2 Copyright (C) 2014-2015 Carl Hetherington <cth@carlh.net>
4 This program is free software; you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 2 of the License, or
7 (at your option) any later version.
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program; if not, write to the Free Software
16 Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
20 /** @file src/subrip_reader.cc
21 * @brief SubripReader class.
24 #include "subrip_reader.h"
25 #include "exceptions.h"
27 #include <boost/algorithm/string.hpp>
28 #include <boost/lexical_cast.hpp>
29 #include <boost/regex.hpp>
30 #include <boost/bind.hpp>
40 using std::stringstream;
41 using boost::lexical_cast;
42 using boost::to_upper;
43 using boost::optional;
44 using boost::function;
47 /** @param s Subtitle string encoded in UTF-8 */
48 SubripReader::SubripReader (string const & s)
51 this->read (boost::bind (&get_line_stringstream, &str));
54 /** @param f Subtitle file encoded in UTF-8 */
55 SubripReader::SubripReader (FILE* f)
57 this->read (boost::bind (&get_line_file, f));
61 SubripReader::read (function<optional<string> ()> get_line)
71 rs.font_size.set_points (48);
72 rs.vertical_position.line = 0;
74 rs.vertical_position.lines = 32;
75 rs.vertical_position.reference = TOP_OF_SUBTITLE;
78 optional<string> line = get_line ();
83 trim_right_if (*line, boost::is_any_of ("\n\r"));
84 remove_unicode_bom (line);
90 /* a blank line at the start is ok */
96 /* Reset stuff that should not persist across separate subtitles */
100 rs.vertical_position.line = 0;
107 /* Further trim this line, removing spaces from the end */
108 trim_right_if (*line, boost::is_any_of (" "));
110 boost::algorithm::split (p, *line, boost::algorithm::is_any_of (" "));
111 if (p.size() != 3 && p.size() != 7) {
112 throw SubripError (*line, "a time/position line");
115 rs.from = convert_time (p[0]);
116 rs.to = convert_time (p[2]);
118 /* XXX: should not ignore coordinate specifications */
124 if (line->empty ()) {
127 convert_line (*line, rs);
128 rs.vertical_position.line = rs.vertical_position.line.get() + 1;
136 SubripReader::convert_time (string t)
139 boost::algorithm::split (a, t, boost::is_any_of (":"));
141 throw SubripError (t, "time in the format h:m:s,ms");
145 boost::algorithm::split (b, a[2], boost::is_any_of (","));
147 return Time::from_hms (
148 lexical_cast<int> (a[0]),
149 lexical_cast<int> (a[1]),
150 lexical_cast<int> (b[0]),
151 lexical_cast<int> (b[1])
156 SubripReader::convert_line (string t, RawSubtitle& p)
165 list<Colour> colours;
166 colours.push_back (Colour (1, 1, 1));
168 /* XXX: missing <font> support */
169 /* XXX: nesting of tags e.g. <b>foo<i>bar<b>baz</b>fred</i>jim</b> might
173 for (size_t i = 0; i < t.size(); ++i) {
176 if (t[i] == '<' || t[i] == '{') {
183 if (t[i] == '>' || t[i] == '}') {
187 } else if (tag == "/b") {
190 } else if (tag == "i") {
193 } else if (tag == "/i") {
196 } else if (tag == "u") {
199 } else if (tag == "/u") {
202 } else if (boost::starts_with (tag, "font")) {
204 boost::regex re (".*color=\"#([0123456789abcdef]+)\"");
206 if (boost::regex_search (tag, match, re) && string (match[1]).size() == 6) {
207 p.colour = Colour::from_rgb_hex (match[1]);
208 colours.push_back (p.colour);
210 } else if (tag == "/font") {
213 p.colour = colours.back ();
227 /* Push p into _subs if it has some text, and clear the text out of p */
229 SubripReader::maybe_content (RawSubtitle& p)
231 if (!p.text.empty ()) {