Package org.apache.lenya.lucene.html

Examples of org.apache.lenya.lucene.html.HTMLParser$JJCalls

79
80
81
82
83
84
85
86
87
88
89
     * @return DOCUMENT ME!
     *
     * @throws Exception DOCUMENT ME!
     */
    public String reTokenize(File file) throws Exception {
        TokenStream ts = new StandardAnalyzer().tokenStream(new HTMLParser(file).getReader());

        Token token = null;

        while ((token = ts.next()) != null) {
            System.out.println("ReTokenizeFile.reTokenize(File): " + token.termText() + " " +
View Full Code Here
286
287
288
289
290
291
292
293
294
295
296
     * @return the content of the file.
     * @throws FileNotFoundException if the file does not exists.
     * @throws IOException if something else went wrong.
     */
    protected String readHtmlFile(File file) throws FileNotFoundException, IOException {
        java.io.Reader reader = new HTMLParser(file).getReader();
        char[] chars = new char[1024];
        int chars_read;
        java.io.Writer writer = new java.io.StringWriter();

        while ((chars_read = reader.read(chars)) > 0) {
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
        // This field is not stored with document, it is indexed, but it is not
        // tokenized prior to indexing.
        doc.add(new Field("uid", uid(f, htdocsDumpDir), false, true, false));

        //HtmlDocument htmlDoc = new HtmlDocument(f);
        HTMLParser parser = new HTMLParser(f);

        // Add the summary as an UnIndexed field, so that it is stored and returned
        // with hit documents for display.
        // Add the title as a separate Text field, so that it can be searched separately.
        /*
                String title = htmlDoc.getTitle();

                if (title != null) {
                    doc.add(Field.Text("title", title));
                } else {
                    doc.add(Field.Text("title", ""));
                }
        */
        doc.add(Field.Text("title", parser.getTitle()));

        //System.out.println("HTMLDocument.getLuceneDocument(): title field added: " + title);
        // Add the tag-stripped contents as a Reader-valued Text field so it will get tokenized and indexed.
        /*
                String body = htmlDoc.getBody();
                String contents = "";

                if ((body != null) && (title != null)) {
                    contents = title + " " + body;
                    doc.add(Field.Text("contents", title + body));
                }

                doc.add(Field.Text("contents", contents));
        */
        doc.add(Field.Text("contents", parser.getReader()));

        return doc;
    }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
     * @param file The file to retokenize
     * @return The path to the retokenized file
     * @throws Exception if an error occurs
     */
    public String reTokenize(File file) throws Exception {
        TokenStream ts = new StandardAnalyzer().tokenStream("",new HTMLParser(file).getReader());

        Token token = null;

        while ((token = ts.next()) != null) {
            System.out.println("ReTokenizeFile.reTokenize(File): " + token.termText() + " " +
View Full Code Here
294
295
296
297
298
299
300
301
302
303
304
     * @return the content of the file.
     * @throws FileNotFoundException if the file does not exists.
     * @throws IOException if something else went wrong.
     */
    protected String readHtmlFile(File file) throws FileNotFoundException, IOException {
        java.io.Reader reader = new HTMLParser(file).getReader();
        char[] chars = new char[1024];
        int chars_read;
        java.io.Writer writer = new java.io.StringWriter();

        while ((chars_read = reader.read(chars)) > 0) {
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
        // This field is not stored with document, it is indexed, but it is not
        // tokenized prior to indexing.
        doc.add(new Field("uid", uid(f, htdocsDumpDir), false, true, false));

        //HtmlDocument htmlDoc = new HtmlDocument(f);
        HTMLParser parser = new HTMLParser(f);

        // Add the summary as an UnIndexed field, so that it is stored and returned
        // with hit documents for display.
        // Add the title as a separate Text field, so that it can be searched separately.
        /*
                String title = htmlDoc.getTitle();

                if (title != null) {
                    doc.add(Field.Text("title", title));
                } else {
                    doc.add(Field.Text("title", ""));
                }
        */
        doc.add(Field.Text("title", parser.getTitle()));

        //System.out.println("HTMLDocument.getLuceneDocument(): title field added: " + title);
        // Add the tag-stripped contents as a Reader-valued Text field so it will get tokenized and indexed.
        /*
                String body = htmlDoc.getBody();
                String contents = "";

                if ((body != null) && (title != null)) {
                    contents = title + " " + body;
                    doc.add(Field.Text("contents", title + body));
                }

                doc.add(Field.Text("contents", contents));
        */
        doc.add(Field.Text("contents", parser.getReader()));

        return doc;
    }
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
     * @return DOCUMENT ME!
     *
     * @throws Exception DOCUMENT ME!
     */
    public String reTokenize(File file) throws Exception {
        TokenStream ts = new StandardAnalyzer().tokenStream(new HTMLParser(file).getReader());

        Token token = null;

        while ((token = ts.next()) != null) {
            System.out.println("ReTokenizeFile.reTokenize(File): " + token.termText() + " " +
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
        throws FileNotFoundException, IOException {
        if (file.getName().substring(file.getName().length() - 4).equals(".pdf")) {
            file = new File(file.getAbsolutePath() + ".txt");
        }

        java.io.Reader reader = new HTMLParser(file).getReader();
        char[] chars = new char[1024];
        int chars_read;
        java.io.Writer writer = new java.io.StringWriter();

        while ((chars_read = reader.read(chars)) > 0) {
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
        // This field is not stored with document, it is indexed, but it is not
        // tokenized prior to indexing.
        doc.add(new Field("uid", uid(f, htdocsDumpDir), false, true, false));

        //HtmlDocument htmlDoc = new HtmlDocument(f);
        HTMLParser parser = new HTMLParser(f);

        // Add the summary as an UnIndexed field, so that it is stored and returned
        // with hit documents for display.
        // Add the title as a separate Text field, so that it can be searched separately.
        /*
                String title = htmlDoc.getTitle();

                if (title != null) {
                    doc.add(Field.Text("title", title));
                } else {
                    doc.add(Field.Text("title", ""));
                }
        */
        doc.add(Field.Text("title", parser.getTitle()));

        //System.out.println("HTMLDocument.getLuceneDocument(): title field added: " + title);
        // Add the tag-stripped contents as a Reader-valued Text field so it will get tokenized and indexed.
        /*
                String body = htmlDoc.getBody();
                String contents = "";

                if ((body != null) && (title != null)) {
                    contents = title + " " + body;
                    doc.add(Field.Text("contents", title + body));
                }

                doc.add(Field.Text("contents", contents));
        */
        doc.add(Field.Text("contents", parser.getReader()));

        //System.out.println("HTMLDocument.getLuceneDocument(): contents field added: " + contents);
        return doc;
    }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
     * @return DOCUMENT ME!
     *
     * @throws Exception DOCUMENT ME!
     */
    public String reTokenize(File file) throws Exception {
        TokenStream ts = new StandardAnalyzer().tokenStream(new HTMLParser(file).getReader());

        Token token = null;

        while ((token = ts.next()) != null) {
            System.out.println("ReTokenizeFile.reTokenize(File): " + token.termText() + " " +
View Full Code Here
TOP

Related Classes of org.apache.lenya.lucene.html.HTMLParser$JJCalls

  • org.apache.lenya.lucene.HTMLDocument
  • org.apache.lenya.lucene.ReTokenizeFile
  • java.io.PipedWriter
  • java.io.FileInputStream
  • java.io.PipedReader
    • 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.