danmuzi commented on a change in pull request #1995: URL: https://github.com/apache/lucene-solr/pull/1995#discussion_r506695505
########## File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTypingFilterFactory.java ########## @@ -0,0 +1,120 @@ +/* + * 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. + */ + +package org.apache.lucene.analysis.pattern; + +import java.io.IOException; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.regex.Pattern; + +import org.apache.lucene.analysis.TokenFilterFactory; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.util.ResourceLoader; +import org.apache.lucene.util.ResourceLoaderAware; + + +/** + * Provides a filter that will analyze tokens with the analyzer from an arbitrary field type. By itself this + * filter is not very useful. Normally it is combined with a filter that reacts to types or flags. + * + * <pre class="prettyprint" > + * <fieldType name="text_taf" class="solr.TextField" positionIncrementGap="100"> + * <analyzer> + * <tokenizer class="solr.WhitespaceTokenizerFactory"/> + * <filter class="com.example.PatternTypingFilter" patternFile="patterns.txt"/> + * <filter class="solr.TokenAnalyzerFilter" asType="text_en" preserveType="true"/> + * <filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" + * ignore="word,&lt;ALPHANUM&gt;,&lt;NUM&gt;,&lt;SOUTHEAST_ASIAN&gt;,&lt;IDEOGRAPHIC&gt;,&lt;HIRAGANA&gt;,&lt;KATAKANA&gt;,&lt;HANGUL&gt;,&lt;EMOJI&gt;"/> + * </analyzer> + * </fieldType></pre> + * <p> + * Note that a configuration such as above may interfere with multi-word synonyms. The patterns file has the format: + * <pre> + * (flags) (pattern) ::: (replacement) + * </pre> + * Therefore to set the first 2 flag bits on the original token matching 401k or 401(k) and adding a type of + * 'legal2_401_k' whenever either one is encountered one would use: + * <pre> + * 3 (\d+)\(?([a-z])\)? ::: legal2_$1_$2 + * </pre> + * Note that the number indicating the flag bits to set must not have leading spaces and be followed by a single + * space, and must be 0 if no flags should be set. The flags number should not contain commas or a decimal point. + * Lines for which the first character is <code>#</code> will be ignored as comments. Does not support producing + * a synonym textually identical to the original term. + * + * @lucene.spi {@value #NAME} + * @since 8.8 + */ +public class PatternTypingFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { + + /** + * SPI name + */ + public static final String NAME = "patternTyping"; + + private final String patternFile; + // todo, perhaps this could be turned into an FST (wanted: regex FST with capturing groups in java) + private final LinkedHashMap<Pattern, String> patterns = new LinkedHashMap<>(); + private final Map<Pattern, Integer> flags = new HashMap<>(); + + /** + * Creates a new KeepWordFilterFactory + */ + public PatternTypingFilterFactory(Map<String, String> args) { + super(args); + patternFile = require(args, "patternFile"); + if (!args.isEmpty()) { + throw new IllegalArgumentException("Unknown parameters: " + args); + } + } + + /** Default ctor for compatibility with SPI */ + public PatternTypingFilterFactory() { + throw defaultCtorException(); + } + + @Override + public void inform(ResourceLoader loader) throws IOException { + List<String> lines = getLines(loader, patternFile); + // format: # regex ::: typename[_$1[_$2 ...]] (technically _$1 does not need the '_' but it usually makes sense) + // eg: 2 (\d+\(?([a-z])\)?\(?(\d+)\)? ::: legal3_$1_$2_3 + // which yields legal3_501_c_3 for 501(c)(3) or 501c3 and sets the second lowest bit in flags + for (String line : lines) { + if (line.trim().startsWith("#")) { Review comment: This part seems to be checked in WordlistLoader.getLines! https://github.com/apache/lucene-solr/blob/f7be9e83e43a549aa92ca6dc26972325f418100a/lucene/core/src/java/org/apache/lucene/analysis/AbstractAnalysisFactory.java#L280-L282 https://github.com/apache/lucene-solr/blob/f7be9e83e43a549aa92ca6dc26972325f418100a/lucene/core/src/java/org/apache/lucene/analysis/WordlistLoader.java#L217-L227 ########## File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTypingFilterFactory.java ########## @@ -0,0 +1,120 @@ +/* + * 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. + */ + +package org.apache.lucene.analysis.pattern; + +import java.io.IOException; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.regex.Pattern; + +import org.apache.lucene.analysis.TokenFilterFactory; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.util.ResourceLoader; +import org.apache.lucene.util.ResourceLoaderAware; + + +/** + * Provides a filter that will analyze tokens with the analyzer from an arbitrary field type. By itself this + * filter is not very useful. Normally it is combined with a filter that reacts to types or flags. + * + * <pre class="prettyprint" > + * <fieldType name="text_taf" class="solr.TextField" positionIncrementGap="100"> + * <analyzer> + * <tokenizer class="solr.WhitespaceTokenizerFactory"/> + * <filter class="com.example.PatternTypingFilter" patternFile="patterns.txt"/> + * <filter class="solr.TokenAnalyzerFilter" asType="text_en" preserveType="true"/> + * <filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" + * ignore="word,&lt;ALPHANUM&gt;,&lt;NUM&gt;,&lt;SOUTHEAST_ASIAN&gt;,&lt;IDEOGRAPHIC&gt;,&lt;HIRAGANA&gt;,&lt;KATAKANA&gt;,&lt;HANGUL&gt;,&lt;EMOJI&gt;"/> + * </analyzer> + * </fieldType></pre> + * <p> + * Note that a configuration such as above may interfere with multi-word synonyms. The patterns file has the format: + * <pre> + * (flags) (pattern) ::: (replacement) + * </pre> + * Therefore to set the first 2 flag bits on the original token matching 401k or 401(k) and adding a type of + * 'legal2_401_k' whenever either one is encountered one would use: + * <pre> + * 3 (\d+)\(?([a-z])\)? ::: legal2_$1_$2 + * </pre> + * Note that the number indicating the flag bits to set must not have leading spaces and be followed by a single + * space, and must be 0 if no flags should be set. The flags number should not contain commas or a decimal point. + * Lines for which the first character is <code>#</code> will be ignored as comments. Does not support producing + * a synonym textually identical to the original term. + * + * @lucene.spi {@value #NAME} + * @since 8.8 + */ +public class PatternTypingFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { + + /** + * SPI name + */ + public static final String NAME = "patternTyping"; + + private final String patternFile; + // todo, perhaps this could be turned into an FST (wanted: regex FST with capturing groups in java) + private final LinkedHashMap<Pattern, String> patterns = new LinkedHashMap<>(); + private final Map<Pattern, Integer> flags = new HashMap<>(); + + /** + * Creates a new KeepWordFilterFactory + */ + public PatternTypingFilterFactory(Map<String, String> args) { + super(args); + patternFile = require(args, "patternFile"); + if (!args.isEmpty()) { + throw new IllegalArgumentException("Unknown parameters: " + args); + } + } + + /** Default ctor for compatibility with SPI */ + public PatternTypingFilterFactory() { + throw defaultCtorException(); + } + + @Override + public void inform(ResourceLoader loader) throws IOException { + List<String> lines = getLines(loader, patternFile); + // format: # regex ::: typename[_$1[_$2 ...]] (technically _$1 does not need the '_' but it usually makes sense) + // eg: 2 (\d+\(?([a-z])\)?\(?(\d+)\)? ::: legal3_$1_$2_3 + // which yields legal3_501_c_3 for 501(c)(3) or 501c3 and sets the second lowest bit in flags + for (String line : lines) { + if (line.trim().startsWith("#")) { + continue; // allow for comments + } + int firstSpace = line.indexOf(" "); // no leading spaces allowed + int flagsVal = Integer.parseInt(line.substring(0,firstSpace)); Review comment: Space character is missing after the comma in the substring method parameter! ########## File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTypingFilterFactory.java ########## @@ -0,0 +1,120 @@ +/* + * 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. + */ + +package org.apache.lucene.analysis.pattern; + +import java.io.IOException; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.regex.Pattern; + +import org.apache.lucene.analysis.TokenFilterFactory; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.util.ResourceLoader; +import org.apache.lucene.util.ResourceLoaderAware; + + +/** + * Provides a filter that will analyze tokens with the analyzer from an arbitrary field type. By itself this + * filter is not very useful. Normally it is combined with a filter that reacts to types or flags. + * + * <pre class="prettyprint" > + * <fieldType name="text_taf" class="solr.TextField" positionIncrementGap="100"> + * <analyzer> + * <tokenizer class="solr.WhitespaceTokenizerFactory"/> + * <filter class="com.example.PatternTypingFilter" patternFile="patterns.txt"/> + * <filter class="solr.TokenAnalyzerFilter" asType="text_en" preserveType="true"/> + * <filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" + * ignore="word,&lt;ALPHANUM&gt;,&lt;NUM&gt;,&lt;SOUTHEAST_ASIAN&gt;,&lt;IDEOGRAPHIC&gt;,&lt;HIRAGANA&gt;,&lt;KATAKANA&gt;,&lt;HANGUL&gt;,&lt;EMOJI&gt;"/> + * </analyzer> + * </fieldType></pre> + * <p> + * Note that a configuration such as above may interfere with multi-word synonyms. The patterns file has the format: + * <pre> + * (flags) (pattern) ::: (replacement) + * </pre> + * Therefore to set the first 2 flag bits on the original token matching 401k or 401(k) and adding a type of + * 'legal2_401_k' whenever either one is encountered one would use: + * <pre> + * 3 (\d+)\(?([a-z])\)? ::: legal2_$1_$2 + * </pre> + * Note that the number indicating the flag bits to set must not have leading spaces and be followed by a single + * space, and must be 0 if no flags should be set. The flags number should not contain commas or a decimal point. + * Lines for which the first character is <code>#</code> will be ignored as comments. Does not support producing + * a synonym textually identical to the original term. + * + * @lucene.spi {@value #NAME} + * @since 8.8 + */ +public class PatternTypingFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { + + /** + * SPI name + */ + public static final String NAME = "patternTyping"; + + private final String patternFile; + // todo, perhaps this could be turned into an FST (wanted: regex FST with capturing groups in java) + private final LinkedHashMap<Pattern, String> patterns = new LinkedHashMap<>(); + private final Map<Pattern, Integer> flags = new HashMap<>(); + + /** + * Creates a new KeepWordFilterFactory + */ + public PatternTypingFilterFactory(Map<String, String> args) { + super(args); + patternFile = require(args, "patternFile"); + if (!args.isEmpty()) { + throw new IllegalArgumentException("Unknown parameters: " + args); + } + } + + /** Default ctor for compatibility with SPI */ + public PatternTypingFilterFactory() { + throw defaultCtorException(); + } + + @Override + public void inform(ResourceLoader loader) throws IOException { + List<String> lines = getLines(loader, patternFile); + // format: # regex ::: typename[_$1[_$2 ...]] (technically _$1 does not need the '_' but it usually makes sense) + // eg: 2 (\d+\(?([a-z])\)?\(?(\d+)\)? ::: legal3_$1_$2_3 + // which yields legal3_501_c_3 for 501(c)(3) or 501c3 and sets the second lowest bit in flags + for (String line : lines) { + if (line.trim().startsWith("#")) { + continue; // allow for comments + } + int firstSpace = line.indexOf(" "); // no leading spaces allowed + int flagsVal = Integer.parseInt(line.substring(0,firstSpace)); + line = line.substring(firstSpace + 1); + String[] split = line.split(" ::: "); // arbitrary, unlikely to occur in a useful regex easy to read + if (split.length != 2) { + throw new RuntimeException("The PatternRecognizerFilter: Always two there are, no more, no less, a pattern and a replacement (separated by ' ::: ' )"); Review comment: Perhaps PatternTypingFilter is right instead of PatternRecognizerFilter. ########## File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTypingFilter.java ########## @@ -0,0 +1,78 @@ +/* + * 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. + */ + +package org.apache.lucene.analysis.pattern; + +import java.io.IOException; +import java.util.LinkedHashMap; +import java.util.Map; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +import org.apache.lucene.analysis.TokenFilter; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.analysis.tokenattributes.FlagsAttribute; +import org.apache.lucene.analysis.tokenattributes.TypeAttribute; + +/** + * Set a type attribute to a parameterized value when tokens are matched by any of a several regex patterns. The + * value set in the type attribute is parameterized with the match groups of the regex used for matching. + * In combination with TypeAsSynonymFilter and DropIfFlagged filter this can supply complex synonym patterns + * that are protected from subsequent analysis, and optionally drop the original term based on the flag + * set in this filter. See {@link PatternTypingFilterFactory} for full documentation. + * + * @since 8.8.0 + * @see PatternTypingFilterFactory + */ +public class PatternTypingFilter extends TokenFilter { + + private final Map<Pattern, String> patterns; + private final Map<Pattern, Integer> flags; + private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); + private final FlagsAttribute flagAtt = addAttribute(FlagsAttribute.class); + private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class); + + public PatternTypingFilter(TokenStream input, LinkedHashMap<Pattern,String> patterns, Map<Pattern,Integer> flags) { Review comment: Space character is missing after the comma in the Map and LinkedHashMap! ########## File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/pattern/PatternTypingFilterFactory.java ########## @@ -0,0 +1,120 @@ +/* + * 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. + */ + +package org.apache.lucene.analysis.pattern; + +import java.io.IOException; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.regex.Pattern; + +import org.apache.lucene.analysis.TokenFilterFactory; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.util.ResourceLoader; +import org.apache.lucene.util.ResourceLoaderAware; + + +/** + * Provides a filter that will analyze tokens with the analyzer from an arbitrary field type. By itself this + * filter is not very useful. Normally it is combined with a filter that reacts to types or flags. + * + * <pre class="prettyprint" > + * <fieldType name="text_taf" class="solr.TextField" positionIncrementGap="100"> + * <analyzer> + * <tokenizer class="solr.WhitespaceTokenizerFactory"/> + * <filter class="com.example.PatternTypingFilter" patternFile="patterns.txt"/> + * <filter class="solr.TokenAnalyzerFilter" asType="text_en" preserveType="true"/> + * <filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" + * ignore="word,&lt;ALPHANUM&gt;,&lt;NUM&gt;,&lt;SOUTHEAST_ASIAN&gt;,&lt;IDEOGRAPHIC&gt;,&lt;HIRAGANA&gt;,&lt;KATAKANA&gt;,&lt;HANGUL&gt;,&lt;EMOJI&gt;"/> + * </analyzer> + * </fieldType></pre> + * <p> + * Note that a configuration such as above may interfere with multi-word synonyms. The patterns file has the format: + * <pre> + * (flags) (pattern) ::: (replacement) + * </pre> + * Therefore to set the first 2 flag bits on the original token matching 401k or 401(k) and adding a type of + * 'legal2_401_k' whenever either one is encountered one would use: + * <pre> + * 3 (\d+)\(?([a-z])\)? ::: legal2_$1_$2 + * </pre> + * Note that the number indicating the flag bits to set must not have leading spaces and be followed by a single + * space, and must be 0 if no flags should be set. The flags number should not contain commas or a decimal point. + * Lines for which the first character is <code>#</code> will be ignored as comments. Does not support producing + * a synonym textually identical to the original term. + * + * @lucene.spi {@value #NAME} + * @since 8.8 + */ +public class PatternTypingFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { + + /** + * SPI name + */ + public static final String NAME = "patternTyping"; + + private final String patternFile; + // todo, perhaps this could be turned into an FST (wanted: regex FST with capturing groups in java) + private final LinkedHashMap<Pattern, String> patterns = new LinkedHashMap<>(); + private final Map<Pattern, Integer> flags = new HashMap<>(); + + /** + * Creates a new KeepWordFilterFactory Review comment: There is a typo in the comment. KeepWordFilterFactory -> PatternTypingFilterFactory ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
