/lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/id/ |
H A D | IndonesianStemmer.java | 28 * http://www.illc.uva.nl/Publications/ResearchReports/MoL-2003-02.text.pdf 47 public int stem(char text[], int length, boolean stemDerivational) { argument 51 if (isVowel(text[i])) 54 if (numSyllables > 2) length = removeParticle(text, length); 55 if (numSyllables > 2) length = removePossessivePronoun(text, length); 58 length = stemDerivational(text, length); 62 private int stemDerivational(char text[], int length) { argument 64 if (numSyllables > 2) length = removeFirstOrderPrefix(text, length); 67 if (numSyllables > 2) length = removeSuffix(text, length); 69 if (numSyllables > 2) length = removeSecondOrderPrefix(text, lengt 90 removeParticle(char text[], int length) argument 101 removePossessivePronoun(char text[], int length) argument 115 removeFirstOrderPrefix(char text[], int length) argument 206 removeSecondOrderPrefix(char text[], int length) argument 245 removeSuffix(char text[], int length) argument [all...] |
/lucene-3.6.0/lucene/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/stats/ |
H A D | Report.java | 25 private String text; field in class:Report 30 public Report (String text, int size, int reported, int outOf) { argument 31 this.text = text; 52 * Returns the report text. 55 return text;
|
/lucene-3.6.0/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/standard/processors/ |
H A D | WildcardQueryNodeProcessor.java | 58 CharSequence text = fqn.getText(); 64 || text.length() <= 0){ 71 if (isPrefixWildcard(text)) { 75 } else if (isWildcard(text)){ 86 private boolean isWildcard(CharSequence text) { argument 87 if (text ==null || text.length() <= 0) return false; 91 for(int i=text.length()-1; i>=0; i--){ 92 if ((text.charAt(i) == '*' || text 100 isPrefixWildcard(CharSequence text) argument [all...] |
/lucene-3.6.0/lucene/core/src/java/org/apache/lucene/index/ |
H A D | Term.java | 23 A Term represents a word from text. This is the unit of search. It is 24 composed of two elements, the text of the word, as a string, and the name of 25 the field that the text occurred in, an interned string. 27 Note that terms may represent more than words from text fields, but also 32 String text; field in class:Term 34 /** Constructs a Term with the given field and text. 35 * <p>Note that a null field or null text value results in undefined 39 text = txt; 42 /** Constructs a Term with the given field and empty text. 54 text 64 public final String text() { return text; } method in class:Term 72 createTerm(String text) argument [all...] |
H A D | FormatPostingsTermsConsumer.java | 33 abstract FormatPostingsDocsConsumer addTerm(char[] text, int start) throws IOException; argument 36 FormatPostingsDocsConsumer addTerm(String text) throws IOException { argument 37 final int len = text.length(); 40 text.getChars(0, len, termBuffer, 0);
|
H A D | TermBuffer.java | 29 private boolean dirty; // true if text was set externally (ie not read via UTF8 bytes) 31 private UnicodeUtil.UTF16Result text = new UnicodeUtil.UTF16Result(); field in class:TermBuffer 36 return compareChars(text.result, text.length, other.text.result, other.text.length); 68 text.setLength(totalLength); 69 input.readChars(text.result, start, length); 74 UnicodeUtil.UTF16toUTF8(text.result, 0, text [all...] |
/lucene-3.6.0/lucene/contrib/benchmark/src/test/org/apache/lucene/benchmark/byTask/feeds/demohtml/ |
H A D | TestHtmlParser.java | 30 String text = "<html><body>汉语</body></html>"; 31 HTMLParser parser = new HTMLParser(new StringReader(text)); 36 String text = "<html><body>汉语¥</body></html>"; 37 HTMLParser parser = new HTMLParser(new StringReader(text)); 42 String text = "<html><body>foo<!-- bar --><! baz --></body></html>"; 43 HTMLParser parser = new HTMLParser(new StringReader(text)); 48 String text = "<html><body><script type=\"text/javascript\">" + 50 HTMLParser parser = new HTMLParser(new StringReader(text)); 55 String text [all...] |
/lucene-3.6.0/lucene/contrib/highlighter/src/test/org/apache/lucene/search/vectorhighlight/ |
H A D | BreakIteratorBoundaryScannerTest.java | 20 import java.text.BreakIterator; 27 "Apache Lucene(TM) is a high-performance, full-featured text search engine library written entirely in Java." + 29 "full-text search, especially cross-platform. \nApache Lucene is an open source project available for free download."; 32 StringBuilder text = new StringBuilder(TEXT); 37 assertEquals(start, scanner.findStartOffset(text, start)); 38 assertEquals(start, scanner.findEndOffset(text, start)); 40 assertEquals(start, scanner.findStartOffset(text, start)); 42 assertEquals(start, scanner.findEndOffset(text, start)); 46 StringBuilder text = new StringBuilder(TEXT); 52 testFindStartOffset(text, star 84 testFindStartOffset(StringBuilder text, int start, int expected, BoundaryScanner scanner) argument 88 testFindEndOffset(StringBuilder text, int start, int expected, BoundaryScanner scanner) argument [all...] |
H A D | SimpleBoundaryScannerTest.java | 27 StringBuilder text = new StringBuilder(TEXT); 32 assertEquals(start, scanner.findStartOffset(text, start)); 34 assertEquals(start, scanner.findStartOffset(text, start)); 38 assertEquals(expected, scanner.findStartOffset(text, start)); 42 assertEquals(expected, scanner.findStartOffset(text, start)); 46 StringBuilder text = new StringBuilder(TEXT); 51 assertEquals(start, scanner.findEndOffset(text, start)); 53 assertEquals(start, scanner.findEndOffset(text, start)); 57 assertEquals(expected, scanner.findEndOffset(text, start));
|
/lucene-3.6.0/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/core/util/ |
H A D | UnescapedCharSequence.java | 47 * @param text 49 public UnescapedCharSequence(CharSequence text) { argument 50 this.chars = new char[text.length()]; 51 this.wasEscaped = new boolean[text.length()]; 52 for (int i = 0; i < text.length(); i++) { 53 this.chars[i] = text.charAt(i); 61 * @param text 64 private UnescapedCharSequence(UnescapedCharSequence text) { argument 65 this.chars = new char[text.length()]; 66 this.wasEscaped = new boolean[text 143 wasEscaped(CharSequence text, int index) argument 149 toLowerCase(CharSequence text) argument [all...] |
/lucene-3.6.0/solr/test-framework/src/java/org/apache/solr/analysis/ |
H A D | StringMockSolrResourceLoader.java | 29 String text; field in class:StringMockSolrResourceLoader 31 StringMockSolrResourceLoader(String text) { argument 32 this.text = text; 36 return Arrays.asList(text.split("\n")); 44 return new ByteArrayInputStream(text.getBytes("UTF-8"));
|
/lucene-3.6.0/lucene/contrib/icu/src/java/org/apache/lucene/analysis/icu/segmentation/ |
H A D | BreakIteratorWrapper.java | 20 import java.text.CharacterIterator; 23 import com.ibm.icu.text.BreakIterator; 24 import com.ibm.icu.text.DictionaryBasedBreakIterator; 25 import com.ibm.icu.text.RuleBasedBreakIterator; 26 import com.ibm.icu.text.UTF16; 45 protected char text[]; field in class:BreakIteratorWrapper 52 abstract void setText(CharacterIterator text); argument 54 void setText(char text[], int start, int length) { argument 55 this.text = text; 104 setText(CharacterIterator text) argument 166 setText(CharacterIterator text) argument [all...] |
H A D | LaoBreakIterator.java | 20 import java.text.CharacterIterator; 23 import com.ibm.icu.text.BreakIterator; 24 import com.ibm.icu.text.RuleBasedBreakIterator; 25 import com.ibm.icu.text.UnicodeSet; 28 * Syllable iterator for Lao text. 30 * This breaks Lao text into syllables according to: 45 * Take for instance the text ກວ່າດອກ 61 CharArrayIterator text; field in class:LaoBreakIterator 89 working.setText(this.text.getText(), this.text 154 setText(CharacterIterator text) argument 187 ccReorder(char[] text, int start, int length) argument [all...] |
H A D | CompositeBreakIterator.java | 21 import com.ibm.icu.text.BreakIterator; 24 * An internal BreakIterator for multilingual text, following recommendations 34 * associated with a piece of text. 46 private char text[]; field in class:CompositeBreakIterator 62 rbbi.setText(text, scriptIterator.getScriptStart(), 102 * Set a new region of text to be examined by this iterator 104 * @param text buffer of text 108 void setText(final char text[], int start, int length) { argument 109 this.text [all...] |
H A D | ICUTokenizerConfig.java | 20 import com.ibm.icu.text.BreakIterator;
|
/lucene-3.6.0/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/core/nodes/ |
H A D | TextableQueryNode.java | 27 void setText(CharSequence text); argument
|
H A D | FieldQueryNode.java | 26 * A {@link FieldQueryNode} represents a element that contains field/text tuple 38 * The term's text. 40 protected CharSequence text; field in class:FieldQueryNode 60 * @param text 67 public FieldQueryNode(CharSequence field, CharSequence text, int begin, argument 70 this.text = text; 78 return escaper.escape(this.text, Locale.getDefault(), Type.NORMAL); 82 return escaper.escape(this.text, Locale.getDefault(), Type.STRING); 96 + this.field + "' text 166 setText(CharSequence text) argument [all...] |
H A D | QuotedFieldQueryNode.java | 33 * @param text 40 public QuotedFieldQueryNode(CharSequence field, CharSequence text, int begin, argument 42 super(field, text, begin, end); 57 + "' field='" + this.field + "' term='" + this.text + "'/>";
|
/lucene-3.6.0/lucene/contrib/icu/src/test/org/apache/lucene/analysis/icu/segmentation/ |
H A D | TestLaoBreakIterator.java | 25 import com.ibm.icu.text.BreakIterator; 26 import com.ibm.icu.text.RuleBasedBreakIterator; 27 import com.ibm.icu.text.UTF16; 44 char text[] = sourceText.toCharArray(); 46 ci.setText(text, 0, text.length); 54 } while (end != BreakIterator.DONE && !isWord(text, start, end)); 57 assertEquals(tokens[i], new String(text, start, end - start)); 63 protected boolean isWord(char text[], int start, int end) { argument 66 codepoint = UTF16.charAt(text, [all...] |
/lucene-3.6.0/lucene/core/src/java/org/apache/lucene/search/ |
H A D | WildcardQuery.java | 45 String text = term.text(); 46 this.termContainsWildcard = (text.indexOf('*') != -1) 47 || (text.indexOf('?') != -1); 49 && (text.indexOf('?') == -1) 50 && (text.indexOf('*') == text.length() - 1); 56 return new PrefixTermEnum(reader, term.createTerm(term.text() 57 .substring(0, term.text().indexOf('*')))); 80 buffer.append(term.text()); [all...] |
/lucene-3.6.0/lucene/contrib/queryparser/src/java/org/apache/lucene/queryParser/standard/nodes/ |
H A D | PrefixWildcardQueryNode.java | 35 * @param text 42 public PrefixWildcardQueryNode(CharSequence field, CharSequence text, argument 44 super(field, text, begin, end); 53 return "<prefixWildcard field='" + this.field + "' term='" + this.text
|
/lucene-3.6.0/solr/client/ruby/solr-ruby/test/unit/ |
H A D | add_document_test.rb | 20 doc = {:id => '123', :text => 'Tlon, Uqbar, Orbis Tertius'} 28 doc = {:id => '123', :text => 'Tlon, Uqbar, Orbis Tertius'} 36 doc = {:id => '123', :text => 'Tlon, Uqbar, Orbis Tertius'} 37 assert_equal true, conn.add(:id => '123', :text => 'Tlon, Uqbar, Orbis Tetius')
|
/lucene-3.6.0/lucene/contrib/analyzers/kuromoji/src/java/org/apache/lucene/analysis/ja/dict/ |
H A D | UnknownDictionary.java | 33 public int lookup(char[] text, int offset, int len) { argument 34 if(!characterDefinition.isGroup(text[offset])) { 39 byte characterIdOfFirstCharacter = characterDefinition.getCharacterClass(text[offset]); 42 if (characterIdOfFirstCharacter == characterDefinition.getCharacterClass(text[offset+i])){
|
/lucene-3.6.0/solr/core/src/java/org/apache/solr/analysis/ |
H A D | WordDelimiterIterator.java | 23 * A BreakIterator-like API for iterating over subwords in text, according to WordDelimiterFilter rules. 33 char text[]; field in class:WordDelimiterIterator 36 /** start position of text, excluding leading delimiters */ 38 /** end position of text, excluding trailing delimiters */ 129 while (current < endBounds && (isSubwordDelim(lastType = charType(text[current])))) { 138 int type = charType(text[end]); 164 int type = charType(text[current]); 176 * Reset the text to a new value, and reset all state 178 * @param text New text 181 setText(char text[], int length) argument [all...] |
/lucene-3.6.0/lucene/contrib/analyzers/common/src/java/org/apache/lucene/analysis/cjk/ |
H A D | CJKWidthFilter.java | 63 char text[] = termAtt.buffer(); 66 final char ch = text[i]; 69 text[i] -= 0xFEE0; 72 if ((ch == 0xFF9E || ch == 0xFF9F) && i > 0 && combine(text, i, ch)) { 73 length = StemmerUtil.delete(text, i--, length); 75 text[i] = KANA_NORM[ch - 0xFF65]; 102 private static boolean combine(char text[], int pos, char ch) { argument 103 final char prev = text[pos-1]; 105 text[pos-1] += (ch == 0xFF9F) 108 return text[po [all...] |