xapian-applications/omega/handler_poppler.cc

   1 /** @file
   2  * @brief Extract text and metadata using poppler.
   3  */
   4 /* Copyright (C) 2019 Bruno Baruffaldi
   5  * Copyright (C) 2022,2023 Olly Betts
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  20  * USA
  21  */
  22
  23 #include <config.h>
  24 #include "handler.h"
  25 #include "str.h"
  26
  27 #include <poppler/glib/poppler-document.h>
  28 #include <poppler/glib/poppler-page.h>
  29
  30 using namespace std;
  31
  32 static gchar*
  33 convert_to_uri(const string& filename, GError** e)
  34 {
  35 #if GLIB_CHECK_VERSION(2,58,0)
  36     gchar* abs_filename = g_canonicalize_filename(filename.c_str(), NULL);
  37 #else
  38     gchar* abs_filename;
  39     if (g_path_is_absolute(filename.c_str())) {
  40         abs_filename = g_strdup(filename.c_str());
  41     } else {
  42         gchar* cwd = g_get_current_dir();
  43         abs_filename = g_build_filename(cwd, filename.c_str(), NULL);
  44         g_free(cwd);
  45     }
  46 #endif
  47     gchar* uri = g_filename_to_uri(abs_filename, NULL, e);
  48     g_free(abs_filename);
  49     return uri;
  50 }
  51
  52 static void
  53 send_glib_field(Field field, gchar* data)
  54 {
  55     if (data) {
  56         send_field(field, data);
  57         g_free(data);
  58     }
  59 }
  60
  61 bool
  62 initialise()
  63 {
  64     return true;
  65 }
  66
  67 void
  68 extract(const string& filename, const string&)
  69 {
  70     GError* e = nullptr;
  71     gchar* uri = convert_to_uri(filename, &e);
  72     if (!uri) {
  73         send_field(FIELD_ERROR, "g_filename_to_uri() failed: ");
  74         send_field(FIELD_ERROR, e->message);
  75         g_error_free(e);
  76         return;
  77     }
  78
  79     PopplerDocument* doc = poppler_document_new_from_file(uri, NULL, &e);
  80     g_free(uri);
  81     if (!doc) {
  82         send_field(FIELD_ERROR, "poppler_document_new_from_file() failed: ");
  83         send_field(FIELD_ERROR, e->message);
  84         g_error_free(e);
  85         return;
  86     }
  87
  88     int pages = poppler_document_get_n_pages(doc);
  89     send_field_page_count(pages);
  90     // Extracting text from PDF file
  91     for (int i = 0; i < pages; ++i) {
  92         PopplerPage* page = poppler_document_get_page(doc, i);
  93         if (!page) {
  94             g_object_unref(doc);
  95             send_field(FIELD_ERROR, "Failed to get page " + str(i));
  96             return;
  97         }
  98         send_field(FIELD_BODY, poppler_page_get_text(page));
  99         g_object_unref(page);
 100     }
 101
 102     // Extract PDF metadata.
 103     send_glib_field(FIELD_AUTHOR, poppler_document_get_author(doc));
 104     send_glib_field(FIELD_TITLE, poppler_document_get_title(doc));
 105     send_glib_field(FIELD_KEYWORDS, poppler_document_get_keywords(doc));
 106     send_field_created_date(poppler_document_get_creation_date(doc));
 107
 108     g_object_unref(doc);
 109 }