libextractor

test_pdf.c (6412B)

---

 /*
      This file is part of libextractor.
      Copyright (C) 2026 Vidyut Samanta and Christian Grothoff
 
      libextractor is free software; you can redistribute it and/or modify
      it under the terms of the GNU General Public License as published
      by the Free Software Foundation; either version 3, or (at your
      option) any later version.
 
      libextractor is distributed in the hope that it will be useful, but
      WITHOUT ANY WARRANTY; without even the implied warranty of
      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
      General Public License for more details.
 
      You should have received a copy of the GNU General Public License
      along with libextractor; see the file COPYING.  If not, write to the
      Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
      Boston, MA 02110-1301, USA.
 */
 /**
  * @file plugins/test_pdf.c
  * @brief testcase for pdf plugin
  * @author Christian Grothoff
  */
 #include "platform.h"
 #include "test_lib.h"
 #include "test_paged_fulltext.h"
 
 
 /**
  * Check the full text of testdata/pdf_fulltext.pdf.
  *
  * @param data the full text
  * @param data_len number of bytes in @a data
  * @return 1 if acceptable
  */
 static int
 validate_pdf_fulltext (const void *data,
                        size_t data_len)
 {
   static const char *const pars[] = {
     "Introduction",
     "Paged documents scatter their words",
     "The second paragraph is indented",
     "Short paragraph number three.",
     "The fourth paragraph",
     "The fifth paragraph runs across the page break",
     "The sixth paragraph",
     "The seventh paragraph opens the two column part",
     "The eighth paragraph continues in the left column",
     "The ninth paragraph",
     "The tenth paragraph is the first one of the right column",
     "The eleventh paragraph concludes the document with a final remark.",
     NULL
   };
   static const char *const needles[] = {
     "The caf\xc3\xa9 serves na\xc3\xafve guests.",
     "the line numbers printed in the margins next to each column must be "
     "dropped by the extractor because they are not part of the text at all.",
     "apples, pears and plums that grow in an orchard near the river.",
     "that guide ships safely through the night along rocky coasts.",
     NULL
   };
   static const char *const absent[] = {
     NULL
   };
   const char *s = data;
 
   if (0 == check_form (s, data_len))
   {
     fprintf (stderr, "Malformed full text\n");
     return 0;
   }
   return check_paragraphs (s, pars) &&
          check_contains (s, common_needles, common_absent) &&
          check_contains (s, needles, absent) &&
          check_no_numbers (s);
 }
 
 
 /**
  * Main function for the PDF testcase.
  *
  * @param argc number of arguments (ignored)
  * @param argv arguments (ignored)
  * @return 0 on success
  */
 int
 main (int argc, char *argv[])
 {
   struct SolutionData pdf_extract_sol[] = {
     {
       EXTRACTOR_METATYPE_MIMETYPE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "application/pdf",
       strlen ("application/pdf") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_TITLE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "GNU libextractor PDF Test",
       strlen ("GNU libextractor PDF Test") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_SUBJECT,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "Metadata extraction",
       strlen ("Metadata extraction") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_KEYWORDS,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "PDF, libextractor, test",
       strlen ("PDF, libextractor, test") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_AUTHOR_NAME,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "Vidyut Samanta",
       strlen ("Vidyut Samanta") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_CREATED_BY_SOFTWARE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "WritePDF",
       strlen ("WritePDF") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_PRODUCED_BY_SOFTWARE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "libextractor testsuite",
       strlen ("libextractor testsuite") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_FORMAT,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "PDF 1.4",
       strlen ("PDF 1.4") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_PAGE_COUNT,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "1",
       strlen ("1") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_CREATION_DATE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "2020-01-15 12:30:00",
       strlen ("2020-01-15 12:30:00") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_MODIFICATION_DATE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "2020-01-16 08:00:00",
       strlen ("2020-01-16 08:00:00") + 1,
       0
     },
     { 0, 0, NULL, NULL, 0, -1 }
   };
   struct SolutionData pdf_fulltext_sol[] = {
     {
       EXTRACTOR_METATYPE_MIMETYPE,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "application/pdf",
       strlen ("application/pdf") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_PAGE_COUNT,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "3",
       strlen ("3") + 1,
       0
     },
     {
       EXTRACTOR_METATYPE_FULL_TEXT,
       EXTRACTOR_METAFORMAT_UTF8,
       "text/plain",
       "^Introduction\n\nPaged documents scatter",
       0,
       0,
       1,
       &validate_pdf_fulltext
     },
     { 0, 0, NULL, NULL, 0, -1 }
   };
   struct ProblemSet ps[] = {
     { "testdata/pdf_extract.pdf",
       pdf_extract_sol },
     { NULL, NULL }
   };
   struct ProblemSet ps_ft[] = {
     { "testdata/pdf_extract.pdf",
       pdf_extract_sol },
     { "testdata/pdf_fulltext.pdf",
       pdf_fulltext_sol },
     { NULL, NULL }
   };
   int ret = 0;
 
   ret |= ET_main ("pdf", ps);
   /* without the option, there must be no full text */
   ret |= check_fulltext_count ("pdf",
                                "testdata/pdf_fulltext.pdf",
                                0);
   ret |= ET_main ("pdf(fulltext)", ps_ft);
   /* a document without text has no full text either */
   ret |= check_fulltext_count ("pdf(fulltext)",
                                "testdata/pdf_extract.pdf",
                                0);
   ret |= check_fulltext_count ("pdf(fulltext)",
                                "testdata/pdf_fulltext.pdf",
                                1);
   return ret;
 }
 
 
 /* end of test_pdf.c */