MappingCharFilter

modules/elasticsearch/src/main/java/org/apache/lucene/analysis/pattern/PatternReplaceFilter.java

@@ -0,0 +1,85 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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 org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+
+import java.util.regex.Pattern;
+import java.util.regex.Matcher;
+import java.io.IOException;
+
+/**
+ * A TokenFilter which applies a Pattern to each token in the stream,
+ * replacing match occurances with the specified replacement string.
+ *
+ * <p>
+ * <b>Note:</b> Depending on the input and the pattern used and the input
+ * TokenStream, this TokenFilter may produce Tokens whose text is the empty
+ * string.
+ * </p>
+ * 
+ * @see Pattern
+ */
+public final class PatternReplaceFilter extends TokenFilter {
+  private final Pattern p;
+  private final String replacement;
+  private final boolean all;
+  private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+  private final Matcher m;
+
+  /**
+   * Constructs an instance to replace either the first, or all occurances
+   *
+   * @param in the TokenStream to process
+   * @param p the patterm to apply to each Token
+   * @param replacement the "replacement string" to substitute, if null a
+   *        blank string will be used. Note that this is not the literal
+   *        string that will be used, '$' and '\' have special meaning.
+   * @param all if true, all matches will be replaced otherwise just the first match.
+   * @see Matcher#quoteReplacement
+   */
+  public PatternReplaceFilter(TokenStream in,
+                              Pattern p,
+                              String replacement,
+                              boolean all) {
+    super(in);
+    this.p=p;
+    this.replacement = (null == replacement) ? "" : replacement;
+    this.all=all;
+    this.m = p.matcher(termAtt);
+  }
+
+  @Override
+  public boolean incrementToken() throws IOException {
+    if (!input.incrementToken()) return false;
+
+    m.reset();
+    if (m.find()) {
+      // replaceAll/replaceFirst will reset() this previous find.
+      String transformed = all ? m.replaceAll(replacement) : m.replaceFirst(replacement);
+      termAtt.setEmpty().append(transformed);
+    }
+
+    return true;
+  }
+
+}

modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java

@@ -366,13 +366,18 @@ private static class DefaultProcessor extends AnalysisBinderProcessor {
     }
 
     private static class ExtendedProcessor extends AnalysisBinderProcessor {
+        @Override public void processCharFilters(CharFiltersBindings charFiltersBindings) {
+            charFiltersBindings.processCharFilter("mapping", MappingCharFilterFactory.class);
+        }
+
         @Override public void processTokenFilters(TokenFiltersBindings tokenFiltersBindings) {
             tokenFiltersBindings.processTokenFilter("snowball", SnowballTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("stemmer", StemmerTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("word_delimiter", WordDelimiterTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("synonym", SynonymTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("elision", ElisionTokenFilterFactory.class);
 
+            tokenFiltersBindings.processTokenFilter("pattern_replace", PatternReplaceTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("phonetic", PhoneticTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("dictionary_decompounder", DictionaryCompoundWordTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("hypennation_decompounder", HyphenationCompoundWordTokenFilterFactory.class);

modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/MappingCharFilterFactory.java

@@ -0,0 +1,121 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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.elasticsearch.index.analysis;
+
+import org.apache.lucene.analysis.CharStream;
+import org.apache.lucene.analysis.MappingCharFilter;
+import org.apache.lucene.analysis.NormalizeCharMap;
+
+import org.elasticsearch.ElasticSearchIllegalArgumentException;
+import org.elasticsearch.common.inject.Inject;
+import org.elasticsearch.common.inject.assistedinject.Assisted;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.Index;
+import org.elasticsearch.index.settings.IndexSettings;
+
+import java.util.*;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+@AnalysisSettingsRequired
+public class MappingCharFilterFactory extends AbstractCharFilterFactory {
+
+    private final NormalizeCharMap normMap;
+
+    @Inject public MappingCharFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name);
+
+        List<String> rules = Analysis.getWordList(env, settings, "mappings");
+        if (rules == null) {
+            throw new ElasticSearchIllegalArgumentException("mapping requires either `mappings` or `mappings_path` to be configured");
+        }
+
+        normMap = new NormalizeCharMap();
+        parseRules(rules, normMap);
+    }
+
+    @Override public CharStream create(CharStream tokenStream) {
+        return new MappingCharFilter(normMap, tokenStream);
+    }
+
+    // source => target
+    private static Pattern rulePattern = Pattern.compile("(.*)\\s*=>\\s*(.*)\\s*$");
+
+    /**
+     * parses a list of MappingCharFilter style rules into a normalize char map
+     */
+    private void parseRules(List<String> rules, NormalizeCharMap map) {
+        for (String rule : rules) {
+            Matcher m = rulePattern.matcher(rule);
+            if (!m.find())
+                throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]");
+            String lhs = parseString(m.group(1).trim());
+            String rhs = parseString(m.group(2).trim());
+            if (lhs == null || rhs == null)
+                throw new RuntimeException("Invalid Mapping Rule : [" + rule + "]. Illegal mapping.");
+            map.add(lhs, rhs);
+        }
+    }
+
+    char[] out = new char[256];
+
+    private String parseString(String s) {
+        int readPos = 0;
+        int len = s.length();
+        int writePos = 0;
+        while (readPos < len) {
+            char c = s.charAt(readPos++);
+            if (c == '\\') {
+                if (readPos >= len)
+                    throw new RuntimeException("Invalid escaped char in [" + s + "]");
+                c = s.charAt(readPos++);
+                switch (c) {
+                case '\\':
+                    c = '\\';
+                    break;
+                case 'n':
+                    c = '\n';
+                    break;
+                case 't':
+                    c = '\t';
+                    break;
+                case 'r':
+                    c = '\r';
+                    break;
+                case 'b':
+                    c = '\b';
+                    break;
+                case 'f':
+                    c = '\f';
+                    break;
+                case 'u':
+                    if (readPos + 3 >= len)
+                        throw new RuntimeException("Invalid escaped char in [" + s + "]");
+                    c = (char) Integer.parseInt(s.substring(readPos, readPos + 4), 16);
+                    readPos += 4;
+                    break;
+                }
+            }
+            out[writePos++] = c;
+        }
+        return new String(out, 0, writePos);
+    }
+}

modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/PatternReplaceTokenFilterFactory.java

@@ -0,0 +1,65 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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.elasticsearch.index.analysis;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.pattern.PatternReplaceFilter;
+import org.elasticsearch.ElasticSearchIllegalArgumentException;
+import org.elasticsearch.common.inject.Inject;
+import org.elasticsearch.common.inject.assistedinject.Assisted;
+import org.elasticsearch.common.regex.Regex;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.index.Index;
+import org.elasticsearch.index.settings.IndexSettings;
+
+import java.io.IOException;
+import java.io.Reader;
+import java.util.regex.Pattern;
+
+public class PatternReplaceTokenFilterFactory extends AbstractTokenFilterFactory {
+
+    private final Pattern pattern;
+    private final String replacement;
+    private final boolean all;
+
+    @Inject public PatternReplaceTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name, settings);
+
+        String sPattern = settings.get("pattern", "");
+        if (sPattern == null) {
+            throw new ElasticSearchIllegalArgumentException("pattern is missing for [" + name + "] token filter of type 'pattern_replace'");
+        }
+
+        this.pattern = Regex.compile(sPattern, settings.get("flags"));
+
+        String sReplacement = settings.get("replacement", "");
+        if (sReplacement == null) {
+            throw new ElasticSearchIllegalArgumentException("replacement is missing for [" + name + "] token filter of type 'pattern_replace'");
+        }
+
+        this.replacement = sReplacement;
+
+        this.all = settings.getAsBoolean("all", true);
+    }
+
+    @Override public TokenStream create(TokenStream tokenStream) {
+        return new PatternReplaceFilter(tokenStream, pattern, replacement, all);
+    }
+}

modules/elasticsearch/src/test/java/org/elasticsearch/index/analysis/AnalysisModuleTests.java

@@ -94,6 +94,12 @@ private void testSimpleConfiguration(Settings settings) {
 //        html = (HtmlStripCharFilterFactory) custom2.charFilters()[1];
 //        assertThat(html.readAheadLimit(), equalTo(1024));
 
+        // verify characters  mapping
+        analyzer = analysisService.analyzer("custom5").analyzer();
+        assertThat(analyzer, instanceOf(CustomAnalyzer.class));
+        CustomAnalyzer custom5 = (CustomAnalyzer) analyzer;
+        assertThat(custom5.tokenFilters()[0], instanceOf(MappingCharFilterFactory.class));
+
         // verify aliases
         analyzer = analysisService.analyzer("alias1").analyzer();
         assertThat(analyzer, instanceOf(StandardAnalyzer.class));

modules/elasticsearch/src/test/java/org/elasticsearch/index/analysis/test1.json

@@ -11,6 +11,10 @@
                     "type" : "html_strip",
                     "escaped_tags" : ["xxx", "yyy"],
                     "read_ahead" : 1024
+                },
+                "my_mapping" : {
+                    "type" : "mapping",
+                    "mappings" : ["ph=>f", "qu=>q"]
                 }
             },
             "filter" : {
@@ -57,6 +61,10 @@
                     "tokenizer" : "standard",
                     "filter" : ["my"]
                 },
+                "custom5" : {
+                    "tokenizer" : "standard",
+                    "char_filter" : ["my_mapping"]
+                },
                 "czechAnalyzerWithStemmer" : {
                     "tokenizer" : "standard",
                     "filter" : ["standard", "lowercase", "stop", "czech_stem"]

modules/elasticsearch/src/test/java/org/elasticsearch/index/analysis/test1.yml

@@ -8,6 +8,9 @@ index :
         type : html_strip
         escaped_tags : [xxx, yyy]
         read_ahead : 1024
+      my_mapping :
+        type : mapping
+        mappings : [ph=>f, qu=>q]
     filter :
       stop :
         type : stop
@@ -41,6 +44,9 @@ index :
       custom4 :
         tokenizer : standard
         filter : [my]
+      custom5 :
+        tokenizer : standard
+        char_filter : [my_mapping]
       czechAnalyzerWithStemmer :
         tokenizer : standard
         filter : [standard, lowercase, stop, czech_stem]