FFmpeg
flac_picture.c
Go to the documentation of this file.
1 /*
2  * Raw FLAC picture parser
3  * Copyright (c) 2001 Fabrice Bellard
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
22 #include "libavutil/intreadwrite.h"
23 #include "libavcodec/bytestream.h"
24 #include "libavcodec/png.h"
25 #include "avformat.h"
26 #include "demux.h"
27 #include "flac_picture.h"
28 #include "id3v2.h"
29 #include "internal.h"
30 
31 #define MAX_TRUNC_PICTURE_SIZE (500 * 1024 * 1024)
32 
33 int ff_flac_parse_picture(AVFormatContext *s, uint8_t **bufp, int buf_size,
34  int truncate_workaround)
35 {
36  const CodecMime *mime = ff_id3v2_mime_tags;
37  enum AVCodecID id = AV_CODEC_ID_NONE;
38  AVBufferRef *data = NULL;
39  uint8_t mimetype[64], *buf = *bufp;
40  const uint8_t *desc = NULL;
41  GetByteContext g;
42  AVStream *st;
43  int width, height, ret = 0;
44  unsigned int type;
45  uint32_t len, left, trunclen = 0;
46 
47  if (buf_size < 34) {
48  av_log(s, AV_LOG_ERROR, "Attached picture metadata block too short\n");
49  if (s->error_recognition & AV_EF_EXPLODE)
50  return AVERROR_INVALIDDATA;
51  return 0;
52  }
53 
54  bytestream2_init(&g, buf, buf_size);
55 
56  /* read the picture type */
57  type = bytestream2_get_be32u(&g);
58  if (type >= FF_ARRAY_ELEMS(ff_id3v2_picture_types)) {
59  av_log(s, AV_LOG_ERROR, "Invalid picture type: %d.\n", type);
60  if (s->error_recognition & AV_EF_EXPLODE) {
61  return AVERROR_INVALIDDATA;
62  }
63  type = 0;
64  }
65 
66  /* picture mimetype */
67  len = bytestream2_get_be32u(&g);
68  if (len <= 0 || len >= sizeof(mimetype)) {
69  av_log(s, AV_LOG_ERROR, "Could not read mimetype from an attached "
70  "picture.\n");
71  if (s->error_recognition & AV_EF_EXPLODE)
72  return AVERROR_INVALIDDATA;
73  return 0;
74  }
75  if (len + 24 > bytestream2_get_bytes_left(&g)) {
76  av_log(s, AV_LOG_ERROR, "Attached picture metadata block too short\n");
77  if (s->error_recognition & AV_EF_EXPLODE)
78  return AVERROR_INVALIDDATA;
79  return 0;
80  }
81  bytestream2_get_bufferu(&g, mimetype, len);
82  mimetype[len] = 0;
83 
84  while (mime->id != AV_CODEC_ID_NONE) {
85  if (!strncmp(mime->str, mimetype, sizeof(mimetype))) {
86  id = mime->id;
87  break;
88  }
89  mime++;
90  }
91  if (id == AV_CODEC_ID_NONE) {
92  av_log(s, AV_LOG_ERROR, "Unknown attached picture mimetype: %s.\n",
93  mimetype);
94  if (s->error_recognition & AV_EF_EXPLODE)
95  return AVERROR_INVALIDDATA;
96  return 0;
97  }
98 
99  /* picture description */
100  len = bytestream2_get_be32u(&g);
101  if (len > bytestream2_get_bytes_left(&g) - 20) {
102  av_log(s, AV_LOG_ERROR, "Attached picture metadata block too short\n");
103  if (s->error_recognition & AV_EF_EXPLODE)
104  return AVERROR_INVALIDDATA;
105  return 0;
106  }
107  if (len > 0) {
108  desc = g.buffer;
109  bytestream2_skipu(&g, len);
110  }
111 
112  /* picture metadata */
113  width = bytestream2_get_be32u(&g);
114  ((uint8_t*)g.buffer)[-4] = '\0'; // NUL-terminate desc.
115  height = bytestream2_get_be32u(&g);
116  bytestream2_skipu(&g, 8);
117 
118  /* picture data */
119  len = bytestream2_get_be32u(&g);
120 
121  left = bytestream2_get_bytes_left(&g);
122  if (len <= 0 || len > left) {
123  if (len > MAX_TRUNC_PICTURE_SIZE || len >= INT_MAX - AV_INPUT_BUFFER_PADDING_SIZE) {
124  av_log(s, AV_LOG_ERROR, "Attached picture metadata block too big %u\n", len);
125  if (s->error_recognition & AV_EF_EXPLODE)
126  return AVERROR_INVALIDDATA;
127  return 0;
128  }
129 
130  // Workaround bug for flac muxers that writs truncated metadata picture block size if
131  // the picture size do not fit in 24 bits. lavf flacenc used to have the issue and based
132  // on existing broken files other unknown flac muxers seems to truncate also.
133  if (truncate_workaround &&
134  s->strict_std_compliance <= FF_COMPLIANCE_NORMAL &&
135  len > left && (len & 0xffffff) == left) {
136  av_log(s, AV_LOG_INFO, "Correcting truncated metadata picture size from %u to %u\n", left, len);
137  trunclen = len - left;
138  } else {
139  av_log(s, AV_LOG_ERROR, "Attached picture metadata block too short\n");
140  if (s->error_recognition & AV_EF_EXPLODE)
141  return AVERROR_INVALIDDATA;
142  return 0;
143  }
144  }
145  if (trunclen == 0 && len >= buf_size - (buf_size >> 4)) {
146  data = av_buffer_create(buf, buf_size + AV_INPUT_BUFFER_PADDING_SIZE,
147  av_buffer_default_free, NULL, 0);
148  if (!data)
149  return AVERROR(ENOMEM);
150  *bufp = NULL;
151  data->data += bytestream2_tell(&g);
152  data->size = len + AV_INPUT_BUFFER_PADDING_SIZE;
153  } else {
154  if (!(data = av_buffer_alloc(len + AV_INPUT_BUFFER_PADDING_SIZE)))
155  return AVERROR(ENOMEM);
156 
157  if (trunclen == 0) {
158  bytestream2_get_bufferu(&g, data->data, len);
159  } else {
160  // If truncation was detected copy all data from block and
161  // read missing bytes not included in the block size.
162  bytestream2_get_bufferu(&g, data->data, left);
163  if (avio_read(s->pb, data->data + len - trunclen, trunclen) < trunclen)
164  RETURN_ERROR(AVERROR_INVALIDDATA);
165  }
166  }
167  memset(data->data + len, 0, AV_INPUT_BUFFER_PADDING_SIZE);
168 
169  if (AV_RB64(data->data) == PNGSIG)
170  id = AV_CODEC_ID_PNG;
171 
172  ret = ff_add_attached_pic(s, NULL, NULL, &data, 0);
173  if (ret < 0)
174  RETURN_ERROR(ret);
175 
176  st = s->streams[s->nb_streams - 1];
177  st->codecpar->codec_id = id;
178  st->codecpar->width = width;
179  st->codecpar->height = height;
180  av_dict_set(&st->metadata, "comment", ff_id3v2_picture_types[type], 0);
181  if (desc)
182  av_dict_set(&st->metadata, "title", desc, 0);
183 
184  return 0;
185 
186 fail:
187  av_buffer_unref(&data);
188 
189  return ret;
190 }
AV_EF_EXPLODE
#define AV_EF_EXPLODE
abort decoding on minor error detection
Definition: defs.h:51
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
GetByteContext
Definition: bytestream.h:33
bytestream2_skipu
static av_always_inline void bytestream2_skipu(GetByteContext *g, unsigned int size)
Definition: bytestream.h:174
id3v2.h
data
const char data[16]
Definition: mxf.c:146
CodecMime
Definition: internal.h:54
fail
#define fail()
Definition: checkasm.h:134
type
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf type
Definition: writing_filters.txt:86
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
FF_ARRAY_ELEMS
#define FF_ARRAY_ELEMS(a)
Definition: sinewin_tablegen.c:29
ff_add_attached_pic
int ff_add_attached_pic(AVFormatContext *s, AVStream *st, AVIOContext *pb, AVBufferRef **buf, int size)
Add an attached pic to an AVStream.
Definition: demux_utils.c:116
width
#define width
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:256
g
const char * g
Definition: vf_curves.c:127
AVCodecParameters::width
int width
Video only.
Definition: codec_par.h:128
av_buffer_default_free
void av_buffer_default_free(void *opaque, uint8_t *data)
Default free callback, which calls av_free() on the buffer data.
Definition: buffer.c:72
flac_picture.h
AV_CODEC_ID_PNG
@ AV_CODEC_ID_PNG
Definition: codec_id.h:113
AVFormatContext
Format I/O context.
Definition: avformat.h:1104
internal.h
AVStream::codecpar
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:861
NULL
#define NULL
Definition: coverity.c:32
av_buffer_unref
void av_buffer_unref(AVBufferRef **buf)
Free a given reference and automatically free the buffer if there are no more references to it.
Definition: buffer.c:139
AVStream::metadata
AVDictionary * metadata
Definition: avformat.h:918
ff_id3v2_picture_types
const char *const ff_id3v2_picture_types[21]
Definition: id3v2.c:108
ff_flac_parse_picture
int ff_flac_parse_picture(AVFormatContext *s, uint8_t **bufp, int buf_size, int truncate_workaround)
Parse a FLAC METADATA_BLOCK_PICTURE.
Definition: flac_picture.c:33
av_buffer_create
AVBufferRef * av_buffer_create(uint8_t *data, size_t size, void(*free)(void *opaque, uint8_t *data), void *opaque, int flags)
Create an AVBuffer from an existing array.
Definition: buffer.c:55
ff_id3v2_mime_tags
const CodecMime ff_id3v2_mime_tags[]
Definition: id3v2.c:132
bytestream2_get_bytes_left
static av_always_inline int bytestream2_get_bytes_left(GetByteContext *g)
Definition: bytestream.h:158
AVCodecID
AVCodecID
Identify the syntax and semantics of the bitstream.
Definition: codec_id.h:49
bytestream2_tell
static av_always_inline int bytestream2_tell(GetByteContext *g)
Definition: bytestream.h:192
FF_COMPLIANCE_NORMAL
#define FF_COMPLIANCE_NORMAL
Definition: defs.h:60
height
#define height
av_buffer_alloc
AVBufferRef * av_buffer_alloc(size_t size)
Allocate an AVBuffer of the given size using av_malloc().
Definition: buffer.c:77
PNGSIG
#define PNGSIG
Definition: png.h:49
AV_LOG_INFO
#define AV_LOG_INFO
Standard information.
Definition: log.h:191
RETURN_ERROR
#define RETURN_ERROR(code)
Definition: flac_picture.h:27
AV_CODEC_ID_NONE
@ AV_CODEC_ID_NONE
Definition: codec_id.h:50
AVCodecParameters::height
int height
Definition: codec_par.h:129
demux.h
len
int len
Definition: vorbis_enc_data.h:426
ret
ret
Definition: filter_design.txt:187
AVStream
Stream structure.
Definition: avformat.h:838
avformat.h
AV_INPUT_BUFFER_PADDING_SIZE
#define AV_INPUT_BUFFER_PADDING_SIZE
Definition: defs.h:40
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
id
enum AVCodecID id
Definition: dts2pts_bsf.c:364
avio_read
int avio_read(AVIOContext *s, unsigned char *buf, int size)
Read size bytes from AVIOContext into buf.
Definition: aviobuf.c:633
CodecMime::str
char str[32]
Definition: internal.h:55
MAX_TRUNC_PICTURE_SIZE
#define MAX_TRUNC_PICTURE_SIZE
Definition: flac_picture.c:31
CodecMime::id
enum AVCodecID id
Definition: internal.h:56
desc
const char * desc
Definition: libsvtav1.c:83
AVBufferRef
A reference to a data buffer.
Definition: buffer.h:82
bytestream2_get_bufferu
static av_always_inline unsigned int bytestream2_get_bufferu(GetByteContext *g, uint8_t *dst, unsigned int size)
Definition: bytestream.h:277
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: codec_par.h:62
png.h
av_dict_set
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
Definition: dict.c:86
bytestream.h
bytestream2_init
static av_always_inline void bytestream2_init(GetByteContext *g, const uint8_t *buf, int buf_size)
Definition: bytestream.h:137
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
AV_RB64
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_WL16 uint64_t_TMPL AV_RB64
Definition: bytestream.h:95
Generated on Tue Feb 28 2023 21:34:04 for FFmpeg by   doxygen 1.8.17