Package org.apache.poi.hwpf.usermodel

Examples of org.apache.poi.hwpf.usermodel.Paragraph

64
65
66
67
68
69
70
71
72
73
74
75
    public void testExtractFromModel() {
      Range r = doc.getRange();
     
      String[] text = new String[r.numParagraphs()];
      for(int i=0; i < r.numParagraphs(); i++) {
        Paragraph p = r.getParagraph(i);
        text[i] = p.text();
      }
     
      assertEquals(p_text.length, text.length);
      for(int i=0; i<p_text.length; i++) {
        assertEquals(p_text[i], text[i]);
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
145
        protected static String[] getParagraphText(Range r) {
                String[] ret;
                ret = new String[r.numParagraphs()];
                for (int i = 0; i < ret.length; i++) {
                        Paragraph p = r.getParagraph(i);
                        ret[i] = p.text();

                        // Fix the line ending
                        if (ret[i].endsWith("\r")) {
                                ret[i] = ret[i] + "\n";
                        }
View Full Code Here
74
75
76
77
78
79
80
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
                    } else if ("Document".equals(name)) {
                        HWPFDocument doc = new HWPFDocument(data.getData());
                        //read the word document
                        Range r = doc.getRange();
                        for(int k = 0; k < r.numParagraphs(); k++) {
                            Paragraph p = r.getParagraph(k);
                            System.out.println(p.text());
                         }

                        //save on disk
                        FileOutputStream out = new FileOutputStream(name + "-("+(j)+").doc");
                        doc.write(out);
                        out.close();
                     }  else {
                        FileOutputStream out = new FileOutputStream(ole.getProgID() + "-"+(j+1)+".dat");
                        InputStream dis = data.getData();
                        byte[] chunk = new byte[2048];
                        int count;
                        while ((count = dis.read(chunk)) >= 0) {
                          out.write(chunk,0,count);
                        }
                        is.close();
                        out.close();
                    }
                }

            }
        }

        //Pictures
        for (int i = 0; i < slide.length; i++) {
            Shape[] shape = slide[i].getShapes();
            for (int j = 0; j < shape.length; j++) {
                if (shape[j] instanceof Picture) {
                    Picture p = (Picture) shape[j];
                    PictureData data = p.getPictureData();
                    String name = p.getPictureName();
                    int type = data.getType();
                    String ext;
                    switch (type) {
                        case Picture.JPEG:
                            ext = ".jpg";
View Full Code Here
54
55
56
57
58
59
60
61
62
63
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
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
    int sectionLevel = 0;
    int lenParagraph = r.numParagraphs ();
    boolean inCode = false;
    for (int x = 0; x < lenParagraph; x++)
    {
      Paragraph p = r.getParagraph (x);
      String text = p.text ();
      if (text.trim ().length () == 0)
      {
        continue;
      }
      StyleDescription paragraphStyle = styleSheet.getStyleDescription (p.
        getStyleIndex ());
      String styleName = paragraphStyle.getName();
      if (styleName.startsWith ("Heading"))
      {
        if (inCode)
        {
          closeSource();
          inCode = false;
        }

        int headerLevel = Integer.parseInt (styleName.substring (8));
        if (headerLevel > sectionLevel)
        {
          openSection ();
        }
        else
        {
          for (int y = 0; y < (sectionLevel - headerLevel) + 1; y++)
          {
            closeSection ();
          }
          openSection ();
        }
        sectionLevel = headerLevel;
        openTitle ();
        writePlainText (text);
        closeTitle ();
      }
      else
      {
        int cruns = p.numCharacterRuns ();
        CharacterRun run = p.getCharacterRun (0);
        String fontName = run.getFontName();
        if (fontName.startsWith ("Courier"))
        {
          if (!inCode)
          {
            openSource ();
            inCode = true;
          }
          writePlainText (p.text());
        }
        else
        {
          if (inCode)
          {
            inCode = false;
            closeSource();
          }
          openParagraph();
          writePlainText(p.text());
          closeParagraph();
        }
      }
    }
    for (int x = 0; x < sectionLevel; x++)
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
      for (int x = 0; x < r.numSections(); x++)
      {
        Section s = r.getSection(x);
        for (int y = 0; y < s.numParagraphs(); y++)
        {
          Paragraph p = s.getParagraph(y);
          for (int z = 0; z < p.numCharacterRuns(); z++)
          {
            //character run
            CharacterRun run = p.getCharacterRun(z);
            //character run text
            String text = run.text();
            // show us the text
            System.out.print(text);
          }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
        Range range = document.getRange();

        StyleSheet stylesheet = document.getStyleSheet();

        for (int i = 0; i < range.numParagraphs(); i++) {
            Paragraph paragraph = range.getParagraph(i);

            String styleName = stylesheet.getStyleDescription(paragraph.getStyleIndex()).getName();

            if (styleName.startsWith(HEADER_PREFIX)) {
                String rawLevelNum = styleName.substring(HEADER_PREFIX.length() + 1).trim();
                int levelNum = 0;

                try {
                    levelNum = Integer.parseInt(rawLevelNum);
                } catch (NumberFormatException nfe) {
                    log.debug("Could not parse heading level from: " + styleName);
                }

                String text = Paragraph.stripFields(paragraph.text());

                if ('\r' == text.charAt(text.length() - 1)) {
                    text = text.substring(0, text.length() - 1);
                }
View Full Code Here
623
624
625
626
627
628
629
630
631
632
633
634
    public void dumpParagraphsDom( boolean withText )
    {
        Range range = _doc.getOverallRange();
        for ( int p = 0; p < range.numParagraphs(); p++ )
        {
            Paragraph paragraph = range.getParagraph( p );
            System.out.println( p + ":\t" + paragraph.toString() );

            if ( withText )
                System.out.println( paragraph.text() );
        }
    }
View Full Code Here
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
        int currentListInfo = 0;

        final int paragraphs = range.numParagraphs();
        for ( int p = 0; p < paragraphs; p++ )
        {
            Paragraph paragraph = range.getParagraph( p );

            if ( paragraph.isInTable()
                    && paragraph.getTableLevel() != currentTableLevel )
            {
                if ( paragraph.getTableLevel() < currentTableLevel )
                    throw new IllegalStateException(
                            "Trying to process table cell with higher level ("
                                    + paragraph.getTableLevel()
                                    + ") than current table level ("
                                    + currentTableLevel
                                    + ") as inner table part" );

                Table table = range.getTable( paragraph );
                processTable( wordDocument, flow, table );

                p += table.numParagraphs();
                p--;
                continue;
            }

            if ( paragraph.text().equals( "\u000c" ) )
            {
                processPageBreak( wordDocument, flow );
            }

            if ( paragraph.getIlfo() != currentListInfo )
            {
                currentListInfo = paragraph.getIlfo();
            }

            if ( currentListInfo != 0 )
            {
                if ( listTables != null )
                {
                    final ListFormatOverride listFormatOverride = listTables
                            .getOverride( paragraph.getIlfo() );

                    String label = AbstractWordUtils.getBulletText( listTables,
                            paragraph, listFormatOverride.getLsid() );

                    processParagraph( wordDocument, flow, currentTableLevel,
                            paragraph, label );
                }
                else
                {
                    logger.log( POILogger.WARN,
                            "Paragraph #" + paragraph.getStartOffset() + "-"
                                    + paragraph.getEndOffset()
                                    + " has reference to list structure #"
                                    + currentListInfo
                                    + ", but listTables not defined in file" );

                    processParagraph( wordDocument, flow, currentTableLevel,
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
        PicturesSource pictures = new PicturesSource(document);
       
        // Do the main paragraph text
        Range r = document.getRange();
        for(int i=0; i<r.numParagraphs(); i++) {
           Paragraph p = r.getParagraph(i);
           i += handleParagraph(p, 0, r, document, pictures, pictureTable, xhtml);
        }

        // Do everything else
        for (String paragraph : wordExtractor.getFootnoteText()) {
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
             for(int cn=0; cn<row.numCells(); cn++) {
                TableCell cell = row.getCell(cn);
                xhtml.startElement("td");

                for(int pn=0; pn<cell.numParagraphs(); pn++) {
                   Paragraph cellP = cell.getParagraph(pn);
                   handleParagraph(cellP, p.getTableLevel(), cell, document, pictures, pictureTable, xhtml);
                }
                xhtml.endElement("td");
             }
             xhtml.endElement("tr");
View Full Code Here
TOP

Related Classes of org.apache.poi.hwpf.usermodel.Paragraph

  • org.apache.poi.hslf.examples.DataExtraction
  • org.apache.poi.hwpf.converter.AbstractWordConverter
  • org.apache.poi.hwpf.dev.HWPFLister
  • org.apache.poi.hwpf.extractor.TestDifferentRoutes
  • org.apache.poi.hwpf.extractor.WordExtractor
  • org.apache.poi.hwpf.HWPFDocumentCore
  • org.apache.poi.hwpf.model.LFO
  • org.apache.poi.hwpf.model.ListFormatOverride
  • org.apache.poi.hwpf.model.ListLevel
  • org.apache.poi.hwpf.model.ListTables
    • 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.