summaryrefslogtreecommitdiff
path: root/utils/pdftotext.cc
blob: 15c741d37237cd30ce2745f371408a8fff699747 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
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
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
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
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
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
//========================================================================
//
// pdftotext.cc
//
// Copyright 1997-2003 Glyph & Cog, LLC
//
// Modified for Debian by Hamish Moffatt, 22 May 2002.
//
//========================================================================

//========================================================================
//
// Modified under the Poppler project - http://poppler.freedesktop.org
//
// All changes made under the Poppler project to this file are licensed
// under GPL version 2 or later
//
// Copyright (C) 2006 Dominic Lachowicz <cinamod@hotmail.com>
// Copyright (C) 2007-2008, 2010, 2011 Albert Astals Cid <aacid@kde.org>
// Copyright (C) 2009 Jan Jockusch <jan@jockusch.de>
// Copyright (C) 2010, 2013 Hib Eris <hib@hiberis.nl>
// Copyright (C) 2010 Kenneth Berland <ken@hero.com>
// Copyright (C) 2011 Tom Gleason <tom@buildadam.com>
// Copyright (C) 2011 Steven Murdoch <Steven.Murdoch@cl.cam.ac.uk>
// Copyright (C) 2013 Yury G. Kudryashov <urkud.urkud@gmail.com>
// Copyright (C) 2013 Suzuki Toshiya <mpsuzuki@hiroshima-u.ac.jp>
//
// To see a description of the changes please see the Changelog file that
// came with your tarball or type make ChangeLog if you are building from git
//
//========================================================================

#include "config.h"
#include <poppler-config.h>
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include "parseargs.h"
#include "printencodings.h"
#include "goo/GooString.h"
#include "goo/gmem.h"
#include "GlobalParams.h"
#include "Object.h"
#include "Stream.h"
#include "Array.h"
#include "Dict.h"
#include "XRef.h"
#include "Catalog.h"
#include "Page.h"
#include "PDFDoc.h"
#include "PDFDocFactory.h"
#include "TextOutputDev.h"
#include "CharTypes.h"
#include "UnicodeMap.h"
#include "PDFDocEncoding.h"
#include "Error.h"
#include <string>

static void printInfoString(FILE *f, Dict *infoDict, const char *key,
			    const char *text1, const char *text2, UnicodeMap *uMap);
static void printInfoDate(FILE *f, Dict *infoDict, const char *key, const char *fmt);

static int firstPage = 1;
static int lastPage = 0;
static double resolution = 72.0;
static int x = 0;
static int y = 0;
static int w = 0;
static int h = 0;
static GBool bbox = gFalse;
static GBool physLayout = gFalse;
static double fixedPitch = 0;
static GBool rawOrder = gFalse;
static GBool htmlMeta = gFalse;
static char textEncName[128] = "";
static char textEOL[16] = "";
static GBool noPageBreaks = gFalse;
static char ownerPassword[33] = "\001";
static char userPassword[33] = "\001";
static GBool quiet = gFalse;
static GBool printVersion = gFalse;
static GBool printHelp = gFalse;
static GBool printEnc = gFalse;

static const ArgDesc argDesc[] = {
  {"-f",       argInt,      &firstPage,     0,
   "first page to convert"},
  {"-l",       argInt,      &lastPage,      0,
   "last page to convert"},
  {"-r",      argFP,       &resolution,    0,
   "resolution, in DPI (default is 72)"},
  {"-x",      argInt,      &x,             0,
   "x-coordinate of the crop area top left corner"},
  {"-y",      argInt,      &y,             0,
   "y-coordinate of the crop area top left corner"},
  {"-W",      argInt,      &w,             0,
   "width of crop area in pixels (default is 0)"},
  {"-H",      argInt,      &h,             0,
   "height of crop area in pixels (default is 0)"},
  {"-layout",  argFlag,     &physLayout,    0,
   "maintain original physical layout"},
  {"-fixed",   argFP,       &fixedPitch,    0,
   "assume fixed-pitch (or tabular) text"},
  {"-raw",     argFlag,     &rawOrder,      0,
   "keep strings in content stream order"},
  {"-htmlmeta", argFlag,   &htmlMeta,       0,
   "generate a simple HTML file, including the meta information"},
  {"-enc",     argString,   textEncName,    sizeof(textEncName),
   "output text encoding name"},
  {"-listenc",argFlag,     &printEnc,      0,
   "list available encodings"},
  {"-eol",     argString,   textEOL,        sizeof(textEOL),
   "output end-of-line convention (unix, dos, or mac)"},
  {"-nopgbrk", argFlag,     &noPageBreaks,  0,
   "don't insert page breaks between pages"},
  {"-bbox", argFlag,     &bbox,  0,
   "output bounding box for each word and page size to html.  Sets -htmlmeta"},
  {"-opw",     argString,   ownerPassword,  sizeof(ownerPassword),
   "owner password (for encrypted files)"},
  {"-upw",     argString,   userPassword,   sizeof(userPassword),
   "user password (for encrypted files)"},
  {"-q",       argFlag,     &quiet,         0,
   "don't print any messages or errors"},
  {"-v",       argFlag,     &printVersion,  0,
   "print copyright and version info"},
  {"-h",       argFlag,     &printHelp,     0,
   "print usage information"},
  {"-help",    argFlag,     &printHelp,     0,
   "print usage information"},
  {"--help",   argFlag,     &printHelp,     0,
   "print usage information"},
  {"-?",       argFlag,     &printHelp,     0,
   "print usage information"},
  {NULL}
};

static std::string myStringReplace(const std::string &inString, const std::string &oldToken, const std::string &newToken) {
  std::string result = inString;
  size_t foundLoc;
  int advance = 0;
  do {
    foundLoc = result.find(oldToken, advance);
    if (foundLoc != std::string::npos){
      result.replace(foundLoc, oldToken.length(), newToken);
      advance = foundLoc + newToken.length();
    }
  } while (foundLoc != std::string::npos );
  return result;
}

static std::string myXmlTokenReplace(const char *inString){
  std::string myString(inString);
  myString = myStringReplace(myString, "&",  "&amp;" );
  myString = myStringReplace(myString, "'",  "&apos;" );
  myString = myStringReplace(myString, "\"", "&quot;" );
  myString = myStringReplace(myString, "<",  "&lt;" );
  myString = myStringReplace(myString, ">",  "&gt;" );
  return myString;
}

int main(int argc, char *argv[]) {
  PDFDoc *doc;
  GooString *fileName;
  GooString *textFileName;
  GooString *ownerPW, *userPW;
  TextOutputDev *textOut;
  FILE *f;
  UnicodeMap *uMap;
  Object info;
  GBool ok;
  char *p;
  int exitCode;

  exitCode = 99;

  // parse args
  ok = parseArgs(argDesc, &argc, argv);
  if (bbox) {
    htmlMeta = gTrue;
  }
  if (!ok || (argc < 2 && !printEnc) || argc > 3 || printVersion || printHelp) {
    fprintf(stderr, "pdftotext version %s\n", PACKAGE_VERSION);
    fprintf(stderr, "%s\n", popplerCopyright);
    fprintf(stderr, "%s\n", xpdfCopyright);
    if (!printVersion) {
      printUsage("pdftotext", "<PDF-file> [<text-file>]", argDesc);
    }
    if (printVersion || printHelp)
      exitCode = 0;
    goto err0;
  }

  // read config file
  globalParams = new GlobalParams();

  if (printEnc) {
    printEncodings();
    delete globalParams;
    exitCode = 0;
    goto err0;
  }

  fileName = new GooString(argv[1]);
  if (fixedPitch) {
    physLayout = gTrue;
  }

  if (textEncName[0]) {
    globalParams->setTextEncoding(textEncName);
  }
  if (textEOL[0]) {
    if (!globalParams->setTextEOL(textEOL)) {
      fprintf(stderr, "Bad '-eol' value on command line\n");
    }
  }
  if (noPageBreaks) {
    globalParams->setTextPageBreaks(gFalse);
  }
  if (quiet) {
    globalParams->setErrQuiet(quiet);
  }

  // get mapping to output encoding
  if (!(uMap = globalParams->getTextEncoding())) {
    error(errCommandLine, -1, "Couldn't get text encoding");
    delete fileName;
    goto err1;
  }

  // open PDF file
  if (ownerPassword[0] != '\001') {
    ownerPW = new GooString(ownerPassword);
  } else {
    ownerPW = NULL;
  }
  if (userPassword[0] != '\001') {
    userPW = new GooString(userPassword);
  } else {
    userPW = NULL;
  }

  if (fileName->cmp("-") == 0) {
      delete fileName;
      fileName = new GooString("fd://0");
  }

  doc = PDFDocFactory().createPDFDoc(*fileName, ownerPW, userPW);

  if (userPW) {
    delete userPW;
  }
  if (ownerPW) {
    delete ownerPW;
  }
  if (!doc->isOk()) {
    exitCode = 1;
    goto err2;
  }

#ifdef ENFORCE_PERMISSIONS
  // check for copy permission
  if (!doc->okToCopy()) {
    error(errNotAllowed, -1, "Copying of text from this document is not allowed.");
    exitCode = 3;
    goto err2;
  }
#endif

  // construct text file name
  if (argc == 3) {
    textFileName = new GooString(argv[2]);
  } else if (fileName->cmp("fd://0") == 0) {
     error(errCommandLine, -1, "You have to provide an output filename when reading form stdin.");
     goto err2;
  } else {
    p = fileName->getCString() + fileName->getLength() - 4;
    if (!strcmp(p, ".pdf") || !strcmp(p, ".PDF")) {
      textFileName = new GooString(fileName->getCString(),
				 fileName->getLength() - 4);
    } else {
      textFileName = fileName->copy();
    }
    textFileName->append(htmlMeta ? ".html" : ".txt");
  }

  // get page range
  if (firstPage < 1) {
    firstPage = 1;
  }
  if (lastPage < 1 || lastPage > doc->getNumPages()) {
    lastPage = doc->getNumPages();
  }
  if (lastPage < firstPage) {
    error(errCommandLine, -1,
          "Wrong page range given: the first page ({0:d}) can not be after the last page ({1:d}).",
          firstPage, lastPage);
    goto err3;
  }

  // write HTML header
  if (htmlMeta) {
    if (!textFileName->cmp("-")) {
      f = stdout;
    } else {
      if (!(f = fopen(textFileName->getCString(), "wb"))) {
	error(errIO, -1, "Couldn't open text file '{0:t}'", textFileName);
	exitCode = 2;
	goto err3;
      }
    }
    fputs("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">", f);
    fputs("<html xmlns=\"http://www.w3.org/1999/xhtml\">\n", f);
    fputs("<head>\n", f);
    doc->getDocInfo(&info);
    if (info.isDict()) {
      Object obj;
      if (info.getDict()->lookup("Title", &obj)->isString()) {
        printInfoString(f, info.getDict(), "Title", "<title>", "</title>\n", uMap);
      } else {
        fputs("<title></title>\n", f);
      }
      obj.free();
      printInfoString(f, info.getDict(), "Subject",
		      "<meta name=\"Subject\" content=\"", "\"/>\n", uMap);
      printInfoString(f, info.getDict(), "Keywords",
		      "<meta name=\"Keywords\" content=\"", "\"/>\n", uMap);
      printInfoString(f, info.getDict(), "Author",
		      "<meta name=\"Author\" content=\"", "\"/>\n", uMap);
      printInfoString(f, info.getDict(), "Creator",
		      "<meta name=\"Creator\" content=\"", "\"/>\n", uMap);
      printInfoString(f, info.getDict(), "Producer",
		      "<meta name=\"Producer\" content=\"", "\"/>\n", uMap);
      printInfoDate(f, info.getDict(), "CreationDate",
		    "<meta name=\"CreationDate\" content=\"\"/>\n");
      printInfoDate(f, info.getDict(), "LastModifiedDate",
		    "<meta name=\"ModDate\" content=\"\"/>\n");
    }
    info.free();
    fputs("</head>\n", f);
    fputs("<body>\n", f);
    if (!bbox) {
      fputs("<pre>\n", f);
      if (f != stdout) {
	fclose(f);
      }
    }
  }

  // write text file
  if (htmlMeta && bbox) { // htmlMeta && is superfluous but makes gcc happier
    textOut = new TextOutputDev(NULL, physLayout, fixedPitch, rawOrder, htmlMeta);

    if (textOut->isOk()) {
      fprintf(f, "<doc>\n");
      for (int page = firstPage; page <= lastPage; ++page) {
        fprintf(f, "  <page width=\"%f\" height=\"%f\">\n",doc->getPageMediaWidth(page), doc->getPageMediaHeight(page));
        doc->displayPage(textOut, page, resolution, resolution, 0, gTrue, gFalse, gFalse);
        TextWordList *wordlist = textOut->makeWordList();
        const int word_length = wordlist != NULL ? wordlist->getLength() : 0;
        TextWord *word;
        double xMinA, yMinA, xMaxA, yMaxA;
        if (word_length == 0)
          fprintf(stderr, "no word list\n");

        for (int i = 0; i < word_length; ++i) {
          word = wordlist->get(i);
          word->getBBox(&xMinA, &yMinA, &xMaxA, &yMaxA);
          const std::string myString = myXmlTokenReplace(word->getText()->getCString());
          fprintf(f,"    <word xMin=\"%f\" yMin=\"%f\" xMax=\"%f\" yMax=\"%f\">%s</word>\n", xMinA, yMinA, xMaxA, yMaxA, myString.c_str());
        }
        fprintf(f, "  </page>\n");
        delete wordlist;
      }
      fprintf(f, "</doc>\n");
    }
    if (f != stdout) {
      fclose(f);
    }
  } else {
    textOut = new TextOutputDev(textFileName->getCString(),
				physLayout, fixedPitch, rawOrder, htmlMeta);
    if (textOut->isOk()) {
      if ((w==0) && (h==0) && (x==0) && (y==0)) {
	doc->displayPages(textOut, firstPage, lastPage, resolution, resolution, 0,
			  gTrue, gFalse, gFalse);
      } else {
	
	for (int page = firstPage; page <= lastPage; ++page) {
	  doc->displayPageSlice(textOut, page, resolution, resolution, 0,
			      gTrue, gFalse, gFalse, 
			      x, y, w, h);
	}
      }

    } else {
      delete textOut;
      exitCode = 2;
      goto err3;
    }
  }
  delete textOut;

  // write end of HTML file
  if (htmlMeta) {
    if (!textFileName->cmp("-")) {
      f = stdout;
    } else {
      if (!(f = fopen(textFileName->getCString(), "ab"))) {
	error(errIO, -1, "Couldn't open text file '{0:t}'", textFileName);
	exitCode = 2;
	goto err3;
      }
    }
    if (!bbox) fputs("</pre>\n", f);
    fputs("</body>\n", f);
    fputs("</html>\n", f);
    if (f != stdout) {
      fclose(f);
    }
  }

  exitCode = 0;

  // clean up
 err3:
  delete textFileName;
 err2:
  delete doc;
  delete fileName;
  uMap->decRefCnt();
 err1:
  delete globalParams;
 err0:

  // check for memory leaks
  Object::memCheck(stderr);
  gMemReport(stderr);

  return exitCode;
}

static void printInfoString(FILE *f, Dict *infoDict, const char *key,
			    const char *text1, const char *text2, UnicodeMap *uMap) {
  Object obj;
  GooString *s1;
  GBool isUnicode;
  Unicode u;
  char buf[9];
  int i, n;

  if (infoDict->lookup(key, &obj)->isString()) {
    fputs(text1, f);
    s1 = obj.getString();
    if ((s1->getChar(0) & 0xff) == 0xfe &&
	(s1->getChar(1) & 0xff) == 0xff) {
      isUnicode = gTrue;
      i = 2;
    } else {
      isUnicode = gFalse;
      i = 0;
    }
    while (i < obj.getString()->getLength()) {
      if (isUnicode) {
	u = ((s1->getChar(i) & 0xff) << 8) |
	    (s1->getChar(i+1) & 0xff);
	i += 2;
      } else {
	u = pdfDocEncoding[s1->getChar(i) & 0xff];
	++i;
      }
      n = uMap->mapUnicode(u, buf, sizeof(buf));
      buf[n] = '\0';
      const std::string myString = myXmlTokenReplace(buf);
      fputs(myString.c_str(), f);
    }
    fputs(text2, f);
  }
  obj.free();
}

static void printInfoDate(FILE *f, Dict *infoDict, const char *key, const char *fmt) {
  Object obj;
  char *s;

  if (infoDict->lookup(key, &obj)->isString()) {
    s = obj.getString()->getCString();
    if (s[0] == 'D' && s[1] == ':') {
      s += 2;
    }
    fprintf(f, fmt, s);
  }
  obj.free();
}