share/subtitle/export/subrip.lua

   1 -- libquvi-scripts
   2 -- Copyright (C) 2013  Toni Gundogdu <legatvs@gmail.com>
   3 --
   4 -- This file is part of libquvi-scripts <http://quvi.sourceforge.net/>.
   5 --
   6 -- This program is free software: you can redistribute it and/or
   7 -- modify it under the terms of the GNU Affero General Public
   8 -- License as published by the Free Software Foundation, either
   9 -- version 3 of the License, or (at your option) any later version.
  10 --
  11 -- This program is distributed in the hope that it will be useful,
  12 -- but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 -- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 -- GNU Affero General Public License for more details.
  15 --
  16 -- You should have received a copy of the GNU Affero General
  17 -- Public License along with this program.  If not, see
  18 -- <http://www.gnu.org/licenses/>.
  19 --
  20
  21 --[[
  22 Notes
  23   * http://en.wikipedia.org/wiki/SubRip#SubRip_text_file_format
  24   * Uses comma (,) for a decimal separator
  25   * Uses CRLF, with LF line terminators
  26 ]]--
  27
  28 local SubRip = {format='subrip'} -- Utility functions unique to this script
  29
  30 -- Identify the script.
  31 function ident(qargs)
  32   return {
  33     can_export_data = (qargs.to_format == SubRip.format),
  34     export_format = SubRip.format
  35   }
  36 end
  37
  38 -- Export data.
  39 function export(qargs)
  40   local C = require 'quvi/const'
  41   if qargs.from_format == C.sif_tt then
  42     return SubRip.from_tt(qargs)
  43   else
  44     error(string.format('unsupported subtitle format: 0x%x',
  45             qargs.from_format))
  46   end
  47 end
  48
  49 --
  50 -- Utility functions
  51 --
  52
  53 -- timed-text (tt) - YouTube uses this for both CCs and TTSes.
  54 function SubRip.from_tt(qargs)
  55
  56   local f = '%d\r\n%02d:%02d:%06.3f --> %02d:%02d:%06.3f\r\n%s\r\n\r\n'
  57   local E = require 'quvi/entity'
  58   local U = require 'quvi/util'
  59   local L = require 'lxp.lom'
  60
  61   local x = quvi.fetch(qargs.input_url)
  62   local t = L.parse(x)
  63   local r = {}
  64
  65   local last_start = 0
  66
  67   --
  68   -- NOTE: Building up a large string by concatenation will create a lot
  69   --       temporary strings burdening the Lua garbage collector. The
  70   --       Lua way is to put the strings into a table.
  71   --
  72
  73   for i=1, #t do
  74     if t[i].tag == 'text' then
  75       local start = tonumber(t[i].attr['start'] or 0)
  76       local dur = tonumber(t[i].attr['dur'] or (start-last_start))
  77       local end_sec = tonumber(start) + dur
  78
  79       local text = U.trim( E.convert_html(t[i][1]) )
  80
  81       local start_tc = SubRip.to_timecode(start)
  82       local end_tc = SubRip.to_timecode(end_sec)
  83
  84       local s = string.format(f, i, start_tc.hh, start_tc.mm, start_tc.ss,
  85                               end_tc.hh, end_tc.mm, end_tc.ss, text)
  86
  87       -- Use comma for a decimal separator.
  88       table.insert(r, (s:gsub('(%d+)%.(%d+)', '%1,%2')))
  89       last_start = start
  90     end
  91   end
  92   qargs.data = table.concat(r, '')
  93   return qargs
  94 end
  95
  96 function SubRip.to_timecode(s)
  97   return {hh=(s/3600)%60, mm=(s/60)%60, ss=s%60}
  98 end
  99
 100 -- vim: set ts=2 sw=2 tw=72 expandtab: