From f830b8f98fa6df96d8fb706fd7c84de40b28d009 Mon Sep 17 00:00:00 2001 From: Christopher Tate Date: Sat, 16 Nov 2024 10:45:47 -0700 Subject: [PATCH] Allowing for a custom solrId field --- .../configsets/computate/conf/managed-schema | 3726 +++-------------- .../org/computate/frFR/java/ConfigSite.java | 8 + .../computate/frFR/java/IndexerClasse.java | 14 +- .../computate/frFR/java/RegarderClasse.java | 2 +- 4 files changed, 618 insertions(+), 3132 deletions(-) diff --git a/config/solr/server/solr/configsets/computate/conf/managed-schema b/config/solr/server/solr/configsets/computate/conf/managed-schema index 7163fece..bcb46db6 100644 --- a/config/solr/server/solr/configsets/computate/conf/managed-schema +++ b/config/solr/server/solr/configsets/computate/conf/managed-schema @@ -1,3127 +1,605 @@ -kind: ConfigMap -apiVersion: v1 -metadata: - name: computate-configset - namespace: solr -data: - contractions_ca.txt: "# Set of Catalan contractions for ElisionFilter\r\n# TODO: - load this as a resource from the analyzer and sync it in build.xml\r\nd\r\nl\r\nm\r\nn\r\ns\r\nt\r\n" - contractions_fr.txt: | - # 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 - d - c - jusqu - quoiqu - lorsqu - puisqu - contractions_ga.txt: "# Set of Irish contractions for ElisionFilter\r\n# TODO: load - this as a resource from the analyzer and sync it in build.xml\r\nd\r\nm\r\nb\r\n" - contractions_it.txt: "# Set of Italian contractions for ElisionFilter\r\n# TODO: - load this as a resource from the analyzer and sync it in build.xml\r\nc\r\nl \r\nall - \r\ndall \r\ndell \r\nnell \r\nsull \r\ncoll \r\npell \r\ngl \r\nagl \r\ndagl - \r\ndegl \r\nnegl \r\nsugl \r\nun \r\nm \r\nt \r\ns \r\nv \r\nd\r\n" - currency.xml: "\n\n\n\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n" - elevate.xml: "\n\n\n\n\n \n\n" - email_url_types.txt: |- - - - hyphenations_ga.txt: "# Set of Irish hyphenations for StopFilter\r\n# TODO: load - this as a resource from the analyzer and sync it in build.xml\r\nh\r\nn\r\nt\r\n" - managed-schema: | - - - - id - + + + + solrId + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - params.json: |- - {"params":{ - "query":{ - "defType":"edismax", - "q.alt":"*:*", - "rows":"10", - "fl":"*,score", - "":{"v":0}}, - "facets":{ - "facet":"on", - "facet.mincount":"1", - "f.doc_type.facet.mincount":"0", - "facet.field":["text_shingles","{!ex=type}doc_type", "language"], - "f.text_shingles.facet.limit":10, - "facet.query":"{!ex=type key=all_types}*:*", - "f.doc_type.facet.missing":true, - "":{"v":0}}, - "browse":{ - "type_fq":"{!field f=doc_type v=$type}", - "hl":"on", - "hl.fl":"content", - "v.locale":"${locale}", - "debug":"true", - "hl.simple.pre":"HL_START", - "hl.simple.post":"HL_END", - "echoParams": "explicit", - "_appends_": { - "fq": "{!switch v=$type tag=type case='*:*' case.all='*:*' case.unknown='-doc_type:[* TO *]' default=$type_fq}" - }, - "":{"v":0}}, - "velocity":{ - "wt":"velocity", - "v.template":"browse", - "v.layout":"layout", - "":{"v":0}}}} - protwords.txt: |- - # 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 - solrconfig.xml: |- - - - - - - - - - 9.3 - - - - - - - - - - - ${solr.data.dir:} - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - ${solr.lock.type:native} - - - - - - - - - - - - - - - - - - - - - ${solr.ulog.dir:} - ${solr.ulog.numVersionBuckets:65536} - - - - - ${solr.autoCommit.maxTime:15000} - false - - - - - - ${solr.autoSoftCommit.maxTime:-1} - - - - - - - - - - - - - - ${solr.max.booleanClauses:1024} - - - - - - - - - - - - - - - - - - - - - - - - true - - - - - - 20 - - - 200 - - - - - - - - - - - - - - - - - - - false - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - explicit - 10 - - - - - - - explicit - json - true - - - - - - - _text_ - - - - - - - text_general - - - - - - default - _text_ - solr.DirectSolrSpellChecker - - internal - - 0.5 - - 2 - - 1 - - 5 - - 4 - - 0.01 - - - - - - - - - - - - default - on - true - 10 - 5 - 5 - true - true - 10 - 5 - - - spellcheck - - - - - - - - - - - - 100 - - - - - - - - 70 - - 0.5 - - [-\w ,/\n\"']{20,200} - - - - - - - ]]> - ]]> - - - - - - - - - - - - - - - - - - - - - - - - ,, - ,, - ,, - ,, - ,]]> - ]]> - - - - - - 10 - .,!? - - - - - - - WORD - - - en - US - - - - - - - - - - - - [^\w-\.] - _ - - - - - - - yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z - yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z - yyyy-MM-dd HH:mm[:ss[.SSS]][z - yyyy-MM-dd HH:mm[:ss[,SSS]][z - [EEE, ]dd MMM yyyy HH:mm[:ss] z - EEEE, dd-MMM-yy HH:mm:ss z - EEE MMM ppd HH:mm:ss [z ]yyyy - - - - - java.lang.String - text_general - - *_str - 256 - - - true - - - java.lang.Boolean - booleans - - - java.util.Date - pdates - - - java.lang.Long - java.lang.Integer - plongs - - - java.lang.Number - pdoubles - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - stemdict_nl.txt: "# Set of overrides for the dutch stemmer\r\n# TODO: load this - as a resource from the analyzer and sync it in build.xml\r\nfiets\tfiets\r\nbromfiets\tbromfiets\r\nei\teier\r\nkind\tkinder\r\n" - stoptags_ja.txt: "#\r\n# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.\r\n#\r\n# - Any token with a part-of-speech tag that exactly matches those defined in this\r\n# - file are removed from the token stream.\r\n#\r\n# Set your own stoptags by uncommenting - the lines below. Note that comments are\r\n# not allowed on the same line as - a stoptag. See LUCENE-3745 for frequency lists,\r\n# etc. that can be useful - for building you own stoptag set.\r\n#\r\n# The entire possible tagset is provided - below for convenience.\r\n#\r\n#####\r\n# noun: unclassified nouns\r\n#名詞\r\n#\r\n# - \ noun-common: Common nouns or nouns where the sub-classification is undefined\r\n#名詞-一般\r\n#\r\n# - \ noun-proper: Proper nouns where the sub-classification is undefined \r\n#名詞-固有名詞\r\n#\r\n# - \ noun-proper-misc: miscellaneous proper nouns\r\n#名詞-固有名詞-一般\r\n#\r\n# noun-proper-person: - Personal names where the sub-classification is undefined\r\n#名詞-固有名詞-人名\r\n#\r\n# - \ noun-proper-person-misc: names that cannot be divided into surname and \r\n# - \ given name; foreign names; names where the surname or given name is unknown.\r\n# - \ e.g. お市の方\r\n#名詞-固有名詞-人名-一般\r\n#\r\n# noun-proper-person-surname: Mainly Japanese - surnames.\r\n# e.g. 山田\r\n#名詞-固有名詞-人名-姓\r\n#\r\n# noun-proper-person-given_name: - Mainly Japanese given names.\r\n# e.g. 太郎\r\n#名詞-固有名詞-人名-名\r\n#\r\n# noun-proper-organization: - Names representing organizations.\r\n# e.g. 通産省, NHK\r\n#名詞-固有名詞-組織\r\n#\r\n# - \ noun-proper-place: Place names where the sub-classification is undefined\r\n#名詞-固有名詞-地域\r\n#\r\n# - \ noun-proper-place-misc: Place names excluding countries.\r\n# e.g. アジア, バルセロナ, - 京都\r\n#名詞-固有名詞-地域-一般\r\n#\r\n# noun-proper-place-country: Country names. \r\n# - \ e.g. 日本, オーストラリア\r\n#名詞-固有名詞-地域-国\r\n#\r\n# noun-pronoun: Pronouns where the - sub-classification is undefined\r\n#名詞-代名詞\r\n#\r\n# noun-pronoun-misc: miscellaneous - pronouns: \r\n# 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\r\n#名詞-代名詞-一般\r\n#\r\n# - \ noun-pronoun-contraction: Spoken language contraction made by combining a \r\n# - \ pronoun and the particle 'wa'.\r\n# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ \r\n#名詞-代名詞-縮約\r\n#\r\n# - \ noun-adverbial: Temporal nouns such as names of days or months that behave \r\n# - \ like adverbs. Nouns that represent amount or ratios and can be used adverbially,\r\n# - \ e.g. 金曜, 一月, 午後, 少量\r\n#名詞-副詞可能\r\n#\r\n# noun-verbal: Nouns that take arguments - with case and can appear followed by \r\n# 'suru' and related verbs (する, できる, - なさる, くださる)\r\n# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り\r\n#名詞-サ変接続\r\n#\r\n# noun-adjective-base: - The base form of adjectives, words that appear before な (\"na\")\r\n# e.g. 健康, - 安易, 駄目, だめ\r\n#名詞-形容動詞語幹\r\n#\r\n# noun-numeric: Arabic numbers, Chinese numerals, - and counters like 何 (回), 数.\r\n# e.g. 0, 1, 2, 何, 数, 幾\r\n#名詞-数\r\n#\r\n# noun-affix: - noun affixes where the sub-classification is undefined\r\n#名詞-非自立\r\n#\r\n# noun-affix-misc: - Of adnominalizers, the case-marker の (\"no\"), and words that \r\n# attach to - the base form of inflectional words, words that cannot be classified \r\n# into - any of the other categories below. This category includes indefinite nouns.\r\n# - \ 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, \r\n# 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, \r\n# 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,\r\n# わり, 割り, 割, ん-口語/, もん-口語/\r\n#名詞-非自立-一般\r\n#\r\n# - \ noun-affix-adverbial: noun affixes that that can behave as adverbs.\r\n# 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, \r\n# 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, \r\n# 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, \r\n# 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, \r\n# 儘, 侭, みぎり, 矢先\r\n#名詞-非自立-副詞可能\r\n#\r\n# - \ noun-affix-aux: noun affixes treated as 助動詞 (\"auxiliary verb\") in school grammars - \r\n# with the stem よう(だ) (\"you(da)\").\r\n# e.g. よう, やう, 様 (よう)\r\n#名詞-非自立-助動詞語幹\r\n# - \ \r\n# noun-affix-adjective-base: noun affixes that can connect to the indeclinable\r\n# - \ connection form な (aux \"da\").\r\n# e.g. みたい, ふう\r\n#名詞-非自立-形容動詞語幹\r\n#\r\n# - \ noun-special: special nouns where the sub-classification is undefined.\r\n#名詞-特殊\r\n#\r\n# - \ noun-special-aux: The そうだ (\"souda\") stem form that is used for reporting news, - is \r\n# treated as 助動詞 (\"auxiliary verb\") in school grammars, and attach to - the base \r\n# form of inflectional words.\r\n# e.g. そう\r\n#名詞-特殊-助動詞語幹\r\n#\r\n# - \ noun-suffix: noun suffixes where the sub-classification is undefined.\r\n#名詞-接尾\r\n#\r\n# - \ noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect - \r\n# to ガル or タイ and can combine into compound nouns, words that cannot be classified - into\r\n# any of the other categories below. In general, this category is more - inclusive than \r\n# 接尾語 (\"suffix\") and is usually the last element in a compound - noun.\r\n# 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,\r\n# - \ よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用\r\n#名詞-接尾-一般\r\n#\r\n# noun-suffix-person: - Suffixes that form nouns and attach to person names more often\r\n# than other - nouns.\r\n# e.g. 君, 様, 著\r\n#名詞-接尾-人名\r\n#\r\n# noun-suffix-place: Suffixes - that form nouns and attach to place names more often \r\n# than other nouns.\r\n# - \ e.g. 町, 市, 県\r\n#名詞-接尾-地域\r\n#\r\n# noun-suffix-verbal: Of the suffixes that - attach to nouns and form nouns, those that \r\n# can appear before スル (\"suru\").\r\n# - \ e.g. 化, 視, 分け, 入り, 落ち, 買い\r\n#名詞-接尾-サ変接続\r\n#\r\n# noun-suffix-aux: The stem - form of そうだ (様態) that is used to indicate conditions, \r\n# is treated as 助動詞 - (\"auxiliary verb\") in school grammars, and attach to the \r\n# conjunctive - form of inflectional words.\r\n# e.g. そう\r\n#名詞-接尾-助動詞語幹\r\n#\r\n# noun-suffix-adjective-base: - Suffixes that attach to other nouns or the conjunctive \r\n# form of inflectional - words and appear before the copula だ (\"da\").\r\n# e.g. 的, げ, がち\r\n#名詞-接尾-形容動詞語幹\r\n#\r\n# - \ noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as - adverbs.\r\n# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)\r\n#名詞-接尾-副詞可能\r\n#\r\n# - \ noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This - category \r\n# is more inclusive than 助数詞 (\"classifier\") and includes common - nouns that attach \r\n# to numbers.\r\n# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, - か国, 区画, 時間, 時半\r\n#名詞-接尾-助数詞\r\n#\r\n# noun-suffix-special: Special suffixes - that mainly attach to inflecting words.\r\n# e.g. (楽し) さ, (考え) 方\r\n#名詞-接尾-特殊\r\n#\r\n# - \ noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words - \r\n# together.\r\n# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)\r\n#名詞-接続詞的\r\n#\r\n# - \ noun-verbal_aux: Nouns that attach to the conjunctive particle て (\"te\") and - are \r\n# semantically verb-like.\r\n# e.g. ごらん, ご覧, 御覧, 頂戴\r\n#名詞-動詞非自立的\r\n#\r\n# - \ noun-quotation: text that cannot be segmented into words, proverbs, Chinese - poetry, \r\n# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 - (\"noun quotation\") \r\n# is いわく (\"iwaku\").\r\n#名詞-引用文字列\r\n#\r\n# noun-nai_adjective: - Words that appear before the auxiliary verb ない (\"nai\") and\r\n# behave like - an adjective.\r\n# e.g. 申し訳, 仕方, とんでも, 違い\r\n#名詞-ナイ形容詞語幹\r\n#\r\n#####\r\n# prefix: - unclassified prefixes\r\n#接頭詞\r\n#\r\n# prefix-nominal: Prefixes that attach - to nouns (including adjective stem forms) \r\n# excluding numerical expressions.\r\n# - \ e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)\r\n#接頭詞-名詞接続\r\n#\r\n# - \ prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb\r\n# - \ in conjunctive form followed by なる/なさる/くださる.\r\n# e.g. お (読みなさい), お (座り)\r\n#接頭詞-動詞接続\r\n#\r\n# - \ prefix-adjectival: Prefixes that attach to adjectives.\r\n# e.g. お (寒いですねえ), - バカ (でかい)\r\n#接頭詞-形容詞接続\r\n#\r\n# prefix-numerical: Prefixes that attach to numerical - expressions.\r\n# e.g. 約, およそ, 毎時\r\n#接頭詞-数接続\r\n#\r\n#####\r\n# verb: unclassified - verbs\r\n#動詞\r\n#\r\n# verb-main:\r\n#動詞-自立\r\n#\r\n# verb-auxiliary:\r\n#動詞-非自立\r\n#\r\n# - \ verb-suffix:\r\n#動詞-接尾\r\n#\r\n#####\r\n# adjective: unclassified adjectives\r\n#形容詞\r\n#\r\n# - \ adjective-main:\r\n#形容詞-自立\r\n#\r\n# adjective-auxiliary:\r\n#形容詞-非自立\r\n#\r\n# - \ adjective-suffix:\r\n#形容詞-接尾\r\n#\r\n#####\r\n# adverb: unclassified adverbs\r\n#副詞\r\n#\r\n# - \ adverb-misc: Words that can be segmented into one unit and where adnominal \r\n# - \ modification is not possible.\r\n# e.g. あいかわらず, 多分\r\n#副詞-一般\r\n#\r\n# adverb-particle_conjunction: - Adverbs that can be followed by の, は, に, \r\n# な, する, だ, etc.\r\n# e.g. こんなに, - そんなに, あんなに, なにか, なんでも\r\n#副詞-助詞類接続\r\n#\r\n#####\r\n# adnominal: Words that only - have noun-modifying forms.\r\n# 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, \r\n# 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, - \r\n# 「(, 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\r\n#連体詞\r\n#\r\n#####\r\n# - \ conjunction: Conjunctions that can occur independently.\r\n# e.g. が, けれども, - そして, じゃあ, それどころか\r\n接続詞\r\n#\r\n#####\r\n# particle: unclassified particles.\r\n助詞\r\n#\r\n# - \ particle-case: case particles where the subclassification is undefined.\r\n助詞-格助詞\r\n#\r\n# - \ particle-case-misc: Case particles.\r\n# e.g. から, が, で, と, に, へ, より, を, の, - にて\r\n助詞-格助詞-一般\r\n#\r\n# particle-case-quote: the \"to\" that appears after - nouns, a person’s speech, \r\n# quotation marks, expressions of decisions from - a meeting, reasons, judgements,\r\n# conjectures, etc.\r\n# e.g. ( だ) と (述べた.), - ( である) と (して執行猶予...)\r\n助詞-格助詞-引用\r\n#\r\n# particle-case-compound: Compounds - of particles and verbs that mainly behave \r\n# like case particles.\r\n# 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,\r\n# 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, \r\n# 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, \r\n# 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, \r\n# 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,\r\n# 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, \r\n# - \ 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,\r\n# 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\r\n助詞-格助詞-連語\r\n#\r\n# particle-conjunctive:\r\n# - \ 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, \r\n# 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/, \r\n# (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/\r\n助詞-接続助詞\r\n#\r\n# particle-dependency:\r\n# - \ e.g. こそ, さえ, しか, すら, は, も, ぞ\r\n助詞-係助詞\r\n#\r\n# particle-adverbial:\r\n# 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/, \r\n# (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/,\r\n# (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, \r\n# (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/,\r\n# 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」)\r\n助詞-副助詞\r\n#\r\n# particle-interjective: particles with interjective - grammatical roles.\r\n# e.g. (松島) や\r\n助詞-間投助詞\r\n#\r\n# particle-coordinate:\r\n# - \ e.g. と, たり, だの, だり, とか, なり, や, やら\r\n助詞-並立助詞\r\n#\r\n# particle-final:\r\n# - \ 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, \r\n# 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/\r\n助詞-終助詞\r\n#\r\n# particle-adverbial/conjunctive/final: - The particle \"ka\" when unknown whether it is \r\n# adverbial, conjunctive, - or sentence final. For example:\r\n# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) - か (.)」\r\n# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」\r\n# - \ 「(祈りが届いたせい) か (, 試験に合格した.)」\r\n# (c) 「かのように」. Ex:「(何もなかった) か - (のように振る舞った.)」\r\n# e.g. か\r\n助詞-副助詞／並立助詞／終助詞\r\n#\r\n# particle-adnominalizer: - The \"no\" that attaches to nouns and modifies \r\n# non-inflectional words.\r\n助詞-連体化\r\n#\r\n# - \ particle-adnominalizer: The \"ni\" and \"to\" that appear following nouns and - adverbs \r\n# that are giongo, giseigo, or gitaigo.\r\n# e.g. に, と\r\n助詞-副詞化\r\n#\r\n# - \ particle-special: A particle that does not fit into one of the above classifications. - \r\n# This includes particles that are used in Tanka, Haiku, and other poetry.\r\n# - \ e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)\r\n助詞-特殊\r\n#\r\n#####\r\n# - \ auxiliary-verb:\r\n助動詞\r\n#\r\n#####\r\n# interjection: Greetings and other - exclamations.\r\n# 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, - \r\n# 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\r\n#感動詞\r\n#\r\n#####\r\n# - \ symbol: unclassified Symbols.\r\n記号\r\n#\r\n# symbol-misc: A general symbol - not in one of the categories below.\r\n# e.g. [○◎@$〒→+]\r\n記号-一般\r\n#\r\n# symbol-comma: - Commas\r\n# e.g. [,、]\r\n記号-読点\r\n#\r\n# symbol-period: Periods and full stops.\r\n# - \ e.g. [.．。]\r\n記号-句点\r\n#\r\n# symbol-space: Full-width whitespace.\r\n記号-空白\r\n#\r\n# - \ symbol-open_bracket:\r\n# e.g. [({‘“『【]\r\n記号-括弧開\r\n#\r\n# symbol-close_bracket:\r\n# - \ e.g. [)}’”』」】]\r\n記号-括弧閉\r\n#\r\n# symbol-alphabetic:\r\n#記号-アルファベット\r\n#\r\n#####\r\n# - \ other: unclassified other\r\n#その他\r\n#\r\n# other-interjection: Words that - are hard to classify as noun-suffixes or \r\n# sentence-final particles.\r\n# - \ e.g. (だ)ァ\r\nその他-間投\r\n#\r\n#####\r\n# filler: Aizuchi that occurs during a - conversation or sounds inserted as filler.\r\n# e.g. あの, うんと, えと\r\nフィラー\r\n#\r\n#####\r\n# - \ non-verbal: non-verbal sound.\r\n非言語音\r\n#\r\n#####\r\n# fragment:\r\n#語断片\r\n#\r\n#####\r\n# - \ unknown: unknown part of speech.\r\n#未知語\r\n#\r\n##### End of file\r\n" - stopwords.txt: |- - # 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. - stopwords_ar.txt: "# This file was created by Jacques Savoy and is distributed under - the BSD license.\r\n# See http://members.unine.ch/jacques.savoy/clef/index.html.\r\n# - Also see http://www.opensource.org/licenses/bsd-license.html\r\n# Cleaned on October - 11, 2009 (not normalized, so use before normalization)\r\n# This means that when - modifying this list, you might need to add some \r\n# redundant entries, for example - containing forms with both أ and ا\r\nمن\r\nومن\r\nمنها\r\nمنه\r\nفي\r\nوفي\r\nفيها\r\nفيه\r\nو\r\nف\r\nثم\r\nاو\r\nأو\r\nب\r\nبها\r\nبه\r\nا\r\nأ\r\nاى\r\nاي\r\nأي\r\nأى\r\nلا\r\nولا\r\nالا\r\nألا\r\nإلا\r\nلكن\r\nما\r\nوما\r\nكما\r\nفما\r\nعن\r\nمع\r\nاذا\r\nإذا\r\nان\r\nأن\r\nإن\r\nانها\r\nأنها\r\nإنها\r\nانه\r\nأنه\r\nإنه\r\nبان\r\nبأن\r\nفان\r\nفأن\r\nوان\r\nوأن\r\nوإن\r\nالتى\r\nالتي\r\nالذى\r\nالذي\r\nالذين\r\nالى\r\nالي\r\nإلى\r\nإلي\r\nعلى\r\nعليها\r\nعليه\r\nاما\r\nأما\r\nإما\r\nايضا\r\nأيضا\r\nكل\r\nوكل\r\nلم\r\nولم\r\nلن\r\nولن\r\nهى\r\nهي\r\nهو\r\nوهى\r\nوهي\r\nوهو\r\nفهى\r\nفهي\r\nفهو\r\nانت\r\nأنت\r\nلك\r\nلها\r\nله\r\nهذه\r\nهذا\r\nتلك\r\nذلك\r\nهناك\r\nكانت\r\nكان\r\nيكون\r\nتكون\r\nوكانت\r\nوكان\r\nغير\r\nبعض\r\nقد\r\nنحو\r\nبين\r\nبينما\r\nمنذ\r\nضمن\r\nحيث\r\nالان\r\nالآن\r\nخلال\r\nبعد\r\nقبل\r\nحتى\r\nعند\r\nعندما\r\nلدى\r\nجميع\r\n" - stopwords_bg.txt: "# This file was created by Jacques Savoy and is distributed under - the BSD license.\r\n# See http://members.unine.ch/jacques.savoy/clef/index.html.\r\n# - Also see http://www.opensource.org/licenses/bsd-license.html\r\nа\r\nаз\r\nако\r\nала\r\nбе\r\nбез\r\nбеше\r\nби\r\nбил\r\nбила\r\nбили\r\nбило\r\nблизо\r\nбъдат\r\nбъде\r\nбяха\r\nв\r\nвас\r\nваш\r\nваша\r\nвероятно\r\nвече\r\nвзема\r\nви\r\nвие\r\nвинаги\r\nвсе\r\nвсеки\r\nвсички\r\nвсичко\r\nвсяка\r\nвъв\r\nвъпреки\r\nвърху\r\nг\r\nги\r\nглавно\r\nго\r\nд\r\nда\r\nдали\r\nдо\r\nдокато\r\nдокога\r\nдори\r\nдосега\r\nдоста\r\nе\r\nедва\r\nедин\r\nето\r\nза\r\nзад\r\nзаедно\r\nзаради\r\nзасега\r\nзатова\r\nзащо\r\nзащото\r\nи\r\nиз\r\nили\r\nим\r\nима\r\nимат\r\nиска\r\nй\r\nказа\r\nкак\r\nкаква\r\nкакво\r\nкакто\r\nкакъв\r\nкато\r\nкога\r\nкогато\r\nкоето\r\nкоито\r\nкой\r\nкойто\r\nколко\r\nкоято\r\nкъде\r\nкъдето\r\nкъм\r\nли\r\nм\r\nме\r\nмежду\r\nмен\r\nми\r\nмнозина\r\nмога\r\nмогат\r\nможе\r\nмоля\r\nмомента\r\nму\r\nн\r\nна\r\nнад\r\nназад\r\nнай\r\nнаправи\r\nнапред\r\nнапример\r\nнас\r\nне\r\nнего\r\nнея\r\nни\r\nние\r\nникой\r\nнито\r\nно\r\nнякои\r\nнякой\r\nняма\r\nобаче\r\nоколо\r\nосвен\r\nособено\r\nот\r\nотгоре\r\nотново\r\nоще\r\nпак\r\nпо\r\nповече\r\nповечето\r\nпод\r\nпоне\r\nпоради\r\nпосле\r\nпочти\r\nправи\r\nпред\r\nпреди\r\nпрез\r\nпри\r\nпък\r\nпърво\r\nс\r\nса\r\nсамо\r\nсе\r\nсега\r\nси\r\nскоро\r\nслед\r\nсме\r\nспоред\r\nсред\r\nсрещу\r\nсте\r\nсъм\r\nсъс\r\nсъщо\r\nт\r\nтази\r\nтака\r\nтакива\r\nтакъв\r\nтам\r\nтвой\r\nте\r\nтези\r\nти\r\nтн\r\nто\r\nтова\r\nтогава\r\nтози\r\nтой\r\nтолкова\r\nточно\r\nтрябва\r\nтук\r\nтъй\r\nтя\r\nтях\r\nу\r\nхаресва\r\nч\r\nче\r\nчесто\r\nчрез\r\nще\r\nщом\r\nя\r\n" - stopwords_ca.txt: "# Catalan stopwords from http://github.com/vcl/cue.language (Apache - 2 Licensed)\r\na\r\nabans\r\nací\r\nah\r\naixí\r\naixò\r\nal\r\nals\r\naleshores\r\nalgun\r\nalguna\r\nalgunes\r\nalguns\r\nalhora\r\nallà\r\nallí\r\nallò\r\naltra\r\naltre\r\naltres\r\namb\r\nambdós\r\nambdues\r\napa\r\naquell\r\naquella\r\naquelles\r\naquells\r\naquest\r\naquesta\r\naquestes\r\naquests\r\naquí\r\nbaix\r\ncada\r\ncadascú\r\ncadascuna\r\ncadascunes\r\ncadascuns\r\ncom\r\ncontra\r\nd'un\r\nd'una\r\nd'unes\r\nd'uns\r\ndalt\r\nde\r\ndel\r\ndels\r\ndes\r\ndesprés\r\ndins\r\ndintre\r\ndonat\r\ndoncs\r\ndurant\r\ne\r\neh\r\nel\r\nels\r\nem\r\nen\r\nencara\r\nens\r\nentre\r\nérem\r\neren\r\néreu\r\nes\r\nés\r\nesta\r\nestà\r\nestàvem\r\nestaven\r\nestàveu\r\nesteu\r\net\r\netc\r\nets\r\nfins\r\nfora\r\ngairebé\r\nha\r\nhan\r\nhas\r\nhavia\r\nhe\r\nhem\r\nheu\r\nhi - \r\nho\r\ni\r\nigual\r\niguals\r\nja\r\nl'hi\r\nla\r\nles\r\nli\r\nli'n\r\nllavors\r\nm'he\r\nma\r\nmal\r\nmalgrat\r\nmateix\r\nmateixa\r\nmateixes\r\nmateixos\r\nme\r\nmentre\r\nmés\r\nmeu\r\nmeus\r\nmeva\r\nmeves\r\nmolt\r\nmolta\r\nmoltes\r\nmolts\r\nmon\r\nmons\r\nn'he\r\nn'hi\r\nne\r\nni\r\nno\r\nnogensmenys\r\nnomés\r\nnosaltres\r\nnostra\r\nnostre\r\nnostres\r\no\r\noh\r\noi\r\non\r\npas\r\npel\r\npels\r\nper\r\nperò\r\nperquè\r\npoc - \r\npoca\r\npocs\r\npoques\r\npotser\r\npropi\r\nqual\r\nquals\r\nquan\r\nquant - \r\nque\r\nquè\r\nquelcom\r\nqui\r\nquin\r\nquina\r\nquines\r\nquins\r\ns'ha\r\ns'han\r\nsa\r\nsemblant\r\nsemblants\r\nses\r\nseu - \r\nseus\r\nseva\r\nseva\r\nseves\r\nsi\r\nsobre\r\nsobretot\r\nsóc\r\nsolament\r\nsols\r\nson - \r\nsón\r\nsons \r\nsota\r\nsou\r\nt'ha\r\nt'han\r\nt'he\r\nta\r\ntal\r\ntambé\r\ntampoc\r\ntan\r\ntant\r\ntanta\r\ntantes\r\nteu\r\nteus\r\nteva\r\nteves\r\nton\r\ntons\r\ntot\r\ntota\r\ntotes\r\ntots\r\nun\r\nuna\r\nunes\r\nuns\r\nus\r\nva\r\nvaig\r\nvam\r\nvan\r\nvas\r\nveu\r\nvosaltres\r\nvostra\r\nvostre\r\nvostres\r\n" - stopwords_cz.txt: "a\r\ns\r\nk\r\no\r\ni\r\nu\r\nv\r\nz\r\ndnes\r\ncz\r\ntímto\r\nbudeš\r\nbudem\r\nbyli\r\njseš\r\nmůj\r\nsvým\r\nta\r\ntomto\r\ntohle\r\ntuto\r\ntyto\r\njej\r\nzda\r\nproč\r\nmáte\r\ntato\r\nkam\r\ntohoto\r\nkdo\r\nkteří\r\nmi\r\nnám\r\ntom\r\ntomuto\r\nmít\r\nnic\r\nproto\r\nkterou\r\nbyla\r\ntoho\r\nprotože\r\nasi\r\nho\r\nnaši\r\nnapište\r\nre\r\ncož\r\ntím\r\ntakže\r\nsvých\r\njejí\r\nsvými\r\njste\r\naj\r\ntu\r\ntedy\r\nteto\r\nbylo\r\nkde\r\nke\r\npravé\r\nji\r\nnad\r\nnejsou\r\nči\r\npod\r\ntéma\r\nmezi\r\npřes\r\nty\r\npak\r\nvám\r\nani\r\nkdyž\r\nvšak\r\nneg\r\njsem\r\ntento\r\nčlánku\r\nčlánky\r\naby\r\njsme\r\npřed\r\npta\r\njejich\r\nbyl\r\nještě\r\naž\r\nbez\r\ntaké\r\npouze\r\nprvní\r\nvaše\r\nkterá\r\nnás\r\nnový\r\ntipy\r\npokud\r\nmůže\r\nstrana\r\njeho\r\nsvé\r\njiné\r\nzprávy\r\nnové\r\nnení\r\nvás\r\njen\r\npodle\r\nzde\r\nuž\r\nbýt\r\nvíce\r\nbude\r\njiž\r\nnež\r\nkterý\r\nby\r\nkteré\r\nco\r\nnebo\r\nten\r\ntak\r\nmá\r\npři\r\nod\r\npo\r\njsou\r\njak\r\ndalší\r\nale\r\nsi\r\nse\r\nve\r\nto\r\njako\r\nza\r\nzpět\r\nze\r\ndo\r\npro\r\nje\r\nna\r\natd\r\natp\r\njakmile\r\npřičemž\r\njá\r\non\r\nona\r\nono\r\noni\r\nony\r\nmy\r\nvy\r\njí\r\nji\r\nmě\r\nmne\r\njemu\r\ntomu\r\ntěm\r\ntěmu\r\nněmu\r\nněmuž\r\njehož\r\njíž\r\njelikož\r\njež\r\njakož\r\nnačež\r\n" - stopwords_da.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Danish stop word list. Comments begin with vertical bar. Each stop\r\n | word - is at the start of a line.\r\n\r\n | This is a ranked list (commonest to rarest) - of stopwords derived from\r\n | a large text sample.\r\n\r\n\r\nog | - and\r\ni | in\r\njeg | I\r\ndet | that (dem. pronoun)/it - (pers. pronoun)\r\nat | that (in front of a sentence)/to (with infinitive)\r\nen - \ | a/an\r\nden | it (pers. pronoun)/that (dem. pronoun)\r\ntil - \ | to/at/for/until/against/by/of/into, more\r\ner | present - tense of \"to be\"\r\nsom | who, as\r\npå | on/upon/in/on/at/to/after/of/with/for, - on\r\nde | they\r\nmed | with/by/in, along\r\nhan | - he\r\naf | of/by/from/off/for/in/with/on, off\r\nfor | at/for/to/from/by/of/ago, - in front/before, because\r\nikke | not\r\nder | who/which, there/those\r\nvar - \ | past tense of \"to be\"\r\nmig | me/myself\r\nsig | - oneself/himself/herself/itself/themselves\r\nmen | but\r\net | - a/an/one, one (number), someone/somebody/one\r\nhar | present tense of - \"to have\"\r\nom | round/about/for/in/a, about/around/down, if\r\nvi - \ | we\r\nmin | my\r\nhavde | past tense of \"to have\"\r\nham - \ | him\r\nhun | she\r\nnu | now\r\nover | - over/above/across/by/beyond/past/on/about, over/past\r\nda | then, when/as/since\r\nfra - \ | from/off/since, off, since\r\ndu | you\r\nud | - out\r\nsin | his/her/its/one's\r\ndem | them\r\nos | - us/ourselves\r\nop | up\r\nman | you/one\r\nhans | - his\r\nhvor | where\r\neller | or\r\nhvad | what\r\nskal - \ | must/shall etc.\r\nselv | myself/youself/herself/ourselves - etc., even\r\nher | here\r\nalle | all/everyone/everybody etc.\r\nvil - \ | will (verb)\r\nblev | past tense of \"to stay/to remain/to - get/to become\"\r\nkunne | could\r\nind | in\r\nnår | - when\r\nvære | present tense of \"to be\"\r\ndog | however/yet/after - all\r\nnoget | something\r\nville | would\r\njo | you - know/you see (adv), yes\r\nderes | their/theirs\r\nefter | after/behind/according - to/for/by/from, later/afterwards\r\nned | down\r\nskulle | should\r\ndenne - \ | this\r\nend | than\r\ndette | this\r\nmit | - my/mine\r\nogså | also\r\nunder | under/beneath/below/during, below/underneath\r\nhave - \ | have\r\ndig | you\r\nanden | other\r\nhende | - her\r\nmine | my\r\nalt | everything\r\nmeget | much/very, - plenty of\r\nsit | his, her, its, one's\r\nsine | his, her, its, - one's\r\nvor | our\r\nmod | against\r\ndisse | these\r\nhvis - \ | if\r\ndin | your/yours\r\nnogle | some\r\nhos | - by/at\r\nblive | be/become\r\nmange | many\r\nad | by/through\r\nbliver - \ | present tense of \"to be/to become\"\r\nhendes | her/hers\r\nværet - \ | be\r\nthi | for (conj)\r\njer | you\r\nsådan | - such, like this/like that\r\n" - stopwords_de.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A German stop word list. Comments begin with vertical bar. Each stop\r\n | word - is at the start of a line.\r\n\r\n | The number of forms in this list is reduced - significantly by passing it\r\n | through the German stemmer.\r\n\r\n\r\naber - \ | but\r\n\r\nalle | all\r\nallem\r\nallen\r\naller\r\nalles\r\n\r\nals - \ | than, as\r\nalso | so\r\nam | an + dem\r\nan - \ | at\r\n\r\nander | other\r\nandere\r\nanderem\r\nanderen\r\nanderer\r\nanderes\r\nanderm\r\nandern\r\nanderr\r\nanders\r\n\r\nauch - \ | also\r\nauf | on\r\naus | out of\r\nbei - \ | by\r\nbin | am\r\nbis | until\r\nbist | - \ art\r\nda | there\r\ndamit | with it\r\ndann | - \ then\r\n\r\nder | the\r\nden\r\ndes\r\ndem\r\ndie\r\ndas\r\n\r\ndaß - \ | that\r\n\r\nderselbe | the same\r\nderselben\r\ndenselben\r\ndesselben\r\ndemselben\r\ndieselbe\r\ndieselben\r\ndasselbe\r\n\r\ndazu - \ | to that\r\n\r\ndein | thy\r\ndeine\r\ndeinem\r\ndeinen\r\ndeiner\r\ndeines\r\n\r\ndenn - \ | because\r\n\r\nderer | of those\r\ndessen | of - him\r\n\r\ndich | thee\r\ndir | to thee\r\ndu | - \ thou\r\n\r\ndies | this\r\ndiese\r\ndiesem\r\ndiesen\r\ndieser\r\ndieses\r\n\r\n\r\ndoch - \ | (several meanings)\r\ndort | (over) there\r\n\r\n\r\ndurch - \ | through\r\n\r\nein | a\r\neine\r\neinem\r\neinen\r\neiner\r\neines\r\n\r\neinig - \ | some\r\neinige\r\neinigem\r\neinigen\r\neiniger\r\neiniges\r\n\r\neinmal - \ | once\r\n\r\ner | he\r\nihn | him\r\nihm | - \ to him\r\n\r\nes | it\r\netwas | something\r\n\r\neuer - \ | your\r\neure\r\neurem\r\neuren\r\neurer\r\neures\r\n\r\nfür | - \ for\r\ngegen | towards\r\ngewesen | p.p. of sein\r\nhab | - \ have\r\nhabe | have\r\nhaben | have\r\nhat | - \ has\r\nhatte | had\r\nhatten | had\r\nhier | here\r\nhin - \ | there\r\nhinter | behind\r\n\r\nich | I\r\nmich - \ | me\r\nmir | to me\r\n\r\n\r\nihr | you, - to her\r\nihre\r\nihrem\r\nihren\r\nihrer\r\nihres\r\neuch | to you\r\n\r\nim - \ | in + dem\r\nin | in\r\nindem | while\r\nins - \ | in + das\r\nist | is\r\n\r\njede | each, - every\r\njedem\r\njeden\r\njeder\r\njedes\r\n\r\njene | that\r\njenem\r\njenen\r\njener\r\njenes\r\n\r\njetzt - \ | now\r\nkann | can\r\n\r\nkein | no\r\nkeine\r\nkeinem\r\nkeinen\r\nkeiner\r\nkeines\r\n\r\nkönnen - \ | can\r\nkönnte | could\r\nmachen | do\r\nman | - \ one\r\n\r\nmanche | some, many a\r\nmanchem\r\nmanchen\r\nmancher\r\nmanches\r\n\r\nmein - \ | my\r\nmeine\r\nmeinem\r\nmeinen\r\nmeiner\r\nmeines\r\n\r\nmit | - \ with\r\nmuss | must\r\nmusste | had to\r\nnach | - \ to(wards)\r\nnicht | not\r\nnichts | nothing\r\nnoch | - \ still, yet\r\nnun | now\r\nnur | only\r\nob | - \ whether\r\noder | or\r\nohne | without\r\nsehr | - \ very\r\n\r\nsein | his\r\nseine\r\nseinem\r\nseinen\r\nseiner\r\nseines\r\n\r\nselbst - \ | self\r\nsich | herself\r\n\r\nsie | they, she\r\nihnen - \ | to them\r\n\r\nsind | are\r\nso | so\r\n\r\nsolche - \ | such\r\nsolchem\r\nsolchen\r\nsolcher\r\nsolches\r\n\r\nsoll | - \ shall\r\nsollte | should\r\nsondern | but\r\nsonst | - \ else\r\nüber | over\r\num | about, around\r\nund | - \ and\r\n\r\nuns | us\r\nunse\r\nunsem\r\nunsen\r\nunser\r\nunses\r\n\r\nunter - \ | under\r\nviel | much\r\nvom | von + dem\r\nvon - \ | from\r\nvor | before\r\nwährend | while\r\nwar - \ | was\r\nwaren | were\r\nwarst | wast\r\nwas - \ | what\r\nweg | away, off\r\nweil | because\r\nweiter - \ | further\r\n\r\nwelche | which\r\nwelchem\r\nwelchen\r\nwelcher\r\nwelches\r\n\r\nwenn - \ | when\r\nwerde | will\r\nwerden | will\r\nwie - \ | how\r\nwieder | again\r\nwill | want\r\nwir - \ | we\r\nwird | will\r\nwirst | willst\r\nwo - \ | where\r\nwollen | want\r\nwollte | wanted\r\nwürde - \ | would\r\nwürden | would\r\nzu | to\r\nzum | - \ zu + dem\r\nzur | zu + der\r\nzwar | indeed\r\nzwischen - \ | between\r\n\r\n" - stopwords_el.txt: "# Lucene Greek Stopwords list\r\n# Note: by default this file - is used after GreekLowerCaseFilter,\r\n# so when modifying this file use 'σ' instead - of 'ς' \r\nο\r\nη\r\nτο\r\nοι\r\nτα\r\nτου\r\nτησ\r\nτων\r\nτον\r\nτην\r\nκαι - \r\nκι\r\nκ\r\nειμαι\r\nεισαι\r\nειναι\r\nειμαστε\r\nειστε\r\nστο\r\nστον\r\nστη\r\nστην\r\nμα\r\nαλλα\r\nαπο\r\nγια\r\nπροσ\r\nμε\r\nσε\r\nωσ\r\nπαρα\r\nαντι\r\nκατα\r\nμετα\r\nθα\r\nνα\r\nδε\r\nδεν\r\nμη\r\nμην\r\nεπι\r\nενω\r\nεαν\r\nαν\r\nτοτε\r\nπου\r\nπωσ\r\nποιοσ\r\nποια\r\nποιο\r\nποιοι\r\nποιεσ\r\nποιων\r\nποιουσ\r\nαυτοσ\r\nαυτη\r\nαυτο\r\nαυτοι\r\nαυτων\r\nαυτουσ\r\nαυτεσ\r\nαυτα\r\nεκεινοσ\r\nεκεινη\r\nεκεινο\r\nεκεινοι\r\nεκεινεσ\r\nεκεινα\r\nεκεινων\r\nεκεινουσ\r\nοπωσ\r\nομωσ\r\nισωσ\r\nοσο\r\nοτι\r\n" - stopwords_en.txt: | - # 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 - stopwords_es.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Spanish stop word list. Comments begin with vertical bar. Each stop\r\n | - word is at the start of a line.\r\n\r\n\r\n | The following is a ranked list (commonest - to rarest) of stopwords\r\n | deriving from a large sample of text.\r\n\r\n | - Extra words have been added at the end.\r\n\r\nde | from, of\r\nla - \ | the, her\r\nque | who, that\r\nel | the\r\nen - \ | in\r\ny | and\r\na | to\r\nlos | - \ the, them\r\ndel | de + el\r\nse | himself, from him - etc\r\nlas | the, them\r\npor | for, by, etc\r\nun | - \ a\r\npara | for\r\ncon | with\r\nno | no\r\nuna - \ | a\r\nsu | his, her\r\nal | a + el\r\n - \ | es from SER\r\nlo | him\r\ncomo | how\r\nmás - \ | more\r\npero | pero\r\nsus | su plural\r\nle - \ | to him, her\r\nya | already\r\no | or\r\n - \ | fue from SER\r\neste | this\r\n | ha from HABER\r\nsí - \ | himself etc\r\nporque | because\r\nesta | this\r\n - \ | son from SER\r\nentre | between\r\n | está from ESTAR\r\ncuando - \ | when\r\nmuy | very\r\nsin | without\r\nsobre - \ | on\r\n | ser from SER\r\n | tiene from TENER\r\ntambién - \ | also\r\nme | me\r\nhasta | until\r\nhay | - \ there is/are\r\ndonde | where\r\n | han from HABER\r\nquien - \ | whom, that\r\n | están from ESTAR\r\n | estado from ESTAR\r\ndesde - \ | from\r\ntodo | all\r\nnos | us\r\ndurante - \ | during\r\n | estados from ESTAR\r\ntodos | all\r\nuno - \ | a\r\nles | to them\r\nni | nor\r\ncontra - \ | against\r\notros | other\r\n | fueron from SER\r\nese - \ | that\r\neso | that\r\n | había from HABER\r\nante - \ | before\r\nellos | they\r\ne | and (variant - of y)\r\nesto | this\r\nmí | me\r\nantes | before\r\nalgunos - \ | some\r\nqué | what?\r\nunos | a\r\nyo | - \ I\r\notro | other\r\notras | other\r\notra | - \ other\r\nél | he\r\ntanto | so much, many\r\nesa | - \ that\r\nestos | these\r\nmucho | much, many\r\nquienes | - \ who\r\nnada | nothing\r\nmuchos | many\r\ncual | - \ who\r\n | sea from SER\r\npoco | few\r\nella | - \ she\r\nestar | to be\r\n | haber from HABER\r\nestas | - \ these\r\n | estaba from ESTAR\r\n | estamos from ESTAR\r\nalgunas | - \ some\r\nalgo | something\r\nnosotros | we\r\n\r\n | other - forms\r\n\r\nmi | me\r\nmis | mi plural\r\ntú | - \ thou\r\nte | thee\r\nti | thee\r\ntu | - \ thy\r\ntus | tu plural\r\nellas | they\r\nnosotras | - \ we\r\nvosotros | you\r\nvosotras | you\r\nos | you\r\nmío - \ | mine\r\nmía |\r\nmíos |\r\nmías |\r\ntuyo - \ | thine\r\ntuya |\r\ntuyos |\r\ntuyas |\r\nsuyo - \ | his, hers, theirs\r\nsuya |\r\nsuyos |\r\nsuyas - \ |\r\nnuestro | ours\r\nnuestra |\r\nnuestros |\r\nnuestras - \ |\r\nvuestro | yours\r\nvuestra |\r\nvuestros |\r\nvuestras - \ |\r\nesos | those\r\nesas | those\r\n\r\n | - forms of estar, to be (not including the infinitive):\r\nestoy\r\nestás\r\nestá\r\nestamos\r\nestáis\r\nestán\r\nesté\r\nestés\r\nestemos\r\nestéis\r\nestén\r\nestaré\r\nestarás\r\nestará\r\nestaremos\r\nestaréis\r\nestarán\r\nestaría\r\nestarías\r\nestaríamos\r\nestaríais\r\nestarían\r\nestaba\r\nestabas\r\nestábamos\r\nestabais\r\nestaban\r\nestuve\r\nestuviste\r\nestuvo\r\nestuvimos\r\nestuvisteis\r\nestuvieron\r\nestuviera\r\nestuvieras\r\nestuviéramos\r\nestuvierais\r\nestuvieran\r\nestuviese\r\nestuvieses\r\nestuviésemos\r\nestuvieseis\r\nestuviesen\r\nestando\r\nestado\r\nestada\r\nestados\r\nestadas\r\nestad\r\n\r\n - \ | forms of haber, to have (not including the infinitive):\r\nhe\r\nhas\r\nha\r\nhemos\r\nhabéis\r\nhan\r\nhaya\r\nhayas\r\nhayamos\r\nhayáis\r\nhayan\r\nhabré\r\nhabrás\r\nhabrá\r\nhabremos\r\nhabréis\r\nhabrán\r\nhabría\r\nhabrías\r\nhabríamos\r\nhabríais\r\nhabrían\r\nhabía\r\nhabías\r\nhabíamos\r\nhabíais\r\nhabían\r\nhube\r\nhubiste\r\nhubo\r\nhubimos\r\nhubisteis\r\nhubieron\r\nhubiera\r\nhubieras\r\nhubiéramos\r\nhubierais\r\nhubieran\r\nhubiese\r\nhubieses\r\nhubiésemos\r\nhubieseis\r\nhubiesen\r\nhabiendo\r\nhabido\r\nhabida\r\nhabidos\r\nhabidas\r\n\r\n - \ | forms of ser, to be (not including the infinitive):\r\nsoy\r\neres\r\nes\r\nsomos\r\nsois\r\nson\r\nsea\r\nseas\r\nseamos\r\nseáis\r\nsean\r\nseré\r\nserás\r\nserá\r\nseremos\r\nseréis\r\nserán\r\nsería\r\nserías\r\nseríamos\r\nseríais\r\nserían\r\nera\r\neras\r\néramos\r\nerais\r\neran\r\nfui\r\nfuiste\r\nfue\r\nfuimos\r\nfuisteis\r\nfueron\r\nfuera\r\nfueras\r\nfuéramos\r\nfuerais\r\nfueran\r\nfuese\r\nfueses\r\nfuésemos\r\nfueseis\r\nfuesen\r\nsiendo\r\nsido\r\n - \ | sed also means 'thirst'\r\n\r\n | forms of tener, to have (not - including the infinitive):\r\ntengo\r\ntienes\r\ntiene\r\ntenemos\r\ntenéis\r\ntienen\r\ntenga\r\ntengas\r\ntengamos\r\ntengáis\r\ntengan\r\ntendré\r\ntendrás\r\ntendrá\r\ntendremos\r\ntendréis\r\ntendrán\r\ntendría\r\ntendrías\r\ntendríamos\r\ntendríais\r\ntendrían\r\ntenía\r\ntenías\r\nteníamos\r\nteníais\r\ntenían\r\ntuve\r\ntuviste\r\ntuvo\r\ntuvimos\r\ntuvisteis\r\ntuvieron\r\ntuviera\r\ntuvieras\r\ntuviéramos\r\ntuvierais\r\ntuvieran\r\ntuviese\r\ntuvieses\r\ntuviésemos\r\ntuvieseis\r\ntuviesen\r\nteniendo\r\ntenido\r\ntenida\r\ntenidos\r\ntenidas\r\ntened\r\n\r\n" - stopwords_eu.txt: "# example set of basque stopwords\r\nal\r\nanitz\r\narabera\r\nasko\r\nbaina\r\nbat\r\nbatean\r\nbatek\r\nbati\r\nbatzuei\r\nbatzuek\r\nbatzuetan\r\nbatzuk\r\nbera\r\nberaiek\r\nberau\r\nberauek\r\nbere\r\nberori\r\nberoriek\r\nbeste\r\nbezala\r\nda\r\ndago\r\ndira\r\nditu\r\ndu\r\ndute\r\nedo\r\negin\r\nere\r\neta\r\neurak\r\nez\r\ngainera\r\ngu\r\ngutxi\r\nguzti\r\nhaiei\r\nhaiek\r\nhaietan\r\nhainbeste\r\nhala\r\nhan\r\nhandik\r\nhango\r\nhara\r\nhari\r\nhark\r\nhartan\r\nhau\r\nhauei\r\nhauek\r\nhauetan\r\nhemen\r\nhemendik\r\nhemengo\r\nhi\r\nhona\r\nhonek\r\nhonela\r\nhonetan\r\nhoni\r\nhor\r\nhori\r\nhoriei\r\nhoriek\r\nhorietan\r\nhorko\r\nhorra\r\nhorrek\r\nhorrela\r\nhorretan\r\nhorri\r\nhortik\r\nhura\r\nizan\r\nni\r\nnoiz\r\nnola\r\nnon\r\nnondik\r\nnongo\r\nnor\r\nnora\r\nze\r\nzein\r\nzen\r\nzenbait\r\nzenbat\r\nzer\r\nzergatik\r\nziren\r\nzituen\r\nzu\r\nzuek\r\nzuen\r\nzuten\r\n" - stopwords_fa.txt: "# This file was created by Jacques Savoy and is distributed under - the BSD license.\r\n# See http://members.unine.ch/jacques.savoy/clef/index.html.\r\n# - Also see http://www.opensource.org/licenses/bsd-license.html\r\n# Note: by default - this file is used after normalization, so when adding entries\r\n# to this file, - use the arabic 'ي' instead of 'ی'\r\nانان\r\nنداشته\r\nسراسر\r\nخياه\r\nايشان\r\nوي\r\nتاكنون\r\nبيشتري\r\nدوم\r\nپس\r\nناشي\r\nوگو\r\nيا\r\nداشتند\r\nسپس\r\nهنگام\r\nهرگز\r\nپنج\r\nنشان\r\nامسال\r\nديگر\r\nگروهي\r\nشدند\r\nچطور\r\nده\r\nو\r\nدو\r\nنخستين\r\nولي\r\nچرا\r\nچه\r\nوسط\r\nه\r\nكدام\r\nقابل\r\nيك\r\nرفت\r\nهفت\r\nهمچنين\r\nدر\r\nهزار\r\nبله\r\nبلي\r\nشايد\r\nاما\r\nشناسي\r\nگرفته\r\nدهد\r\nداشته\r\nدانست\r\nداشتن\r\nخواهيم\r\nميليارد\r\nوقتيكه\r\nامد\r\nخواهد\r\nجز\r\nاورده\r\nشده\r\nبلكه\r\nخدمات\r\nشدن\r\nبرخي\r\nنبود\r\nبسياري\r\nجلوگيري\r\nحق\r\nكردند\r\nنوعي\r\nبعري\r\nنكرده\r\nنظير\r\nنبايد\r\nبوده\r\nبودن\r\nداد\r\nاورد\r\nهست\r\nجايي\r\nشود\r\nدنبال\r\nداده\r\nبايد\r\nسابق\r\nهيچ\r\nهمان\r\nانجا\r\nكمتر\r\nكجاست\r\nگردد\r\nكسي\r\nتر\r\nمردم\r\nتان\r\nدادن\r\nبودند\r\nسري\r\nجدا\r\nندارند\r\nمگر\r\nيكديگر\r\nدارد\r\nدهند\r\nبنابراين\r\nهنگامي\r\nسمت\r\nجا\r\nانچه\r\nخود\r\nدادند\r\nزياد\r\nدارند\r\nاثر\r\nبدون\r\nبهترين\r\nبيشتر\r\nالبته\r\nبه\r\nبراساس\r\nبيرون\r\nكرد\r\nبعضي\r\nگرفت\r\nتوي\r\nاي\r\nميليون\r\nاو\r\nجريان\r\nتول\r\nبر\r\nمانند\r\nبرابر\r\nباشيم\r\nمدتي\r\nگويند\r\nاكنون\r\nتا\r\nتنها\r\nجديد\r\nچند\r\nبي\r\nنشده\r\nكردن\r\nكردم\r\nگويد\r\nكرده\r\nكنيم\r\nنمي\r\nنزد\r\nروي\r\nقصد\r\nفقط\r\nبالاي\r\nديگران\r\nاين\r\nديروز\r\nتوسط\r\nسوم\r\nايم\r\nدانند\r\nسوي\r\nاستفاده\r\nشما\r\nكنار\r\nداريم\r\nساخته\r\nطور\r\nامده\r\nرفته\r\nنخست\r\nبيست\r\nنزديك\r\nطي\r\nكنيد\r\nاز\r\nانها\r\nتمامي\r\nداشت\r\nيكي\r\nطريق\r\nاش\r\nچيست\r\nروب\r\nنمايد\r\nگفت\r\nچندين\r\nچيزي\r\nتواند\r\nام\r\nايا\r\nبا\r\nان\r\nايد\r\nترين\r\nاينكه\r\nديگري\r\nراه\r\nهايي\r\nبروز\r\nهمچنان\r\nپاعين\r\nكس\r\nحدود\r\nمختلف\r\nمقابل\r\nچيز\r\nگيرد\r\nندارد\r\nضد\r\nهمچون\r\nسازي\r\nشان\r\nمورد\r\nباره\r\nمرسي\r\nخويش\r\nبرخوردار\r\nچون\r\nخارج\r\nشش\r\nهنوز\r\nتحت\r\nضمن\r\nهستيم\r\nگفته\r\nفكر\r\nبسيار\r\nپيش\r\nبراي\r\nروزهاي\r\nانكه\r\nنخواهد\r\nبالا\r\nكل\r\nوقتي\r\nكي\r\nچنين\r\nكه\r\nگيري\r\nنيست\r\nاست\r\nكجا\r\nكند\r\nنيز\r\nيابد\r\nبندي\r\nحتي\r\nتوانند\r\nعقب\r\nخواست\r\nكنند\r\nبين\r\nتمام\r\nهمه\r\nما\r\nباشند\r\nمثل\r\nشد\r\nاري\r\nباشد\r\nاره\r\nطبق\r\nبعد\r\nاگر\r\nصورت\r\nغير\r\nجاي\r\nبيش\r\nريزي\r\nاند\r\nزيرا\r\nچگونه\r\nبار\r\nلطفا\r\nمي\r\nدرباره\r\nمن\r\nديده\r\nهمين\r\nگذاري\r\nبرداري\r\nعلت\r\nگذاشته\r\nهم\r\nفوق\r\nنه\r\nها\r\nشوند\r\nاباد\r\nهمواره\r\nهر\r\nاول\r\nخواهند\r\nچهار\r\nنام\r\nامروز\r\nمان\r\nهاي\r\nقبل\r\nكنم\r\nسعي\r\nتازه\r\nرا\r\nهستند\r\nزير\r\nجلوي\r\nعنوان\r\nبود\r\n" - stopwords_fi.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n \r\n| - forms of BE\r\n\r\nolla\r\nolen\r\nolet\r\non\r\nolemme\r\nolette\r\novat\r\nole - \ | negative form\r\n\r\noli\r\nolisi\r\nolisit\r\nolisin\r\nolisimme\r\nolisitte\r\nolisivat\r\nolit\r\nolin\r\nolimme\r\nolitte\r\nolivat\r\nollut\r\nolleet\r\n\r\nen - \ | negation\r\net\r\nei\r\nemme\r\nette\r\neivät\r\n\r\n|Nom Gen Acc - \ Part Iness Elat Illat Adess Ablat Allat Ess Trans\r\nminä - \ minun minut minua minussa minusta minuun minulla minulta minulle | - I\r\nsinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle - \ | you\r\nhän hänen hänet häntä hänessä hänestä häneen hänellä - häneltä hänelle | he she\r\nme meidän meidät meitä meissä meistä - \ meihin meillä meiltä meille | we\r\nte teidän teidät teitä - \ teissä teistä teihin teillä teiltä teille | you\r\nhe heidän - heidät heitä heissä heistä heihin heillä heiltä heille | they\r\n\r\ntämä - \ tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi - \ | this\r\ntuo tuon tuotä tuossa tuosta tuohon tuolla tuolta - \ tuolle tuona tuoksi | that\r\nse sen sitä siinä siitä siihen - sillä siltä sille sinä siksi | it\r\nnämä näiden näitä näissä - \ näistä näihin näillä näiltä näille näinä näiksi | these\r\nnuo noiden - \ noita noissa noista noihin noilla noilta noille noina noiksi | - those\r\nne niiden niitä niissä niistä niihin niillä niiltä niille - \ niinä niiksi | they\r\n\r\nkuka kenen kenet ketä kenessä kenestä keneen - kenellä keneltä kenelle kenenä keneksi| who\r\nketkä keiden ketkä keitä keissä - \ keistä keihin keillä keiltä keille keinä keiksi | (pl)\r\nmikä minkä - minkä mitä missä mistä mihin millä miltä mille minä miksi | - which what\r\nmitkä | - (pl)\r\n\r\njoka jonka jota jossa josta johon jolla jolta jolle - \ jona joksi | who which\r\njotka joiden joita joissa joista joihin - joilla joilta joille joina joiksi | (pl)\r\n\r\n| conjunctions\r\n\r\nettä - \ | that\r\nja | and\r\njos | if\r\nkoska | because\r\nkuin | than\r\nmutta - \ | but\r\nniin | so\r\nsekä | and\r\nsillä | for\r\ntai | or\r\nvaan - \ | but\r\nvai | or\r\nvaikka | although\r\n\r\n\r\n| prepositions\r\n\r\nkanssa - \ | with\r\nmukaan | according to\r\nnoin | about\r\npoikki | across\r\nyli - \ | over, across\r\n\r\n| other\r\n\r\nkun | when\r\nniin | so\r\nnyt - \ | now\r\nitse | self\r\n\r\n" - stopwords_fr.txt: | - | 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. - | - | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" - - | 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 - cela | that - 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 - stopwords_ga.txt: "\r\na\r\nach\r\nag\r\nagus\r\nan\r\naon\r\nar\r\narna\r\nas\r\nb'\r\nba\r\nbeirt\r\nbhúr\r\ncaoga\r\nceathair\r\nceathrar\r\nchomh\r\nchtó\r\nchuig\r\nchun\r\ncois\r\ncéad\r\ncúig\r\ncúigear\r\nd'\r\ndaichead\r\ndar\r\nde\r\ndeich\r\ndeichniúr\r\nden\r\ndhá\r\ndo\r\ndon\r\ndtí\r\ndá\r\ndár\r\ndó\r\nfaoi\r\nfaoin\r\nfaoina\r\nfaoinár\r\nfara\r\nfiche\r\ngach\r\ngan\r\ngo\r\ngur\r\nhaon\r\nhocht\r\ni\r\niad\r\nidir\r\nin\r\nina\r\nins\r\ninár\r\nis\r\nle\r\nleis\r\nlena\r\nlenár\r\nm'\r\nmar\r\nmo\r\nmé\r\nna\r\nnach\r\nnaoi\r\nnaonúr\r\nná\r\nní\r\nníor\r\nnó\r\nnócha\r\nocht\r\nochtar\r\nos\r\nroimh\r\nsa\r\nseacht\r\nseachtar\r\nseachtó\r\nseasca\r\nseisear\r\nsiad\r\nsibh\r\nsinn\r\nsna\r\nsé\r\nsí\r\ntar\r\nthar\r\nthú\r\ntriúr\r\ntrí\r\ntrína\r\ntrínár\r\ntríocha\r\ntú\r\num\r\nár\r\né\r\néis\r\ní\r\nó\r\nón\r\nóna\r\nónár\r\n" - stopwords_gl.txt: "# galican stopwords\r\na\r\naínda\r\nalí\r\naquel\r\naquela\r\naquelas\r\naqueles\r\naquilo\r\naquí\r\nao\r\naos\r\nas\r\nasí\r\ná\r\nben\r\ncando\r\nche\r\nco\r\ncoa\r\ncomigo\r\ncon\r\nconnosco\r\ncontigo\r\nconvosco\r\ncoas\r\ncos\r\ncun\r\ncuns\r\ncunha\r\ncunhas\r\nda\r\ndalgunha\r\ndalgunhas\r\ndalgún\r\ndalgúns\r\ndas\r\nde\r\ndel\r\ndela\r\ndelas\r\ndeles\r\ndesde\r\ndeste\r\ndo\r\ndos\r\ndun\r\nduns\r\ndunha\r\ndunhas\r\ne\r\nel\r\nela\r\nelas\r\neles\r\nen\r\nera\r\neran\r\nesa\r\nesas\r\nese\r\neses\r\nesta\r\nestar\r\nestaba\r\nestá\r\nestán\r\neste\r\nestes\r\nestiven\r\nestou\r\neu\r\né\r\nfacer\r\nfoi\r\nforon\r\nfun\r\nhabía\r\nhai\r\niso\r\nisto\r\nla\r\nlas\r\nlle\r\nlles\r\nlo\r\nlos\r\nmais\r\nme\r\nmeu\r\nmeus\r\nmin\r\nmiña\r\nmiñas\r\nmoi\r\nna\r\nnas\r\nneste\r\nnin\r\nno\r\nnon\r\nnos\r\nnosa\r\nnosas\r\nnoso\r\nnosos\r\nnós\r\nnun\r\nnunha\r\nnuns\r\nnunhas\r\no\r\nos\r\nou\r\nó\r\nós\r\npara\r\npero\r\npode\r\npois\r\npola\r\npolas\r\npolo\r\npolos\r\npor\r\nque\r\nse\r\nsenón\r\nser\r\nseu\r\nseus\r\nsexa\r\nsido\r\nsobre\r\nsúa\r\nsúas\r\ntamén\r\ntan\r\nte\r\nten\r\nteñen\r\nteño\r\nter\r\nteu\r\nteus\r\nti\r\ntido\r\ntiña\r\ntiven\r\ntúa\r\ntúas\r\nun\r\nunha\r\nunhas\r\nuns\r\nvos\r\nvosa\r\nvosas\r\nvoso\r\nvosos\r\nvós\r\n" - stopwords_hi.txt: "# Also see http://www.opensource.org/licenses/bsd-license.html\r\n# - See http://members.unine.ch/jacques.savoy/clef/index.html.\r\n# This file was - created by Jacques Savoy and is distributed under the BSD license.\r\n# Note: - by default this file also contains forms normalized by HindiNormalizer \r\n# for - spelling variation (see section below), such that it can be used whether or \r\n# - not you enable that feature. When adding additional entries to this list,\r\n# - please add the normalized form as well. \r\nअंदर\r\nअत\r\nअपना\r\nअपनी\r\nअपने\r\nअभी\r\nआदि\r\nआप\r\nइत्यादि\r\nइन - \r\nइनका\r\nइन्हीं\r\nइन्हें\r\nइन्हों\r\nइस\r\nइसका\r\nइसकी\r\nइसके\r\nइसमें\r\nइसी\r\nइसे\r\nउन\r\nउनका\r\nउनकी\r\nउनके\r\nउनको\r\nउन्हीं\r\nउन्हें\r\nउन्हों\r\nउस\r\nउसके\r\nउसी\r\nउसे\r\nएक\r\nएवं\r\nएस\r\nऐसे\r\nऔर\r\nकई\r\nकर\r\nकरता\r\nकरते\r\nकरना\r\nकरने\r\nकरें\r\nकहते\r\nकहा\r\nका\r\nकाफ़ी\r\nकि\r\nकितना\r\nकिन्हें\r\nकिन्हों\r\nकिया\r\nकिर\r\nकिस\r\nकिसी\r\nकिसे\r\nकी\r\nकुछ\r\nकुल\r\nके\r\nको\r\nकोई\r\nकौन\r\nकौनसा\r\nगया\r\nघर\r\nजब\r\nजहाँ\r\nजा\r\nजितना\r\nजिन\r\nजिन्हें\r\nजिन्हों\r\nजिस\r\nजिसे\r\nजीधर\r\nजैसा\r\nजैसे\r\nजो\r\nतक\r\nतब\r\nतरह\r\nतिन\r\nतिन्हें\r\nतिन्हों\r\nतिस\r\nतिसे\r\nतो\r\nथा\r\nथी\r\nथे\r\nदबारा\r\nदिया\r\nदुसरा\r\nदूसरे\r\nदो\r\nद्वारा\r\nन\r\nनहीं\r\nना\r\nनिहायत\r\nनीचे\r\nने\r\nपर\r\nपर - \ \r\nपहले\r\nपूरा\r\nपे\r\nफिर\r\nबनी\r\nबही\r\nबहुत\r\nबाद\r\nबाला\r\nबिलकुल\r\nभी\r\nभीतर\r\nमगर\r\nमानो\r\nमे\r\nमें\r\nयदि\r\nयह\r\nयहाँ\r\nयही\r\nया\r\nयिह - \r\nये\r\nरखें\r\nरहा\r\nरहे\r\nऱ्वासा\r\nलिए\r\nलिये\r\nलेकिन\r\nव\r\nवर्ग\r\nवह\r\nवह - \r\nवहाँ\r\nवहीं\r\nवाले\r\nवुह \r\nवे\r\nवग़ैरह\r\nसंग\r\nसकता\r\nसकते\r\nसबसे\r\nसभी\r\nसाथ\r\nसाबुत\r\nसाभ\r\nसारा\r\nसे\r\nसो\r\nही\r\nहुआ\r\nहुई\r\nहुए\r\nहै\r\nहैं\r\nहो\r\nहोता\r\nहोती\r\nहोते\r\nहोना\r\nहोने\r\n# - additional normalized forms of the above\r\nअपनि\r\nजेसे\r\nहोति\r\nसभि\r\nतिंहों\r\nइंहों\r\nदवारा\r\nइसि\r\nकिंहें\r\nथि\r\nउंहों\r\nओर\r\nजिंहें\r\nवहिं\r\nअभि\r\nबनि\r\nहि\r\nउंहिं\r\nउंहें\r\nहें\r\nवगेरह\r\nएसे\r\nरवासा\r\nकोन\r\nनिचे\r\nकाफि\r\nउसि\r\nपुरा\r\nभितर\r\nहे\r\nबहि\r\nवहां\r\nकोइ\r\nयहां\r\nजिंहों\r\nतिंहें\r\nकिसि\r\nकइ\r\nयहि\r\nइंहिं\r\nजिधर\r\nइंहें\r\nअदि\r\nइतयादि\r\nहुइ\r\nकोनसा\r\nइसकि\r\nदुसरे\r\nजहां\r\nअप\r\nकिंहों\r\nउनकि\r\nभि\r\nवरग\r\nहुअ\r\nजेसा\r\nनहिं\r\n" - stopwords_hu.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n \r\n| - Hungarian stop word list\r\n| prepared by Anna Tordai\r\n\r\na\r\nahogy\r\nahol\r\naki\r\nakik\r\nakkor\r\nalatt\r\náltal\r\náltalában\r\namely\r\namelyek\r\namelyekben\r\namelyeket\r\namelyet\r\namelynek\r\nami\r\namit\r\namolyan\r\namíg\r\namikor\r\nát\r\nabban\r\nahhoz\r\nannak\r\narra\r\narról\r\naz\r\nazok\r\nazon\r\nazt\r\nazzal\r\nazért\r\naztán\r\nazután\r\nazonban\r\nbár\r\nbe\r\nbelül\r\nbenne\r\ncikk\r\ncikkek\r\ncikkeket\r\ncsak\r\nde\r\ne\r\neddig\r\negész\r\negy\r\negyes\r\negyetlen\r\negyéb\r\negyik\r\negyre\r\nekkor\r\nel\r\nelég\r\nellen\r\nelő\r\nelőször\r\nelőtt\r\nelső\r\nén\r\néppen\r\nebben\r\nehhez\r\nemilyen\r\nennek\r\nerre\r\nez\r\nezt\r\nezek\r\nezen\r\nezzel\r\nezért\r\nés\r\nfel\r\nfelé\r\nhanem\r\nhiszen\r\nhogy\r\nhogyan\r\nigen\r\nígy\r\nilletve\r\nill.\r\nill\r\nilyen\r\nilyenkor\r\nison\r\nismét\r\nitt\r\njó\r\njól\r\njobban\r\nkell\r\nkellett\r\nkeresztül\r\nkeressünk\r\nki\r\nkívül\r\nközött\r\nközül\r\nlegalább\r\nlehet\r\nlehetett\r\nlegyen\r\nlenne\r\nlenni\r\nlesz\r\nlett\r\nmaga\r\nmagát\r\nmajd\r\nmajd\r\nmár\r\nmás\r\nmásik\r\nmeg\r\nmég\r\nmellett\r\nmert\r\nmely\r\nmelyek\r\nmi\r\nmit\r\nmíg\r\nmiért\r\nmilyen\r\nmikor\r\nminden\r\nmindent\r\nmindenki\r\nmindig\r\nmint\r\nmintha\r\nmivel\r\nmost\r\nnagy\r\nnagyobb\r\nnagyon\r\nne\r\nnéha\r\nnekem\r\nneki\r\nnem\r\nnéhány\r\nnélkül\r\nnincs\r\nolyan\r\nott\r\nössze\r\nő\r\nők\r\nőket\r\npedig\r\npersze\r\nrá\r\ns\r\nsaját\r\nsem\r\nsemmi\r\nsok\r\nsokat\r\nsokkal\r\nszámára\r\nszemben\r\nszerint\r\nszinte\r\ntalán\r\ntehát\r\nteljes\r\ntovább\r\ntovábbá\r\ntöbb\r\núgy\r\nugyanis\r\núj\r\nújabb\r\nújra\r\nután\r\nutána\r\nutolsó\r\nvagy\r\nvagyis\r\nvalaki\r\nvalami\r\nvalamint\r\nvaló\r\nvagyok\r\nvan\r\nvannak\r\nvolt\r\nvoltam\r\nvoltak\r\nvoltunk\r\nvissza\r\nvele\r\nviszont\r\nvolna\r\n" - stopwords_hy.txt: "# example set of Armenian stopwords.\r\nայդ\r\nայլ\r\nայն\r\nայս\r\nդու\r\nդուք\r\nեմ\r\nեն\r\nենք\r\nես\r\nեք\r\nէ\r\nէի\r\nէին\r\nէինք\r\nէիր\r\nէիք\r\nէր\r\nըստ\r\nթ\r\nի\r\nին\r\nիսկ\r\nիր\r\nկամ\r\nհամար\r\nհետ\r\nհետո\r\nմենք\r\nմեջ\r\nմի\r\nն\r\nնա\r\nնաև\r\nնրա\r\nնրանք\r\nոր\r\nորը\r\nորոնք\r\nորպես\r\nու\r\nում\r\nպիտի\r\nվրա\r\nև\r\n" - stopwords_id.txt: "# from appendix D of: A Study of Stemming Effects on Information\r\n# - Retrieval in Bahasa Indonesia\r\nada\r\nadanya\r\nadalah\r\nadapun\r\nagak\r\nagaknya\r\nagar\r\nakan\r\nakankah\r\nakhirnya\r\naku\r\nakulah\r\namat\r\namatlah\r\nanda\r\nandalah\r\nantar\r\ndiantaranya\r\nantara\r\nantaranya\r\ndiantara\r\napa\r\napaan\r\nmengapa\r\napabila\r\napakah\r\napalagi\r\napatah\r\natau\r\nataukah\r\nataupun\r\nbagai\r\nbagaikan\r\nsebagai\r\nsebagainya\r\nbagaimana\r\nbagaimanapun\r\nsebagaimana\r\nbagaimanakah\r\nbagi\r\nbahkan\r\nbahwa\r\nbahwasanya\r\nsebaliknya\r\nbanyak\r\nsebanyak\r\nbeberapa\r\nseberapa\r\nbegini\r\nbeginian\r\nbeginikah\r\nbeginilah\r\nsebegini\r\nbegitu\r\nbegitukah\r\nbegitulah\r\nbegitupun\r\nsebegitu\r\nbelum\r\nbelumlah\r\nsebelum\r\nsebelumnya\r\nsebenarnya\r\nberapa\r\nberapakah\r\nberapalah\r\nberapapun\r\nbetulkah\r\nsebetulnya\r\nbiasa\r\nbiasanya\r\nbila\r\nbilakah\r\nbisa\r\nbisakah\r\nsebisanya\r\nboleh\r\nbolehkah\r\nbolehlah\r\nbuat\r\nbukan\r\nbukankah\r\nbukanlah\r\nbukannya\r\ncuma\r\npercuma\r\ndahulu\r\ndalam\r\ndan\r\ndapat\r\ndari\r\ndaripada\r\ndekat\r\ndemi\r\ndemikian\r\ndemikianlah\r\nsedemikian\r\ndengan\r\ndepan\r\ndi\r\ndia\r\ndialah\r\ndini\r\ndiri\r\ndirinya\r\nterdiri\r\ndong\r\ndulu\r\nenggak\r\nenggaknya\r\nentah\r\nentahlah\r\nterhadap\r\nterhadapnya\r\nhal\r\nhampir\r\nhanya\r\nhanyalah\r\nharus\r\nharuslah\r\nharusnya\r\nseharusnya\r\nhendak\r\nhendaklah\r\nhendaknya\r\nhingga\r\nsehingga\r\nia\r\nialah\r\nibarat\r\ningin\r\ninginkah\r\ninginkan\r\nini\r\ninikah\r\ninilah\r\nitu\r\nitukah\r\nitulah\r\njangan\r\njangankan\r\njanganlah\r\njika\r\njikalau\r\njuga\r\njustru\r\nkala\r\nkalau\r\nkalaulah\r\nkalaupun\r\nkalian\r\nkami\r\nkamilah\r\nkamu\r\nkamulah\r\nkan\r\nkapan\r\nkapankah\r\nkapanpun\r\ndikarenakan\r\nkarena\r\nkarenanya\r\nke\r\nkecil\r\nkemudian\r\nkenapa\r\nkepada\r\nkepadanya\r\nketika\r\nseketika\r\nkhususnya\r\nkini\r\nkinilah\r\nkiranya\r\nsekiranya\r\nkita\r\nkitalah\r\nkok\r\nlagi\r\nlagian\r\nselagi\r\nlah\r\nlain\r\nlainnya\r\nmelainkan\r\nselaku\r\nlalu\r\nmelalui\r\nterlalu\r\nlama\r\nlamanya\r\nselama\r\nselama\r\nselamanya\r\nlebih\r\nterlebih\r\nbermacam\r\nmacam\r\nsemacam\r\nmaka\r\nmakanya\r\nmakin\r\nmalah\r\nmalahan\r\nmampu\r\nmampukah\r\nmana\r\nmanakala\r\nmanalagi\r\nmasih\r\nmasihkah\r\nsemasih\r\nmasing\r\nmau\r\nmaupun\r\nsemaunya\r\nmemang\r\nmereka\r\nmerekalah\r\nmeski\r\nmeskipun\r\nsemula\r\nmungkin\r\nmungkinkah\r\nnah\r\nnamun\r\nnanti\r\nnantinya\r\nnyaris\r\noleh\r\nolehnya\r\nseorang\r\nseseorang\r\npada\r\npadanya\r\npadahal\r\npaling\r\nsepanjang\r\npantas\r\nsepantasnya\r\nsepantasnyalah\r\npara\r\npasti\r\npastilah\r\nper\r\npernah\r\npula\r\npun\r\nmerupakan\r\nrupanya\r\nserupa\r\nsaat\r\nsaatnya\r\nsesaat\r\nsaja\r\nsajalah\r\nsaling\r\nbersama\r\nsama\r\nsesama\r\nsambil\r\nsampai\r\nsana\r\nsangat\r\nsangatlah\r\nsaya\r\nsayalah\r\nse\r\nsebab\r\nsebabnya\r\nsebuah\r\ntersebut\r\ntersebutlah\r\nsedang\r\nsedangkan\r\nsedikit\r\nsedikitnya\r\nsegala\r\nsegalanya\r\nsegera\r\nsesegera\r\nsejak\r\nsejenak\r\nsekali\r\nsekalian\r\nsekalipun\r\nsesekali\r\nsekaligus\r\nsekarang\r\nsekarang\r\nsekitar\r\nsekitarnya\r\nsela\r\nselain\r\nselalu\r\nseluruh\r\nseluruhnya\r\nsemakin\r\nsementara\r\nsempat\r\nsemua\r\nsemuanya\r\nsendiri\r\nsendirinya\r\nseolah\r\nseperti\r\nsepertinya\r\nsering\r\nseringnya\r\nserta\r\nsiapa\r\nsiapakah\r\nsiapapun\r\ndisini\r\ndisinilah\r\nsini\r\nsinilah\r\nsesuatu\r\nsesuatunya\r\nsuatu\r\nsesudah\r\nsesudahnya\r\nsudah\r\nsudahkah\r\nsudahlah\r\nsupaya\r\ntadi\r\ntadinya\r\ntak\r\ntanpa\r\nsetelah\r\ntelah\r\ntentang\r\ntentu\r\ntentulah\r\ntentunya\r\ntertentu\r\nseterusnya\r\ntapi\r\ntetapi\r\nsetiap\r\ntiap\r\nsetidaknya\r\ntidak\r\ntidakkah\r\ntidaklah\r\ntoh\r\nwaduh\r\nwah\r\nwahai\r\nsewaktu\r\nwalau\r\nwalaupun\r\nwong\r\nyaitu\r\nyakni\r\nyang\r\n" - stopwords_it.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | An Italian stop word list. Comments begin with vertical bar. Each stop\r\n | - word is at the start of a line.\r\n\r\nad | a (to) before vowel\r\nal - \ | a + il\r\nallo | a + lo\r\nai | a + i\r\nagli - \ | a + gli\r\nall | a + l'\r\nagl | a + gl'\r\nalla - \ | a + la\r\nalle | a + le\r\ncon | with\r\ncol - \ | con + il\r\ncoi | con + i (forms collo, cogli etc are - now very rare)\r\nda | from\r\ndal | da + il\r\ndallo - \ | da + lo\r\ndai | da + i\r\ndagli | da + gli\r\ndall - \ | da + l'\r\ndagl | da + gll'\r\ndalla | da + - la\r\ndalle | da + le\r\ndi | of\r\ndel | di - + il\r\ndello | di + lo\r\ndei | di + i\r\ndegli | - \ di + gli\r\ndell | di + l'\r\ndegl | di + gl'\r\ndella - \ | di + la\r\ndelle | di + le\r\nin | in\r\nnel - \ | in + el\r\nnello | in + lo\r\nnei | in + - i\r\nnegli | in + gli\r\nnell | in + l'\r\nnegl | - \ in + gl'\r\nnella | in + la\r\nnelle | in + le\r\nsu | - \ on\r\nsul | su + il\r\nsullo | su + lo\r\nsui | - \ su + i\r\nsugli | su + gli\r\nsull | su + l'\r\nsugl | - \ su + gl'\r\nsulla | su + la\r\nsulle | su + le\r\nper | - \ through, by\r\ntra | among\r\ncontro | against\r\nio | - \ I\r\ntu | thou\r\nlui | he\r\nlei | she\r\nnoi - \ | we\r\nvoi | you\r\nloro | they\r\nmio | - \ my\r\nmia |\r\nmiei |\r\nmie |\r\ntuo |\r\ntua - \ |\r\ntuoi | thy\r\ntue |\r\nsuo |\r\nsua - \ |\r\nsuoi | his, her\r\nsue |\r\nnostro | - \ our\r\nnostra |\r\nnostri |\r\nnostre |\r\nvostro | - \ your\r\nvostra |\r\nvostri |\r\nvostre |\r\nmi | - \ me\r\nti | thee\r\nci | us, there\r\nvi | - \ you, there\r\nlo | him, the\r\nla | her, the\r\nli - \ | them\r\nle | them, the\r\ngli | to him, - the\r\nne | from there etc\r\nil | the\r\nun | - \ a\r\nuno | a\r\nuna | a\r\nma | but\r\ned - \ | and\r\nse | if\r\nperché | why, because\r\nanche - \ | also\r\ncome | how\r\ndov | where (as dov')\r\ndove - \ | where\r\nche | who, that\r\nchi | who\r\ncui - \ | whom\r\nnon | not\r\npiù | more\r\nquale - \ | who, that\r\nquanto | how much\r\nquanti |\r\nquanta - \ |\r\nquante |\r\nquello | that\r\nquelli |\r\nquella - \ |\r\nquelle |\r\nquesto | this\r\nquesti |\r\nquesta - \ |\r\nqueste |\r\nsi | yes\r\ntutto | all\r\ntutti - \ | all\r\n\r\n | single letter forms:\r\n\r\na | - \ at\r\nc | as c' for ce or ci\r\ne | and\r\ni | - \ the\r\nl | as l'\r\no | or\r\n\r\n | - forms of avere, to have (not including the infinitive):\r\n\r\nho\r\nhai\r\nha\r\nabbiamo\r\navete\r\nhanno\r\nabbia\r\nabbiate\r\nabbiano\r\navrò\r\navrai\r\navrà\r\navremo\r\navrete\r\navranno\r\navrei\r\navresti\r\navrebbe\r\navremmo\r\navreste\r\navrebbero\r\navevo\r\navevi\r\naveva\r\navevamo\r\navevate\r\navevano\r\nebbi\r\navesti\r\nebbe\r\navemmo\r\naveste\r\nebbero\r\navessi\r\navesse\r\navessimo\r\navessero\r\navendo\r\navuto\r\navuta\r\navuti\r\navute\r\n\r\n - \ | forms of essere, to be (not including the infinitive):\r\nsono\r\nsei\r\nè\r\nsiamo\r\nsiete\r\nsia\r\nsiate\r\nsiano\r\nsarò\r\nsarai\r\nsarà\r\nsaremo\r\nsarete\r\nsaranno\r\nsarei\r\nsaresti\r\nsarebbe\r\nsaremmo\r\nsareste\r\nsarebbero\r\nero\r\neri\r\nera\r\neravamo\r\neravate\r\nerano\r\nfui\r\nfosti\r\nfu\r\nfummo\r\nfoste\r\nfurono\r\nfossi\r\nfosse\r\nfossimo\r\nfossero\r\nessendo\r\n\r\n - \ | forms of fare, to do (not including the infinitive, fa, fat-):\r\nfaccio\r\nfai\r\nfacciamo\r\nfanno\r\nfaccia\r\nfacciate\r\nfacciano\r\nfarò\r\nfarai\r\nfarà\r\nfaremo\r\nfarete\r\nfaranno\r\nfarei\r\nfaresti\r\nfarebbe\r\nfaremmo\r\nfareste\r\nfarebbero\r\nfacevo\r\nfacevi\r\nfaceva\r\nfacevamo\r\nfacevate\r\nfacevano\r\nfeci\r\nfacesti\r\nfece\r\nfacemmo\r\nfaceste\r\nfecero\r\nfacessi\r\nfacesse\r\nfacessimo\r\nfacessero\r\nfacendo\r\n\r\n - \ | forms of stare, to be (not including the infinitive):\r\nsto\r\nstai\r\nsta\r\nstiamo\r\nstanno\r\nstia\r\nstiate\r\nstiano\r\nstarò\r\nstarai\r\nstarà\r\nstaremo\r\nstarete\r\nstaranno\r\nstarei\r\nstaresti\r\nstarebbe\r\nstaremmo\r\nstareste\r\nstarebbero\r\nstavo\r\nstavi\r\nstava\r\nstavamo\r\nstavate\r\nstavano\r\nstetti\r\nstesti\r\nstette\r\nstemmo\r\nsteste\r\nstettero\r\nstessi\r\nstesse\r\nstessimo\r\nstessero\r\nstando\r\n" - stopwords_ja.txt: "#\r\n# This file defines a stopword set for Japanese.\r\n#\r\n# - This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.\r\n# - Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745\r\n# - for frequency lists, etc. that can be useful for making your own set (if desired)\r\n#\r\n# - Note that there is an overlap between these stopwords and the terms stopped when - used\r\n# in combination with the JapanesePartOfSpeechStopFilter. When editing - this file, note\r\n# that comments are not allowed on the same line as stopwords.\r\n#\r\n# - Also note that stopping is done in a case-insensitive manner. Change your StopFilter\r\n# - configuration if you need case-sensitive stopping. Lastly, note that stopping - is done\r\n# using the same character width as the entries in this file. Since - this StopFilter is\r\n# normally done after a CJKWidthFilter in your chain, you - would usually want your romaji\r\n# entries to be in half-width and your kana - entries to be in full-width.\r\n#\r\nの\r\nに\r\nは\r\nを\r\nた\r\nが\r\nで\r\nて\r\nと\r\nし\r\nれ\r\nさ\r\nある\r\nいる\r\nも\r\nする\r\nから\r\nな\r\nこと\r\nとして\r\nい\r\nや\r\nれる\r\nなど\r\nなっ\r\nない\r\nこの\r\nため\r\nその\r\nあっ\r\nよう\r\nまた\r\nもの\r\nという\r\nあり\r\nまで\r\nられ\r\nなる\r\nへ\r\nか\r\nだ\r\nこれ\r\nによって\r\nにより\r\nおり\r\nより\r\nによる\r\nず\r\nなり\r\nられる\r\nにおいて\r\nば\r\nなかっ\r\nなく\r\nしかし\r\nについて\r\nせ\r\nだっ\r\nその後\r\nできる\r\nそれ\r\nう\r\nので\r\nなお\r\nのみ\r\nでき\r\nき\r\nつ\r\nにおける\r\nおよび\r\nいう\r\nさらに\r\nでも\r\nら\r\nたり\r\nその他\r\nに関する\r\nたち\r\nます\r\nん\r\nなら\r\nに対して\r\n特に\r\nせる\r\n及び\r\nこれら\r\nとき\r\nでは\r\nにて\r\nほか\r\nながら\r\nうち\r\nそして\r\nとともに\r\nただし\r\nかつて\r\nそれぞれ\r\nまたは\r\nお\r\nほど\r\nものの\r\nに対する\r\nほとんど\r\nと共に\r\nといった\r\nです\r\nとも\r\nところ\r\nここ\r\n##### - End of file\r\n" - stopwords_lv.txt: "# Set of Latvian stopwords from A Stemming Algorithm for Latvian, - Karlis Kreslins\r\n# the original list of over 800 forms was refined: \r\n# pronouns, - adverbs, interjections were removed\r\n# \r\n# prepositions\r\naiz\r\nap\r\nar\r\napakš\r\nārpus\r\naugšpus\r\nbez\r\ncaur\r\ndēļ\r\ngar\r\niekš\r\niz\r\nkopš\r\nlabad\r\nlejpus\r\nlīdz\r\nno\r\notrpus\r\npa\r\npar\r\npār\r\npēc\r\npie\r\npirms\r\npret\r\npriekš\r\nstarp\r\nšaipus\r\nuz\r\nviņpus\r\nvirs\r\nvirspus\r\nzem\r\napakšpus\r\n# - Conjunctions\r\nun\r\nbet\r\njo\r\nja\r\nka\r\nlai\r\ntomēr\r\ntikko\r\nturpretī\r\narī\r\nkaut\r\ngan\r\ntādēļ\r\ntā\r\nne\r\ntikvien\r\nvien\r\nkā\r\nir\r\nte\r\nvai\r\nkamēr\r\n# - Particles\r\nar\r\ndiezin\r\ndroši\r\ndiemžēl\r\nnebūt\r\nik\r\nit\r\ntaču\r\nnu\r\npat\r\ntiklab\r\niekšpus\r\nnedz\r\ntik\r\nnevis\r\nturpretim\r\njeb\r\niekam\r\niekām\r\niekāms\r\nkolīdz\r\nlīdzko\r\ntiklīdz\r\njebšu\r\ntālab\r\ntāpēc\r\nnekā\r\nitin\r\njā\r\njau\r\njel\r\nnē\r\nnezin\r\ntad\r\ntikai\r\nvis\r\ntak\r\niekams\r\nvien\r\n# - modal verbs\r\nbūt \r\nbiju \r\nbiji\r\nbija\r\nbijām\r\nbijāt\r\nesmu\r\nesi\r\nesam\r\nesat - \r\nbūšu \r\nbūsi\r\nbūs\r\nbūsim\r\nbūsiet\r\ntikt\r\ntiku\r\ntiki\r\ntika\r\ntikām\r\ntikāt\r\ntieku\r\ntiec\r\ntiek\r\ntiekam\r\ntiekat\r\ntikšu\r\ntiks\r\ntiksim\r\ntiksiet\r\ntapt\r\ntapi\r\ntapāt\r\ntopat\r\ntapšu\r\ntapsi\r\ntaps\r\ntapsim\r\ntapsiet\r\nkļūt\r\nkļuvu\r\nkļuvi\r\nkļuva\r\nkļuvām\r\nkļuvāt\r\nkļūstu\r\nkļūsti\r\nkļūst\r\nkļūstam\r\nkļūstat\r\nkļūšu\r\nkļūsi\r\nkļūs\r\nkļūsim\r\nkļūsiet\r\n# - verbs\r\nvarēt\r\nvarēju\r\nvarējām\r\nvarēšu\r\nvarēsim\r\nvar\r\nvarēji\r\nvarējāt\r\nvarēsi\r\nvarēsiet\r\nvarat\r\nvarēja\r\nvarēs\r\n" - stopwords_nl.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Dutch stop word list. Comments begin with vertical bar. Each stop\r\n | word - is at the start of a line.\r\n\r\n | This is a ranked list (commonest to rarest) - of stopwords derived from\r\n | a large sample of Dutch text.\r\n\r\n | Dutch - stop words frequently exhibit homonym clashes. These are indicated\r\n | clearly - below.\r\n\r\nde | the\r\nen | and\r\nvan | - \ of, from\r\nik | I, the ego\r\nte | (1) chez, at etc, - (2) to, (3) too\r\ndat | that, which\r\ndie | that, those, - who, which\r\nin | in, inside\r\neen | a, an, one\r\nhij - \ | he\r\nhet | the, it\r\nniet | not, nothing, - naught\r\nzijn | (1) to be, being, (2) his, one's, its\r\nis | - \ is\r\nwas | (1) was, past tense of all persons sing. of 'zijn' (to - be) (2) wax, (3) the washing, (4) rise of river\r\nop | on, upon, - at, in, up, used up\r\naan | on, upon, to (as dative)\r\nmet | - \ with, by\r\nals | like, such as, when\r\nvoor | (1) before, - in front of, (2) furrow\r\nhad | had, past tense all persons sing. - of 'hebben' (have)\r\ner | there\r\nmaar | but, only\r\nom - \ | round, about, for etc\r\nhem | him\r\ndan | - \ then\r\nzou | should/would, past tense all persons sing. of 'zullen'\r\nof - \ | or, whether, if\r\nwat | what, something, anything\r\nmijn - \ | possessive and noun 'mine'\r\nmen | people, 'one'\r\ndit - \ | this\r\nzo | so, thus, in this way\r\ndoor | - \ through by\r\nover | over, across\r\nze | she, her, - they, them\r\nzich | oneself\r\nbij | (1) a bee, (2) by, - near, at\r\nook | also, too\r\ntot | till, until\r\nje - \ | you\r\nmij | me\r\nuit | out of, from\r\nder - \ | Old Dutch form of 'van der' still found in surnames\r\ndaar | - \ (1) there, (2) because\r\nhaar | (1) her, their, them, (2) hair\r\nnaar - \ | (1) unpleasant, unwell etc, (2) towards, (3) as\r\nheb | - \ present first person sing. of 'to have'\r\nhoe | how, why\r\nheeft - \ | present third person sing. of 'to have'\r\nhebben | 'to - have' and various parts thereof\r\ndeze | this\r\nu | - \ you\r\nwant | (1) for, (2) mitten, (3) rigging\r\nnog | - \ yet, still\r\nzal | 'shall', first and third person sing. of verb - 'zullen' (will)\r\nme | me\r\nzij | she, they\r\nnu | - \ now\r\nge | 'thou', still used in Belgium and south Netherlands\r\ngeen - \ | none\r\nomdat | because\r\niets | something, - somewhat\r\nworden | to become, grow, get\r\ntoch | yet, still\r\nal - \ | all, every, each\r\nwaren | (1) 'were' (2) to wander, - (3) wares, (3)\r\nveel | much, many\r\nmeer | (1) more, - (2) lake\r\ndoen | to do, to make\r\ntoen | then, when\r\nmoet - \ | noun 'spot/mote' and present form of 'to must'\r\nben | - \ (1) am, (2) 'are' in interrogative second person singular of 'to be'\r\nzonder - \ | without\r\nkan | noun 'can' and present form of 'to be - able'\r\nhun | their, them\r\ndus | so, consequently\r\nalles - \ | all, everything, anything\r\nonder | under, beneath\r\nja - \ | yes, of course\r\neens | once, one day\r\nhier | - \ here\r\nwie | who\r\nwerd | imperfect third person sing. - of 'become'\r\naltijd | always\r\ndoch | yet, but etc\r\nwordt - \ | present third person sing. of 'become'\r\nwezen | (1) to - be, (2) 'been' as in 'been fishing', (3) orphans\r\nkunnen | to be able\r\nons - \ | us/our\r\nzelf | self\r\ntegen | against, - towards, at\r\nna | after, near\r\nreeds | already\r\nwil - \ | (1) present tense of 'want', (2) 'will', noun, (3) fender\r\nkon - \ | could; past tense of 'to be able'\r\nniets | nothing\r\nuw - \ | your\r\niemand | somebody\r\ngeweest | been; - past participle of 'be'\r\nandere | other\r\n" - stopwords_no.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Norwegian stop word list. Comments begin with vertical bar. Each stop\r\n - | word is at the start of a line.\r\n\r\n | This stop word list is for the dominant - bokmål dialect. Words unique\r\n | to nynorsk are marked *.\r\n\r\n | Revised - by Jan Bruusgaard , Jan 2005\r\n\r\nog | and\r\ni - \ | in\r\njeg | I\r\ndet | it/this/that\r\nat - \ | to (w. inf.)\r\nen | a/an\r\net | a/an\r\nden - \ | it/this/that\r\ntil | to\r\ner | is/am/are\r\nsom - \ | who/that\r\npå | on\r\nde | they / you(formal)\r\nmed - \ | with\r\nhan | he\r\nav | of\r\nikke | - not\r\nikkje | not *\r\nder | there\r\nså | so\r\nvar - \ | was/were\r\nmeg | me\r\nseg | you\r\nmen | - but\r\nett | one\r\nhar | have\r\nom | about\r\nvi - \ | we\r\nmin | my\r\nmitt | my\r\nha | - have\r\nhadde | had\r\nhun | she\r\nnå | now\r\nover - \ | over\r\nda | when/as\r\nved | by/know\r\nfra - \ | from\r\ndu | you\r\nut | out\r\nsin | - your\r\ndem | them\r\noss | us\r\nopp | up\r\nman - \ | you/one\r\nkan | can\r\nhans | his\r\nhvor - \ | where\r\neller | or\r\nhva | what\r\nskal | - shall/must\r\nselv | self (reflective)\r\nsjøl | self (reflective)\r\nher - \ | here\r\nalle | all\r\nvil | will\r\nbli | - become\r\nble | became\r\nblei | became *\r\nblitt | - have become\r\nkunne | could\r\ninn | in\r\nnår | - when\r\nvære | be\r\nkom | come\r\nnoen | some\r\nnoe - \ | some\r\nville | would\r\ndere | you\r\nsom | - who/which/that\r\nderes | their/theirs\r\nkun | only/just\r\nja - \ | yes\r\netter | after\r\nned | down\r\nskulle - \ | should\r\ndenne | this\r\nfor | for/because\r\ndeg - \ | you\r\nsi | hers/his\r\nsine | hers/his\r\nsitt - \ | hers/his\r\nmot | against\r\nå | to\r\nmeget - \ | much\r\nhvorfor | why\r\ndette | this\r\ndisse | - these/those\r\nuten | without\r\nhvordan | how\r\ningen | - none\r\ndin | your\r\nditt | your\r\nblir | become\r\nsamme - \ | same\r\nhvilken | which\r\nhvilke | which (plural)\r\nsånn - \ | such a\r\ninni | inside/within\r\nmellom | between\r\nvår - \ | our\r\nhver | each\r\nhvem | who\r\nvors | - us/ours\r\nhvis | whose\r\nbåde | both\r\nbare | - only/just\r\nenn | than\r\nfordi | as/because\r\nfør | - before\r\nmange | many\r\nogså | also\r\nslik | just\r\nvært - \ | been\r\nvære | to be\r\nbåe | both *\r\nbegge - \ | both\r\nsiden | since\r\ndykk | your *\r\ndykkar - \ | yours *\r\ndei | they *\r\ndeira | them *\r\ndeires - \ | theirs *\r\ndeim | them *\r\ndi | your (fem.) - *\r\ndå | as/when *\r\neg | I *\r\nein | a/an - *\r\neit | a/an *\r\neitt | a/an *\r\nelles | or - *\r\nhonom | he *\r\nhjå | at *\r\nho | she *\r\nhoe - \ | she *\r\nhenne | her\r\nhennar | her/hers\r\nhennes - \ | hers\r\nhoss | how *\r\nhossen | how *\r\nikkje | - not *\r\ningi | noone *\r\ninkje | noone *\r\nkorleis | - how *\r\nkorso | how *\r\nkva | what/which *\r\nkvar | - where *\r\nkvarhelst | where *\r\nkven | who/whom *\r\nkvi | - why *\r\nkvifor | why *\r\nme | we *\r\nmedan | while - *\r\nmi | my *\r\nmine | my *\r\nmykje | much *\r\nno - \ | now *\r\nnokon | some (masc./neut.) *\r\nnoka | - some (fem.) *\r\nnokor | some *\r\nnoko | some *\r\nnokre | - some *\r\nsi | his/hers *\r\nsia | since *\r\nsidan | - since *\r\nso | so *\r\nsomt | some *\r\nsomme | - some *\r\num | about*\r\nupp | up *\r\nvere | - be *\r\nvore | was *\r\nverte | become *\r\nvort | - become *\r\nvarte | became *\r\nvart | became *\r\n\r\n" - stopwords_pt.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Portuguese stop word list. Comments begin with vertical bar. Each stop\r\n - | word is at the start of a line.\r\n\r\n\r\n | The following is a ranked list - (commonest to rarest) of stopwords\r\n | deriving from a large sample of text.\r\n\r\n - | Extra words have been added at the end.\r\n\r\nde | of, from\r\na - \ | the; to, at; her\r\no | the; him\r\nque | - \ who, that\r\ne | and\r\ndo | de + o\r\nda | - \ de + a\r\nem | in\r\num | a\r\npara | for\r\n - \ | é from SER\r\ncom | with\r\nnão | not, no\r\numa - \ | a\r\nos | the; them\r\nno | em + o\r\nse - \ | himself etc\r\nna | em + a\r\npor | for\r\nmais - \ | more\r\nas | the; them\r\ndos | de + os\r\ncomo - \ | as, like\r\nmas | but\r\n | foi from SER\r\nao - \ | a + o\r\nele | he\r\ndas | de + as\r\n - \ | tem from TER\r\nà | a + a\r\nseu | his\r\nsua - \ | her\r\nou | or\r\n | ser from SER\r\nquando - \ | when\r\nmuito | much\r\n | há from HAV\r\nnos | - \ em + os; us\r\njá | already, now\r\n | está from EST\r\neu - \ | I\r\ntambém | also\r\nsó | only, just\r\npelo - \ | per + o\r\npela | per + a\r\naté | up to\r\nisso - \ | that\r\nela | he\r\nentre | between\r\n | - era from SER\r\ndepois | after\r\nsem | without\r\nmesmo - \ | same\r\naos | a + os\r\n | ter from TER\r\nseus - \ | his\r\nquem | whom\r\nnas | em + as\r\nme - \ | me\r\nesse | that\r\neles | they\r\n | - estão from EST\r\nvocê | you\r\n | tinha from TER\r\n | - foram from SER\r\nessa | that\r\nnum | em + um\r\nnem - \ | nor\r\nsuas | her\r\nmeu | my\r\nàs | - \ a + as\r\nminha | my\r\n | têm from TER\r\nnuma | - \ em + uma\r\npelos | per + os\r\nelas | they\r\n | havia - \ from HAV\r\n | seja from SER\r\nqual | which\r\n | será - \ from SER\r\nnós | we\r\n | tenho from TER\r\nlhe | - \ to him, her\r\ndeles | of them\r\nessas | those\r\nesses - \ | those\r\npelas | per + as\r\neste | this\r\n - \ | fosse from SER\r\ndele | of him\r\n\r\n | other words. There - are many contractions such as naquele = em+aquele,\r\n | mo = me+o, but they are - rare.\r\n | Indefinite article plural forms are also rare.\r\n\r\ntu | - \ thou\r\nte | thee\r\nvocês | you (plural)\r\nvos | - \ you\r\nlhes | to them\r\nmeus | my\r\nminhas\r\nteu | - \ thy\r\ntua\r\nteus\r\ntuas\r\nnosso | our\r\nnossa\r\nnossos\r\nnossas\r\n\r\ndela - \ | of her\r\ndelas | of them\r\n\r\nesta | this\r\nestes - \ | these\r\nestas | these\r\naquele | that\r\naquela - \ | that\r\naqueles | those\r\naquelas | those\r\nisto - \ | this\r\naquilo | that\r\n\r\n | forms of - estar, to be (not including the infinitive):\r\nestou\r\nestá\r\nestamos\r\nestão\r\nestive\r\nesteve\r\nestivemos\r\nestiveram\r\nestava\r\nestávamos\r\nestavam\r\nestivera\r\nestivéramos\r\nesteja\r\nestejamos\r\nestejam\r\nestivesse\r\nestivéssemos\r\nestivessem\r\nestiver\r\nestivermos\r\nestiverem\r\n\r\n - \ | forms of haver, to have (not including the infinitive):\r\nhei\r\nhá\r\nhavemos\r\nhão\r\nhouve\r\nhouvemos\r\nhouveram\r\nhouvera\r\nhouvéramos\r\nhaja\r\nhajamos\r\nhajam\r\nhouvesse\r\nhouvéssemos\r\nhouvessem\r\nhouver\r\nhouvermos\r\nhouverem\r\nhouverei\r\nhouverá\r\nhouveremos\r\nhouverão\r\nhouveria\r\nhouveríamos\r\nhouveriam\r\n\r\n - \ | forms of ser, to be (not including the infinitive):\r\nsou\r\nsomos\r\nsão\r\nera\r\néramos\r\neram\r\nfui\r\nfoi\r\nfomos\r\nforam\r\nfora\r\nfôramos\r\nseja\r\nsejamos\r\nsejam\r\nfosse\r\nfôssemos\r\nfossem\r\nfor\r\nformos\r\nforem\r\nserei\r\nserá\r\nseremos\r\nserão\r\nseria\r\nseríamos\r\nseriam\r\n\r\n - \ | forms of ter, to have (not including the infinitive):\r\ntenho\r\ntem\r\ntemos\r\ntém\r\ntinha\r\ntínhamos\r\ntinham\r\ntive\r\nteve\r\ntivemos\r\ntiveram\r\ntivera\r\ntivéramos\r\ntenha\r\ntenhamos\r\ntenham\r\ntivesse\r\ntivéssemos\r\ntivessem\r\ntiver\r\ntivermos\r\ntiverem\r\nterei\r\nterá\r\nteremos\r\nterão\r\nteria\r\nteríamos\r\nteriam\r\n" - stopwords_ro.txt: "# This file was created by Jacques Savoy and is distributed under - the BSD license.\r\n# See http://members.unine.ch/jacques.savoy/clef/index.html.\r\n# - Also see http://www.opensource.org/licenses/bsd-license.html\r\nacea\r\naceasta\r\naceastă\r\naceea\r\nacei\r\naceia\r\nacel\r\nacela\r\nacele\r\nacelea\r\nacest\r\nacesta\r\naceste\r\nacestea\r\naceşti\r\naceştia\r\nacolo\r\nacum\r\nai\r\naia\r\naibă\r\naici\r\nal\r\năla\r\nale\r\nalea\r\nălea\r\naltceva\r\naltcineva\r\nam\r\nar\r\nare\r\naş\r\naşadar\r\nasemenea\r\nasta\r\năsta\r\nastăzi\r\nastea\r\năstea\r\năştia\r\nasupra\r\naţi\r\nau\r\navea\r\navem\r\naveţi\r\nazi\r\nbine\r\nbucur\r\nbună\r\nca\r\ncă\r\ncăci\r\ncând\r\ncare\r\ncărei\r\ncăror\r\ncărui\r\ncât\r\ncâte\r\ncâţi\r\ncătre\r\ncâtva\r\nce\r\ncel\r\nceva\r\nchiar\r\ncînd\r\ncine\r\ncineva\r\ncît\r\ncîte\r\ncîţi\r\ncîtva\r\ncontra\r\ncu\r\ncum\r\ncumva\r\ncurând\r\ncurînd\r\nda\r\ndă\r\ndacă\r\ndar\r\ndatorită\r\nde\r\ndeci\r\ndeja\r\ndeoarece\r\ndeparte\r\ndeşi\r\ndin\r\ndinaintea\r\ndintr\r\ndintre\r\ndrept\r\ndupă\r\nea\r\nei\r\nel\r\nele\r\neram\r\neste\r\neşti\r\neu\r\nface\r\nfără\r\nfi\r\nfie\r\nfiecare\r\nfii\r\nfim\r\nfiţi\r\niar\r\nieri\r\nîi\r\nîl\r\nîmi\r\nîmpotriva\r\nîn - \r\nînainte\r\nînaintea\r\nîncât\r\nîncît\r\nîncotro\r\nîntre\r\nîntrucât\r\nîntrucît\r\nîţi\r\nla\r\nlângă\r\nle\r\nli\r\nlîngă\r\nlor\r\nlui\r\nmă\r\nmâine\r\nmea\r\nmei\r\nmele\r\nmereu\r\nmeu\r\nmi\r\nmine\r\nmult\r\nmultă\r\nmulţi\r\nne\r\nnicăieri\r\nnici\r\nnimeni\r\nnişte\r\nnoastră\r\nnoastre\r\nnoi\r\nnoştri\r\nnostru\r\nnu\r\nori\r\noricând\r\noricare\r\noricât\r\norice\r\noricînd\r\noricine\r\noricît\r\noricum\r\noriunde\r\npână\r\npe\r\npentru\r\npeste\r\npînă\r\npoate\r\npot\r\nprea\r\nprima\r\nprimul\r\nprin\r\nprintr\r\nsa\r\nsă\r\nsăi\r\nsale\r\nsau\r\nsău\r\nse\r\nşi\r\nsînt\r\nsîntem\r\nsînteţi\r\nspre\r\nsub\r\nsunt\r\nsuntem\r\nsunteţi\r\nta\r\ntăi\r\ntale\r\ntău\r\nte\r\nţi\r\nţie\r\ntine\r\ntoată\r\ntoate\r\ntot\r\ntoţi\r\ntotuşi\r\ntu\r\nun\r\nuna\r\nunde\r\nundeva\r\nunei\r\nunele\r\nuneori\r\nunor\r\nvă\r\nvi\r\nvoastră\r\nvoastre\r\nvoi\r\nvoştri\r\nvostru\r\nvouă\r\nvreo\r\nvreun\r\n" - stopwords_ru.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | a russian stop word list. comments begin with vertical bar. each stop\r\n | - word is at the start of a line.\r\n\r\n | this is a ranked list (commonest to - rarest) of stopwords derived from\r\n | a large text sample.\r\n\r\n | letter - `ё' is translated to `е'.\r\n\r\nи | and\r\nв | in/into\r\nво - \ | alternative form\r\nне | not\r\nчто | what/that\r\nон - \ | he\r\nна | on/onto\r\nя | i\r\nс | - from\r\nсо | alternative form\r\nкак | how\r\nа | - milder form of `no' (but)\r\nто | conjunction and form of `that'\r\nвсе - \ | all\r\nона | she\r\nтак | so, thus\r\nего - \ | him\r\nно | but\r\nда | yes/and\r\nты | - thou\r\nк | towards, by\r\nу | around, chez\r\nже | - intensifier particle\r\nвы | you\r\nза | beyond, behind\r\nбы - \ | conditional/subj. particle\r\nпо | up to, along\r\nтолько - \ | only\r\nее | her\r\nмне | to me\r\nбыло | - it was\r\nвот | here is/are, particle\r\nот | away from\r\nменя - \ | me\r\nеще | still, yet, more\r\nнет | no, there - isnt/arent\r\nо | about\r\nиз | out of\r\nему | - to him\r\nтеперь | now\r\nкогда | when\r\nдаже | even\r\nну - \ | so, well\r\nвдруг | suddenly\r\nли | interrogative - particle\r\nесли | if\r\nуже | already, but homonym of `narrower'\r\nили - \ | or\r\nни | neither\r\nбыть | to be\r\nбыл - \ | he was\r\nнего | prepositional form of его\r\nдо | - up to\r\nвас | you accusative\r\nнибудь | indef. suffix preceded - by hyphen\r\nопять | again\r\nуж | already, but homonym of - `adder'\r\nвам | to you\r\nсказал | he said\r\nведь | - particle `after all'\r\nтам | there\r\nпотом | then\r\nсебя - \ | oneself\r\nничего | nothing\r\nей | to her\r\nможет - \ | usually with `быть' as `maybe'\r\nони | they\r\nтут | - here\r\nгде | where\r\nесть | there is/are\r\nнадо | - got to, must\r\nней | prepositional form of ей\r\nдля | - for\r\nмы | we\r\nтебя | thee\r\nих | them, - their\r\nчем | than\r\nбыла | she was\r\nсам | - self\r\nчтоб | in order to\r\nбез | without\r\nбудто | - as if\r\nчеловек | man, person, one\r\nчего | genitive form of - `what'\r\nраз | once\r\nтоже | also\r\nсебе | to - oneself\r\nпод | beneath\r\nжизнь | life\r\nбудет | - will be\r\nж | short form of intensifer particle `же'\r\nтогда | - then\r\nкто | who\r\nэтот | this\r\nговорил | was - saying\r\nтого | genitive form of `that'\r\nпотому | for that - reason\r\nэтого | genitive form of `this'\r\nкакой | which\r\nсовсем - \ | altogether\r\nним | prepositional form of `его', `они'\r\nздесь - \ | here\r\nэтом | prepositional form of `этот'\r\nодин | - one\r\nпочти | almost\r\nмой | my\r\nтем | instrumental/dative - plural of `тот', `то'\r\nчтобы | full form of `in order that'\r\nнее - \ | her (acc.)\r\nкажется | it seems\r\nсейчас | now\r\nбыли - \ | they were\r\nкуда | where to\r\nзачем | why\r\nсказать - \ | to say\r\nвсех | all (acc., gen. preposn. plural)\r\nникогда - \ | never\r\nсегодня | today\r\nможно | possible, one can\r\nпри - \ | by\r\nнаконец | finally\r\nдва | two\r\nоб | - alternative form of `о', about\r\nдругой | another\r\nхоть | - even\r\nпосле | after\r\nнад | above\r\nбольше | more\r\nтот - \ | that one (masc.)\r\nчерез | across, in\r\nэти | - these\r\nнас | us\r\nпро | about\r\nвсего | in - all, only, of all\r\nних | prepositional form of `они' (they)\r\nкакая - \ | which, feminine\r\nмного | lots\r\nразве | interrogative - particle\r\nсказала | she said\r\nтри | three\r\nэту | - this, acc. fem. sing.\r\nмоя | my, feminine\r\nвпрочем | moreover, - besides\r\nхорошо | good\r\nсвою | ones own, acc. fem. sing.\r\nэтой - \ | oblique form of `эта', fem. `this'\r\nперед | in front of\r\nиногда - \ | sometimes\r\nлучше | better\r\nчуть | a little\r\nтом - \ | preposn. form of `that one'\r\nнельзя | one must not\r\nтакой - \ | such a one\r\nим | to them\r\nболее | more\r\nвсегда - \ | always\r\nконечно | of course\r\nвсю | acc. fem. - sing of `all'\r\nмежду | between\r\n\r\n\r\n | b: some paradigms\r\n - \ |\r\n | personal pronouns\r\n |\r\n | я меня мне мной [мною]\r\n | ты - \ тебя тебе тобой [тобою]\r\n | он его ему им [него, нему, ним]\r\n | - она ее эи ею [нее, нэи, нею]\r\n | оно его ему им [него, нему, ним]\r\n - \ |\r\n | мы нас нам нами\r\n | вы вас вам вами\r\n | они их им ими - \ [них, ним, ними]\r\n |\r\n | себя себе собой [собою]\r\n |\r\n | demonstrative - pronouns: этот (this), тот (that)\r\n |\r\n | этот эта это эти\r\n | этого - \ эты это эти\r\n | этого этой этого этих\r\n | этому этой этому этим\r\n - \ | этим этой этим [этою] этими\r\n | этом этой этом этих\r\n |\r\n | - тот та то те\r\n | того ту то те\r\n | того той того тех\r\n | тому - \ той тому тем\r\n | тем той тем [тою] теми\r\n | том той том тех\r\n - \ |\r\n | determinative pronouns\r\n |\r\n | (a) весь (all)\r\n |\r\n | весь - \ вся все все\r\n | всего всю все все\r\n | всего всей всего всех\r\n - \ | всему всей всему всем\r\n | всем всей всем [всею] всеми\r\n | всем - \ всей всем всех\r\n |\r\n | (b) сам (himself etc)\r\n |\r\n | сам сама - \ само сами\r\n | самого саму само самих\r\n | самого самой самого самих\r\n - \ | самому самой самому самим\r\n | самим самой самим [самою] самими\r\n - \ | самом самой самом самих\r\n |\r\n | stems of verbs `to be', `to have', - `to do' and modal\r\n |\r\n | быть бы буд быв есть суть\r\n | име\r\n - \ | дел\r\n | мог мож мочь\r\n | уме\r\n | хоч хот\r\n | долж\r\n | можн\r\n - \ | нужн\r\n | нельзя\r\n\r\n" - stopwords_sv.txt: " | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt\r\n - | This file is distributed under the BSD License.\r\n | See http://snowball.tartarus.org/license.php\r\n - | Also see http://www.opensource.org/licenses/bsd-license.html\r\n | - Encoding - was converted to UTF-8.\r\n | - This notice was added.\r\n |\r\n | NOTE: To use - this file with StopFilterFactory, you must specify format=\"snowball\"\r\n\r\n - | A Swedish stop word list. Comments begin with vertical bar. Each stop\r\n | - word is at the start of a line.\r\n\r\n | This is a ranked list (commonest to - rarest) of stopwords derived from\r\n | a large text sample.\r\n\r\n | Swedish - stop words occasionally exhibit homonym clashes. For example\r\n | så = so, but - also seed. These are indicated clearly below.\r\n\r\noch | and\r\ndet - \ | it, this/that\r\natt | to (with infinitive)\r\ni | - in, at\r\nen | a\r\njag | I\r\nhon | she\r\nsom - \ | who, that\r\nhan | he\r\npå | on\r\nden | - it, this/that\r\nmed | with\r\nvar | where, each\r\nsig - \ | him(self) etc\r\nför | for\r\nså | so (also: - seed)\r\ntill | to\r\när | is\r\nmen | but\r\nett - \ | a\r\nom | if; around, about\r\nhade | had\r\nde - \ | they, these/those\r\nav | of\r\nicke | not, - no\r\nmig | me\r\ndu | you\r\nhenne | her\r\ndå - \ | then, when\r\nsin | his\r\nnu | now\r\nhar - \ | have\r\ninte | inte någon = no one\r\nhans | - his\r\nhonom | him\r\nskulle | 'sake'\r\nhennes | her\r\ndär - \ | there\r\nmin | my\r\nman | one (pronoun)\r\nej - \ | nor\r\nvid | at, by, on (also: vast)\r\nkunde | - could\r\nnågot | some etc\r\nfrån | from, off\r\nut | - out\r\nnär | when\r\nefter | after, behind\r\nupp | - up\r\nvi | we\r\ndem | them\r\nvara | be\r\nvad - \ | what\r\növer | over\r\nän | than\r\ndig | - you\r\nkan | can\r\nsina | his\r\nhär | here\r\nha - \ | have\r\nmot | towards\r\nalla | all\r\nunder - \ | under (also: wonder)\r\nnågon | some etc\r\neller | - or (else)\r\nallt | all\r\nmycket | much\r\nsedan | - since\r\nju | why\r\ndenna | this/that\r\nsjälv | - myself, yourself etc\r\ndetta | this/that\r\nåt | to\r\nutan - \ | without\r\nvarit | was\r\nhur | how\r\ningen - \ | no\r\nmitt | my\r\nni | you\r\nbli | - to be, become\r\nblev | from bli\r\noss | us\r\ndin | - thy\r\ndessa | these/those\r\nnågra | some etc\r\nderas | - their\r\nblir | from bli\r\nmina | my\r\nsamma | - (the) same\r\nvilken | who, that\r\ner | you, your\r\nsådan - \ | such a\r\nvår | our\r\nblivit | from bli\r\ndess - \ | its\r\ninom | within\r\nmellan | between\r\nsådant - \ | such a\r\nvarför | why\r\nvarje | each\r\nvilka | - who, that\r\nditt | thy\r\nvem | who\r\nvilket | - who, that\r\nsitta | his\r\nsådana | such a\r\nvart | - each\r\ndina | thy\r\nvars | whose\r\nvårt | our\r\nvåra - \ | our\r\nert | your\r\nera | your\r\nvilkas | - whose\r\n\r\n" - stopwords_th.txt: "# Thai stopwords from:\r\n# \"Opinion Detection in Thai Political - News Columns\r\n# Based on Subjectivity Analysis\"\r\n# Khampol Sukhum, Supot - Nitsuwat, and Choochart Haruechaiyasak\r\nไว้\r\nไม่\r\nไป\r\nได้\r\nให้\r\nใน\r\nโดย\r\nแห่ง\r\nแล้ว\r\nและ\r\nแรก\r\nแบบ\r\nแต่\r\nเอง\r\nเห็น\r\nเลย\r\nเริ่ม\r\nเรา\r\nเมื่อ\r\nเพื่อ\r\nเพราะ\r\nเป็นการ\r\nเป็น\r\nเปิดเผย\r\nเปิด\r\nเนื่องจาก\r\nเดียวกัน\r\nเดียว\r\nเช่น\r\nเฉพาะ\r\nเคย\r\nเข้า\r\nเขา\r\nอีก\r\nอาจ\r\nอะไร\r\nออก\r\nอย่าง\r\nอยู่\r\nอยาก\r\nหาก\r\nหลาย\r\nหลังจาก\r\nหลัง\r\nหรือ\r\nหนึ่ง\r\nส่วน\r\nส่ง\r\nสุด\r\nสําหรับ\r\nว่า\r\nวัน\r\nลง\r\nร่วม\r\nราย\r\nรับ\r\nระหว่าง\r\nรวม\r\nยัง\r\nมี\r\nมาก\r\nมา\r\nพร้อม\r\nพบ\r\nผ่าน\r\nผล\r\nบาง\r\nน่า\r\nนี้\r\nนํา\r\nนั้น\r\nนัก\r\nนอกจาก\r\nทุก\r\nที่สุด\r\nที่\r\nทําให้\r\nทํา\r\nทาง\r\nทั้งนี้\r\nทั้ง\r\nถ้า\r\nถูก\r\nถึง\r\nต้อง\r\nต่างๆ\r\nต่าง\r\nต่อ\r\nตาม\r\nตั้งแต่\r\nตั้ง\r\nด้าน\r\nด้วย\r\nดัง\r\nซึ่ง\r\nช่วง\r\nจึง\r\nจาก\r\nจัด\r\nจะ\r\nคือ\r\nความ\r\nครั้ง\r\nคง\r\nขึ้น\r\nของ\r\nขอ\r\nขณะ\r\nก่อน\r\nก็\r\nการ\r\nกับ\r\nกัน\r\nกว่า\r\nกล่าว\r\n" - stopwords_tr.txt: "# Turkish stopwords from LUCENE-559\r\n# merged with the list - from \"Information Retrieval on Turkish Texts\"\r\n# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)\r\nacaba\r\naltmış\r\naltı\r\nama\r\nancak\r\narada\r\naslında\r\nayrıca\r\nbana\r\nbazı\r\nbelki\r\nben\r\nbenden\r\nbeni\r\nbenim\r\nberi\r\nbeş\r\nbile\r\nbin\r\nbir\r\nbirçok\r\nbiri\r\nbirkaç\r\nbirkez\r\nbirşey\r\nbirşeyi\r\nbiz\r\nbize\r\nbizden\r\nbizi\r\nbizim\r\nböyle\r\nböylece\r\nbu\r\nbuna\r\nbunda\r\nbundan\r\nbunlar\r\nbunları\r\nbunların\r\nbunu\r\nbunun\r\nburada\r\nçok\r\nçünkü\r\nda\r\ndaha\r\ndahi\r\nde\r\ndefa\r\ndeğil\r\ndiğer\r\ndiye\r\ndoksan\r\ndokuz\r\ndolayı\r\ndolayısıyla\r\ndört\r\nedecek\r\neden\r\nederek\r\nedilecek\r\nediliyor\r\nedilmesi\r\nediyor\r\neğer\r\nelli\r\nen\r\netmesi\r\netti\r\nettiği\r\nettiğini\r\ngibi\r\ngöre\r\nhalen\r\nhangi\r\nhatta\r\nhem\r\nhenüz\r\nhep\r\nhepsi\r\nher\r\nherhangi\r\nherkesin\r\nhiç\r\nhiçbir\r\niçin\r\niki\r\nile\r\nilgili\r\nise\r\nişte\r\nitibaren\r\nitibariyle\r\nkadar\r\nkarşın\r\nkatrilyon\r\nkendi\r\nkendilerine\r\nkendini\r\nkendisi\r\nkendisine\r\nkendisini\r\nkez\r\nki\r\nkim\r\nkimden\r\nkime\r\nkimi\r\nkimse\r\nkırk\r\nmilyar\r\nmilyon\r\nmu\r\nmü\r\nmı\r\nnasıl\r\nne\r\nneden\r\nnedenle\r\nnerde\r\nnerede\r\nnereye\r\nniye\r\nniçin\r\no\r\nolan\r\nolarak\r\noldu\r\nolduğu\r\nolduğunu\r\nolduklarını\r\nolmadı\r\nolmadığı\r\nolmak\r\nolması\r\nolmayan\r\nolmaz\r\nolsa\r\nolsun\r\nolup\r\nolur\r\nolursa\r\noluyor\r\non\r\nona\r\nondan\r\nonlar\r\nonlardan\r\nonları\r\nonların\r\nonu\r\nonun\r\notuz\r\noysa\r\nöyle\r\npek\r\nrağmen\r\nsadece\r\nsanki\r\nsekiz\r\nseksen\r\nsen\r\nsenden\r\nseni\r\nsenin\r\nsiz\r\nsizden\r\nsizi\r\nsizin\r\nşey\r\nşeyden\r\nşeyi\r\nşeyler\r\nşöyle\r\nşu\r\nşuna\r\nşunda\r\nşundan\r\nşunları\r\nşunu\r\ntarafından\r\ntrilyon\r\ntüm\r\nüç\r\nüzere\r\nvar\r\nvardı\r\nve\r\nveya\r\nya\r\nyani\r\nyapacak\r\nyapılan\r\nyapılması\r\nyapıyor\r\nyapmak\r\nyaptı\r\nyaptığı\r\nyaptığını\r\nyaptıkları\r\nyedi\r\nyerine\r\nyetmiş\r\nyine\r\nyirmi\r\nyoksa\r\nyüz\r\nzaten\r\n" - synonyms.txt: | - # 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 WordDelimiterGraphFilter coming - #after us won't split it into two words. - - # Synonym mappings can be used for spelling correction too - pixima => pixma - - vert.x,vertx - technology,tech - update-script.js: |- - function get_class(name) { - var clazz; - try { - // Java8 Nashorn - clazz = eval("Java.type(name).class"); - } catch(e) { - // Java7 Rhino - clazz = eval("Packages."+name); - } - - return clazz; - } - - function processAdd(cmd) { - - doc = cmd.solrDoc; // org.apache.solr.common.SolrInputDocument - var id = doc.getFieldValue("id"); - logger.info("update-script#processAdd: id=" + id); - - // The idea here is to use the file's content_type value to - // simplify into user-friendly values, such that types of, say, image/jpeg and image/tiff - // are in an "Images" facet - - var ct = doc.getFieldValue("content_type"); - if (ct) { - // strip off semicolon onward - var semicolon_index = ct.indexOf(';'); - if (semicolon_index != -1) { - ct = ct.substring(0,semicolon_index); - } - // and split type/subtype - var ct_type = ct.substring(0,ct.indexOf('/')); - var ct_subtype = ct.substring(ct.indexOf('/')+1); - - var doc_type; - switch(true) { - case /^application\/rtf/.test(ct) || /wordprocessing/.test(ct): - doc_type = "doc"; - break; - - case /html/.test(ct): - doc_type = "html"; - break; - - case /^image\/.*/.test(ct): - doc_type = "image"; - break; - - case /presentation|powerpoint/.test(ct): - doc_type = "presentation"; - break; - - case /spreadsheet|excel/.test(ct): - doc_type = "spreadsheet"; - break; - - case /^application\/pdf/.test(ct): - doc_type = "pdf"; - break; - - case /^text\/plain/.test(ct): - doc_type = "text" - break; - - default: - break; - } - - // TODO: error handling needed? What if there is no slash? - if(doc_type) { doc.setField("doc_type", doc_type); } - doc.setField("content_type_type_s", ct_type); - doc.setField("content_type_subtype_s", ct_subtype); - } - - var content = doc.getFieldValue("content"); - if (!content) { - return; //No content found, so we are done here - } - - var analyzer = - req.getCore().getLatestSchema() - .getFieldTypeByName("text_email_url") - .getIndexAnalyzer(); - - var token_stream = - analyzer.tokenStream("content", content); - var term_att = token_stream.getAttribute(get_class("org.apache.lucene.analysis.tokenattributes.CharTermAttribute")); - var type_att = token_stream.getAttribute(get_class("org.apache.lucene.analysis.tokenattributes.TypeAttribute")); - token_stream.reset(); - while (token_stream.incrementToken()) { - doc.addField(type_att.type().replace(/\<|\>/g,'').toLowerCase()+"_ss", term_att.toString()); - } - token_stream.end(); - token_stream.close(); - } - - function processDelete(cmd) { - // no-op - } - - function processMergeIndexes(cmd) { - // no-op - } - - function processCommit(cmd) { - // no-op - } - - function processRollback(cmd) { - // no-op - } - - function finish() { - // no-op - } - userdict_ja.txt: "#\r\n# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)\r\n#\r\n# - Add entries to this file in order to override the statistical model in terms\r\n# - of segmentation, readings and part-of-speech tags. Notice that entries do\r\n# - not have weights since they are always used when found. This is by-design\r\n# - in order to maximize ease-of-use.\r\n#\r\n# Entries are defined using the following - CSV format:\r\n# , ... , ... ,\r\n#\r\n# Notice that a single half-width space separates tokens and readings, - and\r\n# that the number tokens and readings must match exactly.\r\n#\r\n# Also - notice that multiple entries with the same is undefined.\r\n#\r\n# Whitespace - only lines are ignored. Comments are not allowed on entry lines.\r\n#\r\n\r\n# - Custom segmentation for kanji compounds\r\n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\r\n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\r\n\r\n# Custom segmentation for compound katakana\r\nトートバッグ,トート - バッグ,トート バッグ,かずカナ名詞\r\n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\r\n\r\n# Custom reading - for former sumo wrestler\r\n朝青龍,朝青龍,アサショウリュウ,カスタム人名\r\n" + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/src/main/java/org/computate/frFR/java/ConfigSite.java b/src/main/java/org/computate/frFR/java/ConfigSite.java index 09b74079..ff8ed4eb 100644 --- a/src/main/java/org/computate/frFR/java/ConfigSite.java +++ b/src/main/java/org/computate/frFR/java/ConfigSite.java @@ -587,6 +587,13 @@ protected void _siteZone() throws Exception { langueConfigGlobale.getString(I18n.var_SITE_ZONE)); } + public String solrId; + + protected void _solrId() throws Exception { + solrId = config.getString( + langueConfigGlobale.getString(I18n.var_SOLR_ID)); + } + /** * Var.enUS: solrUrlComputate enUS: The Solr web URL for the "computate" index. */ @@ -933,6 +940,7 @@ public void initConfigSite() throws Exception { _composantsWebPrefixe(); _nomFichierConfig(); _siteZone(); + _solrId(); // _versionMaven(); // _versionZookeeper(); // _prefixePortZookeeper(); diff --git a/src/main/java/org/computate/frFR/java/IndexerClasse.java b/src/main/java/org/computate/frFR/java/IndexerClasse.java index 6946ee7d..72fb295f 100644 --- a/src/main/java/org/computate/frFR/java/IndexerClasse.java +++ b/src/main/java/org/computate/frFR/java/IndexerClasse.java @@ -2697,8 +2697,8 @@ else if("LocalTime".equals(classeMapCleType) && NumberUtils.isCreatable(classeMa classePromesse = true; } - if(classeDoc.getField("id") == null) - classeDoc.addField("id", classeCle); + if(classeDoc.getField(solrId) == null) + classeDoc.addField(solrId, classeCle); indexerStockerSolr(classeDoc, "partEstClasse", true); indexerStockerSolr(classeDoc, "partNumero", partNumero); @@ -2792,7 +2792,7 @@ else if("LocalTime".equals(classeMapCleType) && NumberUtils.isCreatable(classeMa stockerSolr(classeLangueNom, champDoc, "champNomSimpleComplet", champClasseParts.nomSimpleComplet(classeLangueNom)); String champNomCanoniqueComplet = stockerSolr(classeLangueNom, champDoc, "champNomCanoniqueComplet", champClasseParts.nomCanoniqueComplet(classeLangueNom)); stockerSolr(classeLangueNom, champDoc, "champCodeSource", champCodeSource); - champDoc.addField("id", champNomCanoniqueComplet + " " + champCle); + champDoc.addField(solrId, champNomCanoniqueComplet + " " + champCle); if(classeTraduire) { for(String langueNom : classeAutresLangues) { @@ -2861,7 +2861,7 @@ else if(membreQdox instanceof JavaConstructor) { } constructeurCle += ")"; - constructeurDoc.addField("id", constructeurCle); + constructeurDoc.addField(solrId, constructeurCle); indexerStockerSolr(constructeurDoc, "partEstConstructeur", true); indexerStockerSolr(constructeurDoc, "partNumero", partNumero); @@ -3736,7 +3736,7 @@ else if(regexTrouve("^" + i18nGlobale.getString(I18n.var_HtmLigne) + i18nGlobale // Entites Solr du entite. - entiteDoc.addField("id", entiteCle); + entiteDoc.addField(solrId, entiteCle); indexerStockerSolr(entiteDoc, "partEstEntite", true); indexerStockerSolr(entiteDoc, "partNumero", partNumero); @@ -4710,7 +4710,7 @@ else if(StringUtils.equalsAny(entiteNomCanonique, VAL_nomCanoniqueString)) { // Methodes Solr du methode. - methodeDoc.addField("id", methodeCle); + methodeDoc.addField(solrId, methodeCle); indexerStockerSolr(methodeDoc, "partEstMethode", true); indexerStockerSolr(methodeDoc, "partNumero", partNumero); @@ -6122,7 +6122,7 @@ else if(StringUtils.contains(classeApiMethode, i18nGlobale.getString(I18n.var_Re ArrayList fieldNames = new ArrayList<>(properties.fieldNames()); for(Integer i = 0; i < properties.size(); i++) { String fieldName = fieldNames.get(i); - if(!fieldName.equals("id") && !fieldName.equals("type")) { + if(!fieldName.equals(solrId) && !fieldName.equals("type")) { JsonObject field = properties.getJsonObject(fieldName); String jsonType = field.getString("type"); String description = field.getString("description"); diff --git a/src/main/java/org/computate/frFR/java/RegarderClasse.java b/src/main/java/org/computate/frFR/java/RegarderClasse.java index 9e323470..ec1748de 100644 --- a/src/main/java/org/computate/frFR/java/RegarderClasse.java +++ b/src/main/java/org/computate/frFR/java/RegarderClasse.java @@ -166,7 +166,7 @@ public static SolrInputDocument regarderClasse(JsonObject classeLangueConfig, Js if(new File(regarderClasse.classeCheminAbsolu).isFile() && regarderClasse.classeCheminAbsolu.endsWith(".java")) { SolrInputDocument classeDoc = new SolrInputDocument(); -// classeDoc.addField("id", regarderClasse.classeCheminAbsolu); +// classeDoc.addField(solrId, regarderClasse.classeCheminAbsolu); regarderClasse.indexerClasse(regarderClasse.classeCheminAbsolu, classeDoc, classeLangueNom); String classeNomSimple = Optional.ofNullable(classeDoc.get("classeNomSimple_enUS_stored_string")).map(o -> (String)o.getValue()).orElse(null); // Date classeModifie = Optional.ofNullable(classeDoc.get("modifiee_stored_date")).map(o -> (Date)o.getValue()).orElse(null);