Changeset 12976
- Timestamp:
- 2006-10-03T14:22:03+13:00 (17 years ago)
- Location:
- trunk
- Files:
-
- 3 edited
Legend:
- Unmodified
- Added
- Removed
-
trunk/gsdl/src/java/org/nzdl/gsdl/LuceneWrap/GS2LuceneQuery.java
r12975 r12976 125 125 query = query.rewrite(reader); 126 126 127 // Return the list of expanded query terms and their frequencies 128 HashSet terms = new HashSet(); 129 query.extractTerms(terms); 130 Iterator term_iterator = terms.iterator(); 131 System.out.println(" <QueryTermsInfo num=\"" + terms.size() + "\"/>"); 132 while (term_iterator.hasNext()) { 133 Term term = (Term) term_iterator.next(); 134 135 // Get the term frequency over all the documents 136 TermDocs term_docs = reader.termDocs(term); 137 int term_freq = term_docs.freq(); 138 while (term_docs.next()) { 139 term_freq += term_docs.freq(); 140 } 141 142 // If you wanted to limit this to just text terms add 143 // something like this: 144 // if (term.field().equals(TEXTFIELD)) 145 System.out.println(" <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />"); 146 } 147 148 // Return the list of stop words removed from the query 149 HashSet terms_including_stop_words = new HashSet(); 150 query_including_stop_words.extractTerms(terms_including_stop_words); 151 Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator(); 152 while (terms_including_stop_words_iter.hasNext()) { 153 Term term = (Term) terms_including_stop_words_iter.next(); 154 if (!terms.contains(term)) { 155 System.out.println(" <StopWord value=\"" + term.text() + "\"/>"); 156 } 157 } 158 127 159 // Perform the query (filter and sorter may be null) 128 160 Hits hits = searcher.search(query, filter, sorter); … … 152 184 153 185 ++counter; 154 }155 156 // Return the list of expanded query terms and their frequencies157 HashSet terms = new HashSet();158 query.extractTerms(terms);159 Iterator term_iterator = terms.iterator();160 System.out.println(" <QueryTermsInfo num=\"" + terms.size() + "\"/>");161 while (term_iterator.hasNext()) {162 Term term = (Term) term_iterator.next();163 164 // Get the term frequency over all the documents165 TermDocs term_docs = reader.termDocs(term);166 int term_freq = term_docs.freq();167 while (term_docs.next()) {168 term_freq += term_docs.freq();169 }170 171 // If you wanted to limit this to just text terms add172 // something like this:173 // if (term.field().equals(TEXTFIELD))174 System.out.println(" <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />");175 }176 177 // Return the list of stop words removed from the query178 HashSet terms_including_stop_words = new HashSet();179 query_including_stop_words.extractTerms(terms_including_stop_words);180 Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator();181 while (terms_including_stop_words_iter.hasNext()) {182 Term term = (Term) terms_including_stop_words_iter.next();183 if (!terms.contains(term)) {184 System.out.println(" <StopWord value=\"" + term.text() + "\"/>");185 }186 186 } 187 187 } -
trunk/indexers/lucene-gs/src/org/greenstone/LuceneWrapper/GS2LuceneQuery.java
r12975 r12976 125 125 query = query.rewrite(reader); 126 126 127 // Return the list of expanded query terms and their frequencies 128 HashSet terms = new HashSet(); 129 query.extractTerms(terms); 130 Iterator term_iterator = terms.iterator(); 131 System.out.println(" <QueryTermsInfo num=\"" + terms.size() + "\"/>"); 132 while (term_iterator.hasNext()) { 133 Term term = (Term) term_iterator.next(); 134 135 // Get the term frequency over all the documents 136 TermDocs term_docs = reader.termDocs(term); 137 int term_freq = term_docs.freq(); 138 while (term_docs.next()) { 139 term_freq += term_docs.freq(); 140 } 141 142 // If you wanted to limit this to just text terms add 143 // something like this: 144 // if (term.field().equals(TEXTFIELD)) 145 System.out.println(" <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />"); 146 } 147 148 // Return the list of stop words removed from the query 149 HashSet terms_including_stop_words = new HashSet(); 150 query_including_stop_words.extractTerms(terms_including_stop_words); 151 Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator(); 152 while (terms_including_stop_words_iter.hasNext()) { 153 Term term = (Term) terms_including_stop_words_iter.next(); 154 if (!terms.contains(term)) { 155 System.out.println(" <StopWord value=\"" + term.text() + "\"/>"); 156 } 157 } 158 127 159 // Perform the query (filter and sorter may be null) 128 160 Hits hits = searcher.search(query, filter, sorter); … … 152 184 153 185 ++counter; 154 }155 156 // Return the list of expanded query terms and their frequencies157 HashSet terms = new HashSet();158 query.extractTerms(terms);159 Iterator term_iterator = terms.iterator();160 System.out.println(" <QueryTermsInfo num=\"" + terms.size() + "\"/>");161 while (term_iterator.hasNext()) {162 Term term = (Term) term_iterator.next();163 164 // Get the term frequency over all the documents165 TermDocs term_docs = reader.termDocs(term);166 int term_freq = term_docs.freq();167 while (term_docs.next()) {168 term_freq += term_docs.freq();169 }170 171 // If you wanted to limit this to just text terms add172 // something like this:173 // if (term.field().equals(TEXTFIELD))174 System.out.println(" <Term value=\"" + term.text() + "\" field=\"" + term.field() + "\" freq=\"" + term_freq + "\" />");175 }176 177 // Return the list of stop words removed from the query178 HashSet terms_including_stop_words = new HashSet();179 query_including_stop_words.extractTerms(terms_including_stop_words);180 Iterator terms_including_stop_words_iter = terms_including_stop_words.iterator();181 while (terms_including_stop_words_iter.hasNext()) {182 Term term = (Term) terms_including_stop_words_iter.next();183 if (!terms.contains(term)) {184 System.out.println(" <StopWord value=\"" + term.text() + "\"/>");185 }186 186 } 187 187 }
Note:
See TracChangeset
for help on using the changeset viewer.