Package org.htmlparser.beans

Examples of org.htmlparser.beans.StringBean

911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
      if (sTextBody==null) {
          // ****************************
          // Extract plain text from HTML
          if (DebugFile.trace) DebugFile.writeln("new StringBean()");

          StringBean oStrBn = new StringBean();

          try {
            oPrsr.visitAllNodesWith (oStrBn);
          } catch (ParserException pe) {
          throw new MessagingException(pe.getMessage(), pe);
          }

          sTextBody = oStrBn.getStrings();

          oStrBn = null;
      } // fi (sTextBody==null)

      // *******************************
 
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
          DebugFile.writeln(xcpt.getClass().getName()+" "+xcpt.getMessage()+" indexing message "+sGuid+" - "+sSubject);
      }
      if (oStrBuff.length()>0) {
        if (Gadgets.indexOfIgnoreCase(oStrBuff.toString(), "<html>")>=0) {
          Parser oPrsr = Parser.createParser(oStrBuff.toString(), null);
          StringBean oStrs = new StringBean();
          try {
            oPrsr.visitAllNodesWith (oStrs);
          } catch (ParserException pe) {
            if (DebugFile.trace) DebugFile.decIdent();
            throw new IOException(pe.getMessage());         
          }

          if (DebugFile.trace) DebugFile.writeln("Gadgets.ASCIIEncode(StringBean.getStrings())");
          sText = Gadgets.ASCIIEncode(oStrs.getStrings());
          if (DebugFile.trace) DebugFile.writeln("StringBean.getStrings() done");
        } // fi (oStrBuff contains <html>)
        else {
          if (DebugFile.trace) DebugFile.writeln("Gadgets.ASCIIEncode(StringBuffer.toString())");
          sText = Gadgets.ASCIIEncode(oStrBuff.toString());
View Full Code Here
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
    }
    else if (getContentType().startsWith("text/html")) {
      StringBuffer oHtmlBuff = new StringBuffer();
      getText(oHtmlBuff);
      Parser oPrsr = Parser.createParser(oHtmlBuff.toString(), getEncoding());
      StringBean oStrBn = new StringBean();
      try {
        oPrsr.visitAllNodesWith (oStrBn);
      } catch (ParserException pe) {
        throw new MessagingException(pe.getMessage(), pe);
      }
      // Code for HTML parser 1.4
      // oStrBn.setInputHTML(oHtmlBuff.toString());
      oBuffer.append(oStrBn.getStrings());
    }
    else {
      if (DebugFile.trace) DebugFile.writeln("Multipart = DBMimeMessage.getParts()");

      Multipart oParts = getParts();

      final int iParts = oParts.getCount();

      MimePart oPart;

      int p;
      for (p=0; p<iParts && !bHasPlainTextVersion; p++) {
        oPart = (MimePart) oParts.getBodyPart(p);

        String sType = oPart.getContentType();
        if (null!=sType) sType=sType.toLowerCase();
        String sDisp = oPart.getDisposition();
        if (null==sDisp) sDisp="inline"; else if (sDisp.length()==0) sDisp="inline";

        if (DebugFile.trace) DebugFile.writeln("scanning part " + String.valueOf(p) + sDisp + " " + sType.replace('\r',' ').replace('\n', ' '));

        if (sType.startsWith("text/plain") && sDisp.equalsIgnoreCase("inline")) {
          bHasPlainTextVersion = true;
          DBMimePart.parseMimePart (oBuffer, null,
                                    getFolder().getName(),
                                    getMessageID()!=null ? getMessageID() : getContentID(),
                                    oPart, p);
        }
      }

      if (DebugFile.trace) {
        if (bHasPlainTextVersion)
          DebugFile.writeln("MimeMultipart has plain text version at part " + String.valueOf(p));
        else
          DebugFile.writeln("MimeMultipart has no plain text version, converting part 0 from HTML");
      }

      if (!bHasPlainTextVersion) {
        oPart = (MimePart) oParts.getBodyPart(0);
        StringBuffer oHtml = new StringBuffer();
        DBMimePart.parseMimePart (oHtml, null, getFolder().getName(), getMessageID()!=null ? getMessageID() : getContentID(), oPart, 0);

        Parser oPrsr = Parser.createParser(oHtml.toString(), getEncoding());
        StringBean oStrBn = new StringBean();

        try {
          oPrsr.visitAllNodesWith (oStrBn);
        } catch (ParserException pe) {
          throw new MessagingException(pe.getMessage(), pe);
        }

        // Code for HTML parser 1.4
        // oSB.setInputHTML(oHtml.toString());

        String sStrs = oStrBn.getStrings();

        if (DebugFile.trace) {
          DebugFile.writeln("StringBean.getStrings(");
          if (null!=sStrs) DebugFile.write(sStrs); else DebugFile.write("null");
          DebugFile.writeln(")");
View Full Code Here
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
        // ****************************
        // Extract plain text from HTML
        if (DebugFile.trace) DebugFile.writeln("new StringBean()");

        StringBean oStrBn = new StringBean();

        try {
          oPrsr.visitAllNodesWith (oStrBn);
        } catch (ParserException pe) {
          if (DebugFile.trace) {
            DebugFile.writeln("org.htmlparser.util.ParserException " + pe.getMessage());
          }
          throw new MessagingException(pe.getMessage(), pe);
        }

        sText = oStrBn.getStrings();

        oStrBn = null;

        // *******************************
        // Set plain text alternative part
View Full Code Here
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
    // Using HTMLParser to extract the content
    String cleanedContent = null;
    Page htmlPage = new Page(cuttedContent, "UTF-8");
    Parser parser = new Parser(new Lexer(htmlPage));
    StringBean stringBean = new StringBean();

    // replace multiple whitespace with one whitespace
    stringBean.setCollapse(true);
    // Do not extract URLs
    stringBean.setLinks(false);
    // replace &nbsp; with whitespace
    stringBean.setReplaceNonBreakingSpaces(true);

    try {
      // Parse the content
      parser.visitAllNodesWith(stringBean);
      cleanedContent = stringBean.getStrings();

    } catch (ParserException ex) {
      throw new RegainException("Error while parsing content: ", ex);
    }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
            ResourcePropertyMapping resourcePropertyMapping,
            MarshallingContext context) {
        String str = (String) o;
        Lexer l = new Lexer(str);
        Parser parser = new Parser(l);
        StringBean sb = new StringBean();

        try {
            parser.visitAllNodesWith(sb);
        } catch (ParserException e) {
            log.warn("RETURNING ORIG VAL: " + str);
            return str;
        }
        String ret = sb.getStrings();
        log.debug("RETURNING STRIPPED: " + ret);
        return ret;
    }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
                stringBuilder.append(s);
            }

            Lexer l = new Lexer(stringBuilder.toString());
            Parser parser = new Parser(l);
            StringBean sb = new StringBean();

            parser.visitAllNodesWith(sb);

            String ret = sb.getStrings();
            return new StringReader(ret);
        } catch (ParserException e) {
            log.warn("Conversion Exception: " + e);
            throw new ConversionException(e.getMessage());
        } catch (IOException e2) {
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
     * @param links if <code>true</code> include hyperlinks in output.
     * @return The textual contents of the page.
     */
    public String extractStrings(boolean links) throws ParserException
    {
        StringBean sb;

        sb = new StringBean();
        sb.setLinks(links);
        sb.setURL(resource);

        return (sb.getStrings());
    }
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
    }

    public void testSerializableStringBean()
        throws IOException, ClassNotFoundException, ParserException
    {
        StringBean sb;
        String text;
        byte[] data;

        sb = new StringBean();
        sb.setURL("http://htmlparser.sourceforge.net/test/example.html");
        text = sb.getStrings();

        data = pickle(sb);
        sb = (StringBean) unpickle(data);

        assertEquals(
            "Strings before and after serialization differ",
            text,
            sb.getStrings());
    }
View Full Code Here
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
        }
    }

    public void testStringBeanListener()
    {
        final StringBean sb;
        final Boolean hit[] = new Boolean[1];

        sb = new StringBean();
        hit[0] = Boolean.FALSE;
        sb.addPropertyChangeListener(new PropertyChangeListener()
        {
            public void propertyChange(PropertyChangeEvent event)
            {
                if (event.getSource().equals(sb))
                    if (event
                        .getPropertyName()
                        .equals(StringBean.PROP_STRINGS_PROPERTY))
                        hit[0] = Boolean.TRUE;
            }
        });

        hit[0] = Boolean.FALSE;
        sb.setURL("http://htmlparser.sourceforge.net/test/example.html");
        assertTrue(
            "Strings property change not fired for URL change",
            hit[0].booleanValue());

        hit[0] = Boolean.FALSE;
        sb.setLinks(true);
        assertTrue(
            "Strings property change not fired for links change",
            hit[0].booleanValue());
    }
View Full Code Here
TOP

Related Classes of org.htmlparser.beans.StringBean

  • com.apress.progwt.server.lucene.HTMLAnalyzer
  • com.apress.progwt.server.lucene.HTMLConverter
  • com.knowgate.hipermail.DBMimeMessage
  • com.knowgate.hipermail.SessionHandler
  • com.knowgate.lucene.MailIndexer
  • com.wordpress.util.StringUtil
  • com.zesped.util.MailSessionHandler
  • net.sf.regain.crawler.preparator.HtmlPreparator
  • org.exoplatform.services.document.impl.HTMLDocumentReader
  • org.htmlparser.Parser
    • 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.