTER A] +"\uFF41" => "a" + +# Ꜳ [LATIN CAPITAL LETTER AA] +"\uA732" => "AA" + +# Æ [LATIN CAPITAL LETTER AE] +"\u00C6" => "AE" + +# Ǣ [LATIN CAPITAL LETTER AE WITH MACRON] +"\u01E2" => "AE" + +# Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE] +"\u01FC" => "AE" + +# ᴁ [LATIN LETTER SMALL CAPITAL AE] +"\u1D01" => "AE" + +# Ꜵ [LATIN CAPITAL LETTER AO] +"\uA734" => "AO" + +# Ꜷ [LATIN CAPITAL LETTER AU] +"\uA736" => "AU" + +# Ꜹ [LATIN CAPITAL LETTER AV] +"\uA738" => "AV" + +# Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR] +"\uA73A" => "AV" + +# Ꜽ [LATIN CAPITAL LETTER AY] +"\uA73C" => "AY" + +# ⒜ [PARENTHESIZED LATIN SMALL LETTER A] +"\u249C" => "(a)" + +# ꜳ [LATIN SMALL LETTER AA] +"\uA733" => "aa" + +# æ [LATIN SMALL LETTER AE] +"\u00E6" => "ae" + +# ǣ [LATIN SMALL LETTER AE WITH MACRON] +"\u01E3" => "ae" + +# ǽ [LATIN SMALL LETTER AE WITH ACUTE] +"\u01FD" => "ae" + +# ᴂ [LATIN SMALL LETTER TURNED AE] +"\u1D02" => "ae" + +# ꜵ [LATIN SMALL LETTER AO] +"\uA735" => "ao" + +# ꜷ [LATIN SMALL LETTER AU] +"\uA737" => "au" + +# ꜹ [LATIN SMALL LETTER AV] +"\uA739" => "av" + +# ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR] +"\uA73B" => "av" + +# ꜽ [LATIN SMALL LETTER AY] +"\uA73D" => "ay" + +# Ɓ [LATIN CAPITAL LETTER B WITH HOOK] +"\u0181" => "B" + +# Ƃ [LATIN CAPITAL LETTER B WITH TOPBAR] +"\u0182" => "B" + +# Ƀ [LATIN CAPITAL LETTER B WITH STROKE] +"\u0243" => "B" + +# ʙ [LATIN LETTER SMALL CAPITAL B] +"\u0299" => "B" + +# ᴃ [LATIN LETTER SMALL CAPITAL BARRED B] +"\u1D03" => "B" + +# Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE] +"\u1E02" => "B" + +# Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW] +"\u1E04" => "B" + +# Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW] +"\u1E06" => "B" + +# Ⓑ [CIRCLED LATIN CAPITAL LETTER B] +"\u24B7" => "B" + +# Ｂ [FULLWIDTH LATIN CAPITAL LETTER B] +"\uFF22" => "B" + +# ƀ [LATIN SMALL LETTER B WITH STROKE] +"\u0180" => "b" + +# ƃ [LATIN SMALL LETTER B WITH TOPBAR] +"\u0183" => "b" + +# ɓ [LATIN SMALL LETTER B WITH HOOK] +"\u0253" => "b" + +# ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE] +"\u1D6C" => "b" + +# ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK] +"\u1D80" => "b" + +# ḃ [LATIN SMALL LETTER B WITH DOT ABOVE] +"\u1E03" => "b" + +# ḅ [LATIN SMALL LETTER B WITH DOT BELOW] +"\u1E05" => "b" + +# ḇ [LATIN SMALL LETTER B WITH LINE BELOW] +"\u1E07" => "b" + +# ⓑ [CIRCLED LATIN SMALL LETTER B] +"\u24D1" => "b" + +# ｂ [FULLWIDTH LATIN SMALL LETTER B] +"\uFF42" => "b" + +# ⒝ [PARENTHESIZED LATIN SMALL LETTER B] +"\u249D" => "(b)" + +# Ç [LATIN CAPITAL LETTER C WITH CEDILLA] +"\u00C7" => "C" + +# Ć [LATIN CAPITAL LETTER C WITH ACUTE] +"\u0106" => "C" + +# Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX] +"\u0108" => "C" + +# Ċ [LATIN CAPITAL LETTER C WITH DOT ABOVE] +"\u010A" => "C" + +# Č [LATIN CAPITAL LETTER C WITH CARON] +"\u010C" => "C" + +# Ƈ [LATIN CAPITAL LETTER C WITH HOOK] +"\u0187" => "C" + +# Ȼ [LATIN CAPITAL LETTER C WITH STROKE] +"\u023B" => "C" + +# ʗ [LATIN LETTER STRETCHED C] +"\u0297" => "C" + +# ᴄ [LATIN LETTER SMALL CAPITAL C] +"\u1D04" => "C" + +# Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE] +"\u1E08" => "C" + +# Ⓒ [CIRCLED LATIN CAPITAL LETTER C] +"\u24B8" => "C" + +# Ｃ [FULLWIDTH LATIN CAPITAL LETTER C] +"\uFF23" => "C" + +# ç [LATIN SMALL LETTER C WITH CEDILLA] +"\u00E7" => "c" + +# ć [LATIN SMALL LETTER C WITH ACUTE] +"\u0107" => "c" + +# ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX] +"\u0109" => "c" + +# ċ [LATIN SMALL LETTER C WITH DOT ABOVE] +"\u010B" => "c" + +# č [LATIN SMALL LETTER C WITH CARON] +"\u010D" => "c" + +# ƈ [LATIN SMALL LETTER C WITH HOOK] +"\u0188" => "c" + +# ȼ [LATIN SMALL LETTER C WITH STROKE] +"\u023C" => "c" + +# ɕ [LATIN SMALL LETTER C WITH CURL] +"\u0255" => "c" + +# ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE] +"\u1E09" => "c" + +# ↄ [LATIN SMALL LETTER REVERSED C] +"\u2184" => "c" + +# ⓒ [CIRCLED LATIN SMALL LETTER C] +"\u24D2" => "c" + +# Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT] +"\uA73E" => "c" + +# ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT] +"\uA73F" => "c" + +# ｃ [FULLWIDTH LATIN SMALL LETTER C] +"\uFF43" => "c" + +# ⒞ [PARENTHESIZED LATIN SMALL LETTER C] +"\u249E" => "(c)" + +# Ð [LATIN CAPITAL LETTER ETH] +"\u00D0" => "D" + +# Ď [LATIN CAPITAL LETTER D WITH CARON] +"\u010E" => "D" + +# Đ [LATIN CAPITAL LETTER D WITH STROKE] +"\u0110" => "D" + +# Ɖ [LATIN CAPITAL LETTER AFRICAN D] +"\u0189" => "D" + +# Ɗ [LATIN CAPITAL LETTER D WITH HOOK] +"\u018A" => "D" + +# Ƌ [LATIN CAPITAL LETTER D WITH TOPBAR] +"\u018B" => "D" + +# ᴅ [LATIN LETTER SMALL CAPITAL D] +"\u1D05" => "D" + +# ᴆ [LATIN LETTER SMALL CAPITAL ETH] +"\u1D06" => "D" + +# Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE] +"\u1E0A" => "D" + +# Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW] +"\u1E0C" => "D" + +# Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW] +"\u1E0E" => "D" + +# Ḑ [LATIN CAPITAL LETTER D WITH CEDILLA] +"\u1E10" => "D" + +# Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW] +"\u1E12" => "D" + +# Ⓓ [CIRCLED LATIN CAPITAL LETTER D] +"\u24B9" => "D" + +# Ꝺ [LATIN CAPITAL LETTER INSULAR D] +"\uA779" => "D" + +# Ｄ [FULLWIDTH LATIN CAPITAL LETTER D] +"\uFF24" => "D" + +# ð [LATIN SMALL LETTER ETH] +"\u00F0" => "d" + +# ď [LATIN SMALL LETTER D WITH CARON] +"\u010F" => "d" + +# đ [LATIN SMALL LETTER D WITH STROKE] +"\u0111" => "d" + +# ƌ [LATIN SMALL LETTER D WITH TOPBAR] +"\u018C" => "d" + +# ȡ [LATIN SMALL LETTER D WITH CURL] +"\u0221" => "d" + +# ɖ [LATIN SMALL LETTER D WITH TAIL] +"\u0256" => "d" + +# ɗ [LATIN SMALL LETTER D WITH HOOK] +"\u0257" => "d" + +# ᵭ [LATIN SMALL LETTER D WITH MIDDLE TILDE] +"\u1D6D" => "d" + +# ᶁ [LATIN SMALL LETTER D WITH PALATAL HOOK] +"\u1D81" => "d" + +# ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL] +"\u1D91" => "d" + +# ḋ [LATIN SMALL LETTER D WITH DOT ABOVE] +"\u1E0B" => "d" + +# ḍ [LATIN SMALL LETTER D WITH DOT BELOW] +"\u1E0D" => "d" + +# ḏ [LATIN SMALL LETTER D WITH LINE BELOW] +"\u1E0F" => "d" + +# ḑ [LATIN SMALL LETTER D WITH CEDILLA] +"\u1E11" => "d" + +# ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW] +"\u1E13" => "d" + +# ⓓ [CIRCLED LATIN SMALL LETTER D] +"\u24D3" => "d" + +# ꝺ [LATIN SMALL LETTER INSULAR D] +"\uA77A" => "d" + +# ｄ [FULLWIDTH LATIN SMALL LETTER D] +"\uFF44" => "d" + +# DŽ [LATIN CAPITAL LETTER DZ WITH CARON] +"\u01C4" => "DZ" + +# DZ [LATIN CAPITAL LETTER DZ] +"\u01F1" => "DZ" + +# Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON] +"\u01C5" => "Dz" + +# Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z] +"\u01F2" => "Dz" + +# ⒟ [PARENTHESIZED LATIN SMALL LETTER D] +"\u249F" => "(d)" + +# ȸ [LATIN SMALL LETTER DB DIGRAPH] +"\u0238" => "db" + +# dž [LATIN SMALL LETTER DZ WITH CARON] +"\u01C6" => "dz" + +# dz [LATIN SMALL LETTER DZ] +"\u01F3" => "dz" + +# ʣ [LATIN SMALL LETTER DZ DIGRAPH] +"\u02A3" => "dz" + +# ʥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL] +"\u02A5" => "dz" + +# È [LATIN CAPITAL LETTER E WITH GRAVE] +"\u00C8" => "E" + +# É [LATIN CAPITAL LETTER E WITH ACUTE] +"\u00C9" => "E" + +# Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX] +"\u00CA" => "E" + +# Ë [LATIN CAPITAL LETTER E WITH DIAERESIS] +"\u00CB" => "E" + +# Ē [LATIN CAPITAL LETTER E WITH MACRON] +"\u0112" => "E" + +# Ĕ [LATIN CAPITAL LETTER E WITH BREVE] +"\u0114" => "E" + +# Ė [LATIN CAPITAL LETTER E WITH DOT ABOVE] +"\u0116" => "E" + +# Ę [LATIN CAPITAL LETTER E WITH OGONEK] +"\u0118" => "E" + +# Ě [LATIN CAPITAL LETTER E WITH CARON] +"\u011A" => "E" + +# Ǝ [LATIN CAPITAL LETTER REVERSED E] +"\u018E" => "E" + +# Ɛ [LATIN CAPITAL LETTER OPEN E] +"\u0190" => "E" + +# Ȅ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE] +"\u0204" => "E" + +# Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE] +"\u0206" => "E" + +# Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA] +"\u0228" => "E" + +# Ɇ [LATIN CAPITAL LETTER E WITH STROKE] +"\u0246" => "E" + +# ᴇ [LATIN LETTER SMALL CAPITAL E] +"\u1D07" => "E" + +# Ḕ [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE] +"\u1E14" => "E" + +# Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE] +"\u1E16" => "E" + +# Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW] +"\u1E18" => "E" + +# Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW] +"\u1E1A" => "E" + +# Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE] +"\u1E1C" => "E" + +# Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW] +"\u1EB8" => "E" + +# Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE] +"\u1EBA" => "E" + +# Ẽ [LATIN CAPITAL LETTER E WITH TILDE] +"\u1EBC" => "E" + +# Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE] +"\u1EBE" => "E" + +# Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE] +"\u1EC0" => "E" + +# Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1EC2" => "E" + +# Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE] +"\u1EC4" => "E" + +# Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW] +"\u1EC6" => "E" + +# Ⓔ [CIRCLED LATIN CAPITAL LETTER E] +"\u24BA" => "E" + +# ⱻ [LATIN LETTER SMALL CAPITAL TURNED E] +"\u2C7B" => "E" + +# Ｅ [FULLWIDTH LATIN CAPITAL LETTER E] +"\uFF25" => "E" + +# è [LATIN SMALL LETTER E WITH GRAVE] +"\u00E8" => "e" + +# é [LATIN SMALL LETTER E WITH ACUTE] +"\u00E9" => "e" + +# ê [LATIN SMALL LETTER E WITH CIRCUMFLEX] +"\u00EA" => "e" + +# ë [LATIN SMALL LETTER E WITH DIAERESIS] +"\u00EB" => "e" + +# ē [LATIN SMALL LETTER E WITH MACRON] +"\u0113" => "e" + +# ĕ [LATIN SMALL LETTER E WITH BREVE] +"\u0115" => "e" + +# ė [LATIN SMALL LETTER E WITH DOT ABOVE] +"\u0117" => "e" + +# ę [LATIN SMALL LETTER E WITH OGONEK] +"\u0119" => "e" + +# ě [LATIN SMALL LETTER E WITH CARON] +"\u011B" => "e" + +# ǝ [LATIN SMALL LETTER TURNED E] +"\u01DD" => "e" + +# ȅ [LATIN SMALL LETTER E WITH DOUBLE GRAVE] +"\u0205" => "e" + +# ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE] +"\u0207" => "e" + +# ȩ [LATIN SMALL LETTER E WITH CEDILLA] +"\u0229" => "e" + +# ɇ [LATIN SMALL LETTER E WITH STROKE] +"\u0247" => "e" + +# ɘ [LATIN SMALL LETTER REVERSED E] +"\u0258" => "e" + +# ɛ [LATIN SMALL LETTER OPEN E] +"\u025B" => "e" + +# ɜ [LATIN SMALL LETTER REVERSED OPEN E] +"\u025C" => "e" + +# ɝ [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK] +"\u025D" => "e" + +# ɞ [LATIN SMALL LETTER CLOSED REVERSED OPEN E] +"\u025E" => "e" + +# ʚ [LATIN SMALL LETTER CLOSED OPEN E] +"\u029A" => "e" + +# ᴈ [LATIN SMALL LETTER TURNED OPEN E] +"\u1D08" => "e" + +# ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK] +"\u1D92" => "e" + +# ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK] +"\u1D93" => "e" + +# ᶔ [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK] +"\u1D94" => "e" + +# ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE] +"\u1E15" => "e" + +# ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE] +"\u1E17" => "e" + +# ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW] +"\u1E19" => "e" + +# ḛ [LATIN SMALL LETTER E WITH TILDE BELOW] +"\u1E1B" => "e" + +# ḝ [LATIN SMALL LETTER E WITH CEDILLA AND BREVE] +"\u1E1D" => "e" + +# ẹ [LATIN SMALL LETTER E WITH DOT BELOW] +"\u1EB9" => "e" + +# ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE] +"\u1EBB" => "e" + +# ẽ [LATIN SMALL LETTER E WITH TILDE] +"\u1EBD" => "e" + +# ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE] +"\u1EBF" => "e" + +# ề [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE] +"\u1EC1" => "e" + +# ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1EC3" => "e" + +# ễ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE] +"\u1EC5" => "e" + +# ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW] +"\u1EC7" => "e" + +# ₑ [LATIN SUBSCRIPT SMALL LETTER E] +"\u2091" => "e" + +# ⓔ [CIRCLED LATIN SMALL LETTER E] +"\u24D4" => "e" + +# ⱸ [LATIN SMALL LETTER E WITH NOTCH] +"\u2C78" => "e" + +# ｅ [FULLWIDTH LATIN SMALL LETTER E] +"\uFF45" => "e" + +# ⒠ [PARENTHESIZED LATIN SMALL LETTER E] +"\u24A0" => "(e)" + +# Ƒ [LATIN CAPITAL LETTER F WITH HOOK] +"\u0191" => "F" + +# Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE] +"\u1E1E" => "F" + +# Ⓕ [CIRCLED LATIN CAPITAL LETTER F] +"\u24BB" => "F" + +# ꜰ [LATIN LETTER SMALL CAPITAL F] +"\uA730" => "F" + +# Ꝼ [LATIN CAPITAL LETTER INSULAR F] +"\uA77B" => "F" + +# ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F] +"\uA7FB" => "F" + +# Ｆ [FULLWIDTH LATIN CAPITAL LETTER F] +"\uFF26" => "F" + +# ƒ [LATIN SMALL LETTER F WITH HOOK] +"\u0192" => "f" + +# ᵮ [LATIN SMALL LETTER F WITH MIDDLE TILDE] +"\u1D6E" => "f" + +# ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK] +"\u1D82" => "f" + +# ḟ [LATIN SMALL LETTER F WITH DOT ABOVE] +"\u1E1F" => "f" + +# ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE] +"\u1E9B" => "f" + +# ⓕ [CIRCLED LATIN SMALL LETTER F] +"\u24D5" => "f" + +# ꝼ [LATIN SMALL LETTER INSULAR F] +"\uA77C" => "f" + +# ｆ [FULLWIDTH LATIN SMALL LETTER F] +"\uFF46" => "f" + +# ⒡ [PARENTHESIZED LATIN SMALL LETTER F] +"\u24A1" => "(f)" + +# ff [LATIN SMALL LIGATURE FF] +"\uFB00" => "ff" + +# ffi [LATIN SMALL LIGATURE FFI] +"\uFB03" => "ffi" + +# ffl [LATIN SMALL LIGATURE FFL] +"\uFB04" => "ffl" + +# fi [LATIN SMALL LIGATURE FI] +"\uFB01" => "fi" + +# fl [LATIN SMALL LIGATURE FL] +"\uFB02" => "fl" + +# Ĝ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX] +"\u011C" => "G" + +# Ğ [LATIN CAPITAL LETTER G WITH BREVE] +"\u011E" => "G" + +# Ġ [LATIN CAPITAL LETTER G WITH DOT ABOVE] +"\u0120" => "G" + +# Ģ [LATIN CAPITAL LETTER G WITH CEDILLA] +"\u0122" => "G" + +# Ɠ [LATIN CAPITAL LETTER G WITH HOOK] +"\u0193" => "G" + +# Ǥ [LATIN CAPITAL LETTER G WITH STROKE] +"\u01E4" => "G" + +# ǥ [LATIN SMALL LETTER G WITH STROKE] +"\u01E5" => "G" + +# Ǧ [LATIN CAPITAL LETTER G WITH CARON] +"\u01E6" => "G" + +# ǧ [LATIN SMALL LETTER G WITH CARON] +"\u01E7" => "G" + +# Ǵ [LATIN CAPITAL LETTER G WITH ACUTE] +"\u01F4" => "G" + +# ɢ [LATIN LETTER SMALL CAPITAL G] +"\u0262" => "G" + +# ʛ [LATIN LETTER SMALL CAPITAL G WITH HOOK] +"\u029B" => "G" + +# Ḡ [LATIN CAPITAL LETTER G WITH MACRON] +"\u1E20" => "G" + +# Ⓖ [CIRCLED LATIN CAPITAL LETTER G] +"\u24BC" => "G" + +# Ᵹ [LATIN CAPITAL LETTER INSULAR G] +"\uA77D" => "G" + +# Ꝿ [LATIN CAPITAL LETTER TURNED INSULAR G] +"\uA77E" => "G" + +# Ｇ [FULLWIDTH LATIN CAPITAL LETTER G] +"\uFF27" => "G" + +# ĝ [LATIN SMALL LETTER G WITH CIRCUMFLEX] +"\u011D" => "g" + +# ğ [LATIN SMALL LETTER G WITH BREVE] +"\u011F" => "g" + +# ġ [LATIN SMALL LETTER G WITH DOT ABOVE] +"\u0121" => "g" + +# ģ [LATIN SMALL LETTER G WITH CEDILLA] +"\u0123" => "g" + +# ǵ [LATIN SMALL LETTER G WITH ACUTE] +"\u01F5" => "g" + +# ɠ [LATIN SMALL LETTER G WITH HOOK] +"\u0260" => "g" + +# ɡ [LATIN SMALL LETTER SCRIPT G] +"\u0261" => "g" + +# ᵷ [LATIN SMALL LETTER TURNED G] +"\u1D77" => "g" + +# ᵹ [LATIN SMALL LETTER INSULAR G] +"\u1D79" => "g" + +# ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK] +"\u1D83" => "g" + +# ḡ [LATIN SMALL LETTER G WITH MACRON] +"\u1E21" => "g" + +# ⓖ [CIRCLED LATIN SMALL LETTER G] +"\u24D6" => "g" + +# ꝿ [LATIN SMALL LETTER TURNED INSULAR G] +"\uA77F" => "g" + +# ｇ [FULLWIDTH LATIN SMALL LETTER G] +"\uFF47" => "g" + +# ⒢ [PARENTHESIZED LATIN SMALL LETTER G] +"\u24A2" => "(g)" + +# Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX] +"\u0124" => "H" + +# Ħ [LATIN CAPITAL LETTER H WITH STROKE] +"\u0126" => "H" + +# Ȟ [LATIN CAPITAL LETTER H WITH CARON] +"\u021E" => "H" + +# ʜ [LATIN LETTER SMALL CAPITAL H] +"\u029C" => "H" + +# Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE] +"\u1E22" => "H" + +# Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW] +"\u1E24" => "H" + +# Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS] +"\u1E26" => "H" + +# Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA] +"\u1E28" => "H" + +# Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW] +"\u1E2A" => "H" + +# Ⓗ [CIRCLED LATIN CAPITAL LETTER H] +"\u24BD" => "H" + +# Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER] +"\u2C67" => "H" + +# Ⱶ [LATIN CAPITAL LETTER HALF H] +"\u2C75" => "H" + +# Ｈ [FULLWIDTH LATIN CAPITAL LETTER H] +"\uFF28" => "H" + +# ĥ [LATIN SMALL LETTER H WITH CIRCUMFLEX] +"\u0125" => "h" + +# ħ [LATIN SMALL LETTER H WITH STROKE] +"\u0127" => "h" + +# ȟ [LATIN SMALL LETTER H WITH CARON] +"\u021F" => "h" + +# ɥ [LATIN SMALL LETTER TURNED H] +"\u0265" => "h" + +# ɦ [LATIN SMALL LETTER H WITH HOOK] +"\u0266" => "h" + +# ʮ [LATIN SMALL LETTER TURNED H WITH FISHHOOK] +"\u02AE" => "h" + +# ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL] +"\u02AF" => "h" + +# ḣ [LATIN SMALL LETTER H WITH DOT ABOVE] +"\u1E23" => "h" + +# ḥ [LATIN SMALL LETTER H WITH DOT BELOW] +"\u1E25" => "h" + +# ḧ [LATIN SMALL LETTER H WITH DIAERESIS] +"\u1E27" => "h" + +# ḩ [LATIN SMALL LETTER H WITH CEDILLA] +"\u1E29" => "h" + +# ḫ [LATIN SMALL LETTER H WITH BREVE BELOW] +"\u1E2B" => "h" + +# ẖ [LATIN SMALL LETTER H WITH LINE BELOW] +"\u1E96" => "h" + +# ⓗ [CIRCLED LATIN SMALL LETTER H] +"\u24D7" => "h" + +# ⱨ [LATIN SMALL LETTER H WITH DESCENDER] +"\u2C68" => "h" + +# ⱶ [LATIN SMALL LETTER HALF H] +"\u2C76" => "h" + +# ｈ [FULLWIDTH LATIN SMALL LETTER H] +"\uFF48" => "h" + +# Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR] +"\u01F6" => "HV" + +# ⒣ [PARENTHESIZED LATIN SMALL LETTER H] +"\u24A3" => "(h)" + +# ƕ [LATIN SMALL LETTER HV] +"\u0195" => "hv" + +# Ì [LATIN CAPITAL LETTER I WITH GRAVE] +"\u00CC" => "I" + +# Í [LATIN CAPITAL LETTER I WITH ACUTE] +"\u00CD" => "I" + +# Î [LATIN CAPITAL LETTER I WITH CIRCUMFLEX] +"\u00CE" => "I" + +# Ï [LATIN CAPITAL LETTER I WITH DIAERESIS] +"\u00CF" => "I" + +# Ĩ [LATIN CAPITAL LETTER I WITH TILDE] +"\u0128" => "I" + +# Ī [LATIN CAPITAL LETTER I WITH MACRON] +"\u012A" => "I" + +# Ĭ [LATIN CAPITAL LETTER I WITH BREVE] +"\u012C" => "I" + +# Į [LATIN CAPITAL LETTER I WITH OGONEK] +"\u012E" => "I" + +# İ [LATIN CAPITAL LETTER I WITH DOT ABOVE] +"\u0130" => "I" + +# Ɩ [LATIN CAPITAL LETTER IOTA] +"\u0196" => "I" + +# Ɨ [LATIN CAPITAL LETTER I WITH STROKE] +"\u0197" => "I" + +# Ǐ [LATIN CAPITAL LETTER I WITH CARON] +"\u01CF" => "I" + +# Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE] +"\u0208" => "I" + +# Ȋ [LATIN CAPITAL LETTER I WITH INVERTED BREVE] +"\u020A" => "I" + +# ɪ [LATIN LETTER SMALL CAPITAL I] +"\u026A" => "I" + +# ᵻ [LATIN SMALL CAPITAL LETTER I WITH STROKE] +"\u1D7B" => "I" + +# Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW] +"\u1E2C" => "I" + +# Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE] +"\u1E2E" => "I" + +# Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE] +"\u1EC8" => "I" + +# Ị [LATIN CAPITAL LETTER I WITH DOT BELOW] +"\u1ECA" => "I" + +# Ⓘ [CIRCLED LATIN CAPITAL LETTER I] +"\u24BE" => "I" + +# ꟾ [LATIN EPIGRAPHIC LETTER I LONGA] +"\uA7FE" => "I" + +# Ｉ [FULLWIDTH LATIN CAPITAL LETTER I] +"\uFF29" => "I" + +# ì [LATIN SMALL LETTER I WITH GRAVE] +"\u00EC" => "i" + +# í [LATIN SMALL LETTER I WITH ACUTE] +"\u00ED" => "i" + +# î [LATIN SMALL LETTER I WITH CIRCUMFLEX] +"\u00EE" => "i" + +# ï [LATIN SMALL LETTER I WITH DIAERESIS] +"\u00EF" => "i" + +# ĩ [LATIN SMALL LETTER I WITH TILDE] +"\u0129" => "i" + +# ī [LATIN SMALL LETTER I WITH MACRON] +"\u012B" => "i" + +# ĭ [LATIN SMALL LETTER I WITH BREVE] +"\u012D" => "i" + +# į [LATIN SMALL LETTER I WITH OGONEK] +"\u012F" => "i" + +# ı [LATIN SMALL LETTER DOTLESS I] +"\u0131" => "i" + +# ǐ [LATIN SMALL LETTER I WITH CARON] +"\u01D0" => "i" + +# ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE] +"\u0209" => "i" + +# ȋ [LATIN SMALL LETTER I WITH INVERTED BREVE] +"\u020B" => "i" + +# ɨ [LATIN SMALL LETTER I WITH STROKE] +"\u0268" => "i" + +# ᴉ [LATIN SMALL LETTER TURNED I] +"\u1D09" => "i" + +# ᵢ [LATIN SUBSCRIPT SMALL LETTER I] +"\u1D62" => "i" + +# ᵼ [LATIN SMALL LETTER IOTA WITH STROKE] +"\u1D7C" => "i" + +# ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK] +"\u1D96" => "i" + +# ḭ [LATIN SMALL LETTER I WITH TILDE BELOW] +"\u1E2D" => "i" + +# ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE] +"\u1E2F" => "i" + +# ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE] +"\u1EC9" => "i" + +# ị [LATIN SMALL LETTER I WITH DOT BELOW] +"\u1ECB" => "i" + +# ⁱ [SUPERSCRIPT LATIN SMALL LETTER I] +"\u2071" => "i" + +# ⓘ [CIRCLED LATIN SMALL LETTER I] +"\u24D8" => "i" + +# ｉ [FULLWIDTH LATIN SMALL LETTER I] +"\uFF49" => "i" + +# IJ [LATIN CAPITAL LIGATURE IJ] +"\u0132" => "IJ" + +# ⒤ [PARENTHESIZED LATIN SMALL LETTER I] +"\u24A4" => "(i)" + +# ij [LATIN SMALL LIGATURE IJ] +"\u0133" => "ij" + +# Ĵ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX] +"\u0134" => "J" + +# Ɉ [LATIN CAPITAL LETTER J WITH STROKE] +"\u0248" => "J" + +# ᴊ [LATIN LETTER SMALL CAPITAL J] +"\u1D0A" => "J" + +# Ⓙ [CIRCLED LATIN CAPITAL LETTER J] +"\u24BF" => "J" + +# Ｊ [FULLWIDTH LATIN CAPITAL LETTER J] +"\uFF2A" => "J" + +# ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX] +"\u0135" => "j" + +# ǰ [LATIN SMALL LETTER J WITH CARON] +"\u01F0" => "j" + +# ȷ [LATIN SMALL LETTER DOTLESS J] +"\u0237" => "j" + +# ɉ [LATIN SMALL LETTER J WITH STROKE] +"\u0249" => "j" + +# ɟ [LATIN SMALL LETTER DOTLESS J WITH STROKE] +"\u025F" => "j" + +# ʄ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK] +"\u0284" => "j" + +# ʝ [LATIN SMALL LETTER J WITH CROSSED-TAIL] +"\u029D" => "j" + +# ⓙ [CIRCLED LATIN SMALL LETTER J] +"\u24D9" => "j" + +# ⱼ [LATIN SUBSCRIPT SMALL LETTER J] +"\u2C7C" => "j" + +# ｊ [FULLWIDTH LATIN SMALL LETTER J] +"\uFF4A" => "j" + +# ⒥ [PARENTHESIZED LATIN SMALL LETTER J] +"\u24A5" => "(j)" + +# Ķ [LATIN CAPITAL LETTER K WITH CEDILLA] +"\u0136" => "K" + +# Ƙ [LATIN CAPITAL LETTER K WITH HOOK] +"\u0198" => "K" + +# Ǩ [LATIN CAPITAL LETTER K WITH CARON] +"\u01E8" => "K" + +# ᴋ [LATIN LETTER SMALL CAPITAL K] +"\u1D0B" => "K" + +# Ḱ [LATIN CAPITAL LETTER K WITH ACUTE] +"\u1E30" => "K" + +# Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW] +"\u1E32" => "K" + +# Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW] +"\u1E34" => "K" + +# Ⓚ [CIRCLED LATIN CAPITAL LETTER K] +"\u24C0" => "K" + +# Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER] +"\u2C69" => "K" + +# Ꝁ [LATIN CAPITAL LETTER K WITH STROKE] +"\uA740" => "K" + +# Ꝃ [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE] +"\uA742" => "K" + +# Ꝅ [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE] +"\uA744" => "K" + +# Ｋ [FULLWIDTH LATIN CAPITAL LETTER K] +"\uFF2B" => "K" + +# ķ [LATIN SMALL LETTER K WITH CEDILLA] +"\u0137" => "k" + +# ƙ [LATIN SMALL LETTER K WITH HOOK] +"\u0199" => "k" + +# ǩ [LATIN SMALL LETTER K WITH CARON] +"\u01E9" => "k" + +# ʞ [LATIN SMALL LETTER TURNED K] +"\u029E" => "k" + +# ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK] +"\u1D84" => "k" + +# ḱ [LATIN SMALL LETTER K WITH ACUTE] +"\u1E31" => "k" + +# ḳ [LATIN SMALL LETTER K WITH DOT BELOW] +"\u1E33" => "k" + +# ḵ [LATIN SMALL LETTER K WITH LINE BELOW] +"\u1E35" => "k" + +# ⓚ [CIRCLED LATIN SMALL LETTER K] +"\u24DA" => "k" + +# ⱪ [LATIN SMALL LETTER K WITH DESCENDER] +"\u2C6A" => "k" + +# ꝁ [LATIN SMALL LETTER K WITH STROKE] +"\uA741" => "k" + +# ꝃ [LATIN SMALL LETTER K WITH DIAGONAL STROKE] +"\uA743" => "k" + +# ꝅ [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE] +"\uA745" => "k" + +# ｋ [FULLWIDTH LATIN SMALL LETTER K] +"\uFF4B" => "k" + +# ⒦ [PARENTHESIZED LATIN SMALL LETTER K] +"\u24A6" => "(k)" + +# Ĺ [LATIN CAPITAL LETTER L WITH ACUTE] +"\u0139" => "L" + +# Ļ [LATIN CAPITAL LETTER L WITH CEDILLA] +"\u013B" => "L" + +# Ľ [LATIN CAPITAL LETTER L WITH CARON] +"\u013D" => "L" + +# Ŀ [LATIN CAPITAL LETTER L WITH MIDDLE DOT] +"\u013F" => "L" + +# Ł [LATIN CAPITAL LETTER L WITH STROKE] +"\u0141" => "L" + +# Ƚ [LATIN CAPITAL LETTER L WITH BAR] +"\u023D" => "L" + +# ʟ [LATIN LETTER SMALL CAPITAL L] +"\u029F" => "L" + +# ᴌ [LATIN LETTER SMALL CAPITAL L WITH STROKE] +"\u1D0C" => "L" + +# Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW] +"\u1E36" => "L" + +# Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON] +"\u1E38" => "L" + +# Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW] +"\u1E3A" => "L" + +# Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW] +"\u1E3C" => "L" + +# Ⓛ [CIRCLED LATIN CAPITAL LETTER L] +"\u24C1" => "L" + +# Ⱡ [LATIN CAPITAL LETTER L WITH DOUBLE BAR] +"\u2C60" => "L" + +# Ɫ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE] +"\u2C62" => "L" + +# Ꝇ [LATIN CAPITAL LETTER BROKEN L] +"\uA746" => "L" + +# Ꝉ [LATIN CAPITAL LETTER L WITH HIGH STROKE] +"\uA748" => "L" + +# Ꞁ [LATIN CAPITAL LETTER TURNED L] +"\uA780" => "L" + +# Ｌ [FULLWIDTH LATIN CAPITAL LETTER L] +"\uFF2C" => "L" + +# ĺ [LATIN SMALL LETTER L WITH ACUTE] +"\u013A" => "l" + +# ļ [LATIN SMALL LETTER L WITH CEDILLA] +"\u013C" => "l" + +# ľ [LATIN SMALL LETTER L WITH CARON] +"\u013E" => "l" + +# ŀ [LATIN SMALL LETTER L WITH MIDDLE DOT] +"\u0140" => "l" + +# ł [LATIN SMALL LETTER L WITH STROKE] +"\u0142" => "l" + +# ƚ [LATIN SMALL LETTER L WITH BAR] +"\u019A" => "l" + +# ȴ [LATIN SMALL LETTER L WITH CURL] +"\u0234" => "l" + +# ɫ [LATIN SMALL LETTER L WITH MIDDLE TILDE] +"\u026B" => "l" + +# ɬ [LATIN SMALL LETTER L WITH BELT] +"\u026C" => "l" + +# ɭ [LATIN SMALL LETTER L WITH RETROFLEX HOOK] +"\u026D" => "l" + +# ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK] +"\u1D85" => "l" + +# ḷ [LATIN SMALL LETTER L WITH DOT BELOW] +"\u1E37" => "l" + +# ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON] +"\u1E39" => "l" + +# ḻ [LATIN SMALL LETTER L WITH LINE BELOW] +"\u1E3B" => "l" + +# ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW] +"\u1E3D" => "l" + +# ⓛ [CIRCLED LATIN SMALL LETTER L] +"\u24DB" => "l" + +# ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR] +"\u2C61" => "l" + +# ꝇ [LATIN SMALL LETTER BROKEN L] +"\uA747" => "l" + +# ꝉ [LATIN SMALL LETTER L WITH HIGH STROKE] +"\uA749" => "l" + +# ꞁ [LATIN SMALL LETTER TURNED L] +"\uA781" => "l" + +# ｌ [FULLWIDTH LATIN SMALL LETTER L] +"\uFF4C" => "l" + +# LJ [LATIN CAPITAL LETTER LJ] +"\u01C7" => "LJ" + +# Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL] +"\u1EFA" => "LL" + +# Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J] +"\u01C8" => "Lj" + +# ⒧ [PARENTHESIZED LATIN SMALL LETTER L] +"\u24A7" => "(l)" + +# lj [LATIN SMALL LETTER LJ] +"\u01C9" => "lj" + +# ỻ [LATIN SMALL LETTER MIDDLE-WELSH LL] +"\u1EFB" => "ll" + +# ʪ [LATIN SMALL LETTER LS DIGRAPH] +"\u02AA" => "ls" + +# ʫ [LATIN SMALL LETTER LZ DIGRAPH] +"\u02AB" => "lz" + +# Ɯ [LATIN CAPITAL LETTER TURNED M] +"\u019C" => "M" + +# ᴍ [LATIN LETTER SMALL CAPITAL M] +"\u1D0D" => "M" + +# Ḿ [LATIN CAPITAL LETTER M WITH ACUTE] +"\u1E3E" => "M" + +# Ṁ [LATIN CAPITAL LETTER M WITH DOT ABOVE] +"\u1E40" => "M" + +# Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW] +"\u1E42" => "M" + +# Ⓜ [CIRCLED LATIN CAPITAL LETTER M] +"\u24C2" => "M" + +# Ɱ [LATIN CAPITAL LETTER M WITH HOOK] +"\u2C6E" => "M" + +# ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M] +"\uA7FD" => "M" + +# ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M] +"\uA7FF" => "M" + +# Ｍ [FULLWIDTH LATIN CAPITAL LETTER M] +"\uFF2D" => "M" + +# ɯ [LATIN SMALL LETTER TURNED M] +"\u026F" => "m" + +# ɰ [LATIN SMALL LETTER TURNED M WITH LONG LEG] +"\u0270" => "m" + +# ɱ [LATIN SMALL LETTER M WITH HOOK] +"\u0271" => "m" + +# ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE] +"\u1D6F" => "m" + +# ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK] +"\u1D86" => "m" + +# ḿ [LATIN SMALL LETTER M WITH ACUTE] +"\u1E3F" => "m" + +# ṁ [LATIN SMALL LETTER M WITH DOT ABOVE] +"\u1E41" => "m" + +# ṃ [LATIN SMALL LETTER M WITH DOT BELOW] +"\u1E43" => "m" + +# ⓜ [CIRCLED LATIN SMALL LETTER M] +"\u24DC" => "m" + +# ｍ [FULLWIDTH LATIN SMALL LETTER M] +"\uFF4D" => "m" + +# ⒨ [PARENTHESIZED LATIN SMALL LETTER M] +"\u24A8" => "(m)" + +# Ñ [LATIN CAPITAL LETTER N WITH TILDE] +"\u00D1" => "N" + +# Ń [LATIN CAPITAL LETTER N WITH ACUTE] +"\u0143" => "N" + +# Ņ [LATIN CAPITAL LETTER N WITH CEDILLA] +"\u0145" => "N" + +# Ň [LATIN CAPITAL LETTER N WITH CARON] +"\u0147" => "N" + +# Ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG] +"\u014A" => "N" + +# Ɲ [LATIN CAPITAL LETTER N WITH LEFT HOOK] +"\u019D" => "N" + +# Ǹ [LATIN CAPITAL LETTER N WITH GRAVE] +"\u01F8" => "N" + +# Ƞ [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG] +"\u0220" => "N" + +# ɴ [LATIN LETTER SMALL CAPITAL N] +"\u0274" => "N" + +# ᴎ [LATIN LETTER SMALL CAPITAL REVERSED N] +"\u1D0E" => "N" + +# Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE] +"\u1E44" => "N" + +# Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW] +"\u1E46" => "N" + +# Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW] +"\u1E48" => "N" + +# Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW] +"\u1E4A" => "N" + +# Ⓝ [CIRCLED LATIN CAPITAL LETTER N] +"\u24C3" => "N" + +# Ｎ [FULLWIDTH LATIN CAPITAL LETTER N] +"\uFF2E" => "N" + +# ñ [LATIN SMALL LETTER N WITH TILDE] +"\u00F1" => "n" + +# ń [LATIN SMALL LETTER N WITH ACUTE] +"\u0144" => "n" + +# ņ [LATIN SMALL LETTER N WITH CEDILLA] +"\u0146" => "n" + +# ň [LATIN SMALL LETTER N WITH CARON] +"\u0148" => "n" + +# ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE] +"\u0149" => "n" + +# ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG] +"\u014B" => "n" + +# ƞ [LATIN SMALL LETTER N WITH LONG RIGHT LEG] +"\u019E" => "n" + +# ǹ [LATIN SMALL LETTER N WITH GRAVE] +"\u01F9" => "n" + +# ȵ [LATIN SMALL LETTER N WITH CURL] +"\u0235" => "n" + +# ɲ [LATIN SMALL LETTER N WITH LEFT HOOK] +"\u0272" => "n" + +# ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK] +"\u0273" => "n" + +# ᵰ [LATIN SMALL LETTER N WITH MIDDLE TILDE] +"\u1D70" => "n" + +# ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK] +"\u1D87" => "n" + +# ṅ [LATIN SMALL LETTER N WITH DOT ABOVE] +"\u1E45" => "n" + +# ṇ [LATIN SMALL LETTER N WITH DOT BELOW] +"\u1E47" => "n" + +# ṉ [LATIN SMALL LETTER N WITH LINE BELOW] +"\u1E49" => "n" + +# ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW] +"\u1E4B" => "n" + +# ⁿ [SUPERSCRIPT LATIN SMALL LETTER N] +"\u207F" => "n" + +# ⓝ [CIRCLED LATIN SMALL LETTER N] +"\u24DD" => "n" + +# ｎ [FULLWIDTH LATIN SMALL LETTER N] +"\uFF4E" => "n" + +# NJ [LATIN CAPITAL LETTER NJ] +"\u01CA" => "NJ" + +# Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J] +"\u01CB" => "Nj" + +# ⒩ [PARENTHESIZED LATIN SMALL LETTER N] +"\u24A9" => "(n)" + +# nj [LATIN SMALL LETTER NJ] +"\u01CC" => "nj" + +# Ò [LATIN CAPITAL LETTER O WITH GRAVE] +"\u00D2" => "O" + +# Ó [LATIN CAPITAL LETTER O WITH ACUTE] +"\u00D3" => "O" + +# Ô [LATIN CAPITAL LETTER O WITH CIRCUMFLEX] +"\u00D4" => "O" + +# Õ [LATIN CAPITAL LETTER O WITH TILDE] +"\u00D5" => "O" + +# Ö [LATIN CAPITAL LETTER O WITH DIAERESIS] +"\u00D6" => "O" + +# Ø [LATIN CAPITAL LETTER O WITH STROKE] +"\u00D8" => "O" + +# Ō [LATIN CAPITAL LETTER O WITH MACRON] +"\u014C" => "O" + +# Ŏ [LATIN CAPITAL LETTER O WITH BREVE] +"\u014E" => "O" + +# Ő [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE] +"\u0150" => "O" + +# Ɔ [LATIN CAPITAL LETTER OPEN O] +"\u0186" => "O" + +# Ɵ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE] +"\u019F" => "O" + +# Ơ [LATIN CAPITAL LETTER O WITH HORN] +"\u01A0" => "O" + +# Ǒ [LATIN CAPITAL LETTER O WITH CARON] +"\u01D1" => "O" + +# Ǫ [LATIN CAPITAL LETTER O WITH OGONEK] +"\u01EA" => "O" + +# Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON] +"\u01EC" => "O" + +# Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE] +"\u01FE" => "O" + +# Ȍ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE] +"\u020C" => "O" + +# Ȏ [LATIN CAPITAL LETTER O WITH INVERTED BREVE] +"\u020E" => "O" + +# Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON] +"\u022A" => "O" + +# Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON] +"\u022C" => "O" + +# Ȯ [LATIN CAPITAL LETTER O WITH DOT ABOVE] +"\u022E" => "O" + +# Ȱ [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON] +"\u0230" => "O" + +# ᴏ [LATIN LETTER SMALL CAPITAL O] +"\u1D0F" => "O" + +# ᴐ [LATIN LETTER SMALL CAPITAL OPEN O] +"\u1D10" => "O" + +# Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE] +"\u1E4C" => "O" + +# Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS] +"\u1E4E" => "O" + +# Ṑ [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE] +"\u1E50" => "O" + +# Ṓ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE] +"\u1E52" => "O" + +# Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW] +"\u1ECC" => "O" + +# Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE] +"\u1ECE" => "O" + +# Ố [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE] +"\u1ED0" => "O" + +# Ồ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE] +"\u1ED2" => "O" + +# Ổ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1ED4" => "O" + +# Ỗ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE] +"\u1ED6" => "O" + +# Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW] +"\u1ED8" => "O" + +# Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE] +"\u1EDA" => "O" + +# Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE] +"\u1EDC" => "O" + +# Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE] +"\u1EDE" => "O" + +# Ỡ [LATIN CAPITAL LETTER O WITH HORN AND TILDE] +"\u1EE0" => "O" + +# Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW] +"\u1EE2" => "O" + +# Ⓞ [CIRCLED LATIN CAPITAL LETTER O] +"\u24C4" => "O" + +# Ꝋ [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY] +"\uA74A" => "O" + +# Ꝍ [LATIN CAPITAL LETTER O WITH LOOP] +"\uA74C" => "O" + +# Ｏ [FULLWIDTH LATIN CAPITAL LETTER O] +"\uFF2F" => "O" + +# ò [LATIN SMALL LETTER O WITH GRAVE] +"\u00F2" => "o" + +# ó [LATIN SMALL LETTER O WITH ACUTE] +"\u00F3" => "o" + +# ô [LATIN SMALL LETTER O WITH CIRCUMFLEX] +"\u00F4" => "o" + +# õ [LATIN SMALL LETTER O WITH TILDE] +"\u00F5" => "o" + +# ö [LATIN SMALL LETTER O WITH DIAERESIS] +"\u00F6" => "o" + +# ø [LATIN SMALL LETTER O WITH STROKE] +"\u00F8" => "o" + +# ō [LATIN SMALL LETTER O WITH MACRON] +"\u014D" => "o" + +# ŏ [LATIN SMALL LETTER O WITH BREVE] +"\u014F" => "o" + +# ő [LATIN SMALL LETTER O WITH DOUBLE ACUTE] +"\u0151" => "o" + +# ơ [LATIN SMALL LETTER O WITH HORN] +"\u01A1" => "o" + +# ǒ [LATIN SMALL LETTER O WITH CARON] +"\u01D2" => "o" + +# ǫ [LATIN SMALL LETTER O WITH OGONEK] +"\u01EB" => "o" + +# ǭ [LATIN SMALL LETTER O WITH OGONEK AND MACRON] +"\u01ED" => "o" + +# ǿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE] +"\u01FF" => "o" + +# ȍ [LATIN SMALL LETTER O WITH DOUBLE GRAVE] +"\u020D" => "o" + +# ȏ [LATIN SMALL LETTER O WITH INVERTED BREVE] +"\u020F" => "o" + +# ȫ [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON] +"\u022B" => "o" + +# ȭ [LATIN SMALL LETTER O WITH TILDE AND MACRON] +"\u022D" => "o" + +# ȯ [LATIN SMALL LETTER O WITH DOT ABOVE] +"\u022F" => "o" + +# ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON] +"\u0231" => "o" + +# ɔ [LATIN SMALL LETTER OPEN O] +"\u0254" => "o" + +# ɵ [LATIN SMALL LETTER BARRED O] +"\u0275" => "o" + +# ᴖ [LATIN SMALL LETTER TOP HALF O] +"\u1D16" => "o" + +# ᴗ [LATIN SMALL LETTER BOTTOM HALF O] +"\u1D17" => "o" + +# ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK] +"\u1D97" => "o" + +# ṍ [LATIN SMALL LETTER O WITH TILDE AND ACUTE] +"\u1E4D" => "o" + +# ṏ [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS] +"\u1E4F" => "o" + +# ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE] +"\u1E51" => "o" + +# ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE] +"\u1E53" => "o" + +# ọ [LATIN SMALL LETTER O WITH DOT BELOW] +"\u1ECD" => "o" + +# ỏ [LATIN SMALL LETTER O WITH HOOK ABOVE] +"\u1ECF" => "o" + +# ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE] +"\u1ED1" => "o" + +# ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE] +"\u1ED3" => "o" + +# ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE] +"\u1ED5" => "o" + +# ỗ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE] +"\u1ED7" => "o" + +# ộ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW] +"\u1ED9" => "o" + +# ớ [LATIN SMALL LETTER O WITH HORN AND ACUTE] +"\u1EDB" => "o" + +# ờ [LATIN SMALL LETTER O WITH HORN AND GRAVE] +"\u1EDD" => "o" + +# ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE] +"\u1EDF" => "o" + +# ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE] +"\u1EE1" => "o" + +# ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW] +"\u1EE3" => "o" + +# ₒ [LATIN SUBSCRIPT SMALL LETTER O] +"\u2092" => "o" + +# ⓞ [CIRCLED LATIN SMALL LETTER O] +"\u24DE" => "o" + +# ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE] +"\u2C7A" => "o" + +# ꝋ [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY] +"\uA74B" => "o" + +# ꝍ [LATIN SMALL LETTER O WITH LOOP] +"\uA74D" => "o" + +# ｏ [FULLWIDTH LATIN SMALL LETTER O] +"\uFF4F" => "o" + +# Œ [LATIN CAPITAL LIGATURE OE] +"\u0152" => "OE" + +# ɶ [LATIN LETTER SMALL CAPITAL OE] +"\u0276" => "OE" + +# Ꝏ [LATIN CAPITAL LETTER OO] +"\uA74E" => "OO" + +# Ȣ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU] +"\u0222" => "OU" + +# ᴕ [LATIN LETTER SMALL CAPITAL OU] +"\u1D15" => "OU" + +# ⒪ [PARENTHESIZED LATIN SMALL LETTER O] +"\u24AA" => "(o)" + +# œ [LATIN SMALL LIGATURE OE] +"\u0153" => "oe" + +# ᴔ [LATIN SMALL LETTER TURNED OE] +"\u1D14" => "oe" + +# ꝏ [LATIN SMALL LETTER OO] +"\uA74F" => "oo" + +# ȣ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU] +"\u0223" => "ou" + +# Ƥ [LATIN CAPITAL LETTER P WITH HOOK] +"\u01A4" => "P" + +# ᴘ [LATIN LETTER SMALL CAPITAL P] +"\u1D18" => "P" + +# Ṕ [LATIN CAPITAL LETTER P WITH ACUTE] +"\u1E54" => "P" + +# Ṗ [LATIN CAPITAL LETTER P WITH DOT ABOVE] +"\u1E56" => "P" + +# Ⓟ [CIRCLED LATIN CAPITAL LETTER P] +"\u24C5" => "P" + +# Ᵽ [LATIN CAPITAL LETTER P WITH STROKE] +"\u2C63" => "P" + +# Ꝑ [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER] +"\uA750" => "P" + +# Ꝓ [LATIN CAPITAL LETTER P WITH FLOURISH] +"\uA752" => "P" + +# Ꝕ [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL] +"\uA754" => "P" + +# Ｐ [FULLWIDTH LATIN CAPITAL LETTER P] +"\uFF30" => "P" + +# ƥ [LATIN SMALL LETTER P WITH HOOK] +"\u01A5" => "p" + +# ᵱ [LATIN SMALL LETTER P WITH MIDDLE TILDE] +"\u1D71" => "p" + +# ᵽ [LATIN SMALL LETTER P WITH STROKE] +"\u1D7D" => "p" + +# ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK] +"\u1D88" => "p" + +# ṕ [LATIN SMALL LETTER P WITH ACUTE] +"\u1E55" => "p" + +# ṗ [LATIN SMALL LETTER P WITH DOT ABOVE] +"\u1E57" => "p" + +# ⓟ [CIRCLED LATIN SMALL LETTER P] +"\u24DF" => "p" + +# ꝑ [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER] +"\uA751" => "p" + +# ꝓ [LATIN SMALL LETTER P WITH FLOURISH] +"\uA753" => "p" + +# ꝕ [LATIN SMALL LETTER P WITH SQUIRREL TAIL] +"\uA755" => "p" + +# ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P] +"\uA7FC" => "p" + +# ｐ [FULLWIDTH LATIN SMALL LETTER P] +"\uFF50" => "p" + +# ⒫ [PARENTHESIZED LATIN SMALL LETTER P] +"\u24AB" => "(p)" + +# Ɋ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL] +"\u024A" => "Q" + +# Ⓠ [CIRCLED LATIN CAPITAL LETTER Q] +"\u24C6" => "Q" + +# Ꝗ [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER] +"\uA756" => "Q" + +# Ꝙ [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE] +"\uA758" => "Q" + +# Ｑ [FULLWIDTH LATIN CAPITAL LETTER Q] +"\uFF31" => "Q" + +# ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA] +"\u0138" => "q" + +# ɋ [LATIN SMALL LETTER Q WITH HOOK TAIL] +"\u024B" => "q" + +# ʠ [LATIN SMALL LETTER Q WITH HOOK] +"\u02A0" => "q" + +# ⓠ [CIRCLED LATIN SMALL LETTER Q] +"\u24E0" => "q" + +# ꝗ [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER] +"\uA757" => "q" + +# ꝙ [LATIN SMALL LETTER Q WITH DIAGONAL STROKE] +"\uA759" => "q" + +# ｑ [FULLWIDTH LATIN SMALL LETTER Q] +"\uFF51" => "q" + +# ⒬ [PARENTHESIZED LATIN SMALL LETTER Q] +"\u24AC" => "(q)" + +# ȹ [LATIN SMALL LETTER QP DIGRAPH] +"\u0239" => "qp" + +# Ŕ [LATIN CAPITAL LETTER R WITH ACUTE] +"\u0154" => "R" + +# Ŗ [LATIN CAPITAL LETTER R WITH CEDILLA] +"\u0156" => "R" + +# Ř [LATIN CAPITAL LETTER R WITH CARON] +"\u0158" => "R" + +# Ȓ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE] +"\u0210" => "R" + +# Ȓ [LATIN CAPITAL LETTER R WITH INVERTED BREVE] +"\u0212" => "R" + +# Ɍ [LATIN CAPITAL LETTER R WITH STROKE] +"\u024C" => "R" + +# ʀ [LATIN LETTER SMALL CAPITAL R] +"\u0280" => "R" + +# ʁ [LATIN LETTER SMALL CAPITAL INVERTED R] +"\u0281" => "R" + +# ᴙ [LATIN LETTER SMALL CAPITAL REVERSED R] +"\u1D19" => "R" + +# ᴚ [LATIN LETTER SMALL CAPITAL TURNED R] +"\u1D1A" => "R" + +# Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE] +"\u1E58" => "R" + +# Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW] +"\u1E5A" => "R" + +# Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON] +"\u1E5C" => "R" + +# Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW] +"\u1E5E" => "R" + +# Ⓡ [CIRCLED LATIN CAPITAL LETTER R] +"\u24C7" => "R" + +# Ɽ [LATIN CAPITAL LETTER R WITH TAIL] +"\u2C64" => "R" + +# Ꝛ [LATIN CAPITAL LETTER R ROTUNDA] +"\uA75A" => "R" + +# Ꞃ [LATIN CAPITAL LETTER INSULAR R] +"\uA782" => "R" + +# Ｒ [FULLWIDTH LATIN CAPITAL LETTER R] +"\uFF32" => "R" + +# ŕ [LATIN SMALL LETTER R WITH ACUTE] +"\u0155" => "r" + +# ŗ [LATIN SMALL LETTER R WITH CEDILLA] +"\u0157" => "r" + +# ř [LATIN SMALL LETTER R WITH CARON] +"\u0159" => "r" + +# ȑ [LATIN SMALL LETTER R WITH DOUBLE GRAVE] +"\u0211" => "r" + +# ȓ [LATIN SMALL LETTER R WITH INVERTED BREVE] +"\u0213" => "r" + +# ɍ [LATIN SMALL LETTER R WITH STROKE] +"\u024D" => "r" + +# ɼ [LATIN SMALL LETTER R WITH LONG LEG] +"\u027C" => "r" + +# ɽ [LATIN SMALL LETTER R WITH TAIL] +"\u027D" => "r" + +# ɾ [LATIN SMALL LETTER R WITH FISHHOOK] +"\u027E" => "r" + +# ɿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK] +"\u027F" => "r" + +# ᵣ [LATIN SUBSCRIPT SMALL LETTER R] +"\u1D63" => "r" + +# ᵲ [LATIN SMALL LETTER R WITH MIDDLE TILDE] +"\u1D72" => "r" + +# ᵳ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE] +"\u1D73" => "r" + +# ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK] +"\u1D89" => "r" + +# ṙ [LATIN SMALL LETTER R WITH DOT ABOVE] +"\u1E59" => "r" + +# ṛ [LATIN SMALL LETTER R WITH DOT BELOW] +"\u1E5B" => "r" + +# ṝ [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON] +"\u1E5D" => "r" + +# ṟ [LATIN SMALL LETTER R WITH LINE BELOW] +"\u1E5F" => "r" + +# ⓡ [CIRCLED LATIN SMALL LETTER R] +"\u24E1" => "r" + +# ꝛ [LATIN SMALL LETTER R ROTUNDA] +"\uA75B" => "r" + +# ꞃ [LATIN SMALL LETTER INSULAR R] +"\uA783" => "r" + +# ｒ [FULLWIDTH LATIN SMALL LETTER R] +"\uFF52" => "r" + +# ⒭ [PARENTHESIZED LATIN SMALL LETTER R] +"\u24AD" => "(r)" + +# Ś [LATIN CAPITAL LETTER S WITH ACUTE] +"\u015A" => "S" + +# Ŝ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX] +"\u015C" => "S" + +# Ş [LATIN CAPITAL LETTER S WITH CEDILLA] +"\u015E" => "S" + +# Š [LATIN CAPITAL LETTER S WITH CARON] +"\u0160" => "S" + +# Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW] +"\u0218" => "S" + +# Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE] +"\u1E60" => "S" + +# Ṣ [LATIN CAPITAL LETTER S WITH DOT BELOW] +"\u1E62" => "S" + +# Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE] +"\u1E64" => "S" + +# Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE] +"\u1E66" => "S" + +# Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE] +"\u1E68" => "S" + +# Ⓢ [CIRCLED LATIN CAPITAL LETTER S] +"\u24C8" => "S" + +# ꜱ [LATIN LETTER SMALL CAPITAL S] +"\uA731" => "S" + +# ꞅ [LATIN SMALL LETTER INSULAR S] +"\uA785" => "S" + +# Ｓ [FULLWIDTH LATIN CAPITAL LETTER S] +"\uFF33" => "S" + +# ś [LATIN SMALL LETTER S WITH ACUTE] +"\u015B" => "s" + +# ŝ [LATIN SMALL LETTER S WITH CIRCUMFLEX] +"\u015D" => "s" + +# ş [LATIN SMALL LETTER S WITH CEDILLA] +"\u015F" => "s" + +# š [LATIN SMALL LETTER S WITH CARON] +"\u0161" => "s" + +# ſ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S] +"\u017F" => "s" + +# ș [LATIN SMALL LETTER S WITH COMMA BELOW] +"\u0219" => "s" + +# ȿ [LATIN SMALL LETTER S WITH SWASH TAIL] +"\u023F" => "s" + +# ʂ [LATIN SMALL LETTER S WITH HOOK] +"\u0282" => "s" + +# ᵴ [LATIN SMALL LETTER S WITH MIDDLE TILDE] +"\u1D74" => "s" + +# ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK] +"\u1D8A" => "s" + +# ṡ [LATIN SMALL LETTER S WITH DOT ABOVE] +"\u1E61" => "s" + +# ṣ [LATIN SMALL LETTER S WITH DOT BELOW] +"\u1E63" => "s" + +# ṥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE] +"\u1E65" => "s" + +# ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE] +"\u1E67" => "s" + +# ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE] +"\u1E69" => "s" + +# ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE] +"\u1E9C" => "s" + +# ẝ [LATIN SMALL LETTER LONG S WITH HIGH STROKE] +"\u1E9D" => "s" + +# ⓢ [CIRCLED LATIN SMALL LETTER S] +"\u24E2" => "s" + +# Ꞅ [LATIN CAPITAL LETTER INSULAR S] +"\uA784" => "s" + +# ｓ [FULLWIDTH LATIN SMALL LETTER S] +"\uFF53" => "s" + +# ẞ [LATIN CAPITAL LETTER SHARP S] +"\u1E9E" => "SS" + +# ⒮ [PARENTHESIZED LATIN SMALL LETTER S] +"\u24AE" => "(s)" + +# ß [LATIN SMALL LETTER SHARP S] +"\u00DF" => "ss" + +# st [LATIN SMALL LIGATURE ST] +"\uFB06" => "st" + +# Ţ [LATIN CAPITAL LETTER T WITH CEDILLA] +"\u0162" => "T" + +# Ť [LATIN CAPITAL LETTER T WITH CARON] +"\u0164" => "T" + +# Ŧ [LATIN CAPITAL LETTER T WITH STROKE] +"\u0166" => "T" + +# Ƭ [LATIN CAPITAL LETTER T WITH HOOK] +"\u01AC" => "T" + +# Ʈ [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK] +"\u01AE" => "T" + +# Ț [LATIN CAPITAL LETTER T WITH COMMA BELOW] +"\u021A" => "T" + +# Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE] +"\u023E" => "T" + +# ᴛ [LATIN LETTER SMALL CAPITAL T] +"\u1D1B" => "T" + +# Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE] +"\u1E6A" => "T" + +# Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW] +"\u1E6C" => "T" + +# Ṯ [LATIN CAPITAL LETTER T WITH LINE BELOW] +"\u1E6E" => "T" + +# Ṱ [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW] +"\u1E70" => "T" + +# Ⓣ [CIRCLED LATIN CAPITAL LETTER T] +"\u24C9" => "T" + +# Ꞇ [LATIN CAPITAL LETTER INSULAR T] +"\uA786" => "T" + +# Ｔ [FULLWIDTH LATIN CAPITAL LETTER T] +"\uFF34" => "T" + +# ţ [LATIN SMALL LETTER T WITH CEDILLA] +"\u0163" => "t" + +# ť [LATIN SMALL LETTER T WITH CARON] +"\u0165" => "t" + +# ŧ [LATIN SMALL LETTER T WITH STROKE] +"\u0167" => "t" + +# ƫ [LATIN SMALL LETTER T WITH PALATAL HOOK] +"\u01AB" => "t" + +# ƭ [LATIN SMALL LETTER T WITH HOOK] +"\u01AD" => "t" + +# ț [LATIN SMALL LETTER T WITH COMMA BELOW] +"\u021B" => "t" + +# ȶ [LATIN SMALL LETTER T WITH CURL] +"\u0236" => "t" + +# ʇ [LATIN SMALL LETTER TURNED T] +"\u0287" => "t" + +# ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK] +"\u0288" => "t" + +# ᵵ [LATIN SMALL LETTER T WITH MIDDLE TILDE] +"\u1D75" => "t" + +# ṫ [LATIN SMALL LETTER T WITH DOT ABOVE] +"\u1E6B" => "t" + +# ṭ [LATIN SMALL LETTER T WITH DOT BELOW] +"\u1E6D" => "t" + +# ṯ [LATIN SMALL LETTER T WITH LINE BELOW] +"\u1E6F" => "t" + +# ṱ [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW] +"\u1E71" => "t" + +# ẗ [LATIN SMALL LETTER T WITH DIAERESIS] +"\u1E97" => "t" + +# ⓣ [CIRCLED LATIN SMALL LETTER T] +"\u24E3" => "t" + +# ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE] +"\u2C66" => "t" + +# ｔ [FULLWIDTH LATIN SMALL LETTER T] +"\uFF54" => "t" + +# Þ [LATIN CAPITAL LETTER THORN] +"\u00DE" => "TH" + +# Ꝧ [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER] +"\uA766" => "TH" + +# Ꜩ [LATIN CAPITAL LETTER TZ] +"\uA728" => "TZ" + +# ⒯ [PARENTHESIZED LATIN SMALL LETTER T] +"\u24AF" => "(t)" + +# ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL] +"\u02A8" => "tc" + +# þ [LATIN SMALL LETTER THORN] +"\u00FE" => "th" + +# ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH] +"\u1D7A" => "th" + +# ꝧ [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER] +"\uA767" => "th" + +# ʦ [LATIN SMALL LETTER TS DIGRAPH] +"\u02A6" => "ts" + +# ꜩ [LATIN SMALL LETTER TZ] +"\uA729" => "tz" + +# Ù [LATIN CAPITAL LETTER U WITH GRAVE] +"\u00D9" => "U" + +# Ú [LATIN CAPITAL LETTER U WITH ACUTE] +"\u00DA" => "U" + +# Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX] +"\u00DB" => "U" + +# Ü [LATIN CAPITAL LETTER U WITH DIAERESIS] +"\u00DC" => "U" + +# Ũ [LATIN CAPITAL LETTER U WITH TILDE] +"\u0168" => "U" + +# Ū [LATIN CAPITAL LETTER U WITH MACRON] +"\u016A" => "U" + +# Ŭ [LATIN CAPITAL LETTER U WITH BREVE] +"\u016C" => "U" + +# Ů [LATIN CAPITAL LETTER U WITH RING ABOVE] +"\u016E" => "U" + +# Ű [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE] +"\u0170" => "U" + +# Ų [LATIN CAPITAL LETTER U WITH OGONEK] +"\u0172" => "U" + +# Ư [LATIN CAPITAL LETTER U WITH HORN] +"\u01AF" => "U" + +# Ǔ [LATIN CAPITAL LETTER U WITH CARON] +"\u01D3" => "U" + +# Ǖ [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON] +"\u01D5" => "U" + +# Ǘ [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE] +"\u01D7" => "U" + +# Ǚ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON] +"\u01D9" => "U" + +# Ǜ [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE] +"\u01DB" => "U" + +# Ȕ [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE] +"\u0214" => "U" + +# Ȗ [LATIN CAPITAL LETTER U WITH INVERTED BREVE] +"\u0216" => "U" + +# Ʉ [LATIN CAPITAL LETTER U BAR] +"\u0244" => "U" + +# ᴜ [LATIN LETTER SMALL CAPITAL U] +"\u1D1C" => "U" + +# ᵾ [LATIN SMALL CAPITAL LETTER U WITH STROKE] +"\u1D7E" => "U" + +# Ṳ [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW] +"\u1E72" => "U" + +# Ṵ [LATIN CAPITAL LETTER U WITH TILDE BELOW] +"\u1E74" => "U" + +# Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW] +"\u1E76" => "U" + +# Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE] +"\u1E78" => "U" + +# Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS] +"\u1E7A" => "U" + +# Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW] +"\u1EE4" => "U" + +# Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE] +"\u1EE6" => "U" + +# Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE] +"\u1EE8" => "U" + +# Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE] +"\u1EEA" => "U" + +# Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE] +"\u1EEC" => "U" + +# Ữ [LATIN CAPITAL LETTER U WITH HORN AND TILDE] +"\u1EEE" => "U" + +# Ự [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW] +"\u1EF0" => "U" + +# Ⓤ [CIRCLED LATIN CAPITAL LETTER U] +"\u24CA" => "U" + +# Ｕ [FULLWIDTH LATIN CAPITAL LETTER U] +"\uFF35" => "U" + +# ù [LATIN SMALL LETTER U WITH GRAVE] +"\u00F9" => "u" + +# ú [LATIN SMALL LETTER U WITH ACUTE] +"\u00FA" => "u" + +# û [LATIN SMALL LETTER U WITH CIRCUMFLEX] +"\u00FB" => "u" + +# ü [LATIN SMALL LETTER U WITH DIAERESIS] +"\u00FC" => "u" + +# ũ [LATIN SMALL LETTER U WITH TILDE] +"\u0169" => "u" + +# ū [LATIN SMALL LETTER U WITH MACRON] +"\u016B" => "u" + +# ŭ [LATIN SMALL LETTER U WITH BREVE] +"\u016D" => "u" + +# ů [LATIN SMALL LETTER U WITH RING ABOVE] +"\u016F" => "u" + +# ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE] +"\u0171" => "u" + +# ų [LATIN SMALL LETTER U WITH OGONEK] +"\u0173" => "u" + +# ư [LATIN SMALL LETTER U WITH HORN] +"\u01B0" => "u" + +# ǔ [LATIN SMALL LETTER U WITH CARON] +"\u01D4" => "u" + +# ǖ [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON] +"\u01D6" => "u" + +# ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE] +"\u01D8" => "u" + +# ǚ [LATIN SMALL LETTER U WITH DIAERESIS AND CARON] +"\u01DA" => "u" + +# ǜ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE] +"\u01DC" => "u" + +# ȕ [LATIN SMALL LETTER U WITH DOUBLE GRAVE] +"\u0215" => "u" + +# ȗ [LATIN SMALL LETTER U WITH INVERTED BREVE] +"\u0217" => "u" + +# ʉ [LATIN SMALL LETTER U BAR] +"\u0289" => "u" + +# ᵤ [LATIN SUBSCRIPT SMALL LETTER U] +"\u1D64" => "u" + +# ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK] +"\u1D99" => "u" + +# ṳ [LATIN SMALL LETTER U WITH DIAERESIS BELOW] +"\u1E73" => "u" + +# ṵ [LATIN SMALL LETTER U WITH TILDE BELOW] +"\u1E75" => "u" + +# ṷ [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW] +"\u1E77" => "u" + +# ṹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE] +"\u1E79" => "u" + +# ṻ [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS] +"\u1E7B" => "u" + +# ụ [LATIN SMALL LETTER U WITH DOT BELOW] +"\u1EE5" => "u" + +# ủ [LATIN SMALL LETTER U WITH HOOK ABOVE] +"\u1EE7" => "u" + +# ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE] +"\u1EE9" => "u" + +# ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE] +"\u1EEB" => "u" + +# ử [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE] +"\u1EED" => "u" + +# ữ [LATIN SMALL LETTER U WITH HORN AND TILDE] +"\u1EEF" => "u" + +# ự [LATIN SMALL LETTER U WITH HORN AND DOT BELOW] +"\u1EF1" => "u" + +# ⓤ [CIRCLED LATIN SMALL LETTER U] +"\u24E4" => "u" + +# ｕ [FULLWIDTH LATIN SMALL LETTER U] +"\uFF55" => "u" + +# ⒰ [PARENTHESIZED LATIN SMALL LETTER U] +"\u24B0" => "(u)" + +# ᵫ [LATIN SMALL LETTER UE] +"\u1D6B" => "ue" + +# Ʋ [LATIN CAPITAL LETTER V WITH HOOK] +"\u01B2" => "V" + +# Ʌ [LATIN CAPITAL LETTER TURNED V] +"\u0245" => "V" + +# ᴠ [LATIN LETTER SMALL CAPITAL V] +"\u1D20" => "V" + +# Ṽ [LATIN CAPITAL LETTER V WITH TILDE] +"\u1E7C" => "V" + +# Ṿ [LATIN CAPITAL LETTER V WITH DOT BELOW] +"\u1E7E" => "V" + +# Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V] +"\u1EFC" => "V" + +# Ⓥ [CIRCLED LATIN CAPITAL LETTER V] +"\u24CB" => "V" + +# Ꝟ [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE] +"\uA75E" => "V" + +# Ꝩ [LATIN CAPITAL LETTER VEND] +"\uA768" => "V" + +# Ｖ [FULLWIDTH LATIN CAPITAL LETTER V] +"\uFF36" => "V" + +# ʋ [LATIN SMALL LETTER V WITH HOOK] +"\u028B" => "v" + +# ʌ [LATIN SMALL LETTER TURNED V] +"\u028C" => "v" + +# ᵥ [LATIN SUBSCRIPT SMALL LETTER V] +"\u1D65" => "v" + +# ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK] +"\u1D8C" => "v" + +# ṽ [LATIN SMALL LETTER V WITH TILDE] +"\u1E7D" => "v" + +# ṿ [LATIN SMALL LETTER V WITH DOT BELOW] +"\u1E7F" => "v" + +# ⓥ [CIRCLED LATIN SMALL LETTER V] +"\u24E5" => "v" + +# ⱱ [LATIN SMALL LETTER V WITH RIGHT HOOK] +"\u2C71" => "v" + +# ⱴ [LATIN SMALL LETTER V WITH CURL] +"\u2C74" => "v" + +# ꝟ [LATIN SMALL LETTER V WITH DIAGONAL STROKE] +"\uA75F" => "v" + +# ｖ [FULLWIDTH LATIN SMALL LETTER V] +"\uFF56" => "v" + +# Ꝡ [LATIN CAPITAL LETTER VY] +"\uA760" => "VY" + +# ⒱ [PARENTHESIZED LATIN SMALL LETTER V] +"\u24B1" => "(v)" + +# ꝡ [LATIN SMALL LETTER VY] +"\uA761" => "vy" + +# Ŵ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX] +"\u0174" => "W" + +# Ƿ http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN] +"\u01F7" => "W" + +# ᴡ [LATIN LETTER SMALL CAPITAL W] +"\u1D21" => "W" + +# Ẁ [LATIN CAPITAL LETTER W WITH GRAVE] +"\u1E80" => "W" + +# Ẃ [LATIN CAPITAL LETTER W WITH ACUTE] +"\u1E82" => "W" + +# Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS] +"\u1E84" => "W" + +# Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE] +"\u1E86" => "W" + +# Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW] +"\u1E88" => "W" + +# Ⓦ [CIRCLED LATIN CAPITAL LETTER W] +"\u24CC" => "W" + +# Ⱳ [LATIN CAPITAL LETTER W WITH HOOK] +"\u2C72" => "W" + +# Ｗ [FULLWIDTH LATIN CAPITAL LETTER W] +"\uFF37" => "W" + +# ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX] +"\u0175" => "w" + +# ƿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN] +"\u01BF" => "w" + +# ʍ [LATIN SMALL LETTER TURNED W] +"\u028D" => "w" + +# ẁ [LATIN SMALL LETTER W WITH GRAVE] +"\u1E81" => "w" + +# ẃ [LATIN SMALL LETTER W WITH ACUTE] +"\u1E83" => "w" + +# ẅ [LATIN SMALL LETTER W WITH DIAERESIS] +"\u1E85" => "w" + +# ẇ [LATIN SMALL LETTER W WITH DOT ABOVE] +"\u1E87" => "w" + +# ẉ [LATIN SMALL LETTER W WITH DOT BELOW] +"\u1E89" => "w" + +# ẘ [LATIN SMALL LETTER W WITH RING ABOVE] +"\u1E98" => "w" + +# ⓦ [CIRCLED LATIN SMALL LETTER W] +"\u24E6" => "w" + +# ⱳ [LATIN SMALL LETTER W WITH HOOK] +"\u2C73" => "w" + +# ｗ [FULLWIDTH LATIN SMALL LETTER W] +"\uFF57" => "w" + +# ⒲ [PARENTHESIZED LATIN SMALL LETTER W] +"\u24B2" => "(w)" + +# Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE] +"\u1E8A" => "X" + +# Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS] +"\u1E8C" => "X" + +# Ⓧ [CIRCLED LATIN CAPITAL LETTER X] +"\u24CD" => "X" + +# Ｘ [FULLWIDTH LATIN CAPITAL LETTER X] +"\uFF38" => "X" + +# ᶍ [LATIN SMALL LETTER X WITH PALATAL HOOK] +"\u1D8D" => "x" + +# ẋ [LATIN SMALL LETTER X WITH DOT ABOVE] +"\u1E8B" => "x" + +# ẍ [LATIN SMALL LETTER X WITH DIAERESIS] +"\u1E8D" => "x" + +# ₓ [LATIN SUBSCRIPT SMALL LETTER X] +"\u2093" => "x" + +# ⓧ [CIRCLED LATIN SMALL LETTER X] +"\u24E7" => "x" + +# ｘ [FULLWIDTH LATIN SMALL LETTER X] +"\uFF58" => "x" + +# ⒳ [PARENTHESIZED LATIN SMALL LETTER X] +"\u24B3" => "(x)" + +# Ý [LATIN CAPITAL LETTER Y WITH ACUTE] +"\u00DD" => "Y" + +# Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX] +"\u0176" => "Y" + +# Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS] +"\u0178" => "Y" + +# Ƴ [LATIN CAPITAL LETTER Y WITH HOOK] +"\u01B3" => "Y" + +# Ȳ [LATIN CAPITAL LETTER Y WITH MACRON] +"\u0232" => "Y" + +# Ɏ [LATIN CAPITAL LETTER Y WITH STROKE] +"\u024E" => "Y" + +# ʏ [LATIN LETTER SMALL CAPITAL Y] +"\u028F" => "Y" + +# Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE] +"\u1E8E" => "Y" + +# Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE] +"\u1EF2" => "Y" + +# Ỵ [LATIN CAPITAL LETTER Y WITH DOT BELOW] +"\u1EF4" => "Y" + +# Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE] +"\u1EF6" => "Y" + +# Ỹ [LATIN CAPITAL LETTER Y WITH TILDE] +"\u1EF8" => "Y" + +# Ỿ [LATIN CAPITAL LETTER Y WITH LOOP] +"\u1EFE" => "Y" + +# Ⓨ [CIRCLED LATIN CAPITAL LETTER Y] +"\u24CE" => "Y" + +# Ｙ [FULLWIDTH LATIN CAPITAL LETTER Y] +"\uFF39" => "Y" + +# ý [LATIN SMALL LETTER Y WITH ACUTE] +"\u00FD" => "y" + +# ÿ [LATIN SMALL LETTER Y WITH DIAERESIS] +"\u00FF" => "y" + +# ŷ [LATIN SMALL LETTER Y WITH CIRCUMFLEX] +"\u0177" => "y" + +# ƴ [LATIN SMALL LETTER Y WITH HOOK] +"\u01B4" => "y" + +# ȳ [LATIN SMALL LETTER Y WITH MACRON] +"\u0233" => "y" + +# ɏ [LATIN SMALL LETTER Y WITH STROKE] +"\u024F" => "y" + +# ʎ [LATIN SMALL LETTER TURNED Y] +"\u028E" => "y" + +# ẏ [LATIN SMALL LETTER Y WITH DOT ABOVE] +"\u1E8F" => "y" + +# ẙ [LATIN SMALL LETTER Y WITH RING ABOVE] +"\u1E99" => "y" + +# ỳ [LATIN SMALL LETTER Y WITH GRAVE] +"\u1EF3" => "y" + +# ỵ [LATIN SMALL LETTER Y WITH DOT BELOW] +"\u1EF5" => "y" + +# ỷ [LATIN SMALL LETTER Y WITH HOOK ABOVE] +"\u1EF7" => "y" + +# ỹ [LATIN SMALL LETTER Y WITH TILDE] +"\u1EF9" => "y" + +# ỿ [LATIN SMALL LETTER Y WITH LOOP] +"\u1EFF" => "y" + +# ⓨ [CIRCLED LATIN SMALL LETTER Y] +"\u24E8" => "y" + +# ｙ [FULLWIDTH LATIN SMALL LETTER Y] +"\uFF59" => "y" + +# ⒴ [PARENTHESIZED LATIN SMALL LETTER Y] +"\u24B4" => "(y)" + +# Ź [LATIN CAPITAL LETTER Z WITH ACUTE] +"\u0179" => "Z" + +# Ż [LATIN CAPITAL LETTER Z WITH DOT ABOVE] +"\u017B" => "Z" + +# Ž [LATIN CAPITAL LETTER Z WITH CARON] +"\u017D" => "Z" + +# Ƶ [LATIN CAPITAL LETTER Z WITH STROKE] +"\u01B5" => "Z" + +# Ȝ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH] +"\u021C" => "Z" + +# Ȥ [LATIN CAPITAL LETTER Z WITH HOOK] +"\u0224" => "Z" + +# ᴢ [LATIN LETTER SMALL CAPITAL Z] +"\u1D22" => "Z" + +# Ẑ [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX] +"\u1E90" => "Z" + +# Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW] +"\u1E92" => "Z" + +# Ẕ [LATIN CAPITAL LETTER Z WITH LINE BELOW] +"\u1E94" => "Z" + +# Ⓩ [CIRCLED LATIN CAPITAL LETTER Z] +"\u24CF" => "Z" + +# Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER] +"\u2C6B" => "Z" + +# Ꝣ [LATIN CAPITAL LETTER VISIGOTHIC Z] +"\uA762" => "Z" + +# Ｚ [FULLWIDTH LATIN CAPITAL LETTER Z] +"\uFF3A" => "Z" + +# ź [LATIN SMALL LETTER Z WITH ACUTE] +"\u017A" => "z" + +# ż [LATIN SMALL LETTER Z WITH DOT ABOVE] +"\u017C" => "z" + +# ž [LATIN SMALL LETTER Z WITH CARON] +"\u017E" => "z" + +# ƶ [LATIN SMALL LETTER Z WITH STROKE] +"\u01B6" => "z" + +# ȝ http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH] +"\u021D" => "z" + +# ȥ [LATIN SMALL LETTER Z WITH HOOK] +"\u0225" => "z" + +# ɀ [LATIN SMALL LETTER Z WITH SWASH TAIL] +"\u0240" => "z" + +# ʐ [LATIN SMALL LETTER Z WITH RETROFLEX HOOK] +"\u0290" => "z" + +# ʑ [LATIN SMALL LETTER Z WITH CURL] +"\u0291" => "z" + +# ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE] +"\u1D76" => "z" + +# ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK] +"\u1D8E" => "z" + +# ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX] +"\u1E91" => "z" + +# ẓ [LATIN SMALL LETTER Z WITH DOT BELOW] +"\u1E93" => "z" + +# ẕ [LATIN SMALL LETTER Z WITH LINE BELOW] +"\u1E95" => "z" + +# ⓩ [CIRCLED LATIN SMALL LETTER Z] +"\u24E9" => "z" + +# ⱬ [LATIN SMALL LETTER Z WITH DESCENDER] +"\u2C6C" => "z" + +# ꝣ [LATIN SMALL LETTER VISIGOTHIC Z] +"\uA763" => "z" + +# ｚ [FULLWIDTH LATIN SMALL LETTER Z] +"\uFF5A" => "z" + +# ⒵ [PARENTHESIZED LATIN SMALL LETTER Z] +"\u24B5" => "(z)" + +# ⁰ [SUPERSCRIPT ZERO] +"\u2070" => "0" + +# ₀ [SUBSCRIPT ZERO] +"\u2080" => "0" + +# ⓪ [CIRCLED DIGIT ZERO] +"\u24EA" => "0" + +# ⓿ [NEGATIVE CIRCLED DIGIT ZERO] +"\u24FF" => "0" + +# ０ [FULLWIDTH DIGIT ZERO] +"\uFF10" => "0" + +# ¹ [SUPERSCRIPT ONE] +"\u00B9" => "1" + +# ₁ [SUBSCRIPT ONE] +"\u2081" => "1" + +# ① [CIRCLED DIGIT ONE] +"\u2460" => "1" + +# ⓵ [DOUBLE CIRCLED DIGIT ONE] +"\u24F5" => "1" + +# ❶ [DINGBAT NEGATIVE CIRCLED DIGIT ONE] +"\u2776" => "1" + +# ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE] +"\u2780" => "1" + +# ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE] +"\u278A" => "1" + +# １ [FULLWIDTH DIGIT ONE] +"\uFF11" => "1" + +# ⒈ [DIGIT ONE FULL STOP] +"\u2488" => "1." + +# ⑴ [PARENTHESIZED DIGIT ONE] +"\u2474" => "(1)" + +# ² [SUPERSCRIPT TWO] +"\u00B2" => "2" + +# ₂ [SUBSCRIPT TWO] +"\u2082" => "2" + +# ② [CIRCLED DIGIT TWO] +"\u2461" => "2" + +# ⓶ [DOUBLE CIRCLED DIGIT TWO] +"\u24F6" => "2" + +# ❷ [DINGBAT NEGATIVE CIRCLED DIGIT TWO] +"\u2777" => "2" + +# ➁ [DINGBAT CIRCLED SANS-SERIF DIGIT TWO] +"\u2781" => "2" + +# ➋ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO] +"\u278B" => "2" + +# ２ [FULLWIDTH DIGIT TWO] +"\uFF12" => "2" + +# ⒉ [DIGIT TWO FULL STOP] +"\u2489" => "2." + +# ⑵ [PARENTHESIZED DIGIT TWO] +"\u2475" => "(2)" + +# ³ [SUPERSCRIPT THREE] +"\u00B3" => "3" + +# ₃ [SUBSCRIPT THREE] +"\u2083" => "3" + +# ③ [CIRCLED DIGIT THREE] +"\u2462" => "3" + +# ⓷ [DOUBLE CIRCLED DIGIT THREE] +"\u24F7" => "3" + +# ❸ [DINGBAT NEGATIVE CIRCLED DIGIT THREE] +"\u2778" => "3" + +# ➂ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE] +"\u2782" => "3" + +# ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE] +"\u278C" => "3" + +# ３ [FULLWIDTH DIGIT THREE] +"\uFF13" => "3" + +# ⒊ [DIGIT THREE FULL STOP] +"\u248A" => "3." + +# ⑶ [PARENTHESIZED DIGIT THREE] +"\u2476" => "(3)" + +# ⁴ [SUPERSCRIPT FOUR] +"\u2074" => "4" + +# ₄ [SUBSCRIPT FOUR] +"\u2084" => "4" + +# ④ [CIRCLED DIGIT FOUR] +"\u2463" => "4" + +# ⓸ [DOUBLE CIRCLED DIGIT FOUR] +"\u24F8" => "4" + +# ❹ [DINGBAT NEGATIVE CIRCLED DIGIT FOUR] +"\u2779" => "4" + +# ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR] +"\u2783" => "4" + +# ➍ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR] +"\u278D" => "4" + +# ４ [FULLWIDTH DIGIT FOUR] +"\uFF14" => "4" + +# ⒋ [DIGIT FOUR FULL STOP] +"\u248B" => "4." + +# ⑷ [PARENTHESIZED DIGIT FOUR] +"\u2477" => "(4)" + +# ⁵ [SUPERSCRIPT FIVE] +"\u2075" => "5" + +# ₅ [SUBSCRIPT FIVE] +"\u2085" => "5" + +# ⑤ [CIRCLED DIGIT FIVE] +"\u2464" => "5" + +# ⓹ [DOUBLE CIRCLED DIGIT FIVE] +"\u24F9" => "5" + +# ❺ [DINGBAT NEGATIVE CIRCLED DIGIT FIVE] +"\u277A" => "5" + +# ➄ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE] +"\u2784" => "5" + +# ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE] +"\u278E" => "5" + +# ５ [FULLWIDTH DIGIT FIVE] +"\uFF15" => "5" + +# ⒌ [DIGIT FIVE FULL STOP] +"\u248C" => "5." + +# ⑸ [PARENTHESIZED DIGIT FIVE] +"\u2478" => "(5)" + +# ⁶ [SUPERSCRIPT SIX] +"\u2076" => "6" + +# ₆ [SUBSCRIPT SIX] +"\u2086" => "6" + +# ⑥ [CIRCLED DIGIT SIX] +"\u2465" => "6" + +# ⓺ [DOUBLE CIRCLED DIGIT SIX] +"\u24FA" => "6" + +# ❻ [DINGBAT NEGATIVE CIRCLED DIGIT SIX] +"\u277B" => "6" + +# ➅ [DINGBAT CIRCLED SANS-SERIF DIGIT SIX] +"\u2785" => "6" + +# ➏ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX] +"\u278F" => "6" + +# ６ [FULLWIDTH DIGIT SIX] +"\uFF16" => "6" + +# ⒍ [DIGIT SIX FULL STOP] +"\u248D" => "6." + +# ⑹ [PARENTHESIZED DIGIT SIX] +"\u2479" => "(6)" + +# ⁷ [SUPERSCRIPT SEVEN] +"\u2077" => "7" + +# ₇ [SUBSCRIPT SEVEN] +"\u2087" => "7" + +# ⑦ [CIRCLED DIGIT SEVEN] +"\u2466" => "7" + +# ⓻ [DOUBLE CIRCLED DIGIT SEVEN] +"\u24FB" => "7" + +# ❼ [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN] +"\u277C" => "7" + +# ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN] +"\u2786" => "7" + +# ➐ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN] +"\u2790" => "7" + +# ７ [FULLWIDTH DIGIT SEVEN] +"\uFF17" => "7" + +# ⒎ [DIGIT SEVEN FULL STOP] +"\u248E" => "7." + +# ⑺ [PARENTHESIZED DIGIT SEVEN] +"\u247A" => "(7)" + +# ⁸ [SUPERSCRIPT EIGHT] +"\u2078" => "8" + +# ₈ [SUBSCRIPT EIGHT] +"\u2088" => "8" + +# ⑧ [CIRCLED DIGIT EIGHT] +"\u2467" => "8" + +# ⓼ [DOUBLE CIRCLED DIGIT EIGHT] +"\u24FC" => "8" + +# ❽ [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT] +"\u277D" => "8" + +# ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT] +"\u2787" => "8" + +# ➑ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT] +"\u2791" => "8" + +# ８ [FULLWIDTH DIGIT EIGHT] +"\uFF18" => "8" + +# ⒏ [DIGIT EIGHT FULL STOP] +"\u248F" => "8." + +# ⑻ [PARENTHESIZED DIGIT EIGHT] +"\u247B" => "(8)" + +# ⁹ [SUPERSCRIPT NINE] +"\u2079" => "9" + +# ₉ [SUBSCRIPT NINE] +"\u2089" => "9" + +# ⑨ [CIRCLED DIGIT NINE] +"\u2468" => "9" + +# ⓽ [DOUBLE CIRCLED DIGIT NINE] +"\u24FD" => "9" + +# ❾ [DINGBAT NEGATIVE CIRCLED DIGIT NINE] +"\u277E" => "9" + +# ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE] +"\u2788" => "9" + +# ➒ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE] +"\u2792" => "9" + +# ９ [FULLWIDTH DIGIT NINE] +"\uFF19" => "9" + +# ⒐ [DIGIT NINE FULL STOP] +"\u2490" => "9." + +# ⑼ [PARENTHESIZED DIGIT NINE] +"\u247C" => "(9)" + +# ⑩ [CIRCLED NUMBER TEN] +"\u2469" => "10" + +# ⓾ [DOUBLE CIRCLED NUMBER TEN] +"\u24FE" => "10" + +# ❿ [DINGBAT NEGATIVE CIRCLED NUMBER TEN] +"\u277F" => "10" + +# ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN] +"\u2789" => "10" + +# ➓ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN] +"\u2793" => "10" + +# ⒑ [NUMBER TEN FULL STOP] +"\u2491" => "10." + +# ⑽ [PARENTHESIZED NUMBER TEN] +"\u247D" => "(10)" + +# ⑪ [CIRCLED NUMBER ELEVEN] +"\u246A" => "11" + +# ⓫ [NEGATIVE CIRCLED NUMBER ELEVEN] +"\u24EB" => "11" + +# ⒒ [NUMBER ELEVEN FULL STOP] +"\u2492" => "11." + +# ⑾ [PARENTHESIZED NUMBER ELEVEN] +"\u247E" => "(11)" + +# ⑫ [CIRCLED NUMBER TWELVE] +"\u246B" => "12" + +# ⓬ [NEGATIVE CIRCLED NUMBER TWELVE] +"\u24EC" => "12" + +# ⒓ [NUMBER TWELVE FULL STOP] +"\u2493" => "12." + +# ⑿ [PARENTHESIZED NUMBER TWELVE] +"\u247F" => "(12)" + +# ⑬ [CIRCLED NUMBER THIRTEEN] +"\u246C" => "13" + +# ⓭ [NEGATIVE CIRCLED NUMBER THIRTEEN] +"\u24ED" => "13" + +# ⒔ [NUMBER THIRTEEN FULL STOP] +"\u2494" => "13." + +# ⒀ [PARENTHESIZED NUMBER THIRTEEN] +"\u2480" => "(13)" + +# ⑭ [CIRCLED NUMBER FOURTEEN] +"\u246D" => "14" + +# ⓮ [NEGATIVE CIRCLED NUMBER FOURTEEN] +"\u24EE" => "14" + +# ⒕ [NUMBER FOURTEEN FULL STOP] +"\u2495" => "14." + +# ⒁ [PARENTHESIZED NUMBER FOURTEEN] +"\u2481" => "(14)" + +# ⑮ [CIRCLED NUMBER FIFTEEN] +"\u246E" => "15" + +# ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN] +"\u24EF" => "15" + +# ⒖ [NUMBER FIFTEEN FULL STOP] +"\u2496" => "15." + +# ⒂ [PARENTHESIZED NUMBER FIFTEEN] +"\u2482" => "(15)" + +# ⑯ [CIRCLED NUMBER SIXTEEN] +"\u246F" => "16" + +# ⓰ [NEGATIVE CIRCLED NUMBER SIXTEEN] +"\u24F0" => "16" + +# ⒗ [NUMBER SIXTEEN FULL STOP] +"\u2497" => "16." + +# ⒃ [PARENTHESIZED NUMBER SIXTEEN] +"\u2483" => "(16)" + +# ⑰ [CIRCLED NUMBER SEVENTEEN] +"\u2470" => "17" + +# ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN] +"\u24F1" => "17" + +# ⒘ [NUMBER SEVENTEEN FULL STOP] +"\u2498" => "17." + +# ⒄ [PARENTHESIZED NUMBER SEVENTEEN] +"\u2484" => "(17)" + +# ⑱ [CIRCLED NUMBER EIGHTEEN] +"\u2471" => "18" + +# ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN] +"\u24F2" => "18" + +# ⒙ [NUMBER EIGHTEEN FULL STOP] +"\u2499" => "18." + +# ⒅ [PARENTHESIZED NUMBER EIGHTEEN] +"\u2485" => "(18)" + +# ⑲ [CIRCLED NUMBER NINETEEN] +"\u2472" => "19" + +# ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN] +"\u24F3" => "19" + +# ⒚ [NUMBER NINETEEN FULL STOP] +"\u249A" => "19." + +# ⒆ [PARENTHESIZED NUMBER NINETEEN] +"\u2486" => "(19)" + +# ⑳ [CIRCLED NUMBER TWENTY] +"\u2473" => "20" + +# ⓴ [NEGATIVE CIRCLED NUMBER TWENTY] +"\u24F4" => "20" + +# ⒛ [NUMBER TWENTY FULL STOP] +"\u249B" => "20." + +# ⒇ [PARENTHESIZED NUMBER TWENTY] +"\u2487" => "(20)" + +# « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK] +"\u00AB" => "\"" + +# » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK] +"\u00BB" => "\"" + +# “ [LEFT DOUBLE QUOTATION MARK] +"\u201C" => "\"" + +# ” [RIGHT DOUBLE QUOTATION MARK] +"\u201D" => "\"" + +# „ [DOUBLE LOW-9 QUOTATION MARK] +"\u201E" => "\"" + +# ″ [DOUBLE PRIME] +"\u2033" => "\"" + +# ‶ [REVERSED DOUBLE PRIME] +"\u2036" => "\"" + +# ❝ [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT] +"\u275D" => "\"" + +# ❞ [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT] +"\u275E" => "\"" + +# ❮ [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT] +"\u276E" => "\"" + +# ❯ [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT] +"\u276F" => "\"" + +# ＂ [FULLWIDTH QUOTATION MARK] +"\uFF02" => "\"" + +# ‘ [LEFT SINGLE QUOTATION MARK] +"\u2018" => "\'" + +# ’ [RIGHT SINGLE QUOTATION MARK] +"\u2019" => "\'" + +# ‚ [SINGLE LOW-9 QUOTATION MARK] +"\u201A" => "\'" + +# ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK] +"\u201B" => "\'" + +# ′ [PRIME] +"\u2032" => "\'" + +# ‵ [REVERSED PRIME] +"\u2035" => "\'" + +# ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK] +"\u2039" => "\'" + +# › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK] +"\u203A" => "\'" + +# ❛ [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT] +"\u275B" => "\'" + +# ❜ [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT] +"\u275C" => "\'" + +# ＇ [FULLWIDTH APOSTROPHE] +"\uFF07" => "\'" + +# ‐ [HYPHEN] +"\u2010" => "-" + +# ‑ [NON-BREAKING HYPHEN] +"\u2011" => "-" + +# ‒ [FIGURE DASH] +"\u2012" => "-" + +# – [EN DASH] +"\u2013" => "-" + +# — [EM DASH] +"\u2014" => "-" + +# ⁻ [SUPERSCRIPT MINUS] +"\u207B" => "-" + +# ₋ [SUBSCRIPT MINUS] +"\u208B" => "-" + +# － [FULLWIDTH HYPHEN-MINUS] +"\uFF0D" => "-" + +# ⁅ [LEFT SQUARE BRACKET WITH QUILL] +"\u2045" => "[" + +# ❲ [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT] +"\u2772" => "[" + +# ［ [FULLWIDTH LEFT SQUARE BRACKET] +"\uFF3B" => "[" + +# ⁆ [RIGHT SQUARE BRACKET WITH QUILL] +"\u2046" => "]" + +# ❳ [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT] +"\u2773" => "]" + +# ］ [FULLWIDTH RIGHT SQUARE BRACKET] +"\uFF3D" => "]" + +# ⁽ [SUPERSCRIPT LEFT PARENTHESIS] +"\u207D" => "(" + +# ₍ [SUBSCRIPT LEFT PARENTHESIS] +"\u208D" => "(" + +# ❨ [MEDIUM LEFT PARENTHESIS ORNAMENT] +"\u2768" => "(" + +# ❪ [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT] +"\u276A" => "(" + +# （ [FULLWIDTH LEFT PARENTHESIS] +"\uFF08" => "(" + +# ⸨ [LEFT DOUBLE PARENTHESIS] +"\u2E28" => "((" + +# ⁾ [SUPERSCRIPT RIGHT PARENTHESIS] +"\u207E" => ")" + +# ₎ [SUBSCRIPT RIGHT PARENTHESIS] +"\u208E" => ")" + +# ❩ [MEDIUM RIGHT PARENTHESIS ORNAMENT] +"\u2769" => ")" + +# ❫ [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT] +"\u276B" => ")" + +# ） [FULLWIDTH RIGHT PARENTHESIS] +"\uFF09" => ")" + +# ⸩ [RIGHT DOUBLE PARENTHESIS] +"\u2E29" => "))" + +# ❬ [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT] +"\u276C" => "<" + +# ❰ [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT] +"\u2770" => "<" + +# ＜ [FULLWIDTH LESS-THAN SIGN] +"\uFF1C" => "<" + +# ❭ [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT] +"\u276D" => ">" + +# ❱ [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT] +"\u2771" => ">" + +# ＞ [FULLWIDTH GREATER-THAN SIGN] +"\uFF1E" => ">" + +# ❴ [MEDIUM LEFT CURLY BRACKET ORNAMENT] +"\u2774" => "{" + +# ｛ [FULLWIDTH LEFT CURLY BRACKET] +"\uFF5B" => "{" + +# ❵ [MEDIUM RIGHT CURLY BRACKET ORNAMENT] +"\u2775" => "}" + +# ｝ [FULLWIDTH RIGHT CURLY BRACKET] +"\uFF5D" => "}" + +# ⁺ [SUPERSCRIPT PLUS SIGN] +"\u207A" => "+" + +# ₊ [SUBSCRIPT PLUS SIGN] +"\u208A" => "+" + +# ＋ [FULLWIDTH PLUS SIGN] +"\uFF0B" => "+" + +# ⁼ [SUPERSCRIPT EQUALS SIGN] +"\u207C" => "=" + +# ₌ [SUBSCRIPT EQUALS SIGN] +"\u208C" => "=" + +# ＝ [FULLWIDTH EQUALS SIGN] +"\uFF1D" => "=" + +# ！ [FULLWIDTH EXCLAMATION MARK] +"\uFF01" => "!" + +# ‼ [DOUBLE EXCLAMATION MARK] +"\u203C" => "!!" + +# ⁉ [EXCLAMATION QUESTION MARK] +"\u2049" => "!?" + +# ＃ [FULLWIDTH NUMBER SIGN] +"\uFF03" => "#" + +# ＄ [FULLWIDTH DOLLAR SIGN] +"\uFF04" => "$" + +# ⁒ [COMMERCIAL MINUS SIGN] +"\u2052" => "%" + +# ％ [FULLWIDTH PERCENT SIGN] +"\uFF05" => "%" + +# ＆ [FULLWIDTH AMPERSAND] +"\uFF06" => "&" + +# ⁎ [LOW ASTERISK] +"\u204E" => "*" + +# ＊ [FULLWIDTH ASTERISK] +"\uFF0A" => "*" + +# ， [FULLWIDTH COMMA] +"\uFF0C" => "," + +# ． [FULLWIDTH FULL STOP] +"\uFF0E" => "." + +# ⁄ [FRACTION SLASH] +"\u2044" => "/" + +# ／ [FULLWIDTH SOLIDUS] +"\uFF0F" => "/" + +# ： [FULLWIDTH COLON] +"\uFF1A" => ":" + +# ⁏ [REVERSED SEMICOLON] +"\u204F" => ";" + +# ； [FULLWIDTH SEMICOLON] +"\uFF1B" => ";" + +# ？ [FULLWIDTH QUESTION MARK] +"\uFF1F" => "?" + +# ⁇ [DOUBLE QUESTION MARK] +"\u2047" => "??" + +# ⁈ [QUESTION EXCLAMATION MARK] +"\u2048" => "?!" + +# ＠ [FULLWIDTH COMMERCIAL AT] +"\uFF20" => "@" + +# ＼ [FULLWIDTH REVERSE SOLIDUS] +"\uFF3C" => "\\" + +# ‸ [CARET] +"\u2038" => "^" + +# ＾ [FULLWIDTH CIRCUMFLEX ACCENT] +"\uFF3E" => "^" + +# ＿ [FULLWIDTH LOW LINE] +"\uFF3F" => "_" + +# ⁓ [SWUNG DASH] +"\u2053" => "~" + +# ～ [FULLWIDTH TILDE] +"\uFF5E" => "~" + +################################################################ +# Below is the Perl script used to generate the above mappings # +# from ASCIIFoldingFilter.java: # +################################################################ +# +# #!/usr/bin/perl +# +# use warnings; +# use strict; +# +# my @source_chars = (); +# my @source_char_descriptions = (); +# my $target = ''; +# +# while (<>) { +# if (/case\s+'(\\u[A-F0-9]+)':\s*\/\/\s*(.*)/i) { +# push @source_chars, $1; +# push @source_char_descriptions, $2; +# next; +# } +# if (/output\[[^\]]+\]\s*=\s*'(\\'|\\\\|.)'/) { +# $target .= $1; +# next; +# } +# if (/break;/) { +# $target = "\\\"" if ($target eq '"'); +# for my $source_char_num (0..$#source_chars) { +# print "# $source_char_descriptions[$source_char_num]\n"; +# print "\"$source_chars[$source_char_num]\" => \"$target\"\n\n"; +# } +# @source_chars = (); +# @source_char_descriptions = (); +# $target = ''; +# } +# } diff --git a/isuifang_solr/solr/conf/mapping-ISOLatin1Accent.txt b/isuifang_solr/solr/conf/mapping-ISOLatin1Accent.txt new file mode 100644 index 0000000..ede7742 --- /dev/null +++ b/isuifang_solr/solr/conf/mapping-ISOLatin1Accent.txt @@ -0,0 +1,246 @@ +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# Syntax: +# "source" => "target" +# "source".length() > 0 (source cannot be empty.) +# "target".length() >= 0 (target can be empty.) + +# example: +# "À" => "A" +# "\u00C0" => "A" +# "\u00C0" => "\u0041" +# "ß" => "ss" +# "\t" => " " +# "\n" => "" + +# À => A +"\u00C0" => "A" + +# Á => A +"\u00C1" => "A" + +#  => A +"\u00C2" => "A" + +# à => A +"\u00C3" => "A" + +# Ä => A +"\u00C4" => "A" + +# Å => A +"\u00C5" => "A" + +# Æ => AE +"\u00C6" => "AE" + +# Ç => C +"\u00C7" => "C" + +# È => E +"\u00C8" => "E" + +# É => E +"\u00C9" => "E" + +# Ê => E +"\u00CA" => "E" + +# Ë => E +"\u00CB" => "E" + +# Ì => I +"\u00CC" => "I" + +# Í => I +"\u00CD" => "I" + +# Î => I +"\u00CE" => "I" + +# Ï => I +"\u00CF" => "I" + +# IJ => IJ +"\u0132" => "IJ" + +# Ð => D +"\u00D0" => "D" + +# Ñ => N +"\u00D1" => "N" + +# Ò => O +"\u00D2" => "O" + +# Ó => O +"\u00D3" => "O" + +# Ô => O +"\u00D4" => "O" + +# Õ => O +"\u00D5" => "O" + +# Ö => O +"\u00D6" => "O" + +# Ø => O +"\u00D8" => "O" + +# Œ => OE +"\u0152" => "OE" + +# Þ +"\u00DE" => "TH" + +# Ù => U +"\u00D9" => "U" + +# Ú => U +"\u00DA" => "U" + +# Û => U +"\u00DB" => "U" + +# Ü => U +"\u00DC" => "U" + +# Ý => Y +"\u00DD" => "Y" + +# Ÿ => Y +"\u0178" => "Y" + +# à => a +"\u00E0" => "a" + +# á => a +"\u00E1" => "a" + +# â => a +"\u00E2" => "a" + +# ã => a +"\u00E3" => "a" + +# ä => a +"\u00E4" => "a" + +# å => a +"\u00E5" => "a" + +# æ => ae +"\u00E6" => "ae" + +# ç => c +"\u00E7" => "c" + +# è => e +"\u00E8" => "e" + +# é => e +"\u00E9" => "e" + +# ê => e +"\u00EA" => "e" + +# ë => e +"\u00EB" => "e" + +# ì => i +"\u00EC" => "i" + +# í => i +"\u00ED" => "i" + +# î => i +"\u00EE" => "i" + +# ï => i +"\u00EF" => "i" + +# ij => ij +"\u0133" => "ij" + +# ð => d +"\u00F0" => "d" + +# ñ => n +"\u00F1" => "n" + +# ò => o +"\u00F2" => "o" + +# ó => o +"\u00F3" => "o" + +# ô => o +"\u00F4" => "o" + +# õ => o +"\u00F5" => "o" + +# ö => o +"\u00F6" => "o" + +# ø => o +"\u00F8" => "o" + +# œ => oe +"\u0153" => "oe" + +# ß => ss +"\u00DF" => "ss" + +# þ => th +"\u00FE" => "th" + +# ù => u +"\u00F9" => "u" + +# ú => u +"\u00FA" => "u" + +# û => u +"\u00FB" => "u" + +# ü => u +"\u00FC" => "u" + +# ý => y +"\u00FD" => "y" + +# ÿ => y +"\u00FF" => "y" + +# ff => ff +"\uFB00" => "ff" + +# fi => fi +"\uFB01" => "fi" + +# fl => fl +"\uFB02" => "fl" + +# ffi => ffi +"\uFB03" => "ffi" + +# ffl => ffl +"\uFB04" => "ffl" + +# ſt => ft +"\uFB05" => "ft" + +# st => st +"\uFB06" => "st" diff --git a/isuifang_solr/solr/conf/protwords.txt b/isuifang_solr/solr/conf/protwords.txt new file mode 100644 index 0000000..1dfc0ab --- /dev/null +++ b/isuifang_solr/solr/conf/protwords.txt @@ -0,0 +1,21 @@ +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +#----------------------------------------------------------------------- +# Use a protected word file to protect against the stemmer reducing two +# unrelated words to the same base word. + +# Some non-words that normally won't be encountered, +# just to test that they won't be stemmed. +dontstems +zwhacky + diff --git a/isuifang_solr/solr/conf/schema.xml b/isuifang_solr/solr/conf/schema.xml new file mode 100644 index 0000000..1c0cc2c --- /dev/null +++ b/isuifang_solr/solr/conf/schema.xml @@ -0,0 +1,196 @@ +<?xml version="1.0" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<schema name="default" version="1.4"> + <types> + <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> + <fieldtype name="binary" class="solr.BinaryField"/> + + <!-- Numeric field types that manipulate the value into + a string value that isn't human-readable in its internal form, + but with a lexicographic ordering the same as the numeric ordering, + so that range queries work correctly. --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + + <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> + + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + <fieldtype name="geohash" class="solr.GeoHashField"/> + + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- field_type "text_zh", use 'IKAnalyzer' to stop cn words --> + <fieldtype name="text_zh" class="solr.TextField"> + <analyzer type="index"> + <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" /> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords.dic" + enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" + synonyms="synonyms.txt" + ignoreCase="true" + expand="true" /> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" /> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords.dic" + enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" + synonyms="synonyms.txt" + ignoreCase="true" + expand="true" /> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + </fieldtype> + + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + + <fieldType name="ngram" class="solr.TextField" > + <analyzer type="index"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + </analyzer> + </fieldType> + </types> + + <fields> + <!-- general --> + <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> + <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> + <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> + + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> + + + <field name="text" type="text_zh" indexed="true" stored="true" multiValued="false" /> + + <field name="addByUser" type="text_en" indexed="true" stored="true" multiValued="false" /> + + <field name="dataType" type="text_en" indexed="true" stored="true" multiValued="false" /> + + <field name="categories" type="text_en" indexed="true" stored="true" multiValued="true" /> + + </fields> + + <!-- field to use to determine and enforce document uniqueness. --> + <uniqueKey>id</uniqueKey> + + <!-- field for the QueryParser to use when an explicit fieldname is absent --> + <defaultSearchField>text</defaultSearchField> + + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> + <solrQueryParser defaultOperator="AND"/> +</schema> + diff --git a/isuifang_solr/solr/conf/schema.xml.old b/isuifang_solr/solr/conf/schema.xml.old new file mode 100644 index 0000000..fa62a5b --- /dev/null +++ b/isuifang_solr/solr/conf/schema.xml.old @@ -0,0 +1,1052 @@ +<?xml version="1.0" encoding="UTF-8" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<!-- + This is the Solr schema file. This file should be named "schema.xml" and + should be in the conf directory under the solr home + (i.e. ./solr/conf/schema.xml by default) + or located where the classloader for the Solr webapp can find it. + + This example schema is the recommended starting point for users. + It should be kept correct and concise, usable out-of-the-box. + + For more information, on how to customize this file, please see + http://wiki.apache.org/solr/SchemaXml + + PERFORMANCE NOTE: this schema includes many optional features and should not + be used for benchmarking. To improve performance one could + - set stored="false" for all fields possible (esp large fields) when you + only need to search on the field but don't need to return the original + value. + - set indexed="false" if you don't need to search on the field, but only + return the field as a result of searching on other indexed fields. + - remove all unneeded copyField statements + - for best index size and searching performance, set "index" to false + for all general text fields, use copyField to copy them to the + catchall "text" field, and use that for searching. + - For maximum indexing performance, use the StreamingUpdateSolrServer + java client. + - Remember to run the JVM in server mode, and use a higher logging level + that avoids logging every request +--> + +<schema name="example" version="1.5"> + <!-- attribute "name" is the name of this schema and is only used for display purposes. + Applications should change this to reflect the nature of the search collection. + version="x.y" is Solr's version number for the schema syntax and semantics. It should + not normally be changed by applications. + 1.0: multiValued attribute did not exist, all fields are multiValued by nature + 1.1: multiValued attribute introduced, false by default + 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields. + 1.3: removed optional field compress feature + 1.4: default auto-phrase (QueryParser feature) to off + 1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...) + --> + + <types> + <!-- field type definitions. The "name" attribute is + just a label to be used by field definitions. The "class" + attribute and any other attributes determine the real + behavior of the fieldType. + Class names starting with "solr" refer to java classes in the + org.apache.solr.analysis package. + --> + + <!-- The StrField type is not analyzed, but indexed/stored verbatim. --> + <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> + + <!-- boolean type: "true" or "false" --> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> + <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> + <fieldtype name="binary" class="solr.BinaryField"/> + + <!-- The optional sortMissingLast and sortMissingFirst attributes are + currently supported on types that are sorted internally as strings + and on numeric types. + This includes "string","boolean", and, as of 3.5 (and 4.x), + int, float, long, date, double, including the "Trie" variants. + - If sortMissingLast="true", then a sort on this field will cause documents + without the field to come after documents with the field, + regardless of the requested sort order (asc or desc). + - If sortMissingFirst="true", then a sort on this field will cause documents + without the field to come before documents with the field, + regardless of the requested sort order. + - If sortMissingLast="false" and sortMissingFirst="false" (the default), + then default lucene sorting will be used which places docs without the + field first in an ascending sort and last in a descending sort. + --> + + <!-- + Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types. + --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/> + + <!-- + Numeric field types that index each value at various levels of precision + to accelerate range queries when the number of values between the range + endpoints is large. See the javadoc for NumericRangeQuery for internal + implementation details. + + Smaller precisionStep values (specified in bits) will lead to more tokens + indexed per value, slightly larger index size, and faster range queries. + A precisionStep of 0 disables indexing at different precision levels. + --> + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/> + + <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and + is a more restricted form of the canonical representation of dateTime + http://www.w3.org/TR/xmlschema-2/#dateTime + The trailing "Z" designates UTC time and is mandatory. + Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z + All other components are mandatory. + + Expressions can also be used to denote calculations that should be + performed relative to "NOW" to determine the value, ie... + + NOW/HOUR + ... Round to the start of the current hour + NOW-1DAY + ... Exactly 1 day prior to now + NOW/DAY+6MONTHS+3DAYS + ... 6 months and 3 days in the future from the start of + the current day + + Consult the DateField javadocs for more information. + + Note: For faster range queries, consider the tdate type + --> + <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/> + + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/> + + + <!-- + Note: + These should only be used for compatibility with existing indexes (created with older Solr versions) + or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead. + + Plain numeric field types that store and index the text + value verbatim (and hence don't support range queries, since the + lexicographic ordering isn't equal to the numeric ordering) + --> + <fieldType name="pint" class="solr.IntField"/> + <fieldType name="plong" class="solr.LongField"/> + <fieldType name="pfloat" class="solr.FloatField"/> + <fieldType name="pdouble" class="solr.DoubleField"/> + <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/> + + + <!-- + Note: + These should only be used for compatibility with existing indexes (created with older Solr versions). + Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last + + Numeric field types that manipulate the value into + a string value that isn't human-readable in its internal form, + but with a lexicographic ordering the same as the numeric ordering, + so that range queries work correctly. + --> + <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> + + + <!-- The "RandomSortField" is not used to store or search any + data. You can declare fields of this type it in your schema + to generate pseudo-random orderings of your docs for sorting + purposes. The ordering is generated based on the field name + and the version of the index, As long as the index version + remains unchanged, and the same field name is reused, + the ordering of the docs will be consistent. + If you want different psuedo-random orderings of documents, + for the same version of the index, use a dynamicField and + change the name + --> + <fieldType name="random" class="solr.RandomSortField" indexed="true" /> + + <!-- solr.TextField allows the specification of custom text analyzers + specified as a tokenizer and a list of token filters. Different + analyzers may be specified for indexing and querying. + + The optional positionIncrementGap puts space between multiple fields of + this type on the same document, with the purpose of preventing false phrase + matching across fields. + + For more info on customizing your analyzer chain, please see + http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters + --> + + <!-- One can also specify an existing Analyzer class that has a + default constructor via the class attribute on the analyzer element + <fieldType name="text_greek" class="solr.TextField"> + <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> + </fieldType> + --> + + <!-- A text field that only splits on whitespace for exact matching of words --> + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + + <!-- A general text field that has reasonable, generic + cross-language defaults: it tokenizes with StandardTokenizer, + removes stop words from case-insensitive "stopwords.txt" + (empty by default), and down cases. At query time only, it + also applies synonyms. --> + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <!-- A text field with defaults appropriate for English: it + tokenizes with StandardTokenizer, removes English stop words + (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and + finally applies Porter's stemming. The query time analyzer + also applies synonyms from synonyms.txt. --> + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <!-- Case insensitive stop word removal. + add enablePositionIncrements=true in both the index and query + analyzers to leave a 'gap' for more accurate phrase queries. + --> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- A text field with defaults appropriate for English, plus + aggressive word-splitting and autophrase features enabled. + This field is just like text_en, except it adds + WordDelimiterFilter to enable splitting and matching of + words on case-change, alpha numeric boundaries, and + non-alphanumeric chars. This means certain compound word + cases will work, for example query "wi fi" will match + document "WiFi" or "wi-fi". However, other cases will still + not match, for example if the query is "wifi" and the + document is "wi fi" or if the query is "wi-fi" and the + document is "wifi". + --> + <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <!-- Case insensitive stop word removal. + add enablePositionIncrements=true in both the index and query + analyzers to leave a 'gap' for more accurate phrase queries. + --> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Less flexible matching, but less false matches. Probably not ideal for product names, + but may be good for SKUs. Can insert dashes in the wrong place and still match. --> + <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.EnglishMinimalStemFilterFactory"/> + <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes + possible with WordDelimiterFilter in conjuncton with stemming. --> + <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Just like text_general except it reverses the characters of + each token, to enable more efficient leading wildcard queries. --> + <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" + maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <!-- charFilter + WhitespaceTokenizer --> + <!-- + <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" > + <analyzer> + <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + --> + + <!-- This is an example of using the KeywordTokenizer along + With various TokenFilterFactories to produce a sortable field + that does not include some properties of the source text + --> + <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true"> + <analyzer> + <!-- KeywordTokenizer does no actual tokenizing, so the entire + input string is preserved as a single token + --> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <!-- The LowerCase TokenFilter does what you expect, which can be + when you want your sorting to be case insensitive + --> + <filter class="solr.LowerCaseFilterFactory" /> + <!-- The TrimFilter removes any leading or trailing whitespace --> + <filter class="solr.TrimFilterFactory" /> + <!-- The PatternReplaceFilter gives you the flexibility to use + Java Regular expression to replace any sequence of characters + matching a pattern with an arbitrary replacement string, + which may include back references to portions of the original + string matched by the pattern. + + See the Java Regular Expression documentation for more + information on pattern and replacement string syntax. + + http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html + --> + <filter class="solr.PatternReplaceFilterFactory" + pattern="([^a-z])" replacement="" replace="all" + /> + </analyzer> + </fieldType> + + <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" > + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/> + </analyzer> + </fieldtype> + + <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" > + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <!-- + The DelimitedPayloadTokenFilter can put payloads on tokens... for example, + a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f + Attributes of the DelimitedPayloadTokenFilterFactory : + "delimiter" - a one character delimiter. Default is | (pipe) + "encoder" - how to encode the following value into a playload + float -> org.apache.lucene.analysis.payloads.FloatEncoder, + integer -> o.a.l.a.p.IntegerEncoder + identity -> o.a.l.a.p.IdentityEncoder + Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor. + --> + <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/> + </analyzer> + </fieldtype> + + <!-- lowercases the entire field value, keeping it as a single token. --> + <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + </fieldType> + + <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.PathHierarchyTokenizerFactory"/> + </analyzer> + </fieldType> + + + <!-- since fields of this type are by default not stored or indexed, + any data added to them will be ignored outright. --> + <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" /> + + <!-- This point type indexes the coordinates as separate fields (subFields) + If subFieldType is defined, it references a type, and a dynamic field + definition is created matching *___<typename>. Alternately, if + subFieldSuffix is defined, that is used to create the subFields. + Example: if subFieldType="double", then the coordinates would be + indexed in fields myloc_0___double,myloc_1___double. + Example: if subFieldSuffix="_d" then the coordinates would be indexed + in fields myloc_0_d,myloc_1_d + The subFields are an implementation detail of the fieldType, and end + users normally should not need to know about them. + --> + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + + <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + + <!-- + A Geohash is a compact representation of a latitude longitude pair in a single field. + See http://wiki.apache.org/solr/SpatialSearch + --> + <fieldtype name="geohash" class="solr.GeoHashField"/> + <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType + Parameters: + defaultCurrency: Specifies the default currency if none specified. Defaults to "USD" + precisionStep: Specifies the precisionStep for the TrieLong field used for the amount + providerClass: Lets you plug in other exchange provider backend: + solr.FileExchangeRateProvider is the default and takes one parameter: + currencyConfig: name of an xml file holding exhange rates + --> + <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> + + <!-- some examples for different languages (generally ordered by ISO code) --> + + <!-- Arabic --> + <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- for any non-arabic --> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/> + <!-- normalizes ﻯ to ﻱ, etc --> + <filter class="solr.ArabicNormalizationFilterFactory"/> + <filter class="solr.ArabicStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Bulgarian --> + <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/> + <filter class="solr.BulgarianStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Catalan --> + <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- removes l', etc --> + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/> + </analyzer> + </fieldType> + + <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) --> + <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- normalize width before bigram, as e.g. half-width dakuten combine --> + <filter class="solr.CJKWidthFilterFactory"/> + <!-- for any non-CJK --> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.CJKBigramFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Czech --> + <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/> + <filter class="solr.CzechStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Danish --> + <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Danish"/> + </analyzer> + </fieldType> + + <!-- German --> + <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.GermanNormalizationFilterFactory"/> + <filter class="solr.GermanLightStemFilterFactory"/> + <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> --> + <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> --> + </analyzer> + </fieldType> + + <!-- Greek --> + <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- greek specific lowercase for sigma --> + <filter class="solr.GreekLowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/> + <filter class="solr.GreekStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Spanish --> + <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SpanishLightStemFilterFactory"/> + <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> --> + </analyzer> + </fieldType> + + <!-- Basque --> + <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Basque"/> + </analyzer> + </fieldType> + + <!-- Persian --> + <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <!-- for ZWNJ --> + <charFilter class="solr.PersianCharFilterFactory"/> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.ArabicNormalizationFilterFactory"/> + <filter class="solr.PersianNormalizationFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/> + </analyzer> + </fieldType> + + <!-- Finnish --> + <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/> + <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- French --> + <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- removes l', etc --> + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.FrenchLightStemFilterFactory"/> + <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> --> + <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> --> + </analyzer> + </fieldType> + + <!-- Irish --> + <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- removes d', etc --> + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/> + <!-- removes n-, etc. position increments is intentionally false! --> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/> + <filter class="solr.IrishLowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Irish"/> + </analyzer> + </fieldType> + + <!-- Galician --> + <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/> + <filter class="solr.GalicianStemFilterFactory"/> + <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Hindi --> + <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <!-- normalizes unicode representation --> + <filter class="solr.IndicNormalizationFilterFactory"/> + <!-- normalizes variation in spelling --> + <filter class="solr.HindiNormalizationFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/> + <filter class="solr.HindiStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Hungarian --> + <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/> + <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Armenian --> + <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/> + </analyzer> + </fieldType> + + <!-- Indonesian --> + <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/> + <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false --> + <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/> + </analyzer> + </fieldType> + + <!-- Italian --> + <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- removes l', etc --> + <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.ItalianLightStemFilterFactory"/> + <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> --> + </analyzer> + </fieldType> + + <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming) + + NOTE: If you want to optimize search for precision, use default operator AND in your query + parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use + OR if you would like to optimize for recall (default). + --> + <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false"> + <analyzer> + <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer) + + Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic + is used to segment compounds into its parts and the compound itself is kept as synonym. + + Valid values for attribute mode are: + normal: regular segmentation + search: segmentation useful for search with synonyms compounds (default) + extended: same as search mode, but unigrams unknown words (experimental) + + For some applications it might be good to use search mode for indexing and normal mode for + queries to reduce recall and prevent parts of compounds from being matched and highlighted. + Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query. + + Kuromoji also has a convenient user dictionary feature that allows overriding the statistical + model with your own entries for segmentation, part-of-speech tags and readings without a need + to specify weights. Notice that user dictionaries have not been subject to extensive testing. + + User dictionary attributes are: + userDictionary: user dictionary filename + userDictionaryEncoding: user dictionary encoding (default is UTF-8) + + See lang/userdict_ja.txt for a sample user dictionary file. + + See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support. + --> + <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/> + <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>--> + <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) --> + <filter class="solr.JapaneseBaseFormFilterFactory"/> + <!-- Removes tokens with certain part-of-speech tags --> + <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/> + <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) --> + <filter class="solr.CJKWidthFilterFactory"/> + <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking --> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" /> + <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) --> + <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> + <!-- Lower-cases romaji characters --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Latvian --> + <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/> + <filter class="solr.LatvianStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Dutch --> + <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/> + <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/> + </analyzer> + </fieldType> + + <!-- Norwegian --> + <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/> + <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> --> + <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Portuguese --> + <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.PortugueseLightStemFilterFactory"/> + <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> --> + <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> --> + <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Romanian --> + <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/> + </analyzer> + </fieldType> + + <!-- Russian --> + <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Russian"/> + <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Swedish --> + <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/> + <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> --> + </analyzer> + </fieldType> + + <!-- Thai --> + <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.ThaiWordFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/> + </analyzer> + </fieldType> + + <!-- Turkish --> + <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.TurkishLowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/> + </analyzer> + </fieldType> + </types> + + + <fields> + <!-- Valid attributes for fields: + name: mandatory - the name for the field + type: mandatory - the name of a previously defined type from the + <types> section + indexed: true if this field should be indexed (searchable or sortable) + stored: true if this field should be retrievable + multiValued: true if this field may contain multiple values per document + omitNorms: (expert) set to true to omit the norms associated with + this field (this disables length normalization and index-time + boosting for the field, and saves some memory). Only full-text + fields or fields that need an index-time boost need norms. + Norms are omitted for primitive (non-analyzed) types by default. + termVectors: [false] set to true to store the term vector for a + given field. + When using MoreLikeThis, fields used for similarity should be + stored for best performance. + termPositions: Store position information with the term vector. + This will increase storage costs. + termOffsets: Store offset information with the term vector. This + will increase storage costs. + default: a value that should be used if no value is specified + when adding a document. + --> + + <field name="id" type="string" indexed="true" stored="true" required="true" /> + <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> + <field name="name" type="text_general" indexed="true" stored="true"/> + <field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/> + <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> + <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> + <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> + <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> + + <field name="weight" type="float" indexed="true" stored="true"/> + <field name="price" type="float" indexed="true" stored="true"/> + <field name="popularity" type="int" indexed="true" stored="true" /> + <field name="inStock" type="boolean" indexed="true" stored="true" /> + + <!-- + The following store examples are used to demonstrate the various ways one might _CHOOSE_ to + implement spatial. It is highly unlikely that you would ever have ALL of these fields defined. + --> + <field name="store" type="location" indexed="true" stored="true"/> + + <!-- Common metadata fields, named specifically to match up with + SolrCell metadata when parsing rich documents such as Word, PDF. + Some fields are multiValued only because Tika currently may return + multiple values for them. + --> + <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> + <field name="subject" type="text_general" indexed="true" stored="true"/> + <field name="description" type="text_general" indexed="true" stored="true"/> + <field name="comments" type="text_general" indexed="true" stored="true"/> + <field name="author" type="text_general" indexed="true" stored="true"/> + <field name="keywords" type="text_general" indexed="true" stored="true"/> + <field name="category" type="text_general" indexed="true" stored="true"/> + <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/> + <field name="last_modified" type="date" indexed="true" stored="true"/> + <field name="links" type="string" indexed="true" stored="true" multiValued="true"/> + + <!-- catchall field, containing all other searchable text fields (implemented + via copyField further on in this schema --> + <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> + + <!-- catchall text field that indexes tokens both normally and in reverse for efficient + leading wildcard queries. --> + <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> + + <!-- non-tokenized version of manufacturer to make it easier to sort or group + results by manufacturer. copied from "manu" via copyField --> + <field name="manu_exact" type="string" indexed="true" stored="false"/> + + <field name="payloads" type="payloads" indexed="true" stored="true"/> + + <!-- Uncommenting the following will create a "timestamp" field using + a default value of "NOW" to indicate when each document was indexed. + --> + <!-- + <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/> + --> + + <!-- Dynamic field definitions. If a field name is not found, dynamicFields + will be used if the name matches any of the patterns. + RESTRICTION: the glob-like pattern in the name attribute must have + a "*" only at the start or the end. + EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) + Longer patterns will be matched first. if equal size patterns + both match, the first appearing in the schema will be used. --> + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> + <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true" /> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + + <!-- Type used to index the lat and lon components for the "location" FieldType --> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> + + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + + <!-- some trie-coded dynamic fields for faster range queries --> + <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> + <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> + <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> + <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> + <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> + + <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/> + <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> + + <dynamicField name="ignored_*" type="ignored" multiValued="true"/> + <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> + + <dynamicField name="random_*" type="random" /> + + <!-- uncomment the following to ignore any fields that don't already match an existing + field name or dynamic field, rather than reporting them as an error. + alternately, change the type="ignored" to some other type e.g. "text" if you want + unknown fields indexed and/or stored by default --> + <!--dynamicField name="*" type="ignored" multiValued="true" /--> + + </fields> + + <!-- Field to use to determine and enforce document uniqueness. + Unless this field is marked with required="false", it will be a required field + --> + <uniqueKey>id</uniqueKey> + + <!-- field for the QueryParser to use when an explicit fieldname is absent + DEPRECATED: specify "df" in your request handler instead. + <defaultSearchField>text</defaultSearchField> --> + + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" + DEPRECATED: specify "q.op" in your request handler to switch from the default of OR. + <solrQueryParser defaultOperator="OR"/> --> + + <!-- copyField commands copy one field to another at the time a document + is added to the index. It's used either to index the same field differently, + or to add multiple fields to the same field for easier/faster searching. --> + + <copyField source="cat" dest="text"/> + <copyField source="name" dest="text"/> + <copyField source="manu" dest="text"/> + <copyField source="features" dest="text"/> + <copyField source="includes" dest="text"/> + <copyField source="manu" dest="manu_exact"/> + + <!-- Copy the price into a currency enabled field (default USD) --> + <copyField source="price" dest="price_c"/> + + <!-- Above, multiple source fields are copied to the [text] field. + Another way to map multiple source fields to the same + destination field is to use the dynamic field syntax. + copyField also supports a maxChars to copy setting. --> + + <!-- <copyField source="*_t" dest="text" maxChars="3000"/> --> + + <!-- copy name to alphaNameSort, a field designed for sorting by name --> + <!-- <copyField source="name" dest="alphaNameSort"/> --> + + + <!-- Similarity is the scoring routine for each document vs. a query. + A custom similarity may be specified here, but the default is fine + for most applications. --> + <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> --> + <!-- ... OR ... + Specify a SimilarityFactory class name implementation + allowing parameters to be used. + --> + <!-- + <similarity class="com.example.solr.CustomSimilarityFactory"> + <str name="paramkey">param value</str> + </similarity> + --> + + +</schema> diff --git a/isuifang_solr/solr/conf/schema.xml_bak b/isuifang_solr/solr/conf/schema.xml_bak new file mode 100644 index 0000000..4d36ccf --- /dev/null +++ b/isuifang_solr/solr/conf/schema.xml_bak @@ -0,0 +1,190 @@ +<?xml version="1.0" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<schema name="default" version="1.4"> + <types> + <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> + <fieldtype name="binary" class="solr.BinaryField"/> + + <!-- Numeric field types that manipulate the value into + a string value that isn't human-readable in its internal form, + but with a lexicographic ordering the same as the numeric ordering, + so that range queries work correctly. --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> + + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> + + <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> + + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + <fieldtype name="geohash" class="solr.GeoHashField"/> + + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords_en.txt" + enablePositionIncrements="true" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- field_type "text_zh", use 'IKAnalyzer' to stop cn words --> + <fieldtype name="text_zh" class="solr.TextField"> + <analyzer type="index"> + <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" /> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords.dic" + enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" + synonyms="synonyms.txt" + ignoreCase="true" + expand="true" /> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" /> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="stopwords.dic" + enablePositionIncrements="true" /> + <filter class="solr.SynonymFilterFactory" + synonyms="synonyms.txt" + ignoreCase="true" + expand="true" /> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + </fieldtype> + + <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + </analyzer> + </fieldType> + + <fieldType name="ngram" class="solr.TextField" > + <analyzer type="index"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory" /> + <filter class="solr.LowerCaseFilterFactory" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + </analyzer> + </fieldType> + </types> + + <fields> + <!-- general --> + <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> + <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> + <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> + + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> + + + <field name="text" type="text_cn" indexed="true" stored="true" multiValued="false" /> + + </fields> + + <!-- field to use to determine and enforce document uniqueness. --> + <uniqueKey>id</uniqueKey> + + <!-- field for the QueryParser to use when an explicit fieldname is absent --> + <defaultSearchField>text</defaultSearchField> + + <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> + <solrQueryParser defaultOperator="OR"/> +</schema> + diff --git a/isuifang_solr/solr/conf/scripts.conf b/isuifang_solr/solr/conf/scripts.conf new file mode 100644 index 0000000..f58b262 --- /dev/null +++ b/isuifang_solr/solr/conf/scripts.conf @@ -0,0 +1,24 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +user= +solr_hostname=localhost +solr_port=8983 +rsyncd_port=18983 +data_dir= +webapp_name=solr +master_host= +master_data_dir= +master_status_dir= diff --git a/isuifang_solr/solr/conf/solrconfig.xml b/isuifang_solr/solr/conf/solrconfig.xml new file mode 100644 index 0000000..516f69d --- /dev/null +++ b/isuifang_solr/solr/conf/solrconfig.xml @@ -0,0 +1,1625 @@ +<?xml version="1.0" encoding="UTF-8" ?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + +<!-- + For more details about configurations options that may appear in + this file, see http://wiki.apache.org/solr/SolrConfigXml. +--> +<config> + <!-- In all configuration below, a prefix of "solr." for class names + is an alias that causes solr to search appropriate packages, + including org.apache.solr.(search|update|request|core|analysis) + + You may also specify a fully qualified Java classname if you + have your own custom plugins. + --> + + <!-- Set this to 'false' if you want solr to continue working after + it has encountered an severe configuration error. In a + production environment, you may want solr to keep working even + if one handler is mis-configured. + + You may also set this to false using by setting the system + property: + + -Dsolr.abortOnConfigurationError=false + --> + <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError> + + <!-- Controls what version of Lucene various components of Solr + adhere to. Generally, you want to use the latest version to + get all bug fixes and improvements. It is highly recommended + that you fully re-index after changing this setting as it can + affect both how text is indexed and queried. + --> + <luceneMatchVersion>LUCENE_36</luceneMatchVersion> + + <!-- lib directives can be used to instruct Solr to load an Jars + identified and use them to resolve any "plugins" specified in + your solrconfig.xml or schema.xml (ie: Analyzers, Request + Handlers, etc...). + + All directories and paths are resolved relative to the + instanceDir. + + If a "./lib" directory exists in your instanceDir, all files + found in it are included as if you had used the following + syntax... + + <lib dir="./lib" /> + --> + + <!-- A 'dir' option by itself adds any files found in the directory + to the classpath, this is useful for including all jars in a + directory. + --> + <!-- + <lib dir="../add-everything-found-in-this-dir-to-the-classpath" /> + --> + + <!-- When a 'regex' is specified in addition to a 'dir', only the + files in that directory which completely match the regex + (anchored on both ends) will be included. + --> + <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar" /> + <lib dir="../../contrib/extraction/lib" regex=".*\.jar" /> + + <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar" /> + <lib dir="../../contrib/clustering/lib/" regex=".*\.jar" /> + + <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" /> + <lib dir="../../contrib/dataimporthandler/lib/" regex=".*\.jar" /> + + <lib dir="../../dist/" regex="apache-solr-langid-\d.*\.jar" /> + <lib dir="../../contrib/langid/lib/" regex=".*\.jar" /> + + <lib dir="../../dist/" regex="apache-solr-velocity-\d.*\.jar" /> + <lib dir="../../contrib/velocity/lib" regex=".*\.jar" /> + + <!-- If a 'dir' option (with or without a regex) is used and nothing + is found that matches, it will be ignored + --> + <lib dir="/total/crap/dir/ignored" /> + + <!-- an exact 'path' can be used instead of a 'dir' to specify a + specific file. This will cause a serious error to be logged if + it can't be loaded. + --> + <!-- + <lib path="../a-jar-that-does-not-exist.jar" /> + --> + + <!-- Data Directory + + Used to specify an alternate directory to hold all index data + other than the default ./data under the Solr home. If + replication is in use, this should match the replication + configuration. + --> + <dataDir>${solr.data.dir:}</dataDir> + + + <!-- The DirectoryFactory to use for indexes. + + solr.StandardDirectoryFactory, the default, is filesystem + based and tries to pick the best implementation for the current + JVM and platform. One can force a particular implementation + via solr.MMapDirectoryFactory, solr.NIOFSDirectoryFactory, or + solr.SimpleFSDirectoryFactory. + + solr.RAMDirectoryFactory is memory based, not + persistent, and doesn't work with replication. + --> + <directoryFactory name="DirectoryFactory" + class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/> + + <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Index Config - These settings control low-level behavior of indexing + Most example settings here show the default value, but are commented + out, to more easily see where customizations have been made. + + Note: As of Solr 3.6, the <indexDefaults> and <mainIndex> sections + are deprecated and not shown in the example config. They will + still work, but will go away for good in 4.0 + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> + <indexConfig> + <!-- maxFieldLength specifies max number of *tokens* indexed per field. Default: 10000 --> + <!-- <maxFieldLength>10000</maxFieldLength> --> + <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 --> + <!-- <writeLockTimeout>1000</writeLockTimeout> --> + + <!-- Expert: Enabling compound file will use less files for the index, + using fewer file descriptors on the expense of performance decrease. + Default in Lucene is "true". Default in Solr is "false" (since 3.6) --> + <!-- <useCompoundFile>false</useCompoundFile> --> + + <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene + indexing for buffering added documents and deletions before they are + flushed to the Directory. + maxBufferedDocs sets a limit on the number of documents buffered + before flushing. + If both ramBufferSizeMB and maxBufferedDocs is set, then + Lucene will flush based on whichever limit is hit first. --> + <!-- <ramBufferSizeMB>32</ramBufferSizeMB> --> + <!-- <maxBufferedDocs>1000</maxBufferedDocs> --> + + <!-- Expert: Merge Policy + The Merge Policy in Lucene controls how merging of segments is done. + The default since Solr/Lucene 3.3 is TieredMergePolicy. + The default since Lucene 2.3 was the LogByteSizeMergePolicy, + Even older versions of Lucene used LogDocMergePolicy. + --> + <!-- + <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"> + <int name="maxMergeAtOnce">10</int> + <int name="segmentsPerTier">10</int> + </mergePolicy> + --> + + <!-- Merge Factor + The merge factor controls how many segments will get merged at a time. + For TieredMergePolicy, mergeFactor is a convenience parameter which + will set both MaxMergeAtOnce and SegmentsPerTier at once. + For LogByteSizeMergePolicy, mergeFactor decides how many new segments + will be allowed before they are merged into one. + Default is 10 for both merge policies. + --> + <!-- + <mergeFactor>10</mergeFactor> + --> + + <!-- Expert: Merge Scheduler + The Merge Scheduler in Lucene controls how merges are + performed. The ConcurrentMergeScheduler (Lucene 2.3 default) + can perform merges in the background using separate threads. + The SerialMergeScheduler (Lucene 2.2 default) does not. + --> + <!-- + <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/> + --> + + <!-- LockFactory + + This option specifies which Lucene LockFactory implementation + to use. + + single = SingleInstanceLockFactory - suggested for a + read-only index or when there is no possibility of + another process trying to modify the index. + native = NativeFSLockFactory - uses OS native file locking. + Do not use when multiple solr webapps in the same + JVM are attempting to share a single index. + simple = SimpleFSLockFactory - uses a plain file for locking + + Defaults: 'native' is default for Solr3.6 and later, otherwise + 'simple' is the default + + More details on the nuances of each LockFactory... + http://wiki.apache.org/lucene-java/AvailableLockFactories + --> + <!-- <lockType>native</lockType> --> + + <!-- Unlock On Startup + + If true, unlock any held write or commit locks on startup. + This defeats the locking mechanism that allows multiple + processes to safely access a lucene index, and should be used + with care. Default is "false". + + This is not needed if lock type is 'none' or 'single' + --> + <!-- + <unlockOnStartup>false</unlockOnStartup> + --> + + <!-- Expert: Controls how often Lucene loads terms into memory + Default is 128 and is likely good for most everyone. + --> + <!-- <termIndexInterval>128</termIndexInterval> --> + + <!-- If true, IndexReaders will be reopened (often more efficient) + instead of closed and then opened. Default: true + --> + <!-- + <reopenReaders>true</reopenReaders> + --> + + <!-- Commit Deletion Policy + + Custom deletion policies can be specified here. The class must + implement org.apache.lucene.index.IndexDeletionPolicy. + + http://lucene.apache.org/java/3_5_0/api/core/org/apache/lucene/index/IndexDeletionPolicy.html + + The default Solr IndexDeletionPolicy implementation supports + deleting index commit points on number of commits, age of + commit point and optimized status. + + The latest commit point should always be preserved regardless + of the criteria. + --> + <!-- + <deletionPolicy class="solr.SolrDeletionPolicy"> + --> + <!-- The number of commit points to be kept --> + <!-- <str name="maxCommitsToKeep">1</str> --> + <!-- The number of optimized commit points to be kept --> + <!-- <str name="maxOptimizedCommitsToKeep">0</str> --> + <!-- + Delete all commit points once they have reached the given age. + Supports DateMathParser syntax e.g. + --> + <!-- + <str name="maxCommitAge">30MINUTES</str> + <str name="maxCommitAge">1DAY</str> + --> + <!-- + </deletionPolicy> + --> + + <!-- Lucene Infostream + + To aid in advanced debugging, Lucene provides an "InfoStream" + of detailed information when indexing. + + Setting The value to true will instruct the underlying Lucene + IndexWriter to write its debugging info the specified file + --> + <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> --> + </indexConfig> + + + <!-- JMX + + This example enables JMX if and only if an existing MBeanServer + is found, use this if you want to configure JMX through JVM + parameters. Remove this to disable exposing Solr configuration + and statistics to JMX. + + For more details see http://wiki.apache.org/solr/SolrJmx + --> + <jmx /> + <!-- If you want to connect to a particular server, specify the + agentId + --> + <!-- <jmx agentId="myAgent" /> --> + <!-- If you want to start a new MBeanServer, specify the serviceUrl --> + <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/> + --> + + <!-- The default high-performance update handler --> + <updateHandler class="solr.DirectUpdateHandler2"> + + <!-- AutoCommit + + Perform a <commit/> automatically under certain conditions. + Instead of enabling autoCommit, consider using "commitWithin" + when adding documents. + + http://wiki.apache.org/solr/UpdateXmlMessages + + maxDocs - Maximum number of documents to add since the last + commit before automatically triggering a new commit. + + maxTime - Maximum amount of time that is allowed to pass + since a document was added before automaticly + triggering a new commit. + --> + <!-- + <autoCommit> + <maxDocs>10000</maxDocs> + <maxTime>1000</maxTime> + </autoCommit> + --> + + <!-- Update Related Event Listeners + + Various IndexWriter related events can trigger Listeners to + take actions. + + postCommit - fired after every commit or optimize command + postOptimize - fired after every optimize command + --> + <!-- The RunExecutableListener executes an external command from a + hook such as postCommit or postOptimize. + + exe - the name of the executable to run + dir - dir to use as the current working directory. (default=".") + wait - the calling thread waits until the executable returns. + (default="true") + args - the arguments to pass to the program. (default is none) + env - environment variables to set. (default is none) + --> + <!-- This example shows how RunExecutableListener could be used + with the script based replication... + http://wiki.apache.org/solr/CollectionDistribution + --> + <!-- + <listener event="postCommit" class="solr.RunExecutableListener"> + <str name="exe">solr/bin/snapshooter</str> + <str name="dir">.</str> + <bool name="wait">true</bool> + <arr name="args"> <str>arg1</str> <str>arg2</str> </arr> + <arr name="env"> <str>MYVAR=val1</str> </arr> + </listener> + --> + </updateHandler> + + <!-- IndexReaderFactory + + Use the following format to specify a custom IndexReaderFactory, + which allows for alternate IndexReader implementations. + + ** Experimental Feature ** + + Please note - Using a custom IndexReaderFactory may prevent + certain other features from working. The API to + IndexReaderFactory may change without warning or may even be + removed from future releases if the problems cannot be + resolved. + + + ** Features that may not work with custom IndexReaderFactory ** + + The ReplicationHandler assumes a disk-resident index. Using a + custom IndexReader implementation may cause incompatibility + with ReplicationHandler and may cause replication to not work + correctly. See SOLR-1366 for details. + + --> + <!-- + <indexReaderFactory name="IndexReaderFactory" class="package.class"> + <str name="someArg">Some Value</str> + </indexReaderFactory > + --> + <!-- By explicitly declaring the Factory, the termIndexDivisor can + be specified. + --> + <!-- + <indexReaderFactory name="IndexReaderFactory" + class="solr.StandardIndexReaderFactory"> + <int name="setTermIndexDivisor">12</int> + </indexReaderFactory > + --> + + <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Query section - these settings control query time things like caches + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ --> + <query> + <!-- Max Boolean Clauses + + Maximum number of clauses in each BooleanQuery, an exception + is thrown if exceeded. + + ** WARNING ** + + This option actually modifies a global Lucene property that + will affect all SolrCores. If multiple solrconfig.xml files + disagree on this property, the value at any given moment will + be based on the last SolrCore to be initialized. + + --> + <maxBooleanClauses>1024</maxBooleanClauses> + + + <!-- Solr Internal Query Caches + + There are two implementations of cache available for Solr, + LRUCache, based on a synchronized LinkedHashMap, and + FastLRUCache, based on a ConcurrentHashMap. + + FastLRUCache has faster gets and slower puts in single + threaded operation and thus is generally faster than LRUCache + when the hit ratio of the cache is high (> 75%), and may be + faster under other scenarios on multi-cpu systems. + --> + + <!-- Filter Cache + + Cache used by SolrIndexSearcher for filters (DocSets), + unordered sets of *all* documents that match a query. When a + new searcher is opened, its caches may be prepopulated or + "autowarmed" using data from caches in the old searcher. + autowarmCount is the number of items to prepopulate. For + LRUCache, the autowarmed items will be the most recently + accessed items. + + Parameters: + class - the SolrCache implementation LRUCache or + (LRUCache or FastLRUCache) + size - the maximum number of entries in the cache + initialSize - the initial capacity (number of entries) of + the cache. (see java.util.HashMap) + autowarmCount - the number of entries to prepopulate from + and old cache. + --> + <filterCache class="solr.FastLRUCache" + size="512" + initialSize="512" + autowarmCount="0"/> + + <!-- Query Result Cache + + Caches results of searches - ordered lists of document ids + (DocList) based on a query, a sort, and the range of documents + requested. + --> + <queryResultCache class="solr.LRUCache" + size="512" + initialSize="512" + autowarmCount="0"/> + + <!-- Document Cache + + Caches Lucene Document objects (the stored fields for each + document). Since Lucene internal document ids are transient, + this cache will not be autowarmed. + --> + <documentCache class="solr.LRUCache" + size="512" + initialSize="512" + autowarmCount="0"/> + + <!-- Field Value Cache + + Cache used to hold field values that are quickly accessible + by document id. The fieldValueCache is created by default + even if not configured here. + --> + <!-- + <fieldValueCache class="solr.FastLRUCache" + size="512" + autowarmCount="128" + showItems="32" /> + --> + + <!-- Custom Cache + + Example of a generic cache. These caches may be accessed by + name through SolrIndexSearcher.getCache(),cacheLookup(), and + cacheInsert(). The purpose is to enable easy caching of + user/application level data. The regenerator argument should + be specified as an implementation of solr.CacheRegenerator + if autowarming is desired. + --> + <!-- + <cache name="myUserCache" + class="solr.LRUCache" + size="4096" + initialSize="1024" + autowarmCount="1024" + regenerator="com.mycompany.MyRegenerator" + /> + --> + + + <!-- Lazy Field Loading + + If true, stored fields that are not requested will be loaded + lazily. This can result in a significant speed improvement + if the usual case is to not load all stored fields, + especially if the skipped fields are large compressed text + fields. + --> + <enableLazyFieldLoading>true</enableLazyFieldLoading> + + <!-- Use Filter For Sorted Query + + A possible optimization that attempts to use a filter to + satisfy a search. If the requested sort does not include + score, then the filterCache will be checked for a filter + matching the query. If found, the filter will be used as the + source of document ids, and then the sort will be applied to + that. + + For most situations, this will not be useful unless you + frequently get the same search repeatedly with different sort + options, and none of them ever use "score" + --> + <!-- + <useFilterForSortedQuery>true</useFilterForSortedQuery> + --> + + <!-- Result Window Size + + An optimization for use with the queryResultCache. When a search + is requested, a superset of the requested number of document ids + are collected. For example, if a search for a particular query + requests matching documents 10 through 19, and queryWindowSize + is 50, then documents 0 through 49 will be collected and cached. + Any further requests in that range can be satisfied via the cache. + --> + <queryResultWindowSize>20</queryResultWindowSize> + + <!-- Maximum number of documents to cache for any entry in the + queryResultCache. + --> + <queryResultMaxDocsCached>200</queryResultMaxDocsCached> + + <!-- Query Related Event Listeners + + Various IndexSearcher related events can trigger Listeners to + take actions. + + newSearcher - fired whenever a new searcher is being prepared + and there is a current searcher handling requests (aka + registered). It can be used to prime certain caches to + prevent long request times for certain requests. + + firstSearcher - fired whenever a new searcher is being + prepared but there is no current registered searcher to handle + requests or to gain autowarming data from. + + + --> + <!-- QuerySenderListener takes an array of NamedList and executes a + local query request for each NamedList in sequence. + --> + <listener event="newSearcher" class="solr.QuerySenderListener"> + <arr name="queries"> + <!-- + <lst><str name="q">solr</str><str name="sort">price asc</str></lst> + <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst> + --> + </arr> + </listener> + <listener event="firstSearcher" class="solr.QuerySenderListener"> + <arr name="queries"> + <lst> + <str name="q">static firstSearcher warming in solrconfig.xml</str> + </lst> + </arr> + </listener> + + <!-- Use Cold Searcher + + If a search request comes in and there is no current + registered searcher, then immediately register the still + warming searcher and use it. If "false" then all requests + will block until the first searcher is done warming. + --> + <useColdSearcher>false</useColdSearcher> + + <!-- Max Warming Searchers + + Maximum number of searchers that may be warming in the + background concurrently. An error is returned if this limit + is exceeded. + + Recommend values of 1-2 for read-only slaves, higher for + masters w/o cache warming. + --> + <maxWarmingSearchers>2</maxWarmingSearchers> + + </query> + + + <!-- Request Dispatcher + + This section contains instructions for how the SolrDispatchFilter + should behave when processing requests for this SolrCore. + + If you wish to regain use of /select?qt=... style request handler + dispatching, then first add handleSelect="true" to + <requestDispatcher>. Then change the name of the request handler + named "/select" to something else without a leading "/", such as + simply "select" and add default="true" to it. + --> + <requestDispatcher> + <!-- Request Parsing + + These settings indicate how Solr Requests may be parsed, and + what restrictions may be placed on the ContentStreams from + those requests + + enableRemoteStreaming - enables use of the stream.file + and stream.url parameters for specifying remote streams. + SearchRequestHandler won't fetch it, but some others do. + + multipartUploadLimitInKB - specifies the max size of + Multipart File Uploads that Solr will allow in a Request. + + *** WARNING *** + The settings below authorize Solr to fetch remote files, You + should make sure your system has some authentication before + using enableRemoteStreaming="true" + + --> + <requestParsers enableRemoteStreaming="true" + multipartUploadLimitInKB="2048000" /> + + <!-- HTTP Caching + + Set HTTP caching related parameters (for proxy caches and clients). + + The options below instruct Solr not to output any HTTP Caching + related headers + --> + <httpCaching never304="true" /> + <!-- If you include a <cacheControl> directive, it will be used to + generate a Cache-Control header (as well as an Expires header + if the value contains "max-age=") + + By default, no Cache-Control header is generated. + + You can use the <cacheControl> option even if you have set + never304="true" + --> + <!-- + <httpCaching never304="true" > + <cacheControl>max-age=30, public</cacheControl> + </httpCaching> + --> + <!-- To enable Solr to respond with automatically generated HTTP + Caching headers, and to response to Cache Validation requests + correctly, set the value of never304="false" + + This will cause Solr to generate Last-Modified and ETag + headers based on the properties of the Index. + + The following options can also be specified to affect the + values of these headers... + + lastModFrom - the default value is "openTime" which means the + Last-Modified value (and validation against If-Modified-Since + requests) will all be relative to when the current Searcher + was opened. You can change it to lastModFrom="dirLastMod" if + you want the value to exactly correspond to when the physical + index was last modified. + + etagSeed="..." is an option you can change to force the ETag + header (and validation against If-None-Match requests) to be + different even if the index has not changed (ie: when making + significant changes to your config file) + + (lastModifiedFrom and etagSeed are both ignored if you use + the never304="true" option) + --> + <!-- + <httpCaching lastModifiedFrom="openTime" + etagSeed="Solr"> + <cacheControl>max-age=30, public</cacheControl> + </httpCaching> + --> + </requestDispatcher> + + <!-- Request Handlers + + http://wiki.apache.org/solr/SolrRequestHandler + + Incoming queries will be dispatched to the correct handler + based on the matching request path piece. + + If a Request Handler is declared with startup="lazy", then it will + not be initialized until the first request that uses it. + + --> + <!-- SearchHandler + + http://wiki.apache.org/solr/SearchHandler + + For processing Search Queries, the primary Request Handler + provided with Solr is "SearchHandler" It delegates to a sequent + of SearchComponents (see below) and supports distributed + queries across multiple shards + --> + <requestHandler name="/select" class="solr.SearchHandler"> + <!-- default values for query parameters can be specified, these + will be overridden by parameters in the request + --> + <lst name="defaults"> + <str name="echoParams">explicit</str> + <int name="rows">10</int> + <str name="df">text</str> + </lst> + <!-- In addition to defaults, "appends" params can be specified + to identify values which should be appended to the list of + multi-val params from the query (or the existing "defaults"). + --> + <!-- In this example, the param "fq=instock:true" would be appended to + any query time fq params the user may specify, as a mechanism for + partitioning the index, independent of any user selected filtering + that may also be desired (perhaps as a result of faceted searching). + + NOTE: there is *absolutely* nothing a client can do to prevent these + "appends" values from being used, so don't use this mechanism + unless you are sure you always want it. + --> + <!-- + <lst name="appends"> + <str name="fq">inStock:true</str> + </lst> + --> + <!-- "invariants" are a way of letting the Solr maintainer lock down + the options available to Solr clients. Any params values + specified here are used regardless of what values may be specified + in either the query, the "defaults", or the "appends" params. + + In this example, the facet.field and facet.query params would + be fixed, limiting the facets clients can use. Faceting is + not turned on by default - but if the client does specify + facet=true in the request, these are the only facets they + will be able to see counts for; regardless of what other + facet.field or facet.query params they may specify. + + NOTE: there is *absolutely* nothing a client can do to prevent these + "invariants" values from being used, so don't use this mechanism + unless you are sure you always want it. + --> + <!-- + <lst name="invariants"> + <str name="facet.field">cat</str> + <str name="facet.field">manu_exact</str> + <str name="facet.query">price:[* TO 500]</str> + <str name="facet.query">price:[500 TO *]</str> + </lst> + --> + <!-- If the default list of SearchComponents is not desired, that + list can either be overridden completely, or components can be + prepended or appended to the default list. (see below) + --> + <!-- + <arr name="components"> + <str>nameOfCustomComponent1</str> + <str>nameOfCustomComponent2</str> + </arr> + --> + </requestHandler> + + <!-- A Robust Example + + This example SearchHandler declaration shows off usage of the + SearchHandler with many defaults declared + + Note that multiple instances of the same Request Handler + (SearchHandler) can be registered multiple times with different + names (and different init parameters) + --> + <requestHandler name="/browse" class="solr.SearchHandler"> + <lst name="defaults"> + <str name="echoParams">explicit</str> + + <!-- VelocityResponseWriter settings --> + <str name="wt">velocity</str> + + <str name="v.template">browse</str> + <str name="v.layout">layout</str> + <str name="title">Solritas</str> + + <str name="df">text</str> + <str name="defType">edismax</str> + <str name="q.alt">*:*</str> + <str name="rows">10</str> + <str name="fl">*,score</str> + <str name="mlt.qf"> + text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4 + </str> + <str name="mlt.fl">text,features,name,sku,id,manu,cat</str> + <int name="mlt.count">3</int> + + <str name="qf"> + text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4 + </str> + + <str name="facet">on</str> + <str name="facet.field">cat</str> + <str name="facet.field">manu_exact</str> + <str name="facet.query">ipod</str> + <str name="facet.query">GB</str> + <str name="facet.mincount">1</str> + <str name="facet.pivot">cat,inStock</str> + <str name="facet.range.other">after</str> + <str name="facet.range">price</str> + <int name="f.price.facet.range.start">0</int> + <int name="f.price.facet.range.end">600</int> + <int name="f.price.facet.range.gap">50</int> + <str name="facet.range">popularity</str> + <int name="f.popularity.facet.range.start">0</int> + <int name="f.popularity.facet.range.end">10</int> + <int name="f.popularity.facet.range.gap">3</int> + <str name="facet.range">manufacturedate_dt</str> + <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str> + <str name="f.manufacturedate_dt.facet.range.end">NOW</str> + <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str> + <str name="f.manufacturedate_dt.facet.range.other">before</str> + <str name="f.manufacturedate_dt.facet.range.other">after</str> + + + <!-- Highlighting defaults --> + <str name="hl">on</str> + <str name="hl.fl">text features name</str> + <str name="f.name.hl.fragsize">0</str> + <str name="f.name.hl.alternateField">name</str> + </lst> + <arr name="last-components"> + <str>spellcheck</str> + </arr> + <!-- + <str name="url-scheme">httpx</str> + --> + </requestHandler> + + <!-- XML Update Request Handler. + + http://wiki.apache.org/solr/UpdateXmlMessages + + The canonical Request Handler for Modifying the Index through + commands specified using XML. + + Note: Since solr1.1 requestHandlers requires a valid content + type header if posted in the body. For example, curl now + requires: -H 'Content-type:text/xml; charset=utf-8' + --> + <requestHandler name="/update" + class="solr.XmlUpdateRequestHandler"> + <!-- See below for information on defining + updateRequestProcessorChains that can be used by name + on each Update Request + --> + <!-- + <lst name="defaults"> + <str name="update.chain">dedupe</str> + </lst> + --> + </requestHandler> + <!-- Binary Update Request Handler + http://wiki.apache.org/solr/javabin + --> + <requestHandler name="/update/javabin" + class="solr.BinaryUpdateRequestHandler" /> + + <!-- CSV Update Request Handler + http://wiki.apache.org/solr/UpdateCSV + --> + <requestHandler name="/update/csv" + class="solr.CSVRequestHandler" + startup="lazy" /> + + <!-- JSON Update Request Handler + http://wiki.apache.org/solr/UpdateJSON + --> + <requestHandler name="/update/json" + class="solr.JsonUpdateRequestHandler" + startup="lazy" /> + + <!-- Solr Cell Update Request Handler + + http://wiki.apache.org/solr/ExtractingRequestHandler + + --> + <requestHandler name="/update/extract" + startup="lazy" + class="solr.extraction.ExtractingRequestHandler" > + <lst name="defaults"> + <!-- All the main content goes into "text"... if you need to return + the extracted text or do highlighting, use a stored field. --> + <str name="fmap.content">text</str> + <str name="lowernames">true</str> + <str name="uprefix">ignored_</str> + + <!-- capture link hrefs but ignore div attributes --> + <str name="captureAttr">true</str> + <str name="fmap.a">links</str> + <str name="fmap.div">ignored_</str> + </lst> + </requestHandler> + + <!-- XSLT Update Request Handler + Transforms incoming XML with stylesheet identified by tr= + --> + <requestHandler name="/update/xslt" + startup="lazy" + class="solr.XsltUpdateRequestHandler"/> + + <!-- Field Analysis Request Handler + + RequestHandler that provides much the same functionality as + analysis.jsp. Provides the ability to specify multiple field + types and field names in the same request and outputs + index-time and query-time analysis for each of them. + + Request parameters are: + analysis.fieldname - field name whose analyzers are to be used + + analysis.fieldtype - field type whose analyzers are to be used + analysis.fieldvalue - text for index-time analysis + q (or analysis.q) - text for query time analysis + analysis.showmatch (true|false) - When set to true and when + query analysis is performed, the produced tokens of the + field value analysis will be marked as "matched" for every + token that is produces by the query analysis + --> + <requestHandler name="/analysis/field" + startup="lazy" + class="solr.FieldAnalysisRequestHandler" /> + + + <!-- Document Analysis Handler + + http://wiki.apache.org/solr/AnalysisRequestHandler + + An analysis handler that provides a breakdown of the analysis + process of provided docuemnts. This handler expects a (single) + content stream with the following format: + + <docs> + <doc> + <field name="id">1</field> + <field name="name">The Name</field> + <field name="text">The Text Value</field> + </doc> + <doc>...</doc> + <doc>...</doc> + ... + </docs> + + Note: Each document must contain a field which serves as the + unique key. This key is used in the returned response to associate + an analysis breakdown to the analyzed document. + + Like the FieldAnalysisRequestHandler, this handler also supports + query analysis by sending either an "analysis.query" or "q" + request parameter that holds the query text to be analyzed. It + also supports the "analysis.showmatch" parameter which when set to + true, all field tokens that match the query tokens will be marked + as a "match". + --> + <requestHandler name="/analysis/document" + class="solr.DocumentAnalysisRequestHandler" + startup="lazy" /> + + <!-- Admin Handlers + + Admin Handlers - This will register all the standard admin + RequestHandlers. + --> + <requestHandler name="/admin/" + class="solr.admin.AdminHandlers" /> + <!-- This single handler is equivalent to the following... --> + <!-- + <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" /> + <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" /> + <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" /> + <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" /> + <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" /> + <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" > + --> + <!-- If you wish to hide files under ${solr.home}/conf, explicitly + register the ShowFileRequestHandler using: + --> + <!-- + <requestHandler name="/admin/file" + class="solr.admin.ShowFileRequestHandler" > + <lst name="invariants"> + <str name="hidden">synonyms.txt</str> + <str name="hidden">anotherfile.txt</str> + </lst> + </requestHandler> + --> + + <!-- ping/healthcheck --> + <requestHandler name="/admin/ping" class="solr.PingRequestHandler"> + <lst name="invariants"> + <str name="q">solrpingquery</str> + </lst> + <lst name="defaults"> + <str name="echoParams">all</str> + </lst> + </requestHandler> + + <!-- Echo the request contents back to the client --> + <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" > + <lst name="defaults"> + <str name="echoParams">explicit</str> + <str name="echoHandler">true</str> + </lst> + </requestHandler> + + <!-- Solr Replication + + The SolrReplicationHandler supports replicating indexes from a + "master" used for indexing and "slaves" used for queries. + + http://wiki.apache.org/solr/SolrReplication + + In the example below, remove the <lst name="master"> section if + this is just a slave and remove the <lst name="slave"> section + if this is just a master. + --> + <!-- + <requestHandler name="/replication" class="solr.ReplicationHandler" > + <lst name="master"> + <str name="replicateAfter">commit</str> + <str name="replicateAfter">startup</str> + <str name="confFiles">schema.xml,stopwords.txt</str> + </lst> + <lst name="slave"> + <str name="masterUrl">http://localhost:8983/solr/replication</str> + <str name="pollInterval">00:00:60</str> + </lst> + </requestHandler> + --> + + <!-- Search Components + + Search components are registered to SolrCore and used by + instances of SearchHandler (which can access them by name) + + By default, the following components are available: + + <searchComponent name="query" class="solr.QueryComponent" /> + <searchComponent name="facet" class="solr.FacetComponent" /> + <searchComponent name="mlt" class="solr.MoreLikeThisComponent" /> + <searchComponent name="highlight" class="solr.HighlightComponent" /> + <searchComponent name="stats" class="solr.StatsComponent" /> + <searchComponent name="debug" class="solr.DebugComponent" /> + + Default configuration in a requestHandler would look like: + + <arr name="components"> + <str>query</str> + <str>facet</str> + <str>mlt</str> + <str>highlight</str> + <str>stats</str> + <str>debug</str> + </arr> + + If you register a searchComponent to one of the standard names, + that will be used instead of the default. + + To insert components before or after the 'standard' components, use: + + <arr name="first-components"> + <str>myFirstComponentName</str> + </arr> + + <arr name="last-components"> + <str>myLastComponentName</str> + </arr> + + NOTE: The component registered with the name "debug" will + always be executed after the "last-components" + + --> + + <!-- Spell Check + + The spell check component can return a list of alternative spelling + suggestions. + + http://wiki.apache.org/solr/SpellCheckComponent + --> + <searchComponent name="spellcheck" class="solr.SpellCheckComponent"> + + <str name="queryAnalyzerFieldType">textSpell</str> + + <!-- Multiple "Spell Checkers" can be declared and used by this + component + --> + + <!-- a spellchecker built from a field of the main index, and + written to disk + --> + <lst name="spellchecker"> + <str name="name">default</str> + <str name="field">name</str> + <str name="spellcheckIndexDir">spellchecker</str> + <!-- uncomment this to require terms to occur in 1% of the documents + in order to be included in the dictionary + --> + <!-- + <float name="thresholdTokenFrequency">.01</float> + --> + </lst> + + <!-- a spellchecker that uses a different distance measure --> + <!-- + <lst name="spellchecker"> + <str name="name">jarowinkler</str> + <str name="field">spell</str> + <str name="distanceMeasure"> + org.apache.lucene.search.spell.JaroWinklerDistance + </str> + <str name="spellcheckIndexDir">spellcheckerJaro</str> + </lst> + --> + + <!-- a spellchecker that use an alternate comparator + + comparatorClass be one of: + 1. score (default) + 2. freq (Frequency first, then score) + 3. A fully qualified class name + --> + <!-- + <lst name="spellchecker"> + <str name="name">freq</str> + <str name="field">lowerfilt</str> + <str name="spellcheckIndexDir">spellcheckerFreq</str> + <str name="comparatorClass">freq</str> + <str name="buildOnCommit">true</str> + --> + + <!-- A spellchecker that reads the list of words from a file --> + <!-- + <lst name="spellchecker"> + <str name="classname">solr.FileBasedSpellChecker</str> + <str name="name">file</str> + <str name="sourceLocation">spellings.txt</str> + <str name="characterEncoding">UTF-8</str> + <str name="spellcheckIndexDir">spellcheckerFile</str> + </lst> + --> + </searchComponent> + + <!-- A request handler for demonstrating the spellcheck component. + + NOTE: This is purely as an example. The whole purpose of the + SpellCheckComponent is to hook it into the request handler that + handles your normal user queries so that a separate request is + not needed to get suggestions. + + IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS + NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM! + + See http://wiki.apache.org/solr/SpellCheckComponent for details + on the request parameters. + --> + <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy"> + <lst name="defaults"> + <str name="df">text</str> + <str name="spellcheck.onlyMorePopular">false</str> + <str name="spellcheck.extendedResults">false</str> + <str name="spellcheck.count">1</str> + </lst> + <arr name="last-components"> + <str>spellcheck</str> + </arr> + </requestHandler> + + <!-- Term Vector Component + + http://wiki.apache.org/solr/TermVectorComponent + --> + <searchComponent name="tvComponent" class="solr.TermVectorComponent"/> + + <!-- A request handler for demonstrating the term vector component + + This is purely as an example. + + In reality you will likely want to add the component to your + already specified request handlers. + --> + <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy"> + <lst name="defaults"> + <str name="df">text</str> + <bool name="tv">true</bool> + </lst> + <arr name="last-components"> + <str>tvComponent</str> + </arr> + </requestHandler> + + <!-- Clustering Component + + http://wiki.apache.org/solr/ClusteringComponent + + This relies on third party jars which are notincluded in the + release. To use this component (and the "/clustering" handler) + Those jars will need to be downloaded, and you'll need to set + the solr.cluster.enabled system property when running solr... + + java -Dsolr.clustering.enabled=true -jar start.jar + --> + <searchComponent name="clustering" + enable="${solr.clustering.enabled:false}" + class="solr.clustering.ClusteringComponent" > + <!-- Declare an engine --> + <lst name="engine"> + <!-- The name, only one can be named "default" --> + <str name="name">default</str> + + <!-- Class name of Carrot2 clustering algorithm. + + Currently available algorithms are: + + * org.carrot2.clustering.lingo.LingoClusteringAlgorithm + * org.carrot2.clustering.stc.STCClusteringAlgorithm + * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm + + See http://project.carrot2.org/algorithms.html for the + algorithm's characteristics. + --> + <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str> + + <!-- Overriding values for Carrot2 default algorithm attributes. + + For a description of all available attributes, see: + http://download.carrot2.org/stable/manual/#chapter.components. + Use attribute key as name attribute of str elements + below. These can be further overridden for individual + requests by specifying attribute key as request parameter + name and attribute value as parameter value. + --> + <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str> + + <!-- Location of Carrot2 lexical resources. + + A directory from which to load Carrot2-specific stop words + and stop labels. Absolute or relative to Solr config directory. + If a specific resource (e.g. stopwords.en) is present in the + specified dir, it will completely override the corresponding + default one that ships with Carrot2. + + For an overview of Carrot2 lexical resources, see: + http://download.carrot2.org/head/manual/#chapter.lexical-resources + --> + <str name="carrot.lexicalResourcesDir">clustering/carrot2</str> + + <!-- The language to assume for the documents. + + For a list of allowed values, see: + http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage + --> + <str name="MultilingualClustering.defaultLanguage">ENGLISH</str> + </lst> + <lst name="engine"> + <str name="name">stc</str> + <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str> + </lst> + </searchComponent> + + <!-- A request handler for demonstrating the clustering component + + This is purely as an example. + + In reality you will likely want to add the component to your + already specified request handlers. + --> + <requestHandler name="/clustering" + startup="lazy" + enable="${solr.clustering.enabled:false}" + class="solr.SearchHandler"> + <lst name="defaults"> + <bool name="clustering">true</bool> + <str name="clustering.engine">default</str> + <bool name="clustering.results">true</bool> + <!-- The title field --> + <str name="carrot.title">name</str> + <str name="carrot.url">id</str> + <!-- The field to cluster on --> + <str name="carrot.snippet">features</str> + <!-- produce summaries --> + <bool name="carrot.produceSummary">true</bool> + <!-- the maximum number of labels per cluster --> + <!--<int name="carrot.numDescriptions">5</int>--> + <!-- produce sub clusters --> + <bool name="carrot.outputSubClusters">false</bool> + + <str name="df">text</str> + <str name="defType">edismax</str> + <str name="qf"> + text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4 + </str> + <str name="q.alt">*:*</str> + <str name="rows">10</str> + <str name="fl">*,score</str> + </lst> + <arr name="last-components"> + <str>clustering</str> + </arr> + </requestHandler> + + <!-- Terms Component + + http://wiki.apache.org/solr/TermsComponent + + A component to return terms and document frequency of those + terms + --> + <searchComponent name="terms" class="solr.TermsComponent"/> + + <!-- A request handler for demonstrating the terms component --> + <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy"> + <lst name="defaults"> + <bool name="terms">true</bool> + </lst> + <arr name="components"> + <str>terms</str> + </arr> + </requestHandler> + + + <!-- Query Elevation Component + + http://wiki.apache.org/solr/QueryElevationComponent + + a search component that enables you to configure the top + results for a given query regardless of the normal lucene + scoring. + --> + <searchComponent name="elevator" class="solr.QueryElevationComponent" > + <!-- pick a fieldType to analyze queries --> + <str name="queryFieldType">string</str> + <str name="config-file">elevate.xml</str> + </searchComponent> + + <!-- A request handler for demonstrating the elevator component --> + <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy"> + <lst name="defaults"> + <str name="echoParams">explicit</str> + <str name="df">text</str> + </lst> + <arr name="last-components"> + <str>elevator</str> + </arr> + </requestHandler> + + <!-- More Like This --> + <requestHandler name="/mlt" class="solr.MoreLikeThisHandler" /> + + <!-- Highlighting Component + + http://wiki.apache.org/solr/HighlightingParameters + --> + <searchComponent class="solr.HighlightComponent" name="highlight"> + <highlighting> + <!-- Configure the standard fragmenter --> + <!-- This could most likely be commented out in the "default" case --> + <fragmenter name="gap" + default="true" + class="solr.highlight.GapFragmenter"> + <lst name="defaults"> + <int name="hl.fragsize">100</int> + </lst> + </fragmenter> + + <!-- A regular-expression-based fragmenter + (for sentence extraction) + --> + <fragmenter name="regex" + class="solr.highlight.RegexFragmenter"> + <lst name="defaults"> + <!-- slightly smaller fragsizes work better because of slop --> + <int name="hl.fragsize">70</int> + <!-- allow 50% slop on fragment sizes --> + <float name="hl.regex.slop">0.5</float> + <!-- a basic sentence pattern --> + <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str> + </lst> + </fragmenter> + + <!-- Configure the standard formatter --> + <formatter name="html" + default="true" + class="solr.highlight.HtmlFormatter"> + <lst name="defaults"> + <str name="hl.simple.pre"><![CDATA[<em>]]></str> + <str name="hl.simple.post"><![CDATA[</em>]]></str> + </lst> + </formatter> + + <!-- Configure the standard encoder --> + <encoder name="html" + class="solr.highlight.HtmlEncoder" /> + + <!-- Configure the standard fragListBuilder --> + <fragListBuilder name="simple" + default="true" + class="solr.highlight.SimpleFragListBuilder"/> + + <!-- Configure the single fragListBuilder --> + <fragListBuilder name="single" + class="solr.highlight.SingleFragListBuilder"/> + + <!-- default tag FragmentsBuilder --> + <fragmentsBuilder name="default" + default="true" + class="solr.highlight.ScoreOrderFragmentsBuilder"> + <!-- + <lst name="defaults"> + <str name="hl.multiValuedSeparatorChar">/</str> + </lst> + --> + </fragmentsBuilder> + + <!-- multi-colored tag FragmentsBuilder --> + <fragmentsBuilder name="colored" + class="solr.highlight.ScoreOrderFragmentsBuilder"> + <lst name="defaults"> + <str name="hl.tag.pre"><![CDATA[ + <b style="background:yellow">,<b style="background:lawgreen">, + <b style="background:aquamarine">,<b style="background:magenta">, + <b style="background:palegreen">,<b style="background:coral">, + <b style="background:wheat">,<b style="background:khaki">, + <b style="background:lime">,<b style="background:deepskyblue">]]></str> + <str name="hl.tag.post"><![CDATA[</b>]]></str> + </lst> + </fragmentsBuilder> + + <boundaryScanner name="default" + default="true" + class="solr.highlight.SimpleBoundaryScanner"> + <lst name="defaults"> + <str name="hl.bs.maxScan">10</str> + <str name="hl.bs.chars">.,!? 	 </str> + </lst> + </boundaryScanner> + + <boundaryScanner name="breakIterator" + class="solr.highlight.BreakIteratorBoundaryScanner"> + <lst name="defaults"> + <!-- type should be one of: + * CHARACTER + * WORD (default) + * LINE + * SENTENCE + --> + <str name="hl.bs.type">WORD</str> + <!-- language and country are used when constructing Locale + object which will be used when getting instance of + BreakIterator + --> + <str name="hl.bs.language">en</str> + <str name="hl.bs.country">US</str> + </lst> + </boundaryScanner> + </highlighting> + </searchComponent> + + <!-- Update Processors + + Chains of Update Processor Factories for dealing with Update + Requests can be declared, and then used by name in Update + Request Processors + + http://wiki.apache.org/solr/UpdateRequestProcessor + + --> + <!-- Deduplication + + An example dedup update processor that creates the "id" field + on the fly based on the hash code of some other fields. This + example has overwriteDupes set to false since we are using the + id field as the signatureField and Solr will maintain + uniqueness based on that anyway. + + --> + <!-- + <updateRequestProcessorChain name="dedupe"> + <processor class="solr.processor.SignatureUpdateProcessorFactory"> + <bool name="enabled">true</bool> + <str name="signatureField">id</str> + <bool name="overwriteDupes">false</bool> + <str name="fields">name,features,cat</str> + <str name="signatureClass">solr.processor.Lookup3Signature</str> + </processor> + <processor class="solr.LogUpdateProcessorFactory" /> + <processor class="solr.RunUpdateProcessorFactory" /> + </updateRequestProcessorChain> + --> + + <!-- + This example update chain identifies the language of the incoming + documents using the langid contrib. The detected language is + written to field language_s. No field name mapping is done. + The fields used for detection are text, title, subject and description, + making this example suitable for detecting languages form full-text + rich documents injected via ExtractingRequestHandler. + See more about langId at http://wiki.apache.org/solr/LanguageDetection + --> + <!-- + <updateRequestProcessorChain name="langid"> + <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory"> + <str name="langid.fl">text,title,subject,description</str> + <str name="langid.langField">language_s</str> + <str name="langid.fallback">en</str> + </processor> + <processor class="solr.LogUpdateProcessorFactory" /> + <processor class="solr.RunUpdateProcessorFactory" /> + </updateRequestProcessorChain> + --> + + <!-- Response Writers + + http://wiki.apache.org/solr/QueryResponseWriter + + Request responses will be written using the writer specified by + the 'wt' request parameter matching the name of a registered + writer. + + The "default" writer is the default and will be used if 'wt' is + not specified in the request. + --> + <!-- The following response writers are implicitly configured unless + overridden... + --> + <!-- + <queryResponseWriter name="xml" + default="true" + class="solr.XMLResponseWriter" /> + <queryResponseWriter name="json" class="solr.JSONResponseWriter"/> + <queryResponseWriter name="python" class="solr.PythonResponseWriter"/> + <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/> + <queryResponseWriter name="php" class="solr.PHPResponseWriter"/> + <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/> + <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/> + --> + + <queryResponseWriter name="json" class="solr.JSONResponseWriter"> + <!-- For the purposes of the tutorial, JSON responses are written as + plain text so that they are easy to read in *any* browser. + If you expect a MIME type of "application/json" just remove this override. + --> + <str name="content-type">text/plain; charset=UTF-8</str> + </queryResponseWriter> + + <!-- + Custom response writers can be declared as needed... + --> + <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/> + + + <!-- XSLT response writer transforms the XML output by any xslt file found + in Solr's conf/xslt directory. Changes to xslt files are checked for + every xsltCacheLifetimeSeconds. + --> + <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter"> + <int name="xsltCacheLifetimeSeconds">5</int> + </queryResponseWriter> + + <!-- Query Parsers + + http://wiki.apache.org/solr/SolrQuerySyntax + + Multiple QParserPlugins can be registered by name, and then + used in either the "defType" param for the QueryComponent (used + by SearchHandler) or in LocalParams + --> + <!-- example of registering a query parser --> + <!-- + <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/> + --> + + <!-- Function Parsers + + http://wiki.apache.org/solr/FunctionQuery + + Multiple ValueSourceParsers can be registered by name, and then + used as function names when using the "func" QParser. + --> + <!-- example of registering a custom function parser --> + <!-- + <valueSourceParser name="myfunc" + class="com.mycompany.MyValueSourceParser" /> + --> + + <!-- Legacy config for the admin interface --> + <admin> + <defaultQuery>*:*</defaultQuery> + + <!-- configure a healthcheck file for servers behind a + loadbalancer + --> + <!-- + <healthcheck type="file">server-enabled</healthcheck> + --> + </admin> + +</config> diff --git a/isuifang_solr/solr/conf/spellings.txt b/isuifang_solr/solr/conf/spellings.txt new file mode 100644 index 0000000..d7ede6f --- /dev/null +++ b/isuifang_solr/solr/conf/spellings.txt @@ -0,0 +1,2 @@ +pizza +history
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/stopwords.dic b/isuifang_solr/solr/conf/stopwords.dic new file mode 100644 index 0000000..72d3f13 --- /dev/null +++ b/isuifang_solr/solr/conf/stopwords.dic @@ -0,0 +1,37 @@ +a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
+是
+的
+了
+
diff --git a/isuifang_solr/solr/conf/stopwords.txt b/isuifang_solr/solr/conf/stopwords.txt new file mode 100644 index 0000000..ae1e83e --- /dev/null +++ b/isuifang_solr/solr/conf/stopwords.txt @@ -0,0 +1,14 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. diff --git a/isuifang_solr/solr/conf/stopwords_en.txt b/isuifang_solr/solr/conf/stopwords_en.txt new file mode 100644 index 0000000..ae1e83e --- /dev/null +++ b/isuifang_solr/solr/conf/stopwords_en.txt @@ -0,0 +1,14 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. diff --git a/isuifang_solr/solr/conf/synonyms.txt b/isuifang_solr/solr/conf/synonyms.txt new file mode 100644 index 0000000..d059915 --- /dev/null +++ b/isuifang_solr/solr/conf/synonyms.txt @@ -0,0 +1,52 @@ +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +#----------------------------------------------------------------------- +#some test synonym mappings unlikely to appear in real input text +aaafoo => aaabar +bbbfoo => bbbfoo bbbbar +cccfoo => cccbar cccbaz +fooaaa,baraaa,bazaaa + +# Some synonym groups specific to this example +GB,gib,gigabyte,gigabytes +MB,mib,megabyte,megabytes +Television, Televisions, TV, TVs +#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming +#after us won't split it into two words. + +# Synonym mappings can be used for spelling correction too +pixima => pixma + +a\,a => b\,b + +# synonyms.txt +# this is a comment +乙肝,乙型肝炎,慢乙肝,慢性乙肝,CHB +HBeAg,e抗原 +HBsAg,表面抗原 +病毒,HBV +干扰素,派罗欣,佩乐能 +大三阳,e抗原阳性 +小三阳,e抗原阴性 +两对半,e抗原,e抗体,表面抗原,表面抗体,核心抗体 +谷丙转氨酶,ALT +基线,初始,治疗前 +疗效,治愈,治好,应答 +机会,几率,概率,占比 +医院,临床 +报道,研究,调查,实验,试验 ++,阳性 +含量,载量,水平 +反复,复发,反跳,反弹 +核苷类似物,NA,核苷类药物 +停药,治疗结束 diff --git a/isuifang_solr/solr/conf/velocity/VM_global_library.vm b/isuifang_solr/solr/conf/velocity/VM_global_library.vm new file mode 100644 index 0000000..3dd880c --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/VM_global_library.vm @@ -0,0 +1,161 @@ + +#macro(param $key)$request.params.get($key)#end + +#macro(url_for_solr)/solr#if($request.core.name != "")/$request.core.name#end#end +#macro(url_for_home)#url_for_solr/browse#end + +#macro(q)&q=$!{esc.url($params.get('q'))}#end + +#macro(fqs $p)#foreach($fq in $p)#if($velocityCount>1)&#{end}fq=$esc.url($fq)#end#end + +#macro(debug)#if($request.params.get('debugQuery'))&debugQuery=true#end#end + +#macro(boostPrice)#if($request.params.get('bf') == 'price')&bf=price#end#end + +#macro(annotate)#if($request.params.get('annotateBrowse'))&annotateBrowse=true#end#end + +#macro(annTitle $msg)#if($annotate == true)title="$msg"#end#end + +#macro(spatial)#if($request.params.get('sfield'))&sfield=store#end#if($request.params.get('pt'))&pt=$request.params.get('pt')#end#if($request.params.get('d'))&d=$request.params.get('d')#end#end + +#macro(qOpts)#set($queryOpts = $request.params.get("queryOpts"))#if($queryOpts && $queryOpts != "")&queryOpts=$queryOpts#end#end + +#macro(group)#if($request.params.getBool("group") == true)&group=true#end#if($request.params.get("group.field"))#foreach($grp in $request.params.getParams('group.field'))&group.field=$grp#end#end#end + +#macro(lensNoQ)?#if($request.params.getParams('fq') and $list.size($request.params.getParams('fq')) > 0)&#fqs($request.params.getParams('fq'))#end#debug#boostPrice#annotate#spatial#qOpts#group#end +#macro(lens)#lensNoQ#q#end + + +#macro(url_for_lens)#{url_for_home}#lens#end + +#macro(url_for_start $start)#url_for_home#lens&start=$start#end + +#macro(url_for_filters $p)#url_for_home?#q#boostPrice#spatial#qOpts#if($list.size($p) > 0)&#fqs($p)#end#debug#end + + +#macro(url_for_nested_facet_query $field)#url_for_home#lens&fq=$esc.url($field)#end + +## TODO: convert to use {!raw f=$field}$value (with escaping of course) +#macro(url_for_facet_filter $field $value)#url_for_home#lens&fq=$esc.url($field):%22$esc.url($value)%22#end + +#macro(url_for_facet_date_filter $field $value)#url_for_home#lens&fq=$esc.url($field):$esc.url($value)#end + +#macro(url_for_facet_range_filter $field $value)#url_for_home#lens&fq=$esc.url($field):$esc.url($value)#end + + +#macro(link_to_previous_page $text) + #if($page.current_page_number > 1) + #set($prev_start = $page.start - $page.results_per_page) + <a class="prev-page" href="#url_for_start($prev_start)">$text</a> + #end +#end + +#macro(link_to_next_page $text) + #if($page.current_page_number < $page.page_count) + #set($next_start = $page.start + $page.results_per_page) + <a class="next-page" href="#url_for_start($next_start)">$text</a> + #end +#end + +#macro(link_to_page $page_number $text) + #if($page_number == $page.current_page_number) + $text + #else + #if($page_number <= $page.page_count) + #set($page_start = $page_number * $page.results_per_page - $page.results_per_page) + <a class="page" href="#url_for_start($page_start)">$text</a> + #end + #end +#end + +#macro(display_facet_query $field, $display, $fieldName) + #if($field.size() > 0) + <span class="facet-field">$display</span> + <ul> + #foreach ($facet in $field) + #if ($facet.value > 0) + #set($facetURL = "#url_for_nested_facet_query($facet.key)") + #if ($facetURL != '') + <li><a href="$facetURL">$facet.key</a> ($facet.value)</li> + #end + #end + #end + </ul> + #end +#end + + +#macro(display_facet_range $field, $display, $fieldName, $start, $end, $gap, $before, $after) + <span class="facet-field">$display</span> + <ul> + #if($before && $before != "") + #set($value = "[* TO " + "#format_value($start)" + "]") + #set($facetURL = "#url_for_facet_range_filter($fieldName, $value)") + <li><a href="$facetURL">Less than #format_value($start)</a> ($before)</li> + #end + #foreach ($facet in $field) + #set($rangeEnd = "#range_get_to_value($facet.key, $gap)") + #set($value = "[" + $facet.key + " TO " + $rangeEnd + "]") + #set($facetURL = "#url_for_facet_range_filter($fieldName, $value)") + #if ($facetURL != '') + <li><a href="$facetURL">$facet.key - #format_value($rangeEnd)</a> ($facet.value)</li> + #end + #end + #if($end && $end != "" && $after > 0) + #set($value = "[" + "#format_value($end)" + " TO *]") + #set($facetURL = "#url_for_facet_range_filter($fieldName, $value)") + <li><a href="$facetURL">More than #format_value($end)</a> ($after)</li> + #end + </ul> +#end + +## $pivots is a list of facet_pivot +#macro(display_facet_pivot $pivots, $display) + #if($pivots.size() > 0) + <span class="facet-field">$display</span> + <ul> + #foreach ($pivot in $pivots) + #foreach ($entry in $pivot.value) + <a href="#url_for_facet_filter($entry.field, $entry.value)">$entry.field::$entry.value</a> ($entry.count) + <ul> + #foreach($nest in $entry.pivot) + <a href="#url_for_facet_filter($entry.field, $entry.value)&fq=$esc.url($nest.field):%22$esc.url($nest.value)%22">$nest.field::$nest.value</a> ($nest.count) + #end + </ul> + #end + #end + </ul> + #end +#end + +#macro(field $f) + #if($response.response.highlighting.get($docId).get($f).get(0)) + $!response.response.highlighting.get($docId).get($f).get(0) + #else + #foreach($v in $doc.getFieldValues($f)) + $v + #end + #end +#end + +#macro(utc_date $theDate) +$date.format("yyyy-MM-dd'T'HH:mm:ss'Z'",$theDate,$date.getLocale(),$date.getTimeZone().getTimeZone("UTC"))## +#end + +#macro(format_value $val) +#if(${val.class.name} == "java.util.Date") +#utc_date($val)## +#else +$val## +#end +#end + +#macro(range_get_to_value $inval, $gapval) +#if(${gapval.class.name} == "java.lang.String") +$inval$gapval## +#elseif(${gapval.class.name} == "java.lang.Float" || ${inval.class.name} == "java.lang.Float") +$math.toDouble($math.add($inval,$gapval))## +#else +$math.add($inval,$gapval)## +#end +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/browse.vm b/isuifang_solr/solr/conf/velocity/browse.vm new file mode 100644 index 0000000..d7c3c43 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/browse.vm @@ -0,0 +1,45 @@ +#set($searcher=$request.searcher) +#set($params=$request.params) +#set($clusters = $response.response.clusters) +#set($mltResults = $response.response.get("moreLikeThis")) +#set($annotate = $params.get("annotateBrowse")) +#parse('query.vm') +#if($response.response.spellcheck.suggestions and $response.response.spellcheck.suggestions.size() > 0) + Did you mean <a href="#url_for_home?q=$esc.url($response.response.spellcheck.suggestions.collation)#if($list.size($request.params.getParams('fq')) > 0)&#fqs($request.params.getParams('fq'))#end#debug">$response.response.spellcheck.suggestions.collation</a>? +#end + +<div class="navigators"> + #parse("facets.vm") +</div> + +<div class="pagination"> + #if($response.response.get('grouped')) + <span><span class="results-found">$response.response.get('grouped').size() group(s)</span> found in ${response.responseHeader.QTime} ms</span> + #else<span><span class="results-found">$page.results_found</span> results found in ${response.responseHeader.QTime} ms</span> + Page <span class="page-num">$page.current_page_number</span> of <span + class="page-count">$page.page_count</span>#end +</div> + +<div class="results"> + #if($response.response.get('grouped')) + #foreach($grouping in $response.response.get('grouped')) + #parse("hitGrouped.vm") + #end + #else + #foreach($doc in $response.results) + #parse("hit.vm") + #end + #end +</div> + +<div class="pagination"> + #if($response.response.get('grouped')) + #else + #link_to_previous_page("previous") + <span class="results-found">$page.results_found</span> results found. + Page <span class="page-num">$page.current_page_number</span> of <span + class="page-count">$page.page_count</span> + #link_to_next_page("next") + #end + <br/> +</div> diff --git a/isuifang_solr/solr/conf/velocity/cluster.vm b/isuifang_solr/solr/conf/velocity/cluster.vm new file mode 100644 index 0000000..bbe75cf --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/cluster.vm @@ -0,0 +1,26 @@ +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + --> + +<h2 #annTitle("Clusters generated by Carrot2 using the /clustering RequestHandler")>Clusters</h2> +<div id="clusters"> + Run Solr with java -Dsolr.clustering.enabled=true -jar start.jar to see results +</div> +<script type="text/javascript"> + + $('#clusters').load("#url_for_solr/clustering#lens", + {'wt':'velocity', 'v.template':"clusterResults"}); +</script> diff --git a/isuifang_solr/solr/conf/velocity/clusterResults.vm b/isuifang_solr/solr/conf/velocity/clusterResults.vm new file mode 100644 index 0000000..618ebf8 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/clusterResults.vm @@ -0,0 +1,29 @@ +#foreach ($clusters in $response.response.clusters) + #set($labels = $clusters.get('labels')) + #set($docs = $clusters.get('docs')) + <!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + --> + +<h3>#foreach ($label in $labels)$label#if( $foreach.hasNext ),#end#end</h3> + <ol> + #foreach ($cluDoc in $docs) + <li><a href="#url_for_home?q=id:$cluDoc">$cluDoc</a></li> + #end + </ol> + + +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/doc.vm b/isuifang_solr/solr/conf/velocity/doc.vm new file mode 100644 index 0000000..7da97cb --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/doc.vm @@ -0,0 +1,42 @@ +<div class="result-title"><b>#field('name')</b><span class="mlt">#if($params.getBool('mlt', false) == false)<a href="#lensNoQ&q=id:$docId&mlt=true">More Like This</a>#end</span></div> +##do we have a physical store for this product +#set($store = $doc.getFieldValue('store')) +#if($store)<div class="map"><img src="http://maps.google.com/maps/api/staticmap?&zoom=12&size=150x80&maptype=roadmap&markers=$doc.getFieldValue('store')&sensor=false" /><div><small><a target="_map" href="http://maps.google.com/?q=$store&source=embed">Larger Map</a></small></div></div>#end +<div>Price: #field('price_c')</div> +<div>Features: #field('features')</div> +<div>In Stock: #field('inStock')</div> +<div class="mlt"> + #set($mlt = $mltResults.get($docId)) + #set($mltOn = $params.getBool('mlt')) + #if($mltOn == true)<div class="field-name">Similar Items</div>#end + #if ($mltOn && $mlt && $mlt.size() > 0) + <ul> + #foreach($mltHit in $mlt) + #set($mltId = $mltHit.getFieldValue('id')) + <li><div><a href="#url_for_home?q=id:$mltId">$mltId</a></div><div><span class="field-name">Name:</span> $mltHit.getFieldValue('name')</div> + <div><span class="field-name">Price:</span> $!number.currency($mltHit.getFieldValue('price')) <span class="field-name">In Stock:</span> $mltHit.getFieldValue('inStock')</div> + + </li> + #end + </ul> + #elseif($mltOn && $mlt.size() == 0) + <div>No Similar Items Found</div> + #end +</div> +#if($params.getBool("debugQuery",false)) + <a href="#" onclick='jQuery(this).siblings("pre").toggle(); return false;'>toggle explain</a> + <pre style="display:none">$response.getExplainMap().get($doc.getFirstValue('id'))</pre> + <a href="#" onclick='jQuery(this).siblings("pre2").toggle(); return false;'>toggle all fields</a> + <pre2 style="display:none"> + #foreach($fieldname in $doc.fieldNames) + <br> + <span class="field-name">$fieldname :</span> + <span> + #foreach($value in $doc.getFieldValues($fieldname)) + $value + #end + </span> + #end + </br> + </pre2> +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/facet_fields.vm b/isuifang_solr/solr/conf/velocity/facet_fields.vm new file mode 100644 index 0000000..91c50be --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/facet_fields.vm @@ -0,0 +1,12 @@ +#if($response.facetFields) + <h2 #annTitle("Facets generated by adding &facet.field= to the request")>Field Facets</h2> + #foreach($field in $response.facetFields) + <span class="facet-field">$field.name</span> + + <ul> + #foreach($facet in $field.values) + <li><a href="#url_for_facet_filter($field.name, $facet.name)">$facet.name</a> ($facet.count)</li> + #end + </ul> + #end + #end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/facet_queries.vm b/isuifang_solr/solr/conf/velocity/facet_queries.vm new file mode 100644 index 0000000..2ac65d6 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/facet_queries.vm @@ -0,0 +1,3 @@ +#set($field = $response.response.facet_counts.facet_queries) +<h2 #annTitle("Facets generated by adding &facet.query= to the request")>Query Facets</h2> +#display_facet_query($field, "", "")
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/facet_ranges.vm b/isuifang_solr/solr/conf/velocity/facet_ranges.vm new file mode 100644 index 0000000..8d26294 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/facet_ranges.vm @@ -0,0 +1,12 @@ +<h2 #annTitle("Facets generated by adding &facet.range= to the request")>Range Facets</h2> +#foreach ($field in $response.response.facet_counts.facet_ranges) + #set($name = $field.key) + #set($display = "$name") + #set($f = $field.value.counts) + #set($start = $field.value.start) + #set($end = $field.value.end) + #set($gap = $field.value.gap) + #set($before = $field.value.before) + #set($after = $field.value.after) + #display_facet_range($f, $display, $name, $start, $end, $gap, $before, $after) +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/facets.vm b/isuifang_solr/solr/conf/velocity/facets.vm new file mode 100644 index 0000000..5f538f2 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/facets.vm @@ -0,0 +1,7 @@ +#parse('facet_fields.vm') +#parse('facet_queries.vm') +#parse('facet_ranges.vm') +#parse('cluster.vm') + + + diff --git a/isuifang_solr/solr/conf/velocity/footer.vm b/isuifang_solr/solr/conf/velocity/footer.vm new file mode 100644 index 0000000..b55e8a5 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/footer.vm @@ -0,0 +1,17 @@ +<hr/> +<div> + <span>Options:</span> + #if($request.params.get('debugQuery')) + <a href="#url_for_home?#q#if($list.size($request.params.getParams('fq')) > 0)&#fqs($request.params.getParams('fq'))#end">disable debug</a> + #else + <a href="#url_for_lens&debugQuery=true&fl=*,score">enable debug</a> + #end + #if($annotate) + <a href="#url_for_home?#q#if($list.size($request.params.getParams('fq')) > 0)&#fqs($request.params.getParams('fq'))#end#boostPrice">disable annotation</a> + #else + <a href="#url_for_lens&annotateBrowse=true">enable annotation</a> + #end + <a #annTitle("Click to switch to an XML response: &wt=xml") href="#url_for_lens&wt=xml#if($request.params.get('debugQuery'))&debugQuery=true#end">XML</a></div> +<div>Generated by <a href="http://wiki.apache.org/solr/VelocityResponseWriter">VelocityResponseWriter</a></div> +<div><span>Documentation: </span> <a href="http://lucene.apache.org/solr">Solr Home Page</a>, <a href="http://wiki.apache.org/solr">Solr Wiki</a></div> +<div>Disclaimer: The locations displayed in this demonstration are purely fictional. It is more than likely that no store with the items listed actually exists at that location!</div>
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/head.vm b/isuifang_solr/solr/conf/velocity/head.vm new file mode 100644 index 0000000..30c961c --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/head.vm @@ -0,0 +1,45 @@ + + ## An example of using an arbitrary request parameter + <!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + --> + +<title>#param('title')</title> + <meta http-equiv="content-type" content="text/html; charset=UTF-8"/> + +<script type="text/javascript" src="#{url_for_solr}/admin/jquery-1.4.3.min.js"></script> + <link rel="stylesheet" type="text/css" href="#{url_for_solr}/admin/file?file=/velocity/main.css&contentType=text/css"/> + <link rel="stylesheet" href="#{url_for_solr}/admin/file?file=/velocity/jquery.autocomplete.css&contentType=text/css" type="text/css" /> + <script type="text/javascript" src="#{url_for_solr}/admin/file?file=/velocity/jquery.autocomplete.js&contentType=text/javascript"></script> + + + <script> + $(document).ready(function(){ + $("\#q").autocomplete('#{url_for_solr}/terms', { ## backslash escaped #q as that is a macro defined in VM_global_library.vm + extraParams:{ + 'terms.prefix': function() { return $("\#q").val();}, + 'terms.sort': 'count', + 'terms.fl': 'name', + 'wt': 'velocity', + 'v.template': 'suggest' + } + } + ); + + // http://localhost:8983/solr/terms?terms.fl=name&terms.prefix=i&terms.sort=count + }); + + </script>
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/header.vm b/isuifang_solr/solr/conf/velocity/header.vm new file mode 100644 index 0000000..15c3870 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/header.vm @@ -0,0 +1,3 @@ +<div id="head"> + <span ><a href="#url_for_home#if($request.params.get('debugQuery'))?debugQuery=true#end"><img src="#{url_for_solr}/admin/solr_small.png" id="logo"/></a></span> +</div>
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/hit.vm b/isuifang_solr/solr/conf/velocity/hit.vm new file mode 100644 index 0000000..5cd4fe8 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/hit.vm @@ -0,0 +1,5 @@ +#set($docId = $doc.getFieldValue('id')) + +<div class="result-document"> + #parse("doc.vm") +</div> diff --git a/isuifang_solr/solr/conf/velocity/hitGrouped.vm b/isuifang_solr/solr/conf/velocity/hitGrouped.vm new file mode 100644 index 0000000..c3cccf4 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/hitGrouped.vm @@ -0,0 +1,18 @@ +<div class="result-document"> + <div class="result-title"><b>$grouping.key</b></div> + <div>Total Matches in Group: $grouping.value.matches</div> + <div>#foreach ($group in $grouping.value.groups) + <div class="group-value">$group.groupValue <span #annTitle("The count of the number of documents in this group")>($group.doclist.numFound)</span></div> + <div class="group-doclist" #annTitle("Contains the top scoring documents in the group")> + #foreach ($doc in $group.doclist) + #set($docId = $doc.getFieldValue('id')) + #parse("doc.vm") + #end + </div> + #end</div> + </div> + #if($params.getBool("debugQuery",false)) + <a href="#" onclick='jQuery(this).siblings("pre").toggle(); return false;'>toggle explain</a> + <pre style="display:none">$response.getExplainMap().get($doc.getFirstValue('id'))</pre> + #end +</div> diff --git a/isuifang_solr/solr/conf/velocity/jquery.autocomplete.css b/isuifang_solr/solr/conf/velocity/jquery.autocomplete.css new file mode 100644 index 0000000..91b6228 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/jquery.autocomplete.css @@ -0,0 +1,48 @@ +.ac_results { + padding: 0px; + border: 1px solid black; + background-color: white; + overflow: hidden; + z-index: 99999; +} + +.ac_results ul { + width: 100%; + list-style-position: outside; + list-style: none; + padding: 0; + margin: 0; +} + +.ac_results li { + margin: 0px; + padding: 2px 5px; + cursor: default; + display: block; + /* + if width will be 100% horizontal scrollbar will apear + when scroll mode will be used + */ + /*width: 100%;*/ + font: menu; + font-size: 12px; + /* + it is very important, if line-height not setted or setted + in relative units scroll will be broken in firefox + */ + line-height: 16px; + overflow: hidden; +} + +.ac_loading { + background: white url('indicator.gif') right center no-repeat; +} + +.ac_odd { + background-color: #eee; +} + +.ac_over { + background-color: #0A246A; + color: white; +} diff --git a/isuifang_solr/solr/conf/velocity/jquery.autocomplete.js b/isuifang_solr/solr/conf/velocity/jquery.autocomplete.js new file mode 100644 index 0000000..f1b2642 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/jquery.autocomplete.js @@ -0,0 +1,762 @@ +/* + * Autocomplete - jQuery plugin 1.1pre + * + * Copyright (c) 2007 Dylan Verheul, Dan G. Switzer, Anjesh Tuladhar, Jörn Zaefferer + * + * Dual licensed under the MIT and GPL licenses: + * http://www.opensource.org/licenses/mit-license.php + * http://www.gnu.org/licenses/gpl.html + * + * Revision: $Id: jquery.autocomplete.js 5785 2008-07-12 10:37:33Z joern.zaefferer $ + * + */ + +;(function($) { + +$.fn.extend({ + autocomplete: function(urlOrData, options) { + var isUrl = typeof urlOrData == "string"; + options = $.extend({}, $.Autocompleter.defaults, { + url: isUrl ? urlOrData : null, + data: isUrl ? null : urlOrData, + delay: isUrl ? $.Autocompleter.defaults.delay : 10, + max: options && !options.scroll ? 10 : 150 + }, options); + + // if highlight is set to false, replace it with a do-nothing function + options.highlight = options.highlight || function(value) { return value; }; + + // if the formatMatch option is not specified, then use formatItem for backwards compatibility + options.formatMatch = options.formatMatch || options.formatItem; + + return this.each(function() { + new $.Autocompleter(this, options); + }); + }, + result: function(handler) { + return this.bind("result", handler); + }, + search: function(handler) { + return this.trigger("search", [handler]); + }, + flushCache: function() { + return this.trigger("flushCache"); + }, + setOptions: function(options){ + return this.trigger("setOptions", [options]); + }, + unautocomplete: function() { + return this.trigger("unautocomplete"); + } +}); + +$.Autocompleter = function(input, options) { + + var KEY = { + UP: 38, + DOWN: 40, + DEL: 46, + TAB: 9, + RETURN: 13, + ESC: 27, + COMMA: 188, + PAGEUP: 33, + PAGEDOWN: 34, + BACKSPACE: 8 + }; + + // Create $ object for input element + var $input = $(input).attr("autocomplete", "off").addClass(options.inputClass); + + var timeout; + var previousValue = ""; + var cache = $.Autocompleter.Cache(options); + var hasFocus = 0; + var lastKeyPressCode; + var config = { + mouseDownOnSelect: false + }; + var select = $.Autocompleter.Select(options, input, selectCurrent, config); + + var blockSubmit; + + // prevent form submit in opera when selecting with return key + $.browser.opera && $(input.form).bind("submit.autocomplete", function() { + if (blockSubmit) { + blockSubmit = false; + return false; + } + }); + + // only opera doesn't trigger keydown multiple times while pressed, others don't work with keypress at all + $input.bind(($.browser.opera ? "keypress" : "keydown") + ".autocomplete", function(event) { + // track last key pressed + lastKeyPressCode = event.keyCode; + switch(event.keyCode) { + + case KEY.UP: + event.preventDefault(); + if ( select.visible() ) { + select.prev(); + } else { + onChange(0, true); + } + break; + + case KEY.DOWN: + event.preventDefault(); + if ( select.visible() ) { + select.next(); + } else { + onChange(0, true); + } + break; + + case KEY.PAGEUP: + event.preventDefault(); + if ( select.visible() ) { + select.pageUp(); + } else { + onChange(0, true); + } + break; + + case KEY.PAGEDOWN: + event.preventDefault(); + if ( select.visible() ) { + select.pageDown(); + } else { + onChange(0, true); + } + break; + + // matches also semicolon + case options.multiple && $.trim(options.multipleSeparator) == "," && KEY.COMMA: + case KEY.TAB: + case KEY.RETURN: + if( selectCurrent() ) { + // stop default to prevent a form submit, Opera needs special handling + event.preventDefault(); + blockSubmit = true; + return false; + } + break; + + case KEY.ESC: + select.hide(); + break; + + default: + clearTimeout(timeout); + timeout = setTimeout(onChange, options.delay); + break; + } + }).focus(function(){ + // track whether the field has focus, we shouldn't process any + // results if the field no longer has focus + hasFocus++; + }).blur(function() { + hasFocus = 0; + if (!config.mouseDownOnSelect) { + hideResults(); + } + }).click(function() { + // show select when clicking in a focused field + if ( hasFocus++ > 1 && !select.visible() ) { + onChange(0, true); + } + }).bind("search", function() { + // TODO why not just specifying both arguments? + var fn = (arguments.length > 1) ? arguments[1] : null; + function findValueCallback(q, data) { + var result; + if( data && data.length ) { + for (var i=0; i < data.length; i++) { + if( data[i].result.toLowerCase() == q.toLowerCase() ) { + result = data[i]; + break; + } + } + } + if( typeof fn == "function" ) fn(result); + else $input.trigger("result", result && [result.data, result.value]); + } + $.each(trimWords($input.val()), function(i, value) { + request(value, findValueCallback, findValueCallback); + }); + }).bind("flushCache", function() { + cache.flush(); + }).bind("setOptions", function() { + $.extend(options, arguments[1]); + // if we've updated the data, repopulate + if ( "data" in arguments[1] ) + cache.populate(); + }).bind("unautocomplete", function() { + select.unbind(); + $input.unbind(); + $(input.form).unbind(".autocomplete"); + }); + + + function selectCurrent() { + var selected = select.selected(); + if( !selected ) + return false; + + var v = selected.result; + previousValue = v; + + if ( options.multiple ) { + var words = trimWords($input.val()); + if ( words.length > 1 ) { + v = words.slice(0, words.length - 1).join( options.multipleSeparator ) + options.multipleSeparator + v; + } + v += options.multipleSeparator; + } + + $input.val(v); + hideResultsNow(); + $input.trigger("result", [selected.data, selected.value]); + return true; + } + + function onChange(crap, skipPrevCheck) { + if( lastKeyPressCode == KEY.DEL ) { + select.hide(); + return; + } + + var currentValue = $input.val(); + + if ( !skipPrevCheck && currentValue == previousValue ) + return; + + previousValue = currentValue; + + currentValue = lastWord(currentValue); + if ( currentValue.length >= options.minChars) { + $input.addClass(options.loadingClass); + if (!options.matchCase) + currentValue = currentValue.toLowerCase(); + request(currentValue, receiveData, hideResultsNow); + } else { + stopLoading(); + select.hide(); + } + }; + + function trimWords(value) { + if ( !value ) { + return [""]; + } + var words = value.split( options.multipleSeparator ); + var result = []; + $.each(words, function(i, value) { + if ( $.trim(value) ) + result[i] = $.trim(value); + }); + return result; + } + + function lastWord(value) { + if ( !options.multiple ) + return value; + var words = trimWords(value); + return words[words.length - 1]; + } + + // fills in the input box w/the first match (assumed to be the best match) + // q: the term entered + // sValue: the first matching result + function autoFill(q, sValue){ + // autofill in the complete box w/the first match as long as the user hasn't entered in more data + // if the last user key pressed was backspace, don't autofill + if( options.autoFill && (lastWord($input.val()).toLowerCase() == q.toLowerCase()) && lastKeyPressCode != KEY.BACKSPACE ) { + // fill in the value (keep the case the user has typed) + $input.val($input.val() + sValue.substring(lastWord(previousValue).length)); + // select the portion of the value not typed by the user (so the next character will erase) + $.Autocompleter.Selection(input, previousValue.length, previousValue.length + sValue.length); + } + }; + + function hideResults() { + clearTimeout(timeout); + timeout = setTimeout(hideResultsNow, 200); + }; + + function hideResultsNow() { + var wasVisible = select.visible(); + select.hide(); + clearTimeout(timeout); + stopLoading(); + if (options.mustMatch) { + // call search and run callback + $input.search( + function (result){ + // if no value found, clear the input box + if( !result ) { + if (options.multiple) { + var words = trimWords($input.val()).slice(0, -1); + $input.val( words.join(options.multipleSeparator) + (words.length ? options.multipleSeparator : "") ); + } + else + $input.val( "" ); + } + } + ); + } + if (wasVisible) + // position cursor at end of input field + $.Autocompleter.Selection(input, input.value.length, input.value.length); + }; + + function receiveData(q, data) { + if ( data && data.length && hasFocus ) { + stopLoading(); + select.display(data, q); + autoFill(q, data[0].value); + select.show(); + } else { + hideResultsNow(); + } + }; + + function request(term, success, failure) { + if (!options.matchCase) + term = term.toLowerCase(); + var data = cache.load(term); + // recieve the cached data + if (data && data.length) { + success(term, data); + // if an AJAX url has been supplied, try loading the data now + } else if( (typeof options.url == "string") && (options.url.length > 0) ){ + + var extraParams = { + timestamp: +new Date() + }; + $.each(options.extraParams, function(key, param) { + extraParams[key] = typeof param == "function" ? param() : param; + }); + + $.ajax({ + // try to leverage ajaxQueue plugin to abort previous requests + mode: "abort", + // limit abortion to this input + port: "autocomplete" + input.name, + dataType: options.dataType, + url: options.url, + data: $.extend({ + q: lastWord(term), + limit: options.max + }, extraParams), + success: function(data) { + var parsed = options.parse && options.parse(data) || parse(data); + cache.add(term, parsed); + success(term, parsed); + } + }); + } else { + // if we have a failure, we need to empty the list -- this prevents the the [TAB] key from selecting the last successful match + select.emptyList(); + failure(term); + } + }; + + function parse(data) { + var parsed = []; + var rows = data.split("\n"); + for (var i=0; i < rows.length; i++) { + var row = $.trim(rows[i]); + if (row) { + row = row.split("|"); + parsed[parsed.length] = { + data: row, + value: row[0], + result: options.formatResult && options.formatResult(row, row[0]) || row[0] + }; + } + } + return parsed; + }; + + function stopLoading() { + $input.removeClass(options.loadingClass); + }; + +}; + +$.Autocompleter.defaults = { + inputClass: "ac_input", + resultsClass: "ac_results", + loadingClass: "ac_loading", + minChars: 1, + delay: 400, + matchCase: false, + matchSubset: true, + matchContains: false, + cacheLength: 10, + max: 100, + mustMatch: false, + extraParams: {}, + selectFirst: true, + formatItem: function(row) { return row[0]; }, + formatMatch: null, + autoFill: false, + width: 0, + multiple: false, + multipleSeparator: ", ", + highlight: function(value, term) { + return value.replace(new RegExp("(?![^&;]+;)(?!<[^<>]*)(" + term.replace(/([\^\$\(\)\[\]\{\}\*\.\+\?\|\\])/gi, "\\$1") + ")(?![^<>]*>)(?![^&;]+;)", "gi"), "<strong>$1</strong>"); + }, + scroll: true, + scrollHeight: 180 +}; + +$.Autocompleter.Cache = function(options) { + + var data = {}; + var length = 0; + + function matchSubset(s, sub) { + if (!options.matchCase) + s = s.toLowerCase(); + var i = s.indexOf(sub); + if (options.matchContains == "word"){ + i = s.toLowerCase().search("\\b" + sub.toLowerCase()); + } + if (i == -1) return false; + return i == 0 || options.matchContains; + }; + + function add(q, value) { + if (length > options.cacheLength){ + flush(); + } + if (!data[q]){ + length++; + } + data[q] = value; + } + + function populate(){ + if( !options.data ) return false; + // track the matches + var stMatchSets = {}, + nullData = 0; + + // no url was specified, we need to adjust the cache length to make sure it fits the local data store + if( !options.url ) options.cacheLength = 1; + + // track all options for minChars = 0 + stMatchSets[""] = []; + + // loop through the array and create a lookup structure + for ( var i = 0, ol = options.data.length; i < ol; i++ ) { + var rawValue = options.data[i]; + // if rawValue is a string, make an array otherwise just reference the array + rawValue = (typeof rawValue == "string") ? [rawValue] : rawValue; + + var value = options.formatMatch(rawValue, i+1, options.data.length); + if ( value === false ) + continue; + + var firstChar = value.charAt(0).toLowerCase(); + // if no lookup array for this character exists, look it up now + if( !stMatchSets[firstChar] ) + stMatchSets[firstChar] = []; + + // if the match is a string + var row = { + value: value, + data: rawValue, + result: options.formatResult && options.formatResult(rawValue) || value + }; + + // push the current match into the set list + stMatchSets[firstChar].push(row); + + // keep track of minChars zero items + if ( nullData++ < options.max ) { + stMatchSets[""].push(row); + } + }; + + // add the data items to the cache + $.each(stMatchSets, function(i, value) { + // increase the cache size + options.cacheLength++; + // add to the cache + add(i, value); + }); + } + + // populate any existing data + setTimeout(populate, 25); + + function flush(){ + data = {}; + length = 0; + } + + return { + flush: flush, + add: add, + populate: populate, + load: function(q) { + if (!options.cacheLength || !length) + return null; + /* + * if dealing w/local data and matchContains than we must make sure + * to loop through all the data collections looking for matches + */ + if( !options.url && options.matchContains ){ + // track all matches + var csub = []; + // loop through all the data grids for matches + for( var k in data ){ + // don't search through the stMatchSets[""] (minChars: 0) cache + // this prevents duplicates + if( k.length > 0 ){ + var c = data[k]; + $.each(c, function(i, x) { + // if we've got a match, add it to the array + if (matchSubset(x.value, q)) { + csub.push(x); + } + }); + } + } + return csub; + } else + // if the exact item exists, use it + if (data[q]){ + return data[q]; + } else + if (options.matchSubset) { + for (var i = q.length - 1; i >= options.minChars; i--) { + var c = data[q.substr(0, i)]; + if (c) { + var csub = []; + $.each(c, function(i, x) { + if (matchSubset(x.value, q)) { + csub[csub.length] = x; + } + }); + return csub; + } + } + } + return null; + } + }; +}; + +$.Autocompleter.Select = function (options, input, select, config) { + var CLASSES = { + ACTIVE: "ac_over" + }; + + var listItems, + active = -1, + data, + term = "", + needsInit = true, + element, + list; + + // Create results + function init() { + if (!needsInit) + return; + element = $("<div/>") + .hide() + .addClass(options.resultsClass) + .css("position", "absolute") + .appendTo(document.body); + + list = $("<ul/>").appendTo(element).mouseover( function(event) { + if(target(event).nodeName && target(event).nodeName.toUpperCase() == 'LI') { + active = $("li", list).removeClass(CLASSES.ACTIVE).index(target(event)); + $(target(event)).addClass(CLASSES.ACTIVE); + } + }).click(function(event) { + $(target(event)).addClass(CLASSES.ACTIVE); + select(); + // TODO provide option to avoid setting focus again after selection? useful for cleanup-on-focus + input.focus(); + return false; + }).mousedown(function() { + config.mouseDownOnSelect = true; + }).mouseup(function() { + config.mouseDownOnSelect = false; + }); + + if( options.width > 0 ) + element.css("width", options.width); + + needsInit = false; + } + + function target(event) { + var element = event.target; + while(element && element.tagName != "LI") + element = element.parentNode; + // more fun with IE, sometimes event.target is empty, just ignore it then + if(!element) + return []; + return element; + } + + function moveSelect(step) { + listItems.slice(active, active + 1).removeClass(CLASSES.ACTIVE); + movePosition(step); + var activeItem = listItems.slice(active, active + 1).addClass(CLASSES.ACTIVE); + if(options.scroll) { + var offset = 0; + listItems.slice(0, active).each(function() { + offset += this.offsetHeight; + }); + if((offset + activeItem[0].offsetHeight - list.scrollTop()) > list[0].clientHeight) { + list.scrollTop(offset + activeItem[0].offsetHeight - list.innerHeight()); + } else if(offset < list.scrollTop()) { + list.scrollTop(offset); + } + } + }; + + function movePosition(step) { + active += step; + if (active < 0) { + active = listItems.size() - 1; + } else if (active >= listItems.size()) { + active = 0; + } + } + + function limitNumberOfItems(available) { + return options.max && options.max < available + ? options.max + : available; + } + + function fillList() { + list.empty(); + var max = limitNumberOfItems(data.length); + for (var i=0; i < max; i++) { + if (!data[i]) + continue; + var formatted = options.formatItem(data[i].data, i+1, max, data[i].value, term); + if ( formatted === false ) + continue; + var li = $("<li/>").html( options.highlight(formatted, term) ).addClass(i%2 == 0 ? "ac_even" : "ac_odd").appendTo(list)[0]; + $.data(li, "ac_data", data[i]); + } + listItems = list.find("li"); + if ( options.selectFirst ) { + listItems.slice(0, 1).addClass(CLASSES.ACTIVE); + active = 0; + } + // apply bgiframe if available + if ( $.fn.bgiframe ) + list.bgiframe(); + } + + return { + display: function(d, q) { + init(); + data = d; + term = q; + fillList(); + }, + next: function() { + moveSelect(1); + }, + prev: function() { + moveSelect(-1); + }, + pageUp: function() { + if (active != 0 && active - 8 < 0) { + moveSelect( -active ); + } else { + moveSelect(-8); + } + }, + pageDown: function() { + if (active != listItems.size() - 1 && active + 8 > listItems.size()) { + moveSelect( listItems.size() - 1 - active ); + } else { + moveSelect(8); + } + }, + hide: function() { + element && element.hide(); + listItems && listItems.removeClass(CLASSES.ACTIVE); + active = -1; + }, + visible : function() { + return element && element.is(":visible"); + }, + current: function() { + return this.visible() && (listItems.filter("." + CLASSES.ACTIVE)[0] || options.selectFirst && listItems[0]); + }, + show: function() { + var offset = $(input).offset(); + element.css({ + width: typeof options.width == "string" || options.width > 0 ? options.width : $(input).width(), + top: offset.top + input.offsetHeight, + left: offset.left + }).show(); + if(options.scroll) { + list.scrollTop(0); + list.css({ + maxHeight: options.scrollHeight, + overflow: 'auto' + }); + + if($.browser.msie && typeof document.body.style.maxHeight === "undefined") { + var listHeight = 0; + listItems.each(function() { + listHeight += this.offsetHeight; + }); + var scrollbarsVisible = listHeight > options.scrollHeight; + list.css('height', scrollbarsVisible ? options.scrollHeight : listHeight ); + if (!scrollbarsVisible) { + // IE doesn't recalculate width when scrollbar disappears + listItems.width( list.width() - parseInt(listItems.css("padding-left")) - parseInt(listItems.css("padding-right")) ); + } + } + + } + }, + selected: function() { + var selected = listItems && listItems.filter("." + CLASSES.ACTIVE).removeClass(CLASSES.ACTIVE); + return selected && selected.length && $.data(selected[0], "ac_data"); + }, + emptyList: function (){ + list && list.empty(); + }, + unbind: function() { + element && element.remove(); + } + }; +}; + +$.Autocompleter.Selection = function(field, start, end) { + if( field.createTextRange ){ + var selRange = field.createTextRange(); + selRange.collapse(true); + selRange.moveStart("character", start); + selRange.moveEnd("character", end); + selRange.select(); + } else if( field.setSelectionRange ){ + field.setSelectionRange(start, end); + } else { + if( field.selectionStart ){ + field.selectionStart = start; + field.selectionEnd = end; + } + } + field.focus(); +}; + +})(jQuery);
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/layout.vm b/isuifang_solr/solr/conf/velocity/layout.vm new file mode 100644 index 0000000..3a59b97 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/layout.vm @@ -0,0 +1,20 @@ +<html> +<head> + #parse("head.vm") +</head> + <body> + <div id="admin"><a href="#url_for_solr/admin">Solr Admin</a></div> + <div id="header"> + #parse("header.vm") + </div> + <div id="tabs"> + #parse("tabs.vm") + </div> + <div id="content"> + $content + </div> + <div id="footer"> + #parse("footer.vm") + </div> + </body> +</html>
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/main.css b/isuifang_solr/solr/conf/velocity/main.css new file mode 100644 index 0000000..076745d --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/main.css @@ -0,0 +1,184 @@ +#admin{ + text-align: right; + vertical-align: top; +} + +#head{ + width: 100%; +} +.array-field { + border: 2px solid #474747; + background: #FFE9D8; + padding: 5px; + margin: 5px; +} + +.array-field-list li { + list-style: circle; + margin-left: 20px; +} + +body { + font-family: Helvetica, Arial, sans-serif; + font-size: 10pt; +} + +a { + color: #43a4b1; +} + +.navigators { + float: left; + margin: 5px; + margin-top: 0px; + width: 185px; + padding: 5px; + top: -20px; + position: relative; +} + +.navigators h2 { + background: #FEC293; + border: 1px solid #ce9d77; + padding: 5px; +} + +.navigators ul { + list-style: none; + margin: 0; + margin-bottom: 5px; + margin-top: 5px; + padding-left: 10px; +} + +.navigators ul li { + color: #999; + padding: 2px; + text-transform: capitalize; +} + + + +.facet-field { + font-weight: bold; +} + +.highlight { + color: white; + background-color: gray; + border: 1px black solid; +} + +.highlight-box { + margin-left: 15px; +} + +.field-name { + font-weight: bold; +} + +.highlighted-facet-field { + background: white; +} + +.constraints { + margin-top: 10px; +} + +#query-form{ + width: 80%; +} + + + +.query-box, .constraints { + padding: 5px; + margin: 5px; + font-weight: normal; + font-size: 24px; + letter-spacing: 0.08em; +} + +.query-box #q { + margin-left: 8px; + width: 60%; + height: 50px; + border: 1px solid #999; + font-size: 1em; + padding: 0.4em; +} + +.query-box { + +} + +.query-boost { + + top: 10px; + left: 50px; + position: relative; + font-size: 0.8em; +} + +.query-box .inputs{ + left: 180px; + position: relative; + +} + +#logo { + margin: 10px; + border-style: none; +} + +.pagination { + padding-left: 33%; + background: #eee; + margin: 5px; + margin-left: 210px; + padding-top: 5px; + padding-bottom: 5px; +} + +.result-document { + border: 1px solid #999; + padding: 5px; + margin: 5px; + margin-left: 210px; + margin-bottom: 15px; +} + +.result-document div{ + padding: 5px; +} + +.result-title{ + width:60%; +} + +.mlt{ + +} + +.map{ + float: right; + position: relative; + top: -25px; +} + +.result-document:nth-child(2n+1) { + background-color: #eee; +} + + +.selected-facet-field { + font-weight: bold; +} + +li.show { + list-style: disc; +} + +.group-value{ + font-weight: bold; +}
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/query.vm b/isuifang_solr/solr/conf/velocity/query.vm new file mode 100644 index 0000000..2247c53 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/query.vm @@ -0,0 +1,56 @@ +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + --> + +<div class="query-box"> + <form id="query-form" action="#{url_for_home}" method="GET"> + <div class="inputs"> + <span #annTitle("Add the query using the &q= parameter")>Find: <input type="text" id="q" name="q" value="$!esc.html($params.get('q'))"/> <input type="submit" id="querySubmit"/> <input type="reset"/></span> + <div class="query-boost"><span #annTitle("Add the boost function &bf=price to the query")><input type="checkbox" name="bf" value="price" #if($request.params.get('bf') == 'price')checked="true"#end>Boost by Price</input></span> + #parse("querySpatial.vm") + </div> + </div> + + #if($request.params.get('debugQuery')) + <input type="hidden" name="debugQuery" value="true"/> + #end + #if($annotate == true) + <input type="hidden" name="annotateBrowse" value="true"/> + #end + #foreach($fq in $request.params.getParams('fq')) + #if ($fq != "{!bbox}") + <input type="hidden" name="fq" id="allFQs" value="$esc.html($fq)"/> + #end + #end + <div class="constraints" #annTitle("Lists out the &fq filters. Click to remove.")> + #foreach($fq in $params.getParams('fq')) + #set($previous_fq_count=$velocityCount - 1) + #if($fq != '') + > <a style="{text-decoration: line-through;}" href="#url_for_filters($request.params.getParams('fq').subList(0,$previous_fq_count))">$fq</a> + #end + #end + </div> + #if($request.params.get('debugQuery')) + <a href="#" onclick='jQuery(this).siblings("pre").toggle(); return false;'>toggle parsed query</a> + <pre style="display:none">$response.response.debug.parsedquery</pre> + #end + #set($queryOpts = $request.params.get("queryOpts")) + #if($queryOpts && $queryOpts != "") + <input type="hidden" name="queryOpts" value="$queryOpts"/> + #end + </form> + +</div> diff --git a/isuifang_solr/solr/conf/velocity/querySpatial.vm b/isuifang_solr/solr/conf/velocity/querySpatial.vm new file mode 100644 index 0000000..3b57de4 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/querySpatial.vm @@ -0,0 +1,40 @@ +#set($queryOpts = $params.get("queryOpts")) +#if($queryOpts == "spatial") +<div> + #set($loc = $request.params.get('pt')) + #set($dist = $request.params.get('d', "10")) + <label #annTitle("Add the &pt parameter")>Location Filter: + <select id="pt" name="pt"> + <option value="none" + #if($loc == '')selected="true"#end>No Filter</option> + <option value="45.17614,-93.87341" + #if($loc == '45.17614,-93.87341')selected="true"#end>Buffalo, MN</option> + <option value="37.7752,-100.0232" + #if($loc == '37.7752,-100.0232')selected="true"#end>Dodge City, KS</option> + <option value="35.0752,-97.032" + #if($loc == '35.0752,-97.032')selected="true"#end>Oklahoma City, OK</option> + <option value="37.7752,-122.4232" + #if($loc == '37.7752,-122.4232')selected="true"#end>San Francisco CA</option> + </select> + </label> + <span #annTitle("Add the &d parameter")>Distance (KM): <input id="d" name="d" type="text" size="6" + value="#if($dist != '')${dist}#{else}10#end"/></span> +<input type="hidden" name="sfield" value="store"/> +<input type="hidden" id="spatialFQ" name="fq" value=""/> +<input type="hidden" name="queryOpts" value="spatial"/> +</div> +<script type="text/javascript"> + $('#query-form').submit(function() { + if ($("#pt").val() != "none") { + $("#spatialFQ").val("{!bbox}"); + } + $fqs = $("#allFQs").val(); + $fqs = $fqs.replace("{!bbox}", ""); + if ($fqs == ''){ + $("#allFQs").remove(); + } + $("#allFQs").val($fqs); + return true; + }); +</script> +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/suggest.vm b/isuifang_solr/solr/conf/velocity/suggest.vm new file mode 100644 index 0000000..337f056 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/suggest.vm @@ -0,0 +1,3 @@ +#foreach($t in $response.response.terms.name) +$t.key +#end
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/velocity/tabs.vm b/isuifang_solr/solr/conf/velocity/tabs.vm new file mode 100644 index 0000000..a9f3db5 --- /dev/null +++ b/isuifang_solr/solr/conf/velocity/tabs.vm @@ -0,0 +1,22 @@ +##TODO: Make some nice tabs here +#set($queryOpts = $params.get("queryOpts")) +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. + --> + +<span #annTitle("Click the link to demonstrate various Solr capabilities")><span>Examples: </span><span class="tab">#if($queryOpts && $queryOpts != "")<a href="#url_for_home">Simple</a>#{else}Simple#end</span> +<span class="tab">#if($queryOpts == "spatial")Spatial#else<a href="#url_for_home?&queryOpts=spatial">Spatial</a>#end</span> +<hr/>
\ No newline at end of file diff --git a/isuifang_solr/solr/conf/xslt/example.xsl b/isuifang_solr/solr/conf/xslt/example.xsl new file mode 100644 index 0000000..b899270 --- /dev/null +++ b/isuifang_solr/solr/conf/xslt/example.xsl @@ -0,0 +1,132 @@ +<?xml version='1.0' encoding='UTF-8'?> + +<!-- + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + --> + +<!-- + Simple transform of Solr query results to HTML + --> +<xsl:stylesheet version='1.0' + xmlns:xsl='http://www.w3.org/1999/XSL/Transform' +> + + <xsl:output media-type="text/html" encoding="UTF-8"/> + + <xsl:variable name="title" select="concat('Solr search results (',response/result/@numFound,' documents)')"/> + + <xsl:template match='/'> + <html> + <head> + <title><xsl:value-of select="$title"/></title> + <xsl:call-template name="css"/> + </head> + <body> + <h1><xsl:value-of select="$title"/></h1> + <div class="note"> + This has been formatted by the sample "example.xsl" transform - + use your own XSLT to get a nicer page + </div> + <xsl:apply-templates select="response/result/doc"/> + </body> + </html> + </xsl:template> + + <xsl:template match="doc"> + <xsl:variable name="pos" select="position()"/> + <div class="doc"> + <table width="100%"> + <xsl:apply-templates> + <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param> + </xsl:apply-templates> + </table> + </div> + </xsl:template> + + <xsl:template match="doc/*[@name='score']" priority="100"> + <xsl:param name="pos"></xsl:param> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <xsl:value-of select="."/> + + <xsl:if test="boolean(//lst[@name='explain'])"> + <xsl:element name="a"> + <!-- can't allow whitespace here --> + <xsl:attribute name="href">javascript:toggle("<xsl:value-of select="concat('exp-',$pos)" />");</xsl:attribute>?</xsl:element> + <br/> + <xsl:element name="div"> + <xsl:attribute name="class">exp</xsl:attribute> + <xsl:attribute name="id"> + <xsl:value-of select="concat('exp-',$pos)" /> + </xsl:attribute> + <xsl:value-of select="//lst[@name='explain']/str[position()=$pos]"/> + </xsl:element> + </xsl:if> + </td> + </tr> + </xsl:template> + + <xsl:template match="doc/arr" priority="100"> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <ul> + <xsl:for-each select="*"> + <li><xsl:value-of select="."/></li> + </xsl:for-each> + </ul> + </td> + </tr> + </xsl:template> + + + <xsl:template match="doc/*"> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <xsl:value-of select="."/> + </td> + </tr> + </xsl:template> + + <xsl:template match="*"/> + + <xsl:template name="css"> + <script> + function toggle(id) { + var obj = document.getElementById(id); + obj.style.display = (obj.style.display != 'block') ? 'block' : 'none'; + } + </script> + <style type="text/css"> + body { font-family: "Lucida Grande", sans-serif } + td.name { font-style: italic; font-size:80%; } + td { vertical-align: top; } + ul { margin: 0px; margin-left: 1em; padding: 0px; } + .note { font-size:80%; } + .doc { margin-top: 1em; border-top: solid grey 1px; } + .exp { display: none; font-family: monospace; white-space: pre; } + </style> + </xsl:template> + +</xsl:stylesheet> diff --git a/isuifang_solr/solr/conf/xslt/example_atom.xsl b/isuifang_solr/solr/conf/xslt/example_atom.xsl new file mode 100644 index 0000000..b6c2315 --- /dev/null +++ b/isuifang_solr/solr/conf/xslt/example_atom.xsl @@ -0,0 +1,67 @@ +<?xml version='1.0' encoding='UTF-8'?> + +<!-- + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + --> + +<!-- + Simple transform of Solr query results to Atom + --> + +<xsl:stylesheet version='1.0' + xmlns:xsl='http://www.w3.org/1999/XSL/Transform'> + + <xsl:output + method="xml" + encoding="utf-8" + media-type="application/xml" + /> + + <xsl:template match='/'> + <xsl:variable name="query" select="response/lst[@name='responseHeader']/lst[@name='params']/str[@name='q']"/> + <feed xmlns="http://www.w3.org/2005/Atom"> + <title>Example Solr Atom 1.0 Feed</title> + <subtitle> + This has been formatted by the sample "example_atom.xsl" transform - + use your own XSLT to get a nicer Atom feed. + </subtitle> + <author> + <name>Apache Solr</name> + <email>solr-user@lucene.apache.org</email> + </author> + <link rel="self" type="application/atom+xml" + href="http://localhost:8983/solr/q={$query}&wt=xslt&tr=atom.xsl"/> + <updated> + <xsl:value-of select="response/result/doc[position()=1]/date[@name='timestamp']"/> + </updated> + <id>tag:localhost,2007:example</id> + <xsl:apply-templates select="response/result/doc"/> + </feed> + </xsl:template> + + <!-- search results xslt --> + <xsl:template match="doc"> + <xsl:variable name="id" select="str[@name='id']"/> + <entry> + <title><xsl:value-of select="str[@name='name']"/></title> + <link href="http://localhost:8983/solr/select?q={$id}"/> + <id>tag:localhost,2007:<xsl:value-of select="$id"/></id> + <summary><xsl:value-of select="arr[@name='features']"/></summary> + <updated><xsl:value-of select="date[@name='timestamp']"/></updated> + </entry> + </xsl:template> + +</xsl:stylesheet> diff --git a/isuifang_solr/solr/conf/xslt/example_rss.xsl b/isuifang_solr/solr/conf/xslt/example_rss.xsl new file mode 100644 index 0000000..2857f11 --- /dev/null +++ b/isuifang_solr/solr/conf/xslt/example_rss.xsl @@ -0,0 +1,66 @@ +<?xml version='1.0' encoding='UTF-8'?> + +<!-- + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + --> + +<!-- + Simple transform of Solr query results to RSS + --> + +<xsl:stylesheet version='1.0' + xmlns:xsl='http://www.w3.org/1999/XSL/Transform'> + + <xsl:output + method="xml" + encoding="utf-8" + media-type="application/xml" + /> + <xsl:template match='/'> + <rss version="2.0"> + <channel> + <title>Example Solr RSS 2.0 Feed</title> + <link>http://localhost:8983/solr</link> + <description> + This has been formatted by the sample "example_rss.xsl" transform - + use your own XSLT to get a nicer RSS feed. + </description> + <language>en-us</language> + <docs>http://localhost:8983/solr</docs> + <xsl:apply-templates select="response/result/doc"/> + </channel> + </rss> + </xsl:template> + + <!-- search results xslt --> + <xsl:template match="doc"> + <xsl:variable name="id" select="str[@name='id']"/> + <xsl:variable name="timestamp" select="date[@name='timestamp']"/> + <item> + <title><xsl:value-of select="str[@name='name']"/></title> + <link> + http://localhost:8983/solr/select?q=id:<xsl:value-of select="$id"/> + </link> + <description> + <xsl:value-of select="arr[@name='features']"/> + </description> + <pubDate><xsl:value-of select="$timestamp"/></pubDate> + <guid> + http://localhost:8983/solr/select?q=id:<xsl:value-of select="$id"/> + </guid> + </item> + </xsl:template> +</xsl:stylesheet> diff --git a/isuifang_solr/solr/conf/xslt/luke.xsl b/isuifang_solr/solr/conf/xslt/luke.xsl new file mode 100644 index 0000000..8553f3c --- /dev/null +++ b/isuifang_solr/solr/conf/xslt/luke.xsl @@ -0,0 +1,337 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + Licensed to the Apache Software Foundation (ASF) under one or more + contributor license agreements. See the NOTICE file distributed with + this work for additional information regarding copyright ownership. + The ASF licenses this file to You under the Apache License, Version 2.0 + (the "License"); you may not use this file except in compliance with + the License. You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. +--> + + +<!-- + Display the luke request handler with graphs + --> +<xsl:stylesheet + xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + xmlns="http://www.w3.org/1999/xhtml" + version="1.0" + > + <xsl:output + method="html" + encoding="UTF-8" + media-type="text/html" + doctype-public="-//W3C//DTD XHTML 1.0 Strict//EN" + doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd" + /> + + <xsl:variable name="title">Solr Luke Request Handler Response</xsl:variable> + + <xsl:template match="/"> + <html xmlns="http://www.w3.org/1999/xhtml"> + <head> + <link rel="stylesheet" type="text/css" href="solr-admin.css"/> + <link rel="icon" href="favicon.ico" type="image/ico"/> + <link rel="shortcut icon" href="favicon.ico" type="image/ico"/> + <title> + <xsl:value-of select="$title"/> + </title> + <xsl:call-template name="css"/> + + </head> + <body> + <h1> + <xsl:value-of select="$title"/> + </h1> + <div class="doc"> + <ul> + <xsl:if test="response/lst[@name='index']"> + <li> + <a href="#index">Index Statistics</a> + </li> + </xsl:if> + <xsl:if test="response/lst[@name='fields']"> + <li> + <a href="#fields">Field Statistics</a> + <ul> + <xsl:for-each select="response/lst[@name='fields']/lst"> + <li> + <a href="#{@name}"> + <xsl:value-of select="@name"/> + </a> + </li> + </xsl:for-each> + </ul> + </li> + </xsl:if> + <xsl:if test="response/lst[@name='doc']"> + <li> + <a href="#doc">Document statistics</a> + </li> + </xsl:if> + </ul> + </div> + <xsl:if test="response/lst[@name='index']"> + <h2><a name="index"/>Index Statistics</h2> + <xsl:apply-templates select="response/lst[@name='index']"/> + </xsl:if> + <xsl:if test="response/lst[@name='fields']"> + <h2><a name="fields"/>Field Statistics</h2> + <xsl:apply-templates select="response/lst[@name='fields']"/> + </xsl:if> + <xsl:if test="response/lst[@name='doc']"> + <h2><a name="doc"/>Document statistics</h2> + <xsl:apply-templates select="response/lst[@name='doc']"/> + </xsl:if> + </body> + </html> + </xsl:template> + + <xsl:template match="lst"> + <xsl:if test="parent::lst"> + <tr> + <td colspan="2"> + <div class="doc"> + <xsl:call-template name="list"/> + </div> + </td> + </tr> + </xsl:if> + <xsl:if test="not(parent::lst)"> + <div class="doc"> + <xsl:call-template name="list"/> + </div> + </xsl:if> + </xsl:template> + + <xsl:template name="list"> + <xsl:if test="count(child::*)>0"> + <table> + <thead> + <tr> + <th colspan="2"> + <p> + <a name="{@name}"/> + </p> + <xsl:value-of select="@name"/> + </th> + </tr> + </thead> + <tbody> + <xsl:choose> + <xsl:when + test="@name='histogram'"> + <tr> + <td colspan="2"> + <xsl:call-template name="histogram"/> + </td> + </tr> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </tbody> + </table> + </xsl:if> + </xsl:template> + + <xsl:template name="histogram"> + <div class="doc"> + <xsl:call-template name="barchart"> + <xsl:with-param name="max_bar_width">50</xsl:with-param> + <xsl:with-param name="iwidth">800</xsl:with-param> + <xsl:with-param name="iheight">160</xsl:with-param> + <xsl:with-param name="fill">blue</xsl:with-param> + </xsl:call-template> + </div> + </xsl:template> + + <xsl:template name="barchart"> + <xsl:param name="max_bar_width"/> + <xsl:param name="iwidth"/> + <xsl:param name="iheight"/> + <xsl:param name="fill"/> + <xsl:variable name="max"> + <xsl:for-each select="int"> + <xsl:sort data-type="number" order="descending"/> + <xsl:if test="position()=1"> + <xsl:value-of select="."/> + </xsl:if> + </xsl:for-each> + </xsl:variable> + <xsl:variable name="bars"> + <xsl:value-of select="count(int)"/> + </xsl:variable> + <xsl:variable name="bar_width"> + <xsl:choose> + <xsl:when test="$max_bar_width < ($iwidth div $bars)"> + <xsl:value-of select="$max_bar_width"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$iwidth div $bars"/> + </xsl:otherwise> + </xsl:choose> + </xsl:variable> + <table class="histogram"> + <tbody> + <tr> + <xsl:for-each select="int"> + <td> + <xsl:value-of select="."/> + <div class="histogram"> + <xsl:attribute name="style">background-color: <xsl:value-of select="$fill"/>; width: <xsl:value-of select="$bar_width"/>px; height: <xsl:value-of select="($iheight*number(.)) div $max"/>px;</xsl:attribute> + </div> + </td> + </xsl:for-each> + </tr> + <tr> + <xsl:for-each select="int"> + <td> + <xsl:value-of select="@name"/> + </td> + </xsl:for-each> + </tr> + </tbody> + </table> + </xsl:template> + + <xsl:template name="keyvalue"> + <xsl:choose> + <xsl:when test="@name"> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <xsl:value-of select="."/> + </td> + </tr> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="."/> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + <xsl:template match="int|bool|long|float|double|uuid|date"> + <xsl:call-template name="keyvalue"/> + </xsl:template> + + <xsl:template match="arr"> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <ul> + <xsl:for-each select="child::*"> + <li> + <xsl:apply-templates/> + </li> + </xsl:for-each> + </ul> + </td> + </tr> + </xsl:template> + + <xsl:template match="str"> + <xsl:choose> + <xsl:when test="@name='schema' or @name='index' or @name='flags'"> + <xsl:call-template name="schema"/> + </xsl:when> + <xsl:otherwise> + <xsl:call-template name="keyvalue"/> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + <xsl:template name="schema"> + <tr> + <td class="name"> + <xsl:value-of select="@name"/> + </td> + <td class="value"> + <xsl:if test="contains(.,'unstored')"> + <xsl:value-of select="."/> + </xsl:if> + <xsl:if test="not(contains(.,'unstored'))"> + <xsl:call-template name="infochar2string"> + <xsl:with-param name="charList"> + <xsl:value-of select="."/> + </xsl:with-param> + </xsl:call-template> + </xsl:if> + </td> + </tr> + </xsl:template> + + <xsl:template name="infochar2string"> + <xsl:param name="i">1</xsl:param> + <xsl:param name="charList"/> + + <xsl:variable name="char"> + <xsl:value-of select="substring($charList,$i,1)"/> + </xsl:variable> + <xsl:choose> + <xsl:when test="$char='I'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='I']"/> - </xsl:when> + <xsl:when test="$char='T'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='T']"/> - </xsl:when> + <xsl:when test="$char='S'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='S']"/> - </xsl:when> + <xsl:when test="$char='M'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='M']"/> - </xsl:when> + <xsl:when test="$char='V'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='V']"/> - </xsl:when> + <xsl:when test="$char='o'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='o']"/> - </xsl:when> + <xsl:when test="$char='p'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='p']"/> - </xsl:when> + <xsl:when test="$char='O'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='O']"/> - </xsl:when> + <xsl:when test="$char='L'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='L']"/> - </xsl:when> + <xsl:when test="$char='B'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='B']"/> - </xsl:when> + <xsl:when test="$char='C'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='C']"/> - </xsl:when> + <xsl:when test="$char='f'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='f']"/> - </xsl:when> + <xsl:when test="$char='l'"> + <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='l']"/> - + </xsl:when> + </xsl:choose> + + <xsl:if test="not($i>=string-length($charList))"> + <xsl:call-template name="infochar2string"> + <xsl:with-param name="i"> + <xsl:value-of select="$i+1"/> + </xsl:with-param> + <xsl:with-param name="charList"> + <xsl:value-of select="$charList"/> + </xsl:with-param> + </xsl:call-template> + </xsl:if> + </xsl:template> + <xsl:template name="css"> + <style type="text/css"> + <![CDATA[ + td.name {font-style: italic; font-size:80%; } + .doc { margin: 0.5em; border: solid grey 1px; } + .exp { display: none; font-family: monospace; white-space: pre; } + div.histogram { background: none repeat scroll 0%; -moz-background-clip: -moz-initial; -moz-background-origin: -moz-initial; -moz-background-inline-policy: -moz-initial;} + table.histogram { width: auto; vertical-align: bottom; } + table.histogram td, table.histogram th { text-align: center; vertical-align: bottom; border-bottom: 1px solid #ff9933; width: auto; } + ]]> + </style> + </xsl:template> +</xsl:stylesheet> diff --git a/isuifang_solr/solr/conf/xslt/updateXml.xsl b/isuifang_solr/solr/conf/xslt/updateXml.xsl new file mode 100644 index 0000000..daf1344 --- /dev/null +++ b/isuifang_solr/solr/conf/xslt/updateXml.xsl @@ -0,0 +1,70 @@ +<!-- + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + --> + +<!-- + Simple transform of Solr query response into Solr Update XML compliant XML. + When used in the xslt response writer you will get UpdaateXML as output. + But you can also store a query response XML to disk and feed this XML to + the XSLTUpdateRequestHandler to index the content. Provided as example only. + See http://wiki.apache.org/solr/XsltUpdateRequestHandler for more info + --> +<xsl:stylesheet version='1.0' xmlns:xsl='http://www.w3.org/1999/XSL/Transform'> + <xsl:output media-type="text/xml" method="xml" indent="yes"/> + + <xsl:template match='/'> + <add> + <xsl:apply-templates select="response/result/doc"/> + </add> + </xsl:template> + + <!-- Ignore score (makes no sense to index) --> + <xsl:template match="doc/*[@name='score']" priority="100"> + </xsl:template> + + <xsl:template match="doc"> + <xsl:variable name="pos" select="position()"/> + <doc> + <xsl:apply-templates> + <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param> + </xsl:apply-templates> + </doc> + </xsl:template> + + <!-- Flatten arrays to duplicate field lines --> + <xsl:template match="doc/arr" priority="100"> + <xsl:variable name="fn" select="@name"/> + + <xsl:for-each select="*"> + <xsl:element name="field"> + <xsl:attribute name="name"><xsl:value-of select="$fn"/></xsl:attribute> + <xsl:value-of select="."/> + </xsl:element> + </xsl:for-each> + </xsl:template> + + + <xsl:template match="doc/*"> + <xsl:variable name="fn" select="@name"/> + + <xsl:element name="field"> + <xsl:attribute name="name"><xsl:value-of select="$fn"/></xsl:attribute> + <xsl:value-of select="."/> + </xsl:element> + </xsl:template> + + <xsl:template match="*"/> +</xsl:stylesheet> |