X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=modules%2Fcodec%2Fsubtitles%2Fsubsdec.c;h=8a7cf3521e4b706e8468d8b4b0d4e1ae1d8695e9;hb=24cddfa0efa80557f538d6dbf08f9b0b4b4d52a4;hp=688204ad6bf6f50ee4a09e8d8b09ee986e3cd5f5;hpb=bf4a9109b1a6b5f9a4b4f7efe04c0082b8414554;p=vlc diff --git a/modules/codec/subtitles/subsdec.c b/modules/codec/subtitles/subsdec.c index 688204ad6b..8a7cf3521e 100644 --- a/modules/codec/subtitles/subsdec.c +++ b/modules/codec/subtitles/subsdec.c @@ -50,27 +50,112 @@ static char *CreateHtmlSubtitle( int *pi_align, char * ); * Module descriptor. *****************************************************************************/ static const char *const ppsz_encodings[] = { - DEFAULT_NAME, "UTF-8", "", - "ISO-8859-1", "CP1252", "MacRoman", "MacIceland","ISO-8859-15", "", - "ISO-8859-2", "CP1250", "MacCentralEurope", "MacCroatian", "MacRomania", "", - "ISO-8859-5", "CP1251", "MacCyrillic", "MacUkraine", "KOI8-R", "KOI8-U", "KOI8-RU", "", - "ISO-8859-6", "CP1256", "MacArabic", "", - "ISO-8859-7", "CP1253", "MacGreek", "", - "ISO-8859-8", "CP1255", "MacHebrew", "", - "ISO-8859-9", "CP1254", "MacTurkish", "", - "ISO-8859-13", "CP1257", "", - "ISO-2022-JP", "ISO-2022-JP-1", "ISO-2022-JP-2", "EUC-JP", "SHIFT_JIS", "", - "ISO-2022-CN", "ISO-2022-CN-EXT", "EUC-CN", "EUC-TW", "BIG5", "BIG5-HKSCS", "", - "ISO-2022-KR", "EUC-KR", "", - "MacThai", "KOI8-T", "", - "ISO-8859-3", "ISO-8859-4", "ISO-8859-10", "ISO-8859-14", "ISO-8859-16", "", - "CP850", "CP862", "CP866", "CP874", "CP932", "CP949", "CP950", "CP1133", "CP1258", "", - "Macintosh", "", - "UTF-7", "UTF-16", "UTF-16BE", "UTF-16LE", "UTF-32", "UTF-32BE", "UTF-32LE", - "UCS-2", "UCS-2BE", "UCS-2LE", "UCS-4", "UCS-4BE", "UCS-4LE", "", - "GBK", "GB18030", "JOHAB", "ARMSCII-8", - "Georgian-Academy", "Georgian-PS", "TIS-620", "MuleLao-1", "VISCII", "TCVN", - "HPROMAN8", "NEXTSTEP" }; + "", + "UTF-8", + "UTF-16", + "UTF-16BE", + "UTF-16LE", + "GB18030", + "ISO-8859-15", + "Windows-1252", + "ISO-8859-2", + "Windows-1250", + "ISO-8859-3", + "ISO-8859-10", + "Windows-1251", + "KOI8-R", + "KOI8-U", + "ISO-8859-6", + "Windows-1256", + "ISO-8859-7", + "Windows-1256", + "ISO-8859-8", + "Windows-1255", + "ISO-8859-9", + "Windows-1254", + "ISO-8859-11", + "Windows-874", + "ISO-8859-13", + "Windows-1257", + "ISO-8859-14", + "ISO-8859-16", + "ISO-2022-CN-EXT", + "EUC-CN", + "ISO-2022-JP-2", + "EUC-JP", + "Shift_JIS", + "ISO-2022-KR", + "EUC-KR", + "Big5", + "ISO-2022-TW", + "Big5-HKSCS", + "VISCII", + "Windows-1258", +}; + +static const char *const ppsz_encoding_names[] = { + N_("Auto"), + N_("Universal (UTF-8)"), + N_("Universal (UTF-16)"), + N_("Universal (big endian UTF-16)"), + N_("Universal (little endian UTF-16)"), + N_("Universal, Chinese (GB18030)"), + + /* ISO 8859 and the likes */ + /* 1 */ + N_("Western European (Latin-9)"), /* mostly superset of Latin-1 */ + N_("Western European (Windows-1252)"), + /* 2 */ + N_("Eastern European (Latin-2)"), + N_("Eastern European (Windows-1250)"), + /* 3 */ + N_("Esperanto (Latin-3)"), + /* 4 */ + N_("Nordic (Latin-6)"), /* Latin 6 supersedes Latin 4 */ + /* 5 */ + N_("Cyrillic (Windows-1251)"), /* ISO 8859-5 is not practically used */ + N_("Russian (KOI8-R)"), + N_("Ukrainian (KOI8-U)"), + /* 6 */ + N_("Arabic (ISO 8859-6)"), + N_("Arabic (Windows-1256)"), + /* 7 */ + N_("Greek (ISO 8859-7)"), + N_("Greek (Windows-1256)"), + /* 8 */ + N_("Hebrew (ISO 8859-8)"), + N_("Hebrew (Windows-1255)"), + /* 9 */ + N_("Turkish (ISO 8859-9)"), + N_("Turkish (Windows-1254)"), + /* 10 -> 4 */ + /* 11 */ + N_("Thai (TIS 620-2533/ISO 8859-11)"), + N_("Thai (Windows-874)"), + /* 13 */ + N_("Baltic (Latin-7)"), + N_("Baltic (Windows-1257)"), + /* 12 -> /dev/null */ + /* 14 */ + N_("Celtic (Latin-8)"), + /* 15 -> 1 */ + /* 16 */ + N_("South-Eastern European (Latin-10)"), + /* CJK families */ + N_("Simplified Chinese (ISO-2022-CN-EXT)"), + N_("Simplified Chinese Unix (EUC-CN)"), + N_("Japanese (7-bits JIS/ISO-2022-JP-2)"), + N_("Japanese Unix (EUC-JP)"), + N_("Japanese (Shift JIS)"), + N_("Korean (ISO-2022-KR)"), + N_("Korean Unix (EUC-KR)"), + N_("Traditional Chinese (Big5)"), + N_("Traditional Chinese Unix (EUC-TW)"), + N_("Hong-Kong Supplementary (HKSCS)"), + /* Other */ + N_("Vietnamese (VISCII)"), + N_("Vietnamese (Windows-1258)"), +}; /* SSA supports charset selection. The following known charsets are used: @@ -124,9 +209,9 @@ vlc_module_begin () add_integer( "subsdec-align", 0, NULL, ALIGN_TEXT, ALIGN_LONGTEXT, false ) change_integer_list( pi_justification, ppsz_justification_text, NULL ) - add_string( "subsdec-encoding", DEFAULT_NAME, NULL, + add_string( "subsdec-encoding", "", NULL, ENCODING_TEXT, ENCODING_LONGTEXT, false ) - change_string_list( ppsz_encodings, 0, 0 ) + change_string_list( ppsz_encodings, ppsz_encoding_names, 0 ) add_bool( "subsdec-autodetect-utf8", true, NULL, AUTODETECT_UTF8_TEXT, AUTODETECT_UTF8_LONGTEXT, false ) add_bool( "subsdec-formatted", true, NULL, FORMAT_TEXT, FORMAT_LONGTEXT, @@ -147,9 +232,9 @@ static int OpenDecoder( vlc_object_t *p_this ) switch( p_dec->fmt_in.i_codec ) { - case VLC_FOURCC('s','u','b','t'): - case VLC_FOURCC('s','s','a',' '): - case VLC_FOURCC('t','1','4','0'): + case VLC_CODEC_SUBT: + case VLC_CODEC_SSA: + case VLC_CODEC_ITU_T140: break; default: return VLC_EGENERIC; @@ -177,7 +262,7 @@ static int OpenDecoder( vlc_object_t *p_this ) char *psz_charset = NULL; /* First try demux-specified encoding */ - if( p_dec->fmt_in.i_codec == VLC_FOURCC('t','1','4','0') ) + if( p_dec->fmt_in.i_codec == VLC_CODEC_ITU_T140 ) psz_charset = strdup( "UTF-8" ); /* IUT T.140 is always using UTF-8 */ else if( p_dec->fmt_in.subs.psz_encoding && *p_dec->fmt_in.subs.psz_encoding ) @@ -191,12 +276,6 @@ static int OpenDecoder( vlc_object_t *p_this ) if (psz_charset == NULL) { psz_charset = var_CreateGetNonEmptyString (p_dec, "subsdec-encoding"); - if ((psz_charset != NULL) && !strcasecmp (psz_charset, DEFAULT_NAME)) - { - free (psz_charset); - psz_charset = NULL; - } - msg_Dbg (p_dec, "trying configured character encoding: %s", psz_charset ?: "not specified"); } @@ -236,7 +315,7 @@ static int OpenDecoder( vlc_object_t *p_this ) var_Get( p_dec, "subsdec-align", &val ); p_sys->i_align = val.i_int; - if( p_dec->fmt_in.i_codec == VLC_FOURCC('s','s','a',' ') + if( p_dec->fmt_in.i_codec == VLC_CODEC_SSA && var_CreateGetBool( p_dec, "subsdec-formatted" ) ) { if( p_dec->fmt_in.i_extra > 0 ) @@ -413,7 +492,7 @@ static subpicture_t *ParseText( decoder_t *p_dec, block_t *p_block ) /* Create a new subpicture region */ memset( &fmt, 0, sizeof(video_format_t) ); - fmt.i_chroma = VLC_FOURCC('T','E','X','T'); + fmt.i_chroma = VLC_CODEC_TEXT; fmt.i_aspect = 0; fmt.i_width = fmt.i_height = 0; fmt.i_x_offset = fmt.i_y_offset = 0; @@ -427,7 +506,7 @@ static subpicture_t *ParseText( decoder_t *p_dec, block_t *p_block ) } /* Decode and format the subpicture unit */ - if( p_dec->fmt_in.i_codec != VLC_FOURCC('s','s','a',' ') ) + if( p_dec->fmt_in.i_codec != VLC_CODEC_SSA ) { /* Normal text subs, easy markup */ p_spu->p_region->i_align = SUBPICTURE_ALIGN_BOTTOM | p_sys->i_align;