SOLR-1370: Show the output of CharFilters in FieldAnalysisRequestHandler

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@805880 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Koji Sekiguchi 2009-08-19 17:01:12 +00:00
parent a86d0c24c3
commit 00e1299bd6
5 changed files with 316 additions and 2 deletions

View File

@ -271,6 +271,8 @@ New Features
69. SOLR-1372: Enhance FieldAnalysisRequestHandler to accept field value from content stream (ehatcher) 69. SOLR-1372: Enhance FieldAnalysisRequestHandler to accept field value from content stream (ehatcher)
70. SOLR-1370: Show the output of CharFilters in FieldAnalysisRequestHandler (koji)
Optimizations Optimizations
---------------------- ----------------------

View File

@ -18,10 +18,14 @@
package org.apache.solr.handler; package org.apache.solr.handler;
import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharReader;
import org.apache.lucene.analysis.CharStream;
import org.apache.lucene.analysis.Token; import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.analysis.CharFilterFactory;
import org.apache.solr.analysis.TokenFilterFactory; import org.apache.solr.analysis.TokenFilterFactory;
import org.apache.solr.analysis.TokenizerChain; import org.apache.solr.analysis.TokenizerChain;
import org.apache.solr.analysis.TokenizerFactory;
import org.apache.solr.common.util.NamedList; import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.util.SimpleOrderedMap; import org.apache.solr.common.util.SimpleOrderedMap;
import org.apache.solr.common.SolrException; import org.apache.solr.common.SolrException;
@ -83,17 +87,29 @@ public abstract class AnalysisRequestHandlerBase extends RequestHandlerBase {
} }
TokenizerChain tokenizerChain = (TokenizerChain) analyzer; TokenizerChain tokenizerChain = (TokenizerChain) analyzer;
CharFilterFactory[] cfiltfacs = tokenizerChain.getCharFilterFactories();
TokenizerFactory tfac = tokenizerChain.getTokenizerFactory();
TokenFilterFactory[] filtfacs = tokenizerChain.getTokenFilterFactories();
NamedList<List<NamedList>> namedList = new SimpleOrderedMap<List<NamedList>>(); NamedList<List<NamedList>> namedList = new SimpleOrderedMap<List<NamedList>>();
TokenStream tokenStream = tokenizerChain.getTokenizerFactory().create(new StringReader(value)); if( cfiltfacs != null ){
String source = value;
for(CharFilterFactory cfiltfac : cfiltfacs ){
CharStream reader = CharReader.get(new StringReader(source));
reader = cfiltfac.create(reader);
source = writeCharStream(namedList, reader);
}
}
TokenStream tokenStream = tfac.create(tokenizerChain.charStream(new StringReader(value)));
List<Token> tokens = analyzeTokenStream(tokenStream); List<Token> tokens = analyzeTokenStream(tokenStream);
namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokens, context)); namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokens, context));
ListBasedTokenStream listBasedTokenStream = new ListBasedTokenStream(tokens); ListBasedTokenStream listBasedTokenStream = new ListBasedTokenStream(tokens);
for (TokenFilterFactory tokenFilterFactory : tokenizerChain.getTokenFilterFactories()) { for (TokenFilterFactory tokenFilterFactory : filtfacs) {
tokenStream = tokenFilterFactory.create(listBasedTokenStream); tokenStream = tokenFilterFactory.create(listBasedTokenStream);
List<Token> tokenList = analyzeTokenStream(tokenStream); List<Token> tokenList = analyzeTokenStream(tokenStream);
namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokenList, context)); namedList.add(tokenStream.getClass().getName(), convertTokensToNamedLists(tokenList, context));
@ -188,6 +204,23 @@ public abstract class AnalysisRequestHandlerBase extends RequestHandlerBase {
return tokensNamedLists; return tokensNamedLists;
} }
private String writeCharStream(NamedList out, CharStream input ){
final int BUFFER_SIZE = 1024;
char[] buf = new char[BUFFER_SIZE];
int len = 0;
StringBuilder sb = new StringBuilder();
do {
try {
len = input.read( buf, 0, BUFFER_SIZE );
} catch (IOException e) {
throw new SolrException(SolrException.ErrorCode.BAD_REQUEST, e);
}
sb.append(buf, 0, len);
} while( len == BUFFER_SIZE );
out.add( input.getClass().getName(), sb.toString());
return sb.toString();
}
// ================================================= Inner classes ================================================= // ================================================= Inner classes =================================================

View File

@ -293,4 +293,30 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
} }
public void testCharFilterAnalysis() throws Exception {
FieldAnalysisRequest request = new FieldAnalysisRequest();
request.addFieldType("charfilthtmlmap");
request.setFieldValue("<html><body>whátëvêr</body></html>");
request.setShowMatch(false);
NamedList<NamedList> result = handler.handleAnalysisRequest(request, h.getCore().getSchema());
assertTrue("result is null and it shouldn't be", result != null);
NamedList<NamedList> fieldTypes = result.get("field_types");
assertNotNull("field_types should never be null", fieldTypes);
NamedList<NamedList> textType = fieldTypes.get("charfilthtmlmap");
assertNotNull("expecting result for field type 'charfilthtmlmap'", textType);
NamedList indexPart = textType.get("index");
assertNotNull("expecting an index token analysis for field type 'charfilthtmlmap'", indexPart);
assertEquals(" whátëvêr ", indexPart.get("org.apache.solr.analysis.HTMLStripCharFilter"));
assertEquals(" whatever ", indexPart.get("org.apache.lucene.analysis.MappingCharFilter"));
List<NamedList> tokenList = (List<NamedList>)indexPart.get("org.apache.lucene.analysis.WhitespaceTokenizer");
assertNotNull("Expcting WhitespaceTokenizer analysis breakdown", tokenList);
assertEquals(tokenList.size(), 1);
assertToken(tokenList.get(0), new TokenInfo("whatever", null, "word", 12, 20, 1, null, false));
}
} }

View File

@ -0,0 +1,246 @@
# 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.
# Syntax:
# "source" => "target"
# "source".length() > 0 (source cannot be empty.)
# "target".length() >= 0 (target can be empty.)
# example:
# "À" => "A"
# "\u00C0" => "A"
# "\u00C0" => "\u0041"
# "ß" => "ss"
# "\t" => " "
# "\n" => ""
# À => A
"\u00C0" => "A"
# Á => A
"\u00C1" => "A"
# Â => A
"\u00C2" => "A"
# Ã => A
"\u00C3" => "A"
# Ä => A
"\u00C4" => "A"
# Å => A
"\u00C5" => "A"
# Æ => AE
"\u00C6" => "AE"
# Ç => C
"\u00C7" => "C"
# È => E
"\u00C8" => "E"
# É => E
"\u00C9" => "E"
# Ê => E
"\u00CA" => "E"
# Ë => E
"\u00CB" => "E"
# Ì => I
"\u00CC" => "I"
# Í => I
"\u00CD" => "I"
# Î => I
"\u00CE" => "I"
# Ï => I
"\u00CF" => "I"
# IJ => IJ
"\u0132" => "IJ"
# Ð => D
"\u00D0" => "D"
# Ñ => N
"\u00D1" => "N"
# Ò => O
"\u00D2" => "O"
# Ó => O
"\u00D3" => "O"
# Ô => O
"\u00D4" => "O"
# Õ => O
"\u00D5" => "O"
# Ö => O
"\u00D6" => "O"
# Ø => O
"\u00D8" => "O"
# Œ => OE
"\u0152" => "OE"
# Þ
"\u00DE" => "TH"
# Ù => U
"\u00D9" => "U"
# Ú => U
"\u00DA" => "U"
# Û => U
"\u00DB" => "U"
# Ü => U
"\u00DC" => "U"
# Ý => Y
"\u00DD" => "Y"
# Ÿ => Y
"\u0178" => "Y"
# à => a
"\u00E0" => "a"
# á => a
"\u00E1" => "a"
# â => a
"\u00E2" => "a"
# ã => a
"\u00E3" => "a"
# ä => a
"\u00E4" => "a"
# å => a
"\u00E5" => "a"
# æ => ae
"\u00E6" => "ae"
# ç => c
"\u00E7" => "c"
# è => e
"\u00E8" => "e"
# é => e
"\u00E9" => "e"
# ê => e
"\u00EA" => "e"
# ë => e
"\u00EB" => "e"
# ì => i
"\u00EC" => "i"
# í => i
"\u00ED" => "i"
# î => i
"\u00EE" => "i"
# ï => i
"\u00EF" => "i"
# ij => ij
"\u0133" => "ij"
# ð => d
"\u00F0" => "d"
# ñ => n
"\u00F1" => "n"
# ò => o
"\u00F2" => "o"
# ó => o
"\u00F3" => "o"
# ô => o
"\u00F4" => "o"
# õ => o
"\u00F5" => "o"
# ö => o
"\u00F6" => "o"
# ø => o
"\u00F8" => "o"
# œ => oe
"\u0153" => "oe"
# ß => ss
"\u00DF" => "ss"
# þ => th
"\u00FE" => "th"
# ù => u
"\u00F9" => "u"
# ú => u
"\u00FA" => "u"
# û => u
"\u00FB" => "u"
# ü => u
"\u00FC" => "u"
# ý => y
"\u00FD" => "y"
# ÿ => y
"\u00FF" => "y"
# ff => ff
"\uFB00" => "ff"
# fi => fi
"\uFB01" => "fi"
# fl => fl
"\uFB02" => "fl"
# ffi => ffi
"\uFB03" => "ffi"
# ffl => ffl
"\uFB04" => "ffl"
# ſt => ft
"\uFB05" => "ft"
# st => st
"\uFB06" => "st"

View File

@ -247,6 +247,13 @@
<filter class="solr.LengthFilterFactory" min="2" max="5"/> <filter class="solr.LengthFilterFactory" min="2" max="5"/>
</analyzer> </analyzer>
</fieldtype> </fieldtype>
<fieldType name="charfilthtmlmap" class="solr.TextField">
<analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100"> <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
<analyzer type="index"> <analyzer type="index">