xapian-applications/omega/handler.h

   1 /** @file
   2  * @brief Extract text and metadata using an external library.
   3  */
   4 /* Copyright (C) 2011,2022,2023 Olly Betts
   5  * Copyright (C) 2019 Bruno Baruffaldi
   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 #ifndef OMEGA_INCLUDED_HANDLER_H
  24 #define OMEGA_INCLUDED_HANDLER_H
  25
  26 #include <cstring>
  27 #include <string>
  28
  29 /** Called exactly once during helper start-up.
  30  *
  31  *  This will be called before any calls to extract().
  32  *
  33  *  Should return true if initialisation succeeds, false (or throw a C++
  34  *  exception) if it fails.
  35  */
  36 bool
  37 initialise();
  38
  39 /** Extract information from the @a filename and store it in the
  40  *  corresponding variable.
  41  *
  42  *  @param filename     Path to the file.
  43  *  @param mimetype     Mimetype of the file.
  44  *
  45  * Note: This function should only be used by an assistant process.
  46  *
  47  * See Worker::extract() for more details.
  48  */
  49 void
  50 extract(const std::string& filename,
  51         const std::string& mimetype);
  52
  53 enum Field {
  54     FIELD_BODY,
  55     FIELD_TITLE,
  56     FIELD_KEYWORDS,
  57     FIELD_AUTHOR,
  58     FIELD_PAGE_COUNT,
  59     FIELD_CREATED_DATE,
  60     FIELD_ATTACHMENT,
  61     FIELD_TO,
  62     FIELD_CC,
  63     FIELD_BCC,
  64     FIELD_MESSAGE_ID,
  65     FIELD_ERROR,
  66     FIELD_END
  67 };
  68
  69 /** Respond with extracted data.
  70  *
  71  *  @param field    FIELD_* code
  72  *  @param data     pointer to field content
  73  *  @param len      length of field content in bytes
  74  */
  75 void
  76 send_field(Field field, const char* data, size_t len);
  77
  78 /** Respond with extracted data.
  79  *
  80  *  @param field    FIELD_* code
  81  *  @param data     pointer to nul-terminated field content
  82  */
  83 inline void
  84 send_field(Field field, const char* data) {
  85     if (data) send_field(field, data, std::strlen(data));
  86 }
  87
  88 /** Respond with extracted data.
  89  *
  90  *  @param field    FIELD_* code
  91  *  @param data     field content as std::string
  92  */
  93 inline void
  94 send_field(Field field, const std::string& s) {
  95     send_field(field, s.data(), s.size());
  96 }
  97
  98 void send_field_page_count(int value);
  99
 100 void send_field_created_date(time_t value);
 101
 102 #endif // OMEGA_INCLUDED_HANDLER_H