Package com.itextpdf.text.pdf

Examples of com.itextpdf.text.pdf.PRTokeniser

56
57
58
59
60
61
62
    public CidLocationFromByte(byte[] data) {
        this.data = data;
    }
   
    public PRTokeniser getLocation(String location) throws IOException {
        return new PRTokeniser(data);
    }
View Full Code Here
59
60
61
62
63
64
65
    public PRTokeniser getLocation(String location) throws IOException {
        String fullName = BaseFont.RESOURCE_PATH + "cmaps/" + location;
        InputStream inp = BaseFont.getResourceStream(fullName);
        if (inp == null)
            throw new IOException(MessageLocalization.getComposedMessage("the.cmap.1.was.not.found", fullName));
        return new PRTokeniser(new RandomAccessFileOrArray(inp));
    }
View Full Code Here
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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
    }
   
    private static void parseCid(String cmapName, AbstractCMap cmap, CidLocation location, int level) throws IOException {
        if (level >= MAXLEVEL)
            return;
        PRTokeniser inp = location.getLocation(cmapName);
        try {
            ArrayList<PdfObject> list = new ArrayList<PdfObject>();
            PdfContentParser cp = new PdfContentParser(inp);
            int maxExc = 50;
            while (true) {
                try {
                    cp.parse(list);
                }
                catch (Exception ex) {
                    if (--maxExc < 0)
                        break;
                    continue;
                }
                if (list.isEmpty())
                    break;
                String last = list.get(list.size() - 1).toString();
                if (level == 0 && list.size() == 3 && last.equals(DEF)) {
                    PdfObject key = list.get(0);
                    if (PdfName.REGISTRY.equals(key))
                        cmap.setRegistry(list.get(1).toString());
                    else if (PdfName.ORDERING.equals(key))
                        cmap.setOrdering(list.get(1).toString());
                    else if (CMAPNAME.equals(key))
                        cmap.setName(list.get(1).toString());
                    else if (PdfName.SUPPLEMENT.equals(key)) {
                        try {
                            cmap.setSupplement(((PdfNumber)list.get(1)).intValue());
                        }
                        catch (Exception ex) {}
                    }
                }
                else if ((last.equals(ENDCIDCHAR) || last.equals(ENDBFCHAR)) && list.size() >= 3) {
                    int lmax = list.size() - 2;
                    for (int k = 0; k < lmax; k += 2) {
                        if (list.get(k) instanceof PdfString) {
                            cmap.addChar((PdfString)list.get(k), list.get(k + 1));
                        }
                    }
                }
                else if ((last.equals(ENDCIDRANGE) || last.equals(ENDBFRANGE)) && list.size() >= 4) {
                    int lmax = list.size() - 3;
                    for (int k = 0; k < lmax; k += 3) {
                        if (list.get(k) instanceof PdfString && list.get(k + 1) instanceof PdfString) {
                            cmap.addRange((PdfString)list.get(k), (PdfString)list.get(k + 1), list.get(k + 2));
                        }
                    }
                }
                else if (last.equals(USECMAP) && list.size() == 2 && list.get(0) instanceof PdfName) {
                    parseCid(PdfName.decodeName(list.get(0).toString()), cmap, location, level + 1);
                }
            }
        }
        finally {
            inp.close();
        }
    }
View Full Code Here
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
       
        PdfNumber h = imageDictionary.getAsNumber(PdfName.HEIGHT);

        int bytesToRead = computeBytesPerRow(imageDictionary, colorSpaceDic) * h.intValue();
        byte[] bytes = new byte[bytesToRead];
        PRTokeniser tokeniser = ps.getTokeniser();
       
        int shouldBeWhiteSpace = tokeniser.read(); // skip next character (which better be a whitespace character - I suppose we could check for this)
        // from the PDF spec:  Unless the image uses ASCIIHexDecode or ASCII85Decode as one of its filters, the ID operator shall be followed by a single white-space character, and the next character shall be interpreted as the first byte of image data.
        // unfortunately, we've seen some PDFs where there is no space following the ID, so we have to capture this case and handle it
        int startIndex = 0;
        if (!PRTokeniser.isWhitespace(shouldBeWhiteSpace)){
            bytes[0] = (byte)shouldBeWhiteSpace;
            startIndex++;
        }
        for(int i = startIndex; i < bytesToRead; i++){
            int ch = tokeniser.read();
            if (ch == -1)
                throw new InlineImageParseException("End of content stream reached before end of image data");
           
            bytes[i] = (byte)ch;
        }
View Full Code Here
329
330
331
332
333
334
335
336
337
338
339
340
341
        // I'd rather avoid right now.
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        ByteArrayOutputStream accumulated = new ByteArrayOutputStream();
        int ch;
        int found = 0;
        PRTokeniser tokeniser = ps.getTokeniser();
       
        while ((ch = tokeniser.read()) != -1){
            if (found == 0 && PRTokeniser.isWhitespace(ch)){
                found++;
                accumulated.write(ch);
            } else if (found == 1 && ch == 'E'){
                found++;
View Full Code Here
351
352
353
354
355
356
357
358
359
360
361
     * @param resources    the resources that come with the content stream
     */
    public void processContent(byte[] contentBytes, PdfDictionary resources){
        this.resources.push(resources);
        try {
            PRTokeniser tokeniser = new PRTokeniser(contentBytes);
            PdfContentParser ps = new PdfContentParser(tokeniser);
            ArrayList<PdfObject> operands = new ArrayList<PdfObject>();
            while (ps.parse(operands).size() > 0){
                PdfLiteral operator = (PdfLiteral)operands.get(operands.size()-1);
                if ("BI".equals(operator.toString())){
View Full Code Here
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
     */
    public void processContent(byte[] contentBytes, PdfDictionary resources){

        this.resources.push(resources);
        try {
            PRTokeniser tokeniser = new PRTokeniser(contentBytes);
            PdfContentParser ps = new PdfContentParser(tokeniser);
            ArrayList<PdfObject> operands = new ArrayList<PdfObject>();
            while (ps.parse(operands).size() > 0){
                PdfLiteral operator = (PdfLiteral)operands.get(operands.size()-1);
               
                // special handling for embedded images.  If we hit an ID operator, we need
                // to skip all content until we reach an EI operator surrounded by whitespace.
                // The following algorithm has one potential issue: what if the image stream
                // contains <ws>EI<ws> ?
                // it sounds like we would have to actually decode the content stream, which
                // I'd rather avoid right now.
                if ("ID".equals(operator.toString())){
                    ByteArrayOutputStream baos = new ByteArrayOutputStream();
                    ByteArrayOutputStream accumulated = new ByteArrayOutputStream();
                    int ch;
                    int found = 0;
                    while ((ch = tokeniser.read()) != -1){
                        if (found == 0 && PRTokeniser.isWhitespace(ch)){
                            found++;
                            accumulated.write(ch);
                        } else if (found == 1 && ch == 'E'){
                            found++;
View Full Code Here
373
374
375
376
377
378
379
380
381
382
383
     * @param resources    the resources that come with the content stream
     */
    public void processContent(byte[] contentBytes, PdfDictionary resources){
        this.resources.push(resources);
        try {
            PRTokeniser tokeniser = new PRTokeniser(new RandomAccessFileOrArray(new RandomAccessSourceFactory().createSource(contentBytes)));
            PdfContentParser ps = new PdfContentParser(tokeniser);
            ArrayList<PdfObject> operands = new ArrayList<PdfObject>();
            while (ps.parse(operands).size() > 0){
                PdfLiteral operator = (PdfLiteral)operands.get(operands.size()-1);
                if ("BI".equals(operator.toString())){
View Full Code Here
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
       
        PdfNumber h = imageDictionary.getAsNumber(PdfName.HEIGHT);

        int bytesToRead = computeBytesPerRow(imageDictionary, colorSpaceDic) * h.intValue();
        byte[] bytes = new byte[bytesToRead];
        PRTokeniser tokeniser = ps.getTokeniser();
       
        int shouldBeWhiteSpace = tokeniser.read(); // skip next character (which better be a whitespace character - I suppose we could check for this)
        // from the PDF spec:  Unless the image uses ASCIIHexDecode or ASCII85Decode as one of its filters, the ID operator shall be followed by a single white-space character, and the next character shall be interpreted as the first byte of image data.
        // unfortunately, we've seen some PDFs where there is no space following the ID, so we have to capture this case and handle it
        int startIndex = 0;
        if (!PRTokeniser.isWhitespace(shouldBeWhiteSpace) || shouldBeWhiteSpace == 0){ // tokeniser treats 0 as whitespace, but for our purposes, we shouldn't
            bytes[0] = (byte)shouldBeWhiteSpace;
            startIndex++;
        }
        for(int i = startIndex; i < bytesToRead; i++){
            int ch = tokeniser.read();
            if (ch == -1)
                throw new InlineImageParseException("End of content stream reached before end of image data");
           
            bytes[i] = (byte)ch;
        }
View Full Code Here
340
341
342
343
344
345
346
347
348
349
350
351
352
        // I'd rather avoid right now.
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        ByteArrayOutputStream accumulated = new ByteArrayOutputStream();
        int ch;
        int found = 0;
        PRTokeniser tokeniser = ps.getTokeniser();
       
        while ((ch = tokeniser.read()) != -1){
            if (found == 0 && PRTokeniser.isWhitespace(ch)){
                found++;
                accumulated.write(ch);
            } else if (found == 1 && ch == 'E'){
                found++;
View Full Code Here
TOP

Related Classes of com.itextpdf.text.pdf.PRTokeniser

  • br.com.objectos.way.boleto.PdfToText
  • com.itextpdf.text.io.RandomAccessSourceFactory
  • com.itextpdf.text.pdf.fonts.cmaps.CidLocationFromByte
  • com.itextpdf.text.pdf.fonts.cmaps.CidResource
  • com.itextpdf.text.pdf.fonts.cmaps.CMapParserEx
  • com.itextpdf.text.pdf.mc.MCParser
  • com.itextpdf.text.pdf.ocg.OCGParser
  • com.itextpdf.text.pdf.parser.InlineImageUtils
  • com.itextpdf.text.pdf.parser.PdfContentStreamProcessor
  • com.itextpdf.text.exceptions.InvalidPdfException
    • 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.