You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by eh...@apache.org on 2020/09/04 01:11:32 UTC
[lucene-solr] 07/10: Remove velocity-centric example/files
This is an automated email from the ASF dual-hosted git repository.
ehatcher pushed a commit to branch jira/solr-14792
in repository https://gitbox.apache.org/repos/asf/lucene-solr.git
commit 69d2d7a30b5adbf7c6cedf0cd0e40692e12c67aa
Author: Erik Hatcher <er...@lucidworks.com>
AuthorDate: Thu Sep 3 20:41:10 2020 -0400
Remove velocity-centric example/files
---
solr/example/files/README.md | 167 ---
.../browse-resources/velocity/resources.properties | 82 --
.../velocity/resources_de_DE.properties | 18 -
.../velocity/resources_fr_FR.properties | 20 -
solr/example/files/conf/currency.xml | 67 -
solr/example/files/conf/elevate.xml | 42 -
solr/example/files/conf/email_url_types.txt | 2 -
solr/example/files/conf/lang/contractions_ca.txt | 8 -
solr/example/files/conf/lang/contractions_fr.txt | 15 -
solr/example/files/conf/lang/contractions_ga.txt | 5 -
solr/example/files/conf/lang/contractions_it.txt | 23 -
solr/example/files/conf/lang/hyphenations_ga.txt | 5 -
solr/example/files/conf/lang/stemdict_nl.txt | 6 -
solr/example/files/conf/lang/stoptags_ja.txt | 420 ------
solr/example/files/conf/lang/stopwords_ar.txt | 125 --
solr/example/files/conf/lang/stopwords_bg.txt | 193 ---
solr/example/files/conf/lang/stopwords_ca.txt | 220 ---
solr/example/files/conf/lang/stopwords_cz.txt | 172 ---
solr/example/files/conf/lang/stopwords_da.txt | 110 --
solr/example/files/conf/lang/stopwords_de.txt | 294 ----
solr/example/files/conf/lang/stopwords_el.txt | 78 --
solr/example/files/conf/lang/stopwords_en.txt | 54 -
solr/example/files/conf/lang/stopwords_es.txt | 356 -----
solr/example/files/conf/lang/stopwords_eu.txt | 99 --
solr/example/files/conf/lang/stopwords_fa.txt | 313 -----
solr/example/files/conf/lang/stopwords_fi.txt | 97 --
solr/example/files/conf/lang/stopwords_fr.txt | 186 ---
solr/example/files/conf/lang/stopwords_ga.txt | 110 --
solr/example/files/conf/lang/stopwords_gl.txt | 161 ---
solr/example/files/conf/lang/stopwords_hi.txt | 235 ----
solr/example/files/conf/lang/stopwords_hu.txt | 211 ---
solr/example/files/conf/lang/stopwords_hy.txt | 46 -
solr/example/files/conf/lang/stopwords_id.txt | 359 -----
solr/example/files/conf/lang/stopwords_it.txt | 303 -----
solr/example/files/conf/lang/stopwords_ja.txt | 127 --
solr/example/files/conf/lang/stopwords_lv.txt | 172 ---
solr/example/files/conf/lang/stopwords_nl.txt | 119 --
solr/example/files/conf/lang/stopwords_no.txt | 194 ---
solr/example/files/conf/lang/stopwords_pt.txt | 253 ----
solr/example/files/conf/lang/stopwords_ro.txt | 233 ----
solr/example/files/conf/lang/stopwords_ru.txt | 243 ----
solr/example/files/conf/lang/stopwords_sv.txt | 133 --
solr/example/files/conf/lang/stopwords_th.txt | 119 --
solr/example/files/conf/lang/stopwords_tr.txt | 212 ---
solr/example/files/conf/lang/userdict_ja.txt | 29 -
solr/example/files/conf/managed-schema | 520 -------
solr/example/files/conf/params.json | 34 -
solr/example/files/conf/protwords.txt | 21 -
solr/example/files/conf/solrconfig.xml | 1423 --------------------
solr/example/files/conf/stopwords.txt | 14 -
solr/example/files/conf/synonyms.txt | 29 -
solr/example/files/conf/update-script.js | 115 --
solr/example/files/conf/velocity/browse.vm | 32 -
solr/example/files/conf/velocity/dropit.js | 0
solr/example/files/conf/velocity/facet_doc_type.vm | 2 -
.../files/conf/velocity/facet_text_shingles.vm | 12 -
solr/example/files/conf/velocity/facets.vm | 24 -
solr/example/files/conf/velocity/footer.vm | 29 -
solr/example/files/conf/velocity/head.vm | 290 ----
solr/example/files/conf/velocity/hit.vm | 77 --
.../files/conf/velocity/img/english_640.png | Bin 138412 -> 0 bytes
.../example/files/conf/velocity/img/france_640.png | Bin 99992 -> 0 bytes
.../files/conf/velocity/img/germany_640.png | Bin 105271 -> 0 bytes
solr/example/files/conf/velocity/img/globe_256.png | Bin 46622 -> 0 bytes
.../files/conf/velocity/jquery.tx3-tag-cloud.js | 0
solr/example/files/conf/velocity/js/dropit.js | 97 --
.../files/conf/velocity/js/jquery.autocomplete.js | 763 -----------
.../files/conf/velocity/js/jquery.tx3-tag-cloud.js | 70 -
solr/example/files/conf/velocity/layout.vm | 42 -
solr/example/files/conf/velocity/macros.vm | 16 -
.../example/files/conf/velocity/mime_type_lists.vm | 68 -
solr/example/files/conf/velocity/results.vm | 20 -
solr/example/files/conf/velocity/results_list.vm | 21 -
73 files changed, 10155 deletions(-)
diff --git a/solr/example/files/README.md b/solr/example/files/README.md
deleted file mode 100644
index daeb5a3..0000000
--- a/solr/example/files/README.md
+++ /dev/null
@@ -1,167 +0,0 @@
-<!--
- 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.
--->
-
-# Solr-Powered File Search
-
-This README guides you through creating a Solr-powered search engine for your own set of files including Word documents,
-PDFs, HTML, and many other supported types.
-
-For further explanations, see the frequently asked questions at the end of the guide.
-
-## GETTING STARTED
-
-* To start Solr, enter the following command (make sure you’ve cd’ed into the directory in which Solr was installed):
-
-```
- bin/solr start
-```
-
-* If you’ve started correctly, you should see the following output:
-
-```
- Waiting to see Solr listening on port 8983 [/]
- Started Solr server on port 8983 (pid=<your pid>). Happy searching!
-```
-
-## CREATING THE CORE/COLLECTION
-
-* Before you can index your documents, you’ll need to create a core/collection. Do this by entering:
-
-```
- bin/solr create -c files -d example/files/conf
-```
-
-* Now you’ve created a core called “files” using a configuration tuned for indexing and querying rich text files.
-
-* You should see the following response:
-
-```
- Creating new core 'files' using command:
- http://localhost:8983/solr/admin/cores?action=CREATE&name=files&instanceDir=files
-
- {
- "responseHeader":{
- "status":0,
- "QTime":239},
- "core":"files"}
-```
-
-## INDEXING DOCUMENTS
-
-* Return to your command shell. To post all of your documents to the documents core, enter the following:
-
-```
- bin/post -c files ~/Documents
-```
-
-* Depending on how many documents you have, this could take a while. Sit back and watch the magic happen. When all of your documents have been indexed you’ll see something like:
-
-```
- <some number> files indexed.
- COMMITting Solr index changes to http://localhost:8983/solr/files/update...
- Time spent: <some amount of time>
-```
-
-* To see a list of accepted file types, do:
-
-```
- bin/post -h
-```
-
-## BROWSING DOCUMENTS
-
-* Your document information can be viewed in multiple formats: XML, JSON, CSV, as well as a nice HTML interface.
-
-* To view your document information in the HTML interface view, adjust the URL in your address bar to [http://localhost:8983/solr/files/browse](http://localhost:8983/solr/files/browse)
-
-* To view your document information in XML or other formats, add &wt (for writer type) to the end of that URL. i.e. To view your results in xml format direct your browser to:
- [http://localhost:8983/solr/files/browse?&wt=xml](http://localhost:8983/solr/files/browse?&wt=xml)
-
-## ADMIN UI
-
-* Another way to verify that your core has been created is to view it in the Admin User Interface.
-
- - The Admin_UI serves as a visual tool for indexing and querying your index in Solr.
-
-* To access the Admin UI, go to your browser and visit :
- [http://localhost:8983/solr/](http://localhost:8983/solr/)
-
- - <i>The Admin UI is only accessible when Solr is running</i>
-
-* On the left-hand side of the home page, click on “Core Selector”. The core you created, called “files” should be listed there; click on it. If it’s not listed, your core was not created and you’ll need to re-enter the create command.
-* Alternatively, you could just go to the core page directly by visiting : [http://localhost:8983/solr/#/files](http://localhost:8983/solr/#/files)
-
-* Now you’ve opened the core page. On this page there are a multitude of different tools you can use to analyze and search your core. You will make use of these features after indexing your documents.
-* Take note of the "Num Docs" field in your core Statistics. If after indexing your documents, it shows Num Docs to be 0, that means there was a problem indexing.
-
-## QUERYING INDEX
-
-* In the Admin UI, enter a term in the query box to see which documents contain the word.
-
-* You can filter the results by switching between the different content type tabs. To view an international version of this interface, hover over the globe icon in the top right hand section of the page.
-
-* Notice the tag cloud on the right side, which facets by top phrases extracted during indexing.
- Click on the phrases to see which documents contain them.
-
-* Another way to query the index is by manipulating the URL in your address bar once in the browse view.
-
-* i.e. : [http://localhost:8983/solr/files/browse?q=Lucene](http://localhost:8983/solr/files/browse?q=Lucene)
-
-## FAQs
-
-* Why use -d when creating a core?
- * -d specifies a specific configuration to use. This example as a configuration tuned for indexing and query rich
- text files.
-
-* How do I delete a core?
- * To delete a core (i.e. files), you can enter the following in your command shell:
-
- ```
- bin/solr delete -c files
- ```
-
- * You should see the following output:
-
- Deleting core 'files' using command:
-
- ```
- http://localhost:8983/solr/admin/cores?action=UNLOAD&core=files&deleteIndex=true&deleteDataDir=true&deleteInstanceDir=true
-
- {"responseHeader":{
- "status":0,
- "QTime":19}}
- ```
-
- * This calls the Solr core admin handler, "UNLOAD", and the parameters "deleteDataDir" and "deleteInstanceDir" to ensure that all data associated with core is also removed
-
-* How can I change the /browse UI?
-
- The primary templates are under example/files/conf/velocity. **In order to edit those files in place (without having to
- re-create or patch a core/collection with an updated configuration)**, Solr can be started with a special system property
- set to the _absolute_ path to the conf/velocity directory, like this:
-
- ```
- bin/solr start -Dvelocity.template.base.dir=</full/path/to>/example/files/conf/velocity/
- ```
-
-If you want to adjust the browse templates for an existing collection, edit the core’s configuration
-under server/solr/files/conf/velocity.
-
-## Provenance of free images used in this example:
-
- - Globe icon: visualpharm.com
- - Flag icons: freeflagicons.com
\ No newline at end of file
diff --git a/solr/example/files/browse-resources/velocity/resources.properties b/solr/example/files/browse-resources/velocity/resources.properties
deleted file mode 100644
index 4cc15b2..0000000
--- a/solr/example/files/browse-resources/velocity/resources.properties
+++ /dev/null
@@ -1,82 +0,0 @@
-# Title: "<Solr logo> Powered File Search"
-powered_file_search=Powered File Search
-
-# Search box and results
-find=Find
-submit=Submit
-page_of=Page <span class="page-num">{0}</span> of <span class="page-count">{1}</span>
-previous=previous
-next=next
-results_found_in=results found in {0}ms
-results_found=results found
-
-# Facets
-facet.top_phrases=Top Phrases
-facet.language=Language
-
-# Type labels
-type.all=All Types
-type.doc.label=Document
-type.html.label=HTML
-type.pdf.label=PDF
-type.presentation.label=Presentation
-type.spreadsheet.label=Spreadsheet
-type.text.label=text
-type.image.label=image
-type.unknown=unknown
-
-# Language code mappings
-# - from https://code.google.com/p/language-detection/wiki/LanguageList
-language.af=Afrikaans
-language.ar=Arabic
-language.bg=Bulgarian
-language.bn=Bengali
-language.cs=Czech
-language.da=Danish
-language.de=German
-language.el=Greek
-language.en=English
-language.es=Spanish
-language.et=Estonian
-language.fa=Persian
-language.fi=Finnish
-language.fr=French
-language.gu=Gujarati
-language.he=Hebrew
-language.hi=Hindi
-language.hr=Croatian
-language.hu=Hungarian
-language.id=Indonesian
-language.it=Italian
-language.ja=Japanese
-language.kn=Kannada
-language.ko=Korean
-language.lt=Lithuanian
-language.lv=Latvian
-language.mk=Macedonian
-language.ml=Malayalam
-language.mr=Marathi
-language.ne=Nepali
-language.nl=Dutch
-language.no=Norwegian
-language.pa=Punjabi
-language.pl=Polish
-language.pt=Portuguese
-language.ro=Romanian
-language.ru=Russian
-language.sk=Slovak
-language.sl=Slovene
-language.so=Somali
-language.sq=Albanian
-language.sv=Swedish
-language.sw=Swahili
-language.ta=Tamil
-language.te=Telugu
-language.th=Thai
-language.tl=Tagalog
-language.tr=Turkish
-language.uk=Ukrainian
-language.ur=Urdu
-language.vi=Vietnamese
-language.zh-cn=Simplified Chinese
-language.zh-tw=Traditional Chinese
diff --git a/solr/example/files/browse-resources/velocity/resources_de_DE.properties b/solr/example/files/browse-resources/velocity/resources_de_DE.properties
deleted file mode 100644
index 1837bf5..0000000
--- a/solr/example/files/browse-resources/velocity/resources_de_DE.properties
+++ /dev/null
@@ -1,18 +0,0 @@
-find=Durchsuchen
-page_of=Page <span class="page-num">{0}</span> von <span class="page-count">{1}</span>
-previous=vorherige Seite
-next=n\u00e4chste Seite
-results_found_in=Ergebnisse in {0}ms gefunden
-results_found=Ergebnisse gefunden
-powered_file_search= betriebene Dateisuche
-type.text.label=Text
-type.pdf.label=PDF
-type.html.label=HTML
-type.presentation.label=Pr\u00e4sentation
-type.image.label=Bild
-type.doc.label=Dokument
-type.spreadsheet.label=Kalkulationstabelle
-type.unknown=unbekannt
-type.all=alle Arten
-facet.top_phrases=Schl\u00fcssels\u00e4tze
-submit=einreichen
diff --git a/solr/example/files/browse-resources/velocity/resources_fr_FR.properties b/solr/example/files/browse-resources/velocity/resources_fr_FR.properties
deleted file mode 100644
index 5b62757..0000000
--- a/solr/example/files/browse-resources/velocity/resources_fr_FR.properties
+++ /dev/null
@@ -1,20 +0,0 @@
-find=Recherche
-page_of=Page <span class="page-num">{0}</span> de <span class="page-count">{1}</span>
-previous=pr\u00e9c\u00e9dent
-next=suivant
-results_found_in=resultas ficher en {0}ms
-results_found=resultas ficher
-powered_file_search=Recherches de Fichiers
-type.text.label=Texte
-type.pdf.label=PDF
-type.html.label=HTML
-type.image.label=Image
-type.presentation.label=Pr\u00e9sentation
-type.doc.label=Documents
-type.spreadsheet.label=Tableur
-type.unknown=Inconnu
-type.all=Tous les Types
-facet.top_phrases=Phrases Cl\u00e9s
-submit=Recherche
-
-
diff --git a/solr/example/files/conf/currency.xml b/solr/example/files/conf/currency.xml
deleted file mode 100644
index 3a9c58a..0000000
--- a/solr/example/files/conf/currency.xml
+++ /dev/null
@@ -1,67 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
-
-<currencyConfig version="1.0">
- <rates>
- <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
- <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
- <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
- <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
- <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
- <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
- <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
- <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
- <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
- <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
- <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
- <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
- <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
- <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
- <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
- <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
- <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
- <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
- <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
- <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
- <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
- <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
- <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
- <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
- <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
- <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
- <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
- <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
- <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
- <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
- <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
- <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
- <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
- <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
- <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
- <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
- <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
- <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
-
- <!-- Cross-rates for some common currencies -->
- <rate from="EUR" to="GBP" rate="0.869914" />
- <rate from="EUR" to="NOK" rate="7.800095" />
- <rate from="GBP" to="NOK" rate="8.966508" />
- </rates>
-</currencyConfig>
diff --git a/solr/example/files/conf/elevate.xml b/solr/example/files/conf/elevate.xml
deleted file mode 100644
index 2c09ebe..0000000
--- a/solr/example/files/conf/elevate.xml
+++ /dev/null
@@ -1,42 +0,0 @@
-<?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>
diff --git a/solr/example/files/conf/email_url_types.txt b/solr/example/files/conf/email_url_types.txt
deleted file mode 100644
index 622b193..0000000
--- a/solr/example/files/conf/email_url_types.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-<URL>
-<EMAIL>
diff --git a/solr/example/files/conf/lang/contractions_ca.txt b/solr/example/files/conf/lang/contractions_ca.txt
deleted file mode 100644
index 307a85f..0000000
--- a/solr/example/files/conf/lang/contractions_ca.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-# Set of Catalan contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-l
-m
-n
-s
-t
diff --git a/solr/example/files/conf/lang/contractions_fr.txt b/solr/example/files/conf/lang/contractions_fr.txt
deleted file mode 100644
index f1bba51..0000000
--- a/solr/example/files/conf/lang/contractions_fr.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-# 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
diff --git a/solr/example/files/conf/lang/contractions_ga.txt b/solr/example/files/conf/lang/contractions_ga.txt
deleted file mode 100644
index 9ebe7fa..0000000
--- a/solr/example/files/conf/lang/contractions_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-m
-b
diff --git a/solr/example/files/conf/lang/contractions_it.txt b/solr/example/files/conf/lang/contractions_it.txt
deleted file mode 100644
index cac0409..0000000
--- a/solr/example/files/conf/lang/contractions_it.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-# Set of Italian contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-c
-l
-all
-dall
-dell
-nell
-sull
-coll
-pell
-gl
-agl
-dagl
-degl
-negl
-sugl
-un
-m
-t
-s
-v
-d
diff --git a/solr/example/files/conf/lang/hyphenations_ga.txt b/solr/example/files/conf/lang/hyphenations_ga.txt
deleted file mode 100644
index 4d2642c..0000000
--- a/solr/example/files/conf/lang/hyphenations_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish hyphenations for StopFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-h
-n
-t
diff --git a/solr/example/files/conf/lang/stemdict_nl.txt b/solr/example/files/conf/lang/stemdict_nl.txt
deleted file mode 100644
index 4410729..0000000
--- a/solr/example/files/conf/lang/stemdict_nl.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-# Set of overrides for the dutch stemmer
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-fiets fiets
-bromfiets bromfiets
-ei eier
-kind kinder
diff --git a/solr/example/files/conf/lang/stoptags_ja.txt b/solr/example/files/conf/lang/stoptags_ja.txt
deleted file mode 100644
index 71b7508..0000000
--- a/solr/example/files/conf/lang/stoptags_ja.txt
+++ /dev/null
@@ -1,420 +0,0 @@
-#
-# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
-#
-# Any token with a part-of-speech tag that exactly matches those defined in this
-# file are removed from the token stream.
-#
-# Set your own stoptags by uncommenting the lines below. Note that comments are
-# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
-# etc. that can be useful for building you own stoptag set.
-#
-# The entire possible tagset is provided below for convenience.
-#
-#####
-# noun: unclassified nouns
-#名詞
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#名詞-一般
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#名詞-固有名詞
-#
-# noun-proper-misc: miscellaneous proper nouns
-#名詞-固有名詞-一般
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#名詞-固有名詞-人名
-#
-# noun-proper-person-misc: names that cannot be divided into surname and
-# given name; foreign names; names where the surname or given name is unknown.
-# e.g. お市の方
-#名詞-固有名詞-人名-一般
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. 山田
-#名詞-固有名詞-人名-姓
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. 太郎
-#名詞-固有名詞-人名-名
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. 通産省, NHK
-#名詞-固有名詞-組織
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#名詞-固有名詞-地域
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. アジア, バルセロナ, 京都
-#名詞-固有名詞-地域-一般
-#
-# noun-proper-place-country: Country names.
-# e.g. 日本, オーストラリア
-#名詞-固有名詞-地域-国
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#名詞-代名詞
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
-#名詞-代名詞-一般
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
-#名詞-代名詞-縮約
-#
-# noun-adverbial: Temporal nouns such as names of days or months that behave
-# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
-# e.g. 金曜, 一月, 午後, 少量
-#名詞-副詞可能
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (する, できる, なさる, くださる)
-# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
-#名詞-サ変接続
-#
-# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
-# e.g. 健康, 安易, 駄目, だめ
-#名詞-形容動詞語幹
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
-# e.g. 0, 1, 2, 何, 数, 幾
-#名詞-数
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#名詞-非自立
-#
-# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
-# attach to the base form of inflectional words, words that cannot be classified
-# into any of the other categories below. This category includes indefinite nouns.
-# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
-# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
-# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
-# わり, 割り, 割, ん-口語/, もん-口語/
-#名詞-非自立-一般
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
-# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
-# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
-# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
-# 儘, 侭, みぎり, 矢先
-#名詞-非自立-副詞可能
-#
-# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
-# with the stem よう(だ) ("you(da)").
-# e.g. よう, やう, 様 (よう)
-#名詞-非自立-助動詞語幹
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form な (aux "da").
-# e.g. みたい, ふう
-#名詞-非自立-形容動詞語幹
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#名詞-特殊
-#
-# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
-# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. そう
-#名詞-特殊-助動詞語幹
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#名詞-接尾
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
-# any of the other categories below. In general, this category is more inclusive than
-# 接尾語 ("suffix") and is usually the last element in a compound noun.
-# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
-# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
-#名詞-接尾-一般
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. 君, 様, 著
-#名詞-接尾-人名
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. 町, 市, 県
-#名詞-接尾-地域
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before スル ("suru").
-# e.g. 化, 視, 分け, 入り, 落ち, 買い
-#名詞-接尾-サ変接続
-#
-# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
-# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. そう
-#名詞-接尾-助動詞語幹
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula だ ("da").
-# e.g. 的, げ, がち
-#名詞-接尾-形容動詞語幹
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
-#名詞-接尾-副詞可能
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
-#名詞-接尾-助数詞
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (楽し) さ, (考え) 方
-#名詞-接尾-特殊
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
-#名詞-接続詞的
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
-# semantically verb-like.
-# e.g. ごらん, ご覧, 御覧, 頂戴
-#名詞-動詞非自立的
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
-# is いわく ("iwaku").
-#名詞-引用文字列
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
-# behave like an adjective.
-# e.g. 申し訳, 仕方, とんでも, 違い
-#名詞-ナイ形容詞語幹
-#
-#####
-# prefix: unclassified prefixes
-#接頭詞
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
-#接頭詞-名詞接続
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by なる/なさる/くださる.
-# e.g. お (読みなさい), お (座り)
-#接頭詞-動詞接続
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. お (寒いですねえ), バカ (でかい)
-#接頭詞-形容詞接続
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. 約, およそ, 毎時
-#接頭詞-数接続
-#
-#####
-# verb: unclassified verbs
-#動詞
-#
-# verb-main:
-#動詞-自立
-#
-# verb-auxiliary:
-#動詞-非自立
-#
-# verb-suffix:
-#動詞-接尾
-#
-#####
-# adjective: unclassified adjectives
-#形容詞
-#
-# adjective-main:
-#形容詞-自立
-#
-# adjective-auxiliary:
-#形容詞-非自立
-#
-# adjective-suffix:
-#形容詞-接尾
-#
-#####
-# adverb: unclassified adverbs
-#副詞
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. あいかわらず, 多分
-#副詞-一般
-#
-# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
-# な, する, だ, etc.
-# e.g. こんなに, そんなに, あんなに, なにか, なんでも
-#副詞-助詞類接続
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
-# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
-# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
-#連体詞
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. が, けれども, そして, じゃあ, それどころか
-接続詞
-#
-#####
-# particle: unclassified particles.
-助詞
-#
-# particle-case: case particles where the subclassification is undefined.
-助詞-格助詞
-#
-# particle-case-misc: Case particles.
-# e.g. から, が, で, と, に, へ, より, を, の, にて
-助詞-格助詞-一般
-#
-# particle-case-quote: the "to" that appears after nouns, a person’s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
-助詞-格助詞-引用
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
-# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
-# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
-# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
-# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
-# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
-# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
-# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
-助詞-格助詞-連語
-#
-# particle-conjunctive:
-# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
-# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
-# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
-助詞-接続助詞
-#
-# particle-dependency:
-# e.g. こそ, さえ, しか, すら, は, も, ぞ
-助詞-係助詞
-#
-# particle-adverbial:
-# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
-# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
-# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
-# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
-# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
-助詞-副助詞
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (松島) や
-助詞-間投助詞
-#
-# particle-coordinate:
-# e.g. と, たり, だの, だり, とか, なり, や, やら
-助詞-並立助詞
-#
-# particle-final:
-# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
-# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
-助詞-終助詞
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
-# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
-# 「(祈りが届いたせい) か (, 試験に合格した.)」
-# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
-# e.g. か
-助詞-副助詞／並立助詞／終助詞
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-助詞-連体化
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. に, と
-助詞-副詞化
-#
-# particle-special: A particle that does not fit into one of the above classifications.
-# This includes particles that are used in Tanka, Haiku, and other poetry.
-# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
-助詞-特殊
-#
-#####
-# auxiliary-verb:
-助動詞
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
-# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
-#感動詞
-#
-#####
-# symbol: unclassified Symbols.
-記号
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [○◎@$〒→+]
-記号-一般
-#
-# symbol-comma: Commas
-# e.g. [,、]
-記号-読点
-#
-# symbol-period: Periods and full stops.
-# e.g. [.．。]
-記号-句点
-#
-# symbol-space: Full-width whitespace.
-記号-空白
-#
-# symbol-open_bracket:
-# e.g. [({‘“『【]
-記号-括弧開
-#
-# symbol-close_bracket:
-# e.g. [)}’”』」】]
-記号-括弧閉
-#
-# symbol-alphabetic:
-#記号-アルファベット
-#
-#####
-# other: unclassified other
-#その他
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (だ)ァ
-その他-間投
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. あの, うんと, えと
-フィラー
-#
-#####
-# non-verbal: non-verbal sound.
-非言語音
-#
-#####
-# fragment:
-#語断片
-#
-#####
-# unknown: unknown part of speech.
-#未知語
-#
-##### End of file
diff --git a/solr/example/files/conf/lang/stopwords_ar.txt b/solr/example/files/conf/lang/stopwords_ar.txt
deleted file mode 100644
index 046829d..0000000
--- a/solr/example/files/conf/lang/stopwords_ar.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Cleaned on October 11, 2009 (not normalized, so use before normalization)
-# This means that when modifying this list, you might need to add some
-# redundant entries, for example containing forms with both أ and ا
-من
-ومن
-منها
-منه
-في
-وفي
-فيها
-فيه
-و
-ف
-ثم
-او
-أو
-ب
-بها
-به
-ا
-أ
-اى
-اي
-أي
-أى
-لا
-ولا
-الا
-ألا
-إلا
-لكن
-ما
-وما
-كما
-فما
-عن
-مع
-اذا
-إذا
-ان
-أن
-إن
-انها
-أنها
-إنها
-انه
-أنه
-إنه
-بان
-بأن
-فان
-فأن
-وان
-وأن
-وإن
-التى
-التي
-الذى
-الذي
-الذين
-الى
-الي
-إلى
-إلي
-على
-عليها
-عليه
-اما
-أما
-إما
-ايضا
-أيضا
-كل
-وكل
-لم
-ولم
-لن
-ولن
-هى
-هي
-هو
-وهى
-وهي
-وهو
-فهى
-فهي
-فهو
-انت
-أنت
-لك
-لها
-له
-هذه
-هذا
-تلك
-ذلك
-هناك
-كانت
-كان
-يكون
-تكون
-وكانت
-وكان
-غير
-بعض
-قد
-نحو
-بين
-بينما
-منذ
-ضمن
-حيث
-الان
-الآن
-خلال
-بعد
-قبل
-حتى
-عند
-عندما
-لدى
-جميع
diff --git a/solr/example/files/conf/lang/stopwords_bg.txt b/solr/example/files/conf/lang/stopwords_bg.txt
deleted file mode 100644
index 1ae4ba2..0000000
--- a/solr/example/files/conf/lang/stopwords_bg.txt
+++ /dev/null
@@ -1,193 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-а
-аз
-ако
-ала
-бе
-без
-беше
-би
-бил
-била
-били
-било
-близо
-бъдат
-бъде
-бяха
-в
-вас
-ваш
-ваша
-вероятно
-вече
-взема
-ви
-вие
-винаги
-все
-всеки
-всички
-всичко
-всяка
-във
-въпреки
-върху
-г
-ги
-главно
-го
-д
-да
-дали
-до
-докато
-докога
-дори
-досега
-доста
-е
-едва
-един
-ето
-за
-зад
-заедно
-заради
-засега
-затова
-защо
-защото
-и
-из
-или
-им
-има
-имат
-иска
-й
-каза
-как
-каква
-какво
-както
-какъв
-като
-кога
-когато
-което
-които
-кой
-който
-колко
-която
-къде
-където
-към
-ли
-м
-ме
-между
-мен
-ми
-мнозина
-мога
-могат
-може
-моля
-момента
-му
-н
-на
-над
-назад
-най
-направи
-напред
-например
-нас
-не
-него
-нея
-ни
-ние
-никой
-нито
-но
-някои
-някой
-няма
-обаче
-около
-освен
-особено
-от
-отгоре
-отново
-още
-пак
-по
-повече
-повечето
-под
-поне
-поради
-после
-почти
-прави
-пред
-преди
-през
-при
-пък
-първо
-с
-са
-само
-се
-сега
-си
-скоро
-след
-сме
-според
-сред
-срещу
-сте
-съм
-със
-също
-т
-тази
-така
-такива
-такъв
-там
-твой
-те
-тези
-ти
-тн
-то
-това
-тогава
-този
-той
-толкова
-точно
-трябва
-тук
-тъй
-тя
-тях
-у
-харесва
-ч
-че
-често
-чрез
-ще
-щом
-я
diff --git a/solr/example/files/conf/lang/stopwords_ca.txt b/solr/example/files/conf/lang/stopwords_ca.txt
deleted file mode 100644
index 3da65de..0000000
--- a/solr/example/files/conf/lang/stopwords_ca.txt
+++ /dev/null
@@ -1,220 +0,0 @@
-# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
-a
-abans
-ací
-ah
-així
-això
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-allà
-allí
-allò
-altra
-altre
-altres
-amb
-ambdós
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aquí
-baix
-cada
-cadascú
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-després
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-érem
-eren
-éreu
-es
-és
-esta
-està
-estàvem
-estaven
-estàveu
-esteu
-et
-etc
-ets
-fins
-fora
-gairebé
-ha
-han
-has
-havia
-he
-hem
-heu
-hi
-ho
-i
-igual
-iguals
-ja
-l'hi
-la
-les
-li
-li'n
-llavors
-m'he
-ma
-mal
-malgrat
-mateix
-mateixa
-mateixes
-mateixos
-me
-mentre
-més
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-només
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-però
-perquè
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-què
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-sóc
-solament
-sols
-son
-són
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-també
-tampoc
-tan
-tant
-tanta
-tantes
-teu
-teus
-teva
-teves
-ton
-tons
-tot
-tota
-totes
-tots
-un
-una
-unes
-uns
-us
-va
-vaig
-vam
-van
-vas
-veu
-vosaltres
-vostra
-vostre
-vostres
diff --git a/solr/example/files/conf/lang/stopwords_cz.txt b/solr/example/files/conf/lang/stopwords_cz.txt
deleted file mode 100644
index 53c6097..0000000
--- a/solr/example/files/conf/lang/stopwords_cz.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-tímto
-budeš
-budem
-byli
-jseš
-můj
-svým
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-proč
-máte
-tato
-kam
-tohoto
-kdo
-kteří
-mi
-nám
-tom
-tomuto
-mít
-nic
-proto
-kterou
-byla
-toho
-protože
-asi
-ho
-naši
-napište
-re
-což
-tím
-takže
-svých
-její
-svými
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-pravé
-ji
-nad
-nejsou
-či
-pod
-téma
-mezi
-přes
-ty
-pak
-vám
-ani
-když
-však
-neg
-jsem
-tento
-článku
-články
-aby
-jsme
-před
-pta
-jejich
-byl
-ještě
-až
-bez
-také
-pouze
-první
-vaše
-která
-nás
-nový
-tipy
-pokud
-může
-strana
-jeho
-své
-jiné
-zprávy
-nové
-není
-vás
-jen
-podle
-zde
-už
-být
-více
-bude
-již
-než
-který
-by
-které
-co
-nebo
-ten
-tak
-má
-při
-od
-po
-jsou
-jak
-další
-ale
-si
-se
-ve
-to
-jako
-za
-zpět
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-přičemž
-já
-on
-ona
-ono
-oni
-ony
-my
-vy
-jí
-ji
-mě
-mne
-jemu
-tomu
-těm
-těmu
-němu
-němuž
-jehož
-jíž
-jelikož
-jež
-jakož
-načež
diff --git a/solr/example/files/conf/lang/stopwords_da.txt b/solr/example/files/conf/lang/stopwords_da.txt
deleted file mode 100644
index 42e6145..0000000
--- a/solr/example/files/conf/lang/stopwords_da.txt
+++ /dev/null
@@ -1,110 +0,0 @@
- | 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
diff --git a/solr/example/files/conf/lang/stopwords_de.txt b/solr/example/files/conf/lang/stopwords_de.txt
deleted file mode 100644
index 86525e7..0000000
--- a/solr/example/files/conf/lang/stopwords_de.txt
+++ /dev/null
@@ -1,294 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_el.txt b/solr/example/files/conf/lang/stopwords_el.txt
deleted file mode 100644
index 232681f..0000000
--- a/solr/example/files/conf/lang/stopwords_el.txt
+++ /dev/null
@@ -1,78 +0,0 @@
-# Lucene Greek Stopwords list
-# Note: by default this file is used after GreekLowerCaseFilter,
-# so when modifying this file use 'σ' instead of 'ς'
-ο
-η
-το
-οι
-τα
-του
-τησ
-των
-τον
-την
-και
-κι
-κ
-ειμαι
-εισαι
-ειναι
-ειμαστε
-ειστε
-στο
-στον
-στη
-στην
-μα
-αλλα
-απο
-για
-προσ
-με
-σε
-ωσ
-παρα
-αντι
-κατα
-μετα
-θα
-να
-δε
-δεν
-μη
-μην
-επι
-ενω
-εαν
-αν
-τοτε
-που
-πωσ
-ποιοσ
-ποια
-ποιο
-ποιοι
-ποιεσ
-ποιων
-ποιουσ
-αυτοσ
-αυτη
-αυτο
-αυτοι
-αυτων
-αυτουσ
-αυτεσ
-αυτα
-εκεινοσ
-εκεινη
-εκεινο
-εκεινοι
-εκεινεσ
-εκεινα
-εκεινων
-εκεινουσ
-οπωσ
-ομωσ
-ισωσ
-οσο
-οτι
diff --git a/solr/example/files/conf/lang/stopwords_en.txt b/solr/example/files/conf/lang/stopwords_en.txt
deleted file mode 100644
index 2c164c0..0000000
--- a/solr/example/files/conf/lang/stopwords_en.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-# 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.
-
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-# Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-such
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
diff --git a/solr/example/files/conf/lang/stopwords_es.txt b/solr/example/files/conf/lang/stopwords_es.txt
deleted file mode 100644
index 487d78c..0000000
--- a/solr/example/files/conf/lang/stopwords_es.txt
+++ /dev/null
@@ -1,356 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_eu.txt b/solr/example/files/conf/lang/stopwords_eu.txt
deleted file mode 100644
index 25f1db9..0000000
--- a/solr/example/files/conf/lang/stopwords_eu.txt
+++ /dev/null
@@ -1,99 +0,0 @@
-# example set of basque stopwords
-al
-anitz
-arabera
-asko
-baina
-bat
-batean
-batek
-bati
-batzuei
-batzuek
-batzuetan
-batzuk
-bera
-beraiek
-berau
-berauek
-bere
-berori
-beroriek
-beste
-bezala
-da
-dago
-dira
-ditu
-du
-dute
-edo
-egin
-ere
-eta
-eurak
-ez
-gainera
-gu
-gutxi
-guzti
-haiei
-haiek
-haietan
-hainbeste
-hala
-han
-handik
-hango
-hara
-hari
-hark
-hartan
-hau
-hauei
-hauek
-hauetan
-hemen
-hemendik
-hemengo
-hi
-hona
-honek
-honela
-honetan
-honi
-hor
-hori
-horiei
-horiek
-horietan
-horko
-horra
-horrek
-horrela
-horretan
-horri
-hortik
-hura
-izan
-ni
-noiz
-nola
-non
-nondik
-nongo
-nor
-nora
-ze
-zein
-zen
-zenbait
-zenbat
-zer
-zergatik
-ziren
-zituen
-zu
-zuek
-zuen
-zuten
diff --git a/solr/example/files/conf/lang/stopwords_fa.txt b/solr/example/files/conf/lang/stopwords_fa.txt
deleted file mode 100644
index 723641c..0000000
--- a/solr/example/files/conf/lang/stopwords_fa.txt
+++ /dev/null
@@ -1,313 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Note: by default this file is used after normalization, so when adding entries
-# to this file, use the arabic 'ي' instead of 'ی'
-انان
-نداشته
-سراسر
-خياه
-ايشان
-وي
-تاكنون
-بيشتري
-دوم
-پس
-ناشي
-وگو
-يا
-داشتند
-سپس
-هنگام
-هرگز
-پنج
-نشان
-امسال
-ديگر
-گروهي
-شدند
-چطور
-ده
-و
-دو
-نخستين
-ولي
-چرا
-چه
-وسط
-ه
-كدام
-قابل
-يك
-رفت
-هفت
-همچنين
-در
-هزار
-بله
-بلي
-شايد
-اما
-شناسي
-گرفته
-دهد
-داشته
-دانست
-داشتن
-خواهيم
-ميليارد
-وقتيكه
-امد
-خواهد
-جز
-اورده
-شده
-بلكه
-خدمات
-شدن
-برخي
-نبود
-بسياري
-جلوگيري
-حق
-كردند
-نوعي
-بعري
-نكرده
-نظير
-نبايد
-بوده
-بودن
-داد
-اورد
-هست
-جايي
-شود
-دنبال
-داده
-بايد
-سابق
-هيچ
-همان
-انجا
-كمتر
-كجاست
-گردد
-كسي
-تر
-مردم
-تان
-دادن
-بودند
-سري
-جدا
-ندارند
-مگر
-يكديگر
-دارد
-دهند
-بنابراين
-هنگامي
-سمت
-جا
-انچه
-خود
-دادند
-زياد
-دارند
-اثر
-بدون
-بهترين
-بيشتر
-البته
-به
-براساس
-بيرون
-كرد
-بعضي
-گرفت
-توي
-اي
-ميليون
-او
-جريان
-تول
-بر
-مانند
-برابر
-باشيم
-مدتي
-گويند
-اكنون
-تا
-تنها
-جديد
-چند
-بي
-نشده
-كردن
-كردم
-گويد
-كرده
-كنيم
-نمي
-نزد
-روي
-قصد
-فقط
-بالاي
-ديگران
-اين
-ديروز
-توسط
-سوم
-ايم
-دانند
-سوي
-استفاده
-شما
-كنار
-داريم
-ساخته
-طور
-امده
-رفته
-نخست
-بيست
-نزديك
-طي
-كنيد
-از
-انها
-تمامي
-داشت
-يكي
-طريق
-اش
-چيست
-روب
-نمايد
-گفت
-چندين
-چيزي
-تواند
-ام
-ايا
-با
-ان
-ايد
-ترين
-اينكه
-ديگري
-راه
-هايي
-بروز
-همچنان
-پاعين
-كس
-حدود
-مختلف
-مقابل
-چيز
-گيرد
-ندارد
-ضد
-همچون
-سازي
-شان
-مورد
-باره
-مرسي
-خويش
-برخوردار
-چون
-خارج
-شش
-هنوز
-تحت
-ضمن
-هستيم
-گفته
-فكر
-بسيار
-پيش
-براي
-روزهاي
-انكه
-نخواهد
-بالا
-كل
-وقتي
-كي
-چنين
-كه
-گيري
-نيست
-است
-كجا
-كند
-نيز
-يابد
-بندي
-حتي
-توانند
-عقب
-خواست
-كنند
-بين
-تمام
-همه
-ما
-باشند
-مثل
-شد
-اري
-باشد
-اره
-طبق
-بعد
-اگر
-صورت
-غير
-جاي
-بيش
-ريزي
-اند
-زيرا
-چگونه
-بار
-لطفا
-مي
-درباره
-من
-ديده
-همين
-گذاري
-برداري
-علت
-گذاشته
-هم
-فوق
-نه
-ها
-شوند
-اباد
-همواره
-هر
-اول
-خواهند
-چهار
-نام
-امروز
-مان
-هاي
-قبل
-كنم
-سعي
-تازه
-را
-هستند
-زير
-جلوي
-عنوان
-بود
diff --git a/solr/example/files/conf/lang/stopwords_fi.txt b/solr/example/files/conf/lang/stopwords_fi.txt
deleted file mode 100644
index 4372c9a..0000000
--- a/solr/example/files/conf/lang/stopwords_fi.txt
+++ /dev/null
@@ -1,97 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_fr.txt b/solr/example/files/conf/lang/stopwords_fr.txt
deleted file mode 100644
index 749abae..0000000
--- a/solr/example/files/conf/lang/stopwords_fr.txt
+++ /dev/null
@@ -1,186 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_ga.txt b/solr/example/files/conf/lang/stopwords_ga.txt
deleted file mode 100644
index 9ff88d7..0000000
--- a/solr/example/files/conf/lang/stopwords_ga.txt
+++ /dev/null
@@ -1,110 +0,0 @@
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bhúr
-caoga
-ceathair
-ceathrar
-chomh
-chtó
-chuig
-chun
-cois
-céad
-cúig
-cúigear
-d'
-daichead
-dar
-de
-deich
-deichniúr
-den
-dhá
-do
-don
-dtí
-dá
-dár
-dó
-faoi
-faoin
-faoina
-faoinár
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-inár
-is
-le
-leis
-lena
-lenár
-m'
-mar
-mo
-mé
-na
-nach
-naoi
-naonúr
-ná
-ní
-níor
-nó
-nócha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seachtó
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-sé
-sí
-tar
-thar
-thú
-triúr
-trí
-trína
-trínár
-tríocha
-tú
-um
-ár
-é
-éis
-í
-ó
-ón
-óna
-ónár
diff --git a/solr/example/files/conf/lang/stopwords_gl.txt b/solr/example/files/conf/lang/stopwords_gl.txt
deleted file mode 100644
index d8760b1..0000000
--- a/solr/example/files/conf/lang/stopwords_gl.txt
+++ /dev/null
@@ -1,161 +0,0 @@
-# galican stopwords
-a
-aínda
-alí
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aquí
-ao
-aos
-as
-así
-á
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalgún
-dalgúns
-das
-de
-del
-dela
-delas
-deles
-desde
-deste
-do
-dos
-dun
-duns
-dunha
-dunhas
-e
-el
-ela
-elas
-eles
-en
-era
-eran
-esa
-esas
-ese
-eses
-esta
-estar
-estaba
-está
-están
-este
-estes
-estiven
-estou
-eu
-é
-facer
-foi
-foron
-fun
-había
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-miña
-miñas
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-nós
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-ó
-ós
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-senón
-ser
-seu
-seus
-sexa
-sido
-sobre
-súa
-súas
-tamén
-tan
-te
-ten
-teñen
-teño
-ter
-teu
-teus
-ti
-tido
-tiña
-tiven
-túa
-túas
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-vós
diff --git a/solr/example/files/conf/lang/stopwords_hi.txt b/solr/example/files/conf/lang/stopwords_hi.txt
deleted file mode 100644
index 86286bb..0000000
--- a/solr/example/files/conf/lang/stopwords_hi.txt
+++ /dev/null
@@ -1,235 +0,0 @@
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# Note: by default this file also contains forms normalized by HindiNormalizer
-# for spelling variation (see section below), such that it can be used whether or
-# not you enable that feature. When adding additional entries to this list,
-# please add the normalized form as well.
-अंदर
-अत
-अपना
-अपनी
-अपने
-अभी
-आदि
-आप
-इत्यादि
-इन
-इनका
-इन्हीं
-इन्हें
-इन्हों
-इस
-इसका
-इसकी
-इसके
-इसमें
-इसी
-इसे
-उन
-उनका
-उनकी
-उनके
-उनको
-उन्हीं
-उन्हें
-उन्हों
-उस
-उसके
-उसी
-उसे
-एक
-एवं
-एस
-ऐसे
-और
-कई
-कर
-करता
-करते
-करना
-करने
-करें
-कहते
-कहा
-का
-काफ़ी
-कि
-कितना
-किन्हें
-किन्हों
-किया
-किर
-किस
-किसी
-किसे
-की
-कुछ
-कुल
-के
-को
-कोई
-कौन
-कौनसा
-गया
-घर
-जब
-जहाँ
-जा
-जितना
-जिन
-जिन्हें
-जिन्हों
-जिस
-जिसे
-जीधर
-जैसा
-जैसे
-जो
-तक
-तब
-तरह
-तिन
-तिन्हें
-तिन्हों
-तिस
-तिसे
-तो
-था
-थी
-थे
-दबारा
-दिया
-दुसरा
-दूसरे
-दो
-द्वारा
-न
-नहीं
-ना
-निहायत
-नीचे
-ने
-पर
-पर
-पहले
-पूरा
-पे
-फिर
-बनी
-बही
-बहुत
-बाद
-बाला
-बिलकुल
-भी
-भीतर
-मगर
-मानो
-मे
-में
-यदि
-यह
-यहाँ
-यही
-या
-यिह
-ये
-रखें
-रहा
-रहे
-ऱ्वासा
-लिए
-लिये
-लेकिन
-व
-वर्ग
-वह
-वह
-वहाँ
-वहीं
-वाले
-वुह
-वे
-वग़ैरह
-संग
-सकता
-सकते
-सबसे
-सभी
-साथ
-साबुत
-साभ
-सारा
-से
-सो
-ही
-हुआ
-हुई
-हुए
-है
-हैं
-हो
-होता
-होती
-होते
-होना
-होने
-# additional normalized forms of the above
-अपनि
-जेसे
-होति
-सभि
-तिंहों
-इंहों
-दवारा
-इसि
-किंहें
-थि
-उंहों
-ओर
-जिंहें
-वहिं
-अभि
-बनि
-हि
-उंहिं
-उंहें
-हें
-वगेरह
-एसे
-रवासा
-कोन
-निचे
-काफि
-उसि
-पुरा
-भितर
-हे
-बहि
-वहां
-कोइ
-यहां
-जिंहों
-तिंहें
-किसि
-कइ
-यहि
-इंहिं
-जिधर
-इंहें
-अदि
-इतयादि
-हुइ
-कोनसा
-इसकि
-दुसरे
-जहां
-अप
-किंहों
-उनकि
-भि
-वरग
-हुअ
-जेसा
-नहिं
diff --git a/solr/example/files/conf/lang/stopwords_hu.txt b/solr/example/files/conf/lang/stopwords_hu.txt
deleted file mode 100644
index 37526da..0000000
--- a/solr/example/files/conf/lang/stopwords_hu.txt
+++ /dev/null
@@ -1,211 +0,0 @@
- | 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
diff --git a/solr/example/files/conf/lang/stopwords_hy.txt b/solr/example/files/conf/lang/stopwords_hy.txt
deleted file mode 100644
index 60c1c50..0000000
--- a/solr/example/files/conf/lang/stopwords_hy.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-# example set of Armenian stopwords.
-այդ
-այլ
-այն
-այս
-դու
-դուք
-եմ
-են
-ենք
-ես
-եք
-է
-էի
-էին
-էինք
-էիր
-էիք
-էր
-ըստ
-թ
-ի
-ին
-իսկ
-իր
-կամ
-համար
-հետ
-հետո
-մենք
-մեջ
-մի
-ն
-նա
-նաև
-նրա
-նրանք
-որ
-որը
-որոնք
-որպես
-ու
-ում
-պիտի
-վրա
-և
diff --git a/solr/example/files/conf/lang/stopwords_id.txt b/solr/example/files/conf/lang/stopwords_id.txt
deleted file mode 100644
index 4617f83..0000000
--- a/solr/example/files/conf/lang/stopwords_id.txt
+++ /dev/null
@@ -1,359 +0,0 @@
-# from appendix D of: A Study of Stemming Effects on Information
-# Retrieval in Bahasa Indonesia
-ada
-adanya
-adalah
-adapun
-agak
-agaknya
-agar
-akan
-akankah
-akhirnya
-aku
-akulah
-amat
-amatlah
-anda
-andalah
-antar
-diantaranya
-antara
-antaranya
-diantara
-apa
-apaan
-mengapa
-apabila
-apakah
-apalagi
-apatah
-atau
-ataukah
-ataupun
-bagai
-bagaikan
-sebagai
-sebagainya
-bagaimana
-bagaimanapun
-sebagaimana
-bagaimanakah
-bagi
-bahkan
-bahwa
-bahwasanya
-sebaliknya
-banyak
-sebanyak
-beberapa
-seberapa
-begini
-beginian
-beginikah
-beginilah
-sebegini
-begitu
-begitukah
-begitulah
-begitupun
-sebegitu
-belum
-belumlah
-sebelum
-sebelumnya
-sebenarnya
-berapa
-berapakah
-berapalah
-berapapun
-betulkah
-sebetulnya
-biasa
-biasanya
-bila
-bilakah
-bisa
-bisakah
-sebisanya
-boleh
-bolehkah
-bolehlah
-buat
-bukan
-bukankah
-bukanlah
-bukannya
-cuma
-percuma
-dahulu
-dalam
-dan
-dapat
-dari
-daripada
-dekat
-demi
-demikian
-demikianlah
-sedemikian
-dengan
-depan
-di
-dia
-dialah
-dini
-diri
-dirinya
-terdiri
-dong
-dulu
-enggak
-enggaknya
-entah
-entahlah
-terhadap
-terhadapnya
-hal
-hampir
-hanya
-hanyalah
-harus
-haruslah
-harusnya
-seharusnya
-hendak
-hendaklah
-hendaknya
-hingga
-sehingga
-ia
-ialah
-ibarat
-ingin
-inginkah
-inginkan
-ini
-inikah
-inilah
-itu
-itukah
-itulah
-jangan
-jangankan
-janganlah
-jika
-jikalau
-juga
-justru
-kala
-kalau
-kalaulah
-kalaupun
-kalian
-kami
-kamilah
-kamu
-kamulah
-kan
-kapan
-kapankah
-kapanpun
-dikarenakan
-karena
-karenanya
-ke
-kecil
-kemudian
-kenapa
-kepada
-kepadanya
-ketika
-seketika
-khususnya
-kini
-kinilah
-kiranya
-sekiranya
-kita
-kitalah
-kok
-lagi
-lagian
-selagi
-lah
-lain
-lainnya
-melainkan
-selaku
-lalu
-melalui
-terlalu
-lama
-lamanya
-selama
-selama
-selamanya
-lebih
-terlebih
-bermacam
-macam
-semacam
-maka
-makanya
-makin
-malah
-malahan
-mampu
-mampukah
-mana
-manakala
-manalagi
-masih
-masihkah
-semasih
-masing
-mau
-maupun
-semaunya
-memang
-mereka
-merekalah
-meski
-meskipun
-semula
-mungkin
-mungkinkah
-nah
-namun
-nanti
-nantinya
-nyaris
-oleh
-olehnya
-seorang
-seseorang
-pada
-padanya
-padahal
-paling
-sepanjang
-pantas
-sepantasnya
-sepantasnyalah
-para
-pasti
-pastilah
-per
-pernah
-pula
-pun
-merupakan
-rupanya
-serupa
-saat
-saatnya
-sesaat
-saja
-sajalah
-saling
-bersama
-sama
-sesama
-sambil
-sampai
-sana
-sangat
-sangatlah
-saya
-sayalah
-se
-sebab
-sebabnya
-sebuah
-tersebut
-tersebutlah
-sedang
-sedangkan
-sedikit
-sedikitnya
-segala
-segalanya
-segera
-sesegera
-sejak
-sejenak
-sekali
-sekalian
-sekalipun
-sesekali
-sekaligus
-sekarang
-sekarang
-sekitar
-sekitarnya
-sela
-selain
-selalu
-seluruh
-seluruhnya
-semakin
-sementara
-sempat
-semua
-semuanya
-sendiri
-sendirinya
-seolah
-seperti
-sepertinya
-sering
-seringnya
-serta
-siapa
-siapakah
-siapapun
-disini
-disinilah
-sini
-sinilah
-sesuatu
-sesuatunya
-suatu
-sesudah
-sesudahnya
-sudah
-sudahkah
-sudahlah
-supaya
-tadi
-tadinya
-tak
-tanpa
-setelah
-telah
-tentang
-tentu
-tentulah
-tentunya
-tertentu
-seterusnya
-tapi
-tetapi
-setiap
-tiap
-setidaknya
-tidak
-tidakkah
-tidaklah
-toh
-waduh
-wah
-wahai
-sewaktu
-walau
-walaupun
-wong
-yaitu
-yakni
-yang
diff --git a/solr/example/files/conf/lang/stopwords_it.txt b/solr/example/files/conf/lang/stopwords_it.txt
deleted file mode 100644
index 1219cc7..0000000
--- a/solr/example/files/conf/lang/stopwords_it.txt
+++ /dev/null
@@ -1,303 +0,0 @@
- | 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
diff --git a/solr/example/files/conf/lang/stopwords_ja.txt b/solr/example/files/conf/lang/stopwords_ja.txt
deleted file mode 100644
index d4321be..0000000
--- a/solr/example/files/conf/lang/stopwords_ja.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-#
-# This file defines a stopword set for Japanese.
-#
-# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
-# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
-# for frequency lists, etc. that can be useful for making your own set (if desired)
-#
-# Note that there is an overlap between these stopwords and the terms stopped when used
-# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
-# that comments are not allowed on the same line as stopwords.
-#
-# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
-# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
-# using the same character width as the entries in this file. Since this StopFilter is
-# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
-# entries to be in half-width and your kana entries to be in full-width.
-#
-の
-に
-は
-を
-た
-が
-で
-て
-と
-し
-れ
-さ
-ある
-いる
-も
-する
-から
-な
-こと
-として
-い
-や
-れる
-など
-なっ
-ない
-この
-ため
-その
-あっ
-よう
-また
-もの
-という
-あり
-まで
-られ
-なる
-へ
-か
-だ
-これ
-によって
-により
-おり
-より
-による
-ず
-なり
-られる
-において
-ば
-なかっ
-なく
-しかし
-について
-せ
-だっ
-その後
-できる
-それ
-う
-ので
-なお
-のみ
-でき
-き
-つ
-における
-および
-いう
-さらに
-でも
-ら
-たり
-その他
-に関する
-たち
-ます
-ん
-なら
-に対して
-特に
-せる
-及び
-これら
-とき
-では
-にて
-ほか
-ながら
-うち
-そして
-とともに
-ただし
-かつて
-それぞれ
-または
-お
-ほど
-ものの
-に対する
-ほとんど
-と共に
-といった
-です
-とも
-ところ
-ここ
-##### End of file
diff --git a/solr/example/files/conf/lang/stopwords_lv.txt b/solr/example/files/conf/lang/stopwords_lv.txt
deleted file mode 100644
index e21a23c..0000000
--- a/solr/example/files/conf/lang/stopwords_lv.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
-# the original list of over 800 forms was refined:
-# pronouns, adverbs, interjections were removed
-#
-# prepositions
-aiz
-ap
-ar
-apakš
-ārpus
-augšpus
-bez
-caur
-dēļ
-gar
-iekš
-iz
-kopš
-labad
-lejpus
-līdz
-no
-otrpus
-pa
-par
-pār
-pēc
-pie
-pirms
-pret
-priekš
-starp
-šaipus
-uz
-viņpus
-virs
-virspus
-zem
-apakšpus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tomēr
-tikko
-turpretī
-arī
-kaut
-gan
-tādēļ
-tā
-ne
-tikvien
-vien
-kā
-ir
-te
-vai
-kamēr
-# Particles
-ar
-diezin
-droši
-diemžēl
-nebūt
-ik
-it
-taču
-nu
-pat
-tiklab
-iekšpus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iekām
-iekāms
-kolīdz
-līdzko
-tiklīdz
-jebšu
-tālab
-tāpēc
-nekā
-itin
-jā
-jau
-jel
-nē
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-būt
-biju
-biji
-bija
-bijām
-bijāt
-esmu
-esi
-esam
-esat
-būšu
-būsi
-būs
-būsim
-būsiet
-tikt
-tiku
-tiki
-tika
-tikām
-tikāt
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tikšu
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tapāt
-topat
-tapšu
-tapsi
-taps
-tapsim
-tapsiet
-kļūt
-kļuvu
-kļuvi
-kļuva
-kļuvām
-kļuvāt
-kļūstu
-kļūsti
-kļūst
-kļūstam
-kļūstat
-kļūšu
-kļūsi
-kļūs
-kļūsim
-kļūsiet
-# verbs
-varēt
-varēju
-varējām
-varēšu
-varēsim
-var
-varēji
-varējāt
-varēsi
-varēsiet
-varat
-varēja
-varēs
diff --git a/solr/example/files/conf/lang/stopwords_nl.txt b/solr/example/files/conf/lang/stopwords_nl.txt
deleted file mode 100644
index 47a2aea..0000000
--- a/solr/example/files/conf/lang/stopwords_nl.txt
+++ /dev/null
@@ -1,119 +0,0 @@
- | 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
diff --git a/solr/example/files/conf/lang/stopwords_no.txt b/solr/example/files/conf/lang/stopwords_no.txt
deleted file mode 100644
index a7a2c28..0000000
--- a/solr/example/files/conf/lang/stopwords_no.txt
+++ /dev/null
@@ -1,194 +0,0 @@
- | 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 <Ja...@ssb.no>, Jan 2005
-
-og | and
-i | in
-jeg | I
-det | it/this/that
-at | to (w. inf.)
-en | a/an
-et | a/an
-den | it/this/that
-til | to
-er | is/am/are
-som | who/that
-på | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-så | so
-var | was/were
-meg | me
-seg | you
-men | but
-ett | one
-har | have
-om | about
-vi | we
-min | my
-mitt | my
-ha | have
-hadde | had
-hun | she
-nå | now
-over | over
-da | when/as
-ved | by/know
-fra | from
-du | you
-ut | out
-sin | your
-dem | them
-oss | us
-opp | up
-man | you/one
-kan | can
-hans | his
-hvor | where
-eller | or
-hva | what
-skal | shall/must
-selv | self (reflective)
-sjøl | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-når | when
-være | be
-kom | come
-noen | some
-noe | some
-ville | would
-dere | you
-som | who/which/that
-deres | their/theirs
-kun | only/just
-ja | yes
-etter | after
-ned | down
-skulle | should
-denne | this
-for | for/because
-deg | you
-si | hers/his
-sine | hers/his
-sitt | hers/his
-mot | against
-å | to
-meget | much
-hvorfor | why
-dette | this
-disse | these/those
-uten | without
-hvordan | how
-ingen | none
-din | your
-ditt | your
-blir | become
-samme | same
-hvilken | which
-hvilke | which (plural)
-sånn | such a
-inni | inside/within
-mellom | between
-vår | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-både | both
-bare | only/just
-enn | than
-fordi | as/because
-før | before
-mange | many
-også | also
-slik | just
-vært | been
-være | to be
-båe | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-då | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hjå | at *
-ho | she *
-hoe | she *
-henne | her
-hennar | her/hers
-hennes | hers
-hoss | how *
-hossen | how *
-ikkje | not *
-ingi | noone *
-inkje | noone *
-korleis | how *
-korso | how *
-kva | what/which *
-kvar | where *
-kvarhelst | where *
-kven | who/whom *
-kvi | why *
-kvifor | why *
-me | we *
-medan | while *
-mi | my *
-mine | my *
-mykje | much *
-no | now *
-nokon | some (masc./neut.) *
-noka | some (fem.) *
-nokor | some *
-noko | some *
-nokre | some *
-si | his/hers *
-sia | since *
-sidan | since *
-so | so *
-somt | some *
-somme | some *
-um | about*
-upp | up *
-vere | be *
-vore | was *
-verte | become *
-vort | become *
-varte | became *
-vart | became *
-
diff --git a/solr/example/files/conf/lang/stopwords_pt.txt b/solr/example/files/conf/lang/stopwords_pt.txt
deleted file mode 100644
index acfeb01..0000000
--- a/solr/example/files/conf/lang/stopwords_pt.txt
+++ /dev/null
@@ -1,253 +0,0 @@
- | 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
diff --git a/solr/example/files/conf/lang/stopwords_ro.txt b/solr/example/files/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/example/files/conf/lang/stopwords_ro.txt
+++ /dev/null
@@ -1,233 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-acea
-aceasta
-această
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-aceşti
-aceştia
-acolo
-acum
-ai
-aia
-aibă
-aici
-al
-ăla
-ale
-alea
-ălea
-altceva
-altcineva
-am
-ar
-are
-aş
-aşadar
-asemenea
-asta
-ăsta
-astăzi
-astea
-ăstea
-ăştia
-asupra
-aţi
-au
-avea
-avem
-aveţi
-azi
-bine
-bucur
-bună
-ca
-că
-căci
-când
-care
-cărei
-căror
-cărui
-cât
-câte
-câţi
-către
-câtva
-ce
-cel
-ceva
-chiar
-cînd
-cine
-cineva
-cît
-cîte
-cîţi
-cîtva
-contra
-cu
-cum
-cumva
-curând
-curînd
-da
-dă
-dacă
-dar
-datorită
-de
-deci
-deja
-deoarece
-departe
-deşi
-din
-dinaintea
-dintr
-dintre
-drept
-după
-ea
-ei
-el
-ele
-eram
-este
-eşti
-eu
-face
-fără
-fi
-fie
-fiecare
-fii
-fim
-fiţi
-iar
-ieri
-îi
-îl
-îmi
-împotriva
-în
-înainte
-înaintea
-încât
-încît
-încotro
-între
-întrucât
-întrucît
-îţi
-la
-lângă
-le
-li
-lîngă
-lor
-lui
-mă
-mâine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-multă
-mulţi
-ne
-nicăieri
-nici
-nimeni
-nişte
-noastră
-noastre
-noi
-noştri
-nostru
-nu
-ori
-oricând
-oricare
-oricât
-orice
-oricînd
-oricine
-oricît
-oricum
-oriunde
-până
-pe
-pentru
-peste
-pînă
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-să
-săi
-sale
-sau
-său
-se
-şi
-sînt
-sîntem
-sînteţi
-spre
-sub
-sunt
-suntem
-sunteţi
-ta
-tăi
-tale
-tău
-te
-ţi
-ţie
-tine
-toată
-toate
-tot
-toţi
-totuşi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-vă
-vi
-voastră
-voastre
-voi
-voştri
-vostru
-vouă
-vreo
-vreun
diff --git a/solr/example/files/conf/lang/stopwords_ru.txt b/solr/example/files/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 5527140..0000000
--- a/solr/example/files/conf/lang/stopwords_ru.txt
+++ /dev/null
@@ -1,243 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_sv.txt b/solr/example/files/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 096f87f..0000000
--- a/solr/example/files/conf/lang/stopwords_sv.txt
+++ /dev/null
@@ -1,133 +0,0 @@
- | 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
-
diff --git a/solr/example/files/conf/lang/stopwords_th.txt b/solr/example/files/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/example/files/conf/lang/stopwords_th.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-# Thai stopwords from:
-# "Opinion Detection in Thai Political News Columns
-# Based on Subjectivity Analysis"
-# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
-ไว้
-ไม่
-ไป
-ได้
-ให้
-ใน
-โดย
-แห่ง
-แล้ว
-และ
-แรก
-แบบ
-แต่
-เอง
-เห็น
-เลย
-เริ่ม
-เรา
-เมื่อ
-เพื่อ
-เพราะ
-เป็นการ
-เป็น
-เปิดเผย
-เปิด
-เนื่องจาก
-เดียวกัน
-เดียว
-เช่น
-เฉพาะ
-เคย
-เข้า
-เขา
-อีก
-อาจ
-อะไร
-ออก
-อย่าง
-อยู่
-อยาก
-หาก
-หลาย
-หลังจาก
-หลัง
-หรือ
-หนึ่ง
-ส่วน
-ส่ง
-สุด
-สําหรับ
-ว่า
-วัน
-ลง
-ร่วม
-ราย
-รับ
-ระหว่าง
-รวม
-ยัง
-มี
-มาก
-มา
-พร้อม
-พบ
-ผ่าน
-ผล
-บาง
-น่า
-นี้
-นํา
-นั้น
-นัก
-นอกจาก
-ทุก
-ที่สุด
-ที่
-ทําให้
-ทํา
-ทาง
-ทั้งนี้
-ทั้ง
-ถ้า
-ถูก
-ถึง
-ต้อง
-ต่างๆ
-ต่าง
-ต่อ
-ตาม
-ตั้งแต่
-ตั้ง
-ด้าน
-ด้วย
-ดัง
-ซึ่ง
-ช่วง
-จึง
-จาก
-จัด
-จะ
-คือ
-ความ
-ครั้ง
-คง
-ขึ้น
-ของ
-ขอ
-ขณะ
-ก่อน
-ก็
-การ
-กับ
-กัน
-กว่า
-กล่าว
diff --git a/solr/example/files/conf/lang/stopwords_tr.txt b/solr/example/files/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/example/files/conf/lang/stopwords_tr.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-# Turkish stopwords from LUCENE-559
-# merged with the list from "Information Retrieval on Turkish Texts"
-# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
-acaba
-altmış
-altı
-ama
-ancak
-arada
-aslında
-ayrıca
-bana
-bazı
-belki
-ben
-benden
-beni
-benim
-beri
-beş
-bile
-bin
-bir
-birçok
-biri
-birkaç
-birkez
-birşey
-birşeyi
-biz
-bize
-bizden
-bizi
-bizim
-böyle
-böylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunları
-bunların
-bunu
-bunun
-burada
-çok
-çünkü
-da
-daha
-dahi
-de
-defa
-değil
-diğer
-diye
-doksan
-dokuz
-dolayı
-dolayısıyla
-dört
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-eğer
-elli
-en
-etmesi
-etti
-ettiği
-ettiğini
-gibi
-göre
-halen
-hangi
-hatta
-hem
-henüz
-hep
-hepsi
-her
-herhangi
-herkesin
-hiç
-hiçbir
-için
-iki
-ile
-ilgili
-ise
-işte
-itibaren
-itibariyle
-kadar
-karşın
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-kırk
-milyar
-milyon
-mu
-mü
-mı
-nasıl
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-niçin
-o
-olan
-olarak
-oldu
-olduğu
-olduğunu
-olduklarını
-olmadı
-olmadığı
-olmak
-olması
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onları
-onların
-onu
-onun
-otuz
-oysa
-öyle
-pek
-rağmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-şey
-şeyden
-şeyi
-şeyler
-şöyle
-şu
-şuna
-şunda
-şundan
-şunları
-şunu
-tarafından
-trilyon
-tüm
-üç
-üzere
-var
-vardı
-ve
-veya
-ya
-yani
-yapacak
-yapılan
-yapılması
-yapıyor
-yapmak
-yaptı
-yaptığı
-yaptığını
-yaptıkları
-yedi
-yerine
-yetmiş
-yine
-yirmi
-yoksa
-yüz
-zaten
diff --git a/solr/example/files/conf/lang/userdict_ja.txt b/solr/example/files/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/example/files/conf/lang/userdict_ja.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-#
-# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
-#
-# Add entries to this file in order to override the statistical model in terms
-# of segmentation, readings and part-of-speech tags. Notice that entries do
-# not have weights since they are always used when found. This is by-design
-# in order to maximize ease-of-use.
-#
-# Entries are defined using the following CSV format:
-# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
-#
-# Notice that a single half-width space separates tokens and readings, and
-# that the number tokens and readings must match exactly.
-#
-# Also notice that multiple entries with the same <text> is undefined.
-#
-# Whitespace only lines are ignored. Comments are not allowed on entry lines.
-#
-
-# Custom segmentation for kanji compounds
-日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
-関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
-
-# Custom segmentation for compound katakana
-トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
-ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
-
-# Custom reading for former sumo wrestler
-朝青龍,朝青龍,アサショウリュウ,カスタム人名
diff --git a/solr/example/files/conf/managed-schema b/solr/example/files/conf/managed-schema
deleted file mode 100644
index 5ad9883..0000000
--- a/solr/example/files/conf/managed-schema
+++ /dev/null
@@ -1,520 +0,0 @@
-<?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 name="keyword"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="pathHierarchy" 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 name="pathHierarchy" delimiter="/"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="keyword"/>
- </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 name="keyword"/>
- <filter name="lowercase"/>
- </analyzer>
- </fieldType>
- <fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="doubleMetaphone" 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 name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_ar.txt" ignoreCase="true"/>
- <filter name="arabicNormalization"/>
- <filter name="arabicStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_bg.txt" ignoreCase="true"/>
- <filter name="bulgarianStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="elision" articles="lang/contractions_ca.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_ca.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Catalan"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="cjkWidth"/>
- <filter name="lowercase"/>
- <filter name="cjkBigram"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_cz.txt" ignoreCase="true"/>
- <filter name="czechStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Danish"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
- <filter name="germanNormalization"/>
- <filter name="germanLightStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="greekLowercase"/>
- <filter name="stop" words="lang/stopwords_el.txt" ignoreCase="false"/>
- <filter name="greekStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer name="standard"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="englishPossessive"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="porterStem"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="standard"/>
- <filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="englishPossessive"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="porterStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer name="whitespace"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
- <filter name="lowercase"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="porterStem"/>
- <filter name="flattenGraph" />
- </analyzer>
- <analyzer type="query">
- <tokenizer name="whitespace"/>
- <filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="wordDelimiterGraph" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
- <filter name="lowercase"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="porterStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer name="whitespace"/>
- <filter name="synonymGraph" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
- <filter name="lowercase"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="englishMinimalStem"/>
- <filter name="removeDuplicates"/>
- <filter name="flattenGraph" />
- </analyzer>
- <analyzer type="query">
- <tokenizer name="whitespace"/>
- <filter name="synonymGraph" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
- <filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
- <filter name="lowercase"/>
- <filter name="keywordMarker" protected="protwords.txt"/>
- <filter name="englishMinimalStem"/>
- <filter name="removeDuplicates"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
- <filter name="spanishLightStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_eu.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Basque"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <charFilter name="persian"/>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="arabicNormalization"/>
- <filter name="persianNormalization"/>
- <filter name="stop" words="lang/stopwords_fa.txt" ignoreCase="true"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Finnish"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="elision" articles="lang/contractions_fr.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
- <filter name="frenchLightStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="elision" articles="lang/contractions_ga.txt" ignoreCase="true"/>
- <filter name="stop" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
- <filter name="irishLowercase"/>
- <filter name="stop" words="lang/stopwords_ga.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Irish"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
- <analyzer type="index">
- <tokenizer name="standard"/>
- <filter name="stop" words="stopwords.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="standard"/>
- <filter name="stop" words="stopwords.txt" ignoreCase="true"/>
- <filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="lowercase"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer name="standard"/>
- <filter name="stop" words="stopwords.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="reversedWildcard" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="standard"/>
- <filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter name="stop" words="stopwords.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_gl.txt" ignoreCase="true"/>
- <filter name="galicianStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="indicNormalization"/>
- <filter name="hindiNormalization"/>
- <filter name="stop" words="lang/stopwords_hi.txt" ignoreCase="true"/>
- <filter name="hindiStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Hungarian"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_hy.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Armenian"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_id.txt" ignoreCase="true"/>
- <filter name="indonesianStem" stemDerivational="true"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="elision" articles="lang/contractions_it.txt" ignoreCase="true"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
- <filter name="italianLightStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="japanese" mode="search"/>
- <filter name="japaneseBaseForm"/>
- <filter name="japanesePartOfSpeechStop" tags="lang/stoptags_ja.txt"/>
- <filter name="cjkWidth"/>
- <filter name="stop" words="lang/stopwords_ja.txt" ignoreCase="true"/>
- <filter name="japaneseKatakanaStem" minimumLength="4"/>
- <filter name="lowercase"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
- <filter name="koreanPartOfSpeechStop" />
- <filter name="koreanReadingForm" />
- <filter name="lowercase" />
- </analyzer>
- </fieldType>
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_lv.txt" ignoreCase="true"/>
- <filter name="latvianStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
- <filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
- <filter name="snowballPorter" language="Dutch"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Norwegian"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
- <filter name="portugueseLightStem"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_ro.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Romanian"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Russian"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="lowercase"/>
- <filter name="stop" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
- <filter name="snowballPorter" language="Swedish"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="thai"/>
- <filter name="lowercase"/>
- <filter name="stop" words="lang/stopwords_th.txt" ignoreCase="true"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="standard"/>
- <filter name="turkishLowercase"/>
- <filter name="stop" words="lang/stopwords_tr.txt" ignoreCase="false"/>
- <filter name="snowballPorter" language="Turkish"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer name="whitespace"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="text_email_url" class="solr.TextField">
- <analyzer>
- <tokenizer name="UAX29URLEmail"/>
- <filter name="type" types="email_url_types.txt" useWhitelist="true"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="text_shingles" class="solr.TextField" positionIncrementGap="100" multiValued="true">
- <analyzer type="index">
- <tokenizer name="standard"/>
- <!-- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="false" /> -->
- <filter name="length" min="2" max="18"/>
- <filter name="lowercase"/>
- <filter name="patternReplace" pattern="(^[^a-z]+$)" replacement="" replace="all"/>
- <filter name="shingle" minShingleSize="3" maxShingleSize="3"
- outputUnigrams="false" outputUnigramsIfNoShingles="false" tokenSeparator=" " fillerToken="*"/>
- <filter name="patternReplace" pattern="(.*[\*].*)" replacement=""/>
- <filter name="trim"/>
-
- <!-- PRFF could have removed everything down to an empty string, remove if so -->
- <filter name="length" min="1" max="100"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer name="keyword"/>
- <filter name="lowercase"/>
- </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_"/>
-
-
-</schema>
diff --git a/solr/example/files/conf/params.json b/solr/example/files/conf/params.json
deleted file mode 100644
index 22aadcc..0000000
--- a/solr/example/files/conf/params.json
+++ /dev/null
@@ -1,34 +0,0 @@
-{"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}}}}
diff --git a/solr/example/files/conf/protwords.txt b/solr/example/files/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/example/files/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
diff --git a/solr/example/files/conf/solrconfig.xml b/solr/example/files/conf/solrconfig.xml
deleted file mode 100644
index 5d7bedd..0000000
--- a/solr/example/files/conf/solrconfig.xml
+++ /dev/null
@@ -1,1423 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>9.0.0</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <!-- browse-resources must come before solr-velocity JAR in order to override localized resources -->
- <lib path="${solr.install.dir:../../../..}/example/files/browse-resources"/>
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory
- or solr.NIOFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based and not persistent.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="solr.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory. -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>15000</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
- <!--
- <autoSoftCommit>
- <maxTime>1000</maxTime>
- </autoSoftCommit>
- -->
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>${solr.max.booleanClauses:1024}</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
- Starting with Solr 9.0 the default cache implementation used is CaffeineCache.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate.
-
- Parameters:
- class - the SolrCache implementation (CaffeineCache by default)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.CaffeineCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by CaffeineCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
- <queryResultCache class="solr.CaffeineCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.CaffeineCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.CaffeineCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.CaffeineCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- -->
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Circuit Breaker Section - This section consists of configurations for
- circuit breakers
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <circuitBreaker class="solr.CircuitBreakerManager" enabled="true">
- <!-- Enable Circuit Breakers
-
- Circuit breakers are designed to allow stability and predictable query
- execution. They prevent operations that can take down the node and cause
- noisy neighbour issues.
-
- This flag is the uber control switch which controls the activation/deactivation of all circuit
- breakers. At the moment, the only circuit breaker (max JVM circuit breaker) does not have its
- own specific configuration. However, if a circuit breaker wishes to be independently configurable,
- they are free to add their specific configuration but need to ensure that this flag is always
- respected - this should have veto over all independent configuration flags.
- -->
-
- <!-- Memory Circuit Breaker Control Flag
-
- Use the following flag to control the behaviour of this circuit breaker
- -->
- <str name="memEnabled">true</str>
-
- <!-- Memory Circuit Breaker Threshold In Percentage
-
- Specific configuration for max JVM heap usage circuit breaker. This configuration defines the
- threshold percentage of maximum heap allocated beyond which queries will be rejected until the
- current JVM usage goes below the threshold. The valid value range for this parameter is 50 - 95.
-
- Consider a scenario where the max heap allocated is 4 GB and memoryCircuitBreakerThresholdPct is
- defined as 75. Threshold JVM usage will be 4 * 0.75 = 3 GB. Its generally a good idea to keep this value between 75 - 80% of maximum heap
- allocated.
-
- If, at any point, the current JVM heap usage goes above 3 GB, queries will be rejected until the heap usage goes below 3 GB again.
- If you see queries getting rejected with 503 error code, check for "Circuit Breakers tripped"
- in logs and the corresponding error message should tell you what transpired (if the failure
- was caused by tripped circuit breakers).
- -->
- <str name="memThreshold">75</str>
-
- <!-- CPU Based Circuit Breaker Control Flag
-
- Use the following flag to control the behaviour of this circuit breaker
- -->
- <str name="cpuEnabled">true</str>
-
- <!-- CPU Based Circuit Breaker Triggering Threshold
-
- The triggering threshold is defined in units of CPU utilization. The configuration to control this is as below:
- -->
- <str name="cpuThreshold">75</str>
-
-
- </circuitBreaker>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
- -->
- <requestDispatcher>
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- Before enabling remote streaming, you should make sure your
- system has authentication enabled.
-
- <requestParsers enableRemoteStreaming="false"
- multipartUploadLimitInKB="-1"
- formdataUploadLimitInKB="-1"
- addHttpRequestToContext="false"/>
- -->
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <!-- Default search field
- <str name="df">text</str>
- -->
- <!-- Change from JSON to XML format (the default prior to Solr 7.0)
- <str name="wt">xml</str>
- -->
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- </lst>
- </requestHandler>
-
-
- <!--These useParams values are available in params.json-->
- <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse"/>
-
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">_text_</str>
- </lst>
- </initParams>
-
- <initParams path="/update/**">
- <lst name="defaults">
- <str name="update.chain">files-update-processor</str>
- </lst>
- </initParams>
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="xpath">/xhtml:html/xhtml:body/descendant:node()</str>
- <str name="capture">content</str>
- <str name="fmap.meta">attr_meta_</str>
- <str name="uprefix">attr_</str>
- <str name="lowernames">true</str>
- </lst>
- </requestHandler>
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">text</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck.dictionary">wordbreak</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
-
- <!-- Add unknown fields to the schema
-
- An example field type guessing update processor that will
- attempt to parse string-typed field values as Booleans, Longs,
- Doubles, or Dates, and then add schema fields with the guessed
- field types.
-
- This requires that the schema is both managed and mutable, by
- declaring schemaFactory as ManagedIndexSchemaFactory, with
- mutable specified as true.
-
- See http://wiki.apache.org/solr/GuessingFieldTypes
- -->
- <updateRequestProcessorChain name="files-update-processor">
- <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
- <processor class="solr.UUIDUpdateProcessorFactory" />
- <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
- <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
- <str name="pattern">[^\w-\.]</str>
- <str name="replacement">_</str>
- </processor>
- <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDateFieldUpdateProcessorFactory">
- <arr name="format">
- <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
- <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
- <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
- <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
- <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
- <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
- <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
- </arr>
- </processor>
- <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
- <str name="defaultFieldType">strings</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">pdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">plongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">pdoubles</str>
- </lst>
- </processor>
-
-
- <processor class="org.apache.solr.update.processor.LangDetectLanguageIdentifierUpdateProcessorFactory">
- <lst name="defaults">
- <str name="langid.fl">content</str>
- <str name="langid.langField">language</str>
- </lst>
- </processor>
-
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <!--<lst name="params">-->
- <!--<str name="config_param">example config parameter</str>-->
- <!--</lst>-->
- </processor>
-
- <processor class="solr.LogUpdateProcessorFactory"/>
- <processor class="solr.DistributedUpdateProcessorFactory"/>
- <processor class="solr.RunUpdateProcessorFactory"/>
- </updateRequestProcessorChain>
-
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- </queryResponseWriter>
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://lucene.apache.org/solr/guide/query-syntax-and-parsing.html
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-
-</config>
diff --git a/solr/example/files/conf/stopwords.txt b/solr/example/files/conf/stopwords.txt
deleted file mode 100644
index ae1e83e..0000000
--- a/solr/example/files/conf/stopwords.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-# 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.
diff --git a/solr/example/files/conf/synonyms.txt b/solr/example/files/conf/synonyms.txt
deleted file mode 100644
index eab4ee8..0000000
--- a/solr/example/files/conf/synonyms.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-# 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
-
diff --git a/solr/example/files/conf/update-script.js b/solr/example/files/conf/update-script.js
deleted file mode 100644
index 2589968..0000000
--- a/solr/example/files/conf/update-script.js
+++ /dev/null
@@ -1,115 +0,0 @@
-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
-}
diff --git a/solr/example/files/conf/velocity/browse.vm b/solr/example/files/conf/velocity/browse.vm
deleted file mode 100644
index 535a771..0000000
--- a/solr/example/files/conf/velocity/browse.vm
+++ /dev/null
@@ -1,32 +0,0 @@
-<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,$previous_fq_count))">x</a>
- #end
- #end
- </div>
-
-</div>
-
-
-<div id="browse_results">
- #parse("results.vm")
-</div>
-
diff --git a/solr/example/files/conf/velocity/dropit.js b/solr/example/files/conf/velocity/dropit.js
deleted file mode 100644
index e69de29..0000000
diff --git a/solr/example/files/conf/velocity/facet_doc_type.vm b/solr/example/files/conf/velocity/facet_doc_type.vm
deleted file mode 100644
index ff47167..0000000
--- a/solr/example/files/conf/velocity/facet_doc_type.vm
+++ /dev/null
@@ -1,2 +0,0 @@
-## intentionally empty
-
diff --git a/solr/example/files/conf/velocity/facet_text_shingles.vm b/solr/example/files/conf/velocity/facet_text_shingles.vm
deleted file mode 100644
index ddd9693..0000000
--- a/solr/example/files/conf/velocity/facet_text_shingles.vm
+++ /dev/null
@@ -1,12 +0,0 @@
-<div id="facet_$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>
\ No newline at end of file
diff --git a/solr/example/files/conf/velocity/facets.vm b/solr/example/files/conf/velocity/facets.vm
deleted file mode 100644
index bb27b5c..0000000
--- a/solr/example/files/conf/velocity/facets.vm
+++ /dev/null
@@ -1,24 +0,0 @@
-#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
-
-
-
-
-
diff --git a/solr/example/files/conf/velocity/footer.vm b/solr/example/files/conf/velocity/footer.vm
deleted file mode 100644
index 6cb0096..0000000
--- a/solr/example/files/conf/velocity/footer.vm
+++ /dev/null
@@ -1,29 +0,0 @@
-<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>
\ No newline at end of file
diff --git a/solr/example/files/conf/velocity/head.vm b/solr/example/files/conf/velocity/head.vm
deleted file mode 100644
index a7e9b08..0000000
--- a/solr/example/files/conf/velocity/head.vm
+++ /dev/null
@@ -1,290 +0,0 @@
-<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>
diff --git a/solr/example/files/conf/velocity/hit.vm b/solr/example/files/conf/velocity/hit.vm
deleted file mode 100644
index 2c658cd..0000000
--- a/solr/example/files/conf/velocity/hit.vm
+++ /dev/null
@@ -1,77 +0,0 @@
-
-#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>
-
diff --git a/solr/example/files/conf/velocity/img/english_640.png b/solr/example/files/conf/velocity/img/english_640.png
deleted file mode 100644
index 81256a1..0000000
Binary files a/solr/example/files/conf/velocity/img/english_640.png and /dev/null differ
diff --git a/solr/example/files/conf/velocity/img/france_640.png b/solr/example/files/conf/velocity/img/france_640.png
deleted file mode 100644
index 16d4541..0000000
Binary files a/solr/example/files/conf/velocity/img/france_640.png and /dev/null differ
diff --git a/solr/example/files/conf/velocity/img/germany_640.png b/solr/example/files/conf/velocity/img/germany_640.png
deleted file mode 100644
index f5d6ae8..0000000
Binary files a/solr/example/files/conf/velocity/img/germany_640.png and /dev/null differ
diff --git a/solr/example/files/conf/velocity/img/globe_256.png b/solr/example/files/conf/velocity/img/globe_256.png
deleted file mode 100644
index 514597b..0000000
Binary files a/solr/example/files/conf/velocity/img/globe_256.png and /dev/null differ
diff --git a/solr/example/files/conf/velocity/jquery.tx3-tag-cloud.js b/solr/example/files/conf/velocity/jquery.tx3-tag-cloud.js
deleted file mode 100644
index e69de29..0000000
diff --git a/solr/example/files/conf/velocity/js/dropit.js b/solr/example/files/conf/velocity/js/dropit.js
deleted file mode 100644
index 3094414..0000000
--- a/solr/example/files/conf/velocity/js/dropit.js
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * 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);
diff --git a/solr/example/files/conf/velocity/js/jquery.autocomplete.js b/solr/example/files/conf/velocity/js/jquery.autocomplete.js
deleted file mode 100644
index 442f5a0..0000000
--- a/solr/example/files/conf/velocity/js/jquery.autocomplete.js
+++ /dev/null
@@ -1,763 +0,0 @@
-/*
- * 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] = {
... 665 lines suppressed ...