commit 949dae1583254b789e3dafe569e030140a621846
parent 73b50507dba0570f2182f21f8b1c27a95886e4e7
Author: Christian Grothoff <christian@grothoff.org>
Date: Sun, 20 Dec 2009 00:06:45 +0000
id3vx
Diffstat:
10 files changed, 609 insertions(+), 209 deletions(-)
diff --git a/TODO b/TODO
@@ -17,12 +17,12 @@ Core:
Incomplete code (missing features):
* RIFF (idx1 attribute)
-* IDv2{3,4} (some attributes, make testcases in test/id3v2/ work)
* StarOffice sdw (some attributes, see doc/)
* man pages (interpret sections for authors, brief description)
* pdf: full-text extraction!
* EXIV2
* ELF: 64-bit support, lists of architectures, OSes, etc. are incomplete
+* ID3v2x: unsynchronization support, (de)compression support, footer support (24)
Desirable missing formats:
* mbox / various e-mail formats
diff --git a/src/include/extractor.h b/src/include/extractor.h
@@ -280,8 +280,8 @@ enum EXTRACTOR_MetaType
EXTRACTOR_METATYPE_PRODUCT_VERSION = 148,
EXTRACTOR_METATYPE_CONTRIBUTOR_NAME = 149,
EXTRACTOR_METATYPE_MOVIE_DIRECTOR = 150,
- EXTRACTOR_METATYPE_TV_NETWORK_NAME = 151,
- EXTRACTOR_METATYPE_TV_SHOW_NAME = 152,
+ EXTRACTOR_METATYPE_NETWORK_NAME = 151,
+ EXTRACTOR_METATYPE_SHOW_NAME = 152,
EXTRACTOR_METATYPE_CHAPTER_NAME = 153,
EXTRACTOR_METATYPE_SONG_COUNT = 154,
EXTRACTOR_METATYPE_STARTING_SONG = 155,
@@ -295,13 +295,17 @@ enum EXTRACTOR_MetaType
EXTRACTOR_METATYPE_ORIGINAL_ARTIST = 163,
EXTRACTOR_METATYPE_ORIGINAL_WRITER = 164,
EXTRACTOR_METATYPE_ORIGINAL_RELEASE_YEAR = 165,
- EXTRACTOR_METATYPE_LYRICS = 166,
- EXTRACTOR_METATYPE_POPULARITY_METER = 167,
+ EXTRACTOR_METATYPE_ORIGINAL_PERFORMER = 166,
+ EXTRACTOR_METATYPE_LYRICS = 167,
+ EXTRACTOR_METATYPE_POPULARITY_METER = 168,
+ EXTRACTOR_METATYPE_LICENSEE = 169,
+ EXTRACTOR_METATYPE_MUSICIAN_CREDITS_LIST = 170,
+ EXTRACTOR_METATYPE_MOOD = 171,
+ EXTRACTOR_METATYPE_SUBTITLE = 172,
/* fixme: used up to here! */
EXTRACTOR_METATYPE_MUSIC_CD_IDENTIFIER = 117,
- EXTRACTOR_METATYPE_MUSICIAN_CREDITS_LIST = 123,
EXTRACTOR_METATYPE_SCALE = 108,
@@ -342,7 +346,6 @@ enum EXTRACTOR_MetaType
EXTRACTOR_METATYPE_FULL_NAME = 113,
EXTRACTOR_METATYPE_LINK = 116,
EXTRACTOR_METATYPE_TIME = 122,
- EXTRACTOR_METATYPE_MOOD = 124,
EXTRACTOR_METATYPE_TELEVISION_SYSTEM = 126,
EXTRACTOR_METATYPE_HARDWARE_DEPENDENCY = 129,
EXTRACTOR_METATYPE_RIPPER = 130,
diff --git a/src/main/extractor_metatypes.c b/src/main/extractor_metatypes.c
@@ -369,10 +369,10 @@ static const struct MetaTypeDescription meta_type_descriptions[] = {
/* 150 */
{ gettext_noop ("movie director"),
gettext_noop ("name of the director") },
- { gettext_noop ("TV network"),
- gettext_noop ("name of the broadcasting TV network") },
- { gettext_noop ("TV show"),
- gettext_noop ("name of the TV show") },
+ { gettext_noop ("network"),
+ gettext_noop ("name of the broadcasting network or station") },
+ { gettext_noop ("show"),
+ gettext_noop ("name of the show") },
{ gettext_noop ("chapter name"),
gettext_noop ("name of the chapter") },
{ gettext_noop ("song count"),
@@ -402,10 +402,23 @@ static const struct MetaTypeDescription meta_type_descriptions[] = {
/* 165 */
{ gettext_noop ("original release year"),
gettext_noop ("year of the original release") },
+ { gettext_noop ("original performer"),
+ gettext_noop ("name of the original performer") },
{ gettext_noop ("lyrics"),
gettext_noop ("lyrics of the song or text description of vocal activities") },
{ gettext_noop ("popularity"),
gettext_noop ("information about the file's popularity") },
+ { gettext_noop ("licensee"),
+ gettext_noop ("name of the owner or licensee of the file") },
+ /* 170 */
+ { gettext_noop ("musician credit list"),
+ gettext_noop ("names of contributing musicians") },
+ { gettext_noop ("mood"),
+ gettext_noop ("keywords reflecting the mood of the piece") },
+ { gettext_noop ("subtitle"),
+ gettext_noop ("subtitle of this part") },
+ { gettext_noop (""),
+ gettext_noop ("") },
{ gettext_noop (""),
gettext_noop ("") },
#if 0
diff --git a/src/plugins/id3v23_extractor.c b/src/plugins/id3v23_extractor.c
@@ -1,6 +1,6 @@
/*
This file is part of libextractor.
- (C) 2002, 2003, 2004, 2006, 2007 Vidyut Samanta and Christian Grothoff
+ (C) 2002, 2003, 2004, 2006, 2007, 2009 Vidyut Samanta and Christian Grothoff
libextractor is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published
@@ -35,54 +35,83 @@
#include "convert.h"
+enum Id3v23Fmt
+ {
+ T, /* simple, 0-terminated string, prefixed by encoding */
+ U, /* 0-terminated ASCII string, no encoding */
+ UL, /* unsync'ed lyrics */
+ SL, /* sync'ed lyrics */
+ L, /* string with language prefix */
+ I /* image */
+ };
+
typedef struct
{
const char *text;
enum EXTRACTOR_MetaType type;
+ enum Id3v23Fmt fmt;
} Matches;
static Matches tmap[] = {
- {"COMM", EXTRACTOR_METATYPE_COMMENT},
- {"IPLS", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"LINK", EXTRACTOR_METATYPE_LINK},
- {"MCDI", EXTRACTOR_METATYPE_MUSIC_CD_IDENTIFIER},
- {"PCNT", EXTRACTOR_METATYPE_PLAY_COUNTER},
- {"POPM", EXTRACTOR_METATYPE_POPULARITY_METER},
- {"TCOP", EXTRACTOR_METATYPE_COPYRIGHT},
- {"TDAT", EXTRACTOR_METATYPE_DATE},
- {"TCON", EXTRACTOR_METATYPE_CONTENT_TYPE},
- {"TIT1", EXTRACTOR_METATYPE_GENRE},
- {"TENC", EXTRACTOR_METATYPE_ENCODED_BY},
- {"TEXT", EXTRACTOR_METATYPE_LYRICS},
- {"TOLY", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TOPE", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TOWN", EXTRACTOR_METATYPE_OWNER},
- {"TPE1", EXTRACTOR_METATYPE_ARTIST},
- {"TPE2", EXTRACTOR_METATYPE_ARTIST},
- {"TPE3", EXTRACTOR_METATYPE_CONDUCTOR},
- {"TPE4", EXTRACTOR_METATYPE_INTERPRET},
- {"TMED", EXTRACTOR_METATYPE_MEDIA_TYPE},
- {"TCOM", EXTRACTOR_METATYPE_CREATOR},
- {"TIME", EXTRACTOR_METATYPE_TIME},
- {"TOFN", EXTRACTOR_METATYPE_FILENAME},
- {"TOPE", EXTRACTOR_METATYPE_ARTIST},
- {"TPUB", EXTRACTOR_METATYPE_PUBLISHER},
- {"TRCK", EXTRACTOR_METATYPE_TRACK_NUMBER},
- {"TRSC", EXTRACTOR_METATYPE_ISRC},
- {"TRSN", EXTRACTOR_METATYPE_SOURCE},
- {"TRSO", EXTRACTOR_METATYPE_CREATED_FOR},
- {"TSRC", EXTRACTOR_METATYPE_RESOURCE_IDENTIFIER},
- {"TOAL", EXTRACTOR_METATYPE_ALBUM},
- {"TALB", EXTRACTOR_METATYPE_ALBUM},
- {"TLAN", EXTRACTOR_METATYPE_LANGUAGE},
- {"TYER", EXTRACTOR_METATYPE_YEAR},
- {"TLEN", EXTRACTOR_METATYPE_DURATION},
- {"TIT2", EXTRACTOR_METATYPE_TITLE},
- {"TIT3", EXTRACTOR_METATYPE_DESCRIPTION},
- {"WCOM", EXTRACTOR_METATYPE_RELEASE},
- {"WCOP", EXTRACTOR_METATYPE_DISCLAIMER},
- {"", EXTRACTOR_METATYPE_KEYWORDS},
- {NULL, 0}
+ {"TALB", EXTRACTOR_METATYPE_ALBUM, T},
+ {"TBPM", EXTRACTOR_METATYPE_BEATS_PER_MINUTE, T},
+ {"TCOM", EXTRACTOR_METATYPE_COMPOSER, T},
+ {"TCON", EXTRACTOR_METATYPE_SONG_VERSION, T},
+ {"TCOP", EXTRACTOR_METATYPE_COPYRIGHT, T},
+ /* {"TDAT", EXTRACTOR_METATYPE_CREATION_DATE, T}, */
+ /* TDLY */
+ {"TENC", EXTRACTOR_METATYPE_ENCODED_BY, T},
+ {"TEXT", EXTRACTOR_METATYPE_WRITER, T},
+ {"TFLT", EXTRACTOR_METATYPE_FORMAT_VERSION, T},
+ /* TIME */
+ {"TIT1", EXTRACTOR_METATYPE_SECTION, T},
+ {"TIT2", EXTRACTOR_METATYPE_TITLE, T},
+ {"TIT3", EXTRACTOR_METATYPE_SONG_VERSION, T},
+ /* TKEY */
+ {"TLAN", EXTRACTOR_METATYPE_LANGUAGE, T},
+ {"TLEN", EXTRACTOR_METATYPE_DURATION, T}, /* FIXME: should append 'ms' as unit */
+ {"TMED", EXTRACTOR_METATYPE_SOURCE, T},
+ {"TOAL", EXTRACTOR_METATYPE_ORIGINAL_TITLE, T},
+ {"TOFN", EXTRACTOR_METATYPE_ORIGINAL_ARTIST, T},
+ {"TOLY", EXTRACTOR_METATYPE_ORIGINAL_WRITER, T},
+ {"TOPE", EXTRACTOR_METATYPE_ORIGINAL_PERFORMER, T},
+ {"TORY", EXTRACTOR_METATYPE_ORIGINAL_RELEASE_YEAR, T},
+ {"TOWN", EXTRACTOR_METATYPE_LICENSEE, T},
+ {"TPE1", EXTRACTOR_METATYPE_ARTIST, T},
+ {"TPE2", EXTRACTOR_METATYPE_PERFORMER, T},
+ {"TPE3", EXTRACTOR_METATYPE_CONDUCTOR, T},
+ {"TPE4", EXTRACTOR_METATYPE_INTERPRETATION, T},
+ {"TPOS", EXTRACTOR_METATYPE_DISC_NUMBER, T},
+ {"TPUB", EXTRACTOR_METATYPE_PUBLISHER, T},
+ {"TRCK", EXTRACTOR_METATYPE_TRACK_NUMBER, T},
+ /* TRDA */
+ {"TRSN", EXTRACTOR_METATYPE_NETWORK_NAME, T},
+ /* TRSO */
+ {"TSIZ", EXTRACTOR_METATYPE_EMBEDDED_FILE_SIZE, T},
+ {"TSRC", EXTRACTOR_METATYPE_ISRC, T},
+ /* TSSE */
+ {"TYER", EXTRACTOR_METATYPE_PUBLICATION_YEAR, T},
+ {"WCOM", EXTRACTOR_METATYPE_URL, U},
+ {"WCOP", EXTRACTOR_METATYPE_URL, U},
+ {"WOAF", EXTRACTOR_METATYPE_URL, U},
+ {"WOAS", EXTRACTOR_METATYPE_URL, U},
+ {"WORS", EXTRACTOR_METATYPE_URL, U},
+ {"WPAY", EXTRACTOR_METATYPE_URL, U},
+ {"WPUB", EXTRACTOR_METATYPE_URL, U},
+ {"WXXX", EXTRACTOR_METATYPE_URL, T},
+ {"IPLS", EXTRACTOR_METATYPE_CONTRIBUTOR_NAME, T},
+ /* ... */
+ {"USLT", EXTRACTOR_METATYPE_LYRICS, UL },
+ {"SYLT", EXTRACTOR_METATYPE_LYRICS, SL },
+ {"COMM", EXTRACTOR_METATYPE_COMMENT, L},
+ /* ... */
+ {"APIC", EXTRACTOR_METATYPE_PICTURE, I},
+ /* ... */
+ {"LINK", EXTRACTOR_METATYPE_URL, U},
+ /* ... */
+ {"USER", EXTRACTOR_METATYPE_LICENSE, T},
+ /* ... */
+ {NULL, 0, T}
};
@@ -104,6 +133,9 @@ EXTRACTOR_id3v23_extract (const unsigned char *data,
uint32_t csize;
int i;
uint16_t flags;
+ char *mime;
+ enum EXTRACTOR_MetaType type;
+ size_t off;
if ((size < 16) ||
(data[0] != 0x49) ||
@@ -111,12 +143,16 @@ EXTRACTOR_id3v23_extract (const unsigned char *data,
(data[2] != 0x33) || (data[3] != 0x03) || (data[4] != 0x00))
return 0;
unsync = (data[5] & 0x80) > 0;
+ if (unsync)
+ return 0; /* not supported */
extendedHdr = (data[5] & 0x40) > 0;
experimental = (data[5] & 0x20) > 0;
+ if (experimental)
+ return 0;
tsize = (((data[6] & 0x7F) << 21) |
((data[7] & 0x7F) << 14) |
((data[8] & 0x7F) << 7) | ((data[9] & 0x7F) << 0));
- if ((tsize + 10 > size) || (experimental))
+ if (tsize + 10 > size)
return 0;
pos = 10;
padding = 0;
@@ -142,7 +178,8 @@ EXTRACTOR_id3v23_extract (const unsigned char *data,
csize =
(data[pos + 4] << 24) + (data[pos + 5] << 16) + (data[pos + 6] << 8) +
data[pos + 7];
- if ((pos + 10 + csize > tsize) || (csize > tsize) || (csize == 0))
+ if ((pos + 10 + csize > tsize) || (csize > tsize) || (csize == 0) ||
+ (pos + 10 + csize <= pos + 10) || (pos + 10 <= pos))
break;
flags = (data[pos + 8] << 8) + data[pos + 9];
if (((flags & 0x80) > 0) /* compressed, not yet supported */ ||
@@ -163,32 +200,191 @@ EXTRACTOR_id3v23_extract (const unsigned char *data,
pos++;
csize--;
}
- csize--;
- /* this byte describes the encoding
- try to convert strings to UTF-8
- if it fails, then forget it */
- switch (data[pos + 10])
- {
- case 0x00:
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "ISO-8859-1");
- break;
- case 0x01:
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "UCS-2");
- break;
- default:
- /* bad encoding byte,
- try to convert from iso-8859-1 */
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "ISO-8859-1");
- break;
- }
- pos++;
+ switch (tmap[i].fmt)
+ {
+ case T:
+ /* this byte describes the encoding
+ try to convert strings to UTF-8
+ if it fails, then forget it */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "ISO-8859-1");
+ break;
+ }
+ break;
+ case U:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 10],
+ csize, "ISO-8859-1");
+ break;
+ case UL:
+ if (csize < 6)
+ return 0; /* malformed */
+ /* find end of description */
+ off = 14;
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "ISO-8859-1");
+ break;
+ }
+ break;
+ case SL:
+ if (csize < 7)
+ return 0; /* malformed */
+ /* find end of description */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "ISO-8859-1");
+ break;
+ }
+ break;
+ case L:
+ if (csize < 5)
+ return 0; /* malformed */
+ /* find end of description */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "ISO-8859-1");
+ break;
+ }
+ break;
+ case I:
+ if (csize < 2)
+ return 0; /* malformed */
+ /* find end of mime type */
+ off = 11;
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ mime = strdup ((const char*) &data[pos + 11]);
+
+ switch (data[pos+off])
+ {
+ case 0x03:
+ case 0x04:
+ type = EXTRACTOR_METATYPE_COVER_PICTURE;
+ break;
+ case 0x07:
+ case 0x08:
+ case 0x09:
+ case 0x0A:
+ case 0x0B:
+ case 0x0C:
+ type = EXTRACTOR_METATYPE_CONTRIBUTOR_PICTURE;
+ break;
+ case 0x0D:
+ case 0x0E:
+ case 0x0F:
+ type = EXTRACTOR_METATYPE_EVENT_PICTURE;
+ break;
+ case 0x14:
+ type = EXTRACTOR_METATYPE_LOGO;
+ type = EXTRACTOR_METATYPE_LOGO;
+ break;
+ default:
+ type = EXTRACTOR_METATYPE_PICTURE;
+ break;
+ }
+ off++;
+
+ /* find end of description */
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ if (0 == strcasecmp ("-->",
+ mime))
+ {
+ /* not supported */
+ }
+ else
+ {
+ if (0 != proc (proc_cls,
+ "id3v23",
+ type,
+ EXTRACTOR_METAFORMAT_BINARY,
+ mime,
+ (const char*) &data[pos + off],
+ csize + 6 - off))
+ {
+ free (mime);
+ return 1;
+ }
+ }
+ free (mime);
+ word = NULL;
+ break;
+ default:
+ return 0;
+ }
if ((word != NULL) && (strlen (word) > 0))
{
if (0 != proc (proc_cls,
- "id3v2",
+ "id3v23",
tmap[i].type,
EXTRACTOR_METAFORMAT_UTF8,
"text/plain",
diff --git a/src/plugins/id3v24_extractor.c b/src/plugins/id3v24_extractor.c
@@ -1,6 +1,6 @@
/*
This file is part of libextractor.
- (C) 2002, 2003, 2004, 2006, 2009 Vidyut Samanta and Christian Grothoff
+ (C) 2002, 2003, 2004, 2006, 2007, 2009 Vidyut Samanta and Christian Grothoff
libextractor is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published
@@ -18,7 +18,6 @@
Boston, MA 02111-1307, USA.
*/
-
#define DEBUG_EXTRACT_ID3v24 0
#include "platform.h"
@@ -33,72 +32,98 @@
#ifndef MINGW
#include <sys/mman.h>
#endif
+
#include "convert.h"
-
-static struct EXTRACTOR_Keywords *
-addKeyword (EXTRACTOR_KeywordList * oldhead,
- char *phrase, EXTRACTOR_KeywordType type)
-{
- EXTRACTOR_KeywordList *keyword;
-
- keyword = malloc (sizeof (EXTRACTOR_KeywordList));
- keyword->next = oldhead;
- keyword->keyword = phrase;
- keyword->keywordType = type;
- return keyword;
-}
+enum Id3v24Fmt
+ {
+ T, /* simple, 0-terminated string, prefixed by encoding */
+ U, /* 0-terminated ASCII string, no encoding */
+ UL, /* unsync'ed lyrics */
+ SL, /* sync'ed lyrics */
+ L, /* string with language prefix */
+ I /* image */
+ };
typedef struct
{
- char *text;
+ const char *text;
enum EXTRACTOR_MetaType type;
+ enum Id3v24Fmt fmt;
} Matches;
static Matches tmap[] = {
- {"COMM", EXTRACTOR_METATYPE_COMMENT},
- {"IPLS", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TIPL", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TMOO", EXTRACTOR_METATYPE_MOOD},
- {"TMCL", EXTRACTOR_METATYPE_MUSICIAN_CREDITS_LIST},
- {"LINK", EXTRACTOR_METATYPE_LINK},
- {"MCDI", EXTRACTOR_METATYPE_MUSIC_CD_IDENTIFIER},
- {"PCNT", EXTRACTOR_METATYPE_PLAY_COUNTER},
- {"POPM", EXTRACTOR_METATYPE_POPULARITY_METER},
- {"TCOP", EXTRACTOR_METATYPE_COPYRIGHT},
- {"TDRC", EXTRACTOR_METATYPE_DATE},
- {"TCON", EXTRACTOR_METATYPE_GENRE},
- {"TIT1", EXTRACTOR_METATYPE_GENRE},
- {"TENC", EXTRACTOR_METATYPE_ENCODED_BY},
- {"TEXT", EXTRACTOR_METATYPE_LYRICS},
- {"TOLY", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TOPE", EXTRACTOR_METATYPE_CONTRIBUTOR},
- {"TOWN", EXTRACTOR_METATYPE_OWNER},
- {"TPE1", EXTRACTOR_METATYPE_ARTIST},
- {"TPE2", EXTRACTOR_METATYPE_ARTIST},
- {"TPE3", EXTRACTOR_METATYPE_CONDUCTOR},
- {"TPE4", EXTRACTOR_METATYPE_INTERPRET},
- {"TIME", EXTRACTOR_METATYPE_TIME},
- {"TMED", EXTRACTOR_METATYPE_MEDIA_TYPE},
- {"TCOM", EXTRACTOR_METATYPE_CREATOR},
- {"TOFN", EXTRACTOR_METATYPE_FILENAME},
- {"TOPE", EXTRACTOR_METATYPE_ARTIST},
- {"TPUB", EXTRACTOR_METATYPE_PUBLISHER},
- {"TRCK", EXTRACTOR_METATYPE_TRACK_NUMBER},
- {"TRSC", EXTRACTOR_METATYPE_ISRC},
- {"TRSN", EXTRACTOR_METATYPE_SOURCE},
- {"TRSO", EXTRACTOR_METATYPE_CREATED_FOR},
- {"TSRC", EXTRACTOR_METATYPE_RESOURCE_IDENTIFIER},
- {"TYER", EXTRACTOR_METATYPE_YEAR},
- {"TOAL", EXTRACTOR_METATYPE_ALBUM},
- {"TALB", EXTRACTOR_METATYPE_ALBUM},
- {"TLAN", EXTRACTOR_METATYPE_LANGUAGE},
- {"TIT2", EXTRACTOR_METATYPE_TITLE},
- {"TIT3", EXTRACTOR_METATYPE_DESCRIPTION},
- {"WCOM", EXTRACTOR_METATYPE_RELEASE},
- {"WCOP", EXTRACTOR_METATYPE_DISCLAIMER},
- {"", EXTRACTOR_METATYPE_KEYWORDS},
- {NULL, 0}
+ {"TALB", EXTRACTOR_METATYPE_ALBUM, T},
+ {"TBPM", EXTRACTOR_METATYPE_BEATS_PER_MINUTE, T},
+ {"TCOM", EXTRACTOR_METATYPE_COMPOSER, T},
+ {"TCON", EXTRACTOR_METATYPE_SONG_VERSION, T},
+ {"TCOP", EXTRACTOR_METATYPE_COPYRIGHT, T},
+ /* {"TDAT", EXTRACTOR_METATYPE_CREATION_DATE, T}, deprecated in 24 */
+ /* TDLY */
+ {"TENC", EXTRACTOR_METATYPE_ENCODED_BY, T},
+ {"TEXT", EXTRACTOR_METATYPE_WRITER, T},
+ {"TFLT", EXTRACTOR_METATYPE_FORMAT_VERSION, T},
+ /* TIME, deprecated in 24 */
+ {"TIT1", EXTRACTOR_METATYPE_SECTION, T},
+ {"TIT2", EXTRACTOR_METATYPE_TITLE, T},
+ {"TIT3", EXTRACTOR_METATYPE_SONG_VERSION, T},
+ /* TKEY */
+ {"TLAN", EXTRACTOR_METATYPE_LANGUAGE, T},
+ {"TLEN", EXTRACTOR_METATYPE_DURATION, T}, /* FIXME: should append 'ms' as unit */
+ {"TMED", EXTRACTOR_METATYPE_SOURCE, T},
+ {"TOAL", EXTRACTOR_METATYPE_ORIGINAL_TITLE, T},
+ {"TOFN", EXTRACTOR_METATYPE_ORIGINAL_ARTIST, T},
+ {"TOLY", EXTRACTOR_METATYPE_ORIGINAL_WRITER, T},
+ {"TOPE", EXTRACTOR_METATYPE_ORIGINAL_PERFORMER, T},
+ /* {"TORY", EXTRACTOR_METATYPE_ORIGINAL_RELEASE_YEAR, T}, deprecated in 24 */
+ {"TOWN", EXTRACTOR_METATYPE_LICENSEE, T},
+ {"TPE1", EXTRACTOR_METATYPE_ARTIST, T},
+ {"TPE2", EXTRACTOR_METATYPE_PERFORMER, T},
+ {"TPE3", EXTRACTOR_METATYPE_CONDUCTOR, T},
+ {"TPE4", EXTRACTOR_METATYPE_INTERPRETATION, T},
+ {"TPOS", EXTRACTOR_METATYPE_DISC_NUMBER, T},
+ {"TPUB", EXTRACTOR_METATYPE_PUBLISHER, T},
+ {"TRCK", EXTRACTOR_METATYPE_TRACK_NUMBER, T},
+ /* TRDA, deprecated in 24 */
+ {"TRSN", EXTRACTOR_METATYPE_NETWORK_NAME, T},
+ /* TRSO */
+ /* {"TSIZ", EXTRACTOR_METATYPE_EMBEDDED_FILE_SIZE, T}, deprecated in 24 */
+ {"TSRC", EXTRACTOR_METATYPE_ISRC, T},
+ /* TSSE */
+ /* {"TYER", EXTRACTOR_METATYPE_PUBLICATION_YEAR, T}, deprecated in 24 */
+ {"WCOM", EXTRACTOR_METATYPE_URL, U},
+ {"WCOP", EXTRACTOR_METATYPE_URL, U},
+ {"WOAF", EXTRACTOR_METATYPE_URL, U},
+ {"WOAS", EXTRACTOR_METATYPE_URL, U},
+ {"WORS", EXTRACTOR_METATYPE_URL, U},
+ {"WPAY", EXTRACTOR_METATYPE_URL, U},
+ {"WPUB", EXTRACTOR_METATYPE_URL, U},
+ {"WXXX", EXTRACTOR_METATYPE_URL, T},
+ /* {"IPLS", EXTRACTOR_METATYPE_CONTRIBUTOR_NAME, T}, deprecated in 24 */
+ /* ... */
+ {"USLT", EXTRACTOR_METATYPE_LYRICS, UL },
+ {"SYLT", EXTRACTOR_METATYPE_LYRICS, SL },
+ {"COMM", EXTRACTOR_METATYPE_COMMENT, L},
+ /* ... */
+ {"APIC", EXTRACTOR_METATYPE_PICTURE, I},
+ /* ... */
+ {"LINK", EXTRACTOR_METATYPE_URL, U},
+ /* ... */
+ {"USER", EXTRACTOR_METATYPE_LICENSE, T},
+ /* ... */
+ /* new frames in 24 */
+ /* ASPI, EQU2, RVA2, SEEK, SIGN, TDEN */
+ {"TDOR", EXTRACTOR_METATYPE_PUBLICATION_DATE, T},
+ /* TDRC, TDRL, TDTG */
+ {"TIPL", EXTRACTOR_METATYPE_CONTRIBUTOR_NAME, T},
+ {"TMCL", EXTRACTOR_METATYPE_MUSICIAN_CREDITS_LIST, T},
+ {"TMOO", EXTRACTOR_METATYPE_MOOD, T},
+ {"TPRO", EXTRACTOR_METATYPE_COPYRIGHT, T},
+ {"TSOA", EXTRACTOR_METATYPE_ALBUM, T},
+ {"TSOP", EXTRACTOR_METATYPE_PERFORMER, T},
+ {"TSOT", EXTRACTOR_METATYPE_TITLE, T},
+ {"TSST", EXTRACTOR_METATYPE_SUBTITLE, T},
+ {NULL, 0, T}
};
@@ -114,54 +139,60 @@ EXTRACTOR_id3v24_extract (const unsigned char *data,
int extendedHdr;
int experimental;
int footer;
- unsigned int tsize;
- unsigned int pos;
- unsigned int ehdrSize;
- unsigned int padding;
+ uint32_t tsize;
+ uint32_t pos;
+ uint32_t ehdrSize;
+ uint32_t padding;
+ uint32_t csize;
+ int i;
+ uint16_t flags;
+ char *mime;
+ enum EXTRACTOR_MetaType type;
+ size_t off;
if ((size < 16) ||
(data[0] != 0x49) ||
(data[1] != 0x44) ||
(data[2] != 0x33) || (data[3] != 0x04) || (data[4] != 0x00))
- return prev;
+ return 0;
unsync = (data[5] & 0x80) > 0;
+ if (unsync)
+ return 0; /* not supported */
extendedHdr = (data[5] & 0x40) > 0;
experimental = (data[5] & 0x20) > 0;
+ if (experimental)
+ return 0;
footer = (data[5] & 0x10) > 0;
tsize = (((data[6] & 0x7F) << 21) |
((data[7] & 0x7F) << 14) |
((data[8] & 0x7F) << 7) | ((data[9] & 0x7F) << 0));
- if ((tsize + 10 > size) || (experimental))
- return prev;
+ if (tsize + 10 > size)
+ return 0;
pos = 10;
padding = 0;
if (extendedHdr)
{
ehdrSize = (((data[10] & 0x7F) << 21) |
- ((data[11] & 0x7F) << 14) |
- ((data[12] & 0x7F) << 7) | ((data[13] & 0x7F) << 0));
- pos += ehdrSize;
+ ((data[11] & 0x7F) << 14) |
+ ((data[12] & 0x7F) << 7) | ((data[13] & 0x7F) << 0));
+ pos += 4 + ehdrSize;
+ if (ehdrSize > tsize)
+ return 0;
}
-
-
while (pos < tsize)
{
- size_t csize;
- int i;
- unsigned short flags;
-
if (pos + 10 > tsize)
- return prev;
-
- csize = (((data[pos + 4] & 0x7F) << 21) |
- ((data[pos + 5] & 0x7F) << 14) |
- ((data[pos + 6] & 0x7F) << 7) | ((data[pos + 7] & 0x7F) << 0));
-
- if ((pos + 10 + csize > tsize) || (csize > tsize) || (csize == 0))
+ return 0;
+ csize =
+ (data[pos + 4] << 24) + (data[pos + 5] << 16) + (data[pos + 6] << 8) +
+ data[pos + 7];
+ if ((pos + 10 + csize > tsize) || (csize > tsize) || (csize == 0) ||
+ (pos + 10 + csize <= pos + 10) || (pos + 10 <= pos))
break;
flags = (data[pos + 8] << 8) + data[pos + 9];
- if (((flags & 0x80) > 0) /* compressed, not yet supported */ ||
- ((flags & 0x40) > 0) /* encrypted, not supported */ )
+ if (((flags & 0x08) > 0) /* compressed, not yet supported */ ||
+ ((flags & 0x04) > 0) /* encrypted, not supported */ ||
+ ((flags & 0x02) > 0) /* unsynchronized, not supported */ )
{
pos += 10 + csize;
continue;
@@ -172,59 +203,216 @@ EXTRACTOR_id3v24_extract (const unsigned char *data,
if (0 == strncmp (tmap[i].text, (const char *) &data[pos], 4))
{
char *word;
- if ((flags & 0x20) > 0)
+ if ((flags & 0x40) > 0)
{
/* "group" identifier, skip a byte */
pos++;
csize--;
}
- /* this byte describes the encoding
- try to convert strings to UTF-8
- if it fails, then forget it */
- csize--;
- switch (data[pos + 10])
- {
- case 0x00:
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "ISO-8859-1");
- break;
- case 0x01:
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "UTF-16");
- break;
- case 0x02:
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "UTF-16BE");
- break;
- case 0x03:
- word = malloc (csize + 1);
- memcpy (word, &data[pos + 11], csize);
- word[csize] = '\0';
- break;
- default:
- /* bad encoding byte,
- try to convert from iso-8859-1 */
- word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
- csize, "ISO-8859-1");
- break;
- }
- pos++;
+ switch (tmap[i].fmt)
+ {
+ case T:
+ /* this byte describes the encoding
+ try to convert strings to UTF-8
+ if it fails, then forget it */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 11],
+ csize - 1, "ISO-8859-1");
+ break;
+ }
+ break;
+ case U:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 10],
+ csize, "ISO-8859-1");
+ break;
+ case UL:
+ if (csize < 6)
+ return 0; /* malformed */
+ /* find end of description */
+ off = 14;
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + off],
+ csize - off, "ISO-8859-1");
+ break;
+ }
+ break;
+ case SL:
+ if (csize < 7)
+ return 0; /* malformed */
+ /* find end of description */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 16],
+ csize - 6, "ISO-8859-1");
+ break;
+ }
+ break;
+ case L:
+ if (csize < 5)
+ return 0; /* malformed */
+ /* find end of description */
+ switch (data[pos + 10])
+ {
+ case 0x00:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "ISO-8859-1");
+ break;
+ case 0x01:
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "UCS-2");
+ break;
+ default:
+ /* bad encoding byte,
+ try to convert from iso-8859-1 */
+ word = EXTRACTOR_common_convert_to_utf8 ((const char *) &data[pos + 14],
+ csize - 4, "ISO-8859-1");
+ break;
+ }
+ break;
+ case I:
+ if (csize < 2)
+ return 0; /* malformed */
+ /* find end of mime type */
+ off = 11;
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ mime = strdup ((const char*) &data[pos + 11]);
+
+ switch (data[pos+off])
+ {
+ case 0x03:
+ case 0x04:
+ type = EXTRACTOR_METATYPE_COVER_PICTURE;
+ break;
+ case 0x07:
+ case 0x08:
+ case 0x09:
+ case 0x0A:
+ case 0x0B:
+ case 0x0C:
+ type = EXTRACTOR_METATYPE_CONTRIBUTOR_PICTURE;
+ break;
+ case 0x0D:
+ case 0x0E:
+ case 0x0F:
+ type = EXTRACTOR_METATYPE_EVENT_PICTURE;
+ break;
+ case 0x14:
+ type = EXTRACTOR_METATYPE_LOGO;
+ type = EXTRACTOR_METATYPE_LOGO;
+ break;
+ default:
+ type = EXTRACTOR_METATYPE_PICTURE;
+ break;
+ }
+ off++;
+
+ /* find end of description */
+ while ( (off < size) &&
+ (off - pos < csize) &&
+ (data[pos + off] == '\0') )
+ off++;
+ if ( (off >= csize) ||
+ (data[pos+off] != '\0') )
+ return 0; /* malformed */
+ off++;
+ if (0 == strcasecmp ("-->",
+ mime))
+ {
+ /* not supported */
+ }
+ else
+ {
+ if (0 != proc (proc_cls,
+ "id3v24",
+ type,
+ EXTRACTOR_METAFORMAT_BINARY,
+ mime,
+ (const char*) &data[pos + off],
+ csize + 6 - off))
+ {
+ free (mime);
+ return 1;
+ }
+ }
+ free (mime);
+ word = NULL;
+ break;
+ default:
+ return 0;
+ }
if ((word != NULL) && (strlen (word) > 0))
{
- prev = addKeyword (prev, word, tmap[i].type);
- }
- else
- {
- free (word);
+ if (0 != proc (proc_cls,
+ "id3v24",
+ tmap[i].type,
+ EXTRACTOR_METAFORMAT_UTF8,
+ "text/plain",
+ word,
+ strlen(word)+1))
+ {
+ free (word);
+ return 1;
+ }
}
+ free (word);
break;
}
i++;
}
pos += 10 + csize;
}
- return prev;
+ return 0;
}
/* end of id3v24_extractor.c */
diff --git a/src/plugins/id3v2_extractor.c b/src/plugins/id3v2_extractor.c
@@ -113,7 +113,7 @@ static Matches tmap[] = {
/* skipping CRM */
/* skipping CRA */
/* {"LNK", EXTRACTOR_METATYPE_URL, XXX}, */
- {NULL, 0},
+ {NULL, 0, T},
};
diff --git a/src/plugins/odf_extractor.c b/src/plugins/odf_extractor.c
@@ -44,7 +44,7 @@ static Matches tmap[] = {
{ "meta:creation-date", EXTRACTOR_METATYPE_CREATION_DATE },
{ "dc:date", EXTRACTOR_METATYPE_UNKNOWN_DATE },
{ "dc:creator", EXTRACTOR_METATYPE_CREATOR },
- { "dc:language", EXTRACTOR_METATYPE_DOCUMENT_LANGUAGE },
+ { "dc:language", EXTRACTOR_METATYPE_LANGUAGE },
{ "dc:title", EXTRACTOR_METATYPE_TITLE },
{ "dc:description", EXTRACTOR_METATYPE_DESCRIPTION },
{ "dc:subject", EXTRACTOR_METATYPE_SUBJECT },
diff --git a/src/plugins/ole2_extractor.c b/src/plugins/ole2_extractor.c
@@ -107,7 +107,7 @@ static Matches tmap[] = {
{ "meta:generator", EXTRACTOR_METATYPE_CREATED_BY_SOFTWARE },
{ "meta:template", EXTRACTOR_METATYPE_TEMPLATE },
{ "meta:editing-cycles", EXTRACTOR_METATYPE_EDITING_CYCLES },
- /* { "Dictionary", EXTRACTOR_METATYPE_DOCUMENT_LANGUAGE }, */
+ /* { "Dictionary", EXTRACTOR_METATYPE_LANGUAGE }, */
/* { "gsf:security", EXTRACTOR_SECURITY }, */
/* { "gsf:scale", EXTRACTOR_SCALE }, // always "false"? */
/* { "meta:editing-duration", EXTRACTOR_METATYPE_TOTAL_EDITING_TIME }, // encoding? */
@@ -544,7 +544,7 @@ EXTRACTOR_ole2_extract (const char *data,
if ( (lang != NULL) && (ret == 0) )
ret = addKeyword(proc, proc_cls,
lang,
- EXTRACTOR_METATYPE_DOCUMENT_LANGUAGE);
+ EXTRACTOR_METATYPE_LANGUAGE);
if (lcb >= 6) {
for (i=0;i<gsf_infile_num_children(infile);i++) {
if (ret != 0)
diff --git a/src/plugins/png_extractor.c b/src/plugins/png_extractor.c
@@ -141,7 +141,7 @@ processiTXt (const char *data,
language = &data[pos];
ret = 0;
if (stnlen (language, length - pos) > 0)
- ADDF (EXTRACTOR_METATYPE_DOCUMENT_LANGUAGE,
+ ADDF (EXTRACTOR_METATYPE_LANGUAGE,
stndup (language, length - pos));
pos += stnlen (language, length - pos) + 1;
if (pos + 1 >= length)
diff --git a/src/plugins/qt_extractor.c b/src/plugins/qt_extractor.c
@@ -395,9 +395,9 @@ static ITTagConversionEntry it_to_extr_table[] = {
{"catg", EXTRACTOR_METATYPE_SECTION},
{"keyw", EXTRACTOR_METATYPE_KEYWORDS},
{"desc", EXTRACTOR_METATYPE_DESCRIPTION},
- {"tvnn", EXTRACTOR_METATYPE_TV_NETWORK_NAME},
- {"tvsh", EXTRACTOR_METATYPE_TV_SHOW_NAME},
- {"tven", EXTRACTOR_METATYPE_TV_NETWORK_NAME},
+ {"tvnn", EXTRACTOR_METATYPE_NETWORK_NAME},
+ {"tvsh", EXTRACTOR_METATYPE_SHOW_NAME},
+ {"tven", EXTRACTOR_METATYPE_NETWORK_NAME},
{NULL, EXTRACTOR_METATYPE_RESERVED}
};
@@ -850,7 +850,7 @@ processTextTag (const char *input,
lang = ntohs (txt->language);
if (lang >= sizeof (languages) / sizeof (char *))
return 0; /* invalid */
- addKeyword (EXTRACTOR_METATYPE_DOCUMENT_LANGUAGE, languages[lang], ec);
+ addKeyword (EXTRACTOR_METATYPE_LANGUAGE, languages[lang], ec);
meta = malloc (len + 1);
memcpy (meta, &txt[1], len);
