Package org.exist.storage.analysis

Examples of org.exist.storage.analysis.Tokenizer

321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
        return path.getDependencies();
    }

    protected String[] getSearchTerms(String searchString) throws EXistException {
        final List<String> tokens = new ArrayList<String>();
        final Tokenizer tokenizer = context.getBroker().getTextEngine().getTokenizer();
        tokenizer.setText(searchString);
        org.exist.storage.analysis.TextToken token;
        String word;
        while (null != (token = tokenizer.nextToken(true))) {
            word = token.getText();
            tokens.add(word);
        }
        final String[] terms = new String[tokens.size()];
        return tokens.toArray(terms);
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    }

    private Sequence exactMatch(XQueryContext context, String[] terms, NodeSet result) {
        //Walk through hits and calculate term-distances
        final NodeSet r = new ExtArrayNodeSet();
        final Tokenizer tok = context.getBroker().getTextEngine().getTokenizer();
        String term;
        for (final NodeProxy current : result) {
            final String value = current.getNodeValueSeparated();
            tok.setText(value);
            int j = 0;
            if (j < terms.length) {
                term = terms[j];
            } else {
                break;
            }
            int current_distance = -1;
            TextToken token;
            while ((token = tok.nextToken()) != null) {
                final String word = token.getText().toLowerCase();
                if (current_distance > max_distance) {
                    // reset
                    j = 0;
                    term = terms[j];
View Full Code Here
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
                throw new XPathException("Malformed pattern: " + patterns[i]);
            }
        }
        //Walk through hits and calculate term-distances
        final ExtArrayNodeSet r = new ExtArrayNodeSet(100);
        final Tokenizer tok = context.getBroker().getTextEngine().getTokenizer();
        Matcher matcher;
        TextToken token;
        for (final NodeProxy current : result) {
            final String value = current.getNodeValueSeparated();
            tok.setText(value);
            int j = 0;
            if (j < patterns.length) {
                matcher = matchers[j];
            } else {
                break;
            }
            int current_distance = -1;
            while ((token = tok.nextToken()) != null) {
                final String word = token.getText().toLowerCase();
                if (current_distance > max_distance) {
                    //Reset
                    j = 0;
                    matcher = matchers[j];
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
     * @param result
     */
    private Sequence exactMatch(XQueryContext context, String[] terms, NodeSet result) {
        TextToken token;
        final NodeSet r = new ExtArrayNodeSet();
        final Tokenizer tok = context.getBroker().getTextEngine().getTokenizer();
        //Define search phrase for matches
        String matchTerm = "";
        for (int k = 0; k < terms.length ; k++) {
            matchTerm = matchTerm + terms[k];
            if (k != terms.length - 1)
                {matchTerm = matchTerm + "\\W*";}
        }
        //Iterate on results
        for (final NodeProxy current : result) {
            final Vector<NodeId> matchNodeIDs = new Vector<NodeId>();
            //Get first match
            Match nextMatch = current.getMatches();
            //Remove previously found matches on current
            current.setMatches(null);
            //Iterate on attach matches, with unicity of related nodeproxy gid
            String term;
            while(nextMatch != null) {
                final NodeId nodeId= nextMatch.getNodeId();
                //If current node id has not been previously processed
                if (!matchNodeIDs.contains(nodeId)) {
                    final NodeProxy mcurrent = new NodeProxy(current.getDocument(), nodeId);
                    Match match = null;
                    int firstOffset = -1;
                    matchNodeIDs.add(nodeId);
                    final String value = mcurrent.getNodeValue();
                    tok.setText(value);
                    int j = 0;
                    if (j < terms.length)
                        {term = terms[j];}
                    else
                        {break;}
                    int frequency = 0;
                    while ((token = tok.nextToken()) != null) {
                        final String word = token.getText().toLowerCase();
                        if (word.equalsIgnoreCase(term)) {
                            j++;
                            if (j == terms.length) {
                                //All terms found
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
                return Sequence.EMPTY_SEQUENCE;
            }
        }
        //Walk through hits
        final ExtArrayNodeSet r = new ExtArrayNodeSet();
        final Tokenizer tok = context.getBroker().getTextEngine().getTokenizer();
        Matcher matcher;
        for (final NodeProxy current : result) {
            Match nextMatch;
            final Vector<NodeId> matchGid = new Vector<NodeId>();
            //Get first match
            nextMatch = current.getMatches();
            //Remove previously found matches on current
            current.setMatches(null);
            //Iterate on attach matches, with unicity of related nodeproxy gid
            while (nextMatch != null) {
                final Hashtable<String, Match> matchTable = new Hashtable<String, Match>();
                final NodeId nodeId = nextMatch.getNodeId();
                //If current node id has not been previously processed
                if (!matchGid.contains(nodeId)) {
                    final NodeProxy mcurrent = new NodeProxy(current.getDocument(), nodeId);
                    //Add it in node id array
                    matchGid.add(nodeId);
                    final String value = mcurrent.getNodeValue();
                    tok.setText(value);
                    int j = 0;
                    if (j < patterns.length) {
                        matcher = matchers[j];
                    } else
                        {break;}
                    String matchTerm = null;
                    TextToken token;
                    while ((token = tok.nextToken()) != null) {
                        String word = token.getText().toLowerCase();
                        matcher.reset(word);
                        matchers[0].reset(word);
                        if (matcher.matches()) {
                            j++;
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
                    Sequence contextSequence)
      throws XPathException {
    final String searchString = getArgument(1).eval(contextSequence)
        .getStringValue();
    final List<String> tokens = new ArrayList<String>();
    final Tokenizer tokenizer = context.getBroker().getTextEngine()
        .getTokenizer();
    tokenizer.setText(searchString);
    org.exist.storage.analysis.TextToken token;
    String word;
    while (null != (token = tokenizer.nextToken(true))) {
      word = token.getText();
      tokens.add(word);
    }
    return tokens;
  }
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
        return result;
    }
   
    protected String[] getSearchTerms(String searchString) {
        final List<String> tokens = new ArrayList<String>();
        final Tokenizer tokenizer =
            context.getBroker().getTextEngine().getTokenizer();
        tokenizer.setText(searchString);
        org.exist.storage.analysis.TextToken token;
        String word;
        while (null != (token = tokenizer.nextToken(true))) {
            word = token.getText();
            tokens.add(word);
        }
        String[] terms = new String[tokens.size()];
        terms = tokens.toArray(terms);
View Full Code Here
TOP

Related Classes of org.exist.storage.analysis.Tokenizer

  • org.exist.xquery.functions.fn.ExtFulltext
  • org.exist.xquery.functions.fn.ExtNear
  • org.exist.xquery.functions.fn.ExtPhrase
  • org.exist.xquery.functions.system.FtIndexLookup
  • org.exist.xquery.functions.text.AbstractMatchFunction
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.