Srt.cpp

// Author: Torarin Hals Bakke (2012)

// Boost Software License - Version 1.0 - August 17th, 2003

// Permission is hereby granted, free of charge, to any person or organization
// obtaining a copy of the software and accompanying documentation covered by
// this license (the "Software") to use, reproduce, display, distribute,
// execute, and transmit the Software, and to prepare derivative works of the
// Software, and to permit third-parties to whom the Software is furnished to
// do so, all subject to the following:

// The copyright notices in the Software and this entire statement, including
// the above license grant, this restriction and the following disclaimer,
// must be included in all copies of the Software, in whole or in part, and
// all derivative works of the Software, unless such copies or derivative
// works are solely in the form of machine-executable object code generated by
// a source language processor.

// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
// SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
// FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
// ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
// DEALINGS IN THE SOFTWARE.

#include "Srt.h"
#include "Subtitle.h"
#include "utils/utf8.h"

#include <iostream>
#include <istream>
#include <fstream>

static int timecode_to_milliseconds(unsigned h, unsigned m, unsigned s, unsigned f)
{
  return (h * 3600000) + (m * 60000) + (s * 1000) + f;
}

bool ReadSrt(const std::string& filename, std::vector<Subtitle>& subtitles) {
  std::ifstream srt(filename);
  if (!srt) return false;

  srt.seekg( 0, std::ios::end );
  int estimated_lines = srt.tellg() / 75;
  srt.seekg( 0, std::ios::beg );

  subtitles.reserve(estimated_lines);

  std::string text_lines;
  text_lines.reserve(128);
  unsigned h, m, s, f, h2, m2, s2, f2;

  std::string line;
  line.reserve(128);

  while(std::getline(srt, line)) {
    if (sscanf(line.c_str(), "%2u:%2u:%2u,%3u --> %2u:%2u:%2u,%3u",
               &h, &m, &s, &f, &h2, &m2, &s2, &f2)
        != 8)
    {
      continue;
    }

    int start = timecode_to_milliseconds(h, m, s, f);
    int stop = timecode_to_milliseconds(h2, m2, s2 ,f2);

    if(!subtitles.empty() && subtitles.back().stop > stop)
      continue;

    text_lines.clear();
    while(std::getline(srt, line)) {
      if(line.back() == '\r')
        line.pop_back();

      if(line.empty()) break;

      text_lines.append(line);
      text_lines.append("\n");
    }

    if(text_lines.empty()) continue;

    text_lines.pop_back(); // remove trailing new line
    text_lines.shrink_to_fit();

    // validate utf8
    checkAndRescueUtf8Strings(text_lines);

    subtitles.emplace_back(start, stop, text_lines);
  }

  subtitles.shrink_to_fit();

  return true;
}