Package com.substanceofcode.utils

Examples of com.substanceofcode.utils.EncodingUtil

273
274
275
276
277
278
279
280
281
282
283
          " to 2nd redirect url:  " + url);
    }
    m_redirect = true;
    m_redirectUrl = url;
    com.substanceofcode.rssreader.businessentities.RssItunesFeed[] feeds =
        HTMLLinkParser.parseFeeds(new EncodingUtil(is),
                  url, null, null, true
                  //#ifdef DLOGGING
                  ,logger,
                  fineLoggable,
                  finerLoggable,
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
    public RssItunesFeed[] parseFeeds(InputStream is)
    throws IOException, CauseMemoryException, CauseException, Exception {
        // Prepare buffer for input data
        StringBuffer inputBuffer = new StringBuffer();
       
    EncodingUtil encUtl = new EncodingUtil(is);
    EncodingStreamReader esr = encUtl.getEncodingStreamReader();

        try {
      // Read all data to buffer.  Use 100 char increments to save on
      // memory.
      inputBuffer = esr.readFile(100);
        } catch (IOException ex) {
      CauseException cex = new CauseException(
          "Error while parsing line by feed " + m_url, ex);
      throw cex;
        }
        String text;
    if (esr.isUtfDoc()) {
      final String fileEncoding = esr.getFileEncoding();
      if (esr.isUtf16Doc()) {
        encUtl.getEncoding(fileEncoding, "UTF-16");
      } else {
        encUtl.getEncoding(fileEncoding, "UTF-8");
      }
      final String docEncoding = encUtl.getDocEncoding();
      if (docEncoding.length() == 0) {
        text = inputBuffer.toString();
      } else {
        try {
          // We read the bytes in as ISO8859_1, so we must get them
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    */
    public RssItunesFeed[] parseFeeds(InputStream is)
    throws IOException, CauseMemoryException, CauseException, Exception {
    // Init in case we get a severe error.
    try {
      return HTMLLinkParser.parseFeeds(new EncodingUtil(is),
                      m_url,
                      m_feedNameFilter,
                      m_feedURLFilter,
                      m_acceptErrors
                      //#ifdef DLOGGING
View Full Code Here
81
82
83
84
85
86
87
88
89
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
      }
      if (elementType == XmlParser.END_DOCUMENT ) {
        return null;
      }
           
      EncodingUtil encodingUtil = parser.getEncodingUtil();
            do {
        /** RSS item properties */
        String title = "";
        String link = "";
                       
        String tagName = parser.getName();
        System.out.println("tagname: " + tagName);
        if (tagName.equals("outline")) {
          System.out.println("Parsing <outline> tag");
         
          title = parser.getAttributeValue( "text" );
          if (title != null) {
            title = EncodingUtil.replaceAlphaEntities(true,
                title);
            // No need to convert from UTF-8 to Unicode using replace
            // umlauts now because it is done with new String...,encoding.

            // Replace numeric entities including &#8217;, &#8216;
            // &#8220;, and &#8221;
            title = EncodingUtil.replaceNumEntity(title);

            // Replace special chars like left quote, etc.
            // Since we have already converted to unicode, we want
            // to replace with uni chars.
            title = encodingUtil.replaceSpChars(title);
          }
          /**
           * Create new RSS item and add it do RSS document's item
           * collection.  Account for wrong OPML which is an
           * OPML composed of other OPML.  These have url attribute
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
    public RssItunesFeed[] parseFeeds(InputStream is)
    throws IOException, CauseMemoryException, CauseException, Exception {
    // Init in case we get a severe error.
    try {
      return HTMLAutoLinkParser.parseFeeds(new EncodingUtil(is),
                      m_url,
                      m_needRss,
                      m_needFirstRss,
                      m_feedNameFilter,
                      m_feedURLFilter
View Full Code Here
88
89
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
                    "/"+Common.DATA_FOLDER+"/" + Common.LANGUAGE_FILE);
      if (is == null) {
        throw new IOException("Unable to read file " +
                    "/"+Common.DATA_FOLDER+"/" + Common.LANGUAGE_FILE);
      }
      EncodingUtil encUtl = new EncodingUtil(is);
      EncodingStreamReader esr = encUtl.getEncodingStreamReader();
      StringBuffer inputBuffer;
      try {
        inputBuffer = esr.readFile(Common.LANGUAGE_FILE_LEN);
      } catch (IOException ex) {
        CauseException cex = new CauseException(
            "Error while reading file.", ex);
        throw cex;
      } finally {
        if (is != null) {
          try {
            is.close();
          } catch (Exception e) {
          }
        }
      }
      String text;
      /* If not UTF-8, treat it as one since we use XSL to create UTF-8.
         I couldn't create a file with BOM, so this is the next best
         thing.  */
      final String fileEncoding = esr.getFileEncoding();
      if (!esr.isUtfDoc()) {
        esr.setUtfDoc(true);
        encUtl.getEncoding(fileEncoding, "UTF-8");
      }
      if (esr.isUtfDoc()) {
        if (esr.isUtf16Doc()) {
          encUtl.getEncoding(fileEncoding, "UTF-16");
        } else {
          encUtl.getEncoding(fileEncoding, "UTF-8");
        }
        final String docEncoding = encUtl.getDocEncoding();
        if (docEncoding.length() == 0) {
          text = inputBuffer.toString();
        } else {
          try {
            // We read the bytes in as ISO8859_1, so we must get them
View Full Code Here
88
89
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
                    "/"+Common.DATA_FOLDER+"/" + Common.LANGUAGE_FILE);
      if (is == null) {
        throw new IOException("Unable to read file " +
                    "/"+Common.DATA_FOLDER+"/" + Common.LANGUAGE_FILE);
      }
      EncodingUtil encUtl = new EncodingUtil(is);
      EncodingStreamReader esr = encUtl.getEncodingStreamReader();
      StringBuffer inputBuffer;
      try {
        inputBuffer = esr.readFile(Common.LANGUAGE_FILE_LEN);
      } catch (IOException ex) {
        CauseException cex = new CauseException(
            "Error while reading file.", ex);
        throw cex;
      } finally {
        if (is != null) {
          try {
            is.close();
          } catch (Exception e) {
          }
        }
      }
      String text;
      /* If not UTF-8, treat it as one since we use XSL to create UTF-8.
         I couldn't create a file with BOM, so this is the next best
         thing.  */
      final String fileEncoding = esr.getFileEncoding();
      if (!esr.isUtfDoc()) {
        esr.setUtfDoc(true);
        encUtl.getEncoding(fileEncoding, "UTF-8");
      }
      if (esr.isUtfDoc()) {
        if (esr.isUtf16Doc()) {
          encUtl.getEncoding(fileEncoding, "UTF-16");
        } else {
          encUtl.getEncoding(fileEncoding, "UTF-8");
        }
        final String docEncoding = encUtl.getDocEncoding();
        if (docEncoding.length() == 0) {
          text = inputBuffer.toString();
        } else {
          try {
            // We read the bytes in as ISO8859_1, so we must get them
View Full Code Here
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
        final String isoEncoding, final boolean hasWinEncoding,
        final String winEncoding, final String encoding,
        final String expEncoding) {
    String data = "ab";
    ByteArrayInputStream bin = new ByteArrayInputStream( data.getBytes() );
    EncodingUtil encUtl = new EncodingUtil(bin);
    super.append("----------");
    super.append(new StringItem("hasIso8859Encoding=",
          new Boolean(hasIso8859Encoding).toString()));
    super.append(new StringItem("isoEncoding=", isoEncoding));
    super.append(new StringItem("hasWinEncoding=",
          new Boolean(hasWinEncoding).toString()));
    super.append(new StringItem("winEncoding=", winEncoding));
    super.append(new StringItem("encoding=", encoding));
    encUtl.getEncoding(hasIso8859Encoding, isoEncoding, hasWinEncoding,
        winEncoding, "BIG-5", encoding);
    super.append(new StringItem("(" + tstName + ") Exp Result:", "\n" +
        expEncoding));
    final String actEncoding = encUtl.getDocEncoding();
    super.append(new StringItem("(" + tstName + ") Act Result: ", "\n" +
        actEncoding));
    super.append("\n" + new Boolean(actEncoding.equals(
            expEncoding)).toString());
    Vector excs = encUtl.getExcs();
    for (int ic = 0; ic < excs.size(); ic++) {
      Exception exc = (Exception)excs.elementAt(ic);
      super.append(new StringItem("exc " + ic, "\n" +
          exc.getMessage()));
    }
View Full Code Here
273
274
275
276
277
278
279
280
281
282
283
          " to 2nd redirect url:  " + url);
    }
    m_redirect = true;
    m_redirectUrl = url;
    com.substanceofcode.rssreader.businessentities.RssItunesFeed[] feeds =
        HTMLLinkParser.parseFeeds(new EncodingUtil(is),
                  url, null, null, true
                  //#ifdef DLOGGING
//@                  ,logger,
//@                  fineLoggable,
//@                  finerLoggable,
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
    public RssItunesFeed[] parseFeeds(InputStream is)
    throws IOException, CauseMemoryException, CauseException, Exception {
        // Prepare buffer for input data
        StringBuffer inputBuffer = new StringBuffer();
       
    EncodingUtil encUtl = new EncodingUtil(is);
    EncodingStreamReader esr = encUtl.getEncodingStreamReader();

        try {
      // Read all data to buffer.  Use 100 char increments to save on
      // memory.
      inputBuffer = esr.readFile(100);
        } catch (IOException ex) {
      CauseException cex = new CauseException(
          "Error while parsing line by feed " + m_url, ex);
      throw cex;
        }
        String text;
    if (esr.isUtfDoc()) {
      final String fileEncoding = esr.getFileEncoding();
      if (esr.isUtf16Doc()) {
        encUtl.getEncoding(fileEncoding, "UTF-16");
      } else {
        encUtl.getEncoding(fileEncoding, "UTF-8");
      }
      final String docEncoding = encUtl.getDocEncoding();
      if (docEncoding.length() == 0) {
        text = inputBuffer.toString();
      } else {
        try {
          // We read the bytes in as ISO8859_1, so we must get them
View Full Code Here
TOP

Related Classes of com.substanceofcode.utils.EncodingUtil

  • com.substanceofcode.rssreader.businesslogic.HTMLAutoLinkParser
  • com.substanceofcode.rssreader.businesslogic.HTMLLinkParser
  • com.substanceofcode.rssreader.businesslogic.LineByLineParser
  • com.substanceofcode.rssreader.businesslogic.OpmlParser
  • com.substanceofcode.rssreader.businesslogic.URLHandler
  • com.substanceofcode.testutil.presentation.TestingForm
  • cz.cacek.ebook.util.ResourceProviderME
  • net.sf.jlogmicro.util.logging.Logger
  • com.substanceofcode.utils.CauseException
  • java.util.Hashtable
    • 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.