You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

249 lines
7.2KB

  1. /*
  2. * LRC lyrics file format decoder
  3. * Copyright (c) 2014 StarBrilliant <m13253@hotmail.com>
  4. *
  5. * This file is part of FFmpeg.
  6. *
  7. * FFmpeg is free software; you can redistribute it and/or
  8. * modify it under the terms of the GNU Lesser General Public
  9. * License as published by the Free Software Foundation; either
  10. * version 2.1 of the License, or (at your option) any later version.
  11. *
  12. * FFmpeg 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 GNU
  15. * Lesser General Public License for more details.
  16. *
  17. * You should have received a copy of the GNU Lesser General Public
  18. * License along with FFmpeg; if not, write to the Free Software
  19. * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  20. */
  21. #include <inttypes.h>
  22. #include <stdint.h>
  23. #include <string.h>
  24. #include "avformat.h"
  25. #include "internal.h"
  26. #include "lrc.h"
  27. #include "metadata.h"
  28. #include "subtitles.h"
  29. #include "libavutil/bprint.h"
  30. #include "libavutil/dict.h"
  31. typedef struct LRCContext {
  32. FFDemuxSubtitlesQueue q;
  33. int64_t ts_offset; // offset metadata item
  34. } LRCContext;
  35. static int64_t find_header(const char *p)
  36. {
  37. int64_t offset = 0;
  38. while(p[offset] == ' ' || p[offset] == '\t') {
  39. offset++;
  40. }
  41. if(p[offset] == '[' && p[offset + 1] >= 'a' && p[offset + 1] <= 'z') {
  42. return offset;
  43. } else {
  44. return -1;
  45. }
  46. }
  47. static int64_t count_ts(const char *p)
  48. {
  49. int64_t offset = 0;
  50. int in_brackets = 0;
  51. for(;;) {
  52. if(p[offset] == ' ' || p[offset] == '\t') {
  53. offset++;
  54. } else if(p[offset] == '[') {
  55. offset++;
  56. in_brackets++;
  57. } else if (p[offset] == ']' && in_brackets) {
  58. offset++;
  59. in_brackets--;
  60. } else if(in_brackets &&
  61. (p[offset] == ':' || p[offset] == '.' || p[offset] == '-' ||
  62. (p[offset] >= '0' && p[offset] <= '9'))) {
  63. offset++;
  64. } else {
  65. break;
  66. }
  67. }
  68. return offset;
  69. }
  70. static int64_t read_ts(const char *p, int64_t *start)
  71. {
  72. int64_t offset = 0;
  73. uint64_t mm, ss, cs;
  74. while(p[offset] == ' ' || p[offset] == '\t') {
  75. offset++;
  76. }
  77. if(p[offset] != '[') {
  78. return 0;
  79. }
  80. if(sscanf(p, "[-%"SCNu64":%"SCNu64".%"SCNu64"]", &mm, &ss, &cs) == 3) {
  81. /* Just in case negative pts, players may drop it but we won't. */
  82. *start = -(int64_t) (mm*60000 + ss*1000 + cs*10);
  83. } else if(sscanf(p, "[%"SCNu64":%"SCNu64".%"SCNu64"]", &mm, &ss, &cs) == 3) {
  84. *start = mm*60000 + ss*1000 + cs*10;
  85. } else {
  86. return 0;
  87. }
  88. do {
  89. offset++;
  90. } while(p[offset] && p[offset-1] != ']');
  91. return offset;
  92. }
  93. static int64_t read_line(AVBPrint *buf, AVIOContext *pb)
  94. {
  95. int64_t pos = avio_tell(pb);
  96. av_bprint_clear(buf);
  97. while(!avio_feof(pb)) {
  98. int c = avio_r8(pb);
  99. if(c != '\r') {
  100. av_bprint_chars(buf, c, 1);
  101. }
  102. if(c == '\n') {
  103. break;
  104. }
  105. }
  106. return pos;
  107. }
  108. static int lrc_probe(AVProbeData *p)
  109. {
  110. int64_t offset = 0;
  111. int64_t mm;
  112. uint64_t ss, cs;
  113. const AVMetadataConv *metadata_item;
  114. if(!memcmp(p->buf, "\xef\xbb\xbf", 3)) { // Skip UTF-8 BOM header
  115. offset += 3;
  116. }
  117. while(p->buf[offset] == '\n' || p->buf[offset] == '\r') {
  118. offset++;
  119. }
  120. if(p->buf[offset] != '[') {
  121. return 0;
  122. }
  123. offset++;
  124. // Common metadata item but not exist in ff_lrc_metadata_conv
  125. if(!memcmp(p->buf + offset, "offset:", 7)) {
  126. return 40;
  127. }
  128. if(sscanf(p->buf + offset, "%"SCNd64":%"SCNu64".%"SCNu64"]",
  129. &mm, &ss, &cs) == 3) {
  130. return 50;
  131. }
  132. // Metadata items exist in ff_lrc_metadata_conv
  133. for(metadata_item = ff_lrc_metadata_conv;
  134. metadata_item->native; metadata_item++) {
  135. size_t metadata_item_len = strlen(metadata_item->native);
  136. if(p->buf[offset + metadata_item_len] == ':' &&
  137. !memcmp(p->buf + offset, metadata_item->native, metadata_item_len)) {
  138. return 40;
  139. }
  140. }
  141. return 5; // Give it 5 scores since it starts with a bracket
  142. }
  143. static int lrc_read_header(AVFormatContext *s)
  144. {
  145. LRCContext *lrc = s->priv_data;
  146. AVBPrint line;
  147. AVStream *st;
  148. st = avformat_new_stream(s, NULL);
  149. if(!st) {
  150. return AVERROR(ENOMEM);
  151. }
  152. avpriv_set_pts_info(st, 64, 1, 1000);
  153. lrc->ts_offset = 0;
  154. st->codec->codec_type = AVMEDIA_TYPE_SUBTITLE;
  155. st->codec->codec_id = AV_CODEC_ID_TEXT;
  156. av_bprint_init(&line, 0, AV_BPRINT_SIZE_UNLIMITED);
  157. while(!avio_feof(s->pb)) {
  158. int64_t pos = read_line(&line, s->pb);
  159. int64_t header_offset = find_header(line.str);
  160. if(header_offset >= 0) {
  161. char *comma_offset = strchr(line.str, ':');
  162. if(comma_offset) {
  163. char *right_bracket_offset = strchr(line.str, ']');
  164. if(!right_bracket_offset) {
  165. continue;
  166. }
  167. *right_bracket_offset = *comma_offset = '\0';
  168. if(strcmp(line.str + 1, "offset") ||
  169. sscanf(comma_offset + 1, "%"SCNd64, &lrc->ts_offset) != 1) {
  170. av_dict_set(&s->metadata, line.str + 1, comma_offset + 1, 0);
  171. }
  172. *comma_offset = ':';
  173. *right_bracket_offset = ']';
  174. }
  175. } else {
  176. AVPacket *sub;
  177. int64_t ts_start = AV_NOPTS_VALUE;
  178. int64_t ts_stroffset = 0;
  179. int64_t ts_stroffset_incr = 0;
  180. int64_t ts_strlength = count_ts(line.str);
  181. while((ts_stroffset_incr = read_ts(line.str + ts_stroffset,
  182. &ts_start)) != 0) {
  183. ts_stroffset += ts_stroffset_incr;
  184. sub = ff_subtitles_queue_insert(&lrc->q, line.str + ts_strlength,
  185. line.len - ts_strlength, 0);
  186. if(!sub) {
  187. return AVERROR(ENOMEM);
  188. }
  189. sub->pos = pos;
  190. sub->pts = ts_start - lrc->ts_offset;
  191. sub->duration = -1;
  192. }
  193. }
  194. }
  195. ff_subtitles_queue_finalize(&lrc->q);
  196. ff_metadata_conv_ctx(s, NULL, ff_lrc_metadata_conv);
  197. return 0;
  198. }
  199. static int lrc_read_packet(AVFormatContext *s, AVPacket *pkt)
  200. {
  201. LRCContext *lrc = s->priv_data;
  202. return ff_subtitles_queue_read_packet(&lrc->q, pkt);
  203. }
  204. static int lrc_read_seek(AVFormatContext *s, int stream_index,
  205. int64_t min_ts, int64_t ts, int64_t max_ts, int flags)
  206. {
  207. LRCContext *lrc = s->priv_data;
  208. return ff_subtitles_queue_seek(&lrc->q, s, stream_index,
  209. min_ts, ts, max_ts, flags);
  210. }
  211. static int lrc_read_close(AVFormatContext *s)
  212. {
  213. LRCContext *lrc = s->priv_data;
  214. ff_subtitles_queue_clean(&lrc->q);
  215. return 0;
  216. }
  217. AVInputFormat ff_lrc_demuxer = {
  218. .name = "lrc",
  219. .long_name = NULL_IF_CONFIG_SMALL("LRC lyrics"),
  220. .priv_data_size = sizeof (LRCContext),
  221. .read_probe = lrc_probe,
  222. .read_header = lrc_read_header,
  223. .read_packet = lrc_read_packet,
  224. .read_close = lrc_read_close,
  225. .read_seek2 = lrc_read_seek
  226. };