commit
318907ad3d
97 changed files with 11081 additions and 0 deletions
+ 5
- 0
.gitignore
View File
| @@ -0,0 +1,5 @@ | |||
| .DS_Store | |||
| config.env | |||
| config.env.prod | |||
| data | |||
| web/app/__pycache__/ | |||
+ 21
- 0
LICENSE
View File
| @@ -0,0 +1,21 @@ | |||
| MIT License | |||
| Copyright (c) 2021 Simon Bowie <ad7588@coventry.ac.uk> | |||
| Permission is hereby granted, free of charge, to any person obtaining a copy | |||
| of this software and associated documentation files (the "Software"), to deal | |||
| in the Software without restriction, including without limitation the rights | |||
| to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |||
| copies of the Software, and to permit persons to whom the Software is furnished | |||
| to do so, subject to the following conditions: | |||
| The above copyright notice and this permission notice (including the next | |||
| paragraph) shall be included in all copies or substantial portions of the | |||
| Software. | |||
| THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR | |||
| IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS | |||
| FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS | |||
| OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, | |||
| WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF | |||
| OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. | |||
+ 53
- 0
README.md
View File
| @@ -0,0 +1,53 @@ | |||
| # Archival Conversations patents data search engine | |||
| This repository contains the Docker Compose, Nginx, Python, and Solr config files for deploying the development environment for the Archival Conversations patents data search engine site. | |||
| ## to deploy environment | |||
| ### config.env | |||
| To deploy this environment, first copy config.env.template to a new file, config.env. Fill in the appropriate environment variables. | |||
| Note that on Mac the Python container has to communicate with the Solr container using the hostname 'host.docker.internal' rather than 'localhost' or '127.0.0.1': https://stackoverflow.com/questions/24319662/from-inside-of-a-docker-container-how-do-i-connect-to-the-localhost-of-the-mach | |||
| On Linux, you can use the container name e.g. 'solr' as the Solr hostname in config.env. | |||
| ### Docker Compose | |||
| In the command line, navigate to the directory where this repository is stored on your local machine and run: | |||
| `docker-compose up -d --build` | |||
| Docker should build the application environment comprising a Python container (including ImageMagick), an Apache Solr container (deployed Solr for .rtf indexing using instructions at: https://github.com/docker-solr/docker-solr), and an Nginx web server to serve the website. | |||
| The website should then be available in the browser at 'localhost:5000'. | |||
| To take down the environment, run: | |||
| `docker-compose down` | |||
| ## populating Apache Solr | |||
| In order to fill the site with documents, you will have to populate the Apache Solr search engine. There is a solr_import.sh script to help with this. Place whatever files you want indexed in a directory called 'data' within the main directory. | |||
| In solr_import.sh, change the directory to point to the main directory and, if necessary, change the location parameters for the various cores. | |||
| We use different Solr cores for the different themes on the site: 'all' is a core containing all documents while 'active', 'expanding', etc. contain only documents for that theme. | |||
| ### legacy Solr commands | |||
| This section should be fully superseded by solr_import.sh and including the Solr config in the repository. These are left here for reference. | |||
| Created core using: | |||
| `docker exec -it solr solr create_core -c epo_data` | |||
| Note this fix to ensure that .rtf files can be indexed using Apache Tika: https://gitmemory.com/issue/docker-solr/docker-solr/341/682877640. Once you've created the core, run these commands: | |||
| `docker exec -ti --user=solr solr bash -c 'cp -r /opt/solr/example/files/conf/* /var/solr/data/{CORE_NAME}/conf/'` | |||
| `docker restart solr` | |||
| Add files to Solr using: | |||
| `docker run --rm -v "/Users/ad7588/Downloads/2018 (10381):/2018" --network=host solr:latest post -c epo_data /2018` | |||
+ 23
- 0
config.env.template
View File
| @@ -0,0 +1,23 @@ | |||
| # This config file contains the environment variables for the application | |||
| # Flask variables | |||
| FLASK_APP=app/__init__.py | |||
| FLASK_RUN_HOST=0.0.0.0 | |||
| FLASK_DEBUG=1 | |||
| # Solr variables | |||
| # Hostname for Solr | |||
| SOLR_HOSTNAME= | |||
| # Solr port, usually 8983 | |||
| SOLR_PORT= | |||
| # Solr core, usually all | |||
| SOLR_CORE= | |||
| # OPS API variables | |||
| # Hostname for OPS API, usually https://ops.epo.org | |||
| OPS_URL= | |||
| # Hostname for OPS API for images for some reason different to above, usually http://ops.epo.org | |||
| OPS_URL_IMAGES= | |||
| # API credentials from OPS https://developers.epo.org/ | |||
| CONSUMER_KEY= | |||
| CONSUMER_SECRET= | |||
+ 37
- 0
docker-compose.prod.yml
View File
| @@ -0,0 +1,37 @@ | |||
| version: '3.9' | |||
| services: | |||
| python: | |||
| build: ./web | |||
| container_name: python | |||
| expose: | |||
| - 5000 | |||
| env_file: | |||
| - ./config.env.prod | |||
| volumes: | |||
| - ./web:/code | |||
| command: gunicorn --bind 0.0.0.0:5000 "app:create_app()" | |||
| nginx: | |||
| image: nginx:latest | |||
| container_name: nginx | |||
| restart: unless-stopped | |||
| ports: | |||
| - "1337:80" | |||
| volumes: | |||
| - ./nginx-conf:/etc/nginx/conf.d | |||
| depends_on: | |||
| - python | |||
| solr: | |||
| container_name: solr | |||
| image: solr:latest | |||
| ports: | |||
| - '8983:8983' | |||
| volumes: | |||
| - solrdata:/var/solr | |||
| - ./solr_config:/opt/solr/server/solr/configsets/custom | |||
| volumes: | |||
| solrdata: | |||
+ 25
- 0
docker-compose.yml
View File
| @@ -0,0 +1,25 @@ | |||
| version: '3.9' | |||
| services: | |||
| python: | |||
| build: ./web | |||
| container_name: python | |||
| ports: | |||
| - "5000:5000" | |||
| volumes: | |||
| - ./web:/code | |||
| env_file: | |||
| - ./config.env | |||
| solr: | |||
| container_name: solr | |||
| image: solr:latest | |||
| ports: | |||
| - '8983:8983' | |||
| volumes: | |||
| - solrdata:/var/solr | |||
| - ./solr_config:/opt/solr/server/solr/configsets/custom | |||
| volumes: | |||
| solrdata: | |||
+ 16
- 0
nginx-conf/patents.conf
View File
| @@ -0,0 +1,16 @@ | |||
| upstream patents { | |||
| server python:5000; | |||
| } | |||
| server { | |||
| listen 80; | |||
| location / { | |||
| proxy_pass http://patents; | |||
| proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; | |||
| proxy_set_header Host $http_host; | |||
| proxy_redirect off; | |||
| } | |||
| } | |||
+ 67
- 0
solr_config/currency.xml
View File
| @@ -0,0 +1,67 @@ | |||
| <?xml version="1.0" ?> | |||
| <!-- | |||
| Licensed to the Apache Software Foundation (ASF) under one or more | |||
| contributor license agreements. See the NOTICE file distributed with | |||
| this work for additional information regarding copyright ownership. | |||
| The ASF licenses this file to You under the Apache License, Version 2.0 | |||
| (the "License"); you may not use this file except in compliance with | |||
| the License. You may obtain a copy of the License at | |||
| http://www.apache.org/licenses/LICENSE-2.0 | |||
| Unless required by applicable law or agreed to in writing, software | |||
| distributed under the License is distributed on an "AS IS" BASIS, | |||
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |||
| See the License for the specific language governing permissions and | |||
| limitations under the License. | |||
| --> | |||
| <!-- Example exchange rates file for CurrencyField type named "currency" in example schema --> | |||
| <currencyConfig version="1.0"> | |||
| <rates> | |||
| <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 --> | |||
| <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" /> | |||
| <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" /> | |||
| <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" /> | |||
| <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" /> | |||
| <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" /> | |||
| <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" /> | |||
| <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" /> | |||
| <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" /> | |||
| <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" /> | |||
| <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" /> | |||
| <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" /> | |||
| <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" /> | |||
| <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" /> | |||
| <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" /> | |||
| <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" /> | |||
| <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" /> | |||
| <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" /> | |||
| <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" /> | |||
| <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" /> | |||
| <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" /> | |||
| <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" /> | |||
| <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" /> | |||
| <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" /> | |||
| <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" /> | |||
| <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" /> | |||
| <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" /> | |||
| <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" /> | |||
| <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" /> | |||
| <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" /> | |||
| <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" /> | |||
| <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" /> | |||
| <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" /> | |||
| <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" /> | |||
| <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" /> | |||
| <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" /> | |||
| <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" /> | |||
| <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" /> | |||
| <!-- Cross-rates for some common currencies --> | |||
| <rate from="EUR" to="GBP" rate="0.869914" /> | |||
| <rate from="EUR" to="NOK" rate="7.800095" /> | |||
| <rate from="GBP" to="NOK" rate="8.966508" /> | |||
| </rates> | |||
| </currencyConfig> | |||
+ 42
- 0
solr_config/elevate.xml
View File
| @@ -0,0 +1,42 @@ | |||
| <?xml version="1.0" encoding="UTF-8" ?> | |||
| <!-- | |||
| Licensed to the Apache Software Foundation (ASF) under one or more | |||
| contributor license agreements. See the NOTICE file distributed with | |||
| this work for additional information regarding copyright ownership. | |||
| The ASF licenses this file to You under the Apache License, Version 2.0 | |||
| (the "License"); you may not use this file except in compliance with | |||
| the License. You may obtain a copy of the License at | |||
| http://www.apache.org/licenses/LICENSE-2.0 | |||
| Unless required by applicable law or agreed to in writing, software | |||
| distributed under the License is distributed on an "AS IS" BASIS, | |||
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |||
| See the License for the specific language governing permissions and | |||
| limitations under the License. | |||
| --> | |||
| <!-- If this file is found in the config directory, it will only be | |||
| loaded once at startup. If it is found in Solr's data | |||
| directory, it will be re-loaded every commit. | |||
| See http://wiki.apache.org/solr/QueryElevationComponent for more info | |||
| --> | |||
| <elevate> | |||
| <!-- Query elevation examples | |||
| <query text="foo bar"> | |||
| <doc id="1" /> | |||
| <doc id="2" /> | |||
| <doc id="3" /> | |||
| </query> | |||
| for use with techproducts example | |||
| <query text="ipod"> | |||
| <doc id="MA147LL/A" /> put the actual ipod at the top | |||
| <doc id="IW-02" exclude="true" /> exclude this cable | |||
| </query> | |||
| --> | |||
| </elevate> | |||
+ 2
- 0
solr_config/email_url_types.txt
View File
| @@ -0,0 +1,2 @@ | |||
| <URL> | |||
| <EMAIL> | |||
+ 8
- 0
solr_config/lang/contractions_ca.txt
View File
| @@ -0,0 +1,8 @@ | |||
| # Set of Catalan contractions for ElisionFilter | |||
| # TODO: load this as a resource from the analyzer and sync it in build.xml | |||
| d | |||
| l | |||
| m | |||
| n | |||
| s | |||
| t | |||
+ 15
- 0
solr_config/lang/contractions_fr.txt
View File
| @@ -0,0 +1,15 @@ | |||
| # 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 | |||
+ 5
- 0
solr_config/lang/contractions_ga.txt
View File
| @@ -0,0 +1,5 @@ | |||
| # Set of Irish contractions for ElisionFilter | |||
| # TODO: load this as a resource from the analyzer and sync it in build.xml | |||
| d | |||
| m | |||
| b | |||
+ 23
- 0
solr_config/lang/contractions_it.txt
View File
| @@ -0,0 +1,23 @@ | |||
| # Set of Italian contractions for ElisionFilter | |||
| # TODO: load this as a resource from the analyzer and sync it in build.xml | |||
| c | |||
| l | |||
| all | |||
| dall | |||
| dell | |||
| nell | |||
| sull | |||
| coll | |||
| pell | |||
| gl | |||
| agl | |||
| dagl | |||
| degl | |||
| negl | |||
| sugl | |||
| un | |||
| m | |||
| t | |||
| s | |||
| v | |||
| d | |||
+ 5
- 0
solr_config/lang/hyphenations_ga.txt
View File
| @@ -0,0 +1,5 @@ | |||
| # Set of Irish hyphenations for StopFilter | |||
| # TODO: load this as a resource from the analyzer and sync it in build.xml | |||
| h | |||
| n | |||
| t | |||
+ 6
- 0
solr_config/lang/stemdict_nl.txt
View File
| @@ -0,0 +1,6 @@ | |||
| # Set of overrides for the dutch stemmer | |||
| # TODO: load this as a resource from the analyzer and sync it in build.xml | |||
| fiets fiets | |||
| bromfiets bromfiets | |||
| ei eier | |||
| kind kinder | |||
+ 420
- 0
solr_config/lang/stoptags_ja.txt
View File
| @@ -0,0 +1,420 @@ | |||
| # | |||
| # This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter. | |||
| # | |||
| # Any token with a part-of-speech tag that exactly matches those defined in this | |||
| # file are removed from the token stream. | |||
| # | |||
| # Set your own stoptags by uncommenting the lines below. Note that comments are | |||
| # not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists, | |||
| # etc. that can be useful for building you own stoptag set. | |||
| # | |||
| # The entire possible tagset is provided below for convenience. | |||
| # | |||
| ##### | |||
| # noun: unclassified nouns | |||
| #名詞 | |||
| # | |||
| # noun-common: Common nouns or nouns where the sub-classification is undefined | |||
| #名詞-一般 | |||
| # | |||
| # noun-proper: Proper nouns where the sub-classification is undefined | |||
| #名詞-固有名詞 | |||
| # | |||
| # noun-proper-misc: miscellaneous proper nouns | |||
| #名詞-固有名詞-一般 | |||
| # | |||
| # noun-proper-person: Personal names where the sub-classification is undefined | |||
| #名詞-固有名詞-人名 | |||
| # | |||
| # noun-proper-person-misc: names that cannot be divided into surname and | |||
| # given name; foreign names; names where the surname or given name is unknown. | |||
| # e.g. お市の方 | |||
| #名詞-固有名詞-人名-一般 | |||
| # | |||
| # noun-proper-person-surname: Mainly Japanese surnames. | |||
| # e.g. 山田 | |||
| #名詞-固有名詞-人名-姓 | |||
| # | |||
| # noun-proper-person-given_name: Mainly Japanese given names. | |||
| # e.g. 太郎 | |||
| #名詞-固有名詞-人名-名 | |||
| # | |||
| # noun-proper-organization: Names representing organizations. | |||
| # e.g. 通産省, NHK | |||
| #名詞-固有名詞-組織 | |||
| # | |||
| # noun-proper-place: Place names where the sub-classification is undefined | |||
| #名詞-固有名詞-地域 | |||
| # | |||
| # noun-proper-place-misc: Place names excluding countries. | |||
| # e.g. アジア, バルセロナ, 京都 | |||
| #名詞-固有名詞-地域-一般 | |||
| # | |||
| # noun-proper-place-country: Country names. | |||
| # e.g. 日本, オーストラリア | |||
| #名詞-固有名詞-地域-国 | |||
| # | |||
| # noun-pronoun: Pronouns where the sub-classification is undefined | |||
| #名詞-代名詞 | |||
| # | |||
| # noun-pronoun-misc: miscellaneous pronouns: | |||
| # e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ | |||
| #名詞-代名詞-一般 | |||
| # | |||
| # noun-pronoun-contraction: Spoken language contraction made by combining a | |||
| # pronoun and the particle 'wa'. | |||
| # e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ | |||
| #名詞-代名詞-縮約 | |||
| # | |||
| # noun-adverbial: Temporal nouns such as names of days or months that behave | |||
| # like adverbs. Nouns that represent amount or ratios and can be used adverbially, | |||
| # e.g. 金曜, 一月, 午後, 少量 | |||
| #名詞-副詞可能 | |||
| # | |||
| # noun-verbal: Nouns that take arguments with case and can appear followed by | |||
| # 'suru' and related verbs (する, できる, なさる, くださる) | |||
| # e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り | |||
| #名詞-サ変接続 | |||
| # | |||
| # noun-adjective-base: The base form of adjectives, words that appear before な ("na") | |||
| # e.g. 健康, 安易, 駄目, だめ | |||
| #名詞-形容動詞語幹 | |||
| # | |||
| # noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数. | |||
| # e.g. 0, 1, 2, 何, 数, 幾 | |||
| #名詞-数 | |||
| # | |||
| # noun-affix: noun affixes where the sub-classification is undefined | |||
| #名詞-非自立 | |||
| # | |||
| # noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that | |||
| # attach to the base form of inflectional words, words that cannot be classified | |||
| # into any of the other categories below. This category includes indefinite nouns. | |||
| # e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第, | |||
| # 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み, | |||
| # 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳, | |||
| # わり, 割り, 割, ん-口語/, もん-口語/ | |||
| #名詞-非自立-一般 | |||
| # | |||
| # noun-affix-adverbial: noun affixes that that can behave as adverbs. | |||
| # e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ, | |||
| # 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか, | |||
| # 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所, | |||
| # とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま, | |||
| # 儘, 侭, みぎり, 矢先 | |||
| #名詞-非自立-副詞可能 | |||
| # | |||
| # noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars | |||
| # with the stem よう(だ) ("you(da)"). | |||
| # e.g. よう, やう, 様 (よう) | |||
| #名詞-非自立-助動詞語幹 | |||
| # | |||
| # noun-affix-adjective-base: noun affixes that can connect to the indeclinable | |||
| # connection form な (aux "da"). | |||
| # e.g. みたい, ふう | |||
| #名詞-非自立-形容動詞語幹 | |||
| # | |||
| # noun-special: special nouns where the sub-classification is undefined. | |||
| #名詞-特殊 | |||
| # | |||
| # noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is | |||
| # treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base | |||
| # form of inflectional words. | |||
| # e.g. そう | |||
| #名詞-特殊-助動詞語幹 | |||
| # | |||
| # noun-suffix: noun suffixes where the sub-classification is undefined. | |||
| #名詞-接尾 | |||
| # | |||
| # noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect | |||
| # to ガル or タイ and can combine into compound nouns, words that cannot be classified into | |||
| # any of the other categories below. In general, this category is more inclusive than | |||
| # 接尾語 ("suffix") and is usually the last element in a compound noun. | |||
| # e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み, | |||
| # よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用 | |||
| #名詞-接尾-一般 | |||
| # | |||
| # noun-suffix-person: Suffixes that form nouns and attach to person names more often | |||
| # than other nouns. | |||
| # e.g. 君, 様, 著 | |||
| #名詞-接尾-人名 | |||
| # | |||
| # noun-suffix-place: Suffixes that form nouns and attach to place names more often | |||
| # than other nouns. | |||
| # e.g. 町, 市, 県 | |||
| #名詞-接尾-地域 | |||
| # | |||
| # noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that | |||
| # can appear before スル ("suru"). | |||
| # e.g. 化, 視, 分け, 入り, 落ち, 買い | |||
| #名詞-接尾-サ変接続 | |||
| # | |||
| # noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions, | |||
| # is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the | |||
| # conjunctive form of inflectional words. | |||
| # e.g. そう | |||
| #名詞-接尾-助動詞語幹 | |||
| # | |||
| # noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive | |||
| # form of inflectional words and appear before the copula だ ("da"). | |||
| # e.g. 的, げ, がち | |||
| #名詞-接尾-形容動詞語幹 | |||
| # | |||
| # noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs. | |||
| # e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ) | |||
| #名詞-接尾-副詞可能 | |||
| # | |||
| # noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category | |||
| # is more inclusive than 助数詞 ("classifier") and includes common nouns that attach | |||
| # to numbers. | |||
| # e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半 | |||
| #名詞-接尾-助数詞 | |||
| # | |||
| # noun-suffix-special: Special suffixes that mainly attach to inflecting words. | |||
| # e.g. (楽し) さ, (考え) 方 | |||
| #名詞-接尾-特殊 | |||
| # | |||
| # noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words | |||
| # together. | |||
| # e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦) | |||
| #名詞-接続詞的 | |||
| # | |||
| # noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are | |||
| # semantically verb-like. | |||
| # e.g. ごらん, ご覧, 御覧, 頂戴 | |||
| #名詞-動詞非自立的 | |||
| # | |||
| # noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry, | |||
| # dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation") | |||
| # is いわく ("iwaku"). | |||
| #名詞-引用文字列 | |||
| # | |||
| # noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and | |||
| # behave like an adjective. | |||
| # e.g. 申し訳, 仕方, とんでも, 違い | |||
| #名詞-ナイ形容詞語幹 | |||
| # | |||
| ##### | |||
| # prefix: unclassified prefixes | |||
| #接頭詞 | |||
| # | |||
| # prefix-nominal: Prefixes that attach to nouns (including adjective stem forms) | |||
| # excluding numerical expressions. | |||
| # e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派) | |||
| #接頭詞-名詞接続 | |||
| # | |||
| # prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb | |||
| # in conjunctive form followed by なる/なさる/くださる. | |||
| # e.g. お (読みなさい), お (座り) | |||
| #接頭詞-動詞接続 | |||
| # | |||
| # prefix-adjectival: Prefixes that attach to adjectives. | |||
| # e.g. お (寒いですねえ), バカ (でかい) | |||
| #接頭詞-形容詞接続 | |||
| # | |||
| # prefix-numerical: Prefixes that attach to numerical expressions. | |||
| # e.g. 約, およそ, 毎時 | |||
| #接頭詞-数接続 | |||
| # | |||
| ##### | |||
| # verb: unclassified verbs | |||
| #動詞 | |||
| # | |||
| # verb-main: | |||
| #動詞-自立 | |||
| # | |||
| # verb-auxiliary: | |||
| #動詞-非自立 | |||
| # | |||
| # verb-suffix: | |||
| #動詞-接尾 | |||
| # | |||
| ##### | |||
| # adjective: unclassified adjectives | |||
| #形容詞 | |||
| # | |||
| # adjective-main: | |||
| #形容詞-自立 | |||
| # | |||
| # adjective-auxiliary: | |||
| #形容詞-非自立 | |||
| # | |||
| # adjective-suffix: | |||
| #形容詞-接尾 | |||
| # | |||
| ##### | |||
| # adverb: unclassified adverbs | |||
| #副詞 | |||
| # | |||
| # adverb-misc: Words that can be segmented into one unit and where adnominal | |||
| # modification is not possible. | |||
| # e.g. あいかわらず, 多分 | |||
| #副詞-一般 | |||
| # | |||
| # adverb-particle_conjunction: Adverbs that can be followed by の, は, に, | |||
| # な, する, だ, etc. | |||
| # e.g. こんなに, そんなに, あんなに, なにか, なんでも | |||
| #副詞-助詞類接続 | |||
| # | |||
| ##### | |||
| # adnominal: Words that only have noun-modifying forms. | |||
| # e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう, | |||
| # どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした, | |||
| # 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き | |||
| #連体詞 | |||
| # | |||
| ##### | |||
| # conjunction: Conjunctions that can occur independently. | |||
| # e.g. が, けれども, そして, じゃあ, それどころか | |||
| 接続詞 | |||
| # | |||
| ##### | |||
| # particle: unclassified particles. | |||
| 助詞 | |||
| # | |||
| # particle-case: case particles where the subclassification is undefined. | |||
| 助詞-格助詞 | |||
| # | |||
| # particle-case-misc: Case particles. | |||
| # e.g. から, が, で, と, に, へ, より, を, の, にて | |||
| 助詞-格助詞-一般 | |||
| # | |||
| # particle-case-quote: the "to" that appears after nouns, a person’s speech, | |||
| # quotation marks, expressions of decisions from a meeting, reasons, judgements, | |||
| # conjectures, etc. | |||
| # e.g. ( だ) と (述べた.), ( である) と (して執行猶予...) | |||
| 助詞-格助詞-引用 | |||
| # | |||
| # particle-case-compound: Compounds of particles and verbs that mainly behave | |||
| # like case particles. | |||
| # e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って, | |||
| # にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける, | |||
| # にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し, | |||
| # に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして, | |||
| # に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって, | |||
| # にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る, | |||
| # にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる, | |||
| # って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ | |||
| 助詞-格助詞-連語 | |||
| # | |||
| # particle-conjunctive: | |||
| # e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども, | |||
| # ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/, | |||
| # (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/ | |||
| 助詞-接続助詞 | |||
| # | |||
| # particle-dependency: | |||
| # e.g. こそ, さえ, しか, すら, は, も, ぞ | |||
| 助詞-係助詞 | |||
| # | |||
| # particle-adverbial: | |||
| # e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/, | |||
| # (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/, | |||
| # (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに, | |||
| # (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/, | |||
| # ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」) | |||
| 助詞-副助詞 | |||
| # | |||
| # particle-interjective: particles with interjective grammatical roles. | |||
| # e.g. (松島) や | |||
| 助詞-間投助詞 | |||
| # | |||
| # particle-coordinate: | |||
| # e.g. と, たり, だの, だり, とか, なり, や, やら | |||
| 助詞-並立助詞 | |||
| # | |||
| # particle-final: | |||
| # e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ, | |||
| # ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/ | |||
| 助詞-終助詞 | |||
| # | |||
| # particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is | |||
| # adverbial, conjunctive, or sentence final. For example: | |||
| # (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」 | |||
| # (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」 | |||
| # 「(祈りが届いたせい) か (, 試験に合格した.)」 | |||
| # (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」 | |||
| # e.g. か | |||
| 助詞-副助詞／並立助詞／終助詞 | |||
| # | |||
| # particle-adnominalizer: The "no" that attaches to nouns and modifies | |||
| # non-inflectional words. | |||
| 助詞-連体化 | |||
| # | |||
| # particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs | |||
| # that are giongo, giseigo, or gitaigo. | |||
| # e.g. に, と | |||
| 助詞-副詞化 | |||
| # | |||
| # particle-special: A particle that does not fit into one of the above classifications. | |||
| # This includes particles that are used in Tanka, Haiku, and other poetry. | |||
| # e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家) | |||
| 助詞-特殊 | |||
| # | |||
| ##### | |||
| # auxiliary-verb: | |||
| 助動詞 | |||
| # | |||
| ##### | |||
| # interjection: Greetings and other exclamations. | |||
| # e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます, | |||
| # いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい | |||
| #感動詞 | |||
| # | |||
| ##### | |||
| # symbol: unclassified Symbols. | |||
| 記号 | |||
| # | |||
| # symbol-misc: A general symbol not in one of the categories below. | |||
| # e.g. [○◎@$〒→+] | |||
| 記号-一般 | |||
| # | |||
| # symbol-comma: Commas | |||
| # e.g. [,、] | |||
| 記号-読点 | |||
| # | |||
| # symbol-period: Periods and full stops. | |||
| # e.g. [.．。] | |||
| 記号-句点 | |||
| # | |||
| # symbol-space: Full-width whitespace. | |||
| 記号-空白 | |||
| # | |||
| # symbol-open_bracket: | |||
| # e.g. [({‘“『【] | |||
| 記号-括弧開 | |||
| # | |||
| # symbol-close_bracket: | |||
| # e.g. [)}’”』」】] | |||
| 記号-括弧閉 | |||
| # | |||
| # symbol-alphabetic: | |||
| #記号-アルファベット | |||
| # | |||
| ##### | |||
| # other: unclassified other | |||
| #その他 | |||
| # | |||
| # other-interjection: Words that are hard to classify as noun-suffixes or | |||
| # sentence-final particles. | |||
| # e.g. (だ)ァ | |||
| その他-間投 | |||
| # | |||
| ##### | |||
| # filler: Aizuchi that occurs during a conversation or sounds inserted as filler. | |||
| # e.g. あの, うんと, えと | |||
| フィラー | |||
| # | |||
| ##### | |||
| # non-verbal: non-verbal sound. | |||
| 非言語音 | |||
| # | |||
| ##### | |||
| # fragment: | |||
| #語断片 | |||
| # | |||
| ##### | |||
| # unknown: unknown part of speech. | |||
| #未知語 | |||
| # | |||
| ##### End of file | |||
+ 125
- 0
solr_config/lang/stopwords_ar.txt
View File
| @@ -0,0 +1,125 @@ | |||
| # This file was created by Jacques Savoy and is distributed under the BSD license. | |||
| # See http://members.unine.ch/jacques.savoy/clef/index.html. | |||
| # Also see http://www.opensource.org/licenses/bsd-license.html | |||
| # Cleaned on October 11, 2009 (not normalized, so use before normalization) | |||
| # This means that when modifying this list, you might need to add some | |||
| # redundant entries, for example containing forms with both أ and ا | |||
| من | |||
| ومن | |||
| منها | |||
| منه | |||
| في | |||
| وفي | |||
| فيها | |||
| فيه | |||
| و | |||
| ف | |||
| ثم | |||
| او | |||
| أو | |||
| ب | |||
| بها | |||
| به | |||
| ا | |||
| أ | |||
| اى | |||
| اي | |||
| أي | |||
| أى | |||
| لا | |||
| ولا | |||
| الا | |||
| ألا | |||
| إلا | |||
| لكن | |||
| ما | |||
| وما | |||
| كما | |||
| فما | |||
| عن | |||
| مع | |||
| اذا | |||
| إذا | |||
| ان | |||
| أن | |||
| إن | |||
| انها | |||
| أنها | |||
| إنها | |||
| انه | |||
| أنه | |||
| إنه | |||
| بان | |||
| بأن | |||
| فان | |||
| فأن | |||
| وان | |||
| وأن | |||
| وإن | |||
| التى | |||
| التي | |||
| الذى | |||
| الذي | |||
| الذين | |||
| الى | |||
| الي | |||
| إلى | |||
| إلي | |||
| على | |||
| عليها | |||
| عليه | |||
| اما | |||
| أما | |||
| إما | |||
| ايضا | |||
| أيضا | |||
| كل | |||
| وكل | |||
| لم | |||
| ولم | |||
| لن | |||
| ولن | |||
| هى | |||
| هي | |||
| هو | |||
| وهى | |||
| وهي | |||
| وهو | |||
| فهى | |||
| فهي | |||
| فهو | |||
| انت | |||
| أنت | |||
| لك | |||
| لها | |||
| له | |||
| هذه | |||
| هذا | |||
| تلك | |||
| ذلك | |||
| هناك | |||
| كانت | |||
| كان | |||
| يكون | |||
| تكون | |||
| وكانت | |||
| وكان | |||
| غير | |||
| بعض | |||
| قد | |||
| نحو | |||
| بين | |||
| بينما | |||
| منذ | |||
| ضمن | |||
| حيث | |||
| الان | |||
| الآن | |||
| خلال | |||
| بعد | |||
| قبل | |||
| حتى | |||
| عند | |||
| عندما | |||
| لدى | |||
| جميع | |||
+ 193
- 0
solr_config/lang/stopwords_bg.txt
View File
| @@ -0,0 +1,193 @@ | |||
| # This file was created by Jacques Savoy and is distributed under the BSD license. | |||
| # See http://members.unine.ch/jacques.savoy/clef/index.html. | |||
| # Also see http://www.opensource.org/licenses/bsd-license.html | |||
| а | |||
| аз | |||
| ако | |||
| ала | |||
| бе | |||
| без | |||
| беше | |||
| би | |||
| бил | |||
| била | |||
| били | |||
| било | |||
| близо | |||
| бъдат | |||
| бъде | |||
| бяха | |||
| в | |||
| вас | |||
| ваш | |||
| ваша | |||
| вероятно | |||
| вече | |||
| взема | |||
| ви | |||
| вие | |||
| винаги | |||
| все | |||
| всеки | |||
| всички | |||
| всичко | |||
| всяка | |||
| във | |||
| въпреки | |||
| върху | |||
| г | |||
| ги | |||
| главно | |||
| го | |||
| д | |||
| да | |||
| дали | |||
| до | |||
| докато | |||
| докога | |||
| дори | |||
| досега | |||
| доста | |||
| е | |||
| едва | |||
| един | |||
| ето | |||
| за | |||
| зад | |||
| заедно | |||
| заради | |||
| засега | |||
| затова | |||
| защо | |||
| защото | |||
| и | |||
| из | |||
| или | |||
| им | |||
| има | |||
| имат | |||
| иска | |||
| й | |||
| каза | |||
| как | |||
| каква | |||
| какво | |||
| както | |||
| какъв | |||
| като | |||
| кога | |||
| когато | |||
| което | |||
| които | |||
| кой | |||
| който | |||
| колко | |||
| която | |||
| къде | |||
| където | |||
| към | |||
| ли | |||
| м | |||
| ме | |||
| между | |||
| мен | |||
| ми | |||
| мнозина | |||
| мога | |||
| могат | |||
| може | |||
| моля | |||
| момента | |||
| му | |||
| н | |||
| на | |||
| над | |||
| назад | |||
| най | |||
| направи | |||
| напред | |||
| например | |||
| нас | |||
| не | |||
| него | |||
| нея | |||
| ни | |||
| ние | |||
| никой | |||
| нито | |||
| но | |||
| някои | |||
| някой | |||
| няма | |||
| обаче | |||
| около | |||
| освен | |||
| особено | |||
| от | |||
| отгоре | |||
| отново | |||
| още | |||
| пак | |||
| по | |||
| повече | |||
| повечето | |||
| под | |||
| поне | |||
| поради | |||
| после | |||
| почти | |||
| прави | |||
| пред | |||
| преди | |||
| през | |||
| при | |||
| пък | |||
| първо | |||
| с | |||
| са | |||
| само | |||
| се | |||
| сега | |||
| си | |||
| скоро | |||
| след | |||
| сме | |||
| според | |||
| сред | |||
| срещу | |||
| сте | |||
| съм | |||
| със | |||
| също | |||
| т | |||
| тази | |||
| така | |||
| такива | |||
| такъв | |||
| там | |||
| твой | |||
| те | |||
| тези | |||
| ти | |||
| тн | |||
| то | |||
| това | |||
| тогава | |||
| този | |||
| той | |||
| толкова | |||
| точно | |||
| трябва | |||
| тук | |||
| тъй | |||
| тя | |||
| тях | |||
| у | |||
| харесва | |||
| ч | |||
| че | |||
| често | |||
| чрез | |||
| ще | |||
| щом | |||
| я | |||
+ 220
- 0
solr_config/lang/stopwords_ca.txt
View File
| @@ -0,0 +1,220 @@ | |||
| # Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed) | |||
| a | |||
| abans | |||
| ací | |||
| ah | |||
| així | |||
| això | |||
| al | |||
| als | |||
| aleshores | |||
| algun | |||
| alguna | |||
| algunes | |||
| alguns | |||
| alhora | |||
| allà | |||
| allí | |||
| allò | |||
| altra | |||
| altre | |||
| altres | |||
| amb | |||
| ambdós | |||
| ambdues | |||
| apa | |||
| aquell | |||
| aquella | |||
| aquelles | |||
| aquells | |||
| aquest | |||
| aquesta | |||
| aquestes | |||
| aquests | |||
| aquí | |||
| baix | |||
| cada | |||
| cadascú | |||
| cadascuna | |||
| cadascunes | |||
| cadascuns | |||
| com | |||
| contra | |||
| d'un | |||
| d'una | |||
| d'unes | |||
| d'uns | |||
| dalt | |||
| de | |||
| del | |||
| dels | |||
| des | |||
| després | |||
| dins | |||
| dintre | |||
| donat | |||
| doncs | |||
| durant | |||
| e | |||
| eh | |||
| el | |||
| els | |||
| em | |||
| en | |||
| encara | |||
| ens | |||
| entre | |||
| érem | |||
| eren | |||
| éreu | |||
| es | |||
| és | |||
| esta | |||
| està | |||
| estàvem | |||
| estaven | |||
| estàveu | |||
| esteu | |||
| et | |||
| etc | |||
| ets | |||
| fins | |||
| fora | |||
| gairebé | |||
| ha | |||
| han | |||
| has | |||
| havia | |||
| he | |||
| hem | |||
| heu | |||
| hi | |||
| ho | |||
| i | |||
| igual | |||
| iguals | |||
| ja | |||
| l'hi | |||
| la | |||
| les | |||
| li | |||
| li'n | |||
| llavors | |||
| m'he | |||
| ma | |||
| mal | |||
| malgrat | |||
| mateix | |||
| mateixa | |||
| mateixes | |||
| mateixos | |||
| me | |||
| mentre | |||
| més | |||
| meu | |||
| meus | |||
| meva | |||
| meves | |||
| molt | |||
| molta | |||
| moltes | |||
| molts | |||
| mon | |||
| mons | |||
| n'he | |||
| n'hi | |||
| ne | |||
| ni | |||
| no | |||
| nogensmenys | |||
| només | |||
| nosaltres | |||
| nostra | |||
| nostre | |||
| nostres | |||
| o | |||
| oh | |||
| oi | |||
| on | |||
| pas | |||
| pel | |||
| pels | |||
| per | |||
| però | |||
| perquè | |||
| poc | |||
| poca | |||
| pocs | |||
| poques | |||
| potser | |||
| propi | |||
| qual | |||
| quals | |||
| quan | |||
| quant | |||
| que | |||
| què | |||
| quelcom | |||
| qui | |||
| quin | |||
| quina | |||
| quines | |||
| quins | |||
| s'ha | |||
| s'han | |||
| sa | |||
| semblant | |||
| semblants | |||
| ses | |||
| seu | |||
| seus | |||
| seva | |||
| seva | |||
| seves | |||
| si | |||
| sobre | |||
| sobretot | |||
| sóc | |||
| solament | |||
| sols | |||
| son | |||
| són | |||
| sons | |||
| sota | |||
| sou | |||
| t'ha | |||
| t'han | |||
| t'he | |||
| ta | |||
| tal | |||
| també | |||
| tampoc | |||
| tan | |||
| tant | |||
| tanta | |||
| tantes | |||
| teu | |||
| teus | |||
| teva | |||
| teves | |||
| ton | |||
| tons | |||
| tot | |||
| tota | |||
| totes | |||
| tots | |||
| un | |||
| una | |||
| unes | |||
| uns | |||
| us | |||
| va | |||
| vaig | |||
| vam | |||
| van | |||
| vas | |||
| veu | |||
| vosaltres | |||
| vostra | |||
| vostre | |||
| vostres | |||
+ 172
- 0
solr_config/lang/stopwords_cz.txt
View File
| @@ -0,0 +1,172 @@ | |||
| a | |||
| s | |||
| k | |||
| o | |||
| i | |||
| u | |||
| v | |||
| z | |||
| dnes | |||
| cz | |||
| tímto | |||
| budeš | |||
| budem | |||
| byli | |||
| jseš | |||
| můj | |||
| svým | |||
| ta | |||
| tomto | |||
| tohle | |||
| tuto | |||
| tyto | |||
| jej | |||
| zda | |||
| proč | |||
| máte | |||
| tato | |||
| kam | |||
| tohoto | |||
| kdo | |||
| kteří | |||
| mi | |||
| nám | |||
| tom | |||
| tomuto | |||
| mít | |||
| nic | |||
| proto | |||
| kterou | |||
| byla | |||
| toho | |||
| protože | |||
| asi | |||
| ho | |||
| naši | |||
| napište | |||
| re | |||
| což | |||
| tím | |||
| takže | |||
| svých | |||
| její | |||
| svými | |||
| jste | |||
| aj | |||
| tu | |||
| tedy | |||
| teto | |||
| bylo | |||
| kde | |||
| ke | |||
| pravé | |||
| ji | |||
| nad | |||
| nejsou | |||
| či | |||
| pod | |||
| téma | |||
| mezi | |||
| přes | |||
| ty | |||
| pak | |||
| vám | |||
| ani | |||
| když | |||
| však | |||
| neg | |||
| jsem | |||
| tento | |||
| článku | |||
| články | |||
| aby | |||
| jsme | |||
| před | |||
| pta | |||
| jejich | |||
| byl | |||
| ještě | |||
| až | |||
| bez | |||
| také | |||
| pouze | |||
| první | |||
| vaše | |||
| která | |||
| nás | |||
| nový | |||
| tipy | |||
| pokud | |||
| může | |||
| strana | |||
| jeho | |||
| své | |||
| jiné | |||
| zprávy | |||
| nové | |||
| není | |||
| vás | |||
| jen | |||
| podle | |||
| zde | |||
| už | |||
| být | |||
| více | |||
| bude | |||
| již | |||
| než | |||
| který | |||
| by | |||
| které | |||
| co | |||
| nebo | |||
| ten | |||
| tak | |||
| má | |||
| při | |||
| od | |||
| po | |||
| jsou | |||
| jak | |||
| další | |||
| ale | |||
| si | |||
| se | |||
| ve | |||
| to | |||
| jako | |||
| za | |||
| zpět | |||
| ze | |||
| do | |||
| pro | |||
| je | |||
| na | |||
| atd | |||
| atp | |||
| jakmile | |||
| přičemž | |||
| já | |||
| on | |||
| ona | |||
| ono | |||
| oni | |||
| ony | |||
| my | |||
| vy | |||
| jí | |||
| ji | |||
| mě | |||
| mne | |||
| jemu | |||
| tomu | |||
| těm | |||
| těmu | |||
| němu | |||
| němuž | |||
| jehož | |||
| jíž | |||
| jelikož | |||
| jež | |||
| jakož | |||
| načež | |||
+ 110
- 0
solr_config/lang/stopwords_da.txt
View File
| @@ -0,0 +1,110 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Danish stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | This is a ranked list (commonest to rarest) of stopwords derived from | |||
| | a large text sample. | |||
| og | and | |||
| i | in | |||
| jeg | I | |||
| det | that (dem. pronoun)/it (pers. pronoun) | |||
| at | that (in front of a sentence)/to (with infinitive) | |||
| en | a/an | |||
| den | it (pers. pronoun)/that (dem. pronoun) | |||
| til | to/at/for/until/against/by/of/into, more | |||
| er | present tense of "to be" | |||
| som | who, as | |||
| på | on/upon/in/on/at/to/after/of/with/for, on | |||
| de | they | |||
| med | with/by/in, along | |||
| han | he | |||
| af | of/by/from/off/for/in/with/on, off | |||
| for | at/for/to/from/by/of/ago, in front/before, because | |||
| ikke | not | |||
| der | who/which, there/those | |||
| var | past tense of "to be" | |||
| mig | me/myself | |||
| sig | oneself/himself/herself/itself/themselves | |||
| men | but | |||
| et | a/an/one, one (number), someone/somebody/one | |||
| har | present tense of "to have" | |||
| om | round/about/for/in/a, about/around/down, if | |||
| vi | we | |||
| min | my | |||
| havde | past tense of "to have" | |||
| ham | him | |||
| hun | she | |||
| nu | now | |||
| over | over/above/across/by/beyond/past/on/about, over/past | |||
| da | then, when/as/since | |||
| fra | from/off/since, off, since | |||
| du | you | |||
| ud | out | |||
| sin | his/her/its/one's | |||
| dem | them | |||
| os | us/ourselves | |||
| op | up | |||
| man | you/one | |||
| hans | his | |||
| hvor | where | |||
| eller | or | |||
| hvad | what | |||
| skal | must/shall etc. | |||
| selv | myself/youself/herself/ourselves etc., even | |||
| her | here | |||
| alle | all/everyone/everybody etc. | |||
| vil | will (verb) | |||
| blev | past tense of "to stay/to remain/to get/to become" | |||
| kunne | could | |||
| ind | in | |||
| når | when | |||
| være | present tense of "to be" | |||
| dog | however/yet/after all | |||
| noget | something | |||
| ville | would | |||
| jo | you know/you see (adv), yes | |||
| deres | their/theirs | |||
| efter | after/behind/according to/for/by/from, later/afterwards | |||
| ned | down | |||
| skulle | should | |||
| denne | this | |||
| end | than | |||
| dette | this | |||
| mit | my/mine | |||
| også | also | |||
| under | under/beneath/below/during, below/underneath | |||
| have | have | |||
| dig | you | |||
| anden | other | |||
| hende | her | |||
| mine | my | |||
| alt | everything | |||
| meget | much/very, plenty of | |||
| sit | his, her, its, one's | |||
| sine | his, her, its, one's | |||
| vor | our | |||
| mod | against | |||
| disse | these | |||
| hvis | if | |||
| din | your/yours | |||
| nogle | some | |||
| hos | by/at | |||
| blive | be/become | |||
| mange | many | |||
| ad | by/through | |||
| bliver | present tense of "to be/to become" | |||
| hendes | her/hers | |||
| været | be | |||
| thi | for (conj) | |||
| jer | you | |||
| sådan | such, like this/like that | |||
+ 294
- 0
solr_config/lang/stopwords_de.txt
View File
| @@ -0,0 +1,294 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A German stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | The number of forms in this list is reduced significantly by passing it | |||
| | through the German stemmer. | |||
| aber | but | |||
| alle | all | |||
| allem | |||
| allen | |||
| aller | |||
| alles | |||
| als | than, as | |||
| also | so | |||
| am | an + dem | |||
| an | at | |||
| ander | other | |||
| andere | |||
| anderem | |||
| anderen | |||
| anderer | |||
| anderes | |||
| anderm | |||
| andern | |||
| anderr | |||
| anders | |||
| auch | also | |||
| auf | on | |||
| aus | out of | |||
| bei | by | |||
| bin | am | |||
| bis | until | |||
| bist | art | |||
| da | there | |||
| damit | with it | |||
| dann | then | |||
| der | the | |||
| den | |||
| des | |||
| dem | |||
| die | |||
| das | |||
| daß | that | |||
| derselbe | the same | |||
| derselben | |||
| denselben | |||
| desselben | |||
| demselben | |||
| dieselbe | |||
| dieselben | |||
| dasselbe | |||
| dazu | to that | |||
| dein | thy | |||
| deine | |||
| deinem | |||
| deinen | |||
| deiner | |||
| deines | |||
| denn | because | |||
| derer | of those | |||
| dessen | of him | |||
| dich | thee | |||
| dir | to thee | |||
| du | thou | |||
| dies | this | |||
| diese | |||
| diesem | |||
| diesen | |||
| dieser | |||
| dieses | |||
| doch | (several meanings) | |||
| dort | (over) there | |||
| durch | through | |||
| ein | a | |||
| eine | |||
| einem | |||
| einen | |||
| einer | |||
| eines | |||
| einig | some | |||
| einige | |||
| einigem | |||
| einigen | |||
| einiger | |||
| einiges | |||
| einmal | once | |||
| er | he | |||
| ihn | him | |||
| ihm | to him | |||
| es | it | |||
| etwas | something | |||
| euer | your | |||
| eure | |||
| eurem | |||
| euren | |||
| eurer | |||
| eures | |||
| für | for | |||
| gegen | towards | |||
| gewesen | p.p. of sein | |||
| hab | have | |||
| habe | have | |||
| haben | have | |||
| hat | has | |||
| hatte | had | |||
| hatten | had | |||
| hier | here | |||
| hin | there | |||
| hinter | behind | |||
| ich | I | |||
| mich | me | |||
| mir | to me | |||
| ihr | you, to her | |||
| ihre | |||
| ihrem | |||
| ihren | |||
| ihrer | |||
| ihres | |||
| euch | to you | |||
| im | in + dem | |||
| in | in | |||
| indem | while | |||
| ins | in + das | |||
| ist | is | |||
| jede | each, every | |||
| jedem | |||
| jeden | |||
| jeder | |||
| jedes | |||
| jene | that | |||
| jenem | |||
| jenen | |||
| jener | |||
| jenes | |||
| jetzt | now | |||
| kann | can | |||
| kein | no | |||
| keine | |||
| keinem | |||
| keinen | |||
| keiner | |||
| keines | |||
| können | can | |||
| könnte | could | |||
| machen | do | |||
| man | one | |||
| manche | some, many a | |||
| manchem | |||
| manchen | |||
| mancher | |||
| manches | |||
| mein | my | |||
| meine | |||
| meinem | |||
| meinen | |||
| meiner | |||
| meines | |||
| mit | with | |||
| muss | must | |||
| musste | had to | |||
| nach | to(wards) | |||
| nicht | not | |||
| nichts | nothing | |||
| noch | still, yet | |||
| nun | now | |||
| nur | only | |||
| ob | whether | |||
| oder | or | |||
| ohne | without | |||
| sehr | very | |||
| sein | his | |||
| seine | |||
| seinem | |||
| seinen | |||
| seiner | |||
| seines | |||
| selbst | self | |||
| sich | herself | |||
| sie | they, she | |||
| ihnen | to them | |||
| sind | are | |||
| so | so | |||
| solche | such | |||
| solchem | |||
| solchen | |||
| solcher | |||
| solches | |||
| soll | shall | |||
| sollte | should | |||
| sondern | but | |||
| sonst | else | |||
| über | over | |||
| um | about, around | |||
| und | and | |||
| uns | us | |||
| unse | |||
| unsem | |||
| unsen | |||
| unser | |||
| unses | |||
| unter | under | |||
| viel | much | |||
| vom | von + dem | |||
| von | from | |||
| vor | before | |||
| während | while | |||
| war | was | |||
| waren | were | |||
| warst | wast | |||
| was | what | |||
| weg | away, off | |||
| weil | because | |||
| weiter | further | |||
| welche | which | |||
| welchem | |||
| welchen | |||
| welcher | |||
| welches | |||
| wenn | when | |||
| werde | will | |||
| werden | will | |||
| wie | how | |||
| wieder | again | |||
| will | want | |||
| wir | we | |||
| wird | will | |||
| wirst | willst | |||
| wo | where | |||
| wollen | want | |||
| wollte | wanted | |||
| würde | would | |||
| würden | would | |||
| zu | to | |||
| zum | zu + dem | |||
| zur | zu + der | |||
| zwar | indeed | |||
| zwischen | between | |||
+ 78
- 0
solr_config/lang/stopwords_el.txt
View File
| @@ -0,0 +1,78 @@ | |||
| # Lucene Greek Stopwords list | |||
| # Note: by default this file is used after GreekLowerCaseFilter, | |||
| # so when modifying this file use 'σ' instead of 'ς' | |||
| ο | |||
| η | |||
| το | |||
| οι | |||
| τα | |||
| του | |||
| τησ | |||
| των | |||
| τον | |||
| την | |||
| και | |||
| κι | |||
| κ | |||
| ειμαι | |||
| εισαι | |||
| ειναι | |||
| ειμαστε | |||
| ειστε | |||
| στο | |||
| στον | |||
| στη | |||
| στην | |||
| μα | |||
| αλλα | |||
| απο | |||
| για | |||
| προσ | |||
| με | |||
| σε | |||
| ωσ | |||
| παρα | |||
| αντι | |||
| κατα | |||
| μετα | |||
| θα | |||
| να | |||
| δε | |||
| δεν | |||
| μη | |||
| μην | |||
| επι | |||
| ενω | |||
| εαν | |||
| αν | |||
| τοτε | |||
| που | |||
| πωσ | |||
| ποιοσ | |||
| ποια | |||
| ποιο | |||
| ποιοι | |||
| ποιεσ | |||
| ποιων | |||
| ποιουσ | |||
| αυτοσ | |||
| αυτη | |||
| αυτο | |||
| αυτοι | |||
| αυτων | |||
| αυτουσ | |||
| αυτεσ | |||
| αυτα | |||
| εκεινοσ | |||
| εκεινη | |||
| εκεινο | |||
| εκεινοι | |||
| εκεινεσ | |||
| εκεινα | |||
| εκεινων | |||
| εκεινουσ | |||
| οπωσ | |||
| ομωσ | |||
| ισωσ | |||
| οσο | |||
| οτι | |||
+ 54
- 0
solr_config/lang/stopwords_en.txt
View File
| @@ -0,0 +1,54 @@ | |||
| # Licensed to the Apache Software Foundation (ASF) under one or more | |||
| # contributor license agreements. See the NOTICE file distributed with | |||
| # this work for additional information regarding copyright ownership. | |||
| # The ASF licenses this file to You under the Apache License, Version 2.0 | |||
| # (the "License"); you may not use this file except in compliance with | |||
| # the License. You may obtain a copy of the License at | |||
| # | |||
| # http://www.apache.org/licenses/LICENSE-2.0 | |||
| # | |||
| # Unless required by applicable law or agreed to in writing, software | |||
| # distributed under the License is distributed on an "AS IS" BASIS, | |||
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |||
| # See the License for the specific language governing permissions and | |||
| # limitations under the License. | |||
| # a couple of test stopwords to test that the words are really being | |||
| # configured from this file: | |||
| stopworda | |||
| stopwordb | |||
| # Standard english stop words taken from Lucene's StopAnalyzer | |||
| a | |||
| an | |||
| and | |||
| are | |||
| as | |||
| at | |||
| be | |||
| but | |||
| by | |||
| for | |||
| if | |||
| in | |||
| into | |||
| is | |||
| it | |||
| no | |||
| not | |||
| of | |||
| on | |||
| or | |||
| such | |||
| that | |||
| the | |||
| their | |||
| then | |||
| there | |||
| these | |||
| they | |||
| this | |||
| to | |||
| was | |||
| will | |||
| with | |||
+ 356
- 0
solr_config/lang/stopwords_es.txt
View File
| @@ -0,0 +1,356 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Spanish stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | The following is a ranked list (commonest to rarest) of stopwords | |||
| | deriving from a large sample of text. | |||
| | Extra words have been added at the end. | |||
| de | from, of | |||
| la | the, her | |||
| que | who, that | |||
| el | the | |||
| en | in | |||
| y | and | |||
| a | to | |||
| los | the, them | |||
| del | de + el | |||
| se | himself, from him etc | |||
| las | the, them | |||
| por | for, by, etc | |||
| un | a | |||
| para | for | |||
| con | with | |||
| no | no | |||
| una | a | |||
| su | his, her | |||
| al | a + el | |||
| | es from SER | |||
| lo | him | |||
| como | how | |||
| más | more | |||
| pero | pero | |||
| sus | su plural | |||
| le | to him, her | |||
| ya | already | |||
| o | or | |||
| | fue from SER | |||
| este | this | |||
| | ha from HABER | |||
| sí | himself etc | |||
| porque | because | |||
| esta | this | |||
| | son from SER | |||
| entre | between | |||
| | está from ESTAR | |||
| cuando | when | |||
| muy | very | |||
| sin | without | |||
| sobre | on | |||
| | ser from SER | |||
| | tiene from TENER | |||
| también | also | |||
| me | me | |||
| hasta | until | |||
| hay | there is/are | |||
| donde | where | |||
| | han from HABER | |||
| quien | whom, that | |||
| | están from ESTAR | |||
| | estado from ESTAR | |||
| desde | from | |||
| todo | all | |||
| nos | us | |||
| durante | during | |||
| | estados from ESTAR | |||
| todos | all | |||
| uno | a | |||
| les | to them | |||
| ni | nor | |||
| contra | against | |||
| otros | other | |||
| | fueron from SER | |||
| ese | that | |||
| eso | that | |||
| | había from HABER | |||
| ante | before | |||
| ellos | they | |||
| e | and (variant of y) | |||
| esto | this | |||
| mí | me | |||
| antes | before | |||
| algunos | some | |||
| qué | what? | |||
| unos | a | |||
| yo | I | |||
| otro | other | |||
| otras | other | |||
| otra | other | |||
| él | he | |||
| tanto | so much, many | |||
| esa | that | |||
| estos | these | |||
| mucho | much, many | |||
| quienes | who | |||
| nada | nothing | |||
| muchos | many | |||
| cual | who | |||
| | sea from SER | |||
| poco | few | |||
| ella | she | |||
| estar | to be | |||
| | haber from HABER | |||
| estas | these | |||
| | estaba from ESTAR | |||
| | estamos from ESTAR | |||
| algunas | some | |||
| algo | something | |||
| nosotros | we | |||
| | other forms | |||
| mi | me | |||
| mis | mi plural | |||
| tú | thou | |||
| te | thee | |||
| ti | thee | |||
| tu | thy | |||
| tus | tu plural | |||
| ellas | they | |||
| nosotras | we | |||
| vosotros | you | |||
| vosotras | you | |||
| os | you | |||
| mío | mine | |||
| mía | | |||
| míos | | |||
| mías | | |||
| tuyo | thine | |||
| tuya | | |||
| tuyos | | |||
| tuyas | | |||
| suyo | his, hers, theirs | |||
| suya | | |||
| suyos | | |||
| suyas | | |||
| nuestro | ours | |||
| nuestra | | |||
| nuestros | | |||
| nuestras | | |||
| vuestro | yours | |||
| vuestra | | |||
| vuestros | | |||
| vuestras | | |||
| esos | those | |||
| esas | those | |||
| | forms of estar, to be (not including the infinitive): | |||
| estoy | |||
| estás | |||
| está | |||
| estamos | |||
| estáis | |||
| están | |||
| esté | |||
| estés | |||
| estemos | |||
| estéis | |||
| estén | |||
| estaré | |||
| estarás | |||
| estará | |||
| estaremos | |||
| estaréis | |||
| estarán | |||
| estaría | |||
| estarías | |||
| estaríamos | |||
| estaríais | |||
| estarían | |||
| estaba | |||
| estabas | |||
| estábamos | |||
| estabais | |||
| estaban | |||
| estuve | |||
| estuviste | |||
| estuvo | |||
| estuvimos | |||
| estuvisteis | |||
| estuvieron | |||
| estuviera | |||
| estuvieras | |||
| estuviéramos | |||
| estuvierais | |||
| estuvieran | |||
| estuviese | |||
| estuvieses | |||
| estuviésemos | |||
| estuvieseis | |||
| estuviesen | |||
| estando | |||
| estado | |||
| estada | |||
| estados | |||
| estadas | |||
| estad | |||
| | forms of haber, to have (not including the infinitive): | |||
| he | |||
| has | |||
| ha | |||
| hemos | |||
| habéis | |||
| han | |||
| haya | |||
| hayas | |||
| hayamos | |||
| hayáis | |||
| hayan | |||
| habré | |||
| habrás | |||
| habrá | |||
| habremos | |||
| habréis | |||
| habrán | |||
| habría | |||
| habrías | |||
| habríamos | |||
| habríais | |||
| habrían | |||
| había | |||
| habías | |||
| habíamos | |||
| habíais | |||
| habían | |||
| hube | |||
| hubiste | |||
| hubo | |||
| hubimos | |||
| hubisteis | |||
| hubieron | |||
| hubiera | |||
| hubieras | |||
| hubiéramos | |||
| hubierais | |||
| hubieran | |||
| hubiese | |||
| hubieses | |||
| hubiésemos | |||
| hubieseis | |||
| hubiesen | |||
| habiendo | |||
| habido | |||
| habida | |||
| habidos | |||
| habidas | |||
| | forms of ser, to be (not including the infinitive): | |||
| soy | |||
| eres | |||
| es | |||
| somos | |||
| sois | |||
| son | |||
| sea | |||
| seas | |||
| seamos | |||
| seáis | |||
| sean | |||
| seré | |||
| serás | |||
| será | |||
| seremos | |||
| seréis | |||
| serán | |||
| sería | |||
| serías | |||
| seríamos | |||
| seríais | |||
| serían | |||
| era | |||
| eras | |||
| éramos | |||
| erais | |||
| eran | |||
| fui | |||
| fuiste | |||
| fue | |||
| fuimos | |||
| fuisteis | |||
| fueron | |||
| fuera | |||
| fueras | |||
| fuéramos | |||
| fuerais | |||
| fueran | |||
| fuese | |||
| fueses | |||
| fuésemos | |||
| fueseis | |||
| fuesen | |||
| siendo | |||
| sido | |||
| | sed also means 'thirst' | |||
| | forms of tener, to have (not including the infinitive): | |||
| tengo | |||
| tienes | |||
| tiene | |||
| tenemos | |||
| tenéis | |||
| tienen | |||
| tenga | |||
| tengas | |||
| tengamos | |||
| tengáis | |||
| tengan | |||
| tendré | |||
| tendrás | |||
| tendrá | |||
| tendremos | |||
| tendréis | |||
| tendrán | |||
| tendría | |||
| tendrías | |||
| tendríamos | |||
| tendríais | |||
| tendrían | |||
| tenía | |||
| tenías | |||
| teníamos | |||
| teníais | |||
| tenían | |||
| tuve | |||
| tuviste | |||
| tuvo | |||
| tuvimos | |||
| tuvisteis | |||
| tuvieron | |||
| tuviera | |||
| tuvieras | |||
| tuviéramos | |||
| tuvierais | |||
| tuvieran | |||
| tuviese | |||
| tuvieses | |||
| tuviésemos | |||
| tuvieseis | |||
| tuviesen | |||
| teniendo | |||
| tenido | |||
| tenida | |||
| tenidos | |||
| tenidas | |||
| tened | |||
+ 99
- 0
solr_config/lang/stopwords_eu.txt
View File
| @@ -0,0 +1,99 @@ | |||
| # example set of basque stopwords | |||
| al | |||
| anitz | |||
| arabera | |||
| asko | |||
| baina | |||
| bat | |||
| batean | |||
| batek | |||
| bati | |||
| batzuei | |||
| batzuek | |||
| batzuetan | |||
| batzuk | |||
| bera | |||
| beraiek | |||
| berau | |||
| berauek | |||
| bere | |||
| berori | |||
| beroriek | |||
| beste | |||
| bezala | |||
| da | |||
| dago | |||
| dira | |||
| ditu | |||
| du | |||
| dute | |||
| edo | |||
| egin | |||
| ere | |||
| eta | |||
| eurak | |||
| ez | |||
| gainera | |||
| gu | |||
| gutxi | |||
| guzti | |||
| haiei | |||
| haiek | |||
| haietan | |||
| hainbeste | |||
| hala | |||
| han | |||
| handik | |||
| hango | |||
| hara | |||
| hari | |||
| hark | |||
| hartan | |||
| hau | |||
| hauei | |||
| hauek | |||
| hauetan | |||
| hemen | |||
| hemendik | |||
| hemengo | |||
| hi | |||
| hona | |||
| honek | |||
| honela | |||
| honetan | |||
| honi | |||
| hor | |||
| hori | |||
| horiei | |||
| horiek | |||
| horietan | |||
| horko | |||
| horra | |||
| horrek | |||
| horrela | |||
| horretan | |||
| horri | |||
| hortik | |||
| hura | |||
| izan | |||
| ni | |||
| noiz | |||
| nola | |||
| non | |||
| nondik | |||
| nongo | |||
| nor | |||
| nora | |||
| ze | |||
| zein | |||
| zen | |||
| zenbait | |||
| zenbat | |||
| zer | |||
| zergatik | |||
| ziren | |||
| zituen | |||
| zu | |||
| zuek | |||
| zuen | |||
| zuten | |||
+ 313
- 0
solr_config/lang/stopwords_fa.txt
View File
| @@ -0,0 +1,313 @@ | |||
| # This file was created by Jacques Savoy and is distributed under the BSD license. | |||
| # See http://members.unine.ch/jacques.savoy/clef/index.html. | |||
| # Also see http://www.opensource.org/licenses/bsd-license.html | |||
| # Note: by default this file is used after normalization, so when adding entries | |||
| # to this file, use the arabic 'ي' instead of 'ی' | |||
| انان | |||
| نداشته | |||
| سراسر | |||
| خياه | |||
| ايشان | |||
| وي | |||
| تاكنون | |||
| بيشتري | |||
| دوم | |||
| پس | |||
| ناشي | |||
| وگو | |||
| يا | |||
| داشتند | |||
| سپس | |||
| هنگام | |||
| هرگز | |||
| پنج | |||
| نشان | |||
| امسال | |||
| ديگر | |||
| گروهي | |||
| شدند | |||
| چطور | |||
| ده | |||
| و | |||
| دو | |||
| نخستين | |||
| ولي | |||
| چرا | |||
| چه | |||
| وسط | |||
| ه | |||
| كدام | |||
| قابل | |||
| يك | |||
| رفت | |||
| هفت | |||
| همچنين | |||
| در | |||
| هزار | |||
| بله | |||
| بلي | |||
| شايد | |||
| اما | |||
| شناسي | |||
| گرفته | |||
| دهد | |||
| داشته | |||
| دانست | |||
| داشتن | |||
| خواهيم | |||
| ميليارد | |||
| وقتيكه | |||
| امد | |||
| خواهد | |||
| جز | |||
| اورده | |||
| شده | |||
| بلكه | |||
| خدمات | |||
| شدن | |||
| برخي | |||
| نبود | |||
| بسياري | |||
| جلوگيري | |||
| حق | |||
| كردند | |||
| نوعي | |||
| بعري | |||
| نكرده | |||
| نظير | |||
| نبايد | |||
| بوده | |||
| بودن | |||
| داد | |||
| اورد | |||
| هست | |||
| جايي | |||
| شود | |||
| دنبال | |||
| داده | |||
| بايد | |||
| سابق | |||
| هيچ | |||
| همان | |||
| انجا | |||
| كمتر | |||
| كجاست | |||
| گردد | |||
| كسي | |||
| تر | |||
| مردم | |||
| تان | |||
| دادن | |||
| بودند | |||
| سري | |||
| جدا | |||
| ندارند | |||
| مگر | |||
| يكديگر | |||
| دارد | |||
| دهند | |||
| بنابراين | |||
| هنگامي | |||
| سمت | |||
| جا | |||
| انچه | |||
| خود | |||
| دادند | |||
| زياد | |||
| دارند | |||
| اثر | |||
| بدون | |||
| بهترين | |||
| بيشتر | |||
| البته | |||
| به | |||
| براساس | |||
| بيرون | |||
| كرد | |||
| بعضي | |||
| گرفت | |||
| توي | |||
| اي | |||
| ميليون | |||
| او | |||
| جريان | |||
| تول | |||
| بر | |||
| مانند | |||
| برابر | |||
| باشيم | |||
| مدتي | |||
| گويند | |||
| اكنون | |||
| تا | |||
| تنها | |||
| جديد | |||
| چند | |||
| بي | |||
| نشده | |||
| كردن | |||
| كردم | |||
| گويد | |||
| كرده | |||
| كنيم | |||
| نمي | |||
| نزد | |||
| روي | |||
| قصد | |||
| فقط | |||
| بالاي | |||
| ديگران | |||
| اين | |||
| ديروز | |||
| توسط | |||
| سوم | |||
| ايم | |||
| دانند | |||
| سوي | |||
| استفاده | |||
| شما | |||
| كنار | |||
| داريم | |||
| ساخته | |||
| طور | |||
| امده | |||
| رفته | |||
| نخست | |||
| بيست | |||
| نزديك | |||
| طي | |||
| كنيد | |||
| از | |||
| انها | |||
| تمامي | |||
| داشت | |||
| يكي | |||
| طريق | |||
| اش | |||
| چيست | |||
| روب | |||
| نمايد | |||
| گفت | |||
| چندين | |||
| چيزي | |||
| تواند | |||
| ام | |||
| ايا | |||
| با | |||
| ان | |||
| ايد | |||
| ترين | |||
| اينكه | |||
| ديگري | |||
| راه | |||
| هايي | |||
| بروز | |||
| همچنان | |||
| پاعين | |||
| كس | |||
| حدود | |||
| مختلف | |||
| مقابل | |||
| چيز | |||
| گيرد | |||
| ندارد | |||
| ضد | |||
| همچون | |||
| سازي | |||
| شان | |||
| مورد | |||
| باره | |||
| مرسي | |||
| خويش | |||
| برخوردار | |||
| چون | |||
| خارج | |||
| شش | |||
| هنوز | |||
| تحت | |||
| ضمن | |||
| هستيم | |||
| گفته | |||
| فكر | |||
| بسيار | |||
| پيش | |||
| براي | |||
| روزهاي | |||
| انكه | |||
| نخواهد | |||
| بالا | |||
| كل | |||
| وقتي | |||
| كي | |||
| چنين | |||
| كه | |||
| گيري | |||
| نيست | |||
| است | |||
| كجا | |||
| كند | |||
| نيز | |||
| يابد | |||
| بندي | |||
| حتي | |||
| توانند | |||
| عقب | |||
| خواست | |||
| كنند | |||
| بين | |||
| تمام | |||
| همه | |||
| ما | |||
| باشند | |||
| مثل | |||
| شد | |||
| اري | |||
| باشد | |||
| اره | |||
| طبق | |||
| بعد | |||
| اگر | |||
| صورت | |||
| غير | |||
| جاي | |||
| بيش | |||
| ريزي | |||
| اند | |||
| زيرا | |||
| چگونه | |||
| بار | |||
| لطفا | |||
| مي | |||
| درباره | |||
| من | |||
| ديده | |||
| همين | |||
| گذاري | |||
| برداري | |||
| علت | |||
| گذاشته | |||
| هم | |||
| فوق | |||
| نه | |||
| ها | |||
| شوند | |||
| اباد | |||
| همواره | |||
| هر | |||
| اول | |||
| خواهند | |||
| چهار | |||
| نام | |||
| امروز | |||
| مان | |||
| هاي | |||
| قبل | |||
| كنم | |||
| سعي | |||
| تازه | |||
| را | |||
| هستند | |||
| زير | |||
| جلوي | |||
| عنوان | |||
| بود | |||
+ 97
- 0
solr_config/lang/stopwords_fi.txt
View File
| @@ -0,0 +1,97 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | forms of BE | |||
| olla | |||
| olen | |||
| olet | |||
| on | |||
| olemme | |||
| olette | |||
| ovat | |||
| ole | negative form | |||
| oli | |||
| olisi | |||
| olisit | |||
| olisin | |||
| olisimme | |||
| olisitte | |||
| olisivat | |||
| olit | |||
| olin | |||
| olimme | |||
| olitte | |||
| olivat | |||
| ollut | |||
| olleet | |||
| en | negation | |||
| et | |||
| ei | |||
| emme | |||
| ette | |||
| eivät | |||
| |Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans | |||
| minä minun minut minua minussa minusta minuun minulla minulta minulle | I | |||
| sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you | |||
| hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she | |||
| me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we | |||
| te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you | |||
| he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they | |||
| tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this | |||
| tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that | |||
| se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it | |||
| nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these | |||
| nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those | |||
| ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they | |||
| kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who | |||
| ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl) | |||
| mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what | |||
| mitkä | (pl) | |||
| joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which | |||
| jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl) | |||
| | conjunctions | |||
| että | that | |||
| ja | and | |||
| jos | if | |||
| koska | because | |||
| kuin | than | |||
| mutta | but | |||
| niin | so | |||
| sekä | and | |||
| sillä | for | |||
| tai | or | |||
| vaan | but | |||
| vai | or | |||
| vaikka | although | |||
| | prepositions | |||
| kanssa | with | |||
| mukaan | according to | |||
| noin | about | |||
| poikki | across | |||
| yli | over, across | |||
| | other | |||
| kun | when | |||
| niin | so | |||
| nyt | now | |||
| itse | self | |||
+ 186
- 0
solr_config/lang/stopwords_fr.txt
View File
| @@ -0,0 +1,186 @@ | |||
| | 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 | |||
+ 110
- 0
solr_config/lang/stopwords_ga.txt
View File
| @@ -0,0 +1,110 @@ | |||
| a | |||
| ach | |||
| ag | |||
| agus | |||
| an | |||
| aon | |||
| ar | |||
| arna | |||
| as | |||
| b' | |||
| ba | |||
| beirt | |||
| bhúr | |||
| caoga | |||
| ceathair | |||
| ceathrar | |||
| chomh | |||
| chtó | |||
| chuig | |||
| chun | |||
| cois | |||
| céad | |||
| cúig | |||
| cúigear | |||
| d' | |||
| daichead | |||
| dar | |||
| de | |||
| deich | |||
| deichniúr | |||
| den | |||
| dhá | |||
| do | |||
| don | |||
| dtí | |||
| dá | |||
| dár | |||
| dó | |||
| faoi | |||
| faoin | |||
| faoina | |||
| faoinár | |||
| fara | |||
| fiche | |||
| gach | |||
| gan | |||
| go | |||
| gur | |||
| haon | |||
| hocht | |||
| i | |||
| iad | |||
| idir | |||
| in | |||
| ina | |||
| ins | |||
| inár | |||
| is | |||
| le | |||
| leis | |||
| lena | |||
| lenár | |||
| m' | |||
| mar | |||
| mo | |||
| mé | |||
| na | |||
| nach | |||
| naoi | |||
| naonúr | |||
| ná | |||
| ní | |||
| níor | |||
| nó | |||
| nócha | |||
| ocht | |||
| ochtar | |||
| os | |||
| roimh | |||
| sa | |||
| seacht | |||
| seachtar | |||
| seachtó | |||
| seasca | |||
| seisear | |||
| siad | |||
| sibh | |||
| sinn | |||
| sna | |||
| sé | |||
| sí | |||
| tar | |||
| thar | |||
| thú | |||
| triúr | |||
| trí | |||
| trína | |||
| trínár | |||
| tríocha | |||
| tú | |||
| um | |||
| ár | |||
| é | |||
| éis | |||
| í | |||
| ó | |||
| ón | |||
| óna | |||
| ónár | |||
+ 161
- 0
solr_config/lang/stopwords_gl.txt
View File
| @@ -0,0 +1,161 @@ | |||
| # galican stopwords | |||
| a | |||
| aínda | |||
| alí | |||
| aquel | |||
| aquela | |||
| aquelas | |||
| aqueles | |||
| aquilo | |||
| aquí | |||
| ao | |||
| aos | |||
| as | |||
| así | |||
| á | |||
| ben | |||
| cando | |||
| che | |||
| co | |||
| coa | |||
| comigo | |||
| con | |||
| connosco | |||
| contigo | |||
| convosco | |||
| coas | |||
| cos | |||
| cun | |||
| cuns | |||
| cunha | |||
| cunhas | |||
| da | |||
| dalgunha | |||
| dalgunhas | |||
| dalgún | |||
| dalgúns | |||
| das | |||
| de | |||
| del | |||
| dela | |||
| delas | |||
| deles | |||
| desde | |||
| deste | |||
| do | |||
| dos | |||
| dun | |||
| duns | |||
| dunha | |||
| dunhas | |||
| e | |||
| el | |||
| ela | |||
| elas | |||
| eles | |||
| en | |||
| era | |||
| eran | |||
| esa | |||
| esas | |||
| ese | |||
| eses | |||
| esta | |||
| estar | |||
| estaba | |||
| está | |||
| están | |||
| este | |||
| estes | |||
| estiven | |||
| estou | |||
| eu | |||
| é | |||
| facer | |||
| foi | |||
| foron | |||
| fun | |||
| había | |||
| hai | |||
| iso | |||
| isto | |||
| la | |||
| las | |||
| lle | |||
| lles | |||
| lo | |||
| los | |||
| mais | |||
| me | |||
| meu | |||
| meus | |||
| min | |||
| miña | |||
| miñas | |||
| moi | |||
| na | |||
| nas | |||
| neste | |||
| nin | |||
| no | |||
| non | |||
| nos | |||
| nosa | |||
| nosas | |||
| noso | |||
| nosos | |||
| nós | |||
| nun | |||
| nunha | |||
| nuns | |||
| nunhas | |||
| o | |||
| os | |||
| ou | |||
| ó | |||
| ós | |||
| para | |||
| pero | |||
| pode | |||
| pois | |||
| pola | |||
| polas | |||
| polo | |||
| polos | |||
| por | |||
| que | |||
| se | |||
| senón | |||
| ser | |||
| seu | |||
| seus | |||
| sexa | |||
| sido | |||
| sobre | |||
| súa | |||
| súas | |||
| tamén | |||
| tan | |||
| te | |||
| ten | |||
| teñen | |||
| teño | |||
| ter | |||
| teu | |||
| teus | |||
| ti | |||
| tido | |||
| tiña | |||
| tiven | |||
| túa | |||
| túas | |||
| un | |||
| unha | |||
| unhas | |||
| uns | |||
| vos | |||
| vosa | |||
| vosas | |||
| voso | |||
| vosos | |||
| vós | |||
+ 235
- 0
solr_config/lang/stopwords_hi.txt
View File
| @@ -0,0 +1,235 @@ | |||
| # Also see http://www.opensource.org/licenses/bsd-license.html | |||
| # See http://members.unine.ch/jacques.savoy/clef/index.html. | |||
| # This file was created by Jacques Savoy and is distributed under the BSD license. | |||
| # Note: by default this file also contains forms normalized by HindiNormalizer | |||
| # for spelling variation (see section below), such that it can be used whether or | |||
| # not you enable that feature. When adding additional entries to this list, | |||
| # please add the normalized form as well. | |||
| अंदर | |||
| अत | |||
| अपना | |||
| अपनी | |||
| अपने | |||
| अभी | |||
| आदि | |||
| आप | |||
| इत्यादि | |||
| इन | |||
| इनका | |||
| इन्हीं | |||
| इन्हें | |||
| इन्हों | |||
| इस | |||
| इसका | |||
| इसकी | |||
| इसके | |||
| इसमें | |||
| इसी | |||
| इसे | |||
| उन | |||
| उनका | |||
| उनकी | |||
| उनके | |||
| उनको | |||
| उन्हीं | |||
| उन्हें | |||
| उन्हों | |||
| उस | |||
| उसके | |||
| उसी | |||
| उसे | |||
| एक | |||
| एवं | |||
| एस | |||
| ऐसे | |||
| और | |||
| कई | |||
| कर | |||
| करता | |||
| करते | |||
| करना | |||
| करने | |||
| करें | |||
| कहते | |||
| कहा | |||
| का | |||
| काफ़ी | |||
| कि | |||
| कितना | |||
| किन्हें | |||
| किन्हों | |||
| किया | |||
| किर | |||
| किस | |||
| किसी | |||
| किसे | |||
| की | |||
| कुछ | |||
| कुल | |||
| के | |||
| को | |||
| कोई | |||
| कौन | |||
| कौनसा | |||
| गया | |||
| घर | |||
| जब | |||
| जहाँ | |||
| जा | |||
| जितना | |||
| जिन | |||
| जिन्हें | |||
| जिन्हों | |||
| जिस | |||
| जिसे | |||
| जीधर | |||
| जैसा | |||
| जैसे | |||
| जो | |||
| तक | |||
| तब | |||
| तरह | |||
| तिन | |||
| तिन्हें | |||
| तिन्हों | |||
| तिस | |||
| तिसे | |||
| तो | |||
| था | |||
| थी | |||
| थे | |||
| दबारा | |||
| दिया | |||
| दुसरा | |||
| दूसरे | |||
| दो | |||
| द्वारा | |||
| न | |||
| नहीं | |||
| ना | |||
| निहायत | |||
| नीचे | |||
| ने | |||
| पर | |||
| पर | |||
| पहले | |||
| पूरा | |||
| पे | |||
| फिर | |||
| बनी | |||
| बही | |||
| बहुत | |||
| बाद | |||
| बाला | |||
| बिलकुल | |||
| भी | |||
| भीतर | |||
| मगर | |||
| मानो | |||
| मे | |||
| में | |||
| यदि | |||
| यह | |||
| यहाँ | |||
| यही | |||
| या | |||
| यिह | |||
| ये | |||
| रखें | |||
| रहा | |||
| रहे | |||
| ऱ्वासा | |||
| लिए | |||
| लिये | |||
| लेकिन | |||
| व | |||
| वर्ग | |||
| वह | |||
| वह | |||
| वहाँ | |||
| वहीं | |||
| वाले | |||
| वुह | |||
| वे | |||
| वग़ैरह | |||
| संग | |||
| सकता | |||
| सकते | |||
| सबसे | |||
| सभी | |||
| साथ | |||
| साबुत | |||
| साभ | |||
| सारा | |||
| से | |||
| सो | |||
| ही | |||
| हुआ | |||
| हुई | |||
| हुए | |||
| है | |||
| हैं | |||
| हो | |||
| होता | |||
| होती | |||
| होते | |||
| होना | |||
| होने | |||
| # additional normalized forms of the above | |||
| अपनि | |||
| जेसे | |||
| होति | |||
| सभि | |||
| तिंहों | |||
| इंहों | |||
| दवारा | |||
| इसि | |||
| किंहें | |||
| थि | |||
| उंहों | |||
| ओर | |||
| जिंहें | |||
| वहिं | |||
| अभि | |||
| बनि | |||
| हि | |||
| उंहिं | |||
| उंहें | |||
| हें | |||
| वगेरह | |||
| एसे | |||
| रवासा | |||
| कोन | |||
| निचे | |||
| काफि | |||
| उसि | |||
| पुरा | |||
| भितर | |||
| हे | |||
| बहि | |||
| वहां | |||
| कोइ | |||
| यहां | |||
| जिंहों | |||
| तिंहें | |||
| किसि | |||
| कइ | |||
| यहि | |||
| इंहिं | |||
| जिधर | |||
| इंहें | |||
| अदि | |||
| इतयादि | |||
| हुइ | |||
| कोनसा | |||
| इसकि | |||
| दुसरे | |||
| जहां | |||
| अप | |||
| किंहों | |||
| उनकि | |||
| भि | |||
| वरग | |||
| हुअ | |||
| जेसा | |||
| नहिं | |||
+ 211
- 0
solr_config/lang/stopwords_hu.txt
View File
| @@ -0,0 +1,211 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | Hungarian stop word list | |||
| | prepared by Anna Tordai | |||
| a | |||
| ahogy | |||
| ahol | |||
| aki | |||
| akik | |||
| akkor | |||
| alatt | |||
| által | |||
| általában | |||
| amely | |||
| amelyek | |||
| amelyekben | |||
| amelyeket | |||
| amelyet | |||
| amelynek | |||
| ami | |||
| amit | |||
| amolyan | |||
| amíg | |||
| amikor | |||
| át | |||
| abban | |||
| ahhoz | |||
| annak | |||
| arra | |||
| arról | |||
| az | |||
| azok | |||
| azon | |||
| azt | |||
| azzal | |||
| azért | |||
| aztán | |||
| azután | |||
| azonban | |||
| bár | |||
| be | |||
| belül | |||
| benne | |||
| cikk | |||
| cikkek | |||
| cikkeket | |||
| csak | |||
| de | |||
| e | |||
| eddig | |||
| egész | |||
| egy | |||
| egyes | |||
| egyetlen | |||
| egyéb | |||
| egyik | |||
| egyre | |||
| ekkor | |||
| el | |||
| elég | |||
| ellen | |||
| elő | |||
| először | |||
| előtt | |||
| első | |||
| én | |||
| éppen | |||
| ebben | |||
| ehhez | |||
| emilyen | |||
| ennek | |||
| erre | |||
| ez | |||
| ezt | |||
| ezek | |||
| ezen | |||
| ezzel | |||
| ezért | |||
| és | |||
| fel | |||
| felé | |||
| hanem | |||
| hiszen | |||
| hogy | |||
| hogyan | |||
| igen | |||
| így | |||
| illetve | |||
| ill. | |||
| ill | |||
| ilyen | |||
| ilyenkor | |||
| ison | |||
| ismét | |||
| itt | |||
| jó | |||
| jól | |||
| jobban | |||
| kell | |||
| kellett | |||
| keresztül | |||
| keressünk | |||
| ki | |||
| kívül | |||
| között | |||
| közül | |||
| legalább | |||
| lehet | |||
| lehetett | |||
| legyen | |||
| lenne | |||
| lenni | |||
| lesz | |||
| lett | |||
| maga | |||
| magát | |||
| majd | |||
| majd | |||
| már | |||
| más | |||
| másik | |||
| meg | |||
| még | |||
| mellett | |||
| mert | |||
| mely | |||
| melyek | |||
| mi | |||
| mit | |||
| míg | |||
| miért | |||
| milyen | |||
| mikor | |||
| minden | |||
| mindent | |||
| mindenki | |||
| mindig | |||
| mint | |||
| mintha | |||
| mivel | |||
| most | |||
| nagy | |||
| nagyobb | |||
| nagyon | |||
| ne | |||
| néha | |||
| nekem | |||
| neki | |||
| nem | |||
| néhány | |||
| nélkül | |||
| nincs | |||
| olyan | |||
| ott | |||
| össze | |||
| ő | |||
| ők | |||
| őket | |||
| pedig | |||
| persze | |||
| rá | |||
| s | |||
| saját | |||
| sem | |||
| semmi | |||
| sok | |||
| sokat | |||
| sokkal | |||
| számára | |||
| szemben | |||
| szerint | |||
| szinte | |||
| talán | |||
| tehát | |||
| teljes | |||
| tovább | |||
| továbbá | |||
| több | |||
| úgy | |||
| ugyanis | |||
| új | |||
| újabb | |||
| újra | |||
| után | |||
| utána | |||
| utolsó | |||
| vagy | |||
| vagyis | |||
| valaki | |||
| valami | |||
| valamint | |||
| való | |||
| vagyok | |||
| van | |||
| vannak | |||
| volt | |||
| voltam | |||
| voltak | |||
| voltunk | |||
| vissza | |||
| vele | |||
| viszont | |||
| volna | |||
+ 46
- 0
solr_config/lang/stopwords_hy.txt
View File
| @@ -0,0 +1,46 @@ | |||
| # example set of Armenian stopwords. | |||
| այդ | |||
| այլ | |||
| այն | |||
| այս | |||
| դու | |||
| դուք | |||
| եմ | |||
| են | |||
| ենք | |||
| ես | |||
| եք | |||
| է | |||
| էի | |||
| էին | |||
| էինք | |||
| էիր | |||
| էիք | |||
| էր | |||
| ըստ | |||
| թ | |||
| ի | |||
| ին | |||
| իսկ | |||
| իր | |||
| կամ | |||
| համար | |||
| հետ | |||
| հետո | |||
| մենք | |||
| մեջ | |||
| մի | |||
| ն | |||
| նա | |||
| նաև | |||
| նրա | |||
| նրանք | |||
| որ | |||
| որը | |||
| որոնք | |||
| որպես | |||
| ու | |||
| ում | |||
| պիտի | |||
| վրա | |||
| և | |||
+ 359
- 0
solr_config/lang/stopwords_id.txt
View File
| @@ -0,0 +1,359 @@ | |||
| # from appendix D of: A Study of Stemming Effects on Information | |||
| # Retrieval in Bahasa Indonesia | |||
| ada | |||
| adanya | |||
| adalah | |||
| adapun | |||
| agak | |||
| agaknya | |||
| agar | |||
| akan | |||
| akankah | |||
| akhirnya | |||
| aku | |||
| akulah | |||
| amat | |||
| amatlah | |||
| anda | |||
| andalah | |||
| antar | |||
| diantaranya | |||
| antara | |||
| antaranya | |||
| diantara | |||
| apa | |||
| apaan | |||
| mengapa | |||
| apabila | |||
| apakah | |||
| apalagi | |||
| apatah | |||
| atau | |||
| ataukah | |||
| ataupun | |||
| bagai | |||
| bagaikan | |||
| sebagai | |||
| sebagainya | |||
| bagaimana | |||
| bagaimanapun | |||
| sebagaimana | |||
| bagaimanakah | |||
| bagi | |||
| bahkan | |||
| bahwa | |||
| bahwasanya | |||
| sebaliknya | |||
| banyak | |||
| sebanyak | |||
| beberapa | |||
| seberapa | |||
| begini | |||
| beginian | |||
| beginikah | |||
| beginilah | |||
| sebegini | |||
| begitu | |||
| begitukah | |||
| begitulah | |||
| begitupun | |||
| sebegitu | |||
| belum | |||
| belumlah | |||
| sebelum | |||
| sebelumnya | |||
| sebenarnya | |||
| berapa | |||
| berapakah | |||
| berapalah | |||
| berapapun | |||
| betulkah | |||
| sebetulnya | |||
| biasa | |||
| biasanya | |||
| bila | |||
| bilakah | |||
| bisa | |||
| bisakah | |||
| sebisanya | |||
| boleh | |||
| bolehkah | |||
| bolehlah | |||
| buat | |||
| bukan | |||
| bukankah | |||
| bukanlah | |||
| bukannya | |||
| cuma | |||
| percuma | |||
| dahulu | |||
| dalam | |||
| dan | |||
| dapat | |||
| dari | |||
| daripada | |||
| dekat | |||
| demi | |||
| demikian | |||
| demikianlah | |||
| sedemikian | |||
| dengan | |||
| depan | |||
| di | |||
| dia | |||
| dialah | |||
| dini | |||
| diri | |||
| dirinya | |||
| terdiri | |||
| dong | |||
| dulu | |||
| enggak | |||
| enggaknya | |||
| entah | |||
| entahlah | |||
| terhadap | |||
| terhadapnya | |||
| hal | |||
| hampir | |||
| hanya | |||
| hanyalah | |||
| harus | |||
| haruslah | |||
| harusnya | |||
| seharusnya | |||
| hendak | |||
| hendaklah | |||
| hendaknya | |||
| hingga | |||
| sehingga | |||
| ia | |||
| ialah | |||
| ibarat | |||
| ingin | |||
| inginkah | |||
| inginkan | |||
| ini | |||
| inikah | |||
| inilah | |||
| itu | |||
| itukah | |||
| itulah | |||
| jangan | |||
| jangankan | |||
| janganlah | |||
| jika | |||
| jikalau | |||
| juga | |||
| justru | |||
| kala | |||
| kalau | |||
| kalaulah | |||
| kalaupun | |||
| kalian | |||
| kami | |||
| kamilah | |||
| kamu | |||
| kamulah | |||
| kan | |||
| kapan | |||
| kapankah | |||
| kapanpun | |||
| dikarenakan | |||
| karena | |||
| karenanya | |||
| ke | |||
| kecil | |||
| kemudian | |||
| kenapa | |||
| kepada | |||
| kepadanya | |||
| ketika | |||
| seketika | |||
| khususnya | |||
| kini | |||
| kinilah | |||
| kiranya | |||
| sekiranya | |||
| kita | |||
| kitalah | |||
| kok | |||
| lagi | |||
| lagian | |||
| selagi | |||
| lah | |||
| lain | |||
| lainnya | |||
| melainkan | |||
| selaku | |||
| lalu | |||
| melalui | |||
| terlalu | |||
| lama | |||
| lamanya | |||
| selama | |||
| selama | |||
| selamanya | |||
| lebih | |||
| terlebih | |||
| bermacam | |||
| macam | |||
| semacam | |||
| maka | |||
| makanya | |||
| makin | |||
| malah | |||
| malahan | |||
| mampu | |||
| mampukah | |||
| mana | |||
| manakala | |||
| manalagi | |||
| masih | |||
| masihkah | |||
| semasih | |||
| masing | |||
| mau | |||
| maupun | |||
| semaunya | |||
| memang | |||
| mereka | |||
| merekalah | |||
| meski | |||
| meskipun | |||
| semula | |||
| mungkin | |||
| mungkinkah | |||
| nah | |||
| namun | |||
| nanti | |||
| nantinya | |||
| nyaris | |||
| oleh | |||
| olehnya | |||
| seorang | |||
| seseorang | |||
| pada | |||
| padanya | |||
| padahal | |||
| paling | |||
| sepanjang | |||
| pantas | |||
| sepantasnya | |||
| sepantasnyalah | |||
| para | |||
| pasti | |||
| pastilah | |||
| per | |||
| pernah | |||
| pula | |||
| pun | |||
| merupakan | |||
| rupanya | |||
| serupa | |||
| saat | |||
| saatnya | |||
| sesaat | |||
| saja | |||
| sajalah | |||
| saling | |||
| bersama | |||
| sama | |||
| sesama | |||
| sambil | |||
| sampai | |||
| sana | |||
| sangat | |||
| sangatlah | |||
| saya | |||
| sayalah | |||
| se | |||
| sebab | |||
| sebabnya | |||
| sebuah | |||
| tersebut | |||
| tersebutlah | |||
| sedang | |||
| sedangkan | |||
| sedikit | |||
| sedikitnya | |||
| segala | |||
| segalanya | |||
| segera | |||
| sesegera | |||
| sejak | |||
| sejenak | |||
| sekali | |||
| sekalian | |||
| sekalipun | |||
| sesekali | |||
| sekaligus | |||
| sekarang | |||
| sekarang | |||
| sekitar | |||
| sekitarnya | |||
| sela | |||
| selain | |||
| selalu | |||
| seluruh | |||
| seluruhnya | |||
| semakin | |||
| sementara | |||
| sempat | |||
| semua | |||
| semuanya | |||
| sendiri | |||
| sendirinya | |||
| seolah | |||
| seperti | |||
| sepertinya | |||
| sering | |||
| seringnya | |||
| serta | |||
| siapa | |||
| siapakah | |||
| siapapun | |||
| disini | |||
| disinilah | |||
| sini | |||
| sinilah | |||
| sesuatu | |||
| sesuatunya | |||
| suatu | |||
| sesudah | |||
| sesudahnya | |||
| sudah | |||
| sudahkah | |||
| sudahlah | |||
| supaya | |||
| tadi | |||
| tadinya | |||
| tak | |||
| tanpa | |||
| setelah | |||
| telah | |||
| tentang | |||
| tentu | |||
| tentulah | |||
| tentunya | |||
| tertentu | |||
| seterusnya | |||
| tapi | |||
| tetapi | |||
| setiap | |||
| tiap | |||
| setidaknya | |||
| tidak | |||
| tidakkah | |||
| tidaklah | |||
| toh | |||
| waduh | |||
| wah | |||
| wahai | |||
| sewaktu | |||
| walau | |||
| walaupun | |||
| wong | |||
| yaitu | |||
| yakni | |||
| yang | |||
+ 303
- 0
solr_config/lang/stopwords_it.txt
View File
| @@ -0,0 +1,303 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | An Italian stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| ad | a (to) before vowel | |||
| al | a + il | |||
| allo | a + lo | |||
| ai | a + i | |||
| agli | a + gli | |||
| all | a + l' | |||
| agl | a + gl' | |||
| alla | a + la | |||
| alle | a + le | |||
| con | with | |||
| col | con + il | |||
| coi | con + i (forms collo, cogli etc are now very rare) | |||
| da | from | |||
| dal | da + il | |||
| dallo | da + lo | |||
| dai | da + i | |||
| dagli | da + gli | |||
| dall | da + l' | |||
| dagl | da + gll' | |||
| dalla | da + la | |||
| dalle | da + le | |||
| di | of | |||
| del | di + il | |||
| dello | di + lo | |||
| dei | di + i | |||
| degli | di + gli | |||
| dell | di + l' | |||
| degl | di + gl' | |||
| della | di + la | |||
| delle | di + le | |||
| in | in | |||
| nel | in + el | |||
| nello | in + lo | |||
| nei | in + i | |||
| negli | in + gli | |||
| nell | in + l' | |||
| negl | in + gl' | |||
| nella | in + la | |||
| nelle | in + le | |||
| su | on | |||
| sul | su + il | |||
| sullo | su + lo | |||
| sui | su + i | |||
| sugli | su + gli | |||
| sull | su + l' | |||
| sugl | su + gl' | |||
| sulla | su + la | |||
| sulle | su + le | |||
| per | through, by | |||
| tra | among | |||
| contro | against | |||
| io | I | |||
| tu | thou | |||
| lui | he | |||
| lei | she | |||
| noi | we | |||
| voi | you | |||
| loro | they | |||
| mio | my | |||
| mia | | |||
| miei | | |||
| mie | | |||
| tuo | | |||
| tua | | |||
| tuoi | thy | |||
| tue | | |||
| suo | | |||
| sua | | |||
| suoi | his, her | |||
| sue | | |||
| nostro | our | |||
| nostra | | |||
| nostri | | |||
| nostre | | |||
| vostro | your | |||
| vostra | | |||
| vostri | | |||
| vostre | | |||
| mi | me | |||
| ti | thee | |||
| ci | us, there | |||
| vi | you, there | |||
| lo | him, the | |||
| la | her, the | |||
| li | them | |||
| le | them, the | |||
| gli | to him, the | |||
| ne | from there etc | |||
| il | the | |||
| un | a | |||
| uno | a | |||
| una | a | |||
| ma | but | |||
| ed | and | |||
| se | if | |||
| perché | why, because | |||
| anche | also | |||
| come | how | |||
| dov | where (as dov') | |||
| dove | where | |||
| che | who, that | |||
| chi | who | |||
| cui | whom | |||
| non | not | |||
| più | more | |||
| quale | who, that | |||
| quanto | how much | |||
| quanti | | |||
| quanta | | |||
| quante | | |||
| quello | that | |||
| quelli | | |||
| quella | | |||
| quelle | | |||
| questo | this | |||
| questi | | |||
| questa | | |||
| queste | | |||
| si | yes | |||
| tutto | all | |||
| tutti | all | |||
| | single letter forms: | |||
| a | at | |||
| c | as c' for ce or ci | |||
| e | and | |||
| i | the | |||
| l | as l' | |||
| o | or | |||
| | forms of avere, to have (not including the infinitive): | |||
| ho | |||
| hai | |||
| ha | |||
| abbiamo | |||
| avete | |||
| hanno | |||
| abbia | |||
| abbiate | |||
| abbiano | |||
| avrò | |||
| avrai | |||
| avrà | |||
| avremo | |||
| avrete | |||
| avranno | |||
| avrei | |||
| avresti | |||
| avrebbe | |||
| avremmo | |||
| avreste | |||
| avrebbero | |||
| avevo | |||
| avevi | |||
| aveva | |||
| avevamo | |||
| avevate | |||
| avevano | |||
| ebbi | |||
| avesti | |||
| ebbe | |||
| avemmo | |||
| aveste | |||
| ebbero | |||
| avessi | |||
| avesse | |||
| avessimo | |||
| avessero | |||
| avendo | |||
| avuto | |||
| avuta | |||
| avuti | |||
| avute | |||
| | forms of essere, to be (not including the infinitive): | |||
| sono | |||
| sei | |||
| è | |||
| siamo | |||
| siete | |||
| sia | |||
| siate | |||
| siano | |||
| sarò | |||
| sarai | |||
| sarà | |||
| saremo | |||
| sarete | |||
| saranno | |||
| sarei | |||
| saresti | |||
| sarebbe | |||
| saremmo | |||
| sareste | |||
| sarebbero | |||
| ero | |||
| eri | |||
| era | |||
| eravamo | |||
| eravate | |||
| erano | |||
| fui | |||
| fosti | |||
| fu | |||
| fummo | |||
| foste | |||
| furono | |||
| fossi | |||
| fosse | |||
| fossimo | |||
| fossero | |||
| essendo | |||
| | forms of fare, to do (not including the infinitive, fa, fat-): | |||
| faccio | |||
| fai | |||
| facciamo | |||
| fanno | |||
| faccia | |||
| facciate | |||
| facciano | |||
| farò | |||
| farai | |||
| farà | |||
| faremo | |||
| farete | |||
| faranno | |||
| farei | |||
| faresti | |||
| farebbe | |||
| faremmo | |||
| fareste | |||
| farebbero | |||
| facevo | |||
| facevi | |||
| faceva | |||
| facevamo | |||
| facevate | |||
| facevano | |||
| feci | |||
| facesti | |||
| fece | |||
| facemmo | |||
| faceste | |||
| fecero | |||
| facessi | |||
| facesse | |||
| facessimo | |||
| facessero | |||
| facendo | |||
| | forms of stare, to be (not including the infinitive): | |||
| sto | |||
| stai | |||
| sta | |||
| stiamo | |||
| stanno | |||
| stia | |||
| stiate | |||
| stiano | |||
| starò | |||
| starai | |||
| starà | |||
| staremo | |||
| starete | |||
| staranno | |||
| starei | |||
| staresti | |||
| starebbe | |||
| staremmo | |||
| stareste | |||
| starebbero | |||
| stavo | |||
| stavi | |||
| stava | |||
| stavamo | |||
| stavate | |||
| stavano | |||
| stetti | |||
| stesti | |||
| stette | |||
| stemmo | |||
| steste | |||
| stettero | |||
| stessi | |||
| stesse | |||
| stessimo | |||
| stessero | |||
| stando | |||
+ 127
- 0
solr_config/lang/stopwords_ja.txt
View File
| @@ -0,0 +1,127 @@ | |||
| # | |||
| # This file defines a stopword set for Japanese. | |||
| # | |||
| # This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia. | |||
| # Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745 | |||
| # for frequency lists, etc. that can be useful for making your own set (if desired) | |||
| # | |||
| # Note that there is an overlap between these stopwords and the terms stopped when used | |||
| # in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note | |||
| # that comments are not allowed on the same line as stopwords. | |||
| # | |||
| # Also note that stopping is done in a case-insensitive manner. Change your StopFilter | |||
| # configuration if you need case-sensitive stopping. Lastly, note that stopping is done | |||
| # using the same character width as the entries in this file. Since this StopFilter is | |||
| # normally done after a CJKWidthFilter in your chain, you would usually want your romaji | |||
| # entries to be in half-width and your kana entries to be in full-width. | |||
| # | |||
| の | |||
| に | |||
| は | |||
| を | |||
| た | |||
| が | |||
| で | |||
| て | |||
| と | |||
| し | |||
| れ | |||
| さ | |||
| ある | |||
| いる | |||
| も | |||
| する | |||
| から | |||
| な | |||
| こと | |||
| として | |||
| い | |||
| や | |||
| れる | |||
| など | |||
| なっ | |||
| ない | |||
| この | |||
| ため | |||
| その | |||
| あっ | |||
| よう | |||
| また | |||
| もの | |||
| という | |||
| あり | |||
| まで | |||
| られ | |||
| なる | |||
| へ | |||
| か | |||
| だ | |||
| これ | |||
| によって | |||
| により | |||
| おり | |||
| より | |||
| による | |||
| ず | |||
| なり | |||
| られる | |||
| において | |||
| ば | |||
| なかっ | |||
| なく | |||
| しかし | |||
| について | |||
| せ | |||
| だっ | |||
| その後 | |||
| できる | |||
| それ | |||
| う | |||
| ので | |||
| なお | |||
| のみ | |||
| でき | |||
| き | |||
| つ | |||
| における | |||
| および | |||
| いう | |||
| さらに | |||
| でも | |||
| ら | |||
| たり | |||
| その他 | |||
| に関する | |||
| たち | |||
| ます | |||
| ん | |||
| なら | |||
| に対して | |||
| 特に | |||
| せる | |||
| 及び | |||
| これら | |||
| とき | |||
| では | |||
| にて | |||
| ほか | |||
| ながら | |||
| うち | |||
| そして | |||
| とともに | |||
| ただし | |||
| かつて | |||
| それぞれ | |||
| または | |||
| お | |||
| ほど | |||
| ものの | |||
| に対する | |||
| ほとんど | |||
| と共に | |||
| といった | |||
| です | |||
| とも | |||
| ところ | |||
| ここ | |||
| ##### End of file | |||
+ 172
- 0
solr_config/lang/stopwords_lv.txt
View File
| @@ -0,0 +1,172 @@ | |||
| # Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins | |||
| # the original list of over 800 forms was refined: | |||
| # pronouns, adverbs, interjections were removed | |||
| # | |||
| # prepositions | |||
| aiz | |||
| ap | |||
| ar | |||
| apakš | |||
| ārpus | |||
| augšpus | |||
| bez | |||
| caur | |||
| dēļ | |||
| gar | |||
| iekš | |||
| iz | |||
| kopš | |||
| labad | |||
| lejpus | |||
| līdz | |||
| no | |||
| otrpus | |||
| pa | |||
| par | |||
| pār | |||
| pēc | |||
| pie | |||
| pirms | |||
| pret | |||
| priekš | |||
| starp | |||
| šaipus | |||
| uz | |||
| viņpus | |||
| virs | |||
| virspus | |||
| zem | |||
| apakšpus | |||
| # Conjunctions | |||
| un | |||
| bet | |||
| jo | |||
| ja | |||
| ka | |||
| lai | |||
| tomēr | |||
| tikko | |||
| turpretī | |||
| arī | |||
| kaut | |||
| gan | |||
| tādēļ | |||
| tā | |||
| ne | |||
| tikvien | |||
| vien | |||
| kā | |||
| ir | |||
| te | |||
| vai | |||
| kamēr | |||
| # Particles | |||
| ar | |||
| diezin | |||
| droši | |||
| diemžēl | |||
| nebūt | |||
| ik | |||
| it | |||
| taču | |||
| nu | |||
| pat | |||
| tiklab | |||
| iekšpus | |||
| nedz | |||
| tik | |||
| nevis | |||
| turpretim | |||
| jeb | |||
| iekam | |||
| iekām | |||
| iekāms | |||
| kolīdz | |||
| līdzko | |||
| tiklīdz | |||
| jebšu | |||
| tālab | |||
| tāpēc | |||
| nekā | |||
| itin | |||
| jā | |||
| jau | |||
| jel | |||
| nē | |||
| nezin | |||
| tad | |||
| tikai | |||
| vis | |||
| tak | |||
| iekams | |||
| vien | |||
| # modal verbs | |||
| būt | |||
| biju | |||
| biji | |||
| bija | |||
| bijām | |||
| bijāt | |||
| esmu | |||
| esi | |||
| esam | |||
| esat | |||
| būšu | |||
| būsi | |||
| būs | |||
| būsim | |||
| būsiet | |||
| tikt | |||
| tiku | |||
| tiki | |||
| tika | |||
| tikām | |||
| tikāt | |||
| tieku | |||
| tiec | |||
| tiek | |||
| tiekam | |||
| tiekat | |||
| tikšu | |||
| tiks | |||
| tiksim | |||
| tiksiet | |||
| tapt | |||
| tapi | |||
| tapāt | |||
| topat | |||
| tapšu | |||
| tapsi | |||
| taps | |||
| tapsim | |||
| tapsiet | |||
| kļūt | |||
| kļuvu | |||
| kļuvi | |||
| kļuva | |||
| kļuvām | |||
| kļuvāt | |||
| kļūstu | |||
| kļūsti | |||
| kļūst | |||
| kļūstam | |||
| kļūstat | |||
| kļūšu | |||
| kļūsi | |||
| kļūs | |||
| kļūsim | |||
| kļūsiet | |||
| # verbs | |||
| varēt | |||
| varēju | |||
| varējām | |||
| varēšu | |||
| varēsim | |||
| var | |||
| varēji | |||
| varējāt | |||
| varēsi | |||
| varēsiet | |||
| varat | |||
| varēja | |||
| varēs | |||
+ 119
- 0
solr_config/lang/stopwords_nl.txt
View File
| @@ -0,0 +1,119 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Dutch stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | This is a ranked list (commonest to rarest) of stopwords derived from | |||
| | a large sample of Dutch text. | |||
| | Dutch stop words frequently exhibit homonym clashes. These are indicated | |||
| | clearly below. | |||
| de | the | |||
| en | and | |||
| van | of, from | |||
| ik | I, the ego | |||
| te | (1) chez, at etc, (2) to, (3) too | |||
| dat | that, which | |||
| die | that, those, who, which | |||
| in | in, inside | |||
| een | a, an, one | |||
| hij | he | |||
| het | the, it | |||
| niet | not, nothing, naught | |||
| zijn | (1) to be, being, (2) his, one's, its | |||
| is | is | |||
| was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river | |||
| op | on, upon, at, in, up, used up | |||
| aan | on, upon, to (as dative) | |||
| met | with, by | |||
| als | like, such as, when | |||
| voor | (1) before, in front of, (2) furrow | |||
| had | had, past tense all persons sing. of 'hebben' (have) | |||
| er | there | |||
| maar | but, only | |||
| om | round, about, for etc | |||
| hem | him | |||
| dan | then | |||
| zou | should/would, past tense all persons sing. of 'zullen' | |||
| of | or, whether, if | |||
| wat | what, something, anything | |||
| mijn | possessive and noun 'mine' | |||
| men | people, 'one' | |||
| dit | this | |||
| zo | so, thus, in this way | |||
| door | through by | |||
| over | over, across | |||
| ze | she, her, they, them | |||
| zich | oneself | |||
| bij | (1) a bee, (2) by, near, at | |||
| ook | also, too | |||
| tot | till, until | |||
| je | you | |||
| mij | me | |||
| uit | out of, from | |||
| der | Old Dutch form of 'van der' still found in surnames | |||
| daar | (1) there, (2) because | |||
| haar | (1) her, their, them, (2) hair | |||
| naar | (1) unpleasant, unwell etc, (2) towards, (3) as | |||
| heb | present first person sing. of 'to have' | |||
| hoe | how, why | |||
| heeft | present third person sing. of 'to have' | |||
| hebben | 'to have' and various parts thereof | |||
| deze | this | |||
| u | you | |||
| want | (1) for, (2) mitten, (3) rigging | |||
| nog | yet, still | |||
| zal | 'shall', first and third person sing. of verb 'zullen' (will) | |||
| me | me | |||
| zij | she, they | |||
| nu | now | |||
| ge | 'thou', still used in Belgium and south Netherlands | |||
| geen | none | |||
| omdat | because | |||
| iets | something, somewhat | |||
| worden | to become, grow, get | |||
| toch | yet, still | |||
| al | all, every, each | |||
| waren | (1) 'were' (2) to wander, (3) wares, (3) | |||
| veel | much, many | |||
| meer | (1) more, (2) lake | |||
| doen | to do, to make | |||
| toen | then, when | |||
| moet | noun 'spot/mote' and present form of 'to must' | |||
| ben | (1) am, (2) 'are' in interrogative second person singular of 'to be' | |||
| zonder | without | |||
| kan | noun 'can' and present form of 'to be able' | |||
| hun | their, them | |||
| dus | so, consequently | |||
| alles | all, everything, anything | |||
| onder | under, beneath | |||
| ja | yes, of course | |||
| eens | once, one day | |||
| hier | here | |||
| wie | who | |||
| werd | imperfect third person sing. of 'become' | |||
| altijd | always | |||
| doch | yet, but etc | |||
| wordt | present third person sing. of 'become' | |||
| wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans | |||
| kunnen | to be able | |||
| ons | us/our | |||
| zelf | self | |||
| tegen | against, towards, at | |||
| na | after, near | |||
| reeds | already | |||
| wil | (1) present tense of 'want', (2) 'will', noun, (3) fender | |||
| kon | could; past tense of 'to be able' | |||
| niets | nothing | |||
| uw | your | |||
| iemand | somebody | |||
| geweest | been; past participle of 'be' | |||
| andere | other | |||
+ 194
- 0
solr_config/lang/stopwords_no.txt
View File
| @@ -0,0 +1,194 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Norwegian stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | This stop word list is for the dominant bokmål dialect. Words unique | |||
| | to nynorsk are marked *. | |||
| | Revised by Jan Bruusgaard <Jan.Bruusgaard@ssb.no>, Jan 2005 | |||
| og | and | |||
| i | in | |||
| jeg | I | |||
| det | it/this/that | |||
| at | to (w. inf.) | |||
| en | a/an | |||
| et | a/an | |||
| den | it/this/that | |||
| til | to | |||
| er | is/am/are | |||
| som | who/that | |||
| på | on | |||
| de | they / you(formal) | |||
| med | with | |||
| han | he | |||
| av | of | |||
| ikke | not | |||
| ikkje | not * | |||
| der | there | |||
| så | so | |||
| var | was/were | |||
| meg | me | |||
| seg | you | |||
| men | but | |||
| ett | one | |||
| har | have | |||
| om | about | |||
| vi | we | |||
| min | my | |||
| mitt | my | |||
| ha | have | |||
| hadde | had | |||
| hun | she | |||
| nå | now | |||
| over | over | |||
| da | when/as | |||
| ved | by/know | |||
| fra | from | |||
| du | you | |||
| ut | out | |||
| sin | your | |||
| dem | them | |||
| oss | us | |||
| opp | up | |||
| man | you/one | |||
| kan | can | |||
| hans | his | |||
| hvor | where | |||
| eller | or | |||
| hva | what | |||
| skal | shall/must | |||
| selv | self (reflective) | |||
| sjøl | self (reflective) | |||
| her | here | |||
| alle | all | |||
| vil | will | |||
| bli | become | |||
| ble | became | |||
| blei | became * | |||
| blitt | have become | |||
| kunne | could | |||
| inn | in | |||
| når | when | |||
| være | be | |||
| kom | come | |||
| noen | some | |||
| noe | some | |||
| ville | would | |||
| dere | you | |||
| som | who/which/that | |||
| deres | their/theirs | |||
| kun | only/just | |||
| ja | yes | |||
| etter | after | |||
| ned | down | |||
| skulle | should | |||
| denne | this | |||
| for | for/because | |||
| deg | you | |||
| si | hers/his | |||
| sine | hers/his | |||
| sitt | hers/his | |||
| mot | against | |||
| å | to | |||
| meget | much | |||
| hvorfor | why | |||
| dette | this | |||
| disse | these/those | |||
| uten | without | |||
| hvordan | how | |||
| ingen | none | |||
| din | your | |||
| ditt | your | |||
| blir | become | |||
| samme | same | |||
| hvilken | which | |||
| hvilke | which (plural) | |||
| sånn | such a | |||
| inni | inside/within | |||
| mellom | between | |||
| vår | our | |||
| hver | each | |||
| hvem | who | |||
| vors | us/ours | |||
| hvis | whose | |||
| både | both | |||
| bare | only/just | |||
| enn | than | |||
| fordi | as/because | |||
| før | before | |||
| mange | many | |||
| også | also | |||
| slik | just | |||
| vært | been | |||
| være | to be | |||
| båe | both * | |||
| begge | both | |||
| siden | since | |||
| dykk | your * | |||
| dykkar | yours * | |||
| dei | they * | |||
| deira | them * | |||
| deires | theirs * | |||
| deim | them * | |||
| di | your (fem.) * | |||
| då | as/when * | |||
| eg | I * | |||
| ein | a/an * | |||
| eit | a/an * | |||
| eitt | a/an * | |||
| elles | or * | |||
| honom | he * | |||
| hjå | at * | |||
| ho | she * | |||
| hoe | she * | |||
| henne | her | |||
| hennar | her/hers | |||
| hennes | hers | |||
| hoss | how * | |||
| hossen | how * | |||
| ikkje | not * | |||
| ingi | noone * | |||
| inkje | noone * | |||
| korleis | how * | |||
| korso | how * | |||
| kva | what/which * | |||
| kvar | where * | |||
| kvarhelst | where * | |||
| kven | who/whom * | |||
| kvi | why * | |||
| kvifor | why * | |||
| me | we * | |||
| medan | while * | |||
| mi | my * | |||
| mine | my * | |||
| mykje | much * | |||
| no | now * | |||
| nokon | some (masc./neut.) * | |||
| noka | some (fem.) * | |||
| nokor | some * | |||
| noko | some * | |||
| nokre | some * | |||
| si | his/hers * | |||
| sia | since * | |||
| sidan | since * | |||
| so | so * | |||
| somt | some * | |||
| somme | some * | |||
| um | about* | |||
| upp | up * | |||
| vere | be * | |||
| vore | was * | |||
| verte | become * | |||
| vort | become * | |||
| varte | became * | |||
| vart | became * | |||
+ 253
- 0
solr_config/lang/stopwords_pt.txt
View File
| @@ -0,0 +1,253 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Portuguese stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | The following is a ranked list (commonest to rarest) of stopwords | |||
| | deriving from a large sample of text. | |||
| | Extra words have been added at the end. | |||
| de | of, from | |||
| a | the; to, at; her | |||
| o | the; him | |||
| que | who, that | |||
| e | and | |||
| do | de + o | |||
| da | de + a | |||
| em | in | |||
| um | a | |||
| para | for | |||
| | é from SER | |||
| com | with | |||
| não | not, no | |||
| uma | a | |||
| os | the; them | |||
| no | em + o | |||
| se | himself etc | |||
| na | em + a | |||
| por | for | |||
| mais | more | |||
| as | the; them | |||
| dos | de + os | |||
| como | as, like | |||
| mas | but | |||
| | foi from SER | |||
| ao | a + o | |||
| ele | he | |||
| das | de + as | |||
| | tem from TER | |||
| à | a + a | |||
| seu | his | |||
| sua | her | |||
| ou | or | |||
| | ser from SER | |||
| quando | when | |||
| muito | much | |||
| | há from HAV | |||
| nos | em + os; us | |||
| já | already, now | |||
| | está from EST | |||
| eu | I | |||
| também | also | |||
| só | only, just | |||
| pelo | per + o | |||
| pela | per + a | |||
| até | up to | |||
| isso | that | |||
| ela | he | |||
| entre | between | |||
| | era from SER | |||
| depois | after | |||
| sem | without | |||
| mesmo | same | |||
| aos | a + os | |||
| | ter from TER | |||
| seus | his | |||
| quem | whom | |||
| nas | em + as | |||
| me | me | |||
| esse | that | |||
| eles | they | |||
| | estão from EST | |||
| você | you | |||
| | tinha from TER | |||
| | foram from SER | |||
| essa | that | |||
| num | em + um | |||
| nem | nor | |||
| suas | her | |||
| meu | my | |||
| às | a + as | |||
| minha | my | |||
| | têm from TER | |||
| numa | em + uma | |||
| pelos | per + os | |||
| elas | they | |||
| | havia from HAV | |||
| | seja from SER | |||
| qual | which | |||
| | será from SER | |||
| nós | we | |||
| | tenho from TER | |||
| lhe | to him, her | |||
| deles | of them | |||
| essas | those | |||
| esses | those | |||
| pelas | per + as | |||
| este | this | |||
| | fosse from SER | |||
| dele | of him | |||
| | other words. There are many contractions such as naquele = em+aquele, | |||
| | mo = me+o, but they are rare. | |||
| | Indefinite article plural forms are also rare. | |||
| tu | thou | |||
| te | thee | |||
| vocês | you (plural) | |||
| vos | you | |||
| lhes | to them | |||
| meus | my | |||
| minhas | |||
| teu | thy | |||
| tua | |||
| teus | |||
| tuas | |||
| nosso | our | |||
| nossa | |||
| nossos | |||
| nossas | |||
| dela | of her | |||
| delas | of them | |||
| esta | this | |||
| estes | these | |||
| estas | these | |||
| aquele | that | |||
| aquela | that | |||
| aqueles | those | |||
| aquelas | those | |||
| isto | this | |||
| aquilo | that | |||
| | forms of estar, to be (not including the infinitive): | |||
| estou | |||
| está | |||
| estamos | |||
| estão | |||
| estive | |||
| esteve | |||
| estivemos | |||
| estiveram | |||
| estava | |||
| estávamos | |||
| estavam | |||
| estivera | |||
| estivéramos | |||
| esteja | |||
| estejamos | |||
| estejam | |||
| estivesse | |||
| estivéssemos | |||
| estivessem | |||
| estiver | |||
| estivermos | |||
| estiverem | |||
| | forms of haver, to have (not including the infinitive): | |||
| hei | |||
| há | |||
| havemos | |||
| hão | |||
| houve | |||
| houvemos | |||
| houveram | |||
| houvera | |||
| houvéramos | |||
| haja | |||
| hajamos | |||
| hajam | |||
| houvesse | |||
| houvéssemos | |||
| houvessem | |||
| houver | |||
| houvermos | |||
| houverem | |||
| houverei | |||
| houverá | |||
| houveremos | |||
| houverão | |||
| houveria | |||
| houveríamos | |||
| houveriam | |||
| | forms of ser, to be (not including the infinitive): | |||
| sou | |||
| somos | |||
| são | |||
| era | |||
| éramos | |||
| eram | |||
| fui | |||
| foi | |||
| fomos | |||
| foram | |||
| fora | |||
| fôramos | |||
| seja | |||
| sejamos | |||
| sejam | |||
| fosse | |||
| fôssemos | |||
| fossem | |||
| for | |||
| formos | |||
| forem | |||
| serei | |||
| será | |||
| seremos | |||
| serão | |||
| seria | |||
| seríamos | |||
| seriam | |||
| | forms of ter, to have (not including the infinitive): | |||
| tenho | |||
| tem | |||
| temos | |||
| tém | |||
| tinha | |||
| tínhamos | |||
| tinham | |||
| tive | |||
| teve | |||
| tivemos | |||
| tiveram | |||
| tivera | |||
| tivéramos | |||
| tenha | |||
| tenhamos | |||
| tenham | |||
| tivesse | |||
| tivéssemos | |||
| tivessem | |||
| tiver | |||
| tivermos | |||
| tiverem | |||
| terei | |||
| terá | |||
| teremos | |||
| terão | |||
| teria | |||
| teríamos | |||
| teriam | |||
+ 233
- 0
solr_config/lang/stopwords_ro.txt
View File
| @@ -0,0 +1,233 @@ | |||
| # This file was created by Jacques Savoy and is distributed under the BSD license. | |||
| # See http://members.unine.ch/jacques.savoy/clef/index.html. | |||
| # Also see http://www.opensource.org/licenses/bsd-license.html | |||
| acea | |||
| aceasta | |||
| această | |||
| aceea | |||
| acei | |||
| aceia | |||
| acel | |||
| acela | |||
| acele | |||
| acelea | |||
| acest | |||
| acesta | |||
| aceste | |||
| acestea | |||
| aceşti | |||
| aceştia | |||
| acolo | |||
| acum | |||
| ai | |||
| aia | |||
| aibă | |||
| aici | |||
| al | |||
| ăla | |||
| ale | |||
| alea | |||
| ălea | |||
| altceva | |||
| altcineva | |||
| am | |||
| ar | |||
| are | |||
| aş | |||
| aşadar | |||
| asemenea | |||
| asta | |||
| ăsta | |||
| astăzi | |||
| astea | |||
| ăstea | |||
| ăştia | |||
| asupra | |||
| aţi | |||
| au | |||
| avea | |||
| avem | |||
| aveţi | |||
| azi | |||
| bine | |||
| bucur | |||
| bună | |||
| ca | |||
| că | |||
| căci | |||
| când | |||
| care | |||
| cărei | |||
| căror | |||
| cărui | |||
| cât | |||
| câte | |||
| câţi | |||
| către | |||
| câtva | |||
| ce | |||
| cel | |||
| ceva | |||
| chiar | |||
| cînd | |||
| cine | |||
| cineva | |||
| cît | |||
| cîte | |||
| cîţi | |||
| cîtva | |||
| contra | |||
| cu | |||
| cum | |||
| cumva | |||
| curând | |||
| curînd | |||
| da | |||
| dă | |||
| dacă | |||
| dar | |||
| datorită | |||
| de | |||
| deci | |||
| deja | |||
| deoarece | |||
| departe | |||
| deşi | |||
| din | |||
| dinaintea | |||
| dintr | |||
| dintre | |||
| drept | |||
| după | |||
| ea | |||
| ei | |||
| el | |||
| ele | |||
| eram | |||
| este | |||
| eşti | |||
| eu | |||
| face | |||
| fără | |||
| fi | |||
| fie | |||
| fiecare | |||
| fii | |||
| fim | |||
| fiţi | |||
| iar | |||
| ieri | |||
| îi | |||
| îl | |||
| îmi | |||
| împotriva | |||
| în | |||
| înainte | |||
| înaintea | |||
| încât | |||
| încît | |||
| încotro | |||
| între | |||
| întrucât | |||
| întrucît | |||
| îţi | |||
| la | |||
| lângă | |||
| le | |||
| li | |||
| lîngă | |||
| lor | |||
| lui | |||
| mă | |||
| mâine | |||
| mea | |||
| mei | |||
| mele | |||
| mereu | |||
| meu | |||
| mi | |||
| mine | |||
| mult | |||
| multă | |||
| mulţi | |||
| ne | |||
| nicăieri | |||
| nici | |||
| nimeni | |||
| nişte | |||
| noastră | |||
| noastre | |||
| noi | |||
| noştri | |||
| nostru | |||
| nu | |||
| ori | |||
| oricând | |||
| oricare | |||
| oricât | |||
| orice | |||
| oricînd | |||
| oricine | |||
| oricît | |||
| oricum | |||
| oriunde | |||
| până | |||
| pe | |||
| pentru | |||
| peste | |||
| pînă | |||
| poate | |||
| pot | |||
| prea | |||
| prima | |||
| primul | |||
| prin | |||
| printr | |||
| sa | |||
| să | |||
| săi | |||
| sale | |||
| sau | |||
| său | |||
| se | |||
| şi | |||
| sînt | |||
| sîntem | |||
| sînteţi | |||
| spre | |||
| sub | |||
| sunt | |||
| suntem | |||
| sunteţi | |||
| ta | |||
| tăi | |||
| tale | |||
| tău | |||
| te | |||
| ţi | |||
| ţie | |||
| tine | |||
| toată | |||
| toate | |||
| tot | |||
| toţi | |||
| totuşi | |||
| tu | |||
| un | |||
| una | |||
| unde | |||
| undeva | |||
| unei | |||
| unele | |||
| uneori | |||
| unor | |||
| vă | |||
| vi | |||
| voastră | |||
| voastre | |||
| voi | |||
| voştri | |||
| vostru | |||
| vouă | |||
| vreo | |||
| vreun | |||
+ 243
- 0
solr_config/lang/stopwords_ru.txt
View File
| @@ -0,0 +1,243 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | a russian stop word list. comments begin with vertical bar. each stop | |||
| | word is at the start of a line. | |||
| | this is a ranked list (commonest to rarest) of stopwords derived from | |||
| | a large text sample. | |||
| | letter `ё' is translated to `е'. | |||
| и | and | |||
| в | in/into | |||
| во | alternative form | |||
| не | not | |||
| что | what/that | |||
| он | he | |||
| на | on/onto | |||
| я | i | |||
| с | from | |||
| со | alternative form | |||
| как | how | |||
| а | milder form of `no' (but) | |||
| то | conjunction and form of `that' | |||
| все | all | |||
| она | she | |||
| так | so, thus | |||
| его | him | |||
| но | but | |||
| да | yes/and | |||
| ты | thou | |||
| к | towards, by | |||
| у | around, chez | |||
| же | intensifier particle | |||
| вы | you | |||
| за | beyond, behind | |||
| бы | conditional/subj. particle | |||
| по | up to, along | |||
| только | only | |||
| ее | her | |||
| мне | to me | |||
| было | it was | |||
| вот | here is/are, particle | |||
| от | away from | |||
| меня | me | |||
| еще | still, yet, more | |||
| нет | no, there isnt/arent | |||
| о | about | |||
| из | out of | |||
| ему | to him | |||
| теперь | now | |||
| когда | when | |||
| даже | even | |||
| ну | so, well | |||
| вдруг | suddenly | |||
| ли | interrogative particle | |||
| если | if | |||
| уже | already, but homonym of `narrower' | |||
| или | or | |||
| ни | neither | |||
| быть | to be | |||
| был | he was | |||
| него | prepositional form of его | |||
| до | up to | |||
| вас | you accusative | |||
| нибудь | indef. suffix preceded by hyphen | |||
| опять | again | |||
| уж | already, but homonym of `adder' | |||
| вам | to you | |||
| сказал | he said | |||
| ведь | particle `after all' | |||
| там | there | |||
| потом | then | |||
| себя | oneself | |||
| ничего | nothing | |||
| ей | to her | |||
| может | usually with `быть' as `maybe' | |||
| они | they | |||
| тут | here | |||
| где | where | |||
| есть | there is/are | |||
| надо | got to, must | |||
| ней | prepositional form of ей | |||
| для | for | |||
| мы | we | |||
| тебя | thee | |||
| их | them, their | |||
| чем | than | |||
| была | she was | |||
| сам | self | |||
| чтоб | in order to | |||
| без | without | |||
| будто | as if | |||
| человек | man, person, one | |||
| чего | genitive form of `what' | |||
| раз | once | |||
| тоже | also | |||
| себе | to oneself | |||
| под | beneath | |||
| жизнь | life | |||
| будет | will be | |||
| ж | short form of intensifer particle `же' | |||
| тогда | then | |||
| кто | who | |||
| этот | this | |||
| говорил | was saying | |||
| того | genitive form of `that' | |||
| потому | for that reason | |||
| этого | genitive form of `this' | |||
| какой | which | |||
| совсем | altogether | |||
| ним | prepositional form of `его', `они' | |||
| здесь | here | |||
| этом | prepositional form of `этот' | |||
| один | one | |||
| почти | almost | |||
| мой | my | |||
| тем | instrumental/dative plural of `тот', `то' | |||
| чтобы | full form of `in order that' | |||
| нее | her (acc.) | |||
| кажется | it seems | |||
| сейчас | now | |||
| были | they were | |||
| куда | where to | |||
| зачем | why | |||
| сказать | to say | |||
| всех | all (acc., gen. preposn. plural) | |||
| никогда | never | |||
| сегодня | today | |||
| можно | possible, one can | |||
| при | by | |||
| наконец | finally | |||
| два | two | |||
| об | alternative form of `о', about | |||
| другой | another | |||
| хоть | even | |||
| после | after | |||
| над | above | |||
| больше | more | |||
| тот | that one (masc.) | |||
| через | across, in | |||
| эти | these | |||
| нас | us | |||
| про | about | |||
| всего | in all, only, of all | |||
| них | prepositional form of `они' (they) | |||
| какая | which, feminine | |||
| много | lots | |||
| разве | interrogative particle | |||
| сказала | she said | |||
| три | three | |||
| эту | this, acc. fem. sing. | |||
| моя | my, feminine | |||
| впрочем | moreover, besides | |||
| хорошо | good | |||
| свою | ones own, acc. fem. sing. | |||
| этой | oblique form of `эта', fem. `this' | |||
| перед | in front of | |||
| иногда | sometimes | |||
| лучше | better | |||
| чуть | a little | |||
| том | preposn. form of `that one' | |||
| нельзя | one must not | |||
| такой | such a one | |||
| им | to them | |||
| более | more | |||
| всегда | always | |||
| конечно | of course | |||
| всю | acc. fem. sing of `all' | |||
| между | between | |||
| | b: some paradigms | |||
| | | |||
| | personal pronouns | |||
| | | |||
| | я меня мне мной [мною] | |||
| | ты тебя тебе тобой [тобою] | |||
| | он его ему им [него, нему, ним] | |||
| | она ее эи ею [нее, нэи, нею] | |||
| | оно его ему им [него, нему, ним] | |||
| | | |||
| | мы нас нам нами | |||
| | вы вас вам вами | |||
| | они их им ими [них, ним, ними] | |||
| | | |||
| | себя себе собой [собою] | |||
| | | |||
| | demonstrative pronouns: этот (this), тот (that) | |||
| | | |||
| | этот эта это эти | |||
| | этого эты это эти | |||
| | этого этой этого этих | |||
| | этому этой этому этим | |||
| | этим этой этим [этою] этими | |||
| | этом этой этом этих | |||
| | | |||
| | тот та то те | |||
| | того ту то те | |||
| | того той того тех | |||
| | тому той тому тем | |||
| | тем той тем [тою] теми | |||
| | том той том тех | |||
| | | |||
| | determinative pronouns | |||
| | | |||
| | (a) весь (all) | |||
| | | |||
| | весь вся все все | |||
| | всего всю все все | |||
| | всего всей всего всех | |||
| | всему всей всему всем | |||
| | всем всей всем [всею] всеми | |||
| | всем всей всем всех | |||
| | | |||
| | (b) сам (himself etc) | |||
| | | |||
| | сам сама само сами | |||
| | самого саму само самих | |||
| | самого самой самого самих | |||
| | самому самой самому самим | |||
| | самим самой самим [самою] самими | |||
| | самом самой самом самих | |||
| | | |||
| | stems of verbs `to be', `to have', `to do' and modal | |||
| | | |||
| | быть бы буд быв есть суть | |||
| | име | |||
| | дел | |||
| | мог мож мочь | |||
| | уме | |||
| | хоч хот | |||
| | долж | |||
| | можн | |||
| | нужн | |||
| | нельзя | |||
+ 133
- 0
solr_config/lang/stopwords_sv.txt
View File
| @@ -0,0 +1,133 @@ | |||
| | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt | |||
| | This file is distributed under the BSD License. | |||
| | See http://snowball.tartarus.org/license.php | |||
| | Also see http://www.opensource.org/licenses/bsd-license.html | |||
| | - Encoding was converted to UTF-8. | |||
| | - This notice was added. | |||
| | | |||
| | NOTE: To use this file with StopFilterFactory, you must specify format="snowball" | |||
| | A Swedish stop word list. Comments begin with vertical bar. Each stop | |||
| | word is at the start of a line. | |||
| | This is a ranked list (commonest to rarest) of stopwords derived from | |||
| | a large text sample. | |||
| | Swedish stop words occasionally exhibit homonym clashes. For example | |||
| | så = so, but also seed. These are indicated clearly below. | |||
| och | and | |||
| det | it, this/that | |||
| att | to (with infinitive) | |||
| i | in, at | |||
| en | a | |||
| jag | I | |||
| hon | she | |||
| som | who, that | |||
| han | he | |||
| på | on | |||
| den | it, this/that | |||
| med | with | |||
| var | where, each | |||
| sig | him(self) etc | |||
| för | for | |||
| så | so (also: seed) | |||
| till | to | |||
| är | is | |||
| men | but | |||
| ett | a | |||
| om | if; around, about | |||
| hade | had | |||
| de | they, these/those | |||
| av | of | |||
| icke | not, no | |||
| mig | me | |||
| du | you | |||
| henne | her | |||
| då | then, when | |||
| sin | his | |||
| nu | now | |||
| har | have | |||
| inte | inte någon = no one | |||
| hans | his | |||
| honom | him | |||
| skulle | 'sake' | |||
| hennes | her | |||
| där | there | |||
| min | my | |||
| man | one (pronoun) | |||
| ej | nor | |||
| vid | at, by, on (also: vast) | |||
| kunde | could | |||
| något | some etc | |||
| från | from, off | |||
| ut | out | |||
| när | when | |||
| efter | after, behind | |||
| upp | up | |||
| vi | we | |||
| dem | them | |||
| vara | be | |||
| vad | what | |||
| över | over | |||
| än | than | |||
| dig | you | |||
| kan | can | |||
| sina | his | |||
| här | here | |||
| ha | have | |||
| mot | towards | |||
| alla | all | |||
| under | under (also: wonder) | |||
| någon | some etc | |||
| eller | or (else) | |||
| allt | all | |||
| mycket | much | |||
| sedan | since | |||
| ju | why | |||
| denna | this/that | |||
| själv | myself, yourself etc | |||
| detta | this/that | |||
| åt | to | |||
| utan | without | |||
| varit | was | |||
| hur | how | |||
| ingen | no | |||
| mitt | my | |||
| ni | you | |||
| bli | to be, become | |||
| blev | from bli | |||
| oss | us | |||
| din | thy | |||
| dessa | these/those | |||
| några | some etc | |||
| deras | their | |||
| blir | from bli | |||
| mina | my | |||
| samma | (the) same | |||
| vilken | who, that | |||
| er | you, your | |||
| sådan | such a | |||
| vår | our | |||
| blivit | from bli | |||
| dess | its | |||
| inom | within | |||
| mellan | between | |||
| sådant | such a | |||
| varför | why | |||
| varje | each | |||
| vilka | who, that | |||
| ditt | thy | |||
| vem | who | |||
| vilket | who, that | |||
| sitta | his | |||
| sådana | such a | |||
| vart | each | |||
| dina | thy | |||
| vars | whose | |||
| vårt | our | |||
| våra | our | |||
| ert | your | |||
| era | your | |||
| vilkas | whose | |||
+ 119
- 0
solr_config/lang/stopwords_th.txt
View File
| @@ -0,0 +1,119 @@ | |||
| # Thai stopwords from: | |||
| # "Opinion Detection in Thai Political News Columns | |||
| # Based on Subjectivity Analysis" | |||
| # Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak | |||
| ไว้ | |||
| ไม่ | |||
| ไป | |||
| ได้ | |||
| ให้ | |||
| ใน | |||
| โดย | |||
| แห่ง | |||
| แล้ว | |||
| และ | |||
| แรก | |||
| แบบ | |||
| แต่ | |||
| เอง | |||
| เห็น | |||
| เลย | |||
| เริ่ม | |||
| เรา | |||
| เมื่อ | |||
| เพื่อ | |||
| เพราะ | |||
| เป็นการ | |||
| เป็น | |||
| เปิดเผย | |||
| เปิด | |||
| เนื่องจาก | |||
| เดียวกัน | |||
| เดียว | |||
| เช่น | |||
| เฉพาะ | |||
| เคย | |||
| เข้า | |||
| เขา | |||
| อีก | |||
| อาจ | |||
| อะไร | |||
| ออก | |||
| อย่าง | |||
| อยู่ | |||
| อยาก | |||
| หาก | |||
| หลาย | |||
| หลังจาก | |||
| หลัง | |||
| หรือ | |||
| หนึ่ง | |||
| ส่วน | |||
| ส่ง | |||
| สุด | |||
| สําหรับ | |||
| ว่า | |||
| วัน | |||
| ลง | |||
| ร่วม | |||
| ราย | |||
| รับ | |||
| ระหว่าง | |||
| รวม | |||
| ยัง | |||
| มี | |||
| มาก | |||
| มา | |||
| พร้อม | |||
| พบ | |||
| ผ่าน | |||
| ผล | |||
| บาง | |||
| น่า | |||
| นี้ | |||
| นํา | |||
| นั้น | |||
| นัก | |||
| นอกจาก | |||
| ทุก | |||
| ที่สุด | |||
| ที่ | |||
| ทําให้ | |||
| ทํา | |||
| ทาง | |||
| ทั้งนี้ | |||
| ทั้ง | |||
| ถ้า | |||
| ถูก | |||
| ถึง | |||
| ต้อง | |||
| ต่างๆ | |||
| ต่าง | |||
| ต่อ | |||
| ตาม | |||
| ตั้งแต่ | |||
| ตั้ง | |||
| ด้าน | |||
| ด้วย | |||
| ดัง | |||
| ซึ่ง | |||
| ช่วง | |||
| จึง | |||
| จาก | |||
| จัด | |||
| จะ | |||
| คือ | |||
| ความ | |||
| ครั้ง | |||
| คง | |||
| ขึ้น | |||
| ของ | |||
| ขอ | |||
| ขณะ | |||
| ก่อน | |||
| ก็ | |||
| การ | |||
| กับ | |||
| กัน | |||
| กว่า | |||
| กล่าว | |||
+ 212
- 0
solr_config/lang/stopwords_tr.txt
View File
| @@ -0,0 +1,212 @@ | |||
| # Turkish stopwords from LUCENE-559 | |||
| # merged with the list from "Information Retrieval on Turkish Texts" | |||
| # (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf) | |||
| acaba | |||
| altmış | |||
| altı | |||
| ama | |||
| ancak | |||
| arada | |||
| aslında | |||
| ayrıca | |||
| bana | |||
| bazı | |||
| belki | |||
| ben | |||
| benden | |||
| beni | |||
| benim | |||
| beri | |||
| beş | |||
| bile | |||
| bin | |||
| bir | |||
| birçok | |||
| biri | |||
| birkaç | |||
| birkez | |||
| birşey | |||
| birşeyi | |||
| biz | |||
| bize | |||
| bizden | |||
| bizi | |||
| bizim | |||
| böyle | |||
| böylece | |||
| bu | |||
| buna | |||
| bunda | |||
| bundan | |||
| bunlar | |||
| bunları | |||
| bunların | |||
| bunu | |||
| bunun | |||
| burada | |||
| çok | |||
| çünkü | |||
| da | |||
| daha | |||
| dahi | |||
| de | |||
| defa | |||
| değil | |||
| diğer | |||
| diye | |||
| doksan | |||
| dokuz | |||
| dolayı | |||
| dolayısıyla | |||
| dört | |||
| edecek | |||
| eden | |||
| ederek | |||
| edilecek | |||
| ediliyor | |||
| edilmesi | |||
| ediyor | |||
| eğer | |||
| elli | |||
| en | |||
| etmesi | |||
| etti | |||
| ettiği | |||
| ettiğini | |||
| gibi | |||
| göre | |||
| halen | |||
| hangi | |||
| hatta | |||
| hem | |||
| henüz | |||
| hep | |||
| hepsi | |||
| her | |||
| herhangi | |||
| herkesin | |||
| hiç | |||
| hiçbir | |||
| için | |||
| iki | |||
| ile | |||
| ilgili | |||
| ise | |||
| işte | |||
| itibaren | |||
| itibariyle | |||
| kadar | |||
| karşın | |||
| katrilyon | |||
| kendi | |||
| kendilerine | |||
| kendini | |||
| kendisi | |||
| kendisine | |||
| kendisini | |||
| kez | |||
| ki | |||
| kim | |||
| kimden | |||
| kime | |||
| kimi | |||
| kimse | |||
| kırk | |||
| milyar | |||
| milyon | |||
| mu | |||
| mü | |||
| mı | |||
| nasıl | |||
| ne | |||
| neden | |||
| nedenle | |||
| nerde | |||
| nerede | |||
| nereye | |||
| niye | |||
| niçin | |||
| o | |||
| olan | |||
| olarak | |||
| oldu | |||
| olduğu | |||
| olduğunu | |||
| olduklarını | |||
| olmadı | |||
| olmadığı | |||
| olmak | |||
| olması | |||
| olmayan | |||
| olmaz | |||
| olsa | |||
| olsun | |||
| olup | |||
| olur | |||
| olursa | |||
| oluyor | |||
| on | |||
| ona | |||
| ondan | |||
| onlar | |||
| onlardan | |||
| onları | |||
| onların | |||
| onu | |||
| onun | |||
| otuz | |||
| oysa | |||
| öyle | |||
| pek | |||
| rağmen | |||
| sadece | |||
| sanki | |||
| sekiz | |||
| seksen | |||
| sen | |||
| senden | |||
| seni | |||
| senin | |||
| siz | |||
| sizden | |||
| sizi | |||
| sizin | |||
| şey | |||
| şeyden | |||
| şeyi | |||
| şeyler | |||
| şöyle | |||
| şu | |||
| şuna | |||
| şunda | |||
| şundan | |||
| şunları | |||
| şunu | |||
| tarafından | |||
| trilyon | |||
| tüm | |||
| üç | |||
| üzere | |||
| var | |||
| vardı | |||
| ve | |||
| veya | |||
| ya | |||
| yani | |||
| yapacak | |||
| yapılan | |||
| yapılması | |||
| yapıyor | |||
| yapmak | |||
| yaptı | |||
| yaptığı | |||
| yaptığını | |||
| yaptıkları | |||
| yedi | |||
| yerine | |||
| yetmiş | |||
| yine | |||
| yirmi | |||
| yoksa | |||
| yüz | |||
| zaten | |||
+ 29
- 0
solr_config/lang/userdict_ja.txt
View File
| @@ -0,0 +1,29 @@ | |||
| # | |||
| # This is a sample user dictionary for Kuromoji (JapaneseTokenizer) | |||
| # | |||
| # Add entries to this file in order to override the statistical model in terms | |||
| # of segmentation, readings and part-of-speech tags. Notice that entries do | |||
| # not have weights since they are always used when found. This is by-design | |||
| # in order to maximize ease-of-use. | |||
| # | |||
| # Entries are defined using the following CSV format: | |||
| # <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag> | |||
| # | |||
| # Notice that a single half-width space separates tokens and readings, and | |||
| # that the number tokens and readings must match exactly. | |||
| # | |||
| # Also notice that multiple entries with the same <text> is undefined. | |||
| # | |||
| # Whitespace only lines are ignored. Comments are not allowed on entry lines. | |||
| # | |||
| # Custom segmentation for kanji compounds | |||
| 日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞 | |||
| 関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞 | |||
| # Custom segmentation for compound katakana | |||
| トートバッグ,トート バッグ,トート バッグ,かずカナ名詞 | |||
| ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞 | |||
| # Custom reading for former sumo wrestler | |||
| 朝青龍,朝青龍,アサショウリュウ,カスタム人名 | |||
+ 34
- 0
solr_config/params.json
View File
| @@ -0,0 +1,34 @@ | |||
| {"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}}}} | |||
+ 21
- 0
solr_config/protwords.txt
View File
| @@ -0,0 +1,21 @@ | |||
| # The ASF licenses this file to You under the Apache License, Version 2.0 | |||
| # (the "License"); you may not use this file except in compliance with | |||
| # the License. You may obtain a copy of the License at | |||
| # | |||
| # http://www.apache.org/licenses/LICENSE-2.0 | |||
| # | |||
| # Unless required by applicable law or agreed to in writing, software | |||
| # distributed under the License is distributed on an "AS IS" BASIS, | |||
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |||
| # See the License for the specific language governing permissions and | |||
| # limitations under the License. | |||
| #----------------------------------------------------------------------- | |||
| # Use a protected word file to protect against the stemmer reducing two | |||
| # unrelated words to the same base word. | |||
| # Some non-words that normally won't be encountered, | |||
| # just to test that they won't be stemmed. | |||
| dontstems | |||
| zwhacky | |||
+ 530
- 0
solr_config/schema.xml
View File
| @@ -0,0 +1,530 @@ | |||
| <?xml version="1.0" encoding="UTF-8"?> | |||
| <!-- Solr managed schema - automatically generated - DO NOT EDIT --> | |||
| <schema name="example-data-driven-schema" version="1.6"> | |||
| <uniqueKey>id</uniqueKey> | |||
| <fieldType name="ancestor_path" class="solr.TextField"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.KeywordTokenizerFactory"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="binary" class="solr.BinaryField"/> | |||
| <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> | |||
| <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/> | |||
| <fieldType name="currency" class="solr.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns" defaultCurrency="USD" currencyConfig="currency.xml" /> | |||
| <fieldType name="descendent_path" class="solr.TextField"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.KeywordTokenizerFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/> | |||
| <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> | |||
| <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/> | |||
| <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.KeywordTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="pdate" class="solr.DatePointField" docValues="true"/> | |||
| <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/> | |||
| <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/> | |||
| <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/> | |||
| <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/> | |||
| <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/> | |||
| <fieldType name="pint" class="solr.IntPointField" docValues="true"/> | |||
| <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/> | |||
| <fieldType name="plong" class="solr.LongPointField" docValues="true"/> | |||
| <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/> | |||
| <fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/> | |||
| <fieldType name="random" class="solr.RandomSortField" indexed="true"/> | |||
| <fieldType name="string" class="solr.StrField" sortMissingLast="true"/> | |||
| <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true"/> | |||
| <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_ar.txt" ignoreCase="true"/> | |||
| <filter class="solr.ArabicNormalizationFilterFactory"/> | |||
| <filter class="solr.ArabicStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_bg.txt" ignoreCase="true"/> | |||
| <filter class="solr.BulgarianStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.ElisionFilterFactory" articles="lang/contractions_ca.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_ca.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.CJKWidthFilterFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.CJKBigramFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_cz.txt" ignoreCase="true"/> | |||
| <filter class="solr.CzechStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Danish"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/> | |||
| <filter class="solr.GermanNormalizationFilterFactory"/> | |||
| <filter class="solr.GermanLightStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.GreekLowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_el.txt" ignoreCase="false"/> | |||
| <filter class="solr.GreekStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.EnglishPossessiveFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.PorterStemFilterFactory"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.EnglishPossessiveFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.PorterStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.PorterStemFilterFactory"/> | |||
| <filter class="solr.FlattenGraphFilterFactory" /> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.PorterStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.EnglishMinimalStemFilterFactory"/> | |||
| <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> | |||
| <filter class="solr.FlattenGraphFilterFactory" /> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/> | |||
| <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |||
| <filter class="solr.EnglishMinimalStemFilterFactory"/> | |||
| <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/> | |||
| <filter class="solr.SpanishLightStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_eu.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Basque"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <charFilter class="solr.PersianCharFilterFactory"/> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.ArabicNormalizationFilterFactory"/> | |||
| <filter class="solr.PersianNormalizationFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_fa.txt" ignoreCase="true"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.ElisionFilterFactory" articles="lang/contractions_fr.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/> | |||
| <filter class="solr.FrenchLightStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.ElisionFilterFactory" articles="lang/contractions_ga.txt" ignoreCase="true"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/hyphenations_ga.txt" ignoreCase="true"/> | |||
| <filter class="solr.IrishLowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_ga.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Irish"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/> | |||
| <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_gl.txt" ignoreCase="true"/> | |||
| <filter class="solr.GalicianStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.IndicNormalizationFilterFactory"/> | |||
| <filter class="solr.HindiNormalizationFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_hi.txt" ignoreCase="true"/> | |||
| <filter class="solr.HindiStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_hy.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_id.txt" ignoreCase="true"/> | |||
| <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt" ignoreCase="true"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/> | |||
| <filter class="solr.ItalianLightStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/> | |||
| <filter class="solr.JapaneseBaseFormFilterFactory"/> | |||
| <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/> | |||
| <filter class="solr.CJKWidthFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_ja.txt" ignoreCase="true"/> | |||
| <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/> | |||
| <filter class="solr.KoreanPartOfSpeechStopFilterFactory" /> | |||
| <filter class="solr.KoreanReadingFormFilterFactory" /> | |||
| <filter class="solr.LowerCaseFilterFactory" /> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_lv.txt" ignoreCase="true"/> | |||
| <filter class="solr.LatvianStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/> | |||
| <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/> | |||
| <filter class="solr.PortugueseLightStemFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_ro.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Russian"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.ThaiTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_th.txt" ignoreCase="true"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <filter class="solr.TurkishLowerCaseFilterFactory"/> | |||
| <filter class="solr.StopFilterFactory" words="lang/stopwords_tr.txt" ignoreCase="false"/> | |||
| <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_email_url" class="solr.TextField"> | |||
| <analyzer> | |||
| <tokenizer class="solr.UAX29URLEmailTokenizerFactory"/> | |||
| <filter class="solr.TypeTokenFilterFactory" types="email_url_types.txt" useWhitelist="true"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <fieldType name="text_shingles" class="solr.TextField" positionIncrementGap="100" multiValued="true"> | |||
| <analyzer type="index"> | |||
| <tokenizer class="solr.StandardTokenizerFactory"/> | |||
| <!-- <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="false" /> --> | |||
| <filter class="solr.LengthFilterFactory" min="2" max="18"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| <filter class="solr.PatternReplaceFilterFactory" pattern="(^[^a-z]+$)" replacement="" replace="all"/> | |||
| <filter class="solr.ShingleFilterFactory" minShingleSize="3" maxShingleSize="3" | |||
| outputUnigrams="false" outputUnigramsIfNoShingles="false" tokenSeparator=" " fillerToken="*"/> | |||
| <filter class="solr.PatternReplaceFilterFactory" pattern="(.*[\*].*)" replacement=""/> | |||
| <filter class="solr.TrimFilterFactory"/> | |||
| <!-- PRFF could have removed everything down to an empty string, remove if so --> | |||
| <filter class="solr.LengthFilterFactory" min="1" max="100"/> | |||
| </analyzer> | |||
| <analyzer type="query"> | |||
| <tokenizer class="solr.KeywordTokenizerFactory"/> | |||
| <filter class="solr.LowerCaseFilterFactory"/> | |||
| </analyzer> | |||
| </fieldType> | |||
| <field name="id" type="string" multiValued="false" indexed="true" required="true" stored="true"/> | |||
| <field name="_version_" type="plong" indexed="true" stored="true"/> | |||
| <field name="content_type" type="string" indexed="true" stored="true"/> | |||
| <field name="doc_type" type="string" indexed="true" stored="true"/> | |||
| <field name="title" type="string" indexed="true" stored="true"/> | |||
| <field name="language" type="string" indexed="true" stored="true"/> | |||
| <field name="content" type="text_general" multiValued="false" indexed="true" stored="true"/> | |||
| <field name="text_shingles" type="text_shingles" indexed="true" stored="false"/> | |||
| <field name="_text_" type="text_general" multiValued="true" indexed="true" stored="false"/> | |||
| <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/> | |||
| <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/> | |||
| <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/> | |||
| <dynamicField name="*_coordinate" type="pdouble" indexed="true" stored="false"/> | |||
| <dynamicField name="ignored_*" type="ignored" multiValued="true"/> | |||
| <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/> | |||
| <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/> | |||
| <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/> | |||
| <dynamicField name="random_*" type="random"/> | |||
| <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ko" type="text_ko" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/> | |||
| <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/> | |||
| <dynamicField name="*_point" type="point" indexed="true" stored="true"/> | |||
| <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/> | |||
| <dynamicField name="attr_*" type="text_general" multiValued="true" indexed="true" stored="true"/> | |||
| <dynamicField name="*_l_ns" type="plong" indexed="true" stored="false"/> | |||
| <dynamicField name="*_s_ns" type="string" indexed="true" stored="false"/> | |||
| <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/> | |||
| <dynamicField name="*_dts" type="pdate" multiValued="true" indexed="true" stored="true"/> | |||
| <dynamicField name="*_is" type="pints" indexed="true" stored="true"/> | |||
| <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/> | |||
| <dynamicField name="*_ls" type="plongs" indexed="true" stored="true"/> | |||
| <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/> | |||
| <dynamicField name="*_fs" type="pfloats" indexed="true" stored="true"/> | |||
| <dynamicField name="*_ds" type="pdoubles" indexed="true" stored="true"/> | |||
| <dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/> | |||
| <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/> | |||
| <dynamicField name="*_i" type="pint" indexed="true" stored="true"/> | |||
| <dynamicField name="*_s" type="string" indexed="true" stored="true"/> | |||
| <dynamicField name="*_l" type="plong" indexed="true" stored="true"/> | |||
| <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> | |||
| <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> | |||
| <dynamicField name="*_f" type="pfloat" indexed="true" stored="true"/> | |||
| <dynamicField name="*_d" type="pdouble" indexed="true" stored="true"/> | |||
| <dynamicField name="*_p" type="location" indexed="true" stored="true"/> | |||
| <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> | |||
| <copyField source="content" dest="text_shingles"/> | |||
| <copyField source="*" dest="_text_"/> | |||
| <!-- ADDED BY SIMON BOWIE 2022-04-04 --> | |||
| <copyField source="content" dest="year"/> | |||
| <field name="year" type="year" indexed="true" stored="true"/> | |||
| <fieldType name="year" class="solr.TextField" positionIncrementGap="100"> | |||
| <analyzer> | |||
| <tokenizer class="solr.PatternTokenizerFactory" pattern="=D[^\s]*\s[^\s]*\s[^\s]*\s[^\s]*\s(\d{4})" group="1" /> | |||
| </analyzer> | |||
| </fieldType> | |||
| <!-- END --> | |||
| </schema> | |||
+ 1368
- 0
solr_config/solrconfig.xml
File diff suppressed because it is too large
View File
+ 14
- 0
solr_config/stopwords.txt
View File
| @@ -0,0 +1,14 @@ | |||
| # Licensed to the Apache Software Foundation (ASF) under one or more | |||
| # contributor license agreements. See the NOTICE file distributed with | |||
| # this work for additional information regarding copyright ownership. | |||
| # The ASF licenses this file to You under the Apache License, Version 2.0 | |||
| # (the "License"); you may not use this file except in compliance with | |||
| # the License. You may obtain a copy of the License at | |||
| # | |||
| # http://www.apache.org/licenses/LICENSE-2.0 | |||
| # | |||
| # Unless required by applicable law or agreed to in writing, software | |||
| # distributed under the License is distributed on an "AS IS" BASIS, | |||
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |||
| # See the License for the specific language governing permissions and | |||
| # limitations under the License. | |||
+ 29
- 0
solr_config/synonyms.txt
View File
| @@ -0,0 +1,29 @@ | |||
| # 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 | |||
+ 115
- 0
solr_config/update-script.js
View File
| @@ -0,0 +1,115 @@ | |||
| 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 | |||
| } | |||
+ 32
- 0
solr_config/velocity/browse.vm
View File
| @@ -0,0 +1,32 @@ | |||
| <div id="query-box"> | |||
| <form id="query-form" action="#{url_for_home}" method="GET"> | |||
| $resource.find: | |||
| <input type="text" id="q" name="q" style="width: 50%" value="$!esc.html($request.params.get('q'))"/> | |||
| <input type="submit" value="$resource.submit"/> | |||
| <div id="debug_query" class="debug"> | |||
| <span id="parsed_query">$esc.html($response.response.debug.parsedquery)</span> | |||
| </div> | |||
| <input type="hidden" name="type" value="#current_type"/> | |||
| #if("#current_locale"!="")<input type="hidden" value="locale" value="#current_locale"/>#end | |||
| #foreach($fq in $response.responseHeader.params.getAll("fq")) | |||
| <input type="hidden" name="fq" id="allFQs" value="$esc.html($fq)"/> | |||
| #end | |||
| </form> | |||
| <div id="constraints"> | |||
| #foreach($fq in $response.responseHeader.params.getAll("fq")) | |||
| #set($previous_fq_count=$velocityCount - 1) | |||
| #if($fq != '') | |||
| > $fq<a href="#url_for_filters($response.responseHeader.params.fq.subList(0,$previous_fq_count))">x</a> | |||
| #end | |||
| #end | |||
| </div> | |||
| </div> | |||
| <div id="browse_results"> | |||
| #parse("results.vm") | |||
| </div> | |||
+ 0
- 0
solr_config/velocity/dropit.js
View File
+ 2
- 0
solr_config/velocity/facet_doc_type.vm
View File
| @@ -0,0 +1,2 @@ | |||
| ## intentionally empty | |||
+ 12
- 0
solr_config/velocity/facet_text_shingles.vm
View File
| @@ -0,0 +1,12 @@ | |||
| <div id="facet_$field.name"> | |||
| <span class="facet-field">$resource.facet.top_phrases</span><br/> | |||
| <ul id="tagcloud"> | |||
| #foreach($facet in $sort.sort($field.values,"name")) | |||
| <li data-weight="$math.mul($facet.count,1)"> | |||
| <a href="#url_for_facet_filter($field.name, $facet.name)">$facet.name</a> | |||
| </li> | |||
| #end | |||
| </ul> | |||
| </div> | |||
+ 24
- 0
solr_config/velocity/facets.vm
View File
| @@ -0,0 +1,24 @@ | |||
| #if($response.facetFields.size() > 0) | |||
| #foreach($field in $response.facetFields) | |||
| #if($field.values.size() > 0) | |||
| #if($engine.resourceExists("facet_${field.name}.vm")) | |||
| #parse("facet_${field.name}.vm") | |||
| #else | |||
| <div id="facet_$field.name" class="facet_field"> | |||
| <span class="facet-field">#label("facet.${field.name}",$field.name)</span><br/> | |||
| <ul> | |||
| #foreach($facet in $field.values) | |||
| <li><a href="#url_for_facet_filter($field.name, $facet.name)">#if($facet.name!=$null)#label("${field.name}.${facet.name}","${field.name}.${facet.name}")#else<em>missing</em>#end</a> ($facet.count)</li> | |||
| #end | |||
| </ul> | |||
| </div> | |||
| #end | |||
| #end | |||
| #end ## end if field.values > 0 | |||
| #end ## end if facetFields > 0 | |||
+ 29
- 0
solr_config/velocity/footer.vm
View File
| @@ -0,0 +1,29 @@ | |||
| <hr/> | |||
| <div> | |||
| <div id="admin"><a href="#url_root/index.html#/#{core_name}">Solr Admin</a></div> | |||
| <a href="#" onclick='jQuery(".debug").toggle(); return false;'>toggle debug mode</a> | |||
| <a href="#url_for_lens&wt=xml#if($debug)&debug=true#end">XML results</a> ## TODO: Add links for other formats, maybe dynamically? | |||
| </div> | |||
| <div> | |||
| <a href="http://lucene.apache.org/solr">Solr Home Page</a> | |||
| </div> | |||
| <div class="debug"> | |||
| <hr/> | |||
| Request: | |||
| <pre> | |||
| $esc.html($request) | |||
| </pre> | |||
| <hr/> | |||
| Debug: | |||
| <pre> | |||
| $esc.html($response.response.debug) | |||
| </pre> | |||
| </div> | |||
+ 290
- 0
solr_config/velocity/head.vm
View File
| @@ -0,0 +1,290 @@ | |||
| <title>Solr browse: #core_name</title> | |||
| <meta http-equiv="content-type" content="text/html; charset=UTF-8"/> | |||
| <link rel="icon" type="image/x-icon" href="#{url_root}/img/favicon.ico"/> | |||
| <link rel="shortcut icon" type="image/x-icon" href="#{url_root}/img/favicon.ico"/> | |||
| <script type="text/javascript" src="#{url_root}/libs/jquery-3.4.1.min.js"></script> | |||
| <script type="text/javascript" src="#{url_for_solr}/admin/file?file=/velocity/js/jquery.tx3-tag-cloud.js&contentType=text/javascript"></script> | |||
| <script type="text/javascript" src="#{url_for_solr}/admin/file?file=/velocity/js/dropit.js&contentType=text/javascript"></script> | |||
| <script type="text/javascript" src="#{url_for_solr}/admin/file?file=/velocity/js/jquery.autocomplete.js&contentType=text/javascript"></script> | |||
| <script type="text/javascript"> | |||
| $(document).ready(function() { | |||
| $("#tagcloud").tx3TagCloud({ | |||
| multiplier: 1 | |||
| }); | |||
| $('.menu').dropit(); | |||
| $( document ).ajaxComplete(function() { | |||
| $("#tagcloud").tx3TagCloud({ | |||
| multiplier: 5 | |||
| }); | |||
| }); | |||
| $('\#q').keyup(function() { | |||
| $('#browse_results').load('#{url_for_home}?#lensNoQ&v.layout.enabled=false&v.template=results&q='+encodeURI($('\#q').val())); | |||
| $("\#q").autocomplete('#{url_for_solr}/suggest', { | |||
| extraParams: { | |||
| 'suggest.q': function() { return $("\#q").val();}, | |||
| 'suggest.build': 'true', | |||
| 'wt': 'json', | |||
| } | |||
| }).keydown(function(e) { | |||
| if (e.keyCode === 13){ | |||
| $("#query-form").trigger('submit'); | |||
| } | |||
| }); | |||
| }); | |||
| }); | |||
| </script> | |||
| <style> | |||
| html { | |||
| background-color: #F0F8FF; | |||
| } | |||
| body { | |||
| font-family: Helvetica, Arial, sans-serif; | |||
| font-size: 10pt; | |||
| } | |||
| #header { | |||
| width: 100%; | |||
| font-size: 20pt; | |||
| } | |||
| #header2 { | |||
| margin-left:1200px; | |||
| } | |||
| #logo { | |||
| width: 115px; | |||
| margin: 0px 0px 0px 0px; | |||
| border-style: none; | |||
| } | |||
| a { | |||
| color: #305CB3; | |||
| } | |||
| a.hidden { | |||
| display:none; | |||
| } | |||
| em { | |||
| color: #FF833D; | |||
| } | |||
| .error { | |||
| color: white; | |||
| background-color: red; | |||
| left: 210px; | |||
| width:80%; | |||
| position: relative; | |||
| } | |||
| .debug { display: none; font-size: 10pt} | |||
| #debug_query { | |||
| font-family: Helvetica, Arial, sans-serif; | |||
| font-size: 10pt; | |||
| font-weight: bold; | |||
| } | |||
| #parsed_query { | |||
| font-family: Courier, Courier New, monospaced; | |||
| font-size: 10pt; | |||
| font-weight: normal; | |||
| } | |||
| #admin { | |||
| text-align: right; | |||
| vertical-align: top; | |||
| } | |||
| #query-form { | |||
| width: 90%; | |||
| } | |||
| #query-box { | |||
| padding: 5px; | |||
| margin: 5px; | |||
| font-weight: normal; | |||
| font-size: 24px; | |||
| letter-spacing: 0.08em; | |||
| } | |||
| #constraints { | |||
| margin: 10px; | |||
| } | |||
| #tabs { } | |||
| #tabs li { display: inline; font-size: 10px;} | |||
| #tabs li a { border-radius: 20px; border: 2px solid #C1CDCD; padding: 10px;color: #42454a; background-color: #dedbde;} | |||
| #tabs li a:hover { background-color: #f1f0ee; } | |||
| #tabs li a.selected { color: #000; background-color: #f1f0ee; font-weight: bold; padding: 5px } | |||
| #tabs li a.no_results { color: #000; background-color: #838B8B; font-style: italic; padding: 5px; pointer-events: none; | |||
| cursor: default; text-decoration: none;} | |||
| .pagination { | |||
| width: 305px; | |||
| border-radius: 25px; | |||
| border: 2px solid #C1CDCD; | |||
| padding: 20px; | |||
| padding-left: 10%; | |||
| background: #eee; | |||
| margin-left: 190px; | |||
| margin-top : 42px; | |||
| padding-top: 5px; | |||
| padding-bottom: 5px; | |||
| text-align:left; | |||
| } | |||
| #results_list { width: 70%; } | |||
| .result-document { | |||
| border-radius: 25px; | |||
| border: 2px solid #C1CDCD; | |||
| padding: 10px; | |||
| // width: 800px; | |||
| // height: 120px; | |||
| margin: 5px; | |||
| // margin-left: 60px; | |||
| // margin-right: 210px; | |||
| // margin-bottom: 15px; | |||
| transition: 1s ease; | |||
| } | |||
| .result-document:hover | |||
| { | |||
| webkit-transform: scale(1.1); | |||
| -ms-transform: scale(1.1); | |||
| transform: scale(1.1); | |||
| transition: 1s ease; | |||
| } | |||
| .result-document div { | |||
| padding: 5px; | |||
| } | |||
| .result-title { | |||
| width:60%; | |||
| } | |||
| .result-body { | |||
| background: #ddd; | |||
| } | |||
| .result-document:nth-child(2n+1) { | |||
| background-color: #FFFFFD; | |||
| } | |||
| #facets { | |||
| margin: 5px; | |||
| margin-top: 0px; | |||
| padding: 5px; | |||
| top: -20px; | |||
| position: relative; | |||
| float: right; | |||
| width: 25%; | |||
| } | |||
| .facet-field { | |||
| font-weight: bold; | |||
| } | |||
| #facets ul { | |||
| list-style: none; | |||
| margin: 0; | |||
| margin-bottom: 5px; | |||
| margin-top: 5px; | |||
| padding-left: 10px; | |||
| } | |||
| #facets ul li { | |||
| color: #999; | |||
| padding: 2px; | |||
| } | |||
| div.facet_field { | |||
| clear: left; | |||
| } | |||
| ul.tx3-tag-cloud { } | |||
| ul.tx3-tag-cloud li { | |||
| display: block; | |||
| float: left; | |||
| list-style: none; | |||
| margin-right: 4px; | |||
| } | |||
| ul.tx3-tag-cloud li a { | |||
| display: block; | |||
| text-decoration: none; | |||
| color: #c9c9c9; | |||
| padding: 3px 10px; | |||
| } | |||
| ul.tx3-tag-cloud li a:hover { | |||
| color: #000000; | |||
| -webkit-transition: color 250ms linear; | |||
| -moz-transition: color 250ms linear; | |||
| -o-transition: color 250ms linear; | |||
| -ms-transition: color 250ms linear; | |||
| transition: color 250ms linear; | |||
| } | |||
| .dropit { | |||
| list-style: none; | |||
| padding: 0; | |||
| margin: 0; | |||
| } | |||
| .dropit .dropit-trigger { position: relative; } | |||
| .dropit .dropit-submenu { | |||
| position: absolute; | |||
| top: 100%; | |||
| left: 0; /* dropdown left or right */ | |||
| z-index: 1000; | |||
| display: none; | |||
| min-width: 150px; | |||
| list-style: none; | |||
| padding: 0; | |||
| margin: 0; | |||
| } | |||
| .dropit .dropit-open .dropit-submenu { display: block; } | |||
| <!--autocomplete css--> | |||
| .ac_results { | |||
| padding: 0px; | |||
| border: 1px solid black; | |||
| background-color: white; | |||
| overflow: hidden; | |||
| z-index: 99999; | |||
| } | |||
| .ac_results ul { | |||
| width: 100%; | |||
| list-style-position: outside; | |||
| list-style: none; | |||
| padding: 0; | |||
| margin: 0; | |||
| } | |||
| .ac_results li { | |||
| margin: 0px; | |||
| padding: 2px 5px; | |||
| cursor: default; | |||
| display: block; | |||
| font: menu; | |||
| font-size: 12px; | |||
| line-height: 16px; | |||
| overflow: hidden; | |||
| } | |||
| .ac_loading { | |||
| // background: white url('˜indicator.gif') right center no-repeat; | |||
| } | |||
| .ac_odd { | |||
| background-color: #eee; | |||
| } | |||
| .ac_over { | |||
| background-color: #0A246A; | |||
| color: white; | |||
| } | |||
| </style> | |||
+ 77
- 0
solr_config/velocity/hit.vm
View File
| @@ -0,0 +1,77 @@ | |||
| #set($docId = $doc.getFirstValue($request.schema.uniqueKeyField.name)) | |||
| ## Load Mime-Type List and Mapping | |||
| #parse('mime_type_lists.vm') | |||
| ## Title | |||
| #if($doc.getFieldValue('title')) | |||
| #set($title = $esc.html($doc.getFirstValue('title'))) | |||
| #else | |||
| #set($title = "$doc.getFirstValue('id').substring($math.add(1,$doc.getFirstValue('id').lastIndexOf('/')))") | |||
| #end | |||
| ## Date | |||
| #if($doc.getFieldValue('attr_meta_creation_date')) | |||
| #set($date = $esc.html($doc.getFirstValue('attr_meta_creation_date'))) | |||
| #else | |||
| #set($date = "No date found") | |||
| #end | |||
| ## URL | |||
| #if($doc.getFieldValue('url')) | |||
| #set($url = $doc.getFieldValue('url')) | |||
| #elseif($doc.getFieldValue('resourcename')) | |||
| #set($url = "file:///$doc.getFirstValue('resourcename')") | |||
| #else | |||
| #set($url = "$doc.getFieldValue('id')") | |||
| #end | |||
| ## Sort out Mime-Type | |||
| #set($ct = $doc.getFirstValue('content_type').split(";").get(0)) | |||
| #set($filename = $doc.getFirstValue('resourcename')) | |||
| #set($filetype = false) | |||
| #set($filetype = $mimeExtensionsMap.get($ct)) | |||
| #if(!$filetype) | |||
| #set($filetype = $filename.substring($filename.lastIndexOf(".")).substring(1)) | |||
| #end | |||
| #if(!$filetype) | |||
| #set($filetype = "file") | |||
| #end | |||
| #if(!$supportedMimeTypes.contains($filetype)) | |||
| #set($filetype = "file") | |||
| #end | |||
| <div class="result-document"> | |||
| <span class="result-title"> | |||
| <img src="#{url_root}/img/filetypes/${filetype}.png" align="center"> | |||
| <b>$title</b> | |||
| </span> | |||
| <div> | |||
| id: $docId </br> | |||
| </div> | |||
| #set($pad = "") | |||
| #foreach($v in $response.response.highlighting.get($docId).get("content")) | |||
| $pad$esc.html($v).replace("HL_START","<em>").replace("HL_END","</em>") | |||
| #set($pad = " ... ") | |||
| #end | |||
| </div> | |||
| <a href="#" class="debug" onclick='jQuery(this).next().toggle(); return false;'>toggle explain</a> | |||
| <pre style="display: none;"> | |||
| $esc.html($response.getExplainMap().get($doc.getFirstValue('id'))) | |||
| </pre> | |||
| <a href="#" class="debug" onclick='jQuery(this).next().toggle(); return false;'>show all fields</a> | |||
| <pre style="display:none;"> | |||
| #foreach($fieldname in $doc.fieldNames) | |||
| <span>$fieldname :</span> | |||
| <span>#foreach($value in $doc.getFieldValues($fieldname))$esc.html($value)#end</span> | |||
| #end | |||
| </pre> | |||
BIN
solr_config/velocity/img/english_640.png
View File
| Before | After |
|---|---|
|
|
| Width: 640 | Height: 480 | Size: 135KB |
BIN
solr_config/velocity/img/france_640.png
View File
| Before | After |
|---|---|
|
|
| Width: 640 | Height: 480 | Size: 98KB |
BIN
solr_config/velocity/img/germany_640.png
View File
| Before | After |
|---|---|
|
|
| Width: 640 | Height: 480 | Size: 103KB |
BIN
solr_config/velocity/img/globe_256.png
View File
| Before | After |
|---|---|
|
|
| Width: 256 | Height: 256 | Size: 46KB |
+ 0
- 0
solr_config/velocity/jquery.tx3-tag-cloud.js
View File
+ 97
- 0
solr_config/velocity/js/dropit.js
View File
| @@ -0,0 +1,97 @@ | |||
| /* | |||
| * Dropit v1.1.0 | |||
| * http://dev7studios.com/dropit | |||
| * | |||
| * Copyright 2012, Dev7studios | |||
| * Free to use and abuse under the MIT license. | |||
| * http://www.opensource.org/licenses/mit-license.php | |||
| */ | |||
| ;(function($) { | |||
| $.fn.dropit = function(method) { | |||
| var methods = { | |||
| init : function(options) { | |||
| this.dropit.settings = $.extend({}, this.dropit.defaults, options); | |||
| return this.each(function() { | |||
| var $el = $(this), | |||
| el = this, | |||
| settings = $.fn.dropit.settings; | |||
| // Hide initial submenus | |||
| $el.addClass('dropit') | |||
| .find('>'+ settings.triggerParentEl +':has('+ settings.submenuEl +')').addClass('dropit-trigger') | |||
| .find(settings.submenuEl).addClass('dropit-submenu').hide(); | |||
| // Open on click | |||
| $el.off(settings.action).on(settings.action, settings.triggerParentEl +':has('+ settings.submenuEl +') > '+ settings.triggerEl +'', function(){ | |||
| // Close click menu's if clicked again | |||
| if(settings.action == 'click' && $(this).parents(settings.triggerParentEl).hasClass('dropit-open')){ | |||
| settings.beforeHide.call(this); | |||
| $(this).parents(settings.triggerParentEl).removeClass('dropit-open').find(settings.submenuEl).hide(); | |||
| settings.afterHide.call(this); | |||
| return false; | |||
| } | |||
| // Hide open menus | |||
| settings.beforeHide.call(this); | |||
| $('.dropit-open').removeClass('dropit-open').find('.dropit-submenu').hide(); | |||
| settings.afterHide.call(this); | |||
| // Open this menu | |||
| settings.beforeShow.call(this); | |||
| $(this).parents(settings.triggerParentEl).addClass('dropit-open').find(settings.submenuEl).show(); | |||
| settings.afterShow.call(this); | |||
| return false; | |||
| }); | |||
| // Close if outside click | |||
| $(document).on('click', function(){ | |||
| settings.beforeHide.call(this); | |||
| $('.dropit-open').removeClass('dropit-open').find('.dropit-submenu').hide(); | |||
| settings.afterHide.call(this); | |||
| }); | |||
| // If hover | |||
| if(settings.action == 'mouseenter'){ | |||
| $el.on('mouseleave', '.dropit-open', function(){ | |||
| settings.beforeHide.call(this); | |||
| $(this).removeClass('dropit-open').find(settings.submenuEl).hide(); | |||
| settings.afterHide.call(this); | |||
| }); | |||
| } | |||
| settings.afterLoad.call(this); | |||
| }); | |||
| } | |||
| }; | |||
| if (methods[method]) { | |||
| return methods[method].apply(this, Array.prototype.slice.call(arguments, 1)); | |||
| } else if (typeof method === 'object' || !method) { | |||
| return methods.init.apply(this, arguments); | |||
| } else { | |||
| $.error( 'Method "' + method + '" does not exist in dropit plugin!'); | |||
| } | |||
| }; | |||
| $.fn.dropit.defaults = { | |||
| action: 'mouseenter', // The open action for the trigger | |||
| submenuEl: 'ul', // The submenu element | |||
| triggerEl: 'a', // The trigger element | |||
| triggerParentEl: 'li', // The trigger parent element | |||
| afterLoad: function(){}, // Triggers when plugin has loaded | |||
| beforeShow: function(){}, // Triggers before submenu is shown | |||
| afterShow: function(){}, // Triggers after submenu is shown | |||
| beforeHide: function(){}, // Triggers before submenu is hidden | |||
| afterHide: function(){} // Triggers before submenu is hidden | |||
| }; | |||
| $.fn.dropit.settings = {}; | |||
| })(jQuery); | |||
+ 763
- 0
solr_config/velocity/js/jquery.autocomplete.js
View File
| @@ -0,0 +1,763 @@ | |||
| /* | |||
| * Autocomplete - jQuery plugin 1.1pre | |||
| * | |||
| * Copyright (c) 2007 Dylan Verheul, Dan G. Switzer, Anjesh Tuladhar, Jörn Zaefferer | |||
| * | |||
| * Dual licensed under the MIT and GPL licenses: | |||
| * http://www.opensource.org/licenses/mit-license.php | |||
| * http://www.gnu.org/licenses/gpl.html | |||
| * | |||
| * Revision: Id: jquery.autocomplete.js 5785 2008-07-12 10:37:33Z joern.zaefferer $ | |||
| * | |||
| */ | |||
| ;(function($) { | |||
| $.fn.extend({ | |||
| autocomplete: function(urlOrData, options) { | |||
| var isUrl = typeof urlOrData == "string"; | |||
| options = $.extend({}, $.Autocompleter.defaults, { | |||
| url: isUrl ? urlOrData : null, | |||
| data: isUrl ? null : urlOrData, | |||
| delay: isUrl ? $.Autocompleter.defaults.delay : 10, | |||
| max: options && !options.scroll ? 10 : 150 | |||
| }, options); | |||
| // if highlight is set to false, replace it with a do-nothing function | |||
| options.highlight = options.highlight || function(value) { return value; }; | |||
| // if the formatMatch option is not specified, then use formatItem for backwards compatibility | |||
| options.formatMatch = options.formatMatch || options.formatItem; | |||
| return this.each(function() { | |||
| new $.Autocompleter(this, options); | |||
| }); | |||
| }, | |||
| result: function(handler) { | |||
| return this.bind("result", handler); | |||
| }, | |||
| search: function(handler) { | |||
| return this.trigger("search", [handler]); | |||
| }, | |||
| flushCache: function() { | |||
| return this.trigger("flushCache"); | |||
| }, | |||
| setOptions: function(options){ | |||
| return this.trigger("setOptions", [options]); | |||
| }, | |||
| unautocomplete: function() { | |||
| return this.trigger("unautocomplete"); | |||
| } | |||
| }); | |||
| $.Autocompleter = function(input, options) { | |||
| var KEY = { | |||
| UP: 38, | |||
| DOWN: 40, | |||
| DEL: 46, | |||
| TAB: 9, | |||
| RETURN: 13, | |||
| ESC: 27, | |||
| COMMA: 188, | |||
| PAGEUP: 33, | |||
| PAGEDOWN: 34, | |||
| BACKSPACE: 8 | |||
| }; | |||
| // Create $ object for input element | |||
| var $input = $(input).attr("autocomplete", "off").addClass(options.inputClass); | |||
| var timeout; | |||
| var previousValue = ""; | |||
| var cache = $.Autocompleter.Cache(options); | |||
| var hasFocus = 0; | |||
| var lastKeyPressCode; | |||
| var config = { | |||
| mouseDownOnSelect: false | |||
| }; | |||
| var select = $.Autocompleter.Select(options, input, selectCurrent, config); | |||
| var blockSubmit; | |||
| // prevent form submit in opera when selecting with return key | |||
| $.browser.opera && $(input.form).bind("submit.autocomplete", function() { | |||
| if (blockSubmit) { | |||
| blockSubmit = false; | |||
| return false; | |||
| } | |||
| }); | |||
| // only opera doesn't trigger keydown multiple times while pressed, others don't work with keypress at all | |||
| $input.bind(($.browser.opera ? "keypress" : "keydown") + ".autocomplete", function(event) { | |||
| // track last key pressed | |||
| lastKeyPressCode = event.keyCode; | |||
| switch(event.keyCode) { | |||
| case KEY.UP: | |||
| event.preventDefault(); | |||
| if ( select.visible() ) { | |||
| select.prev(); | |||
| } else { | |||
| onChange(0, true); | |||
| } | |||
| break; | |||
| case KEY.DOWN: | |||
| event.preventDefault(); | |||
| if ( select.visible() ) { | |||
| select.next(); | |||
| } else { | |||
| onChange(0, true); | |||
| } | |||
| break; | |||
| case KEY.PAGEUP: | |||
| event.preventDefault(); | |||
| if ( select.visible() ) { | |||
| select.pageUp(); | |||
| } else { | |||
| onChange(0, true); | |||
| } | |||
| break; | |||
| case KEY.PAGEDOWN: | |||
| event.preventDefault(); | |||
| if ( select.visible() ) { | |||
| select.pageDown(); | |||
| } else { | |||
| onChange(0, true); | |||
| } | |||
| break; | |||
| // matches also semicolon | |||
| case options.multiple && $.trim(options.multipleSeparator) == "," && KEY.COMMA: | |||
| case KEY.TAB: | |||
| case KEY.RETURN: | |||
| if( selectCurrent() ) { | |||
| // stop default to prevent a form submit, Opera needs special handling | |||
| event.preventDefault(); | |||
| blockSubmit = true; | |||
| return false; | |||
| } | |||
| break; | |||
| case KEY.ESC: | |||
| select.hide(); | |||
| break; | |||
| default: | |||
| clearTimeout(timeout); | |||
| timeout = setTimeout(onChange, options.delay); | |||
| break; | |||
| } | |||
| }).focus(function(){ | |||
| // track whether the field has focus, we shouldn't process any | |||
| // results if the field no longer has focus | |||
| hasFocus++; | |||
| }).blur(function() { | |||
| hasFocus = 0; | |||
| if (!config.mouseDownOnSelect) { | |||
| hideResults(); | |||
| } | |||
| }).click(function() { | |||
| // show select when clicking in a focused field | |||
| if ( hasFocus++ > 1 && !select.visible() ) { | |||
| onChange(0, true); | |||
| } | |||
| }).bind("search", function() { | |||
| // TODO why not just specifying both arguments? | |||
| var fn = (arguments.length > 1) ? arguments[1] : null; | |||
| function findValueCallback(q, data) { | |||
| var result; | |||
| if( data && data.length ) { | |||
| for (var i=0; i < data.length; i++) { | |||
| if( data[i].result.toLowerCase() == q.toLowerCase() ) { | |||
| result = data[i]; | |||
| break; | |||
| } | |||
| } | |||
| } | |||
| if( typeof fn == "function" ) fn(result); | |||
| else $input.trigger("result", result && [result.data, result.value]); | |||
| } | |||
| $.each(trimWords($input.val()), function(i, value) { | |||
| request(value, findValueCallback, findValueCallback); | |||
| }); | |||
| }).bind("flushCache", function() { | |||
| cache.flush(); | |||
| }).bind("setOptions", function() { | |||
| $.extend(options, arguments[1]); | |||
| // if we've updated the data, repopulate | |||
| if ( "data" in arguments[1] ) | |||
| cache.populate(); | |||
| }).bind("unautocomplete", function() { | |||
| select.unbind(); | |||
| $input.unbind(); | |||
| $(input.form).unbind(".autocomplete"); | |||
| }); | |||
| function selectCurrent() { | |||
| var selected = select.selected(); | |||
| if( !selected ) | |||
| return false; | |||
| var v = selected.result; | |||
| previousValue = v; | |||
| if ( options.multiple ) { | |||
| var words = trimWords($input.val()); | |||
| if ( words.length > 1 ) { | |||
| v = words.slice(0, words.length - 1).join( options.multipleSeparator ) + options.multipleSeparator + v; | |||
| } | |||
| v += options.multipleSeparator; | |||
| } | |||
| $input.val(v); | |||
| hideResultsNow(); | |||
| $input.trigger("result", [selected.data, selected.value]); | |||
| return true; | |||
| } | |||
| function onChange(crap, skipPrevCheck) { | |||
| if( lastKeyPressCode == KEY.DEL ) { | |||
| select.hide(); | |||
| return; | |||
| } | |||
| var currentValue = $input.val(); | |||
| if ( !skipPrevCheck && currentValue == previousValue ) | |||
| return; | |||
| previousValue = currentValue; | |||
| currentValue = lastWord(currentValue); | |||
| if ( currentValue.length >= options.minChars) { | |||
| $input.addClass(options.loadingClass); | |||
| if (!options.matchCase) | |||
| currentValue = currentValue.toLowerCase(); | |||
| request(currentValue, receiveData, hideResultsNow); | |||
| } else { | |||
| stopLoading(); | |||
| select.hide(); | |||
| } | |||
| }; | |||
| function trimWords(value) { | |||
| if ( !value ) { | |||
| return [""]; | |||
| } | |||
| var words = value.split( options.multipleSeparator ); | |||
| var result = []; | |||
| $.each(words, function(i, value) { | |||
| if ( $.trim(value) ) | |||
| result[i] = $.trim(value); | |||
| }); | |||
| return result; | |||
| } | |||
| function lastWord(value) { | |||
| if ( !options.multiple ) | |||
| return value; | |||
| var words = trimWords(value); | |||
| return words[words.length - 1]; | |||
| } | |||
| // fills in the input box w/the first match (assumed to be the best match) | |||
| // q: the term entered | |||
| // sValue: the first matching result | |||
| function autoFill(q, sValue){ | |||
| // autofill in the complete box w/the first match as long as the user hasn't entered in more data | |||
| // if the last user key pressed was backspace, don't autofill | |||
| if( options.autoFill && (lastWord($input.val()).toLowerCase() == q.toLowerCase()) && lastKeyPressCode != KEY.BACKSPACE ) { | |||
| // fill in the value (keep the case the user has typed) | |||
| $input.val($input.val() + sValue.substring(lastWord(previousValue).length)); | |||
| // select the portion of the value not typed by the user (so the next character will erase) | |||
| $.Autocompleter.Selection(input, previousValue.length, previousValue.length + sValue.length); | |||
| } | |||
| }; | |||
| function hideResults() { | |||
| clearTimeout(timeout); | |||
| timeout = setTimeout(hideResultsNow, 200); | |||
| }; | |||
| function hideResultsNow() { | |||
| var wasVisible = select.visible(); | |||
| select.hide(); | |||
| clearTimeout(timeout); | |||
| stopLoading(); | |||
| if (options.mustMatch) { | |||
| // call search and run callback | |||
| $input.search( | |||
| function (result){ | |||
| // if no value found, clear the input box | |||
| if( !result ) { | |||
| if (options.multiple) { | |||
| var words = trimWords($input.val()).slice(0, -1); | |||
| $input.val( words.join(options.multipleSeparator) + (words.length ? options.multipleSeparator : "") ); | |||
| } | |||
| else | |||
| $input.val( "" ); | |||
| } | |||
| } | |||
| ); | |||
| } | |||
| if (wasVisible) | |||
| // position cursor at end of input field | |||
| $.Autocompleter.Selection(input, input.value.length, input.value.length); | |||
| }; | |||
| function receiveData(q, data) { | |||
| if ( data && data.length && hasFocus ) { | |||
| stopLoading(); | |||
| select.display(data, q); | |||
| autoFill(q, data[0].value); | |||
| select.show(); | |||
| } else { | |||
| hideResultsNow(); | |||
| } | |||
| }; | |||
| function request(term, success, failure) { | |||
| if (!options.matchCase) | |||
| term = term.toLowerCase(); | |||
| var data = cache.load(term); | |||
| data = null; // Avoid buggy cache and go to Solr every time | |||
| // recieve the cached data | |||
| if (data && data.length) { | |||
| success(term, data); | |||
| // if an AJAX url has been supplied, try loading the data now | |||
| } else if( (typeof options.url == "string") && (options.url.length > 0) ){ | |||
| var extraParams = { | |||
| timestamp: +new Date() | |||
| }; | |||
| $.each(options.extraParams, function(key, param) { | |||
| extraParams[key] = typeof param == "function" ? param() : param; | |||
| }); | |||
| $.ajax({ | |||
| // try to leverage ajaxQueue plugin to abort previous requests | |||
| mode: "abort", | |||
| // limit abortion to this input | |||
| port: "autocomplete" + input.name, | |||
| dataType: options.dataType, | |||
| url: options.url, | |||
| data: $.extend({ | |||
| q: lastWord(term), | |||
| limit: options.max | |||
| }, extraParams), | |||
| success: function(data) { | |||
| var parsed = options.parse && options.parse(data) || parse(data); | |||
| cache.add(term, parsed); | |||
| success(term, parsed); | |||
| } | |||
| }); | |||
| } else { | |||
| // if we have a failure, we need to empty the list -- this prevents the the [TAB] key from selecting the last successful match | |||
| select.emptyList(); | |||
| failure(term); | |||
| } | |||
| }; | |||
| function parse(data) { | |||
| var parsed = []; | |||
| var rows = data.split("\n"); | |||
| for (var i=0; i < rows.length; i++) { | |||
| var row = $.trim(rows[i]); | |||
| if (row) { | |||
| row = row.split("|"); | |||
| parsed[parsed.length] = { | |||
| data: row, | |||
| value: row[0], | |||
| result: options.formatResult && options.formatResult(row, row[0]) || row[0] | |||
| }; | |||
| } | |||
| } | |||
| return parsed; | |||
| }; | |||
| function stopLoading() { | |||
| $input.removeClass(options.loadingClass); | |||
| }; | |||
| }; | |||
| $.Autocompleter.defaults = { | |||
| inputClass: "ac_input", | |||
| resultsClass: "ac_results", | |||
| loadingClass: "ac_loading", | |||
| minChars: 1, | |||
| delay: 400, | |||
| matchCase: false, | |||
| matchSubset: true, | |||
| matchContains: false, | |||
| cacheLength: 10, | |||
| max: 100, | |||
| mustMatch: false, | |||
| extraParams: {}, | |||
| selectFirst: false, | |||
| formatItem: function(row) { return row[0]; }, | |||
| formatMatch: null, | |||
| autoFill: false, | |||
| width: 0, | |||
| multiple: false, | |||
| multipleSeparator: ", ", | |||
| highlight: function(value, term) { | |||
| return value.replace(new RegExp("(?![^&;]+;)(?!<[^<>]*)(" + term.replace(/([\^\$\(\)\[\]\{\}\*\.\+\?\|\\])/gi, "\\$1") + ")(?![^<>]*>)(?![^&;]+;)", "gi"), "<strong>$1</strong>"); | |||
| }, | |||
| scroll: true, | |||
| scrollHeight: 180 | |||
| }; | |||
| $.Autocompleter.Cache = function(options) { | |||
| var data = {}; | |||
| var length = 0; | |||
| function matchSubset(s, sub) { | |||
| if (!options.matchCase) | |||
| s = s.toLowerCase(); | |||
| var i = s.indexOf(sub); | |||
| if (options.matchContains == "word"){ | |||
| i = s.toLowerCase().search("\\b" + sub.toLowerCase()); | |||
| } | |||
| if (i == -1) return false; | |||
| return i == 0 || options.matchContains; | |||
| }; | |||
| function add(q, value) { | |||
| if (length > options.cacheLength){ | |||
| flush(); | |||
| } | |||
| if (!data[q]){ | |||
| length++; | |||
| } | |||
| data[q] = value; | |||
| } | |||
| function populate(){ | |||
| if( !options.data ) return false; | |||
| // track the matches | |||
| var stMatchSets = {}, | |||
| nullData = 0; | |||
| // no url was specified, we need to adjust the cache length to make sure it fits the local data store | |||
| if( !options.url ) options.cacheLength = 1; | |||
| // track all options for minChars = 0 | |||
| stMatchSets[""] = []; | |||
| // loop through the array and create a lookup structure | |||
| for ( var i = 0, ol = options.data.length; i < ol; i++ ) { | |||
| var rawValue = options.data[i]; | |||
| // if rawValue is a string, make an array otherwise just reference the array | |||
| rawValue = (typeof rawValue == "string") ? [rawValue] : rawValue; | |||
| var value = options.formatMatch(rawValue, i+1, options.data.length); | |||
| if ( value === false ) | |||
| continue; | |||
| var firstChar = value.charAt(0).toLowerCase(); | |||
| // if no lookup array for this character exists, look it up now | |||
| if( !stMatchSets[firstChar] ) | |||
| stMatchSets[firstChar] = []; | |||
| // if the match is a string | |||
| var row = { | |||
| value: value, | |||
| data: rawValue, | |||
| result: options.formatResult && options.formatResult(rawValue) || value | |||
| }; | |||
| // push the current match into the set list | |||
| stMatchSets[firstChar].push(row); | |||
| // keep track of minChars zero items | |||
| if ( nullData++ < options.max ) { | |||
| stMatchSets[""].push(row); | |||
| } | |||
| }; | |||
| // add the data items to the cache | |||
| $.each(stMatchSets, function(i, value) { | |||
| // increase the cache size | |||
| options.cacheLength++; | |||
| // add to the cache | |||
| add(i, value); | |||
| }); | |||
| } | |||
| // populate any existing data | |||
| setTimeout(populate, 25); | |||
| function flush(){ | |||
| data = {}; | |||
| length = 0; | |||
| } | |||
| return { | |||
| flush: flush, | |||
| add: add, | |||
| populate: populate, | |||
| load: function(q) { | |||
| if (!options.cacheLength || !length) | |||
| return null; | |||
| /* | |||
| * if dealing w/local data and matchContains than we must make sure | |||
| * to loop through all the data collections looking for matches | |||
| */ | |||
| if( !options.url && options.matchContains ){ | |||
| // track all matches | |||
| var csub = []; | |||
| // loop through all the data grids for matches | |||
| for( var k in data ){ | |||
| // don't search through the stMatchSets[""] (minChars: 0) cache | |||
| // this prevents duplicates | |||
| if( k.length > 0 ){ | |||
| var c = data[k]; | |||
| $.each(c, function(i, x) { | |||
| // if we've got a match, add it to the array | |||
| if (matchSubset(x.value, q)) { | |||
| csub.push(x); | |||
| } | |||
| }); | |||
| } | |||
| } | |||
| return csub; | |||
| } else | |||
| // if the exact item exists, use it | |||
| if (data[q]){ | |||
| return data[q]; | |||
| } else | |||
| if (options.matchSubset) { | |||
| for (var i = q.length - 1; i >= options.minChars; i--) { | |||
| var c = data[q.substr(0, i)]; | |||
| if (c) { | |||
| var csub = []; | |||
| $.each(c, function(i, x) { | |||
| if (matchSubset(x.value, q)) { | |||
| csub[csub.length] = x; | |||
| } | |||
| }); | |||
| return csub; | |||
| } | |||
| } | |||
| } | |||
| return null; | |||
| } | |||
| }; | |||
| }; | |||
| $.Autocompleter.Select = function (options, input, select, config) { | |||
| var CLASSES = { | |||
| ACTIVE: "ac_over" | |||
| }; | |||
| var listItems, | |||
| active = -1, | |||
| data, | |||
| term = "", | |||
| needsInit = true, | |||
| element, | |||
| list; | |||
| // Create results | |||
| function init() { | |||
| if (!needsInit) | |||
| return; | |||
| element = $("<div/>") | |||
| .hide() | |||
| .addClass(options.resultsClass) | |||
| .css("position", "absolute") | |||
| .appendTo(document.body); | |||
| list = $("<ul/>").appendTo(element).mouseover( function(event) { | |||
| if(target(event).nodeName && target(event).nodeName.toUpperCase() == 'LI') { | |||
| active = $("li", list).removeClass(CLASSES.ACTIVE).index(target(event)); | |||
| $(target(event)).addClass(CLASSES.ACTIVE); | |||
| } | |||
| }).click(function(event) { | |||
| $(target(event)).addClass(CLASSES.ACTIVE); | |||
| select(); | |||
| // TODO provide option to avoid setting focus again after selection? useful for cleanup-on-focus | |||
| input.focus(); | |||
| return false; | |||
| }).mousedown(function() { | |||
| config.mouseDownOnSelect = true; | |||
| }).mouseup(function() { | |||
| config.mouseDownOnSelect = false; | |||
| }); | |||
| if( options.width > 0 ) | |||
| element.css("width", options.width); | |||
| needsInit = false; | |||
| } | |||
| function target(event) { | |||
| var element = event.target; | |||
| while(element && element.tagName != "LI") | |||
| element = element.parentNode; | |||
| // more fun with IE, sometimes event.target is empty, just ignore it then | |||
| if(!element) | |||
| return []; | |||
| return element; | |||
| } | |||
| function moveSelect(step) { | |||
| listItems.slice(active, active + 1).removeClass(CLASSES.ACTIVE); | |||
| movePosition(step); | |||
| var activeItem = listItems.slice(active, active + 1).addClass(CLASSES.ACTIVE); | |||
| if(options.scroll) { | |||
| var offset = 0; | |||
| listItems.slice(0, active).each(function() { | |||
| offset += this.offsetHeight; | |||
| }); | |||
| if((offset + activeItem[0].offsetHeight - list.scrollTop()) > list[0].clientHeight) { | |||
| list.scrollTop(offset + activeItem[0].offsetHeight - list.innerHeight()); | |||
| } else if(offset < list.scrollTop()) { | |||
| list.scrollTop(offset); | |||
| } | |||
| } | |||
| }; | |||
| function movePosition(step) { | |||
| active += step; | |||
| if (active < 0) { | |||
| active = listItems.size() - 1; | |||
| } else if (active >= listItems.size()) { | |||
| active = 0; | |||
| } | |||
| } | |||
| function limitNumberOfItems(available) { | |||
| return options.max && options.max < available | |||
| ? options.max | |||
| : available; | |||
| } | |||
| function fillList() { | |||
| list.empty(); | |||
| var max = limitNumberOfItems(data.length); | |||
| for (var i=0; i < max; i++) { | |||
| if (!data[i]) | |||
| continue; | |||
| var formatted = options.formatItem(data[i].data, i+1, max, data[i].value, term); | |||
| if ( formatted === false ) | |||
| continue; | |||
| var li = $("<li/>").html( options.highlight(formatted, term) ).addClass(i%2 == 0 ? "ac_even" : "ac_odd").appendTo(list)[0]; | |||
| $.data(li, "ac_data", data[i]); | |||
| } | |||
| listItems = list.find("li"); | |||
| if ( options.selectFirst ) { | |||
| listItems.slice(0, 1).addClass(CLASSES.ACTIVE); | |||
| active = 0; | |||
| } | |||
| // apply bgiframe if available | |||
| if ( $.fn.bgiframe ) | |||
| list.bgiframe(); | |||
| } | |||
| return { | |||
| display: function(d, q) { | |||
| init(); | |||
| data = d; | |||
| term = q; | |||
| fillList(); | |||
| }, | |||
| next: function() { | |||
| moveSelect(1); | |||
| }, | |||
| prev: function() { | |||
| moveSelect(-1); | |||
| }, | |||
| pageUp: function() { | |||
| if (active != 0 && active - 8 < 0) { | |||
| moveSelect( -active ); | |||
| } else { | |||
| moveSelect(-8); | |||
| } | |||
| }, | |||
| pageDown: function() { | |||
| if (active != listItems.size() - 1 && active + 8 > listItems.size()) { | |||
| moveSelect( listItems.size() - 1 - active ); | |||
| } else { | |||
| moveSelect(8); | |||
| } | |||
| }, | |||
| hide: function() { | |||
| element && element.hide(); | |||
| listItems && listItems.removeClass(CLASSES.ACTIVE); | |||
| active = -1; | |||
| }, | |||
| visible : function() { | |||
| return element && element.is(":visible"); | |||
| }, | |||
| current: function() { | |||
| return this.visible() && (listItems.filter("." + CLASSES.ACTIVE)[0] || options.selectFirst && listItems[0]); | |||
| }, | |||
| show: function() { | |||
| var offset = $(input).offset(); | |||
| element.css({ | |||
| width: typeof options.width == "string" || options.width > 0 ? options.width : $(input).width(), | |||
| top: offset.top + input.offsetHeight, | |||
| left: offset.left | |||
| }).show(); | |||
| if(options.scroll) { | |||
| list.scrollTop(0); | |||
| list.css({ | |||
| maxHeight: options.scrollHeight, | |||
| overflow: 'auto' | |||
| }); | |||
| if($.browser.msie && typeof document.body.style.maxHeight === "undefined") { | |||
| var listHeight = 0; | |||
| listItems.each(function() { | |||
| listHeight += this.offsetHeight; | |||
| }); | |||
| var scrollbarsVisible = listHeight > options.scrollHeight; | |||
| list.css('height', scrollbarsVisible ? options.scrollHeight : listHeight ); | |||
| if (!scrollbarsVisible) { | |||
| // IE doesn't recalculate width when scrollbar disappears | |||
| listItems.width( list.width() - parseInt(listItems.css("padding-left")) - parseInt(listItems.css("padding-right")) ); | |||
| } | |||
| } | |||
| } | |||
| }, | |||
| selected: function() { | |||
| var selected = listItems && listItems.filter("." + CLASSES.ACTIVE).removeClass(CLASSES.ACTIVE); | |||
| return selected && selected.length && $.data(selected[0], "ac_data"); | |||
| }, | |||
| emptyList: function (){ | |||
| list && list.empty(); | |||
| }, | |||
| unbind: function() { | |||
| element && element.remove(); | |||
| } | |||
| }; | |||
| }; | |||
| $.Autocompleter.Selection = function(field, start, end) { | |||
| if( field.createTextRange ){ | |||
| var selRange = field.createTextRange(); | |||
| selRange.collapse(true); | |||
| selRange.moveStart("character", start); | |||
| selRange.moveEnd("character", end); | |||
| selRange.select(); | |||
| } else if( field.setSelectionRange ){ | |||
| field.setSelectionRange(start, end); | |||
| } else { | |||
| if( field.selectionStart ){ | |||
| field.selectionStart = start; | |||
| field.selectionEnd = end; | |||
| } | |||
| } | |||
| field.focus(); | |||
| }; | |||
| })(jQuery); | |||
+ 70
- 0
solr_config/velocity/js/jquery.tx3-tag-cloud.js
View File
| @@ -0,0 +1,70 @@ | |||
| /* | |||
| * ---------------------------------------------------------------------------- | |||
| * "THE BEER-WARE LICENSE" (Revision 42): | |||
| * Tuxes3 wrote this file. As long as you retain this notice you | |||
| * can do whatever you want with this stuff. If we meet some day, and you think | |||
| * this stuff is worth it, you can buy me a beer in return Tuxes3 | |||
| * ---------------------------------------------------------------------------- | |||
| */ | |||
| (function($) | |||
| { | |||
| var settings; | |||
| $.fn.tx3TagCloud = function(options) | |||
| { | |||
| // | |||
| // DEFAULT SETTINGS | |||
| // | |||
| settings = $.extend({ | |||
| multiplier : 1 | |||
| }, options); | |||
| main(this); | |||
| } | |||
| function main(element) | |||
| { | |||
| // adding style attr | |||
| element.addClass("tx3-tag-cloud"); | |||
| addListElementFontSize(element); | |||
| } | |||
| /** | |||
| * calculates the font size on each li element | |||
| * according to their data-weight attribut | |||
| */ | |||
| function addListElementFontSize(element) | |||
| { | |||
| var hDataWeight = -9007199254740992; | |||
| var lDataWeight = 9007199254740992; | |||
| $.each(element.find("li"), function(){ | |||
| cDataWeight = getDataWeight(this); | |||
| if (cDataWeight == undefined) | |||
| { | |||
| logWarning("No \"data-weight\" attribut defined on <li> element"); | |||
| } | |||
| else | |||
| { | |||
| hDataWeight = cDataWeight > hDataWeight ? cDataWeight : hDataWeight; | |||
| lDataWeight = cDataWeight < lDataWeight ? cDataWeight : lDataWeight; | |||
| } | |||
| }); | |||
| $.each(element.find("li"), function(){ | |||
| var dataWeight = getDataWeight(this); | |||
| var percent = Math.abs((dataWeight - lDataWeight)/(lDataWeight - hDataWeight)); | |||
| $(this).css('font-size', (1 + (percent * settings['multiplier'])) + "em"); | |||
| }); | |||
| } | |||
| function getDataWeight(element) | |||
| { | |||
| return parseInt($(element).attr("data-weight")); | |||
| } | |||
| function logWarning(message) | |||
| { | |||
| console.log("[WARNING] " + Date.now() + " : " + message); | |||
| } | |||
| }(jQuery)); | |||
+ 42
- 0
solr_config/velocity/layout.vm
View File
| @@ -0,0 +1,42 @@ | |||
| <html> | |||
| <head> | |||
| #parse("head.vm") | |||
| </head> | |||
| <body> | |||
| <div id="header"> | |||
| <a href="#url_for_home"><img src="#{url_root}/img/solr.svg" id="logo" title="Solr"/></a> $resource.powered_file_search | |||
| </div> | |||
| <div id="header2" onclick="javascript:locale_select()"> | |||
| <ul class="menu"> | |||
| <li> | |||
| <a href="#"><img src="#{url_for_solr}/admin/file?file=/velocity/img/globe_256.png&contentType=image/png" id="locale_pic" title="locale_select" width="30px" height="27px"/></a> | |||
| <ul> | |||
| <li><a href="#url_for_locale('fr_FR')" #if("#current_locale"=="fr_FR")class="hidden"#end> | |||
| <img src="#{url_for_solr}/admin/file?file=/velocity/img/france_640.png&contentType=image/png" id="french_flag" width="40px" height="40px"/>Français</a></li> | |||
| <li><a href="#url_for_locale('de_DE')" #if("#current_locale"=="de_DE")class="hidden"#end> | |||
| <img src="#{url_for_solr}/admin/file?file=/velocity/img/germany_640.png&contentType=image/png" id="german_flag" width="40px" height="40px"/>Deutsch</a></li> | |||
| <li><a href="#url_for_locale('')" #if("#current_locale"=="")class="hidden"#end> | |||
| <img src="#{url_for_solr}/admin/file?file=/velocity/img/english_640.png&contentType=image/png" id="english_flag" width="40px" height="40px"/>English</a></li> | |||
| </ul> | |||
| </li> | |||
| </ul> | |||
| </div> | |||
| #if($response.response.error.code) | |||
| <div class="error"> | |||
| <h1>ERROR $response.response.error.code</h1> | |||
| $response.response.error.msg | |||
| </div> | |||
| #else | |||
| <div id="content"> | |||
| $content | |||
| </div> | |||
| #end | |||
| <div id="footer"> | |||
| #parse("footer.vm") | |||
| </div> | |||
| </body> | |||
| </html> | |||
+ 16
- 0
solr_config/velocity/macros.vm
View File
| @@ -0,0 +1,16 @@ | |||
| #macro(lensFilterSortOnly)?#if($response.responseHeader.params.getAll("fq").size() > 0)&#fqs($response.responseHeader.params.getAll("fq"))#end#sort($request.params.getParams('sort'))#end | |||
| #macro(lensNoQ)#lensFilterSortOnly&type=#current_type#if("#current_locale"!="")&locale=#current_locale#end#end | |||
| #macro(lensNoType)#lensFilterSortOnly#q#if("#current_locale"!="")&locale=#current_locale#end#end | |||
| #macro(lensNoLocale)#lensFilterSortOnly#q&type=#current_type#end | |||
| ## lens modified for example/files - to use fq from responseHeader rather than request, and #debug removed too as it is built into browse params now, also added type to lens | |||
| #macro(lens)#lensNoQ#q#end | |||
| ## Macros defined custom for the "files" example | |||
| #macro(url_for_type $type)#url_for_home#lensNoType&type=$type#end | |||
| #macro(current_type)#if($response.responseHeader.params.type)${response.responseHeader.params.type}#{else}all#end#end | |||
| #macro(url_for_locale $locale)#url_for_home#lensNoLocale#if($locale!="")&locale=$locale#end&start=$page.start#end | |||
| #macro(current_locale)$!{response.responseHeader.params.locale}#end | |||
| ## Usage: #label(resource_key[, default_value]) - resource_key is used as label if no default value specified and no resource exists | |||
| #macro(label $key $default)#if($resource.get($key).exists)${resource.get($key)}#else#if($default)$default#else${key}#end#end#end | |||
+ 68
- 0
solr_config/velocity/mime_type_lists.vm
View File
| @@ -0,0 +1,68 @@ | |||
| #** | |||
| * Define some Mime-Types, short and long form | |||
| *# | |||
| ## MimeType to extension map for detecting file type | |||
| ## and showing proper icon | |||
| ## List of types match the icons in /solr/img/filetypes | |||
| ## Short MimeType Names | |||
| ## Was called $supportedtypes | |||
| #set($supportedMimeTypes = "7z;ai;aiff;asc;audio;bin;bz2;c;cfc;cfm;chm;class;conf;cpp;cs;css;csv;deb;divx;doc;dot;eml;enc;file;gif;gz;hlp;htm;html;image;iso;jar;java;jpeg;jpg;js;lua;m;mm;mov;mp3;mpg;odc;odf;odg;odi;odp;ods;odt;ogg;pdf;pgp;php;pl;png;ppt;ps;py;ram;rar;rb;rm;rpm;rtf;sig;sql;swf;sxc;sxd;sxi;sxw;tar;tex;tgz;txt;vcf;video;vsd;wav;wma;wmv;xls;xml;xpi;xvid;zip") | |||
| ## Long Form: map MimeType headers to our Short names | |||
| ## Was called $extMap | |||
| #set( $mimeExtensionsMap = { | |||
| "application/x-7z-compressed": "7z", | |||
| "application/postscript": "ai", | |||
| "application/pgp-signature": "asc", | |||
| "application/octet-stream": "bin", | |||
| "application/x-bzip2": "bz2", | |||
| "text/x-c": "c", | |||
| "application/vnd.ms-htmlhelp": "chm", | |||
| "application/java-vm": "class", | |||
| "text/css": "css", | |||
| "text/csv": "csv", | |||
| "application/x-debian-package": "deb", | |||
| "application/msword": "doc", | |||
| "message/rfc822": "eml", | |||
| "image/gif": "gif", | |||
| "application/winhlp": "hlp", | |||
| "text/html": "html", | |||
| "application/java-archive": "jar", | |||
| "text/x-java-source": "java", | |||
| "image/jpeg": "jpeg", | |||
| "application/javascript": "js", | |||
| "application/vnd.oasis.opendocument.chart": "odc", | |||
| "application/vnd.oasis.opendocument.formula": "odf", | |||
| "application/vnd.oasis.opendocument.graphics": "odg", | |||
| "application/vnd.oasis.opendocument.image": "odi", | |||
| "application/vnd.oasis.opendocument.presentation": "odp", | |||
| "application/vnd.oasis.opendocument.spreadsheet": "ods", | |||
| "application/vnd.oasis.opendocument.text": "odt", | |||
| "application/pdf": "pdf", | |||
| "application/pgp-encrypted": "pgp", | |||
| "image/png": "png", | |||
| "application/vnd.ms-powerpoint": "ppt", | |||
| "audio/x-pn-realaudio": "ram", | |||
| "application/x-rar-compressed": "rar", | |||
| "application/vnd.rn-realmedia": "rm", | |||
| "application/rtf": "rtf", | |||
| "application/x-shockwave-flash": "swf", | |||
| "application/vnd.sun.xml.calc": "sxc", | |||
| "application/vnd.sun.xml.draw": "sxd", | |||
| "application/vnd.sun.xml.impress": "sxi", | |||
| "application/vnd.sun.xml.writer": "sxw", | |||
| "application/x-tar": "tar", | |||
| "application/x-tex": "tex", | |||
| "text/plain": "txt", | |||
| "text/x-vcard": "vcf", | |||
| "application/vnd.visio": "vsd", | |||
| "audio/x-wav": "wav", | |||
| "audio/x-ms-wma": "wma", | |||
| "video/x-ms-wmv": "wmv", | |||
| "application/vnd.ms-excel": "xls", | |||
| "application/xml": "xml", | |||
| "application/x-xpinstall": "xpi", | |||
| "application/zip": "zip" | |||
| }) | |||
+ 20
- 0
solr_config/velocity/results.vm
View File
| @@ -0,0 +1,20 @@ | |||
| <div id="facets"> | |||
| #parse("facets.vm") | |||
| </div> | |||
| <div id="results_list"> | |||
| <div class="pagination"> | |||
| <span class="results-found">$page.results_found</span> $resource.results_found_in.insert(${response.responseHeader.QTime}) | |||
| $resource.page_of.insert($page.current_page_number,$page.page_count) | |||
| </div> | |||
| #parse("results_list.vm") | |||
| <div class="pagination"> | |||
| #link_to_previous_page | |||
| <span class="results-found">$page.results_found</span> $resource.results_found. | |||
| $resource.page_of.insert($page.current_page_number,$page.page_count) | |||
| #link_to_next_page | |||
| </div> | |||
| </div> | |||
+ 21
- 0
solr_config/velocity/results_list.vm
View File
| @@ -0,0 +1,21 @@ | |||
| <ul id="tabs"> | |||
| <li><a href="#url_for_type('all')" #if("#current_type"=="all")class="selected"#end>$resource.type.all ($response.response.facet_counts.facet_queries.all_types)</a></li> | |||
| #foreach($type in $response.response.facet_counts.facet_fields.doc_type) | |||
| #if($type.key) | |||
| <li><a href="#url_for_type($type.key)" #if($type.value=="0")class="no_results"#end #if("#current_type"==$type.key)class="selected"#end> #label("type.${type.key}.label", $type.key) ($type.value)</a></li> | |||
| #else | |||
| #if($type.value > 0) | |||
| <li><a href="#url_for_type('unknown')" #if("#current_type"=="unknown")class="selected"#end>$resource.type.unknown ($type.value)</a></li> | |||
| #end | |||
| #end | |||
| #end | |||
| </ul> | |||
| <div id="results"> | |||
| #foreach($doc in $response.results) | |||
| #parse("hit.vm") | |||
| #end | |||
| </div> | |||
+ 144
- 0
solr_import.sh
View File
| @@ -0,0 +1,144 @@ | |||
| #!/bin/bash | |||
| # @name: solr_import.sh | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-03-11 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: Runs imports of files into Solr indexes | |||
| # @acknowledgements: | |||
| # https://www.redhat.com/sysadmin/arguments-options-bash-scripts | |||
| ############################################################ | |||
| # Subprograms # | |||
| ############################################################ | |||
| License() | |||
| { | |||
| echo 'Copyright 2022 Simon Bowie <ad7588@coventry.ac.uk>' | |||
| echo | |||
| echo 'Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:' | |||
| echo | |||
| echo 'The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.' | |||
| echo | |||
| echo 'THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.' | |||
| } | |||
| Help() | |||
| { | |||
| # Display Help | |||
| echo "This script performs Solr import functions for different cores." | |||
| echo | |||
| echo "Syntax: solr_import.sh [-l|h|z|a|e|i|m|p|x|d|s|w]" | |||
| echo "options:" | |||
| echo "l Print the MIT License notification." | |||
| echo "h Print this Help." | |||
| echo "z Index all." | |||
| echo "a Index ACTIVE folder." | |||
| echo "e Index EXPANDING folder." | |||
| echo "i Index INVISIBLE folder." | |||
| echo "m Index MULTI-SPECIES folder." | |||
| echo "p Index PISSING & LEAKING folder." | |||
| echo "x Index SECRET folder." | |||
| echo "d Index SELF-DEFENDING folder." | |||
| echo "s Index SURVIVING folder." | |||
| echo "w Index WORKING folder." | |||
| echo | |||
| } | |||
| Import() | |||
| { | |||
| docker exec -it solr bin/solr delete -c $core | |||
| docker exec -it solr solr create_core -c $core -d custom | |||
| #docker exec -ti --user=solr solr bash -c "cp -r /opt/solr/example/files/conf/* /var/solr/data/$core/conf/" | |||
| #docker restart solr | |||
| sleep 30 | |||
| docker run --rm -v "$directory/$location:/$core" --network=host solr:latest post -c $core /$core | |||
| } | |||
| Import_recursive() | |||
| { | |||
| docker run --rm -v "$directory/$subdirectory:/$core" --network=host solr:latest post -c $core /$core | |||
| } | |||
| ############################################################ | |||
| ############################################################ | |||
| # Main program # | |||
| ############################################################ | |||
| ############################################################ | |||
| # Set variables | |||
| directory="/Users/ad7588/projects/patent_site" | |||
| # Get the options | |||
| while getopts ":hlimzaespxdw" option; do | |||
| case $option in | |||
| l) # display License | |||
| License | |||
| exit;; | |||
| h) # display Help | |||
| Help | |||
| exit;; | |||
| z) # index all | |||
| core="all" | |||
| docker exec -it solr bin/solr delete -c $core | |||
| docker exec -it solr solr create_core -c $core -d custom | |||
| location="data/POP_Dataset_2022" | |||
| for subdirectory in $location/*/ | |||
| do | |||
| subdirectory=${subdirectory%*/} # remove the trailing "/" | |||
| Import_recursive | |||
| done | |||
| exit;; | |||
| a) # index ACTIVE folder | |||
| core="active" | |||
| location="data/pop_rtfs/ACTIVE (160)" | |||
| Import | |||
| exit;; | |||
| e) # index EXPANDING folder | |||
| core="expanding" | |||
| location="data/pop_rtfs/EXPANDING (169)" | |||
| Import | |||
| exit;; | |||
| i) # index INVISIBLE folder | |||
| core="invisible" | |||
| location="data/pop_rtfs/IN.VISIBLE (204)" | |||
| Import | |||
| exit;; | |||
| m) # index MULTI-SPECIES folder | |||
| core="multispecies" | |||
| location="data/pop_rtfs/MULTI-SPECIES (180)" | |||
| Import | |||
| exit;; | |||
| p) # index PISSING & LEAKING folder | |||
| core="pissing" | |||
| location="data/pop_rtfs/PISSING & LEAKING (168)" | |||
| Import | |||
| exit;; | |||
| x) # index SECRET folder | |||
| core="secret" | |||
| location="data/pop_rtfs/SECRET (92)" | |||
| Import | |||
| exit;; | |||
| d) # index SELF-DEFENDING folder | |||
| core="defending" | |||
| location="data/pop_rtfs/SELF-DEFENDING (115)" | |||
| Import | |||
| exit;; | |||
| s) # index SURVIVING folder | |||
| core="surviving" | |||
| location="data/pop_rtfs/SURVIVING (166)" | |||
| Import | |||
| exit;; | |||
| w) # index WORKING folder | |||
| core="working" | |||
| location="data/pop_rtfs/WORKING (101)" | |||
| Import | |||
| exit;; | |||
| \?) # Invalid option | |||
| echo "Error: Invalid option" | |||
| exit;; | |||
| esac | |||
| done | |||
+ 10
- 0
web/Dockerfile
View File
| @@ -0,0 +1,10 @@ | |||
| # syntax=docker/dockerfile:1 | |||
| FROM python:3.10.7-slim-buster | |||
| RUN apt-get update -y && apt-get install -y imagemagick | |||
| WORKDIR /code | |||
| COPY requirements.txt requirements.txt | |||
| RUN pip install -r requirements.txt | |||
| COPY . . | |||
| CMD ["python3", "-m", "flask", "run"] | |||
+ 34
- 0
web/app/__init__.py
View File
| @@ -0,0 +1,34 @@ | |||
| # @name: __init__.py | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: Initialises the app, SQLAlchemy, and configuration variables | |||
| # @acknowledgements: | |||
| # https://www.digitalocean.com/community/tutorials/how-to-add-authentication-to-your-app-with-flask-login | |||
| # Config stuff adapted from https://blog.miguelgrinberg.com/post/the-flask-mega-tutorial-part-iii-web-forms | |||
| from flask import Flask | |||
| from flask_moment import Moment | |||
| import os | |||
| # initiate Moment for datetime functions | |||
| moment = Moment() | |||
| def create_app(): | |||
| app = Flask(__name__) | |||
| moment.init_app(app) | |||
| # blueprint for main parts of app | |||
| from .main import main as main_blueprint | |||
| app.register_blueprint(main_blueprint) | |||
| # blueprint for search parts of app | |||
| from .search import search as search_blueprint | |||
| app.register_blueprint(search_blueprint) | |||
| # blueprint for random parts of app | |||
| from .random import random as random_blueprint | |||
| app.register_blueprint(random_blueprint) | |||
| return app | |||
+ 16
- 0
web/app/main.py
View File
| @@ -0,0 +1,16 @@ | |||
| # @name: main.py | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: Main route for index and other pages | |||
| # @acknowledgements: | |||
| # https://www.digitalocean.com/community/tutorials/how-to-add-authentication-to-your-app-with-flask-login | |||
| from flask import Blueprint, render_template | |||
| main = Blueprint('main', __name__) | |||
| # route for index page | |||
| @main.route('/') | |||
| def index(): | |||
| return render_template('index.html') | |||
+ 153
- 0
web/app/ops.py
View File
| @@ -0,0 +1,153 @@ | |||
| # @name: ops.py | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-09-08 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <simon.bowie.19@gmail.com> | |||
| # @purpose: Performs functions against the European Patent Office's Open Patent Services (OPS) API | |||
| # @acknowledgements: | |||
| # OPS documented at https://www.epo.org/searching-for-patents/data/web-services/ops.html | |||
| # OPS RESTful API specification at http://documents.epo.org/projects/babylon/eponet.nsf/0/F3ECDCC915C9BCD8C1258060003AA712/$File/ops_v3.2_documentation_-_version_1.3.18_en.pdf | |||
| # OPS API functions list at https://developers.epo.org/ops-v3-2/apis | |||
| import os | |||
| import requests | |||
| import base64 | |||
| from wand.image import Image | |||
| # get config variables from OS environment variables: set in env file passed through Docker Compose | |||
| ops_url = os.environ.get('OPS_URL') | |||
| ops_url_images = os.environ.get('OPS_URL_IMAGES') | |||
| consumer_key = os.environ.get('CONSUMER_KEY') | |||
| consumer_secret = os.environ.get('CONSUMER_SECRET') | |||
| def get_access_token(): | |||
| # OPS API credentials (details at http://documents.epo.org/projects/babylon/eponet.nsf/0/F3ECDCC915C9BCD8C1258060003AA712/$File/ops_v3.2_documentation_-_version_1.3.18_en.pdf) | |||
| endpoint_url = ops_url + '3.2/auth/accesstoken' | |||
| auth = consumer_key + ":" + consumer_secret | |||
| auth_bytes = auth.encode("ascii") | |||
| base64_bytes = base64.b64encode(auth_bytes) | |||
| base64_string = base64_bytes.decode("ascii") | |||
| # set up API call | |||
| headers = {"Authorization": "Basic " + base64_string, "Content-Type": "application/x-www-form-urlencoded"} | |||
| data = "grant_type=client_credentials" | |||
| # give back result | |||
| response = requests.post(endpoint_url, headers=headers, data=data) | |||
| if response.status_code == 200: | |||
| # turn the API response into useful Json | |||
| json = response.json() | |||
| access_token = json['access_token'] | |||
| return access_token | |||
| def get_publication_details(doc_ref): | |||
| access_token = get_access_token() | |||
| # OPS API credentials (details at http://documents.epo.org/projects/babylon/eponet.nsf/0/F3ECDCC915C9BCD8C1258060003AA712/$File/ops_v3.2_documentation_-_version_1.3.16_en.pdf) | |||
| endpoint_url = ops_url + 'rest-services/published-data/publication/docdb/' + doc_ref + '/biblio' | |||
| # set up API call | |||
| headers = {"Authorization": "Bearer " + access_token, "Accept": "application/json"} | |||
| # get result | |||
| response = requests.get(endpoint_url, headers=headers) | |||
| output = {} | |||
| if response.status_code == 200: | |||
| # turn the API response into useful Json | |||
| json = response.json() | |||
| # for each invention title, check if it's in the original language | |||
| try: | |||
| json['ops:world-patent-data']['exchange-documents']['exchange-document']['bibliographic-data']['invention-title'] | |||
| invention_titles = json['ops:world-patent-data']['exchange-documents']['exchange-document']['bibliographic-data']['invention-title'] | |||
| try: | |||
| invention_titles[1] | |||
| for invention_title in invention_titles: | |||
| if invention_title['@lang'] is not None and invention_title['@lang'] != 'en': | |||
| output['original_title'] = invention_title['$'] | |||
| except KeyError: | |||
| if invention_titles['@lang'] is not None and invention_titles['@lang'] != 'en': | |||
| output['original_title'] = invention_titles['$'] | |||
| except KeyError: | |||
| pass | |||
| # for each abstract, check if it's in the original language | |||
| try: | |||
| json['ops:world-patent-data']['exchange-documents']['exchange-document']['abstract'] | |||
| abstracts = json['ops:world-patent-data']['exchange-documents']['exchange-document']['abstract'] | |||
| try: | |||
| abstracts[1] | |||
| for abstract in abstracts: | |||
| if abstract['@lang'] is not None and abstract['@lang'] != 'en': | |||
| output['original_abstract'] = abstract['p']['$'] | |||
| except KeyError: | |||
| if abstracts['@lang'] is not None and abstracts['@lang'] != 'en': | |||
| output['original_abstract'] = abstracts['p']['$'] | |||
| except KeyError: | |||
| pass | |||
| return output | |||
| def get_images(doc_ref): | |||
| access_token = get_access_token() | |||
| # OPS API credentials (details at http://documents.epo.org/projects/babylon/eponet.nsf/0/F3ECDCC915C9BCD8C1258060003AA712/$File/ops_v3.2_documentation_-_version_1.3.16_en.pdf) | |||
| endpoint_url = ops_url + 'rest-services/published-data/publication/docdb/' + doc_ref + '/images' | |||
| # set up API call | |||
| headers = {"Authorization": "Bearer " + access_token, "Accept": "application/json"} | |||
| # give back result | |||
| response = requests.get(endpoint_url, headers=headers) | |||
| if response.status_code == 200: | |||
| output = {} | |||
| drawings_url = {} | |||
| # turn the API response into useful Json | |||
| json = response.json() | |||
| try: | |||
| json['ops:world-patent-data']['ops:document-inquiry']['ops:inquiry-result']['ops:document-instance'] | |||
| document_instances = json['ops:world-patent-data']['ops:document-inquiry']['ops:inquiry-result']['ops:document-instance'] | |||
| try: | |||
| document_instances[1] | |||
| for document_instance in document_instances: | |||
| if document_instance['@desc'] == 'Drawing': | |||
| drawings_url = ops_url_images + '3.2/rest-services/' + document_instance['@link'] + '?Range=1' | |||
| if drawings_url is None: | |||
| for document_instance in document_instances: | |||
| if document_instance['@desc'] == 'FullDocument': | |||
| drawings_url = ops_url_images + '3.2/rest-services/' + document_instance['@link'] + '?Range=1' | |||
| except KeyError: | |||
| pass | |||
| if drawings_url is not None: | |||
| # set up API call | |||
| headers = {"Authorization": "Bearer " + access_token, "Accept": "application/tiff"} | |||
| # give back result | |||
| response = requests.get(drawings_url, headers=headers) | |||
| if response.status_code == 200: | |||
| with Image(blob = response.content) as image: | |||
| png_blob = image.make_blob('png') | |||
| base64_bytes = base64.b64encode(png_blob) | |||
| output['image'] = base64_bytes.decode("ascii") | |||
| except KeyError: | |||
| pass | |||
| else: | |||
| output = False | |||
| return output | |||
+ 62
- 0
web/app/random.py
View File
| @@ -0,0 +1,62 @@ | |||
| # @name: random.py | |||
| # @creation_date: 2022-09-09 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: random route for random | |||
| # @acknowledgements: | |||
| from flask import Blueprint, render_template, request | |||
| from . import solr | |||
| from . import ops | |||
| random = Blueprint('random', __name__) | |||
| # route for random page | |||
| @random.route('/random/') | |||
| def random_record(): | |||
| core = 'all' | |||
| results = solr.get_random_record(core) | |||
| for result in results: | |||
| publication_details = ops.get_publication_details(result['doc_ref']) | |||
| result.update(publication_details) | |||
| if ops.get_images(result['doc_ref']): | |||
| image = ops.get_images(result['doc_ref']) | |||
| result.update(image) | |||
| return render_template('record.html', results=results) | |||
| # route for comparing two random records | |||
| @random.route('/random/two/') | |||
| def two_random_records(): | |||
| core = 'all' | |||
| results_list = [] | |||
| i = 0 | |||
| while i <= 1: | |||
| results = solr.get_random_record(core) | |||
| for result in results: | |||
| publication_details = ops.get_publication_details(result['doc_ref']) | |||
| result.update(publication_details) | |||
| if ops.get_images(result['doc_ref']): | |||
| image = ops.get_images(result['doc_ref']) | |||
| result.update(image) | |||
| results_list.append(result) | |||
| i += 1 | |||
| return render_template('compare.html', results=results_list) | |||
| # route for getting ten random titles | |||
| @random.route('/random/titles/') | |||
| def ten_random_titles(): | |||
| titles = solr.get_ten_random_elements('title') | |||
| additional_titles = solr.get_ten_random_elements('title') | |||
| return render_template('titles.html', titles=titles, additional_titles=additional_titles) | |||
| # route for getting ten random abstracts | |||
| @random.route('/random/abstracts/') | |||
| def ten_random_abstracts(): | |||
| abstracts = solr.get_ten_random_elements('abstract') | |||
| return render_template('abstracts.html', abstracts=abstracts) | |||
| # route for getting ten random images | |||
| @random.route('/random/images/') | |||
| def ten_random_images(): | |||
| results = solr.get_ten_random_images() | |||
| return render_template('images.html', results=results) | |||
+ 51
- 0
web/app/search.py
View File
| @@ -0,0 +1,51 @@ | |||
| # @name: search.py | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: search route for search | |||
| # @acknowledgements: | |||
| # https://www.digitalocean.com/community/tutorials/how-to-add-authentication-to-your-app-with-flask-login | |||
| from flask import Blueprint, render_template, request | |||
| from . import solr | |||
| from . import ops | |||
| search = Blueprint('search', __name__) | |||
| # route for search page | |||
| @search.route('/search/', methods=['POST']) | |||
| def basic_search(): | |||
| search = request.form.get('search') | |||
| if request.form.get('core') is not None: | |||
| core = request.form.get('core') | |||
| else: | |||
| core = 'all' | |||
| if request.form.get('sort') is not None: | |||
| sort = request.form.get('sort') | |||
| else: | |||
| sort = 'relevance' | |||
| results = solr.solr_search(core, sort, search) | |||
| return render_template('search.html', results=results, search=search, core=core, sort=sort) | |||
| # route for id_search page | |||
| @search.route('/search/id/') | |||
| def id_search(): | |||
| if request.args.get('core') is not None: | |||
| core = request.args.get('core') | |||
| else: | |||
| core = 'all' | |||
| if request.args.get('sort') is not None: | |||
| sort = request.args.get('sort') | |||
| else: | |||
| sort = 'relevance' | |||
| id = request.args.get('id') | |||
| results = solr.solr_search(core, sort, search, id) | |||
| for result in results: | |||
| publication_details = ops.get_publication_details(result['doc_ref']) | |||
| result.update(publication_details) | |||
| if ops.get_images(result['doc_ref']): | |||
| image = ops.get_images(result['doc_ref']) | |||
| result.update(image) | |||
| return render_template('record.html', results=results) | |||
+ 145
- 0
web/app/solr.py
View File
| @@ -0,0 +1,145 @@ | |||
| # @name: solr.py | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <simon.bowie.19@gmail.com> | |||
| # @purpose: Performs Solr functions | |||
| # @acknowledgements: | |||
| import os | |||
| import requests | |||
| import re | |||
| import urllib | |||
| import random | |||
| from . import ops | |||
| # get config variables from OS environment variables: set in env file passed through Docker Compose | |||
| solr_hostname = os.environ.get('SOLR_HOSTNAME') | |||
| solr_port = os.environ.get('SOLR_PORT') | |||
| def solr_search(core, sort, search=None, id=None): | |||
| # Assemble a query string to send to Solr. This uses the Solr hostname from config.env. Solr's query syntax can be found at many sites including https://lucene.apache.org/solr/guide/6_6/the-standard-query-parser.html | |||
| if id is not None: | |||
| solrurl = 'http://' + solr_hostname + ':' + solr_port + '/solr/' + core + '/select?q.op=OR&q=id%3A"' + id + '"&wt=json' | |||
| else: | |||
| if (sort == 'relevance'): | |||
| solrurl = 'http://' + solr_hostname + ':' + solr_port + '/solr/' + core + '/select?q.op=OR&q=content%3A' + urllib.parse.quote_plus(search) + '&wt=json' | |||
| else: | |||
| solrurl = 'http://' + solr_hostname + ':' + solr_port + '/solr/' + core + '/select?q.op=OR&q=content%3A' + urllib.parse.quote_plus(search) + '&wt=json&sort=' + sort | |||
| # get result | |||
| request = requests.get(solrurl) | |||
| # turn the API response into useful Json | |||
| json = request.json() | |||
| if (json['response']['numFound'] == 0): | |||
| output = 'no results found' | |||
| else: | |||
| output = [] | |||
| for result in json['response']['docs']: | |||
| # set ID variable | |||
| id = result['id'] | |||
| # set content variable | |||
| content = result['content'] | |||
| # parse result | |||
| result_output = parse_result(id, content) | |||
| output.append(result_output) | |||
| return output | |||
| def parse_result(id, input): | |||
| output = {} | |||
| output['id'] = id | |||
| # set document reference number (used for OPS API) | |||
| doc_ref = re.search('=D\s(([^\s]*)\s([^\s]*)\s([^\s]*))', input) | |||
| if doc_ref is None: | |||
| doc_ref = re.search('=D&locale=en_EP\s(([^\s]*)\s([^\s]*)\s([^\s]*))', input) | |||
| output['doc_ref'] = doc_ref.group(1).replace(" ","") | |||
| else: | |||
| output['doc_ref'] = doc_ref.group(1).replace(" ","") | |||
| # search for the application ID in the content element and display it | |||
| application_id = re.search('Application.*\n(.*)\n', input) | |||
| output['application_id'] = application_id.group(1) | |||
| # search for the EPO publication URL in the content element and display it | |||
| epo_publication = re.search('Publication.*\n(.*)\n', input) | |||
| output['epo_publication_url'] = epo_publication.group(1) | |||
| # search for the IPC publication URL in the content element and display it | |||
| ipc_publication = re.search('IPC.*\n(.*)\n', input) | |||
| output['ipc_publication_url'] = ipc_publication.group(1) | |||
| # search for the title in the content element and display it | |||
| title = re.search('Title.*\n(.*)\n', input) | |||
| if title is not None: | |||
| output['title'] = title.group(1) | |||
| # search for the abstract in the content element and display it | |||
| abstract = re.search('Abstract.*\n(.*)\n', input) | |||
| if abstract is None: | |||
| abstract = re.search('\(.\) \\n\\n(.*)\\n', input) | |||
| if abstract is not None: | |||
| output['abstract'] = abstract.group(1); | |||
| # search for the year in the content element and display it | |||
| year = re.search('=D[^\s]*\s[^\s]*\s[^\s]*\s[^\s]*\s(\d{4})', input) | |||
| if year is not None: | |||
| output['year'] = year.group(1) | |||
| return output | |||
| def get_random_record(core): | |||
| rand = str(random.randint(0, 9999999)) | |||
| # Assemble a query string to send to Solr. This uses the Solr hostname from config.env. Solr's query syntax can be found at many sites including https://lucene.apache.org/solr/guide/6_6/the-standard-query-parser.html | |||
| solrurl = 'http://' + solr_hostname + ':' + solr_port + '/solr/' + core + '/select?q.op=OR&q=*%3A*&wt=json&sort=random_' + rand + '%20asc&rows=1' | |||
| # get result | |||
| request = requests.get(solrurl) | |||
| # turn the API response into useful Json | |||
| json = request.json() | |||
| if (json['response']['numFound'] == 0): | |||
| output = 'no results found' | |||
| else: | |||
| output = [] | |||
| for result in json['response']['docs']: | |||
| # set ID variables | |||
| id = result['id'] | |||
| # set content variable | |||
| content = result['content'] | |||
| # parse result | |||
| result_output = parse_result(id, content) | |||
| output.append(result_output) | |||
| return output | |||
| def get_ten_random_elements(field): | |||
| core = 'all' | |||
| output = [] | |||
| i = 0 | |||
| while i <= 9: | |||
| results = get_random_record(core) | |||
| for result in results: | |||
| if field in result: | |||
| dict = {'id': result['id'], field: result[field]} | |||
| output.append(dict) | |||
| i += 1 | |||
| return output | |||
| def get_ten_random_images(): | |||
| core = 'all' | |||
| output = [] | |||
| i = 0 | |||
| while i <= 9: | |||
| results = get_random_record(core) | |||
| for result in results: | |||
| if ops.get_images(result['doc_ref']): | |||
| image = ops.get_images(result['doc_ref']) | |||
| result.update(image) | |||
| output.append(result) | |||
| i += 1 | |||
| return output | |||
+ 9
- 0
web/app/static/js/main.js
View File
| @@ -0,0 +1,9 @@ | |||
| /* | |||
| # @name: main.js | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: JavaScript functions for various functions | |||
| # @acknowledgements: | |||
| */ | |||
+ 10
- 0
web/app/static/styles/custom.css
View File
| @@ -0,0 +1,10 @@ | |||
| /* | |||
| # @name: custom.css | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: Custom CSS to override Bootstrap 5 defaults | |||
| # @acknowledgements: | |||
| # Bootstrap 5.1.3: https://getbootstrap.com/ | |||
| */ | |||
+ 15
- 0
web/app/templates/abstracts.html
View File
| @@ -0,0 +1,15 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| {% for abstract in abstracts %} | |||
| {{ abstract['abstract'] }} | |||
| <br><br> | |||
| <hr> | |||
| {% endfor %} | |||
| {% endblock %} | |||
+ 51
- 0
web/app/templates/base.html
View File
| @@ -0,0 +1,51 @@ | |||
| <!-- | |||
| # @name: base.html | |||
| # @version: 0.1 | |||
| # @creation_date: 2022-09-07 | |||
| # @license: The MIT License <https://opensource.org/licenses/MIT> | |||
| # @author: Simon Bowie <ad7588@coventry.ac.uk> | |||
| # @purpose: Basic layout for all pages | |||
| # @acknowledgements: | |||
| # https://www.digitalocean.com/community/tutorials/how-to-make-a-web-application-using-flask-in-python-3 | |||
| # Bootstrap 5.1.3: https://getbootstrap.com/ | |||
| # Flask-Moment: https://flask-moment.readthedocs.io/en/latest/ | |||
| # Boostrap select: https://stackoverflow.com/questions/67942546/bootstrap-5-select-dropdown-with-the-multiple-attribute-collapsed | |||
| --> | |||
| <!DOCTYPE html> | |||
| <html> | |||
| <head> | |||
| <title>Performing Patents Otherwise: Archival conversations with 320.000 clothing inventions</title> | |||
| <meta charset="utf-8"> | |||
| <meta http-equiv="X-UA-Compatible" content="IE=edge"> | |||
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |||
| <!-- Bootstrap CSS --> | |||
| <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-1BmE4kWBq78iYhFldvKuhfTAU6auU8tT94WrHftjDbrCEXSU1oBoqyl2QvZ6jIW3" crossorigin="anonymous"> | |||
| <link href="{{ url_for('static',filename='styles/custom.css') }}" rel="stylesheet"> | |||
| <!-- JavaScript --> | |||
| <script src="https://code.jquery.com/jquery-3.6.0.js" integrity="sha256-H+K7U5CnXl1h5ywQfKtSj8PCmoN9aaq30gDh27Xc0jk=" crossorigin="anonymous"></script> | |||
| <script src="{{ url_for('static',filename='js/main.js') }}"></script> | |||
| <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/js/bootstrap.bundle.min.js" integrity="sha384-ka7Sk0Gln4gmtz2MlQnikT1wXgYsOg+OMhuP+IlRH9sENBO0LRn5q+8nbTov4+1p" crossorigin="anonymous"></script> | |||
| </head> | |||
| <body class="d-flex flex-column min-vh-100"> | |||
| <main class="flex-shrink-0"> | |||
| <div class="container-fluid p-5 my-5 border"> | |||
| {% block content %} | |||
| {% endblock %} | |||
| </div> | |||
| </main> | |||
| <footer class="footer py-3 mt-auto bg-light"> | |||
| <div class="container"> | |||
| <span class="text-muted">Data from the <a href="https://www.epo.org/">European Patent Office's</a> <a href="https://worldwide.espacenet.com/">Espacenet patent search engine</a> and reconfigured by Goldsmiths, University of London's Archival Conversations project.</span> | |||
| </div> | |||
| </footer> | |||
| </body> | |||
| </html> | |||
+ 71
- 0
web/app/templates/compare.html
View File
| @@ -0,0 +1,71 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| <div class="row"> | |||
| {% for result in results %} | |||
| <div class="col-6 text-center"> | |||
| Application ID: | |||
| <a href="/search/id?id={{ result['id'] }}&core=all"> | |||
| {{ result['application_id'] }} | |||
| </a> | |||
| <br><br> | |||
| Year: | |||
| {{ result['year'] }} | |||
| <br><br> | |||
| EPO publication: | |||
| <a href="{{ result['epo_publication_url'] }}"> | |||
| {{ result['epo_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| IPC publication: | |||
| <a href="{{ result['ipc_publication_url'] }}"> | |||
| {{ result['ipc_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| {% if result['title'] is defined %} | |||
| Title: | |||
| {{ result['title'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['original_title'] is defined %} | |||
| Original language title: | |||
| {{ result['original_title'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['abstract'] is defined %} | |||
| Abstract: | |||
| {{ result['abstract'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['original_abstract'] is defined %} | |||
| Original language abstract: | |||
| {{ result['original_abstract'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['image'] is defined %} | |||
| <img class="img-fluid" src="data:image/jpg;base64,{{ result['image'] }}" alt="Drawing of patent" />' | |||
| {% endif %} | |||
| </div> | |||
| {% endfor %} | |||
| </div> | |||
| {% endblock %} | |||
+ 11
- 0
web/app/templates/images.html
View File
| @@ -0,0 +1,11 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| {% for result in results %} | |||
| <img class="img-fluid" src="data:image/jpg;base64,{{ result['image'] }}" alt="Drawing accompanying patent for{{ result['title'] }}" />' | |||
| {% endfor %} | |||
| {% endblock %} | |||
+ 46
- 0
web/app/templates/index.html
View File
| @@ -0,0 +1,46 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| <div class="row"> | |||
| <div class="col text-center"> | |||
| <p class="h1">Performing Patents Otherwise</p> | |||
| <p class="h2">Archival conversations with 320,000 clothing inventions</p> | |||
| </div> | |||
| </div> | |||
| <div class="row justify-content-center p-3"> | |||
| <div class="col-sm-6 text-center"> | |||
| <form action="/search" method="POST"> | |||
| <input type="text" name="search" placeholder="search for a patent record"> | |||
| <input type="submit" id="submit" value="search"> | |||
| </form> | |||
| </div> | |||
| </div> | |||
| <div class="row p-3"> | |||
| <div class="col text-center"> | |||
| <a href="/random">show a random record</a> | |||
| </div> | |||
| <div class="col text-center"> | |||
| <a href="/random/two">compare two random records</a> | |||
| </div> | |||
| </div> | |||
| <div class="row p-3"> | |||
| <div class="col text-center"> | |||
| <a href="/random/titles">ten random titles</a> | |||
| </div> | |||
| <div class="col text-center"> | |||
| <a href="/random/abstracts">ten random abstracts</a> | |||
| </div> | |||
| <div class="col text-center"> | |||
| <a href="/random/images">ten random images (takes a long time to load)</a> | |||
| </div> | |||
| </div> | |||
| {% endblock %} | |||
+ 69
- 0
web/app/templates/record.html
View File
| @@ -0,0 +1,69 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| {% for result in results %} | |||
| <div id="result"> | |||
| Application ID: | |||
| <a href="/search/id?id={{ result['id'] }}&core=all"> | |||
| {{ result['application_id'] }} | |||
| </a> | |||
| <br><br> | |||
| Year: | |||
| {{ result['year'] }} | |||
| <br><br> | |||
| EPO publication: | |||
| <a href="{{ result['epo_publication_url'] }}"> | |||
| {{ result['epo_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| IPC publication: | |||
| <a href="{{ result['ipc_publication_url'] }}"> | |||
| {{ result['ipc_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| {% if result['title'] is defined %} | |||
| Title: | |||
| {{ result['title'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['original_title'] is defined %} | |||
| Original language title: | |||
| {{ result['original_title'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['abstract'] is defined %} | |||
| Abstract: | |||
| {{ result['abstract'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['original_abstract'] is defined %} | |||
| Original language abstract: | |||
| {{ result['original_abstract'] }} | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['image'] is defined %} | |||
| <img class="img-fluid" src="data:image/jpg;base64,{{ result['image'] }}" alt="Drawing of patent" />' | |||
| {% endif %} | |||
| </div> | |||
| {% endfor %} | |||
| {% endblock %} | |||
+ 95
- 0
web/app/templates/search.html
View File
| @@ -0,0 +1,95 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| <div class="row p-3"> | |||
| <form action="/search" method="POST"> | |||
| <input type="hidden" name="search" value="{{ search }}"> | |||
| <input type="hidden" name="searchopt" value="{{ core }}"> | |||
| sort by: | |||
| <select name="sort" id="sort" onchange="this.form.submit()"> | |||
| <option value="relevance" {% if sort == 'relevance' %} selected {% endif %}>relevance</option> | |||
| <option value="year desc" {% if sort == 'year desc' %} selected {% endif %}>year descending</option> | |||
| <option value="year asc" {% if sort == 'year asc' %} selected {% endif %}>year ascending</option> | |||
| </select> | |||
| <noscript> | |||
| <input type="submit" class="btn btn-default" value="Set" /> | |||
| </noscript> | |||
| </form> | |||
| </div> | |||
| {% if results == 'no results found' %} | |||
| {{ results }} | |||
| {% else %} | |||
| {% for result in results %} | |||
| Application ID: | |||
| <a href="/search/id?id={{ result['id'] }}&core=all"> | |||
| <span class="result-entry"> | |||
| {{ result['application_id'] }} | |||
| </span> | |||
| </a> | |||
| <br><br> | |||
| Year: | |||
| {{ result['year'] }} | |||
| <br><br> | |||
| EPO publication: | |||
| <a href="{{ result['epo_publication_url'] }}"> | |||
| {{ result['epo_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| IPC publication: | |||
| <a href="{{ result['ipc_publication_url'] }}"> | |||
| {{ result['ipc_publication_url'] }} | |||
| </a> | |||
| <br><br> | |||
| {% if result['title'] is defined %} | |||
| Title: | |||
| <span class="result-entry"> | |||
| {{ result['title'] }} | |||
| </span> | |||
| <br><br> | |||
| {% endif %} | |||
| {% if result['abstract'] is defined %} | |||
| Abstract: | |||
| <span class="result-entry"> | |||
| {{ result['abstract'] }} | |||
| </span> | |||
| <br><br> | |||
| {% endif %} | |||
| <hr> | |||
| {% endfor %} | |||
| {% endif %} | |||
| <script> | |||
| let search_string = "{{ search }}"; | |||
| const search_array = search_string.split(" "); | |||
| for (const term of search_array){ | |||
| $("span[class=result-entry]:contains('" + term + "')").html(function(_, html) { | |||
| var replace = "(" + term + ")"; | |||
| var re = new RegExp(replace, "g"); | |||
| return html.replace(re, '<span style="color:orange">$1</span>'); | |||
| }); | |||
| } | |||
| </script> | |||
| {% endblock %} | |||
+ 42
- 0
web/app/templates/titles.html
View File
| @@ -0,0 +1,42 @@ | |||
| {% extends "base.html" %} | |||
| {% block content %} | |||
| <button class="float-end btn btn-danger" onclick="removeRandomTitle()">-</button> | |||
| <button class="float-end btn btn-danger" onclick="addRandomTitle()">+</button> | |||
| {% for title in titles %} | |||
| <span class="title"> | |||
| <a href="/search/id?id={{ title['id'] }}&core=all"> | |||
| {{ title['title'] }} | |||
| </a> | |||
| </span> | |||
| <br><br> | |||
| <hr> | |||
| {% endfor %} | |||
| <script> | |||
| var titles = {{ additional_titles|tojson }}; | |||
| x = 0; | |||
| function addRandomTitle(){ | |||
| var record_array = titles[x]; | |||
| document.querySelector('.container-fluid').innerHTML += "<a href='/search/id?id=" + record_array['id'] + "&core=all'><span class='title'>" + record_array['title'] + "</span></a><br><br><hr>"; | |||
| x++; | |||
| } | |||
| function removeRandomTitle() { | |||
| var elts = document.getElementsByClassName("title"); | |||
| var RandomSpan = elts[Math.floor(Math.random() * elts.length)]; | |||
| var TextReplacement = RandomSpan.textContent.replace(/\w/g,"-"); | |||
| RandomSpan.removeAttribute("href"); | |||
| RandomSpan.innerHTML = TextReplacement; | |||
| } | |||
| </script> | |||
| {% endblock %} | |||
+ 23
- 0
web/content/about.md
View File
| @@ -0,0 +1,23 @@ | |||
| Version 0.1 of the Experimental Publishing Compendium was edited by members of COPIM’s experimental publishing group formally known as Work Package Six. Since then a great many contributors, from tool and technology makers to authors, designers and publishers have contributed, slowly transforming the Compendium from an edited volume to a collective resource. | |||
| The Compendium is © 2022–2022 [COPIM](https://copim.ac.uk) and licensed under a [Creative Commons Attribution 4.0 International License (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/) to make it open for reuse and disappropriation. | |||
| ... List all contributors.... | |||
| The Compendium is designed to be periodically updated, growing with the practices it aims to catalogue and support. Keeping the Compendium updated takes labour, care and attention and like any processual book it will die at some point. Currently, the Compendium is hosted by the Centre for Postdigital Cultures, Coventry University and is version 0.1. | |||
| ## Preface | |||
| We — the editors of this compendium — do not wish to impose one version of experimental publishing, yet we recognise that a collection such as this is necessarily biased and thus political. In this preface to the first version, we are sharing how this particular version of the compendium came about, in the hope that this will open the compendium for amendments by those who maintain and use it. | |||
| The COPIM experimental publishing group, formerly known as work package six, worked for three-and-a-half-years on experimental publishing, in the context of the largely Anglo-American Community-led Open Publication Infrastructures for Monographs Project, COPIM. At a time when commercial consolidation threatened to monopolise the emerging scholarly Open Access publishing landscape, COPIM gathered publishers, libraries and infrastructure providers to develop community-owned infrastructure that can support small and large players. Open infrastructure, we proposed as an alternative to proprietary platforms that extract value and control access. Under the banner of scaling small, COPIM worked towards a diverse publishing landscape characterised by community ownership, collective production and governance, scholar-led publishing, and the sharing of resources and open infrastructures amongst diverse institutions. COPIM’s work packages were largely dedicated to serious infrastructure building, with the exception of the experimental publishing group, which grants the question how experimental publishing contributes to the ambition to establish infrastructures that allow diverse small initiatives to proliferate at scale? | |||
| The closely related metaphors of publishing landscape, ecology, ecosystems or bibliodiversity shaped COPIM’s work. Staying with these images of lively and abundant interdependence allows us to locate experimental publishing’s place in scholarly knowledge production. Speaking of publishing ecologies implies that scholarly publishing cannot be separated from the wider academic landscape. How scholarly work is published cannot be separated from how it is funded, conceptualised, written, valued, reviewed, rewarded, read and taught. In this metaphor, scholarly works, like all specimen, coevolve with the environment they inhabit. | |||
| Many things can be said about this environment: the contemporary academy. There isn’t one academy for starters. Opinions and politics differ, so do the stakes and subject position of the beholders. | |||
| We, invested in feminist techno-politics, yearn for more collective, inclusive, embodied, situated and caring modes of knowledge production. But the notion that changes in publishing affect the entire scholarly landscape applies just as neatly to those, for example, who pursue scholarly excellence through competition and streamlining. Our point here, is that scholarly publishing ecologies reflect and materialise the wider scholarly landscape. Scholarly books, in this ecological view, are not containers of knowledge but relational nodes that materialise what does and doesn’t count as valuable practices, sites, labour, and subjects of knowledge. | |||
| The flow of water is commonly used to model the flow of knowledge, taking us further into the question which forces shape the metaphorical scholarly landscape. Bureaucratic fantasies, enshrined in grant applications, project timetables and scholarly self-understanding and career paths imagine scholarly publishing at the end of an orderly pipeline of knowledge. The way that institutions such as libraries, universities, publishers, funders, and intellectual property regimes are organised tends to reinforce the notion of a manageable flow from funding, to research question, to investigation to publication to evaluation. The metaphor of channeled flow and the premises of contained stages provides structure. Channeling the flow of valuable knowledge, gives publishing a place and a form: the book, at the end of the pipe. But… you see it coming… where there are pipes there is , breakage, spillage and blockage. And… without overflow and contamination… there won’t be much to be piped. A sanitised scholarly landscape of industrial pipage is a nightmare, that evokes the very real nightmare streamlined industrial production has brought upon very real ecologies—leaving but scraplands for diversity which alone can ensure life. And... also… despite all efforts to establish well irrigated, drip-fed academies, the flow of scholarly knowledge is not easily channeled. Swamps, oceans, ice shields, underground currents, floods and drought prone rivers evoke alternative models of flow, that might inspire a diverse knowledge-scape that cannot be contained within the academy or otherwise. | |||
| Coming back to experimental publishing, new forms of publication might create new kinds of pipes or spill-over into more relational circulation. Either way, we posit that experimental publishing is one of the sites where the shape of scholarly landscapes, and their relationship to other ecologies of knowledge and power is negotiated and materialised in practice. How we do publish matters. Experimenting with scholarly books is to experiment with scholarly modes of knowledge production. This labour of love, like other experimental practice, takes place at the growing edges and in the cracks of established practices, where by steady corrosion, underground commotion or capital intense incubation forms of writing, making, sharing, reviewing, discovering, reading and cataloging books come into being that will change what counts as scholarly work. | |||
+ 15
- 0
web/content/home.md
View File
| @@ -0,0 +1,15 @@ | |||
| # ExPub Compendium | |||
| The Experimental Publishing Compendium is for authors, designers, publishers, institutions and technologist who challenge, push and redefine the shape, form and rationale of scholarly works. The compendium offers a catalogues of tools, practices, publishers, and books to inspire experimental scholarly works. | |||
| ## How to use the compendium | |||
| The compendium catalogues potential ingredients for the making of experimental publications. | |||
| - Under [Tools](/tools) you’ll find mostly software that supports experimental publication from collective writing to the annotation and remix of published texts. | |||
| - [Practices](/practices) provide inspiration for experimental book making. | |||
| - [Books](/books) and [publishers](/publishers) provides examples of experimental books and those who publish them. | |||
| Each item is cross linked so that a practice will take you to relevant tools or examples and vice versa. | |||
| The selection is tentative, reflecting the knowledge and biases of the contributors of current and previous versions. If you want to submit or edit anything in the catalogue please do so by doing XXthisXXX. | |||
+ 6
- 0
web/requirements.txt
View File
| @@ -0,0 +1,6 @@ | |||
| flask | |||
| flask-moment | |||
| gunicorn | |||
| markdown | |||
| requests | |||
| Wand | |||
Loading…