com.jaeksoft.searchlib.template.file_crawler.config.xml Maven / Gradle / Ivy
<?xml version="1.0" encoding="UTF-8"?>
<!-- License Agreement for OpenSearchServer -->
<!-- -->
<!-- Copyright (C) 2008-2014 Emmanuel Keller / Jaeksoft -->
<!-- -->
<!-- This file is part of OpenSearchServer. -->
<!-- http://www.open-search-server.com -->
<!-- -->
<!-- OpenSearchServer is free software: you can -->
<!-- redistribute it and/or modify it under the terms of -->
<!-- the GNU General Public License as published by the -->
<!-- Free Software Foundation, either version 3 of the -->
<!-- License, or (at your option) any later version. -->
<!-- -->
<!-- OpenSearchServer is distributed in the -->
<!-- hope that it will be useful, but WITHOUT ANY -->
<!-- WARRANTY; without even the implied warranty of -->
<!-- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. -->
<!-- -->
<!-- See the GNU General Public License for more details. -->
<configuration>
<indices>
<index name="index" searchCache="100" filterCache="100"
fieldCache="500" remoteURI="{remoteURI}" />
</indices>
<schema>
<analyzers>
<!-- Default standard analyzer -->
<analyzer name="StandardAnalyzer" tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
</analyzer>
<!-- Phonetic analyzer -->
<analyzer name="PhoneticAnalyzer" tokenizer="StandardTokenizer">
<filter class="LowerCaseFilter" />
<filter class="PhoneticFilter" codec="Beider Morse" scope="QUERY_INDEX" />
</analyzer>
<!-- Default text analyser -->
<analyzer name="TextAnalyzer" tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
</analyzer>
<!-- Keyword analyzer -->
<analyzer name="KeywordLikeAnalyzer" tokenizer="KeywordTokenizer">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
</analyzer>
<!-- Arabic -->
<analyzer name="TextAnalyzer" lang="ar" tokenizer="ArabicLetterTokenizer">
<filter class="ArabicNormalizerFilter" />
<filter class="ArabicStemFilter" />
</analyzer>
<!-- Chinese -->
<analyzer name="TextAnalyzer" lang="zh" tokenizer="ChineseTokenizer">
<filter class="ChineseFilter" />
</analyzer>
<!-- Czech -->
<analyzer name="TextAnalyzer" lang="cz"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="CzechStemFilter" />
</analyzer>
<!-- Danish -->
<analyzer name="TextAnalyzer" lang="da"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballDanishFilter" />
</analyzer>
<!-- Dutch -->
<analyzer name="TextAnalyzer" lang="nl"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="DutchStemFilter" />
</analyzer>
<!-- English -->
<analyzer name="TextAnalyzer" lang="en"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="SnowballEnglishFilter" />
</analyzer>
<!-- Finish -->
<analyzer name="TextAnalyzer" lang="fi"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballFinnishFilter" />
</analyzer>
<!-- French -->
<analyzer name="TextAnalyzer" lang="fr"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="FrenchStemFilter" />
</analyzer>
<!-- German -->
<analyzer name="TextAnalyzer" lang="de"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballGermanFilter" />
</analyzer>
<!-- Italian -->
<analyzer name="TextAnalyzer" lang="it"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballItalianFilter" />
</analyzer>
<!-- Japanese -->
<analyzer name="TextAnalyzer" lang="ja" tokenizer="CJKTokenizer" />
<!-- Korean -->
<analyzer name="TextAnalyzer" lang="kr" tokenizer="CJKTokenizer" />
<!-- Norwegian -->
<analyzer name="TextAnalyzer" lang="no"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballNorwegianFilter" />
</analyzer>
<!-- Polish -->
<analyzer name="TextAnalyzer" lang="pl"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="PolishStemFilter" />
</analyzer>
<!-- Portuguese -->
<analyzer name="TextAnalyzer" lang="pt"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballPortugueseFilter" />
</analyzer>
<!-- Romanian -->
<analyzer name="TextAnalyzer" lang="ro"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballRomanianFilter" />
</analyzer>
<!-- Russian -->
<analyzer name="TextAnalyzer" lang="ru" tokenizer="RussianLetterTokenizer">
<filter class="RussianStemFilter" />
</analyzer>
<!-- Spanish -->
<analyzer name="TextAnalyzer" lang="es"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballSpanishFilter" />
</analyzer>
<!-- Swedish -->
<analyzer name="TextAnalyzer" lang="sv"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballSwedishFilter" />
</analyzer>
<!-- Turkish -->
<analyzer name="TextAnalyzer" lang="tr"
tokenizer="LetterOrDigitTokenizerFactory">
<filter class="LowerCaseFilter" />
<filter class="ISOLatin1AccentFilter" />
<filter class="SnowballTurkishFilter" />
</analyzer>
<!-- Autocompletion -->
<analyzer name="AutoCompletionAnalyzer" lang="">
<tokenizer class="StandardTokenizer" />
<filter class="ShingleFilter" max_shingle_size="5"
min_shingle_size="1" scope="QUERY_INDEX" token_separator=" " />
<filter class="PrefixSuffixStopFilter" ignore_case="true"
prefixList="English stop words" scope="QUERY_INDEX" suffixList="English stop words"
token_separator=" " />
<filter class="PrefixSuffixStopFilter" ignore_case="true"
prefixList="French stop words" scope="QUERY_INDEX" suffixList="French stop words"
token_separator=" " />
<filter class="PrefixSuffixStopFilter" ignore_case="true"
prefixList="German stop words" scope="QUERY_INDEX" suffixList="German stop words"
token_separator=" " />
</analyzer>
<!-- Default analyzer for suggestion on autocomplete -->
<analyzer name="SuggestionAnalyzer" lang="">
<tokenizer class="StandardTokenizer" />
<filter class="LowerCaseFilter" scope="QUERY_INDEX" />
<filter class="ISOLatin1AccentFilter" scope="QUERY_INDEX" />
<filter class="EdgeNGramFilter" max_gram="100" min_gram="1"
scope="QUERY_INDEX" side="front" />
</analyzer>
<!-- Numeric -->
<analyzer name="IntegerAnalyzer" lang="">
<tokenizer class="KeywordTokenizer" />
<filter class="NumberFormatFilter"
numberFormat="'>'0000000000;'<'0000000000"
scope="QUERY_INDEX" />
</analyzer>
<analyzer name="LongAnalyzer" lang="">
<tokenizer class="KeywordTokenizer" />
<filter class="NumberFormatFilter"
numberFormat="'>'00000000000000000000;'<'00000000000000000000"
scope="QUERY_INDEX" />
</analyzer>
<analyzer name="DecimalAnalyzer" lang="">
<tokenizer class="KeywordTokenizer" />
<filter class="NumberFormatFilter"
numberFormat="'>'0000000000.##########;'<'0000000000.##########"
scope="QUERY_INDEX" />
</analyzer>
<!-- Geospatial -->
<analyzer name="GeoDegreesAnalyzer" lang="">
<tokenizer class="KeywordTokenizer" />
<filter class="DegreesRadiansFilter"
degrees_radians_conversion="Degrees to Radians" fault_tolerant="true"
scope="QUERY_INDEX" />
</analyzer>
<analyzer name="GeoRadianAnalyzer" lang="">
<tokenizer class="KeywordTokenizer" />
<filter class="DegreesRadiansFilter"
degrees_radians_conversion="Check radians" fault_tolerant="true"
scope="QUERY_INDEX" />
</analyzer>
</analyzers>
<fields default="content" unique="url">
<field name="lang" indexed="yes" stored="no" termVector="no" />
<field name="title" analyzer="TextAnalyzer" indexed="yes"
stored="yes" termVector="positions_offsets" />
<field name="titleExact" analyzer="StandardAnalyzer" indexed="yes"
stored="no" termVector="yes">
<copyOf field="title" />
</field>
<field name="titlePhonetic" analyzer="PhoneticAnalyzer"
indexed="yes" stored="no" termVector="no">
<copyOf field="title" />
</field>
<field name="content" analyzer="TextAnalyzer" indexed="yes"
stored="compress" termVector="positions_offsets" />
<field name="contentExact" analyzer="StandardAnalyzer" indexed="yes"
stored="no" termVector="yes">
<copyOf field="content" />
</field>
<field name="contentPhonetic" analyzer="PhoneticAnalyzer"
indexed="yes" stored="no" termVector="no">
<copyOf field="content" />
</field>
<field name="url" indexed="yes" stored="no" termVector="no" />
<field name="urlSplit" indexed="yes" stored="no" analyzer="TextAnalyzer"
termVector="no">
<copyOf field="url" />
</field>
<field name="urlExact" indexed="yes" stored="no" analyzer="StandardAnalyzer"
termVector="no">
<copyOf field="url" />
</field>
<field name="urlPhonetic" indexed="yes" stored="no"
analyzer="PhoneticAnalyzer" termVector="no">
<copyOf field="url" />
</field>
<field name="fileName" analyzer="TextAnalyzer" indexed="yes"
stored="yes" termVector="positions_offsets" />
<field name="fileNamePhonetic" analyzer="PhoneticAnalyzer"
indexed="yes" stored="no" termVector="no">
<copyOf field="fileName" />
</field>
<field name="fileNameExact" analyzer="StandardAnalyzer"
indexed="yes" stored="no">
<copyOf field="fileName" />
</field>
<field name="full" analyzer="TextAnalyzer" indexed="yes"
stored="no" termVector="no">
<copyOf field="title" />
<copyOf field="content" />
<copyOf field="fileName" />
<copyOf field="url" />
</field>
<field name="fullExact" analyzer="StandardAnalyzer" indexed="yes"
stored="no" termVector="no">
<copyOf field="title" />
<copyOf field="content" />
<copyOf field="fileName" />
<copyOf field="url" />
</field>
<field name="fullPhonetic" analyzer="PhoneticAnalyzer" indexed="yes"
stored="no" termVector="no">
<copyOf field="title" />
<copyOf field="content" />
<copyOf field="fileName" />
<copyOf field="url" />
</field>
<field name="autocomplete" analyzer="AutoCompletionAnalyzer"
indexed="yes" stored="no" termVector="no">
<copyOf field="title" />
<copyOf field="fileName" />
</field>
<field name="directory" indexed="yes" stored="no" />
<field name="subDirectory" indexed="yes" stored="no" />
<field name="crawlDate" indexed="yes" stored="no" />
<field name="fileSystemDate" indexed="yes" stored="no" />
<field name="fileExtension" indexed="yes" stored="no" />
<field name="fileType" indexed="yes" stored="no" />
<field name="fileSize" indexed="yes" stored="no" analyzer="LongAnalyzer" />
<field name="userAllow" indexed="yes" stored="no" />
<field name="userDeny" indexed="yes" stored="no" />
<field name="groupAllow" indexed="yes" stored="no" />
<field name="groupDeny" indexed="yes" stored="no" />
</fields>
</schema>
<statistics>
<statistic type="SEARCH" period="MINUTE" maxRetention="60"
writeToLog="no" />
<statistic type="SEARCH" period="HOUR" maxRetention="24"
writeToLog="yes" />
<statistic type="SEARCH" period="DAY" maxRetention="30"
writeToLog="yes" />
<statistic type="UPDATE" period="HOUR" maxRetention="24"
writeToLog="yes" />
<statistic type="UPDATE" period="DAY" maxRetention="30"
writeToLog="yes" />
<statistic type="DELETE" period="HOUR" maxRetention="24"
writeToLog="yes" />
<statistic type="DELETE" period="DAY" maxRetention="30"
writeToLog="yes" />
<statistic type="RELOAD" period="HOUR" maxRetention="24"
writeToLog="yes" />
<statistic type="RELOAD" period="DAY" maxRetention="30"
writeToLog="yes" />
<statistic type="OPTIMIZE" period="DAY" maxRetention="30"
writeToLog="yes" />
</statistics>
</configuration> © 2015 - 2025 Weber Informatics LLC | Privacy Policy