xapian-applications/omega/assistant.cc

   1 /** @file
   2  * @brief Worker module for putting text extraction into a separate process.
   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 #include <config.h>
  24
  25 #include "worker_comms.h"
  26 #include "handler.h"
  27 #include "safeunistd.h"
  28
  29 #include <cerrno>
  30 #include <csignal>
  31 #include <iostream>
  32
  33 #include "safesysexits.h"
  34
  35 using namespace std;
  36
  37 const int FD = 3;
  38 const int time_limit = 300;
  39
  40 #if defined HAVE_ALARM
  41
  42 static void
  43 timeout_handler(int) {
  44     _Exit(EX_TEMPFAIL);
  45 }
  46
  47 static void
  48 set_timeout() {
  49     // Causes the system to generate a SIGALRM signal for the process after
  50     // time_limit of seconds
  51     alarm(time_limit);
  52     // Set a signal handler for SIGALRM
  53     signal(SIGALRM, timeout_handler);
  54 }
  55
  56 static void
  57 stop_timeout() {
  58     // Set SIGALRM to be ignore
  59     signal(SIGALRM, SIG_IGN);
  60     // A pending alarm request, if any, is cancelled by calling alarm(0)
  61     alarm(0);
  62 }
  63
  64 #else
  65
  66 static void set_timeout() { }
  67 static void stop_timeout() { }
  68
  69 #endif
  70
  71 static FILE* sockt;
  72
  73 void
  74 send_field(Field field,
  75            const char* data,
  76            size_t len)
  77 {
  78     if (len == 0) return;
  79     putc(static_cast<unsigned char>(field), sockt);
  80     if (!write_string(sockt, data, len)) {
  81         _Exit(OMEGA_EX_SOCKET_WRITE_ERROR);
  82     }
  83 }
  84
  85 static void
  86 send_field_end()
  87 {
  88     putc(static_cast<unsigned char>(FIELD_END), sockt);
  89 }
  90
  91 void
  92 send_field_page_count(int value)
  93 {
  94     if (value < 0) return;
  95     putc(static_cast<unsigned char>(FIELD_PAGE_COUNT), sockt);
  96     if (!write_unsigned(sockt, unsigned(value))) {
  97         _Exit(OMEGA_EX_SOCKET_WRITE_ERROR);
  98     }
  99 }
 100
 101 void
 102 send_field_created_date(time_t value)
 103 {
 104     if (value == time_t(-1)) return;
 105     putc(static_cast<unsigned char>(FIELD_CREATED_DATE), sockt);
 106     auto u_value = static_cast<unsigned long>(value);
 107     if (!write_unsigned(sockt, u_value)) {
 108         _Exit(OMEGA_EX_SOCKET_WRITE_ERROR);
 109     }
 110 }
 111
 112 // FIXME: Restart filter every N files processed?
 113
 114 int main()
 115 {
 116     string filename, mimetype;
 117     sockt = fdopen(FD, "r+");
 118
 119     try {
 120         if (!initialise())
 121             _Exit(EX_UNAVAILABLE);
 122     } catch (const std::exception& e) {
 123         cerr << "Initialisation failed with exception: " << e.what() << '\n';
 124         _Exit(EX_UNAVAILABLE);
 125     } catch (...) {
 126         _Exit(EX_UNAVAILABLE);
 127     }
 128
 129     while (true) {
 130         // Read filename.
 131         errno = 0;
 132         if (!read_string(sockt, filename)) break;
 133         if (!read_string(sockt, mimetype)) break;
 134         // Setting a timeout for avoid infinity loops
 135         set_timeout();
 136         try {
 137             extract(filename, mimetype);
 138         } catch (...) {
 139             send_field(FIELD_ERROR, "Caught C++ exception");
 140         }
 141         stop_timeout();
 142         send_field_end();
 143     }
 144
 145     _Exit(errno ? OMEGA_EX_SOCKET_READ_ERROR : EX_OK);
 146 }