diff options
author | Jan Schmidt <thaytan@mad.scientist.com> | 2005-12-18 15:14:44 +0000 |
---|---|---|
committer | Jan Schmidt <thaytan@mad.scientist.com> | 2005-12-18 15:14:44 +0000 |
commit | a05fc627837838ff157ab4b702674407e627c498 (patch) | |
tree | 4c4761c9fdce1b4a1eb17d24b04c53761885769e /gst/id3demux | |
parent | 3ba78f01938cff141b93018d7f7523079a256873 (diff) |
configure.ac: Check for optional dependency on zlib for id3demux
Original commit message from CVS:
* configure.ac:
Check for optional dependency on zlib for id3demux
* gst/id3demux/Makefile.am:
* gst/id3demux/gstid3demux.c: (gst_gst_id3demux_get_type),
(gst_id3demux_base_init), (gst_id3demux_class_init),
(gst_id3demux_reset), (gst_id3demux_init), (gst_id3demux_dispose),
(gst_id3demux_add_srcpad), (gst_id3demux_remove_srcpad),
(gst_id3demux_trim_buffer), (gst_id3demux_chain),
(gst_id3demux_set_property), (gst_id3demux_get_property),
(id3demux_get_upstream_size), (gst_id3demux_srcpad_event),
(gst_id3demux_read_id3v1), (gst_id3demux_read_id3v2),
(gst_id3demux_sink_activate), (gst_id3demux_src_activate_pull),
(gst_id3demux_src_checkgetrange), (gst_id3demux_read_range),
(gst_id3demux_src_getrange), (gst_id3demux_change_state),
(gst_id3demux_pad_query), (gst_id3demux_get_query_types),
(simple_find_peek), (simple_find_suggest),
(gst_id3demux_do_typefind), (gst_id3demux_send_tag_event),
(plugin_init):
* gst/id3demux/gstid3demux.h:
* gst/id3demux/id3tags.c: (read_synch_uint),
(id3demux_read_id3v1_tag), (id3demux_read_id3v2_tag),
(id3demux_id3v2_frame_hdr_size), (convert_fid_to_v240),
(id3demux_id3v2_frames_to_tag_list):
* gst/id3demux/id3tags.h:
* gst/id3demux/id3v2.4.0-frames.txt:
* gst/id3demux/id3v2.4.0-structure.txt:
* gst/id3demux/id3v2frames.c: (id3demux_id3v2_parse_frame),
(parse_comment_frame), (parse_text_identification_frame),
(id3v2_tag_to_taglist), (parse_split_strings):
All new LGPL id3 demuxer. Can use zlib for compressed frames,
otherwise it discards them. Works on my test files.
* gst/wavparse/gstwavparse.c: (gst_wavparse_loop):
Don't send EOS to a non-existing srcpad
The debug category can be static
Diffstat (limited to 'gst/id3demux')
-rw-r--r-- | gst/id3demux/Makefile.am | 8 | ||||
-rw-r--r-- | gst/id3demux/gstid3demux.c | 1086 | ||||
-rw-r--r-- | gst/id3demux/gstid3demux.h | 79 | ||||
-rw-r--r-- | gst/id3demux/id3tags.c | 431 | ||||
-rw-r--r-- | gst/id3demux/id3tags.h | 112 | ||||
-rw-r--r-- | gst/id3demux/id3v2.4.0-frames.txt | 1734 | ||||
-rw-r--r-- | gst/id3demux/id3v2.4.0-structure.txt | 733 | ||||
-rw-r--r-- | gst/id3demux/id3v2frames.c | 382 |
8 files changed, 4565 insertions, 0 deletions
diff --git a/gst/id3demux/Makefile.am b/gst/id3demux/Makefile.am new file mode 100644 index 00000000..afb79c31 --- /dev/null +++ b/gst/id3demux/Makefile.am @@ -0,0 +1,8 @@ +plugin_LTLIBRARIES = libgstid3demux.la + +libgstid3demux_la_SOURCES = gstid3demux.c id3tags.c id3v2frames.c +libgstid3demux_la_CFLAGS = $(GST_PLUGINS_BASE_CFLAGS) $(GST_CFLAGS) +libgstid3demux_la_LIBADD = $(GST_PLUGINS_BASE_LIBS) -lgsttag-@GST_MAJORMINOR@ $(ZLIB_LIBS) +libgstid3demux_la_LDFLAGS = $(GST_PLUGIN_LDFLAGS) + +noinst_HEADERS = gstid3demux.h id3tags.h diff --git a/gst/id3demux/gstid3demux.c b/gst/id3demux/gstid3demux.c new file mode 100644 index 00000000..4a7a370d --- /dev/null +++ b/gst/id3demux/gstid3demux.c @@ -0,0 +1,1086 @@ +/* -*- Mode: C; tab-width: 2; indent-tabs-mode: t; c-basic-offset: 2 -*- */ +/* Copyright 2005 Jan Schmidt <thaytan@mad.scientist.com> + * Copyright (C) 2003-2004 Benjamin Otte <otte@gnome.org> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with this library; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif +#include <gst/gst.h> +#include <gst/gst-i18n-plugin.h> + +#include "gstid3demux.h" +#include "id3tags.h" + +enum +{ + ARG_0, + ARG_PREFER_V1 +}; + +/* Require at least 4kB of data before we attempt typefind. + * Seems a decent value based on test files + * 40kB is massive overkill for the maximum, I think, but it + * doesn't do any harm */ +#define ID3_TYPE_FIND_MIN_SIZE 4096 +#define ID3_TYPE_FIND_MAX_SIZE 40960 + +GST_DEBUG_CATEGORY (id3demux_debug); +#define GST_CAT_DEFAULT (id3demux_debug) + +static GstStaticPadTemplate sink_factory = GST_STATIC_PAD_TEMPLATE ("sink", + GST_PAD_SINK, + GST_PAD_ALWAYS, + GST_STATIC_CAPS ("application/x-id3") + ); + +static GstStaticPadTemplate src_factory = GST_STATIC_PAD_TEMPLATE ("src", + GST_PAD_SRC, + GST_PAD_SOMETIMES, + GST_STATIC_CAPS ("ANY") + ); + +static void gst_id3demux_class_init (GstID3DemuxClass * klass); +static void gst_id3demux_base_init (GstID3DemuxClass * klass); +static void gst_id3demux_init (GstID3Demux * id3demux); +static void gst_id3demux_dispose (GObject * object); + +static void gst_id3demux_set_property (GObject * object, guint prop_id, + const GValue * value, GParamSpec * pspec); +static void gst_id3demux_get_property (GObject * object, guint prop_id, + GValue * value, GParamSpec * pspec); + +static GstFlowReturn gst_id3demux_chain (GstPad * pad, GstBuffer * buf); + +static gboolean gst_id3demux_src_activate_pull (GstPad * pad, gboolean active); +static GstFlowReturn gst_id3demux_read_range (GstID3Demux * id3demux, + guint64 offset, guint length, GstBuffer ** buffer); + +static gboolean gst_id3demux_src_checkgetrange (GstPad * srcpad); +static GstFlowReturn gst_id3demux_src_getrange (GstPad * srcpad, + guint64 offset, guint length, GstBuffer ** buffer); + +static gboolean gst_id3demux_add_srcpad (GstID3Demux * id3demux, + GstCaps * new_caps); +static gboolean gst_id3demux_remove_srcpad (GstID3Demux * id3demux); + +static gboolean gst_id3demux_srcpad_event (GstPad * pad, GstEvent * event); +static gboolean gst_id3demux_sink_activate (GstPad * sinkpad); +static GstStateChangeReturn gst_id3demux_change_state (GstElement * element, + GstStateChange transition); +static gboolean gst_id3demux_pad_query (GstPad * pad, GstQuery * query); +static const GstQueryType *gst_id3demux_get_query_types (GstPad * pad); +static gboolean id3demux_get_upstream_size (GstID3Demux * id3demux); +static GstCaps *gst_id3demux_do_typefind (GstID3Demux * id3demux, + GstBuffer * buffer); +static void gst_id3demux_send_tag_event (GstID3Demux * id3demux); + +static GstElementClass *parent_class = NULL; + +GType +gst_gst_id3demux_get_type (void) +{ + static GType plugin_type = 0; + + if (!plugin_type) { + static const GTypeInfo plugin_info = { + sizeof (GstID3DemuxClass), + (GBaseInitFunc) gst_id3demux_base_init, + NULL, + (GClassInitFunc) gst_id3demux_class_init, + NULL, + NULL, + sizeof (GstID3Demux), + 0, + (GInstanceInitFunc) gst_id3demux_init, + }; + plugin_type = g_type_register_static (GST_TYPE_ELEMENT, + "GstID3Demux", &plugin_info, 0); + } + return plugin_type; +} + +static void +gst_id3demux_base_init (GstID3DemuxClass * klass) +{ + static GstElementDetails plugin_details = { + "GStreamer ID3 Demuxer", + "Codec/Demuxer/Metadata", + "ID3 tag reader and demuxer", + "Jan Schmidt <thaytan@mad.scientist.com>" + }; + GstElementClass *element_class = GST_ELEMENT_CLASS (klass); + + gst_element_class_add_pad_template (element_class, + gst_static_pad_template_get (&src_factory)); + gst_element_class_add_pad_template (element_class, + gst_static_pad_template_get (&sink_factory)); + gst_element_class_set_details (element_class, &plugin_details); +} + +static void +gst_id3demux_class_init (GstID3DemuxClass * klass) +{ + GObjectClass *gobject_class; + GstElementClass *gstelement_class; + + gobject_class = (GObjectClass *) klass; + gstelement_class = (GstElementClass *) klass; + + parent_class = g_type_class_ref (GST_TYPE_ELEMENT); + + gobject_class->dispose = gst_id3demux_dispose; + + gobject_class->set_property = gst_id3demux_set_property; + gobject_class->get_property = gst_id3demux_get_property; + + gstelement_class->change_state = gst_id3demux_change_state; + + g_object_class_install_property (gobject_class, ARG_PREFER_V1, + g_param_spec_boolean ("prefer-v1", "Prefer version 1 tag", + "Prefer tags from ID3v1 tag at end of file", FALSE, + G_PARAM_READWRITE | G_PARAM_CONSTRUCT)); +} + +static void +gst_id3demux_reset (GstID3Demux * id3demux) +{ + id3demux->strip_start = 0; + id3demux->strip_end = 0; + id3demux->upstream_size = -1; + id3demux->state = GST_ID3DEMUX_READID3V2; + id3demux->send_tag_event = FALSE; + + gst_buffer_replace (&(id3demux->collect), NULL); + gst_caps_replace (&(id3demux->src_caps), NULL); + + gst_id3demux_remove_srcpad (id3demux); + + if (id3demux->event_tags) { + gst_tag_list_free (id3demux->event_tags); + id3demux->event_tags = NULL; + } + if (id3demux->parsed_tags) { + gst_tag_list_free (id3demux->parsed_tags); + id3demux->parsed_tags = NULL; + } + +} + +static void +gst_id3demux_init (GstID3Demux * id3demux) +{ + GstElementClass *klass = GST_ELEMENT_GET_CLASS (id3demux); + + id3demux->sinkpad = + gst_pad_new_from_template (gst_element_class_get_pad_template (klass, + "sink"), "sink"); + gst_pad_set_activate_function (id3demux->sinkpad, + GST_DEBUG_FUNCPTR (gst_id3demux_sink_activate)); + gst_pad_set_chain_function (id3demux->sinkpad, + GST_DEBUG_FUNCPTR (gst_id3demux_chain)); + gst_element_add_pad (GST_ELEMENT (id3demux), id3demux->sinkpad); + + id3demux->prefer_v1 = FALSE; + gst_id3demux_reset (id3demux); +} + +static void +gst_id3demux_dispose (GObject * object) +{ + GstID3Demux *id3demux = GST_ID3DEMUX (object); + + gst_id3demux_reset (id3demux); + + G_OBJECT_CLASS (parent_class)->dispose (object); +} + +static gboolean +gst_id3demux_add_srcpad (GstID3Demux * id3demux, GstCaps * new_caps) +{ + GstPad *srcpad = NULL; + + if (id3demux->src_caps == NULL || + !gst_caps_is_equal (new_caps, id3demux->src_caps)) { + + gst_caps_replace (&(id3demux->src_caps), new_caps); + if (id3demux->srcpad != NULL) { + GST_DEBUG_OBJECT (id3demux, "Changing src pad caps to %" GST_PTR_FORMAT, + id3demux->src_caps); + + gst_pad_set_caps (id3demux->srcpad, id3demux->src_caps); + } + } else { + /* Caps never changed */ + gst_caps_unref (new_caps); + } + + if (id3demux->srcpad == NULL) { + srcpad = id3demux->srcpad = + gst_pad_new_from_template (gst_element_class_get_pad_template + (GST_ELEMENT_GET_CLASS (id3demux), "src"), "src"); + g_return_val_if_fail (id3demux->srcpad != NULL, FALSE); + + gst_pad_set_query_type_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_get_query_types)); + gst_pad_set_query_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_pad_query)); + gst_pad_set_event_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_srcpad_event)); + gst_pad_set_activatepull_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_src_activate_pull)); + gst_pad_set_checkgetrange_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_src_checkgetrange)); + gst_pad_set_getrange_function (id3demux->srcpad, + GST_DEBUG_FUNCPTR (gst_id3demux_src_getrange)); + + gst_pad_use_fixed_caps (id3demux->srcpad); + + if (id3demux->src_caps) + gst_pad_set_caps (id3demux->srcpad, id3demux->src_caps); + + GST_DEBUG_OBJECT (id3demux, "Adding src pad with caps %" GST_PTR_FORMAT, + id3demux->src_caps); + + gst_object_ref (id3demux->srcpad); + return gst_element_add_pad (GST_ELEMENT (id3demux), id3demux->srcpad); + } + + return TRUE; +} + +static gboolean +gst_id3demux_remove_srcpad (GstID3Demux * id3demux) +{ + if (id3demux->srcpad != NULL) { + GST_DEBUG_OBJECT (id3demux, "Removing src pad"); + g_return_val_if_fail (gst_element_remove_pad (GST_ELEMENT (id3demux), + id3demux->srcpad), FALSE); + gst_object_unref (id3demux->srcpad); + id3demux->srcpad = NULL; + } + + return TRUE; +}; + +static gboolean +gst_id3demux_trim_buffer (GstID3Demux * id3demux, GstBuffer ** buf_ref) +{ + GstBuffer *buf = *buf_ref; + + guint trim_start = 0; + guint out_size = GST_BUFFER_SIZE (buf); + guint64 out_offset = GST_BUFFER_OFFSET (buf); + gboolean need_sub = FALSE; + + /* Adjust offset and length */ + if (!GST_BUFFER_OFFSET_IS_VALID (buf)) { + /* Can't change anything without an offset */ + return TRUE; + } + + /* If the buffer crosses the ID3v1 tag at the end of file, trim it */ + if (id3demux->strip_end > 0) { + if (id3demux_get_upstream_size (id3demux)) { + guint64 v1tag_offset = id3demux->upstream_size - id3demux->strip_end; + + if (out_offset >= v1tag_offset) { + GST_DEBUG_OBJECT (id3demux, "Buffer is past the end of the data"); + goto no_out_buffer; + } + + if (out_offset + out_size > v1tag_offset) { + out_size = v1tag_offset - out_offset; + need_sub = TRUE; + } + } + } + + if (id3demux->strip_start > 0) { + /* If the buffer crosses the ID3v2 tag at the start of file, trim it */ + if (out_offset <= id3demux->strip_start) { + if (out_offset + out_size <= id3demux->strip_start) { + GST_DEBUG_OBJECT (id3demux, "Buffer is before the start of the data"); + goto no_out_buffer; + } + + trim_start = id3demux->strip_start - out_offset; + out_size -= trim_start; + out_offset = 0; + } else { + out_offset -= id3demux->strip_start; + } + need_sub = TRUE; + } + + g_assert (out_size > 0); + + if (need_sub == TRUE) { + if (out_size != GST_BUFFER_SIZE (buf) || !gst_buffer_is_writable (buf)) { + GstBuffer *sub; + + GST_DEBUG_OBJECT (id3demux, "Sub-buffering to trim size %d offset %" + G_GINT64_FORMAT " to %d offset %" G_GINT64_FORMAT, + GST_BUFFER_SIZE (buf), GST_BUFFER_OFFSET (buf), out_size, out_offset); + + sub = gst_buffer_create_sub (buf, trim_start, out_size); + g_return_val_if_fail (sub != NULL, FALSE); + gst_buffer_unref (buf); + *buf_ref = buf = sub; + } else { + GST_DEBUG_OBJECT (id3demux, "Adjusting buffer from size %d offset %" + G_GINT64_FORMAT " to %d offset %" G_GINT64_FORMAT, + GST_BUFFER_SIZE (buf), GST_BUFFER_OFFSET (buf), out_size, out_offset); + } + + GST_BUFFER_OFFSET (buf) = out_offset; + GST_BUFFER_OFFSET_END (buf) = out_offset + out_size; + gst_buffer_set_caps (buf, id3demux->src_caps); + } + + return TRUE; +no_out_buffer: + gst_buffer_unref (buf); + *buf_ref = NULL; + return TRUE; +} + +static GstFlowReturn +gst_id3demux_chain (GstPad * pad, GstBuffer * buf) +{ + GstID3Demux *id3demux; + + id3demux = GST_ID3DEMUX (GST_PAD_PARENT (pad)); + g_return_val_if_fail (GST_IS_ID3DEMUX (id3demux), GST_FLOW_ERROR); + + if (id3demux->collect == NULL) { + id3demux->collect = buf; + } else { + id3demux->collect = gst_buffer_join (id3demux->collect, buf); + } + buf = NULL; + + switch (id3demux->state) { + case GST_ID3DEMUX_READID3V2: + /* If we receive a buffer that's from the middle of the file, + * we can't read tags so move to typefinding */ + if (GST_BUFFER_OFFSET (id3demux->collect) != 0) { + GST_DEBUG_OBJECT (id3demux, + "Received buffer from non-zero offset. Can't read tags"); + id3demux->state = GST_ID3DEMUX_TYPEFINDING; + break; + } else { + ID3TagsResult tag_result; + + tag_result = id3demux_read_id3v2_tag (id3demux->collect, + &id3demux->strip_start, &id3demux->parsed_tags); + if (tag_result == ID3TAGS_MORE_DATA) + break; /* Go get more data and try again */ + else if (tag_result == ID3TAGS_BROKEN_TAG) + GST_WARNING_OBJECT (id3demux, + "Ignoring broken ID3v2 tag of size %d", id3demux->strip_start); + else + GST_DEBUG_OBJECT (id3demux, "Found an ID3v2 tag of size %d\n", + id3demux->strip_start); + + id3demux->state = GST_ID3DEMUX_TYPEFINDING; + id3demux->send_tag_event = TRUE; + } + + /* Fall-through */ + case GST_ID3DEMUX_TYPEFINDING:{ + GstCaps *caps; + GstBuffer *typefind_buf = NULL; + + if (GST_BUFFER_SIZE (id3demux->collect) < ID3_TYPE_FIND_MIN_SIZE) + break; /* Go get more data first */ + + GST_DEBUG_OBJECT (id3demux, "Typefinding with size %d", + GST_BUFFER_SIZE (id3demux->collect)); + + /* Trim the buffer and adjust offset for typefinding */ + typefind_buf = id3demux->collect; + gst_buffer_ref (typefind_buf); + if (!gst_id3demux_trim_buffer (id3demux, &typefind_buf)) + return GST_FLOW_ERROR; + + caps = gst_id3demux_do_typefind (id3demux, typefind_buf); + + if (caps == NULL) { + if (GST_BUFFER_SIZE (typefind_buf) < ID3_TYPE_FIND_MAX_SIZE) { + /* Just break for more data */ + gst_buffer_unref (typefind_buf); + return GST_FLOW_OK; + } + + /* We failed typefind */ + GST_ELEMENT_ERROR (id3demux, CORE, CAPS, (NULL), ("no caps found")); + gst_buffer_unref (typefind_buf); + gst_buffer_unref (id3demux->collect); + id3demux->collect = NULL; + return GST_FLOW_ERROR; + } + gst_buffer_unref (typefind_buf); + + if (!gst_id3demux_add_srcpad (id3demux, caps)) { + GST_DEBUG_OBJECT (id3demux, "Failed to add srcpad"); + gst_caps_unref (caps); + goto error; + } + gst_caps_unref (caps); + + /* Move onto streaming and fall-through to push out existing + * data */ + id3demux->state = GST_ID3DEMUX_STREAMING; + /* fall-through */ + } + case GST_ID3DEMUX_STREAMING:{ + GstBuffer *outbuf = NULL; + + if (id3demux->send_tag_event) { + gst_id3demux_send_tag_event (id3demux); + id3demux->send_tag_event = FALSE; + } + + /* Trim the buffer and adjust offset */ + if (id3demux->collect) { + outbuf = id3demux->collect; + id3demux->collect = NULL; + if (!gst_id3demux_trim_buffer (id3demux, &outbuf)) + return GST_FLOW_ERROR; + } + if (outbuf) { + if (G_UNLIKELY (id3demux->srcpad == NULL)) { + gst_buffer_unref (outbuf); + return GST_FLOW_ERROR; + } + + GST_DEBUG_OBJECT (id3demux, "Pushing buffer %p", outbuf); + return gst_pad_push (id3demux->srcpad, outbuf); + } + } + } + return GST_FLOW_OK; + +error: + GST_DEBUG_OBJECT (id3demux, "error in chain function"); + + return GST_FLOW_ERROR; +} + +static void +gst_id3demux_set_property (GObject * object, guint prop_id, + const GValue * value, GParamSpec * pspec) +{ + GstID3Demux *id3demux; + + g_return_if_fail (GST_IS_ID3DEMUX (object)); + id3demux = GST_ID3DEMUX (object); + + switch (prop_id) { + case ARG_PREFER_V1: + id3demux->prefer_v1 = g_value_get_boolean (value); + break; + default: + G_OBJECT_WARN_INVALID_PROPERTY_ID (object, prop_id, pspec); + break; + } +} + +static void +gst_id3demux_get_property (GObject * object, guint prop_id, + GValue * value, GParamSpec * pspec) +{ + GstID3Demux *id3demux; + + g_return_if_fail (GST_IS_ID3DEMUX (object)); + id3demux = GST_ID3DEMUX (object); + + switch (prop_id) { + case ARG_PREFER_V1: + g_value_set_boolean (value, id3demux->prefer_v1); + break; + default: + G_OBJECT_WARN_INVALID_PROPERTY_ID (object, prop_id, pspec); + break; + } +} + +static gboolean +id3demux_get_upstream_size (GstID3Demux * id3demux) +{ + GstQuery *query; + GstPad *peer = NULL; + GstFormat format; + gint64 result; + gboolean res = FALSE; + + /* Short-cut if we already queried upstream */ + if (id3demux->upstream_size > 0) + return TRUE; + + if ((peer = gst_pad_get_peer (id3demux->sinkpad)) == NULL) + return FALSE; + + query = gst_query_new_duration (GST_FORMAT_BYTES); + gst_query_set_duration (query, GST_FORMAT_BYTES, -1); + + if (!gst_pad_query (peer, query)) + goto out; + + gst_query_parse_duration (query, &format, &result); + + if (format != GST_FORMAT_BYTES || result == -1) + goto out; + + id3demux->upstream_size = result; + res = TRUE; + +out: + gst_object_unref (peer); + return res; +} + +static gboolean +gst_id3demux_srcpad_event (GstPad * pad, GstEvent * event) +{ + gboolean res = FALSE; + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (pad)); + + /* Handle SEEK events, with adjusted byte offsets and sizes. */ + + switch (GST_EVENT_TYPE (event)) { + case GST_EVENT_SEEK: + { + gdouble rate; + GstFormat format; + GstSeekType cur_type, stop_type; + GstSeekFlags flags; + gint64 cur, stop; + + gst_event_parse_seek (event, &rate, &format, &flags, + &cur_type, &cur, &stop_type, &stop); + + if (format == GST_FORMAT_BYTES && + id3demux->state == GST_ID3DEMUX_STREAMING && + gst_pad_is_linked (id3demux->sinkpad)) { + GstEvent *upstream; + + switch (cur_type) { + case GST_SEEK_TYPE_SET: + cur += id3demux->strip_start; + break; + case GST_SEEK_TYPE_CUR: + break; + case GST_SEEK_TYPE_END: + cur += id3demux->strip_end; + break; + default: + g_assert_not_reached (); + break; + } + switch (stop_type) { + case GST_SEEK_TYPE_SET: + stop += id3demux->strip_start; + break; + case GST_SEEK_TYPE_CUR: + break; + case GST_SEEK_TYPE_END: + stop += id3demux->strip_end; + break; + default: + break; + } + upstream = gst_event_new_seek (rate, format, flags, + cur_type, cur, stop_type, stop); + res = gst_pad_push_event (id3demux->sinkpad, upstream); + } + break; + } + default: + break; + } + + gst_event_unref (event); + return res; +} + +/* Read and interpret any ID3v1 tag when activating in pull_range */ +static gboolean +gst_id3demux_read_id3v1 (GstID3Demux * id3demux, GstTagList ** tags) +{ + GstBuffer *buffer = NULL; + gboolean res = FALSE; + ID3TagsResult tag_res; + GstFlowReturn flow_ret; + guint64 id3v1_offset; + + if (id3demux->upstream_size < ID3V1_TAG_SIZE) + return TRUE; + id3v1_offset = id3demux->upstream_size - ID3V1_TAG_SIZE; + + flow_ret = gst_pad_pull_range (id3demux->sinkpad, id3v1_offset, + ID3V1_TAG_SIZE, &buffer); + if (flow_ret != GST_FLOW_OK) { + GST_DEBUG_OBJECT (id3demux, + "Could not read data from start of file ret=%d", flow_ret); + goto beach; + } + + if (GST_BUFFER_SIZE (buffer) != ID3V1_TAG_SIZE) { + GST_DEBUG_OBJECT (id3demux, + "Only managed to read %u bytes from file - not an ID3 file", + GST_BUFFER_SIZE (buffer)); + goto beach; + } + + tag_res = id3demux_read_id3v1_tag (buffer, &id3demux->strip_end, tags); + if (tag_res == ID3TAGS_READ_TAG) { + GST_DEBUG_OBJECT (id3demux, "Read ID3v1 tag"); + res = TRUE; + } else if (tag_res == ID3TAGS_BROKEN_TAG) { + GST_WARNING_OBJECT (id3demux, "Ignoring broken ID3v1 tag"); + res = TRUE; + } +beach: + if (buffer) + gst_buffer_unref (buffer); + return res; +} + +/* Read and interpret any ID3v2 tag when activating in pull_range */ +static gboolean +gst_id3demux_read_id3v2 (GstID3Demux * id3demux, GstTagList ** tags) +{ + GstBuffer *buffer = NULL; + gboolean res = FALSE; + ID3TagsResult tag_res; + GstFlowReturn flow_ret; + + /* Handle ID3V2 tag. Try with 4kB to start with */ + flow_ret = gst_pad_pull_range (id3demux->sinkpad, 0, 4096, &buffer); + if (flow_ret != GST_FLOW_OK) { + GST_DEBUG_OBJECT (id3demux, + "Could not read data from start of file ret=%d", flow_ret); + goto beach; + } + + if (GST_BUFFER_SIZE (buffer) < ID3V2_HDR_SIZE) { + GST_DEBUG_OBJECT (id3demux, + "Only managed to read %u bytes from file - not an ID3 file", + GST_BUFFER_SIZE (buffer)); + goto beach; + } + + tag_res = id3demux_read_id3v2_tag (buffer, &id3demux->strip_start, tags); + if (tag_res == ID3TAGS_MORE_DATA) { + /* Need more data to interpret the tag */ + if (buffer) { + gst_buffer_unref (buffer); + buffer = NULL; + } + g_assert (id3demux->strip_start > ID3V2_HDR_SIZE); + + GST_DEBUG_OBJECT (id3demux, "Reading %u bytes to decode ID3v2", + id3demux->strip_start); + flow_ret = gst_pad_pull_range (id3demux->sinkpad, 0, id3demux->strip_start, + &buffer); + if (flow_ret != GST_FLOW_OK) { + GST_DEBUG_OBJECT (id3demux, + "Could not read data from start of file ret=%d", flow_ret); + goto beach; + } + tag_res = id3demux_read_id3v2_tag (buffer, &id3demux->strip_start, tags); + } + + if (tag_res == ID3TAGS_READ_TAG) { + res = TRUE; + GST_DEBUG_OBJECT (id3demux, "Read ID3v2 tag of size %d", + id3demux->strip_start); + } else if (tag_res == ID3TAGS_BROKEN_TAG) { + res = TRUE; + GST_WARNING_OBJECT (id3demux, "Ignoring broken ID3v2 tag of size %d", + id3demux->strip_start); + } +beach: + if (buffer) + gst_buffer_unref (buffer); + return res; +} + +/* This function operates similarly to gst_type_find_element_activate + * in the typefind element + * 1. try to activate in pull mode. if not, switch to push and succeed. + * 2. try to read tags in pull mode + * 3. typefind the contents + * 4. deactivate pull mode. + * 5. if we didn't find any caps, fail. + * 6. Add the srcpad + * 7. if the sink pad is activated, we are in pull mode. succeed. + * otherwise activate both pads in push mode and succeed. + */ +static gboolean +gst_id3demux_sink_activate (GstPad * sinkpad) +{ + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (sinkpad)); + gboolean ret = FALSE; + GstBuffer *buf = NULL; + GstCaps *caps = NULL; + GstFlowReturn flow_ret; + + /* 1: */ + /* If we can activate pull_range upstream, then read any ID3v1 and ID3v2 + * tags, otherwise activate in push mode and the chain function will + * collect buffers, read the ID3v2 tag and output a buffer to end + * preroll. + */ + if (!gst_pad_check_pull_range (sinkpad) || + !gst_pad_activate_pull (sinkpad, TRUE)) { + GST_DEBUG_OBJECT (id3demux, + "No pull mode. Changing to push, but won't be able to read ID3v1 tags"); + id3demux->state = GST_ID3DEMUX_READID3V2; + return gst_pad_activate_push (sinkpad, TRUE); + } + + /* Look for tags at start and end of file */ + GST_DEBUG_OBJECT (id3demux, "Activated pull mode. Looking for tags"); + if (!id3demux_get_upstream_size (id3demux)) + return FALSE; + + id3demux->strip_start = 0; + id3demux->strip_end = 0; + + + if (id3demux->prefer_v1) { + if (!gst_id3demux_read_id3v2 (id3demux, &(id3demux->parsed_tags))) + return FALSE; + if (!gst_id3demux_read_id3v1 (id3demux, &(id3demux->parsed_tags))) + return FALSE; + } else { + if (!gst_id3demux_read_id3v1 (id3demux, &(id3demux->parsed_tags))) + return FALSE; + if (!gst_id3demux_read_id3v2 (id3demux, &(id3demux->parsed_tags))) + return FALSE; + } + if (id3demux->parsed_tags != NULL) { + id3demux->send_tag_event = TRUE; + } + + flow_ret = + gst_id3demux_read_range (id3demux, 0, ID3_TYPE_FIND_MAX_SIZE, &buf); + if (flow_ret != GST_FLOW_OK) { + GST_DEBUG_OBJECT (id3demux, "Could not read data from start of file ret=%d", + flow_ret); + goto done_activate; + } + + caps = gst_id3demux_do_typefind (id3demux, buf); + gst_buffer_unref (buf); + buf = NULL; + + /* 4 - Deactivate pull mode */ + if (!gst_pad_activate_pull (sinkpad, FALSE)) { + if (caps) + gst_caps_unref (caps); + GST_DEBUG_OBJECT (id3demux, + "Could not deactivate sinkpad after reading tags"); + return FALSE; + } + + /* 5 - If we didn't find the caps, fail */ + if (caps == NULL) { + GST_DEBUG_OBJECT (id3demux, "Could not detect type of contents"); + goto done_activate; + } + + /* tag reading and typefinding were already done, don't do them again in + the chain function if we end up in push mode */ + id3demux->state = GST_ID3DEMUX_STREAMING; + + /* 6 Add the srcpad for output now we know caps. */ + /* add_srcpad takes ownership of the caps */ + if (!gst_id3demux_add_srcpad (id3demux, caps)) { + GST_DEBUG_OBJECT (id3demux, "Could not add source pad"); + goto done_activate; + } + + /* 7 - if the sinkpad is active, it was done by downstream so we're + * done, otherwise switch to push */ + ret = TRUE; + if (!gst_pad_is_active (sinkpad)) { + ret = gst_pad_activate_push (id3demux->srcpad, TRUE); + ret &= gst_pad_activate_push (sinkpad, TRUE); + } + +done_activate: + if (buf) + gst_buffer_unref (buf); + + return ret; +} + +static gboolean +gst_id3demux_src_activate_pull (GstPad * pad, gboolean active) +{ + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (pad)); + + return gst_pad_activate_pull (id3demux->sinkpad, active); +} + +static gboolean +gst_id3demux_src_checkgetrange (GstPad * srcpad) +{ + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (srcpad)); + + return gst_pad_check_pull_range (id3demux->sinkpad); +} + +static GstFlowReturn +gst_id3demux_read_range (GstID3Demux * id3demux, + guint64 offset, guint length, GstBuffer ** buffer) +{ + GstFlowReturn ret; + guint64 in_offset; + guint in_length; + + g_return_val_if_fail (buffer != NULL, GST_FLOW_ERROR); + + /* Adjust offset and length of the request to trim off ID3 information. + * For the returned buffer, adjust the output offset to match what downstream + * should see */ + in_offset = offset + id3demux->strip_start; + + if (!id3demux_get_upstream_size (id3demux)) + return GST_FLOW_ERROR; + + if (in_offset + length >= id3demux->upstream_size - id3demux->strip_end) + in_length = id3demux->upstream_size - id3demux->strip_end - in_offset; + else + in_length = length; + + ret = gst_pad_pull_range (id3demux->sinkpad, in_offset, in_length, buffer); + + if (ret == GST_FLOW_OK && *buffer) { + if (!gst_id3demux_trim_buffer (id3demux, buffer)) + goto error; + } + + return ret; +error: + if (*buffer != NULL) { + gst_buffer_unref (buffer); + *buffer = NULL; + } + return GST_FLOW_ERROR; +} + +static GstFlowReturn +gst_id3demux_src_getrange (GstPad * srcpad, + guint64 offset, guint length, GstBuffer ** buffer) +{ + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (srcpad)); + + if (id3demux->send_tag_event) { + gst_id3demux_send_tag_event (id3demux); + id3demux->send_tag_event = FALSE; + } + return gst_id3demux_read_range (id3demux, offset, length, buffer); +} + +static GstStateChangeReturn +gst_id3demux_change_state (GstElement * element, GstStateChange transition) +{ + GstStateChangeReturn ret; + GstID3Demux *id3demux = GST_ID3DEMUX (element); + + ret = GST_ELEMENT_CLASS (parent_class)->change_state (element, transition); + + switch (transition) { + case GST_STATE_CHANGE_PAUSED_TO_READY: + gst_id3demux_reset (id3demux); + break; + default: + break; + } + return ret; +} + +static gboolean +gst_id3demux_pad_query (GstPad * pad, GstQuery * query) +{ + /* For a position or duration query, adjust the returned + * bytes to strip off the id3v1 and id3v2 areas */ + + GstID3Demux *id3demux = GST_ID3DEMUX (GST_PAD_PARENT (pad)); + GstPad *peer = NULL; + GstFormat format; + gint64 result; + + if ((peer = gst_pad_get_peer (id3demux->sinkpad)) == NULL) + return FALSE; + + if (!gst_pad_query (peer, query)) { + gst_object_unref (peer); + return FALSE; + } + + gst_object_unref (peer); + + switch (GST_QUERY_TYPE (query)) { + case GST_QUERY_POSITION: + { + gst_query_parse_position (query, &format, &result); + if (format == GST_FORMAT_BYTES) { + result -= id3demux->strip_start; + gst_query_set_position (query, format, result); + } + break; + } + case GST_QUERY_DURATION: + { + gst_query_parse_duration (query, &format, &result); + if (format == GST_FORMAT_BYTES) { + result -= id3demux->strip_start + id3demux->strip_end; + gst_query_set_duration (query, format, result); + } + break; + } + default: + break; + } + + return TRUE; +} + +static const GstQueryType * +gst_id3demux_get_query_types (GstPad * pad) +{ + static const GstQueryType types[] = { + GST_QUERY_POSITION, + GST_QUERY_DURATION, + 0 + }; + + return types; +} + +typedef struct +{ + guint best_probability; + GstCaps *caps; + GstBuffer *buffer; +} + +SimpleTypeFind; +guint8 * +simple_find_peek (gpointer data, gint64 offset, guint size) +{ + SimpleTypeFind *find = (SimpleTypeFind *) data; + + if (offset < 0) + return NULL; + + if (GST_BUFFER_SIZE (find->buffer) >= offset + size) { + return GST_BUFFER_DATA (find->buffer) + offset; + } + return NULL; +} +static void +simple_find_suggest (gpointer data, guint probability, const GstCaps * caps) +{ + SimpleTypeFind *find = (SimpleTypeFind *) data; + + if (probability > find->best_probability) { + GstCaps *copy = gst_caps_copy (caps); + + gst_caps_replace (&find->caps, copy); + gst_caps_unref (copy); + find->best_probability = probability; + } +} + +static GstCaps * +gst_id3demux_do_typefind (GstID3Demux * id3demux, GstBuffer * buffer) +{ + GList *walk, *type_list; + SimpleTypeFind find; + GstTypeFind gst_find; + + walk = type_list = gst_type_find_factory_get_list (); + + find.buffer = buffer; + find.best_probability = 0; + find.caps = NULL; + gst_find.data = &find; + gst_find.peek = simple_find_peek; + gst_find.get_length = NULL; + gst_find.suggest = simple_find_suggest; + while (walk) { + GstTypeFindFactory *factory = GST_TYPE_FIND_FACTORY (walk->data); + + gst_type_find_factory_call_function (factory, &gst_find); + if (find.best_probability >= GST_TYPE_FIND_MAXIMUM) + break; + walk = g_list_next (walk); + } + gst_plugin_feature_list_free (type_list); + if (find.best_probability > 0) { + GST_DEBUG ("Found caps %" GST_PTR_FORMAT " with buf size %u", find.caps, + GST_BUFFER_SIZE (buffer)); + return find.caps; + } + + return NULL; +} + +static void +gst_id3demux_send_tag_event (GstID3Demux * id3demux) +{ + /* FIXME: what's the correct merge mode? Docs need to tell... */ + GstTagList *merged = gst_tag_list_merge (id3demux->event_tags, + id3demux->parsed_tags, GST_TAG_MERGE_KEEP); + + if (id3demux->parsed_tags) + gst_element_post_message (GST_ELEMENT (id3demux), + gst_message_new_tag (GST_OBJECT (id3demux), + gst_tag_list_copy (id3demux->parsed_tags))); + + if (merged) { + GstEvent *event = gst_event_new_tag (merged); + + GST_EVENT_TIMESTAMP (event) = 0; + GST_DEBUG_OBJECT (id3demux, "Sending tag event on src pad"); + gst_pad_push_event (id3demux->srcpad, event); + } +} + +static gboolean +plugin_init (GstPlugin * plugin) +{ + GST_DEBUG_CATEGORY_INIT (id3demux_debug, "id3demux", 0, + "GStreamer ID3 tag demuxer"); + + return gst_element_register (plugin, "id3demux", + GST_RANK_PRIMARY, GST_TYPE_ID3DEMUX); +} + +GST_PLUGIN_DEFINE (GST_VERSION_MAJOR, + GST_VERSION_MINOR, + "id3demux", + "Demux ID3v1 and ID3v2 tags from a file", + plugin_init, VERSION, GST_LICENSE, GST_PACKAGE_NAME, GST_PACKAGE_ORIGIN) diff --git a/gst/id3demux/gstid3demux.h b/gst/id3demux/gstid3demux.h new file mode 100644 index 00000000..46ae6f1e --- /dev/null +++ b/gst/id3demux/gstid3demux.h @@ -0,0 +1,79 @@ +/* Copyright 2005 Jan Schmidt <thaytan@mad.scientist.com> + * Copyright (C) 2003-2004 Benjamin Otte <otte@gnome.org> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with this library; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +#ifndef __GST_ID3DEMUX_H__ +#define __GST_ID3DEMUX_H__ + +#include <gst/gst.h> + +G_BEGIN_DECLS + +#define GST_TYPE_ID3DEMUX \ + (gst_gst_id3demux_get_type()) +#define GST_ID3DEMUX(obj) \ + (G_TYPE_CHECK_INSTANCE_CAST((obj),GST_TYPE_ID3DEMUX,GstID3Demux)) +#define GST_ID3DEMUX_CLASS(klass) \ + (G_TYPE_CHECK_CLASS_CAST((klass),GST_TYPE_ID3DEMUX,GstID3Demux)) +#define GST_IS_ID3DEMUX(obj) \ + (G_TYPE_CHECK_INSTANCE_TYPE((obj),GST_TYPE_ID3DEMUX)) +#define GST_IS_ID3DEMUX_CLASS(obj) \ + (G_TYPE_CHECK_CLASS_TYPE((klass),GST_TYPE_ID3DEMUX)) + +typedef struct _GstID3Demux GstID3Demux; +typedef struct _GstID3DemuxClass GstID3DemuxClass; + +typedef enum { + GST_ID3DEMUX_READID3V2, + GST_ID3DEMUX_TYPEFINDING, + GST_ID3DEMUX_STREAMING +} GstID3DemuxState; + +struct _GstID3Demux +{ + GstElement element; + + GstPad *sinkpad, *srcpad; + + /* Number of bytes to remove from the start of file (ID3v2) */ + guint strip_start; + /* Number of bytes to remove from the end of file (ID3v1) */ + guint strip_end; + + gint64 upstream_size; + + GstID3DemuxState state; + GstBuffer *collect; + GstCaps *src_caps; + + gboolean prefer_v1; + GstTagList *event_tags; + GstTagList *parsed_tags; + gboolean send_tag_event; +}; + +struct _GstID3DemuxClass +{ + GstElementClass parent_class; +}; + +GType gst_gst_id3demux_get_type (void); + +G_END_DECLS + +#endif /* __GST_ID3DEMUX_H__ */ diff --git a/gst/id3demux/id3tags.c b/gst/id3demux/id3tags.c new file mode 100644 index 00000000..1cc8c14e --- /dev/null +++ b/gst/id3demux/id3tags.c @@ -0,0 +1,431 @@ +/* -*- Mode: C; tab-width: 2; indent-tabs-mode: t; c-basic-offset: 2 -*- */ +/* Copyright 2005 Jan Schmidt <thaytan@mad.scientist.com> + * Copyright 2002,2003 Scott Wheeler <wheeler@kde.org> (portions from taglib) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with this library; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include <string.h> +#include <gst/tag/tag.h> + +#include "id3tags.h" + +GST_DEBUG_CATEGORY_EXTERN (id3demux_debug); +#define GST_CAT_DEFAULT (id3demux_debug) + +#define HANDLE_INVALID_SYNCSAFE +static ID3TagsResult +id3demux_id3v2_frames_to_tag_list (ID3TagsWorking * work, guint size); + +guint +read_synch_uint (guint8 * data, guint size) +{ + gint i; + guint result = 0; + gint invalid = 0; + + g_assert (size <= 4); + + size--; + for (i = 0; i <= size; i++) { + invalid |= data[i] & 0x80; + result |= (data[i] & 0x7f) << ((size - i) * 7); + } + +#ifdef HANDLE_INVALID_SYNCSAFE + if (invalid) { + GST_WARNING ("Invalid synch-safe integer in ID3v2 frame " + "- using the actual value instead"); + result = 0; + for (i = 0; i <= size; i++) { + result |= data[i] << ((size - i) * 8); + } + } +#endif + return result; +} + +ID3TagsResult +id3demux_read_id3v1_tag (GstBuffer * buffer, guint * id3v1_size, + GstTagList ** tags) +{ + GstTagList *new_tags; + + guint8 *data; + + g_return_val_if_fail (buffer != NULL, ID3TAGS_V1_BAD_SIZE); + + data = GST_BUFFER_DATA (buffer); + + if (GST_BUFFER_SIZE (buffer) != ID3V1_TAG_SIZE) + return ID3TAGS_V1_BAD_SIZE; + + /* Check that buffer starts with 'TAG' */ + if (data[0] != 'T' || data[1] != 'A' || data[2] != 'G') { + if (id3v1_size) + *id3v1_size = 0; + GST_DEBUG ("No ID3v1 tag in data"); + return ID3TAGS_READ_TAG; + } + + g_return_val_if_fail (tags != NULL, ID3TAGS_READ_TAG); + + new_tags = gst_tag_list_new_from_id3v1 (GST_BUFFER_DATA (buffer)); + if (new_tags == NULL) + return ID3TAGS_BROKEN_TAG; + + if (*tags) { + GstTagList *merged; + + merged = gst_tag_list_merge (*tags, new_tags, GST_TAG_MERGE_REPLACE); + gst_tag_list_free (*tags); + gst_tag_list_free (new_tags); + *tags = merged; + } else + *tags = new_tags; + + return ID3TAGS_READ_TAG; +} + +ID3TagsResult +id3demux_read_id3v2_tag (GstBuffer * buffer, guint * id3v2_size, + GstTagList ** tags) +{ + guint8 *data; + guint read_size; + ID3TagsWorking work; + guint8 flags; + ID3TagsResult result; + guint16 version; + + g_return_val_if_fail (buffer != NULL, ID3TAGS_MORE_DATA); + + if (GST_BUFFER_SIZE (buffer) < ID3V2_MARK_SIZE) + return ID3TAGS_MORE_DATA; /* Need more data to decide with */ + + data = GST_BUFFER_DATA (buffer); + + /* Check for 'ID3' string at start of buffer */ + if (data[0] != 'I' || data[1] != 'D' || data[2] != '3') { + if (id3v2_size) + *id3v2_size = 0; + GST_DEBUG ("No ID3v2 tag in data"); + return ID3TAGS_READ_TAG; + } + + /* OK, get enough data to read the entire header */ + if (GST_BUFFER_SIZE (buffer) < ID3V2_HDR_SIZE) + return ID3TAGS_MORE_DATA; /* Need more data to decide with */ + + /* Read the version */ + version = GST_READ_UINT16_BE (data + 3); + + /* Read the flags */ + flags = data[5]; + + /* Read the size from the header */ + read_size = read_synch_uint (data + 6, 4); + if (read_size == 0) { + return ID3TAGS_BROKEN_TAG; + } + read_size += 10; + + /* Expand the read size to include a footer if there is one */ + if (flags & ID3V2_HDR_FLAG_FOOTER) { + read_size += 10; + } + + if (id3v2_size) + *id3v2_size = read_size; + + /* Validate the version. At the moment, we only support up to 2.4.0 */ + if (ID3V2_VER_MAJOR (version) > 4 || ID3V2_VER_MINOR (version) > 0) { + GST_WARNING ("ID3v2 tag is from revision 2.%d.%d, " + "but decoder only supports 2.%d.%d. Ignoring as per spec.", + version >> 8, version & 0xff, ID3V2_VERSION >> 8, ID3V2_VERSION & 0xff); + return ID3TAGS_READ_TAG; + } + GST_DEBUG ("ID3v2 tag with revision 2.%d.%d\n", version >> 8, version & 0xff); + + if (GST_BUFFER_SIZE (buffer) < read_size) + return ID3TAGS_MORE_DATA; /* Need more data to decode with */ + + g_return_val_if_fail (tags != NULL, ID3TAGS_READ_TAG); + + memset (&work, 0, sizeof (ID3TagsWorking)); + work.buffer = buffer; + work.hdr.version = version; + work.hdr.size = read_size; + work.hdr.flags = flags; + work.hdr.frame_data = GST_BUFFER_DATA (buffer) + ID3V2_HDR_SIZE; + if (flags & ID3V2_HDR_FLAG_FOOTER) + work.hdr.frame_data_size = read_size - ID3V2_HDR_SIZE - 10; + else + work.hdr.frame_data_size = read_size - ID3V2_HDR_SIZE; + + result = id3demux_id3v2_frames_to_tag_list (&work, read_size); + + /* Actually read the tags */ + if (work.tags != NULL) { + if (*tags) { + GstTagList *merged; + + merged = gst_tag_list_merge (*tags, work.tags, GST_TAG_MERGE_REPLACE); + gst_tag_list_free (*tags); + gst_tag_list_free (work.tags); + *tags = merged; + } else + *tags = work.tags; + } + + return result; +} + +static guint +id3demux_id3v2_frame_hdr_size (guint id3v2ver) +{ + /* ID3v2 < 2.3.0 only had 6 byte header */ + switch (ID3V2_VER_MAJOR (id3v2ver)) { + case 0: + case 1: + case 2: + return 6; + case 3: + case 4: + default: + return 10; + } +} + +static const gchar *obsolete_frame_ids[] = { + "CRM", "EQU", "LNK", "RVA", "TIM", "TSI", /* From 2.2 */ + "EQUA", "RVAD", "TIME", "TRDA", "TSIZ", /* From 2.3 */ + NULL +}; + +const struct ID3v2FrameIDConvert +{ + gchar *orig; + gchar *new; +} frame_id_conversions[] = { + /* 2.3.x frames */ + { + "TDAT", "TDRC"}, { + "TORY", "TDOR"}, { + "TYER", "TDRC"}, + /* 2.2.x frames */ + { + "BUF", "RBUF"}, { + "CNT", "PCNT"}, { + "COM", "COMM"}, { + "CRA", "AENC"}, { + "ETC", "ETCO"}, { + "GEO", "GEOB"}, { + "IPL", "TIPL"}, { + "MCI", "MCDI"}, { + "MLL", "MLLT"}, { + "PIC", "APIC"}, { + "POP", "POPM"}, { + "REV", "RVRB"}, { + "SLT", "SYLT"}, { + "STC", "SYTC"}, { + "TAL", "TALB"}, { + "TBP", "TBPM"}, { + "TCM", "TCOM"}, { + "TCR", "TCOP"}, { + "TDA", "TDRC"}, { + "TDY", "TDLY"}, { + "TEN", "TENC"}, { + "TFT", "TFLT"}, { + "TKE", "TKEY"}, { + "TLA", "TLAN"}, { + "TLE", "TLEN"}, { + "TMT", "TMED"}, { + "TOA", "TOAL"}, { + "TOF", "TOFN"}, { + "TOL", "TOLY"}, { + "TOR", "TDOR"}, { + "TOT", "TOAL"}, { + "TP1", "TPE1"}, { + "TP2", "TPE2"}, { + "TP3", "TPE3"}, { + "TP4", "TPE4"}, { + "TPA", "TPOS"}, { + "TPB", "TPUB"}, { + "TRC", "TSRC"}, { + "TRD", "TDRC"}, { + "TRK", "TRCK"}, { + "TSS", "TSSE"}, { + "TT1", "TIT1"}, { + "TT2", "TIT2"}, { + "TT3", "TIT3"}, { + "TXT", "TOLY"}, { + "TXX", "TXXX"}, { + "TYE", "TDRC"}, { + "UFI", "UFID"}, { + "ULT", "USLT"}, { + "WAF", "WOAF"}, { + "WAR", "WOAR"}, { + "WAS", "WOAS"}, { + "WCM", "WCOM"}, { + "WCP", "WCOP"}, { + "WPB", "WPUB"}, { + "WXX", "WXXX"}, { + NULL, NULL} +}; + +static gboolean +convert_fid_to_v240 (gchar * frame_id) +{ + gint i = 0; + + while (obsolete_frame_ids[i] != NULL) { + if (strncmp (frame_id, obsolete_frame_ids[i], 5) == 0) + return TRUE; + i++; + } + + i = 0; + while (frame_id_conversions[i].orig != NULL) { + if (strncmp (frame_id, frame_id_conversions[i].orig, 5) == 0) { + strcpy (frame_id, frame_id_conversions[i].new); + return FALSE; + } + i++; + } + return FALSE; +} + +static ID3TagsResult +id3demux_id3v2_frames_to_tag_list (ID3TagsWorking * work, guint size) +{ + guint frame_hdr_size; + gboolean read_a_frame = FALSE; + guint8 *start; + + /* Extended header if present */ + if (work->hdr.flags & ID3V2_HDR_FLAG_EXTHDR) { + work->hdr.ext_hdr_size = read_synch_uint (work->hdr.frame_data, 4); + if (work->hdr.ext_hdr_size < 6 || + (work->hdr.ext_hdr_size) > work->hdr.frame_data_size) { + return ID3TAGS_BROKEN_TAG; + } + work->hdr.ext_flag_bytes = work->hdr.frame_data[4]; + if (5 + work->hdr.ext_flag_bytes > work->hdr.frame_data_size) { + GST_DEBUG + ("Tag claims extended header, but doesn't have enough bytes. Broken tag"); + return ID3TAGS_BROKEN_TAG; + } + + work->hdr.ext_flag_data = work->hdr.frame_data + 5; + work->hdr.frame_data += work->hdr.ext_hdr_size; + work->hdr.frame_data_size -= work->hdr.ext_hdr_size; + } + + start = GST_BUFFER_DATA (work->buffer); + frame_hdr_size = id3demux_id3v2_frame_hdr_size (work->hdr.version); + if (work->hdr.frame_data_size <= frame_hdr_size) { + GST_DEBUG ("Tag has no data frames. Broken tag"); + return ID3TAGS_BROKEN_TAG; /* Must have at least one frame */ + } + + work->tags = gst_tag_list_new (); + g_return_val_if_fail (work->tags != NULL, ID3TAGS_READ_TAG); + + while (work->hdr.frame_data_size > frame_hdr_size) { + guint frame_size = 0; + gchar frame_id[5] = ""; + guint16 frame_flags = 0x0; + gboolean obsolete_id = FALSE; + + /* Read the header */ + switch (ID3V2_VER_MAJOR (work->hdr.version)) { + case 0: + case 1: + case 2: + frame_id[0] = work->hdr.frame_data[0]; + frame_id[1] = work->hdr.frame_data[1]; + frame_id[2] = work->hdr.frame_data[2]; + frame_id[3] = 0; + frame_id[4] = 0; + obsolete_id = convert_fid_to_v240 (frame_id); + + frame_size = read_synch_uint (work->hdr.frame_data + 3, 3); + frame_flags = 0; + break; + case 3: + case 4: + default: + frame_id[0] = work->hdr.frame_data[0]; + frame_id[1] = work->hdr.frame_data[1]; + frame_id[2] = work->hdr.frame_data[2]; + frame_id[3] = work->hdr.frame_data[3]; + frame_id[4] = 0; + frame_size = read_synch_uint (work->hdr.frame_data + 4, 4); + frame_flags = GST_READ_UINT16_BE (work->hdr.frame_data + 8); + + if (ID3V2_VER_MAJOR (work->hdr.version) == 3) { + frame_flags &= ID3V2_3_FRAME_FLAGS_MASK; + obsolete_id = convert_fid_to_v240 (frame_id); + } + break; + } + + work->hdr.frame_data += frame_hdr_size; + work->hdr.frame_data_size -= frame_hdr_size; + + if (frame_size > work->hdr.frame_data_size || + frame_size == 0 || strcmp (frame_id, "") == 0) + break; /* No more frames to read */ + +#if 0 + g_print + ("Frame @ %d (0x%02x) id %s size %d, next=%d (0x%02x) obsolete=%d\n", + work->hdr.frame_data - start, work->hdr.frame_data - start, frame_id, + frame_size, work->hdr.frame_data + frame_hdr_size + frame_size - start, + work->hdr.frame_data + frame_hdr_size + frame_size - start, + obsolete_id); +#endif + + if (!obsolete_id) { + /* Now, read, decompress etc the contents of the frame + * into a TagList entry */ + work->cur_frame_size = frame_size; + work->frame_id = frame_id; + work->frame_flags = frame_flags; + + if (id3demux_id3v2_parse_frame (work)) { + read_a_frame = TRUE; + GST_LOG ("Extracted frame with id %s", frame_id); + } + } + work->hdr.frame_data += frame_size; + work->hdr.frame_data_size -= frame_size; + } + + if (!read_a_frame) { + GST_DEBUG ("Could not extract any frames from tag. Broken tag"); + gst_tag_list_free (work->tags); + work->tags = NULL; + return ID3TAGS_BROKEN_TAG; + } + + return ID3TAGS_READ_TAG; +} diff --git a/gst/id3demux/id3tags.h b/gst/id3demux/id3tags.h new file mode 100644 index 00000000..c81cd550 --- /dev/null +++ b/gst/id3demux/id3tags.h @@ -0,0 +1,112 @@ +/* Copyright 2005 Jan Schmidt <thaytan@mad.scientist.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with this library; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +#ifndef __ID3TAGS_H__ +#define __ID3TAGS_H__ + +#include <gst/gst.h> + +G_BEGIN_DECLS + +#define ID3V1_TAG_SIZE 128 +#define ID3V2_MARK_SIZE 3 +#define ID3V2_HDR_SIZE 10 + +typedef enum { + ID3TAGS_V1_BAD_SIZE, + ID3TAGS_MORE_DATA, + ID3TAGS_READ_TAG, + ID3TAGS_BROKEN_TAG +} ID3TagsResult; + +/* From id3tags.c */ +ID3TagsResult id3demux_read_id3v1_tag (GstBuffer *buffer, guint *id3v1_size, + GstTagList **tags); +ID3TagsResult id3demux_read_id3v2_tag (GstBuffer *buffer, guint *id3v2_size, + GstTagList **tags); +G_END_DECLS + +/* Things shared by id3tags.c and id3v2frames.c */ +#define ID3V2_VERSION 0x0400 +#define ID3V2_VER_MAJOR(v) ((v) >> 8) +#define ID3V2_VER_MINOR(v) ((v) & 0xff) + +typedef struct { + guint16 version; + guint8 flags; + guint32 size; + + guint8 *frame_data; + guint32 frame_data_size; + + guint32 ext_hdr_size; + guint8 ext_flag_bytes; + guint8 *ext_flag_data; +} ID3v2Header; + +typedef struct { + ID3v2Header hdr; + + GstBuffer *buffer; + GstTagList *tags; + + /* Current frame decoding */ + guint cur_frame_size; + gchar *frame_id; + guint16 frame_flags; + + guint8 *parse_data; + guint parse_size; +} ID3TagsWorking; + +enum { + ID3V2_HDR_FLAG_UNSYNC = 0x80, + ID3V2_HDR_FLAG_EXTHDR = 0x40, + ID3V2_HDR_FLAG_EXPERIMENTAL = 0x20, + ID3V2_HDR_FLAG_FOOTER = 0x10 +}; + +enum { + ID3V2_EXT_FLAG_UPDATE = 0x80, + ID3V2_EXT_FLAG_CRC = 0x40, + ID3V2_EXT_FLAG_RESTRICTED = 0x20 +}; + +enum { + ID3V2_FRAME_STATUS_FRAME_ALTER_PRESERVE = 0x4000, + ID3V2_FRAME_STATUS_FILE_ALTER_PRESERVE = 0x2000, + ID3V2_FRAME_STATUS_READONLY = 0x1000, + ID3V2_FRAME_FORMAT_GROUPING_ID = 0x0040, + ID3V2_FRAME_FORMAT_COMPRESSION = 0x0008, + ID3V2_FRAME_FORMAT_ENCRYPTION = 0x0004, + ID3V2_FRAME_FORMAT_UNSYNCHRONISATION = 0x0002, + ID3V2_FRAME_FORMAT_DATA_LENGTH_INDICATOR = 0x0001 +}; + +#define ID3V2_3_FRAME_FLAGS_MASK \ + (ID3V2_FRAME_STATUS_FRAME_ALTER_PRESERVE | \ + ID3V2_FRAME_STATUS_FILE_ALTER_PRESERVE | \ + ID3V2_FRAME_STATUS_READONLY | \ + ID3V2_FRAME_FORMAT_GROUPING_ID | \ + ID3V2_FRAME_FORMAT_COMPRESSION | \ + ID3V2_FRAME_FORMAT_ENCRYPTION) + +/* From id3v2frames.c */ +gboolean id3demux_id3v2_parse_frame (ID3TagsWorking *work); + +#endif diff --git a/gst/id3demux/id3v2.4.0-frames.txt b/gst/id3demux/id3v2.4.0-frames.txt new file mode 100644 index 00000000..74a21bed --- /dev/null +++ b/gst/id3demux/id3v2.4.0-frames.txt @@ -0,0 +1,1734 @@ +$Id$ + +Informal standard M. Nilsson +Document: id3v2.4.0-frames.txt 1st November 2000 + + + ID3 tag version 2.4.0 - Native Frames + +Status of this document + + This document is an informal standard and replaces the ID3v2.3.0 + standard [ID3v2]. A formal standard will use another revision number + even if the content is identical to document. The contents in this + document may change for clarifications but never for added or altered + functionallity. + + Distribution of this document is unlimited. + + +Abstract + + This document describes the frames natively supported by ID3v2.4.0, + which is a revised version of the ID3v2 informal standard [ID3v2.3.0] + version 2.3.0. The ID3v2 offers a flexible way of storing audio meta + information within audio file itself. The information may be + technical information, such as equalisation curves, as well as title, + performer, copyright etc. + + ID3v2.4.0 is meant to be as close as possible to ID3v2.3.0 in order + to allow for implementations to be revised as easily as possible. + + +1. Table of contents + + 2. Conventions in this document + 3. Default flags + 4. Declared ID3v2 frames + 4.1. Unique file identifier + 4.2. Text information frames + 4.2.1. Identification frames + 4.2.2. Involved persons frames + 4.2.3. Derived and subjective properties frames + 4.2.4. Rights and license frames + 4.2.5. Other text frames + 4.2.6. User defined text information frame + 4.3. URL link frames + 4.3.1. URL link frames - details + 4.3.2. User defined URL link frame + 4.4. Music CD Identifier + 4.5. Event timing codes + 4.6. MPEG location lookup table + 4.7. Synced tempo codes + 4.8. Unsynchronised lyrics/text transcription + 4.9. Synchronised lyrics/text + 4.10. Comments + 4.11. Relative volume adjustment (2) + 4.12. Equalisation (2) + 4.13. Reverb + 4.14. Attached picture + 4.15. General encapsulated object + 4.16. Play counter + 4.17. Popularimeter + 4.18. Recommended buffer size + 4.19. Audio encryption + 4.20. Linked information + 4.21. Position synchronisation frame + 4.22. Terms of use + 4.23. Ownership frame + 4.24. Commercial frame + 4.25. Encryption method registration + 4.26. Group identification registration + 4.27. Private frame + 4.28. Signature frame + 4.29. Seek frame + 4.30. Audio seek point index + 5. Copyright + 6. References + 7. Appendix + A. Appendix A - Genre List from ID3v1 + 8. Author's Address + + +2. Conventions in this document + + Text within "" is a text string exactly as it appears in a tag. + Numbers preceded with $ are hexadecimal and numbers preceded with % + are binary. $xx is used to indicate a byte with unknown content. %x + is used to indicate a bit with unknown content. The most significant + bit (MSB) of a byte is called 'bit 7' and the least significant bit + (LSB) is called 'bit 0'. + + A tag is the whole tag described the ID3v2 main structure document + [ID3v2-strct]. A frame is a block of information in the tag. The tag + consists of a header, frames and optional padding. A field is a piece + of information; one value, a string etc. A numeric string is a string + that consists of the characters "0123456789" only. + + The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", + "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this + document are to be interpreted as described in RFC 2119 [KEYWORDS]. + + +3. Default flags + + The default settings for the frames described in this document can be + divided into the following classes. The flags may be set differently + if found more suitable by the software. + + 1. Discarded if tag is altered, discarded if file is altered. + + None. + + 2. Discarded if tag is altered, preserved if file is altered. + + None. + + 3. Preserved if tag is altered, discarded if file is altered. + + ASPI, AENC, ETCO, EQU2, MLLT, POSS, SEEK, SYLT, SYTC, RVA2, TENC, + TLEN + + 4. Preserved if tag is altered, preserved if file is altered. + + The rest of the frames. + + +4. Declared ID3v2 frames + + The following frames are declared in this draft. + + 4.19 AENC Audio encryption + 4.14 APIC Attached picture + 4.30 ASPI Audio seek point index + + 4.10 COMM Comments + 4.24 COMR Commercial frame + + 4.25 ENCR Encryption method registration + 4.12 EQU2 Equalisation (2) + 4.5 ETCO Event timing codes + + 4.15 GEOB General encapsulated object + 4.26 GRID Group identification registration + + 4.20 LINK Linked information + + 4.4 MCDI Music CD identifier + 4.6 MLLT MPEG location lookup table + + 4.23 OWNE Ownership frame + + 4.27 PRIV Private frame + 4.16 PCNT Play counter + 4.17 POPM Popularimeter + 4.21 POSS Position synchronisation frame + + 4.18 RBUF Recommended buffer size + 4.11 RVA2 Relative volume adjustment (2) + 4.13 RVRB Reverb + + 4.29 SEEK Seek frame + 4.28 SIGN Signature frame + 4.9 SYLT Synchronised lyric/text + 4.7 SYTC Synchronised tempo codes + + 4.2.1 TALB Album/Movie/Show title + 4.2.3 TBPM BPM (beats per minute) + 4.2.2 TCOM Composer + 4.2.3 TCON Content type + 4.2.4 TCOP Copyright message + 4.2.5 TDEN Encoding time + 4.2.5 TDLY Playlist delay + 4.2.5 TDOR Original release time + 4.2.5 TDRC Recording time + 4.2.5 TDRL Release time + 4.2.5 TDTG Tagging time + 4.2.2 TENC Encoded by + 4.2.2 TEXT Lyricist/Text writer + 4.2.3 TFLT File type + 4.2.2 TIPL Involved people list + 4.2.1 TIT1 Content group description + 4.2.1 TIT2 Title/songname/content description + 4.2.1 TIT3 Subtitle/Description refinement + 4.2.3 TKEY Initial key + 4.2.3 TLAN Language(s) + 4.2.3 TLEN Length + 4.2.2 TMCL Musician credits list + 4.2.3 TMED Media type + 4.2.3 TMOO Mood + 4.2.1 TOAL Original album/movie/show title + 4.2.5 TOFN Original filename + 4.2.2 TOLY Original lyricist(s)/text writer(s) + 4.2.2 TOPE Original artist(s)/performer(s) + 4.2.4 TOWN File owner/licensee + 4.2.2 TPE1 Lead performer(s)/Soloist(s) + 4.2.2 TPE2 Band/orchestra/accompaniment + 4.2.2 TPE3 Conductor/performer refinement + 4.2.2 TPE4 Interpreted, remixed, or otherwise modified by + 4.2.1 TPOS Part of a set + 4.2.4 TPRO Produced notice + 4.2.4 TPUB Publisher + 4.2.1 TRCK Track number/Position in set + 4.2.4 TRSN Internet radio station name + 4.2.4 TRSO Internet radio station owner + 4.2.5 TSOA Album sort order + 4.2.5 TSOP Performer sort order + 4.2.5 TSOT Title sort order + 4.2.1 TSRC ISRC (international standard recording code) + 4.2.5 TSSE Software/Hardware and settings used for encoding + 4.2.1 TSST Set subtitle + 4.2.2 TXXX User defined text information frame + + 4.1 UFID Unique file identifier + 4.22 USER Terms of use + 4.8 USLT Unsynchronised lyric/text transcription + + 4.3.1 WCOM Commercial information + 4.3.1 WCOP Copyright/Legal information + 4.3.1 WOAF Official audio file webpage + 4.3.1 WOAR Official artist/performer webpage + 4.3.1 WOAS Official audio source webpage + 4.3.1 WORS Official Internet radio station homepage + 4.3.1 WPAY Payment + 4.3.1 WPUB Publishers official webpage + 4.3.2 WXXX User defined URL link frame + + +4.1. Unique file identifier + + This frame's purpose is to be able to identify the audio file in a + database, that may provide more information relevant to the content. + Since standardisation of such a database is beyond this document, all + UFID frames begin with an 'owner identifier' field. It is a null- + terminated string with a URL [URL] containing an email address, or a + link to a location where an email address can be found, that belongs + to the organisation responsible for this specific database + implementation. Questions regarding the database should be sent to + the indicated email address. The URL should not be used for the + actual database queries. The string + "http://www.id3.org/dummy/ufid.html" should be used for tests. The + 'Owner identifier' must be non-empty (more than just a termination). + The 'Owner identifier' is then followed by the actual identifier, + which may be up to 64 bytes. There may be more than one "UFID" frame + in a tag, but only one with the same 'Owner identifier'. + + <Header for 'Unique file identifier', ID: "UFID"> + Owner identifier <text string> $00 + Identifier <up to 64 bytes binary data> + + +4.2. Text information frames + + The text information frames are often the most important frames, + containing information like artist, album and more. There may only be + one text information frame of its kind in an tag. All text + information frames supports multiple strings, stored as a null + separated list, where null is reperesented by the termination code + for the charater encoding. All text frame identifiers begin with "T". + Only text frame identifiers begin with "T", with the exception of the + "TXXX" frame. All the text information frames have the following + format: + + <Header for 'Text information frame', ID: "T000" - "TZZZ", + excluding "TXXX" described in 4.2.6.> + Text encoding $xx + Information <text string(s) according to encoding> + + +4.2.1. Identification frames + + TIT1 + The 'Content group description' frame is used if the sound belongs to + a larger category of sounds/music. For example, classical music is + often sorted in different musical sections (e.g. "Piano Concerto", + "Weather - Hurricane"). + + TIT2 + The 'Title/Songname/Content description' frame is the actual name of + the piece (e.g. "Adagio", "Hurricane Donna"). + + TIT3 + The 'Subtitle/Description refinement' frame is used for information + directly related to the contents title (e.g. "Op. 16" or "Performed + live at Wembley"). + + TALB + The 'Album/Movie/Show title' frame is intended for the title of the + recording (or source of sound) from which the audio in the file is + taken. + + TOAL + The 'Original album/movie/show title' frame is intended for the title + of the original recording (or source of sound), if for example the + music in the file should be a cover of a previously released song. + + TRCK + The 'Track number/Position in set' frame is a numeric string + containing the order number of the audio-file on its original + recording. This MAY be extended with a "/" character and a numeric + string containing the total number of tracks/elements on the original + recording. E.g. "4/9". + + TPOS + The 'Part of a set' frame is a numeric string that describes which + part of a set the audio came from. This frame is used if the source + described in the "TALB" frame is divided into several mediums, e.g. a + double CD. The value MAY be extended with a "/" character and a + numeric string containing the total number of parts in the set. E.g. + "1/2". + + TSST + The 'Set subtitle' frame is intended for the subtitle of the part of + a set this track belongs to. + + TSRC + The 'ISRC' frame should contain the International Standard Recording + Code [ISRC] (12 characters). + + +4.2.2. Involved persons frames + + TPE1 + The 'Lead artist/Lead performer/Soloist/Performing group' is + used for the main artist. + + TPE2 + The 'Band/Orchestra/Accompaniment' frame is used for additional + information about the performers in the recording. + + TPE3 + The 'Conductor' frame is used for the name of the conductor. + + TPE4 + The 'Interpreted, remixed, or otherwise modified by' frame contains + more information about the people behind a remix and similar + interpretations of another existing piece. + + TOPE + The 'Original artist/performer' frame is intended for the performer + of the original recording, if for example the music in the file + should be a cover of a previously released song. + + TEXT + The 'Lyricist/Text writer' frame is intended for the writer of the + text or lyrics in the recording. + + TOLY + The 'Original lyricist/text writer' frame is intended for the + text writer of the original recording, if for example the music in + the file should be a cover of a previously released song. + + TCOM + The 'Composer' frame is intended for the name of the composer. + + TMCL + The 'Musician credits list' is intended as a mapping between + instruments and the musician that played it. Every odd field is an + instrument and every even is an artist or a comma delimited list of + artists. + + TIPL + The 'Involved people list' is very similar to the musician credits + list, but maps between functions, like producer, and names. + + TENC + The 'Encoded by' frame contains the name of the person or + organisation that encoded the audio file. This field may contain a + copyright message, if the audio file also is copyrighted by the + encoder. + + +4.2.3. Derived and subjective properties frames + + TBPM + The 'BPM' frame contains the number of beats per minute in the + main part of the audio. The BPM is an integer and represented as a + numerical string. + + TLEN + The 'Length' frame contains the length of the audio file in + milliseconds, represented as a numeric string. + + TKEY + The 'Initial key' frame contains the musical key in which the sound + starts. It is represented as a string with a maximum length of three + characters. The ground keys are represented with "A","B","C","D","E", + "F" and "G" and halfkeys represented with "b" and "#". Minor is + represented as "m", e.g. "Dbm" $00. Off key is represented with an + "o" only. + + TLAN + The 'Language' frame should contain the languages of the text or + lyrics spoken or sung in the audio. The language is represented with + three characters according to ISO-639-2 [ISO-639-2]. If more than one + language is used in the text their language codes should follow + according to the amount of their usage, e.g. "eng" $00 "sve" $00. + + TCON + The 'Content type', which ID3v1 was stored as a one byte numeric + value only, is now a string. You may use one or several of the ID3v1 + types as numerical strings, or, since the category list would be + impossible to maintain with accurate and up to date categories, + define your own. Example: "21" $00 "Eurodisco" $00 + + You may also use any of the following keywords: + + RX Remix + CR Cover + + TFLT + The 'File type' frame indicates which type of audio this tag defines. + The following types and refinements are defined: + + MIME MIME type follows + MPG MPEG Audio + /1 MPEG 1/2 layer I + /2 MPEG 1/2 layer II + /3 MPEG 1/2 layer III + /2.5 MPEG 2.5 + /AAC Advanced audio compression + VQF Transform-domain Weighted Interleave Vector Quantisation + PCM Pulse Code Modulated audio + + but other types may be used, but not for these types though. This is + used in a similar way to the predefined types in the "TMED" frame, + but without parentheses. If this frame is not present audio type is + assumed to be "MPG". + + TMED + The 'Media type' frame describes from which media the sound + originated. This may be a text string or a reference to the + predefined media types found in the list below. Example: + "VID/PAL/VHS" $00. + + DIG Other digital media + /A Analogue transfer from media + + ANA Other analogue media + /WAC Wax cylinder + /8CA 8-track tape cassette + + CD CD + /A Analogue transfer from media + /DD DDD + /AD ADD + /AA AAD + + LD Laserdisc + + TT Turntable records + /33 33.33 rpm + /45 45 rpm + /71 71.29 rpm + /76 76.59 rpm + /78 78.26 rpm + /80 80 rpm + + MD MiniDisc + /A Analogue transfer from media + + DAT DAT + /A Analogue transfer from media + /1 standard, 48 kHz/16 bits, linear + /2 mode 2, 32 kHz/16 bits, linear + /3 mode 3, 32 kHz/12 bits, non-linear, low speed + /4 mode 4, 32 kHz/12 bits, 4 channels + /5 mode 5, 44.1 kHz/16 bits, linear + /6 mode 6, 44.1 kHz/16 bits, 'wide track' play + + DCC DCC + /A Analogue transfer from media + + DVD DVD + /A Analogue transfer from media + + TV Television + /PAL PAL + /NTSC NTSC + /SECAM SECAM + + VID Video + /PAL PAL + /NTSC NTSC + /SECAM SECAM + /VHS VHS + /SVHS S-VHS + /BETA BETAMAX + + RAD Radio + /FM FM + /AM AM + /LW LW + /MW MW + + TEL Telephone + /I ISDN + + MC MC (normal cassette) + /4 4.75 cm/s (normal speed for a two sided cassette) + /9 9.5 cm/s + /I Type I cassette (ferric/normal) + /II Type II cassette (chrome) + /III Type III cassette (ferric chrome) + /IV Type IV cassette (metal) + + REE Reel + /9 9.5 cm/s + /19 19 cm/s + /38 38 cm/s + /76 76 cm/s + /I Type I cassette (ferric/normal) + /II Type II cassette (chrome) + /III Type III cassette (ferric chrome) + /IV Type IV cassette (metal) + + TMOO + The 'Mood' frame is intended to reflect the mood of the audio with a + few keywords, e.g. "Romantic" or "Sad". + + +4.2.4. Rights and license frames + + TCOP + The 'Copyright message' frame, in which the string must begin with a + year and a space character (making five characters), is intended for + the copyright holder of the original sound, not the audio file + itself. The absence of this frame means only that the copyright + information is unavailable or has been removed, and must not be + interpreted to mean that the audio is public domain. Every time this + field is displayed the field must be preceded with "Copyright " (C) " + ", where (C) is one character showing a C in a circle. + + TPRO + The 'Produced notice' frame, in which the string must begin with a + year and a space character (making five characters), is intended for + the production copyright holder of the original sound, not the audio + file itself. The absence of this frame means only that the production + copyright information is unavailable or has been removed, and must + not be interpreted to mean that the audio is public domain. Every + time this field is displayed the field must be preceded with + "Produced " (P) " ", where (P) is one character showing a P in a + circle. + + TPUB + The 'Publisher' frame simply contains the name of the label or + publisher. + + TOWN + The 'File owner/licensee' frame contains the name of the owner or + licensee of the file and it's contents. + + TRSN + The 'Internet radio station name' frame contains the name of the + internet radio station from which the audio is streamed. + + TRSO + The 'Internet radio station owner' frame contains the name of the + owner of the internet radio station from which the audio is + streamed. + +4.2.5. Other text frames + + TOFN + The 'Original filename' frame contains the preferred filename for the + file, since some media doesn't allow the desired length of the + filename. The filename is case sensitive and includes its suffix. + + TDLY + The 'Playlist delay' defines the numbers of milliseconds of silence + that should be inserted before this audio. The value zero indicates + that this is a part of a multifile audio track that should be played + continuously. + + TDEN + The 'Encoding time' frame contains a timestamp describing when the + audio was encoded. Timestamp format is described in the ID3v2 + structure document [ID3v2-strct]. + + TDOR + The 'Original release time' frame contains a timestamp describing + when the original recording of the audio was released. Timestamp + format is described in the ID3v2 structure document [ID3v2-strct]. + + TDRC + The 'Recording time' frame contains a timestamp describing when the + audio was recorded. Timestamp format is described in the ID3v2 + structure document [ID3v2-strct]. + + TDRL + The 'Release time' frame contains a timestamp describing when the + audio was first released. Timestamp format is described in the ID3v2 + structure document [ID3v2-strct]. + + TDTG + The 'Tagging time' frame contains a timestamp describing then the + audio was tagged. Timestamp format is described in the ID3v2 + structure document [ID3v2-strct]. + + TSSE + The 'Software/Hardware and settings used for encoding' frame + includes the used audio encoder and its settings when the file was + encoded. Hardware refers to hardware encoders, not the computer on + which a program was run. + + TSOA + The 'Album sort order' frame defines a string which should be used + instead of the album name (TALB) for sorting purposes. E.g. an album + named "A Soundtrack" might preferably be sorted as "Soundtrack". + + TSOP + The 'Performer sort order' frame defines a string which should be + used instead of the performer (TPE2) for sorting purposes. + + TSOT + The 'Title sort order' frame defines a string which should be used + instead of the title (TIT2) for sorting purposes. + + +4.2.6. User defined text information frame + + This frame is intended for one-string text information concerning the + audio file in a similar way to the other "T"-frames. The frame body + consists of a description of the string, represented as a terminated + string, followed by the actual string. There may be more than one + "TXXX" frame in each tag, but only one with the same description. + + <Header for 'User defined text information frame', ID: "TXXX"> + Text encoding $xx + Description <text string according to encoding> $00 (00) + Value <text string according to encoding> + + +4.3. URL link frames + + With these frames dynamic data such as webpages with touring + information, price information or plain ordinary news can be added to + the tag. There may only be one URL [URL] link frame of its kind in an + tag, except when stated otherwise in the frame description. If the + text string is followed by a string termination, all the following + information should be ignored and not be displayed. All URL link + frame identifiers begins with "W". Only URL link frame identifiers + begins with "W", except for "WXXX". All URL link frames have the + following format: + + <Header for 'URL link frame', ID: "W000" - "WZZZ", excluding "WXXX" + described in 4.3.2.> + URL <text string> + + +4.3.1. URL link frames - details + + WCOM + The 'Commercial information' frame is a URL pointing at a webpage + with information such as where the album can be bought. There may be + more than one "WCOM" frame in a tag, but not with the same content. + + WCOP + The 'Copyright/Legal information' frame is a URL pointing at a + webpage where the terms of use and ownership of the file is + described. + + WOAF + The 'Official audio file webpage' frame is a URL pointing at a file + specific webpage. + + WOAR + The 'Official artist/performer webpage' frame is a URL pointing at + the artists official webpage. There may be more than one "WOAR" frame + in a tag if the audio contains more than one performer, but not with + the same content. + + WOAS + The 'Official audio source webpage' frame is a URL pointing at the + official webpage for the source of the audio file, e.g. a movie. + + WORS + The 'Official Internet radio station homepage' contains a URL + pointing at the homepage of the internet radio station. + + WPAY + The 'Payment' frame is a URL pointing at a webpage that will handle + the process of paying for this file. + + WPUB + The 'Publishers official webpage' frame is a URL pointing at the + official webpage for the publisher. + + +4.3.2. User defined URL link frame + + This frame is intended for URL [URL] links concerning the audio file + in a similar way to the other "W"-frames. The frame body consists + of a description of the string, represented as a terminated string, + followed by the actual URL. The URL is always encoded with ISO-8859-1 + [ISO-8859-1]. There may be more than one "WXXX" frame in each tag, + but only one with the same description. + + <Header for 'User defined URL link frame', ID: "WXXX"> + Text encoding $xx + Description <text string according to encoding> $00 (00) + URL <text string> + + +4.4. Music CD identifier + + This frame is intended for music that comes from a CD, so that the CD + can be identified in databases such as the CDDB [CDDB]. The frame + consists of a binary dump of the Table Of Contents, TOC, from the CD, + which is a header of 4 bytes and then 8 bytes/track on the CD plus 8 + bytes for the 'lead out', making a maximum of 804 bytes. The offset + to the beginning of every track on the CD should be described with a + four bytes absolute CD-frame address per track, and not with absolute + time. When this frame is used the presence of a valid "TRCK" frame is + REQUIRED, even if the CD's only got one track. It is recommended that + this frame is always added to tags originating from CDs. There may + only be one "MCDI" frame in each tag. + + <Header for 'Music CD identifier', ID: "MCDI"> + CD TOC <binary data> + + +4.5. Event timing codes + + This frame allows synchronisation with key events in the audio. The + header is: + + <Header for 'Event timing codes', ID: "ETCO"> + Time stamp format $xx + + Where time stamp format is: + + $01 Absolute time, 32 bit sized, using MPEG [MPEG] frames as unit + $02 Absolute time, 32 bit sized, using milliseconds as unit + + Absolute time means that every stamp contains the time from the + beginning of the file. + + Followed by a list of key events in the following format: + + Type of event $xx + Time stamp $xx (xx ...) + + The 'Time stamp' is set to zero if directly at the beginning of the + sound or after the previous event. All events MUST be sorted in + chronological order. The type of event is as follows: + + $00 padding (has no meaning) + $01 end of initial silence + $02 intro start + $03 main part start + $04 outro start + $05 outro end + $06 verse start + $07 refrain start + $08 interlude start + $09 theme start + $0A variation start + $0B key change + $0C time change + $0D momentary unwanted noise (Snap, Crackle & Pop) + $0E sustained noise + $0F sustained noise end + $10 intro end + $11 main part end + $12 verse end + $13 refrain end + $14 theme end + $15 profanity + $16 profanity end + + $17-$DF reserved for future use + + $E0-$EF not predefined synch 0-F + + $F0-$FC reserved for future use + + $FD audio end (start of silence) + $FE audio file ends + $FF one more byte of events follows (all the following bytes with + the value $FF have the same function) + + Terminating the start events such as "intro start" is OPTIONAL. The + 'Not predefined synch's ($E0-EF) are for user events. You might want + to synchronise your music to something, like setting off an explosion + on-stage, activating a screensaver etc. + + There may only be one "ETCO" frame in each tag. + + +4.6. MPEG location lookup table + + To increase performance and accuracy of jumps within a MPEG [MPEG] + audio file, frames with time codes in different locations in the file + might be useful. This ID3v2 frame includes references that the + software can use to calculate positions in the file. After the frame + header follows a descriptor of how much the 'frame counter' should be + increased for every reference. If this value is two then the first + reference points out the second frame, the 2nd reference the 4th + frame, the 3rd reference the 6th frame etc. In a similar way the + 'bytes between reference' and 'milliseconds between reference' points + out bytes and milliseconds respectively. + + Each reference consists of two parts; a certain number of bits, as + defined in 'bits for bytes deviation', that describes the difference + between what is said in 'bytes between reference' and the reality and + a certain number of bits, as defined in 'bits for milliseconds + deviation', that describes the difference between what is said in + 'milliseconds between reference' and the reality. The number of bits + in every reference, i.e. 'bits for bytes deviation'+'bits for + milliseconds deviation', must be a multiple of four. There may only + be one "MLLT" frame in each tag. + + <Header for 'Location lookup table', ID: "MLLT"> + MPEG frames between reference $xx xx + Bytes between reference $xx xx xx + Milliseconds between reference $xx xx xx + Bits for bytes deviation $xx + Bits for milliseconds dev. $xx + + Then for every reference the following data is included; + + Deviation in bytes %xxx.... + Deviation in milliseconds %xxx.... + + +4.7. Synchronised tempo codes + + For a more accurate description of the tempo of a musical piece, this + frame might be used. After the header follows one byte describing + which time stamp format should be used. Then follows one or more + tempo codes. Each tempo code consists of one tempo part and one time + part. The tempo is in BPM described with one or two bytes. If the + first byte has the value $FF, one more byte follows, which is added + to the first giving a range from 2 - 510 BPM, since $00 and $01 is + reserved. $00 is used to describe a beat-free time period, which is + not the same as a music-free time period. $01 is used to indicate one + single beat-stroke followed by a beat-free period. + + The tempo descriptor is followed by a time stamp. Every time the + tempo in the music changes, a tempo descriptor may indicate this for + the player. All tempo descriptors MUST be sorted in chronological + order. The first beat-stroke in a time-period is at the same time as + the beat description occurs. There may only be one "SYTC" frame in + each tag. + + <Header for 'Synchronised tempo codes', ID: "SYTC"> + Time stamp format $xx + Tempo data <binary data> + + Where time stamp format is: + + $01 Absolute time, 32 bit sized, using MPEG [MPEG] frames as unit + $02 Absolute time, 32 bit sized, using milliseconds as unit + + Absolute time means that every stamp contains the time from the + beginning of the file. + + +4.8. Unsynchronised lyrics/text transcription + + This frame contains the lyrics of the song or a text transcription of + other vocal activities. The head includes an encoding descriptor and + a content descriptor. The body consists of the actual text. The + 'Content descriptor' is a terminated string. If no descriptor is + entered, 'Content descriptor' is $00 (00) only. Newline characters + are allowed in the text. There may be more than one 'Unsynchronised + lyrics/text transcription' frame in each tag, but only one with the + same language and content descriptor. + + <Header for 'Unsynchronised lyrics/text transcription', ID: "USLT"> + Text encoding $xx + Language $xx xx xx + Content descriptor <text string according to encoding> $00 (00) + Lyrics/text <full text string according to encoding> + + +4.9. Synchronised lyrics/text + + This is another way of incorporating the words, said or sung lyrics, + in the audio file as text, this time, however, in sync with the + audio. It might also be used to describing events e.g. occurring on a + stage or on the screen in sync with the audio. The header includes a + content descriptor, represented with as terminated text string. If no + descriptor is entered, 'Content descriptor' is $00 (00) only. + + <Header for 'Synchronised lyrics/text', ID: "SYLT"> + Text encoding $xx + Language $xx xx xx + Time stamp format $xx + Content type $xx + Content descriptor <text string according to encoding> $00 (00) + + Content type: $00 is other + $01 is lyrics + $02 is text transcription + $03 is movement/part name (e.g. "Adagio") + $04 is events (e.g. "Don Quijote enters the stage") + $05 is chord (e.g. "Bb F Fsus") + $06 is trivia/'pop up' information + $07 is URLs to webpages + $08 is URLs to images + + Time stamp format: + + $01 Absolute time, 32 bit sized, using MPEG [MPEG] frames as unit + $02 Absolute time, 32 bit sized, using milliseconds as unit + + Absolute time means that every stamp contains the time from the + beginning of the file. + + The text that follows the frame header differs from that of the + unsynchronised lyrics/text transcription in one major way. Each + syllable (or whatever size of text is considered to be convenient by + the encoder) is a null terminated string followed by a time stamp + denoting where in the sound file it belongs. Each sync thus has the + following structure: + + Terminated text to be synced (typically a syllable) + Sync identifier (terminator to above string) $00 (00) + Time stamp $xx (xx ...) + + The 'time stamp' is set to zero or the whole sync is omitted if + located directly at the beginning of the sound. All time stamps + should be sorted in chronological order. The sync can be considered + as a validator of the subsequent string. + + Newline characters are allowed in all "SYLT" frames and MUST be used + after every entry (name, event etc.) in a frame with the content type + $03 - $04. + + A few considerations regarding whitespace characters: Whitespace + separating words should mark the beginning of a new word, thus + occurring in front of the first syllable of a new word. This is also + valid for new line characters. A syllable followed by a comma should + not be broken apart with a sync (both the syllable and the comma + should be before the sync). + + An example: The "USLT" passage + + "Strangers in the night" $0A "Exchanging glances" + + would be "SYLT" encoded as: + + "Strang" $00 xx xx "ers" $00 xx xx " in" $00 xx xx " the" $00 xx xx + " night" $00 xx xx 0A "Ex" $00 xx xx "chang" $00 xx xx "ing" $00 xx + xx "glan" $00 xx xx "ces" $00 xx xx + + There may be more than one "SYLT" frame in each tag, but only one + with the same language and content descriptor. + + +4.10. Comments + + This frame is intended for any kind of full text information that + does not fit in any other frame. It consists of a frame header + followed by encoding, language and content descriptors and is ended + with the actual comment as a text string. Newline characters are + allowed in the comment text string. There may be more than one + comment frame in each tag, but only one with the same language and + content descriptor. + + <Header for 'Comment', ID: "COMM"> + Text encoding $xx + Language $xx xx xx + Short content descrip. <text string according to encoding> $00 (00) + The actual text <full text string according to encoding> + + +4.11. Relative volume adjustment (2) + + This is a more subjective frame than the previous ones. It allows the + user to say how much he wants to increase/decrease the volume on each + channel when the file is played. The purpose is to be able to align + all files to a reference volume, so that you don't have to change the + volume constantly. This frame may also be used to balance adjust the + audio. The volume adjustment is encoded as a fixed point decibel + value, 16 bit signed integer representing (adjustment*512), giving + +/- 64 dB with a precision of 0.001953125 dB. E.g. +2 dB is stored as + $04 00 and -2 dB is $FC 00. There may be more than one "RVA2" frame + in each tag, but only one with the same identification string. + + <Header for 'Relative volume adjustment (2)', ID: "RVA2"> + Identification <text string> $00 + + The 'identification' string is used to identify the situation and/or + device where this adjustment should apply. The following is then + repeated for every channel + + Type of channel $xx + Volume adjustment $xx xx + Bits representing peak $xx + Peak volume $xx (xx ...) + + + Type of channel: $00 Other + $01 Master volume + $02 Front right + $03 Front left + $04 Back right + $05 Back left + $06 Front centre + $07 Back centre + $08 Subwoofer + + Bits representing peak can be any number between 0 and 255. 0 means + that there is no peak volume field. The peak volume field is always + padded to whole bytes, setting the most significant bits to zero. + + +4.12. Equalisation (2) + + This is another subjective, alignment frame. It allows the user to + predefine an equalisation curve within the audio file. There may be + more than one "EQU2" frame in each tag, but only one with the same + identification string. + + <Header of 'Equalisation (2)', ID: "EQU2"> + Interpolation method $xx + Identification <text string> $00 + + The 'interpolation method' describes which method is preferred when + an interpolation between the adjustment point that follows. The + following methods are currently defined: + + $00 Band + No interpolation is made. A jump from one adjustment level to + another occurs in the middle between two adjustment points. + $01 Linear + Interpolation between adjustment points is linear. + + The 'identification' string is used to identify the situation and/or + device where this adjustment should apply. The following is then + repeated for every adjustment point + + Frequency $xx xx + Volume adjustment $xx xx + + The frequency is stored in units of 1/2 Hz, giving it a range from 0 + to 32767 Hz. + + The volume adjustment is encoded as a fixed point decibel value, 16 + bit signed integer representing (adjustment*512), giving +/- 64 dB + with a precision of 0.001953125 dB. E.g. +2 dB is stored as $04 00 + and -2 dB is $FC 00. + + Adjustment points should be ordered by frequency and one frequency + should only be described once in the frame. + + +4.13. Reverb + + Yet another subjective frame, with which you can adjust echoes of + different kinds. Reverb left/right is the delay between every bounce + in ms. Reverb bounces left/right is the number of bounces that should + be made. $FF equals an infinite number of bounces. Feedback is the + amount of volume that should be returned to the next echo bounce. $00 + is 0%, $FF is 100%. If this value were $7F, there would be 50% volume + reduction on the first bounce, 50% of that on the second and so on. + Left to left means the sound from the left bounce to be played in the + left speaker, while left to right means sound from the left bounce to + be played in the right speaker. + + 'Premix left to right' is the amount of left sound to be mixed in the + right before any reverb is applied, where $00 id 0% and $FF is 100%. + 'Premix right to left' does the same thing, but right to left. + Setting both premix to $FF would result in a mono output (if the + reverb is applied symmetric). There may only be one "RVRB" frame in + each tag. + + <Header for 'Reverb', ID: "RVRB"> + Reverb left (ms) $xx xx + Reverb right (ms) $xx xx + Reverb bounces, left $xx + Reverb bounces, right $xx + Reverb feedback, left to left $xx + Reverb feedback, left to right $xx + Reverb feedback, right to right $xx + Reverb feedback, right to left $xx + Premix left to right $xx + Premix right to left $xx + + +4.14. Attached picture + + This frame contains a picture directly related to the audio file. + Image format is the MIME type and subtype [MIME] for the image. In + the event that the MIME media type name is omitted, "image/" will be + implied. The "image/png" [PNG] or "image/jpeg" [JFIF] picture format + should be used when interoperability is wanted. Description is a + short description of the picture, represented as a terminated + text string. There may be several pictures attached to one file, each + in their individual "APIC" frame, but only one with the same content + descriptor. There may only be one picture with the picture type + declared as picture type $01 and $02 respectively. There is the + possibility to put only a link to the image file by using the 'MIME + type' "-->" and having a complete URL [URL] instead of picture data. + The use of linked files should however be used sparingly since there + is the risk of separation of files. + + <Header for 'Attached picture', ID: "APIC"> + Text encoding $xx + MIME type <text string> $00 + Picture type $xx + Description <text string according to encoding> $00 (00) + Picture data <binary data> + + + Picture type: $00 Other + $01 32x32 pixels 'file icon' (PNG only) + $02 Other file icon + $03 Cover (front) + $04 Cover (back) + $05 Leaflet page + $06 Media (e.g. label side of CD) + $07 Lead artist/lead performer/soloist + $08 Artist/performer + $09 Conductor + $0A Band/Orchestra + $0B Composer + $0C Lyricist/text writer + $0D Recording Location + $0E During recording + $0F During performance + $10 Movie/video screen capture + $11 A bright coloured fish + $12 Illustration + $13 Band/artist logotype + $14 Publisher/Studio logotype + + +4.15. General encapsulated object + + In this frame any type of file can be encapsulated. After the header, + 'Frame size' and 'Encoding' follows 'MIME type' [MIME] represented as + as a terminated string encoded with ISO 8859-1 [ISO-8859-1]. The + filename is case sensitive and is encoded as 'Encoding'. Then follows + a content description as terminated string, encoded as 'Encoding'. + The last thing in the frame is the actual object. The first two + strings may be omitted, leaving only their terminations. MIME type is + always an ISO-8859-1 text string. There may be more than one "GEOB" + frame in each tag, but only one with the same content descriptor. + + <Header for 'General encapsulated object', ID: "GEOB"> + Text encoding $xx + MIME type <text string> $00 + Filename <text string according to encoding> $00 (00) + Content description <text string according to encoding> $00 (00) + Encapsulated object <binary data> + + +4.16. Play counter + + This is simply a counter of the number of times a file has been + played. The value is increased by one every time the file begins to + play. There may only be one "PCNT" frame in each tag. When the + counter reaches all one's, one byte is inserted in front of the + counter thus making the counter eight bits bigger. The counter must + be at least 32-bits long to begin with. + + <Header for 'Play counter', ID: "PCNT"> + Counter $xx xx xx xx (xx ...) + + +4.17. Popularimeter + + The purpose of this frame is to specify how good an audio file is. + Many interesting applications could be found to this frame such as a + playlist that features better audio files more often than others or + it could be used to profile a person's taste and find other 'good' + files by comparing people's profiles. The frame contains the email + address to the user, one rating byte and a four byte play counter, + intended to be increased with one for every time the file is played. + The email is a terminated string. The rating is 1-255 where 1 is + worst and 255 is best. 0 is unknown. If no personal counter is wanted + it may be omitted. When the counter reaches all one's, one byte is + inserted in front of the counter thus making the counter eight bits + bigger in the same away as the play counter ("PCNT"). There may be + more than one "POPM" frame in each tag, but only one with the same + email address. + + <Header for 'Popularimeter', ID: "POPM"> + Email to user <text string> $00 + Rating $xx + Counter $xx xx xx xx (xx ...) + + +4.18. Recommended buffer size + + Sometimes the server from which an audio file is streamed is aware of + transmission or coding problems resulting in interruptions in the + audio stream. In these cases, the size of the buffer can be + recommended by the server using this frame. If the 'embedded info + flag' is true (1) then this indicates that an ID3 tag with the + maximum size described in 'Buffer size' may occur in the audio + stream. In such case the tag should reside between two MPEG [MPEG] + frames, if the audio is MPEG encoded. If the position of the next tag + is known, 'offset to next tag' may be used. The offset is calculated + from the end of tag in which this frame resides to the first byte of + the header in the next. This field may be omitted. Embedded tags are + generally not recommended since this could render unpredictable + behaviour from present software/hardware. + + For applications like streaming audio it might be an idea to embed + tags into the audio stream though. If the clients connects to + individual connections like HTTP and there is a possibility to begin + every transmission with a tag, then this tag should include a + 'recommended buffer size' frame. If the client is connected to a + arbitrary point in the stream, such as radio or multicast, then the + 'recommended buffer size' frame SHOULD be included in every tag. + + The 'Buffer size' should be kept to a minimum. There may only be one + "RBUF" frame in each tag. + + <Header for 'Recommended buffer size', ID: "RBUF"> + Buffer size $xx xx xx + Embedded info flag %0000000x + Offset to next tag $xx xx xx xx + + +4.19. Audio encryption + + This frame indicates if the actual audio stream is encrypted, and by + whom. Since standardisation of such encryption scheme is beyond this + document, all "AENC" frames begin with a terminated string with a + URL containing an email address, or a link to a location where an + email address can be found, that belongs to the organisation + responsible for this specific encrypted audio file. Questions + regarding the encrypted audio should be sent to the email address + specified. If a $00 is found directly after the 'Frame size' and the + audio file indeed is encrypted, the whole file may be considered + useless. + + After the 'Owner identifier', a pointer to an unencrypted part of the + audio can be specified. The 'Preview start' and 'Preview length' is + described in frames. If no part is unencrypted, these fields should + be left zeroed. After the 'preview length' field follows optionally a + data block required for decryption of the audio. There may be more + than one "AENC" frames in a tag, but only one with the same 'Owner + identifier'. + + <Header for 'Audio encryption', ID: "AENC"> + Owner identifier <text string> $00 + Preview start $xx xx + Preview length $xx xx + Encryption info <binary data> + + +4.20. Linked information + + To keep information duplication as low as possible this frame may be + used to link information from another ID3v2 tag that might reside in + another audio file or alone in a binary file. It is RECOMMENDED that + this method is only used when the files are stored on a CD-ROM or + other circumstances when the risk of file separation is low. The + frame contains a frame identifier, which is the frame that should be + linked into this tag, a URL [URL] field, where a reference to the + file where the frame is given, and additional ID data, if needed. + Data should be retrieved from the first tag found in the file to + which this link points. There may be more than one "LINK" frame in a + tag, but only one with the same contents. A linked frame is to be + considered as part of the tag and has the same restrictions as if it + was a physical part of the tag (i.e. only one "RVRB" frame allowed, + whether it's linked or not). + + <Header for 'Linked information', ID: "LINK"> + Frame identifier $xx xx xx xx + URL <text string> $00 + ID and additional data <text string(s)> + + Frames that may be linked and need no additional data are "ASPI", + "ETCO", "EQU2", "MCID", "MLLT", "OWNE", "RVA2", "RVRB", "SYTC", the + text information frames and the URL link frames. + + The "AENC", "APIC", "GEOB" and "TXXX" frames may be linked with + the content descriptor as additional ID data. + + The "USER" frame may be linked with the language field as additional + ID data. + + The "PRIV" frame may be linked with the owner identifier as + additional ID data. + + The "COMM", "SYLT" and "USLT" frames may be linked with three bytes + of language descriptor directly followed by a content descriptor as + additional ID data. + + +4.21. Position synchronisation frame + + This frame delivers information to the listener of how far into the + audio stream he picked up; in effect, it states the time offset from + the first frame in the stream. The frame layout is: + + <Head for 'Position synchronisation', ID: "POSS"> + Time stamp format $xx + Position $xx (xx ...) + + Where time stamp format is: + + $01 Absolute time, 32 bit sized, using MPEG frames as unit + $02 Absolute time, 32 bit sized, using milliseconds as unit + + and position is where in the audio the listener starts to receive, + i.e. the beginning of the next frame. If this frame is used in the + beginning of a file the value is always 0. There may only be one + "POSS" frame in each tag. + + +4.22. Terms of use frame + + This frame contains a brief description of the terms of use and + ownership of the file. More detailed information concerning the legal + terms might be available through the "WCOP" frame. Newlines are + allowed in the text. There may be more than one 'Terms of use' frame + in a tag, but only one with the same 'Language'. + + <Header for 'Terms of use frame', ID: "USER"> + Text encoding $xx + Language $xx xx xx + The actual text <text string according to encoding> + + +4.23. Ownership frame + + The ownership frame might be used as a reminder of a made transaction + or, if signed, as proof. Note that the "USER" and "TOWN" frames are + good to use in conjunction with this one. The frame begins, after the + frame ID, size and encoding fields, with a 'price paid' field. The + first three characters of this field contains the currency used for + the transaction, encoded according to ISO 4217 [ISO-4217] alphabetic + currency code. Concatenated to this is the actual price paid, as a + numerical string using "." as the decimal separator. Next is an 8 + character date string (YYYYMMDD) followed by a string with the name + of the seller as the last field in the frame. There may only be one + "OWNE" frame in a tag. + + <Header for 'Ownership frame', ID: "OWNE"> + Text encoding $xx + Price paid <text string> $00 + Date of purch. <text string> + Seller <text string according to encoding> + + +4.24. Commercial frame + + This frame enables several competing offers in the same tag by + bundling all needed information. That makes this frame rather complex + but it's an easier solution than if one tries to achieve the same + result with several frames. The frame begins, after the frame ID, + size and encoding fields, with a price string field. A price is + constructed by one three character currency code, encoded according + to ISO 4217 [ISO-4217] alphabetic currency code, followed by a + numerical value where "." is used as decimal separator. In the price + string several prices may be concatenated, separated by a "/" + character, but there may only be one currency of each type. + + The price string is followed by an 8 character date string in the + format YYYYMMDD, describing for how long the price is valid. After + that is a contact URL, with which the user can contact the seller, + followed by a one byte 'received as' field. It describes how the + audio is delivered when bought according to the following list: + + $00 Other + $01 Standard CD album with other songs + $02 Compressed audio on CD + $03 File over the Internet + $04 Stream over the Internet + $05 As note sheets + $06 As note sheets in a book with other sheets + $07 Music on other media + $08 Non-musical merchandise + + Next follows a terminated string with the name of the seller followed + by a terminated string with a short description of the product. The + last thing is the ability to include a company logotype. The first of + them is the 'Picture MIME type' field containing information about + which picture format is used. In the event that the MIME media type + name is omitted, "image/" will be implied. Currently only "image/png" + and "image/jpeg" are allowed. This format string is followed by the + binary picture data. This two last fields may be omitted if no + picture is attached. There may be more than one 'commercial frame' in + a tag, but no two may be identical. + + <Header for 'Commercial frame', ID: "COMR"> + Text encoding $xx + Price string <text string> $00 + Valid until <text string> + Contact URL <text string> $00 + Received as $xx + Name of seller <text string according to encoding> $00 (00) + Description <text string according to encoding> $00 (00) + Picture MIME type <string> $00 + Seller logo <binary data> + + +4.25. Encryption method registration + + To identify with which method a frame has been encrypted the + encryption method must be registered in the tag with this frame. The + 'Owner identifier' is a null-terminated string with a URL [URL] + containing an email address, or a link to a location where an email + address can be found, that belongs to the organisation responsible + for this specific encryption method. Questions regarding the + encryption method should be sent to the indicated email address. The + 'Method symbol' contains a value that is associated with this method + throughout the whole tag, in the range $80-F0. All other values are + reserved. The 'Method symbol' may optionally be followed by + encryption specific data. There may be several "ENCR" frames in a tag + but only one containing the same symbol and only one containing the + same owner identifier. The method must be used somewhere in the tag. + See the description of the frame encryption flag in the ID3v2 + structure document [ID3v2-strct] for more information. + + <Header for 'Encryption method registration', ID: "ENCR"> + Owner identifier <text string> $00 + Method symbol $xx + Encryption data <binary data> + + +4.26. Group identification registration + + This frame enables grouping of otherwise unrelated frames. This can + be used when some frames are to be signed. To identify which frames + belongs to a set of frames a group identifier must be registered in + the tag with this frame. The 'Owner identifier' is a null-terminated + string with a URL [URL] containing an email address, or a link to a + location where an email address can be found, that belongs to the + organisation responsible for this grouping. Questions regarding the + grouping should be sent to the indicated email address. The 'Group + symbol' contains a value that associates the frame with this group + throughout the whole tag, in the range $80-F0. All other values are + reserved. The 'Group symbol' may optionally be followed by some group + specific data, e.g. a digital signature. There may be several "GRID" + frames in a tag but only one containing the same symbol and only one + containing the same owner identifier. The group symbol must be used + somewhere in the tag. See the description of the frame grouping flag + in the ID3v2 structure document [ID3v2-strct] for more information. + + <Header for 'Group ID registration', ID: "GRID"> + Owner identifier <text string> $00 + Group symbol $xx + Group dependent data <binary data> + + +4.27. Private frame + + This frame is used to contain information from a software producer + that its program uses and does not fit into the other frames. The + frame consists of an 'Owner identifier' string and the binary data. + The 'Owner identifier' is a null-terminated string with a URL [URL] + containing an email address, or a link to a location where an email + address can be found, that belongs to the organisation responsible + for the frame. Questions regarding the frame should be sent to the + indicated email address. The tag may contain more than one "PRIV" + frame but only with different contents. + + <Header for 'Private frame', ID: "PRIV"> + Owner identifier <text string> $00 + The private data <binary data> + + +4.28. Signature frame + + This frame enables a group of frames, grouped with the 'Group + identification registration', to be signed. Although signatures can + reside inside the registration frame, it might be desired to store + the signature elsewhere, e.g. in watermarks. There may be more than + one 'signature frame' in a tag, but no two may be identical. + + <Header for 'Signature frame', ID: "SIGN"> + Group symbol $xx + Signature <binary data> + + +4.29. Seek frame + + This frame indicates where other tags in a file/stream can be found. + The 'minimum offset to next tag' is calculated from the end of this + tag to the beginning of the next. There may only be one 'seek frame' + in a tag. + + <Header for 'Seek frame', ID: "SEEK"> + Minimum offset to next tag $xx xx xx xx + + +4.30. Audio seek point index + + Audio files with variable bit rates are intrinsically difficult to + deal with in the case of seeking within the file. The ASPI frame + makes seeking easier by providing a list a seek points within the + audio file. The seek points are a fractional offset within the audio + data, providing a starting point from which to find an appropriate + point to start decoding. The presence of an ASPI frame requires the + existence of a TLEN frame, indicating the duration of the file in + milliseconds. There may only be one 'audio seek point index' frame in + a tag. + + <Header for 'Seek Point Index', ID: "ASPI"> + Indexed data start (S) $xx xx xx xx + Indexed data length (L) $xx xx xx xx + Number of index points (N) $xx xx + Bits per index point (b) $xx + + Then for every index point the following data is included; + + Fraction at index (Fi) $xx (xx) + + 'Indexed data start' is a byte offset from the beginning of the file. + 'Indexed data length' is the byte length of the audio data being + indexed. 'Number of index points' is the number of index points, as + the name implies. The recommended number is 100. 'Bits per index + point' is 8 or 16, depending on the chosen precision. 8 bits works + well for short files (less than 5 minutes of audio), while 16 bits is + advantageous for long files. 'Fraction at index' is the numerator of + the fraction representing a relative position in the data. The + denominator is 2 to the power of b. + + Here are the algorithms to be used in the calculation. The known data + must be the offset of the start of the indexed data (S), the offset + of the end of the indexed data (E), the number of index points (N), + the offset at index i (Oi). We calculate the fraction at index i + (Fi). + + Oi is the offset of the frame whose start is soonest after the point + for which the time offset is (i/N * duration). + + The frame data should be calculated as follows: + + Fi = Oi/L * 2^b (rounded down to the nearest integer) + + Offset calculation should be calculated as follows from data in the + frame: + + Oi = (Fi/2^b)*L (rounded up to the nearest integer) + + +5. Copyright + + Copyright (C) Martin Nilsson 2000. All Rights Reserved. + + This document and translations of it may be copied and furnished to + others, and derivative works that comment on or otherwise explain it + or assist in its implementation may be prepared, copied, published + and distributed, in whole or in part, without restriction of any + kind, provided that a reference to this document is included on all + such copies and derivative works. However, this document itself may + not be modified in any way and reissued as the original document. + + The limited permissions granted above are perpetual and will not be + revoked. + + This document and the information contained herein is provided on an + "AS IS" basis and THE AUTHORS DISCLAIMS ALL WARRANTIES, EXPRESS OR + IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF + THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED + WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. + + +6. References + + [CDDB] Compact Disc Data Base + + <url:http://www.cddb.com> + + [ID3v2.3.0] Martin Nilsson, "ID3v2 informal standard". + + <url:http://www.id3.org/id3v2.3.0.txt> + + [ID3v2-strct] Martin Nilsson, + "ID3 tag version 2.4.0 - Main Structure" + + <url:http//www.id3.org/id3v2.4.0-structure.txt> + + [ISO-639-2] ISO/FDIS 639-2. + Codes for the representation of names of languages, Part 2: Alpha-3 + code. Technical committee / subcommittee: TC 37 / SC 2 + + [ISO-4217] ISO 4217:1995. + Codes for the representation of currencies and funds. + Technical committee / subcommittee: TC 68 + + [ISO-8859-1] ISO/IEC DIS 8859-1. + 8-bit single-byte coded graphic character sets, Part 1: Latin + alphabet No. 1. Technical committee / subcommittee: JTC 1 / SC 2 + + [ISRC] ISO 3901:1986 + International Standard Recording Code (ISRC). + Technical committee / subcommittee: TC 46 / SC 9 + + [JFIF] JPEG File Interchange Format, version 1.02 + + <url:http://www.w3.org/Graphics/JPEG/jfif.txt> + + [KEYWORDS] S. Bradner, 'Key words for use in RFCs to Indicate + Requirement Levels', RFC 2119, March 1997. + + <url:ftp://ftp.isi.edu/in-notes/rfc2119.txt> + + [MIME] Freed, N. and N. Borenstein, "Multipurpose Internet Mail + Extensions (MIME) Part One: Format of Internet Message Bodies", + RFC 2045, November 1996. + + <url:ftp://ftp.isi.edu/in-notes/rfc2045.txt> + + [MPEG] ISO/IEC 11172-3:1993. + Coding of moving pictures and associated audio for digital storage + media at up to about 1,5 Mbit/s, Part 3: Audio. + Technical committee / subcommittee: JTC 1 / SC 29 + and + ISO/IEC 13818-3:1995 + Generic coding of moving pictures and associated audio information, + Part 3: Audio. + Technical committee / subcommittee: JTC 1 / SC 29 + and + ISO/IEC DIS 13818-3 + Generic coding of moving pictures and associated audio information, + Part 3: Audio (Revision of ISO/IEC 13818-3:1995) + + + [PNG] Portable Network Graphics, version 1.0 + + <url:http://www.w3.org/TR/REC-png-multi.html> + + [URL] T. Berners-Lee, L. Masinter & M. McCahill, "Uniform Resource + Locators (URL).", RFC 1738, December 1994. + + <url:ftp://ftp.isi.edu/in-notes/rfc1738.txt> + + [ZLIB] P. Deutsch, Aladdin Enterprises & J-L. Gailly, "ZLIB + Compressed + Data Format Specification version 3.3", RFC 1950, May 1996. + + <url:ftp://ftp.isi.edu/in-notes/rfc1950.txt> + + +7. Appendix + + +A. Appendix A - Genre List from ID3v1 + + The following genres is defined in ID3v1 + + 0.Blues + 1.Classic Rock + 2.Country + 3.Dance + 4.Disco + 5.Funk + 6.Grunge + 7.Hip-Hop + 8.Jazz + 9.Metal + 10.New Age + 11.Oldies + 12.Other + 13.Pop + 14.R&B + 15.Rap + 16.Reggae + 17.Rock + 18.Techno + 19.Industrial + 20.Alternative + 21.Ska + 22.Death Metal + 23.Pranks + 24.Soundtrack + 25.Euro-Techno + 26.Ambient + 27.Trip-Hop + 28.Vocal + 29.Jazz+Funk + 30.Fusion + 31.Trance + 32.Classical + 33.Instrumental + 34.Acid + 35.House + 36.Game + 37.Sound Clip + 38.Gospel + 39.Noise + 40.AlternRock + 41.Bass + 42.Soul + 43.Punk + 44.Space + 45.Meditative + 46.Instrumental Pop + 47.Instrumental Rock + 48.Ethnic + 49.Gothic + 50.Darkwave + 51.Techno-Industrial + 52.Electronic + 53.Pop-Folk + 54.Eurodance + 55.Dream + 56.Southern Rock + 57.Comedy + 58.Cult + 59.Gangsta + 60.Top 40 + 61.Christian Rap + 62.Pop/Funk + 63.Jungle + 64.Native American + 65.Cabaret + 66.New Wave + 67.Psychadelic + 68.Rave + 69.Showtunes + 70.Trailer + 71.Lo-Fi + 72.Tribal + 73.Acid Punk + 74.Acid Jazz + 75.Polka + 76.Retro + 77.Musical + 78.Rock & Roll + 79.Hard Rock + + +8. Author's Address + + Written by + + Martin Nilsson + Rydsvägen 246 C. 30 + SE-584 34 Linköping + Sweden + + Email: nilsson@id3.org diff --git a/gst/id3demux/id3v2.4.0-structure.txt b/gst/id3demux/id3v2.4.0-structure.txt new file mode 100644 index 00000000..5fa156a0 --- /dev/null +++ b/gst/id3demux/id3v2.4.0-structure.txt @@ -0,0 +1,733 @@ + +Informal standard M. Nilsson +Document: id3v2.4.0-structure.txt 16 September 2001 + + + ID3 tag version 2.4.0 - Main Structure + +Status of this document + + This document is an informal standard and replaces the ID3v2.3.0 + standard [ID3v2]. A formal standard will use another revision number + even if the content is identical to document. The contents in this + document may change for clarifications but never for added or altered + functionallity. + + Distribution of this document is unlimited. + + +Abstract + + This document describes the main structure of ID3v2.4.0, which is a + revised version of the ID3v2 informal standard [ID3v2] version + 2.3.0. The ID3v2 offers a flexible way of storing audio meta + information within the audio file itself. The information may be + technical information, such as equalisation curves, as well as + title, performer, copyright etc. + + ID3v2.4.0 is meant to be as close as possible to ID3v2.3.0 in order + to allow for implementations to be revised as easily as possible. + + +1. Table of contents + + Status of this document + Abstract + 1. Table of contents + 2. Conventions in this document + 2. Standard overview + 3. ID3v2 overview + 3.1. ID3v2 header + 3.2. ID3v2 extended header + 3.3. Padding + 3.4. ID3v2 footer + 4. ID3v2 frames overview + 4.1. Frame header flags + 4.1.1. Frame status flags + 4.1.2. Frame format flags + 5. Tag location + 6. Unsynchronisation + 6.1. The unsynchronisation scheme + 6.2. Synchsafe integers + 7. Copyright + 8. References + 9. Author's Address + + +2. Conventions in this document + + Text within "" is a text string exactly as it appears in a tag. + Numbers preceded with $ are hexadecimal and numbers preceded with % + are binary. $xx is used to indicate a byte with unknown content. %x + is used to indicate a bit with unknown content. The most significant + bit (MSB) of a byte is called 'bit 7' and the least significant bit + (LSB) is called 'bit 0'. + + A tag is the whole tag described in this document. A frame is a block + of information in the tag. The tag consists of a header, frames and + optional padding. A field is a piece of information; one value, a + string etc. A numeric string is a string that consists of the + characters "0123456789" only. + + The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", + "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this + document are to be interpreted as described in RFC 2119 [KEYWORDS]. + + +3. ID3v2 overview + + ID3v2 is a general tagging format for audio, which makes it possible + to store meta data about the audio inside the audio file itself. The + ID3 tag described in this document is mainly targeted at files + encoded with MPEG-1/2 layer I, MPEG-1/2 layer II, MPEG-1/2 layer III + and MPEG-2.5, but may work with other types of encoded audio or as a + stand alone format for audio meta data. + + ID3v2 is designed to be as flexible and expandable as possible to + meet new meta information needs that might arise. To achieve that + ID3v2 is constructed as a container for several information blocks, + called frames, whose format need not be known to the software that + encounters them. At the start of every frame is an unique and + predefined identifier, a size descriptor that allows software to skip + unknown frames and a flags field. The flags describes encoding + details and if the frame should remain in the tag, should it be + unknown to the software, if the file is altered. + + The bitorder in ID3v2 is most significant bit first (MSB). The + byteorder in multibyte numbers is most significant byte first (e.g. + $12345678 would be encoded $12 34 56 78), also known as big endian + and network byte order. + + Overall tag structure: + + +-----------------------------+ + | Header (10 bytes) | + +-----------------------------+ + | Extended Header | + | (variable length, OPTIONAL) | + +-----------------------------+ + | Frames (variable length) | + +-----------------------------+ + | Padding | + | (variable length, OPTIONAL) | + +-----------------------------+ + | Footer (10 bytes, OPTIONAL) | + +-----------------------------+ + + In general, padding and footer are mutually exclusive. See details in + sections 3.3, 3.4 and 5. + + +3.1. ID3v2 header + + The first part of the ID3v2 tag is the 10 byte tag header, laid out + as follows: + + ID3v2/file identifier "ID3" + ID3v2 version $04 00 + ID3v2 flags %abcd0000 + ID3v2 size 4 * %0xxxxxxx + + The first three bytes of the tag are always "ID3", to indicate that + this is an ID3v2 tag, directly followed by the two version bytes. The + first byte of ID3v2 version is its major version, while the second + byte is its revision number. In this case this is ID3v2.4.0. All + revisions are backwards compatible while major versions are not. If + software with ID3v2.4.0 and below support should encounter version + five or higher it should simply ignore the whole tag. Version or + revision will never be $FF. + + The version is followed by the ID3v2 flags field, of which currently + four flags are used. + + + a - Unsynchronisation + + Bit 7 in the 'ID3v2 flags' indicates whether or not + unsynchronisation is applied on all frames (see section 6.1 for + details); a set bit indicates usage. + + + b - Extended header + + The second bit (bit 6) indicates whether or not the header is + followed by an extended header. The extended header is described in + section 3.2. A set bit indicates the presence of an extended + header. + + + c - Experimental indicator + + The third bit (bit 5) is used as an 'experimental indicator'. This + flag SHALL always be set when the tag is in an experimental stage. + + + d - Footer present + + Bit 4 indicates that a footer (section 3.4) is present at the very + end of the tag. A set bit indicates the presence of a footer. + + + All the other flags MUST be cleared. If one of these undefined flags + are set, the tag might not be readable for a parser that does not + know the flags function. + + The ID3v2 tag size is stored as a 32 bit synchsafe integer (section + 6.2), making a total of 28 effective bits (representing up to 256MB). + + The ID3v2 tag size is the sum of the byte length of the extended + header, the padding and the frames after unsynchronisation. If a + footer is present this equals to ('total size' - 20) bytes, otherwise + ('total size' - 10) bytes. + + An ID3v2 tag can be detected with the following pattern: + $49 44 33 yy yy xx zz zz zz zz + Where yy is less than $FF, xx is the 'flags' byte and zz is less than + $80. + + +3.2. Extended header + + The extended header contains information that can provide further + insight in the structure of the tag, but is not vital to the correct + parsing of the tag information; hence the extended header is + optional. + + Extended header size 4 * %0xxxxxxx + Number of flag bytes $01 + Extended Flags $xx + + Where the 'Extended header size' is the size of the whole extended + header, stored as a 32 bit synchsafe integer. An extended header can + thus never have a size of fewer than six bytes. + + The extended flags field, with its size described by 'number of flag + bytes', is defined as: + + %0bcd0000 + + Each flag that is set in the extended header has data attached, which + comes in the order in which the flags are encountered (i.e. the data + for flag 'b' comes before the data for flag 'c'). Unset flags cannot + have any attached data. All unknown flags MUST be unset and their + corresponding data removed when a tag is modified. + + Every set flag's data starts with a length byte, which contains a + value between 0 and 127 ($00 - $7f), followed by data that has the + field length indicated by the length byte. If a flag has no attached + data, the value $00 is used as length byte. + + + b - Tag is an update + + If this flag is set, the present tag is an update of a tag found + earlier in the present file or stream. If frames defined as unique + are found in the present tag, they are to override any + corresponding ones found in the earlier tag. This flag has no + corresponding data. + + Flag data length $00 + + c - CRC data present + + If this flag is set, a CRC-32 [ISO-3309] data is included in the + extended header. The CRC is calculated on all the data between the + header and footer as indicated by the header's tag length field, + minus the extended header. Note that this includes the padding (if + there is any), but excludes the footer. The CRC-32 is stored as an + 35 bit synchsafe integer, leaving the upper four bits always + zeroed. + + Flag data length $05 + Total frame CRC 5 * %0xxxxxxx + + d - Tag restrictions + + For some applications it might be desired to restrict a tag in more + ways than imposed by the ID3v2 specification. Note that the + presence of these restrictions does not affect how the tag is + decoded, merely how it was restricted before encoding. If this flag + is set the tag is restricted as follows: + + Flag data length $01 + Restrictions %ppqrrstt + + p - Tag size restrictions + + 00 No more than 128 frames and 1 MB total tag size. + 01 No more than 64 frames and 128 KB total tag size. + 10 No more than 32 frames and 40 KB total tag size. + 11 No more than 32 frames and 4 KB total tag size. + + q - Text encoding restrictions + + 0 No restrictions + 1 Strings are only encoded with ISO-8859-1 [ISO-8859-1] or + UTF-8 [UTF-8]. + + r - Text fields size restrictions + + 00 No restrictions + 01 No string is longer than 1024 characters. + 10 No string is longer than 128 characters. + 11 No string is longer than 30 characters. + + Note that nothing is said about how many bytes is used to + represent those characters, since it is encoding dependent. If a + text frame consists of more than one string, the sum of the + strungs is restricted as stated. + + s - Image encoding restrictions + + 0 No restrictions + 1 Images are encoded only with PNG [PNG] or JPEG [JFIF]. + + t - Image size restrictions + + 00 No restrictions + 01 All images are 256x256 pixels or smaller. + 10 All images are 64x64 pixels or smaller. + 11 All images are exactly 64x64 pixels, unless required + otherwise. + + +3.3. Padding + + It is OPTIONAL to include padding after the final frame (at the end + of the ID3 tag), making the size of all the frames together smaller + than the size given in the tag header. A possible purpose of this + padding is to allow for adding a few additional frames or enlarge + existing frames within the tag without having to rewrite the entire + file. The value of the padding bytes must be $00. A tag MUST NOT have + any padding between the frames or between the tag header and the + frames. Furthermore it MUST NOT have any padding when a tag footer is + added to the tag. + + +3.4. ID3v2 footer + + To speed up the process of locating an ID3v2 tag when searching from + the end of a file, a footer can be added to the tag. It is REQUIRED + to add a footer to an appended tag, i.e. a tag located after all + audio data. The footer is a copy of the header, but with a different + identifier. + + ID3v2 identifier "3DI" + ID3v2 version $04 00 + ID3v2 flags %abcd0000 + ID3v2 size 4 * %0xxxxxxx + + +4. ID3v2 frame overview + + All ID3v2 frames consists of one frame header followed by one or more + fields containing the actual information. The header is always 10 + bytes and laid out as follows: + + Frame ID $xx xx xx xx (four characters) + Size 4 * %0xxxxxxx + Flags $xx xx + + The frame ID is made out of the characters capital A-Z and 0-9. + Identifiers beginning with "X", "Y" and "Z" are for experimental + frames and free for everyone to use, without the need to set the + experimental bit in the tag header. Bear in mind that someone else + might have used the same identifier as you. All other identifiers are + either used or reserved for future use. + + The frame ID is followed by a size descriptor containing the size of + the data in the final frame, after encryption, compression and + unsynchronisation. The size is excluding the frame header ('total + frame size' - 10 bytes) and stored as a 32 bit synchsafe integer. + + In the frame header the size descriptor is followed by two flag + bytes. These flags are described in section 4.1. + + There is no fixed order of the frames' appearance in the tag, + although it is desired that the frames are arranged in order of + significance concerning the recognition of the file. An example of + such order: UFID, TIT2, MCDI, TRCK ... + + A tag MUST contain at least one frame. A frame must be at least 1 + byte big, excluding the header. + + If nothing else is said, strings, including numeric strings and URLs + [URL], are represented as ISO-8859-1 [ISO-8859-1] characters in the + range $20 - $FF. Such strings are represented in frame descriptions + as <text string>, or <full text string> if newlines are allowed. If + nothing else is said newline character is forbidden. In ISO-8859-1 a + newline is represented, when allowed, with $0A only. + + Frames that allow different types of text encoding contains a text + encoding description byte. Possible encodings: + + $00 ISO-8859-1 [ISO-8859-1]. Terminated with $00. + $01 UTF-16 [UTF-16] encoded Unicode [UNICODE] with BOM. All + strings in the same frame SHALL have the same byteorder. + Terminated with $00 00. + $02 UTF-16BE [UTF-16] encoded Unicode [UNICODE] without BOM. + Terminated with $00 00. + $03 UTF-8 [UTF-8] encoded Unicode [UNICODE]. Terminated with $00. + + Strings dependent on encoding are represented in frame descriptions + as <text string according to encoding>, or <full text string + according to encoding> if newlines are allowed. Any empty strings of + type $01 which are NULL-terminated may have the Unicode BOM followed + by a Unicode NULL ($FF FE 00 00 or $FE FF 00 00). + + The timestamp fields are based on a subset of ISO 8601. When being as + precise as possible the format of a time string is + yyyy-MM-ddTHH:mm:ss (year, "-", month, "-", day, "T", hour (out of + 24), ":", minutes, ":", seconds), but the precision may be reduced by + removing as many time indicators as wanted. Hence valid timestamps + are + yyyy, yyyy-MM, yyyy-MM-dd, yyyy-MM-ddTHH, yyyy-MM-ddTHH:mm and + yyyy-MM-ddTHH:mm:ss. All time stamps are UTC. For durations, use + the slash character as described in 8601, and for multiple non- + contiguous dates, use multiple strings, if allowed by the frame + definition. + + The three byte language field, present in several frames, is used to + describe the language of the frame's content, according to ISO-639-2 + [ISO-639-2]. The language should be represented in lower case. If the + language is not known the string "XXX" should be used. + + All URLs [URL] MAY be relative, e.g. "picture.png", "../doc.txt". + + If a frame is longer than it should be, e.g. having more fields than + specified in this document, that indicates that additions to the + frame have been made in a later version of the ID3v2 standard. This + is reflected by the revision number in the header of the tag. + + +4.1. Frame header flags + + In the frame header the size descriptor is followed by two flag + bytes. All unused flags MUST be cleared. The first byte is for + 'status messages' and the second byte is a format description. If an + unknown flag is set in the first byte the frame MUST NOT be changed + without that bit cleared. If an unknown flag is set in the second + byte the frame is likely to not be readable. Some flags in the second + byte indicates that extra information is added to the header. These + fields of extra information is ordered as the flags that indicates + them. The flags field is defined as follows (l and o left out because + ther resemblence to one and zero): + + %0abc0000 %0h00kmnp + + Some frame format flags indicate that additional information fields + are added to the frame. This information is added after the frame + header and before the frame data in the same order as the flags that + indicates them. I.e. the four bytes of decompressed size will precede + the encryption method byte. These additions affects the 'frame size' + field, but are not subject to encryption or compression. + + The default status flags setting for a frame is, unless stated + otherwise, 'preserved if tag is altered' and 'preserved if file is + altered', i.e. %00000000. + + +4.1.1. Frame status flags + + a - Tag alter preservation + + This flag tells the tag parser what to do with this frame if it is + unknown and the tag is altered in any way. This applies to all + kinds of alterations, including adding more padding and reordering + the frames. + + 0 Frame should be preserved. + 1 Frame should be discarded. + + + b - File alter preservation + + This flag tells the tag parser what to do with this frame if it is + unknown and the file, excluding the tag, is altered. This does not + apply when the audio is completely replaced with other audio data. + + 0 Frame should be preserved. + 1 Frame should be discarded. + + + c - Read only + + This flag, if set, tells the software that the contents of this + frame are intended to be read only. Changing the contents might + break something, e.g. a signature. If the contents are changed, + without knowledge of why the frame was flagged read only and + without taking the proper means to compensate, e.g. recalculating + the signature, the bit MUST be cleared. + + +4.1.2. Frame format flags + + h - Grouping identity + + This flag indicates whether or not this frame belongs in a group + with other frames. If set, a group identifier byte is added to the + frame. Every frame with the same group identifier belongs to the + same group. + + 0 Frame does not contain group information + 1 Frame contains group information + + + k - Compression + + This flag indicates whether or not the frame is compressed. + A 'Data Length Indicator' byte MUST be included in the frame. + + 0 Frame is not compressed. + 1 Frame is compressed using zlib [zlib] deflate method. + If set, this requires the 'Data Length Indicator' bit + to be set as well. + + + m - Encryption + + This flag indicates whether or not the frame is encrypted. If set, + one byte indicating with which method it was encrypted will be + added to the frame. See description of the ENCR frame for more + information about encryption method registration. Encryption + should be done after compression. Whether or not setting this flag + requires the presence of a 'Data Length Indicator' depends on the + specific algorithm used. + + 0 Frame is not encrypted. + 1 Frame is encrypted. + + n - Unsynchronisation + + This flag indicates whether or not unsynchronisation was applied + to this frame. See section 6 for details on unsynchronisation. + If this flag is set all data from the end of this header to the + end of this frame has been unsynchronised. Although desirable, the + presence of a 'Data Length Indicator' is not made mandatory by + unsynchronisation. + + 0 Frame has not been unsynchronised. + 1 Frame has been unsyrchronised. + + p - Data length indicator + + This flag indicates that a data length indicator has been added to + the frame. The data length indicator is the value one would write + as the 'Frame length' if all of the frame format flags were + zeroed, represented as a 32 bit synchsafe integer. + + 0 There is no Data Length Indicator. + 1 A data length Indicator has been added to the frame. + + +5. Tag location + + The default location of an ID3v2 tag is prepended to the audio so + that players can benefit from the information when the data is + streamed. It is however possible to append the tag, or make a + prepend/append combination. When deciding upon where an unembedded + tag should be located, the following order of preference SHOULD be + considered. + + 1. Prepend the tag. + + 2. Prepend a tag with all vital information and add a second tag at + the end of the file, before tags from other tagging systems. The + first tag is required to have a SEEK frame. + + 3. Add a tag at the end of the file, before tags from other tagging + systems. + + In case 2 and 3 the tag can simply be appended if no other known tags + are present. The suggested method to find ID3v2 tags are: + + 1. Look for a prepended tag using the pattern found in section 3.1. + + 2. If a SEEK frame was found, use its values to guide further + searching. + + 3. Look for a tag footer, scanning from the back of the file. + + For every new tag that is found, the old tag should be discarded + unless the update flag in the extended header (section 3.2) is set. + + +6. Unsynchronisation + + The only purpose of unsynchronisation is to make the ID3v2 tag as + compatible as possible with existing software and hardware. There is + no use in 'unsynchronising' tags if the file is only to be processed + only by ID3v2 aware software and hardware. Unsynchronisation is only + useful with tags in MPEG 1/2 layer I, II and III, MPEG 2.5 and AAC + files. + + +6.1. The unsynchronisation scheme + + Whenever a false synchronisation is found within the tag, one zeroed + byte is inserted after the first false synchronisation byte. The + format of synchronisations that should be altered by ID3 encoders is + as follows: + + %11111111 111xxxxx + + and should be replaced with: + + %11111111 00000000 111xxxxx + + This has the side effect that all $FF 00 combinations have to be + altered, so they will not be affected by the decoding process. + Therefore all the $FF 00 combinations have to be replaced with the + $FF 00 00 combination during the unsynchronisation. + + To indicate usage of the unsynchronisation, the unsynchronisation + flag in the frame header should be set. This bit MUST be set if the + frame was altered by the unsynchronisation and SHOULD NOT be set if + unaltered. If all frames in the tag are unsynchronised the + unsynchronisation flag in the tag header SHOULD be set. It MUST NOT + be set if the tag has a frame which is not unsynchronised. + + Assume the first byte of the audio to be $FF. The special case when + the last byte of the last frame is $FF and no padding nor footer is + used will then introduce a false synchronisation. This can be solved + by adding a footer, adding padding or unsynchronising the frame and + add $00 to the end of the frame data, thus adding more byte to the + frame size than a normal unsynchronisation would. Although not + preferred, it is allowed to apply the last method on all frames + ending with $FF. + + It is preferred that the tag is either completely unsynchronised or + not unsynchronised at all. A completely unsynchronised tag has no + false synchonisations in it, as defined above, and does not end with + $FF. A completely non-unsynchronised tag contains no unsynchronised + frames, and thus the unsynchronisation flag in the header is cleared. + + Do bear in mind, that if compression or encryption is used, the + unsynchronisation scheme MUST be applied afterwards. When decoding an + unsynchronised frame, the unsynchronisation scheme MUST be reversed + first, encryption and decompression afterwards. + + +6.2. Synchsafe integers + + In some parts of the tag it is inconvenient to use the + unsychronisation scheme because the size of unsynchronised data is + not known in advance, which is particularly problematic with size + descriptors. The solution in ID3v2 is to use synchsafe integers, in + which there can never be any false synchs. Synchsafe integers are + integers that keep its highest bit (bit 7) zeroed, making seven bits + out of eight available. Thus a 32 bit synchsafe integer can store 28 + bits of information. + + Example: + + 255 (%11111111) encoded as a 16 bit synchsafe integer is 383 + (%00000001 01111111). + + +7. Copyright + + Copyright (C) Martin Nilsson 2000. All Rights Reserved. + + This document and translations of it may be copied and furnished to + others, and derivative works that comment on or otherwise explain it + or assist in its implementation may be prepared, copied, published + and distributed, in whole or in part, without restriction of any + kind, provided that a reference to this document is included on all + such copies and derivative works. However, this document itself may + not be modified in any way and reissued as the original document. + + The limited permissions granted above are perpetual and will not be + revoked. + + This document and the information contained herein is provided on an + 'AS IS' basis and THE AUTHORS DISCLAIMS ALL WARRANTIES, EXPRESS OR + IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF + THE INFORMATION HEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED + WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. + + +8. References + + [ID3v2] Martin Nilsson, 'ID3v2 informal standard'. + + <url:http://www.id3.org/id3v2.3.0.txt> + + [ISO-639-2] ISO/FDIS 639-2. + 'Codes for the representation of names of languages, Part 2: Alpha-3 + code.' Technical committee / subcommittee: TC 37 / SC 2 + + [ISO-3309] ISO 3309 + 'Information Processing Systems--Data Communication High-Level Data + Link Control Procedure--Frame Structure', IS 3309, October 1984, 3rd + Edition. + + [ISO-8859-1] ISO/IEC DIS 8859-1. + '8-bit single-byte coded graphic character sets, Part 1: Latin + alphabet No. 1.' Technical committee / subcommittee: JTC 1 / SC 2 + + [JFIF] 'JPEG File Interchange Format, version 1.02' + + <url:http://www.w3.org/Graphics/JPEG/jfif.txt> + + [KEYWORDS] S. Bradner, 'Key words for use in RFCs to Indicate + Requirement Levels', RFC 2119, March 1997. + + <url:ftp://ftp.isi.edu/in-notes/rfc2119.txt> + + [MPEG] ISO/IEC 11172-3:1993. + 'Coding of moving pictures and associated audio for digital storage + media at up to about 1,5 Mbit/s, Part 3: Audio.' + Technical committee / subcommittee: JTC 1 / SC 29 + and + ISO/IEC 13818-3:1995 + 'Generic coding of moving pictures and associated audio information, + Part 3: Audio.' + Technical committee / subcommittee: JTC 1 / SC 29 + and + ISO/IEC DIS 13818-3 + 'Generic coding of moving pictures and associated audio information, + Part 3: Audio (Revision of ISO/IEC 13818-3:1995)' + + [PNG] 'Portable Network Graphics, version 1.0' + + <url:http://www.w3.org/TR/REC-png-multi.html> + + [UNICODE] The Unicode Consortium, + 'The Unicode Standard Version 3.0', ISBN 0-201-61633-5. + + <url:http://www.unicode.org/unicode/standard/versions/Unicode3.0.htm> + + [URL] T. Berners-Lee, L. Masinter & M. McCahill, 'Uniform Resource + Locators (URL)', RFC 1738, December 1994. + + <url:ftp://ftp.isi.edu/in-notes/rfc1738.txt> + + [UTF-8] F. Yergeau, 'UTF-8, a transformation format of ISO 10646', + RFC 2279, January 1998. + + <url:ftp://ftp.isi.edu/in-notes/rfc2279.txt> + + [UTF-16] F. Yergeau, 'UTF-16, an encoding of ISO 10646', RFC 2781, + February 2000. + + <url:ftp://ftp.isi.edu/in-notes/rfc2781.txt> + + [ZLIB] P. Deutsch, Aladdin Enterprises & J-L. Gailly, 'ZLIB + Compressed Data Format Specification version 3.3', RFC 1950, + May 1996. + + <url:ftp://ftp.isi.edu/in-notes/rfc1950.txt> + + +9. Author's Address + + Written by + + Martin Nilsson + Rydsvägen 246 C. 30 + SE-584 34 Linköping + Sweden + + Email: nilsson@id3.org + diff --git a/gst/id3demux/id3v2frames.c b/gst/id3demux/id3v2frames.c new file mode 100644 index 00000000..fec70123 --- /dev/null +++ b/gst/id3demux/id3v2frames.c @@ -0,0 +1,382 @@ +/* -*- Mode: C; tab-width: 2; indent-tabs-mode: t; c-basic-offset: 2 -*- */ +/* Copyright 2005 Jan Schmidt <thaytan@mad.scientist.com> + * Copyright 2002,2003 Scott Wheeler <wheeler@kde.org> (portions from taglib) + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Library General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Library General Public License for more details. + * + * You should have received a copy of the GNU Library General Public + * License along with this library; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 02111-1307, USA. + */ + +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include <string.h> +#include <gst/tag/tag.h> + +#ifdef HAVE_ZLIB +#include <zlib.h> +#endif + +#include "id3tags.h" + +GST_DEBUG_CATEGORY_EXTERN (id3demux_debug); +#define GST_CAT_DEFAULT (id3demux_debug) + +static gchar *parse_comment_frame (ID3TagsWorking * work); +static gchar *parse_text_identification_frame (ID3TagsWorking * work); +static gboolean id3v2_tag_to_taglist (ID3TagsWorking * work, + const gchar * tag_name, gchar * tag_str); +static void parse_split_strings (ID3TagsWorking * work, guint8 encoding, + gchar ** field1, gchar ** field2); + +#define ID3V2_ENCODING_ISO8859 0x00 +#define ID3V2_ENCODING_UTF16 0x01 +#define ID3V2_ENCODING_UTF16BE 0x02 +#define ID3V2_ENCODING_UTF8 0x03 + +extern guint read_synch_uint (guint8 * data, guint size); + +gboolean +id3demux_id3v2_parse_frame (ID3TagsWorking * work) +{ + const gchar *tag_name; + gboolean result = FALSE; + gint i; + guint8 *frame_data = work->hdr.frame_data; + guint frame_data_size = work->cur_frame_size; + gchar *tag_str = NULL; + + /* Check that the frame id is valid */ + for (i = 0; i < 5 && work->frame_id[i] != '\0'; i++) { + if (!g_ascii_isalnum (work->frame_id[i])) { + GST_DEBUG ("Encountered invalid frame_id"); + return FALSE; + } + } + + /* Can't handle encrypted frames right now */ + if (work->frame_flags & ID3V2_FRAME_FORMAT_ENCRYPTION) { + GST_WARNING ("Encrypted frames are not supported"); + return FALSE; + } + + if (work->frame_flags & ID3V2_FRAME_FORMAT_UNSYNCHRONISATION) { + GST_WARNING ("ID3v2 frame with unsupported unsynchronisation applied. " + "May fail badly"); + } + + tag_name = gst_tag_from_id3_tag (work->frame_id); + if (tag_name == NULL) + return FALSE; + + if (work->frame_flags & (ID3V2_FRAME_FORMAT_COMPRESSION | + ID3V2_FRAME_FORMAT_DATA_LENGTH_INDICATOR)) { + if (work->hdr.frame_data_size <= 4) + return FALSE; + work->parse_size = read_synch_uint (frame_data, 4); + frame_data += 4; + frame_data_size -= 4; + } else + work->parse_size = frame_data_size; + + if (work->frame_flags & ID3V2_FRAME_FORMAT_COMPRESSION) { + uLongf destSize = work->parse_size; + Bytef *dest, *src; + + work->parse_data = g_malloc (work->parse_size); + g_return_val_if_fail (work->parse_data != NULL, FALSE); + + dest = (Bytef *) work->parse_data; + src = (Bytef *) frame_data; + + if (uncompress (dest, &destSize, src, frame_data_size) != Z_OK) { + g_free (work->parse_data); + return FALSE; + } + } else { + work->parse_data = work->hdr.frame_data; + } + + if (work->frame_id[0] == 'T') { + if (strcmp (work->frame_id, "TXXX") != 0) { + /* Text identification frame */ + tag_str = parse_text_identification_frame (work); + } else { + /* Handle user text frame */ + } + } else if (!strcmp (work->frame_id, "COMM")) { + /* Comment */ + tag_str = parse_comment_frame (work); + } else if (!strcmp (work->frame_id, "APIC")) { + /* Attached picture */ + } else if (!strcmp (work->frame_id, "RVA2")) { + /* Relative volume */ + } else if (!strcmp (work->frame_id, "UFID")) { + /* Unique file identifier */ + } + + if (work->frame_flags & ID3V2_FRAME_FORMAT_COMPRESSION) { + g_free (work->parse_data); + } + + if (tag_str != NULL) { + /* g_print ("Tag %s value %s\n", tag_name, tag_str); */ + result = id3v2_tag_to_taglist (work, tag_name, tag_str); + g_free (tag_str); + } + + return result; +} + +static gchar * +parse_comment_frame (ID3TagsWorking * work) +{ + guint8 encoding; + gchar language[4]; + gchar *description = NULL; + gchar *text = NULL; + gchar *out_str = NULL; + + if (work->parse_size < 6) + return NULL; + + encoding = work->parse_data[0]; + language[0] = work->parse_data[1]; + language[1] = work->parse_data[2]; + language[2] = work->parse_data[3]; + language[3] = 0; + + parse_split_strings (work, encoding, &description, &text); + + if (text == NULL || description == NULL) { + GST_ERROR ("Failed to decode comment frame"); + goto fail; + } + + if (!g_utf8_validate (text, -1, NULL)) { + GST_ERROR ("Converted string is not valid utf-8"); + goto fail; + } else { + if (strlen (description) > 0 && g_utf8_validate (description, -1, NULL)) { + out_str = g_strdup_printf ("Description: %s\nComment: %s", + description, text); + } else { + out_str = g_strdup (text); + } + } + +fail: + g_free (description); + g_free (text); + + return out_str; +} + +static gchar * +parse_text_identification_frame (ID3TagsWorking * work) +{ + guchar encoding; + gchar *text = NULL; + + if (work->parse_size < 2) + return NULL; + + encoding = work->parse_data[0]; + + switch (encoding) { + case ID3V2_ENCODING_ISO8859: + text = g_convert ((gchar *) (work->parse_data + 1), + work->parse_size - 1, "UTF-8", "ISO-8859-1", NULL, NULL, NULL); + break; + case ID3V2_ENCODING_UTF8: + text = g_strndup ((gchar *) (work->parse_data + 1), work->parse_size - 1); + break; + case ID3V2_ENCODING_UTF16: + text = g_convert ((gchar *) (work->parse_data + 1), + work->parse_size - 1, "UTF-8", "UTF-16", NULL, NULL, NULL); + break; + case ID3V2_ENCODING_UTF16BE: + text = g_convert ((gchar *) (work->parse_data + 1), + work->parse_size - 1, "UTF-8", "UTF-16BE", NULL, NULL, NULL); + break; + } + + if (text != NULL && !g_utf8_validate (text, -1, NULL)) { + GST_ERROR ("Converted string is not valid utf-8"); + g_free (text); + text = NULL; + } + + return text; +} + +static gboolean +id3v2_tag_to_taglist (ID3TagsWorking * work, const gchar * tag_name, + gchar * tag_str) +{ + GType tag_type = gst_tag_get_type (tag_name); + GstTagList *tag_list = work->tags; + + switch (tag_type) { + case G_TYPE_UINT: + { + guint tmp; + gchar *check; + + tmp = strtoul ((char *) tag_str, &check, 10); + + if (strcmp (tag_name, GST_TAG_DATE) == 0) { + GDate *d; + + if (*check != '\0') + break; + if (tmp == 0) + break; + d = g_date_new_dmy (1, 1, tmp); + tmp = g_date_get_julian (d); + g_date_free (d); + } else if (strcmp (tag_name, GST_TAG_TRACK_NUMBER) == 0) { + if (*check == '/') { + guint total; + + check++; + total = strtoul (check, &check, 10); + if (*check != '\0') + break; + + gst_tag_list_add (tag_list, GST_TAG_MERGE_APPEND, + GST_TAG_TRACK_COUNT, total, NULL); + } + } else if (strcmp (tag_name, GST_TAG_ALBUM_VOLUME_NUMBER) == 0) { + if (*check == '/') { + guint total; + + check++; + total = strtoul (check, &check, 10); + if (*check != '\0') + break; + + gst_tag_list_add (tag_list, GST_TAG_MERGE_APPEND, + GST_TAG_ALBUM_VOLUME_COUNT, total, NULL); + } + } + + if (*check != '\0') + break; + + gst_tag_list_add (tag_list, GST_TAG_MERGE_APPEND, tag_name, tmp, NULL); + break; + } + case G_TYPE_UINT64: + { + guint64 tmp; + + g_assert (strcmp (tag_name, GST_TAG_DURATION) == 0); + tmp = strtoul ((char *) tag_str, NULL, 10); + if (tmp == 0) { + break; + } + gst_tag_list_add (tag_list, GST_TAG_MERGE_APPEND, + GST_TAG_DURATION, tmp * 1000 * 1000, NULL); + break; + } + case G_TYPE_STRING:{ + gst_tag_list_add (tag_list, GST_TAG_MERGE_APPEND, + tag_name, (const gchar *) tag_str, NULL); + break; + } + /* handles GST_TYPE_DATE and anything else */ + default:{ + GValue src = { 0, }; + GValue dest = { 0, }; + + g_value_init (&src, G_TYPE_STRING); + g_value_set_string (&src, (const gchar *) tag_str); + + g_value_init (&dest, tag_type); + if (g_value_transform (&src, &dest)) { + gst_tag_list_add_values (tag_list, GST_TAG_MERGE_APPEND, + tag_name, &dest, NULL); + } else { + GST_WARNING ("Failed to transform tag from string to type '%s'", + g_type_name (tag_type)); + } + g_value_unset (&src); + g_value_unset (&dest); + break; + } + } + + return TRUE; +} + +static void +parse_split_strings (ID3TagsWorking * work, guint8 encoding, + gchar ** field1, gchar ** field2) +{ + guint text_pos; + + *field1 = *field2 = NULL; + + switch (encoding) { + case ID3V2_ENCODING_ISO8859: + for (text_pos = 4; text_pos < work->parse_size - 1; text_pos++) { + if (work->parse_data[text_pos] == 0) { + *field1 = g_convert ((gchar *) (work->parse_data + 4), + text_pos - 4, "UTF-8", "ISO-8859-1", NULL, NULL, NULL); + *field2 = g_convert ((gchar *) (work->parse_data + text_pos + 5), + work->parse_size - text_pos - 5, + "UTF-8", "ISO-8859-1", NULL, NULL, NULL); + break; + } + } + break; + case ID3V2_ENCODING_UTF8: + *field1 = g_strndup ((gchar *) (work->parse_data + 4), + work->parse_size - 4); + text_pos = 4 + strlen (*field1) + 1; /* Offset by one more for the null */ + if (text_pos < work->parse_size) { + *field2 = g_strndup ((gchar *) (work->parse_data + text_pos), + work->parse_size - text_pos); + } + break; + case ID3V2_ENCODING_UTF16: + case ID3V2_ENCODING_UTF16BE: + { + /* Find '\0\0' terminator */ + for (text_pos = 4; text_pos < work->parse_size - 2; text_pos++) { + if (work->parse_data[text_pos] == 0 && + work->parse_data[text_pos + 1] == 0) { + /* found our delimiter */ + if (encoding == ID3V2_ENCODING_UTF16) { + *field1 = g_convert ((gchar *) (work->parse_data + 4), + text_pos - 4, "UTF-8", "UTF-16", NULL, NULL, NULL); + *field2 = g_convert ((gchar *) (work->parse_data + text_pos + 6), + work->parse_size - text_pos - 6, + "UTF-8", "UTF-16", NULL, NULL, NULL); + } else { + *field1 = g_convert ((gchar *) (work->parse_data + 4), + text_pos - 4, "UTF-8", "UTF-16BE", NULL, NULL, NULL); + *field2 = g_convert ((gchar *) (work->parse_data + text_pos + 6), + work->parse_size - text_pos - 6, + "UTF-8", "UTF-16BE", NULL, NULL, NULL); + } + break; + } + } + break; + } + } +} |