Package org.apache.poi.hwpf.model

Examples of org.apache.poi.hwpf.model.TextPiece

121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
  public String getTextFromPieces() {
      StringBuffer textBuf = new StringBuffer();
     
      Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
      while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();

        String encoding = "Cp1252";
        if (piece.usesUnicode()) {
          encoding = "UTF-16LE";
        }
        try {
          String text = new String(piece.getRawBytes(), encoding);
          textBuf.append(text);
        } catch(UnsupportedEncodingException e) {
          throw new InternalError("Standard Encoding " + encoding + " not found, JVM broken");
        }
      }
View Full Code Here
235
236
237
238
239
240
241
242
243
244
245
246
  initText();

  for (int i = _textStart; i < _textEnd; i++)
  {
    TextPiece piece = (TextPiece)_text.get(i);
    if (piece.usesUnicode())
      return true;
  }

  return false;
  }
View Full Code Here
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
    StringBuffer sb = new StringBuffer();

    for (int x = _textStart; x < _textEnd; x++)
    {
      TextPiece piece = (TextPiece)_text.get(x);
      int start = _start > piece.getStart() ? _start - piece.getStart() : 0;
      int end = _end <= piece.getEnd() ? _end - piece.getStart() : piece.getEnd() - piece.getStart();

      if(piece.usesUnicode()) // convert the byte pointers to char pointers
      {
        start/=2;
        end/=2;
      }
      sb.append(piece.getStringBuffer().substring(start, end));
    }
    return sb.toString();
  }
View Full Code Here
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
  public CharacterRun insertBefore(String text)
    //throws UnsupportedEncodingException
  {
    initAll();

    TextPiece tp = (TextPiece)_text.get(_textStart);
    StringBuffer sb = (StringBuffer)tp.getStringBuffer();

    // Since this is the first item in our list, it is safe to assume that
    // _start >= tp.getStart()
    int insertIndex = _start - tp.getStart();
  if (tp.usesUnicode())
    insertIndex /= 2;
    sb.insert(insertIndex, text);

    int adjustedLength = _doc.getTextTable().adjustForInsert(_textStart, text.length());
    _doc.getCharacterTable().adjustForInsert(_charStart, adjustedLength);
View Full Code Here
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
  public CharacterRun insertAfter(String text)
  {
    initAll();

    int listIndex = _textEnd - 1;
    TextPiece tp = (TextPiece)_text.get(listIndex);
    StringBuffer sb = (StringBuffer)tp.getStringBuffer();

    int insertIndex = _end - tp.getStart();

    if (tp.getStringBuffer().charAt(_end - 1) == '\r' && text.charAt(0) != '\u0007')
    {
      insertIndex--;
    }
    sb.insert(insertIndex, text);
    int adjustedLength = _doc.getTextTable().adjustForInsert(listIndex, text.length());
View Full Code Here
540
541
542
543
544
545
546
547
548
549
550
551
      sepx.adjustForDelete(_start, _end - _start);
    }
   
    for (int x = _textStart; x < numTextPieces; x++)
    {
      TextPiece piece = (TextPiece)_text.get(x);
      piece.adjustForDelete(_start, _end - _start);
    }

  // update the FIB.CCPText field
  if (usesUnicode())
    adjustFIB(-((_end - _start) / 2));
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
    public void testExtractFromTextPieces() throws Exception {
      StringBuffer textBuf = new StringBuffer();
     
      Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
      while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();

        String encoding = "Cp1252";
        if (piece.usesUnicode()) {
          encoding = "UTF-16LE";
        }
        String text = new String(piece.getRawBytes(), encoding);
        textBuf.append(text);
      }
     
      StringBuffer exp = new StringBuffer();
      for(int i=0; i<p_text.length; i++) {
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
        List textRuns = cbt.getTextRuns();
        Iterator runIt = textRuns.iterator();
        Iterator textIt = textPieces.iterator();

        TextPiece currentPiece = (TextPiece)textIt.next();
        int currentTextStart = currentPiece.getStart();
        int currentTextEnd = currentPiece.getEnd();

        WordTextBuffer finalTextBuf = new WordTextBuffer(appendable);

        // iterate through all text runs extract the text only if they haven't been
        // deleted
        while (runIt.hasNext()) {
            CHPX chpx = (CHPX)runIt.next();
            boolean deleted = isDeleted(chpx.getGrpprl());
            if (deleted) {
                continue;
            }

            int runStart = chpx.getStart();
            int runEnd = chpx.getEnd();

            while (runStart >= currentTextEnd) {
                currentPiece = (TextPiece) textIt.next ();
                currentTextStart = currentPiece.getStart ();
                currentTextEnd = currentPiece.getEnd ();
            }

            if (runEnd < currentTextEnd) {
                String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
                finalTextBuf.append(str);
            } else if (runEnd > currentTextEnd) {
                while (runEnd > currentTextEnd) {
                    String str = currentPiece.substring(runStart - currentTextStart,
                            currentTextEnd - currentTextStart);
                    finalTextBuf.append(str);
                    if (textIt.hasNext()) {
                        currentPiece = (TextPiece) textIt.next ();
                        currentTextStart = currentPiece.getStart ();
                        runStart = currentTextStart;
                        currentTextEnd = currentPiece.getEnd ();
                    } else {
                        return;
                    }
                }
                String str = currentPiece.substring(0, runEnd - currentTextStart);
                finalTextBuf.append(str);
            } else {
                String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
                if (textIt.hasNext()) {
                    currentPiece = (TextPiece) textIt.next();
                    currentTextStart = currentPiece.getStart();
                    currentTextEnd = currentPiece.getEnd();
                }
                finalTextBuf.append(str);
            }
        }
    }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
    public void testExtractFromTextPieces() throws Exception {
      StringBuffer textBuf = new StringBuffer();

      Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
      while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();

        String encoding = "Cp1252";
        if (piece.isUnicode()) {
          encoding = "UTF-16LE";
        }
        String text = new String(piece.getRawBytes(), encoding);
        textBuf.append(text);
      }

      StringBuffer exp = new StringBuffer();
      for(int i=0; i<p_text.length; i++) {
View Full Code Here
254
255
256
257
258
259
260
261
262
263
264
265
  initText();

  for (int i = _textStart; i < _textEnd; i++)
  {
    TextPiece piece = (TextPiece)_text.get(i);
    if (piece.isUnicode())
      return true;
  }

  return false;
  }
View Full Code Here
TOP

Related Classes of org.apache.poi.hwpf.model.TextPiece

  • org.apache.nutch.parse.msword.WordExtractor
  • org.apache.poi.hwpf.extractor.TestDifferentRoutes
  • org.apache.poi.hwpf.extractor.WordExtractor
  • org.apache.poi.hwpf.HWPFDocument
  • org.apache.poi.hwpf.HWPFOldDocument
  • org.apache.poi.hwpf.usermodel.Range
  • org.apache.tika.parser.microsoft.WordParser
    • 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.