1 /*****************************************************************************
3 *****************************************************************************
4 * Copyright (C) 2010-2017 L-SMASH project
6 * Authors: Yusuke Nakamura <muken.the.vfrmaniac@gmail.com>
8 * Permission to use, copy, modify, and/or distribute this software for any
9 * purpose with or without fee is hereby granted, provided that the above
10 * copyright notice and this permission notice appear in all copies.
12 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
13 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
14 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
15 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
16 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
17 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
18 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
19 *****************************************************************************/
21 /* This file is available under an ISC license. */
26 /* For generating creation_time and modification_time.
27 * According to ISO/IEC-14496-5-2001, the difference between Unix time and Mac OS time is 2082758400.
28 * However this is wrong and 2082844800 is correct. */
30 #define ISOM_MAC_EPOCH_OFFSET 2082844800
34 /* aliases internally used only for convenience */
35 typedef struct lsmash_file_tag isom_file_abstract_t
;
36 typedef struct lsmash_root_tag isom_root_abstract_t
;
37 typedef struct isom_unknown_box_tag isom_unknown_t
;
39 typedef struct lsmash_box_tag isom_box_t
;
40 typedef struct isom_unknown_box_tag isom_unknown_box_t
;
41 typedef struct isom_mdhd_tag isom_mdhd_t
;
42 typedef struct isom_stbl_tag isom_stbl_t
;
44 typedef void (*isom_extension_destructor_t
)( void *extension_data
);
45 typedef int (*isom_extension_writer_t
)( lsmash_bs_t
*bs
, isom_box_t
*box
);
47 typedef int (*isom_bitrate_updater_t
)( isom_stbl_t
*stbl
, isom_mdhd_t
*mdhd
, uint32_t sample_description_index
);
49 /* If size is 1, then largesize is actual size.
50 * If size is 0, then this box is the last one in the file. */
51 #define ISOM_BASEBOX_COMMON \
52 const lsmash_class_t *class; \
53 lsmash_root_t *root; /* pointer to root */ \
54 lsmash_file_t *file; /* pointer to file */ \
55 isom_box_t *parent; /* pointer to the parent box of this box */ \
56 void *nonexist_ptr; /* pointer to non-existing box constant */ \
57 uint8_t *binary; /* used only when LSMASH_BINARY_CODED_BOX */ \
58 isom_extension_destructor_t destruct; /* box specific destructor */ \
59 isom_extension_writer_t write; /* box specific writer */ \
60 size_t offset_in_parent; /* offset of this box in parent box struct */ \
61 uint32_t manager; /* flags for L-SMASH */ \
62 uint64_t precedence; /* precedence of the box position */ \
63 uint64_t pos; /* starting position of this box in the file */ \
64 lsmash_entry_list_t extensions; /* extension boxes */ \
65 uint64_t size; /* the number of bytes in this box */ \
66 lsmash_box_type_t type
68 #define ISOM_FULLBOX_COMMON \
69 ISOM_BASEBOX_COMMON; \
70 uint8_t version; /* Basically, version is either 0 or 1 */ \
71 uint32_t flags /* In the actual structure of box, flags is 24 bits. */
73 #define ISOM_BASEBOX_COMMON_SIZE 8
74 #define ISOM_FULLBOX_COMMON_SIZE 12
75 #define ISOM_LIST_FULLBOX_COMMON_SIZE 16
77 /* flags for L-SMASH */
78 #define LSMASH_UNKNOWN_BOX 0x001
79 #define LSMASH_ABSENT_IN_FILE 0x002
80 #define LSMASH_QTFF_BASE 0x004
81 #define LSMASH_VIDEO_DESCRIPTION 0x008
82 #define LSMASH_AUDIO_DESCRIPTION 0x010
83 #define LSMASH_FULLBOX 0x020
84 #define LSMASH_LAST_BOX 0x040
85 #define LSMASH_INCOMPLETE_BOX 0x080
86 #define LSMASH_BINARY_CODED_BOX 0x100
87 #define LSMASH_PLACEHOLDER 0x200
88 #define LSMASH_WRITTEN_BOX 0x400
89 #define LSMASH_NON_EXISTING_BOX 0x800 /* This flag indicates a read only non-existing box constant.
90 * Don't use for wild boxes other than non-existing box constants
91 * because this flags prevents attempting to freeing its box. */
93 /* Use these macros for checking existences of boxes.
94 * If the result of LSMASH_IS_EXISTING_BOX is 0, the evaluated box is read only.
95 * If the result of LSMASH_IS_NON_EXISTING_BOX is 1, the evaluated box is read only. */
96 #define LSMASH_IS_EXISTING_BOX( box_ptr ) \
97 ((box_ptr) && !((box_ptr)->manager & LSMASH_NON_EXISTING_BOX))
98 #define LSMASH_IS_NON_EXISTING_BOX( box_ptr ) \
99 (!(box_ptr) || ((box_ptr)->manager & LSMASH_NON_EXISTING_BOX))
101 #define LSMASH_IS_BOX_ADDITION_SUCCESS( box_ptr ) \
102 (!((box_ptr)->manager & LSMASH_NON_EXISTING_BOX))
103 #define LSMASH_IS_BOX_ADDITION_FAILURE( box_ptr ) \
104 (!!((box_ptr)->manager & LSMASH_NON_EXISTING_BOX))
106 /* Use this macro for disabling a predefined child box in struct.
107 * Predefined childs must not be NULL for safety. */
108 #define LSMASH_MAKE_BOX_NON_EXISTING( box_ptr ) \
109 (box_ptr) = (void *)(box_ptr)->nonexist_ptr
111 /* 12-byte ISO reserved value:
112 * 0xXXXXXXXX-0011-0010-8000-00AA00389B71 */
113 static const uint8_t static_lsmash_iso_12_bytes
[12]
114 = { 0x00, 0x11, 0x00, 0x10, 0x80, 0x00, 0x00, 0xAA, 0x00, 0x38, 0x9B, 0x71 };
115 #define LSMASH_ISO_12_BYTES static_lsmash_iso_12_bytes
117 /* L-SMASH original 12-byte QuickTime file format value for CODEC discrimination mainly:
118 * 0xXXXXXXXX-0F11-4DA5-BF4E-F2C48C6AA11E */
119 static const uint8_t static_lsmash_qtff_12_bytes
[12]
120 = { 0x0F, 0x11, 0x4D, 0xA5, 0xBF, 0x4E, 0xF2, 0xC4, 0x8C, 0x6A, 0xA1, 0x1E };
121 #define LSMASH_QTFF_12_BYTES static_lsmash_qtff_12_bytes
123 struct lsmash_box_tag
129 * This structure is for boxes we don't know or define yet.
130 * This box must be always appended as an extension box. */
131 struct isom_unknown_box_tag
134 uint32_t unknown_size
;
135 uint8_t *unknown_field
;
139 * This box identifies the specifications to which this file complies.
140 * This box shall occur before any variable-length box.
141 * In the absence of this box, the file is QuickTime file format or MP4 version 1 file format.
142 * In MP4 version 1 file format, Object Descriptor Box is mandatory.
143 * In QuickTime file format, Object Descriptor Box isn't defined.
144 * Therefore, if this box and an Object Descriptor Box are absent in the file, the file shall be QuickTime file format. */
148 uint32_t major_brand
; /* brand identifier */
149 uint32_t minor_version
; /* the minor version of the major brand */
150 uint32_t *compatible_brands
; /* a list, to the end of the box, of brands */
152 uint32_t brand_count
; /* the number of factors in compatible_brands array */
156 * This box defines a list of preferred colors for displaying the movie on devices that support only 256 colors.
157 * The list may contain up to 256 colors. This box contains a Macintosh color table data structure.
158 * This box is defined in QuickTime File Format Specification.
159 * The color table structure is also defined in struct ColorTable defined in Quickdraw.h. */
162 /* An array of colors.
163 * Each color is made of four unsigned 16-bit integers. */
164 uint16_t value
; /* index or other value
165 * Must be set to 0. */
167 uint16_t r
; /* magnitude of red component */
168 uint16_t g
; /* magnitude of green component */
169 uint16_t b
; /* magnitude of blue component */
170 } isom_qt_color_array_t
;
174 uint32_t seed
; /* unique identifier for table
175 * Must be set to 0. */
176 uint16_t flags
; /* high bit: 0 = PixMap; 1 = device
177 * Must be set to 0x8000. */
178 uint16_t size
; /* the number of colors in the following color array
179 * This is a zero-relative value;
180 * setting this field to 0 means that there is one color in the array. */
181 isom_qt_color_array_t
*array
;
182 } isom_qt_color_table_t
;
187 isom_qt_color_table_t color_table
;
191 * This box specifies the characteristics of a single track. */
194 /* version is either 0 or 1
196 * 0x000001: Indicates that the track is enabled.
197 * A disabled track is treated as if it were not present.
198 * 0x000002: Indicates that the track is used in the presentation.
199 * 0x000004: Indicates that the track is used when previewing the presentation.
200 * 0x000008: Indicates that the track is used in the movie's poster. (only defined in QuickTime file format)
201 * ISOM: If in a presentation all tracks have neither track_in_movie nor track_in_preview set,
202 * then all tracks shall be treated as if both flags were set on all tracks. */
204 /* version == 0: uint64_t -> uint32_t */
205 uint64_t creation_time
; /* the creation time of this track (in seconds since midnight, Jan. 1, 1904, in UTC time) */
206 uint64_t modification_time
; /* the most recent time the track was modified (in seconds since midnight, Jan. 1, 1904, in UTC time) */
207 uint32_t track_ID
; /* an integer that uniquely identifies the track
208 * Track IDs are never re-used and cannot be zero. */
210 uint64_t duration
; /* the duration of this track expressed in the movie timescale units */
211 /* The following fields are treated as
212 * ISOM: template fields.
213 * MP41: reserved fields.
214 * MP42: ignored fileds since compositions are done using BIFS system.
215 * 3GPP: ignored fields except for alternate_group.
216 * QTFF: usable fields. */
217 uint32_t reserved2
[2];
218 int16_t layer
; /* the front-to-back ordering of video tracks; tracks with lower numbers are closer to the viewer. */
219 int16_t alternate_group
; /* an integer that specifies a group or collection of tracks
220 * If this field is not 0, it should be the same for tracks that contain alternate data for one another
221 * and different for tracks belonging to different such groups.
222 * Only one track within an alternate group should be played or streamed at any one time. */
223 int16_t volume
; /* fixed point 8.8 number. 0x0100 is full volume. */
225 int32_t matrix
[9]; /* transformation matrix for the video */
226 /* track's visual presentation size
227 * All images in the sequence are scaled to this size, before any overall transformation of the track represented by the matrix.
228 * Note: these fields are treated as reserved in MP4 version 1. */
229 uint32_t width
; /* fixed point 16.16 number */
230 uint32_t height
; /* fixed point 16.16 number */
234 /* Track Clean Aperture Dimensions Box
235 * A presentation mode where clap and pasp are reflected. */
239 uint32_t width
; /* fixed point 16.16 number */
240 uint32_t height
; /* fixed point 16.16 number */
243 /* Track Production Aperture Dimensions Box
244 * A presentation mode where pasp is reflected. */
248 uint32_t width
; /* fixed point 16.16 number */
249 uint32_t height
; /* fixed point 16.16 number */
252 /* Track Encoded Pixels Dimensions Box
253 * A presentation mode where clap and pasp are not reflected. */
257 uint32_t width
; /* fixed point 16.16 number */
258 uint32_t height
; /* fixed point 16.16 number */
261 /* Track Aperture Mode Dimensions Box */
265 isom_clef_t
*clef
; /* Track Clean Aperture Dimensions Box */
266 isom_prof_t
*prof
; /* Track Production Aperture Dimensions Box */
267 isom_enof_t
*enof
; /* Track Encoded Pixels Dimensions Box */
271 * This box contains an explicit timeline map.
272 * Each entry defines part of the track timeline: by mapping part of the media timeline, or by indicating 'empty' time,
273 * or by defining a 'dwell', where a single time-point in the media is held for a period.
274 * The last edit in a track shall never be an empty edit.
275 * Any difference between the duration in the Movie Header Box, and the track's duration is expressed as an implicit empty edit at the end.
276 * It is recommended that any edits, explicit or implied, not select any portion of the composition timeline that doesn't map to a sample.
277 * Therefore, if the first sample in the track has non-zero CTS, then this track should have at least one edit and the start time in it should
278 * correspond to the value of the CTS the first sample has or more not to exceed the largest CTS in this track. */
281 /* This entry is called Timeline Mapping Edit (TME) entry in UltraViolet Common File Format.
282 * version == 0: 64bits -> 32bits */
283 uint64_t segment_duration
; /* the duration of this edit expressed in the movie timescale units */
284 int64_t media_time
; /* the starting composition time within the media of this edit segment
285 * If this field is set to -1, it is an empty edit. */
286 int32_t media_rate
; /* the relative rate at which to play the media corresponding to this edit segment
287 * If this value is 0, then the edit is specifying a 'dwell':
288 * the media at media_time is presented for the segment_duration.
289 * This field is expressed as 16.16 fixed-point number. */
294 ISOM_FULLBOX_COMMON
; /* version is either 0 or 1 */
295 lsmash_entry_list_t
*list
;
299 * This optional box maps the presentation time-line to the media time-line as it is stored in the file.
300 * In the absence of this box, there is an implicit one-to-one mapping of these time-lines,
301 * and the presentation of a track starts at the beginning of the presentation. */
305 isom_elst_t
*elst
; /* Edit List Box */
308 /* Track Reference Box
309 * The Track Reference Box contains Track Reference Type Boxes.
310 * Track Reference Type Boxes define relationships between tracks.
311 * They allow one track to specify how it is related to other tracks. */
315 uint32_t *track_ID
; /* track_IDs of reference tracks / Zero value must not be used */
317 uint32_t ref_count
; /* number of reference tracks */
323 lsmash_entry_list_t ref_list
; /* Track Reference Type Boxes */
327 * This box declares overall information that is media-independent, and relevant to characteristics of the media in a track.*/
330 ISOM_FULLBOX_COMMON
; /* version is either 0 or 1 */
331 /* version == 0: uint64_t -> uint32_t */
332 uint64_t creation_time
; /* the creation time of the media in this track (in seconds since midnight, Jan. 1, 1904, in UTC time) */
333 uint64_t modification_time
; /* the most recent time the media in this track was modified (in seconds since midnight, Jan. 1, 1904, in UTC time) */
334 uint32_t timescale
; /* media timescale: timescale for this media */
335 uint64_t duration
; /* the duration of this media expressed in the timescale indicated in this box */
337 uint16_t language
; /* ISOM: ISO-639-2/T language codes. Most significant 1-bit is 0.
338 * Each character is packed as the difference between its ASCII value and 0x60.
339 * QTFF: Macintosh language codes is usually used.
340 * Mac's value is less than 0x800 while ISO's value is 0x800 or greater. */
341 int16_t quality
; /* ISOM: pre_defined / QTFF: the media's playback quality */
344 /* Handler Reference Box
345 * In Media Box, this box is mandatory and (ISOM: should/QTFF: must) come before Media Information Box.
346 * ISOM: this box might be also in Meta Box.
347 * QTFF: this box might be also in Media Information Box. If this box is present there, it must come before Data Information Box. */
351 uint32_t componentType
; /* ISOM: pre_difined = 0
352 * QTFF: 'mhlr' for Media Handler Reference Box and 'dhlr' for Data Handler Reference Box */
353 uint32_t componentSubtype
; /* Both ISOM and QT: when present in Media Handler Reference Box, this field defines the type of media data.
354 * ISOM: when present in Metadata Handler Reference Box, this field defines the format of the meta box contents.
355 * QTFF: when present in Data Handler Reference Box, this field defines the data reference type. */
356 /* The following fields are defined in QTFF however these fields aren't mentioned in QuickTime SDK and are reserved in the specification.
357 * In ISOM, these fields are still defined as reserved. */
358 uint32_t componentManufacturer
; /* vendor indentification / A value of 0 matches any manufacturer. */
359 uint32_t componentFlags
; /* flags describing required component capabilities
360 * The high-order 8 bits should be set to 0.
361 * The low-order 24 bits are specific to each component type. */
362 uint32_t componentFlagsMask
; /* This field indicates which flags in the componentFlags field are relevant to this operation. */
364 uint8_t *componentName
; /* ISOM: a null-terminated string in UTF-8 characters
365 * QTFF: Pascal string */
367 uint32_t componentName_length
;
371 /** Media Information Header Boxes
372 ** There is a different media information header for each track type
373 ** (corresponding to the media handler-type); the matching header shall be present. **/
374 /* Video Media Header Box
375 * This box contains general presentation information, independent of the coding, for video media. */
378 ISOM_FULLBOX_COMMON
; /* flags is 1 */
379 uint16_t graphicsmode
; /* template: graphicsmode = 0 */
380 uint16_t opcolor
[3]; /* template: opcolor = { 0, 0, 0 } */
383 /* Sound Media Header Box
384 * This box contains general presentation information, independent of the coding, for audio media. */
388 int16_t balance
; /* a fixed-point 8.8 number that places mono audio tracks in a stereo space. template: balance = 0 */
392 /* Hint Media Header Box
393 * This box contains general information, independent of the protocol, for hint tracks. (A PDU is a Protocol Data Unit.) */
397 uint16_t maxPDUsize
; /* the size in bytes of the largest PDU in this (hint) stream */
398 uint16_t avgPDUsize
; /* the average size of a PDU over the entire presentation */
399 uint32_t maxbitrate
; /* the maximum rate in bits/second over any window of one second */
400 uint32_t avgbitrate
; /* the average rate in bits/second over the entire presentation */
404 /* Null Media Header Box
405 * This box may be used for streams other than visual and audio (e.g., timed metadata streams). */
408 /* Streams other than visual and audio may use a Null Media Header Box */
409 ISOM_FULLBOX_COMMON
; /* flags is currently all zero */
412 /* Generic Media Information Box */
416 uint16_t graphicsmode
;
418 int16_t balance
; /* This field is nomally set to 0. */
419 uint16_t reserved
; /* Reserved for use by Apple. Set this field to 0. */
422 /* Text Media Information Box */
426 int32_t matrix
[9]; /* Unkown fields. Default values are probably:
427 * { 0x00010000, 0, 0, 0, 0x00010000, 0, 0, 0, 0x40000000 } */
430 /* Generic Media Information Header Box */
434 isom_gmin_t
*gmin
; /* Generic Media Information Box */
435 isom_text_t
*text
; /* Text Media Information Box */
439 /* Data Reference Box
440 * name and location fields are expressed in null-terminated string using UTF-8 characters. */
443 /* This box is DataEntryUrlBox or DataEntryUrnBox */
444 ISOM_FULLBOX_COMMON
; /* flags == 0x000001 means that the media data is in the same file
445 * as the Movie Box containing this data reference. */
446 char *name
; /* only for DataEntryUrnBox */
447 char *location
; /* a location to find the resource with the given name */
449 uint32_t name_length
;
450 uint32_t location_length
;
451 lsmash_file_t
*ref_file
; /* pointer to the handle of the referenced file */
457 lsmash_entry_list_t list
;
460 /* Data Information Box */
463 /* This box is in Media Information Box or Meta Box */
465 isom_dref_t
*dref
; /* Data Reference Box */
468 /** Sample Description **/
469 /* ES Descriptor Box */
470 struct mp4sys_ES_Descriptor_t
; /* FIXME: I think these structs using mp4sys should be placed in isom.c */
474 struct mp4sys_ES_Descriptor_t
*ES
;
477 /* MPEG-4 Bit Rate Box
478 * This box signals the bit rate information of the AVC video stream. */
482 uint32_t bufferSizeDB
; /* the size of the decoding buffer for the elementary stream in bytes */
483 uint32_t maxBitrate
; /* the maximum rate in bits/second over any window of one second */
484 uint32_t avgBitrate
; /* the average rate in bits/second over the entire presentation */
487 /* Global Header Box */
491 uint32_t header_size
;
492 uint8_t *header_data
;
495 /* Clean Aperture Box
496 * There are notionally four values in this box and these parameters are represented as a fraction N/D.
497 * Here, we refer to the pair of parameters fooN and fooD as foo.
498 * Considering the pixel dimensions as defined by the VisualSampleEntry width and height.
499 * If picture centre of the image is at pcX and pcY, then horizOff and vertOff are defined as follows:
500 * pcX = horizOff + (width - 1)/2;
501 * pcY = vertOff + (height - 1)/2;
502 * The leftmost/rightmost pixel and the topmost/bottommost line of the clean aperture fall at:
503 * pcX +/- (cleanApertureWidth - 1)/2;
504 * pcY +/- (cleanApertureHeight - 1)/2;
505 * QTFF: this box is a mandatory extension for all uncompressed Y'CbCr data formats. */
509 uint32_t cleanApertureWidthN
;
510 uint32_t cleanApertureWidthD
;
511 uint32_t cleanApertureHeightN
;
512 uint32_t cleanApertureHeightD
;
519 /* Pixel Aspect Ratio Box
520 * This box specifies the aspect ratio of a pixel, in arbitrary units.
521 * If a pixel appears H wide and V tall, then hSpacing/vSpacing is equal to H/V.
522 * When adjusting pixel aspect ratio, normally, the horizontal dimension of the video is scaled, if needed. */
526 uint32_t hSpacing
; /* horizontal spacing */
527 uint32_t vSpacing
; /* vertical spacing */
530 /* ISOM: Colour Information Box / QTFF: Color Parameter Box
531 * This box is used to map the numerical values of pixels in the file to a common representation of color
532 * in which images can be correctly compared, combined, and displayed.
533 * If colour information is supplied in both this box, and also in the video bitstream,
534 * this box takes precedence, and over-rides the information in the bitstream.
535 * For QuickTime file format:
536 * This box ('colr') supersedes the Gamma Level Box ('gama').
537 * Writers of QTFF should never write both into an Image Description, and readers of QTFF should ignore 'gama' if 'colr' is present.
538 * Note: this box is a mandatory extension for all uncompressed Y'CbCr data formats.
539 * For ISO Base Media file format:
540 * Colour information may be supplied in one or more Colour Information Boxes placed in a VisualSampleEntry.
541 * These should be placed in order in the sample entry starting with the most accurate (and potentially the most difficult to process), in progression to the least.
542 * These are advisory and concern rendering and colour conversion, and there is no normative behaviour associated with them; a reader may choose to use the most suitable. */
546 uint32_t color_parameter_type
; /* QTFF: 'nclc' or 'prof'
547 * ISOM: 'nclx', 'rICC' or 'prof' */
548 /* for 'nclc' and 'nclx' */
549 uint16_t primaries_index
; /* CIE 1931 xy chromaticity coordinates */
550 uint16_t transfer_function_index
; /* nonlinear transfer function from RGB to ErEgEb */
551 uint16_t matrix_index
; /* matrix from ErEgEb to EyEcbEcr */
553 unsigned full_range_flag
: 1;
554 unsigned reserved
: 7;
558 * This box is used to indicate that the decompressor corrects gamma level at display time.
559 * This box is defined in QuickTime File Format Specification and ImageCompression.h. */
563 uint32_t level
; /* A fixed-point 16.16 number indicating the gamma level at which the image was captured.
564 * Zero value indicates platform's standard gamma. */
567 /* Field/Frame Information Box
568 * This box is used by applications to modify decompressed image data or by decompressor components to determine field display order.
569 * This box is defined in QuickTime File Format Specification, dispatch019 and ImageCodec.h.
570 * Note: this box is a mandatory extension for all uncompressed Y'CbCr data formats. */
574 uint8_t fields
; /* the number of fields per frame
575 * 1: progressive scan
576 * 2: 2:1 interlaced */
577 uint8_t detail
; /* field ordering */
581 * This box is defined in ImageCompression.h. */
585 uint32_t pixel_format
; /* the native pixel format of an image */
588 /* Significant Bits Box
589 * This box is defined in Letters from the Ice Floe dispatch019.
590 * Note: this box is a mandatory extension for 'v216' (Uncompressed Y'CbCr, 10, 12, 14, or 16-bit-per-component 4:2:2). */
594 uint8_t significantBits
; /* the number of significant bits per component */
598 * If this box is present and can be interpreted by the decoder,
599 * all samples shall be displayed according to the scaling behaviour that is specified in this box.
600 * Otherwise, all samples are scaled to the size that is indicated by the width and height field in the Track Header Box.
601 * This box is defined in ISO Base Media file format. */
605 uint8_t constraint_flag
; /* Upper 7-bits are reserved.
606 * If this flag is set, all samples described by this sample entry shall be scaled
607 * according to the method specified by the field 'scale_method'. */
608 uint8_t scale_method
; /* The semantics of the values for scale_method are as specified for the 'fit' attribute of regions in SMIL 1.0. */
609 int16_t display_center_x
;
610 int16_t display_center_y
;
614 #define ISOM_SAMPLE_ENTRY \
615 ISOM_BASEBOX_COMMON; \
616 uint8_t reserved[6]; \
617 uint16_t data_reference_index
622 } isom_sample_entry_t
;
624 /* Mpeg Sample Entry */
630 /* ISOM: Visual Sample Entry / QTFF: Image Description
631 * For maximum compatibility, the following extension boxes should follow, not precede,
632 * any extension boxes defined in or required by derived specifications.
634 * Pixel Aspect Ratio Box */
638 int16_t version
; /* ISOM: pre_defined / QTFF: sample description version */
639 int16_t revision_level
; /* ISOM: reserved / QTFF: version of the CODEC */
640 int32_t vendor
; /* ISOM: pre_defined / QTFF: whose CODEC */
641 uint32_t temporalQuality
; /* ISOM: pre_defined / QTFF: the temporal quality factor */
642 uint32_t spatialQuality
; /* ISOM: pre_defined / QTFF: the spatial quality factor */
643 /* The width and height are the maximum pixel counts that the codec will deliver.
644 * Since these are counts they do not take into account pixel aspect ratio. */
648 uint32_t horizresolution
; /* 16.16 fixed-point / template: horizresolution = 0x00480000 / 72 dpi */
649 uint32_t vertresolution
; /* 16.16 fixed-point / template: vertresolution = 0x00480000 / 72 dpi */
650 uint32_t dataSize
; /* ISOM: reserved / QTFF: if known, the size of data for this descriptor */
651 uint16_t frame_count
; /* frame per sample / template: frame_count = 1 */
652 char compressorname
[33]; /* a fixed 32-byte field, with the first byte set to the number of bytes to be displayed */
653 uint16_t depth
; /* ISOM: template: depth = 0x0018
654 * AVC : 0x0018: colour with no alpha
655 * 0x0028: grayscale with no alpha
656 * 0x0020: gray or colour with alpha
657 * QTFF: depth of this data (1-32) or (33-40 grayscale) */
658 int16_t color_table_ID
; /* ISOM: template: pre_defined = -1
659 * QTFF: color table ID
660 * If this field is set to -1, the default color table should be used for the specified depth
661 * If the color table ID is set to 0, a color table is contained within the sample description itself.
662 * The color table immediately follows the color table ID field. */
663 /* Color table follows color_table_ID only when color_table_ID is set to 0. */
664 isom_qt_color_table_t color_table
; /* a list of preferred colors for displaying the movie on devices that support only 256 colors */
665 } isom_visual_entry_t
;
668 * This box shows the data format of the stored sound media.
669 * ISO base media file format also defines the same four-character-code for the type field,
670 * however, that is used to indicate original sample description of the media when a protected sample entry is used. */
674 uint32_t data_format
; /* copy of sample description type */
677 /* Audio Endian Box */
681 int16_t littleEndian
;
684 /* MPEG-4 Audio Box */
688 uint32_t unknown
; /* always 0? */
692 * This box is present to indicate the end of the sound description. It contains no data. */
695 ISOM_BASEBOX_COMMON
; /* size = 8, type = 0x00000000 */
698 /* Sound Information Decompression Parameters Box
699 * This box is defined in QuickTime file format.
700 * This box provides the ability to store data specific to a given audio decompressor in the sound description.
701 * The contents of this box are dependent on the audio decompressor. */
705 isom_frma_t
*frma
; /* Format Box */
706 isom_enda_t
*enda
; /* Audio Endian Box */
707 isom_mp4a_t
*mp4a
; /* MPEG-4 Audio Box */
708 isom_terminator_t
*terminator
; /* Terminator Box */
711 /* Audio Channel Layout Box
712 * This box is defined in QuickTime file format or Apple Lossless Audio inside ISO Base Media. */
715 uint32_t channelLabel
; /* the channelLabel that describes the channel */
716 uint32_t channelFlags
; /* flags that control the interpretation of coordinates */
717 uint32_t coordinates
[3]; /* an ordered triple that specifies a precise speaker location / 32-bit floating point */
718 } isom_channel_description_t
;
723 uint32_t channelLayoutTag
; /* the channelLayoutTag indicates the layout */
724 uint32_t channelBitmap
; /* If channelLayoutTag is set to 0x00010000, this field is the channel usage bitmap. */
725 uint32_t numberChannelDescriptions
; /* the number of items in the Channel Descriptions array */
726 /* Channel Descriptions array */
727 isom_channel_description_t
*channelDescriptions
;
731 * This box may be present only in an AudioSampleEntryV1, and when present,
732 * it overrides the samplerate field and documents the actual sampling rate.
733 * When this box is present, the media timescale should be the same as the
734 * sampling rate, or an integer division or multiple of it. */
738 uint32_t sampling_rate
; /* the actual sampling rate of the audio media, expressed as a 32-bit integer
739 * The value of this field overrides the samplerate field in the AudioSampleEntryV1
740 * and documents the actual sampling rate. */
743 /* ISOM: Audio Sample Entry / QTFF: Sound Description */
747 int16_t version
; /* ISOM: version = 0 is used to support non-high samplerate audio format.
748 * version = 1, called AudioSampleEntryV1, is used to support high samplerate audio format.
749 * An AudioSampleEntryV1 requires that the enclosing Sample Description Box also takes the version 1.
750 * For maximum compatibility, an AudioSampleEntryV1 should only be used when needed.
751 * QTFF: version = 0 supports only 'raw ' or 'twos' audio format.
752 * version = 1 is used to support out-of-band configuration settings for decompression.
753 * version = 2 is used to support high samplerate, or 3 or more multichannel audio format. */
754 int16_t revision_level
; /* ISOM: reserved / QTFF: version of the CODEC */
755 int32_t vendor
; /* ISOM: reserved / QTFF: whose CODEC */
756 uint16_t channelcount
; /* ISOM: template: channelcount = 2
757 * channelcount is a value greater than zero that indicates the maximum number of channels that the
758 * audio could deliver.
759 * A channelcount of 1 indicates mono audio, and 2 indicates stereo (left/right).
760 * When values greater than 2 are used, the codec configuration should identify the channel assignment.
761 * QTFF: the number of audio channels
762 * Allowable values are 1 (mono) or 2 (stereo).
763 * For more than 2, set this field to 3 and use numAudioChannels instead of this field. */
764 uint16_t samplesize
; /* ISOM: template: samplesize = 16
765 * QTFF: the number of bits in each uncompressed sample for a single channel
766 * Allowable values are 8 or 16.
767 * For non-mod8, set this field to 16 and use constBitsPerChannel instead of this field.
768 * For more than 16, set this field to 16 and use bytesPerPacket instead of this field. */
769 int16_t compression_ID
; /* ISOM: pre_defined
770 * QTFF: version = 0 -> must be set to 0.
771 * version = 2 -> must be set to -2. */
772 uint16_t packet_size
; /* ISOM: reserved / QTFF: must be set to 0. */
773 uint32_t samplerate
; /* the sampling rate expressed as a 16.16 fixed-point number
774 * ISOM: template: samplerate = {default samplerate of media}<<16
775 * When it is desired to indicate an audio sampling rate greater than the value that can be represented in
776 * this field, this field should contain a value left-shifted 16 bits that matches the media timescale,
777 * or be an integer division or multiple of it.
778 * QTFF: the integer portion should match the media's timescale.
779 * If this field is invalid because of higher samplerate,
780 * then set this field to 0x00010000 and use audioSampleRate instead of this field. */
781 /* QTFF-based version 1 fields
782 * These fields are for description of the compression ratio of fixed ratio audio compression algorithms.
783 * If these fields are not used, they are set to 0. */
784 uint32_t samplesPerPacket
; /* For compressed audio, be set to the number of uncompressed frames generated by a compressed frame.
785 * For uncompressed audio, shall be set to 1. */
786 uint32_t bytesPerPacket
; /* the number of bytes in a sample for a single channel */
787 uint32_t bytesPerFrame
; /* the number of bytes in a frame */
788 uint32_t bytesPerSample
; /* 8-bit audio: 1, other audio: 2 */
789 /* QTFF-based version 2 fields
790 * LPCMFrame: one sample from each channel.
791 * AudioPacket: For uncompressed audio, an AudioPacket is simply one LPCMFrame.
792 * For compressed audio, an AudioPacket is the natural compressed access unit of that format. */
793 uint32_t sizeOfStructOnly
; /* offset to extensions */
794 uint64_t audioSampleRate
; /* 64-bit floating point */
795 uint32_t numAudioChannels
; /* any channel assignment info will be in Audio Channel Layout Box. */
796 int32_t always7F000000
; /* always 0x7F000000 */
797 uint32_t constBitsPerChannel
; /* only set if constant (and only for uncompressed audio) */
798 uint32_t formatSpecificFlags
;
799 uint32_t constBytesPerAudioPacket
; /* only set if constant */
800 uint32_t constLPCMFramesPerAudioPacket
; /* only set if constant */
801 } isom_audio_entry_t
;
803 /* Hint Sample Entry */
804 #define ISOM_HINT_SAMPLE_ENTRY \
810 ISOM_HINT_SAMPLE_ENTRY
;
811 uint32_t data_length
;
814 /* Metadata Sample Entry */
815 #define ISOM_METADATA_SAMPLE_ENTRY \
820 ISOM_METADATA_SAMPLE_ENTRY
;
821 } isom_metadata_entry_t
;
823 /* QuickTime Text Sample Description */
827 int32_t displayFlags
;
828 int32_t textJustification
;
829 uint16_t bgColor
[3]; /* background RGB color */
836 int32_t scrpStartChar
; /* starting character position */
840 uint16_t scrpFace
; /* only first 8-bits are used */
842 uint16_t scrpColor
[3]; /* foreground RGB color */
843 /* defaultFontName is Pascal string */
844 uint8_t font_name_length
;
846 } isom_qt_text_entry_t
;
853 uint8_t font_name_length
;
855 } isom_font_record_t
;
862 * entry_count is uint16_t. */
863 lsmash_entry_list_t
*list
;
866 /* 3GPP Timed Text Sample Entry */
870 uint32_t displayFlags
;
871 int8_t horizontal_justification
;
872 int8_t vertical_justification
;
873 uint8_t background_color_rgba
[4];
874 /* BoxRecord default_text_box */
879 /* StyleRecord default_style */
880 uint16_t startChar
; /* always 0 */
881 uint16_t endChar
; /* always 0 */
883 uint8_t face_style_flags
;
885 uint8_t text_color_rgba
[4];
886 /* Font Table Box font_table */
890 /* Sample Description Box */
894 uint32_t entry_count
; /* print only */
895 lsmash_entry_list_t list
;
899 /* Decoding Time to Sample Box
900 * This box contains a compact version of a table that allows indexing from decoding time to sample number.
901 * Each entry in the table gives the number of consecutive samples with the same time delta, and the delta of those samples.
902 * By adding the deltas a complete time-to-sample map may be built.
903 * All samples must have non-zero durations except for the last one.
904 * The sum of all deltas gives the media duration in the track (not mapped to the movie timescale, and not considering any edit list).
905 * DTS is an abbreviation of 'decoding time stamp'. */
908 uint32_t sample_count
; /* number of consecutive samples that have the given sample_delta */
909 uint32_t sample_delta
; /* DTS[0] = 0; DTS[n+1] = DTS[n] + sample_delta[n]; */
915 lsmash_entry_list_t
*list
;
918 /* Composition Time to Sample Box
919 * This box provides the offset between decoding time and composition time.
920 * CTS is an abbreviation of 'composition time stamp'.
921 * This box is optional and must only be present if DTS and CTS differ for any samples. */
924 #define ISOM_NON_OUTPUT_SAMPLE_OFFSET 0x80000000
925 uint32_t sample_count
; /* number of consecutive samples that have the given sample_offset */
926 uint32_t sample_offset
; /* CTS[n] = DTS[n] + sample_offset[n];
927 * ISOM: if version is set to 1, sample_offset is signed 32-bit integer.
928 * QTFF: sample_offset is always signed 32-bit integer. */
934 lsmash_entry_list_t
*list
;
937 /* Composition to Decode Box (Composition Shift Least Greatest Box)
938 * This box may be used to relate the composition and decoding timelines,
939 * and deal with some of the ambiguities that signed composition offsets introduce. */
943 int32_t compositionToDTSShift
; /* If this value is added to the composition times (as calculated by the CTS offsets from the DTS),
944 * then for all samples, their CTS is guaranteed to be greater than or equal to their DTS,
945 * and the buffer model implied by the indicated profile/level will be honoured;
946 * if leastDecodeToDisplayDelta is positive or zero, this field can be 0;
947 * otherwise it should be at least (- leastDecodeToDisplayDelta). */
948 int32_t leastDecodeToDisplayDelta
; /* the smallest sample_offset in this track */
949 int32_t greatestDecodeToDisplayDelta
; /* the largest sample_offset in this track */
950 int32_t compositionStartTime
; /* the smallest CTS for any sample */
951 int32_t compositionEndTime
; /* the CTS plus the composition duration, of the sample with the largest CTS in this track */
954 /* Sample Size Box / Compact Sample Size Box
955 * This box contains the sample count and a table giving the size in bytes of each sample.
956 * The total number of samples in the media within the initial movie is always indicated in the sample_count.
957 * Note: a sample size of zero is not prohibited in general, but it must be valid and defined for the coding system,
958 * as defined by the sample entry, that the sample belongs to. */
961 uint32_t entry_size
; /* the size of a sample */
967 uint32_t sample_size
; /* the default sample size
968 * If this field is set to 0, then the samples have different sizes. */
969 uint32_t sample_count
; /* the number of samples in the media within the initial movie */
970 lsmash_entry_list_t
*list
; /* available if sample_size == 0 */
976 unsigned int reserved
: 24; /* 0 */
977 unsigned int field_size
: 8; /* the size in bits of the entries in the following table
978 * It shall take the value 4, 8 or 16. If the value 4 is used, then each byte contains two values
979 * entry[i]<<4 + entry[i+1]; if the sizes do not fill an integral number of bytes, the last byte is
980 * padded with zero. */
981 uint32_t sample_count
; /* the number of entries in the following table */
982 lsmash_entry_list_t
*list
; /* L-SMASH uses isom_stsz_entry_t for its internal processes. */
986 * If this box is not present, every sample is a random access point.
987 * In AVC streams, this box cannot point non-IDR samples.
988 * The table is arranged in strictly increasing order of sample number. */
991 uint32_t sample_number
; /* the numbers of the samples that are random access points in the stream. */
997 lsmash_entry_list_t
*list
;
1000 /* Partial Sync Sample Box
1001 * Tip from QT engineering - Open-GOP intra frames need to be marked as "partial sync samples".
1002 * Partial sync frames perform a partial reset of inter-frame dependencies;
1003 * decoding two partial sync frames and the non-droppable difference frames between them is
1004 * sufficient to prepare a decompressor for correctly decoding the difference frames that follow. */
1007 uint32_t sample_number
; /* the numbers of the samples that are partial sync samples in the stream. */
1008 } isom_stps_entry_t
;
1012 ISOM_FULLBOX_COMMON
;
1013 lsmash_entry_list_t
*list
;
1016 /* Independent and Disposable Samples Box */
1019 unsigned is_leading
: 2; /* ISOM: leading / QTFF: samples later in decode order may have earlier display times */
1020 unsigned sample_depends_on
: 2; /* independency */
1021 unsigned sample_is_depended_on
: 2; /* disposable */
1022 unsigned sample_has_redundancy
: 2; /* redundancy */
1023 } isom_sdtp_entry_t
;
1027 ISOM_FULLBOX_COMMON
;
1028 /* According to the specification, the size of the table, sample_count, doesn't exist in this box.
1029 * Instead of this, it is taken from the sample_count in the stsz or the stz2 box. */
1030 lsmash_entry_list_t
*list
;
1033 /* Sample To Chunk Box
1034 * This box can be used to find the chunk that contains a sample, its position, and the associated sample description.
1035 * The table is compactly coded. Each entry gives the index of the first chunk of a run of chunks with the same characteristics.
1036 * By subtracting one entry here from the previous one, you can compute how many chunks are in this run.
1037 * You can convert this to a sample count by multiplying by the appropriate samples_per_chunk. */
1040 uint32_t first_chunk
; /* the index of the first chunk in this run of chunks that share the same samples_per_chunk and sample_description_index */
1041 uint32_t samples_per_chunk
; /* the number of samples in each of these chunks */
1042 uint32_t sample_description_index
; /* the index of the sample entry that describes the samples in this chunk */
1043 } isom_stsc_entry_t
;
1047 ISOM_FULLBOX_COMMON
;
1048 lsmash_entry_list_t
*list
;
1052 * chunk_offset is the offset of the start of a chunk into its containing media file.
1053 * Offsets are file offsets, not the offset into any box within the file. */
1056 uint32_t chunk_offset
;
1057 } isom_stco_entry_t
;
1061 /* for large presentations */
1062 uint64_t chunk_offset
;
1063 } isom_co64_entry_t
;
1067 ISOM_FULLBOX_COMMON
; /* type = 'stco': 32-bit chunk offsets / type = 'co64': 64-bit chunk offsets */
1068 lsmash_entry_list_t
*list
;
1070 uint8_t large_presentation
; /* Set 1 to this if 64-bit chunk-offset are needed. */
1071 } isom_stco_t
; /* share with co64 box */
1073 /* Sample Group Description Box
1074 * This box gives information about the characteristics of sample groups. */
1077 ISOM_FULLBOX_COMMON
; /* Use of version 0 entries is deprecated. */
1078 uint32_t grouping_type
; /* an integer that identifies the sbgp that is associated with this sample group description */
1079 uint32_t default_length
; /* the length of every group entry (if the length is constant), or zero (if it is variable)
1080 * This field is available only if version == 1. */
1081 lsmash_entry_list_t
*list
;
1084 /* Random Access Entry
1085 * Samples marked by this group must be random access points, and may also be sync points. */
1088 /* grouping_type is 'rap ' */
1089 uint32_t description_length
; /* This field is available only if version == 1 and default_length == 0. */
1090 unsigned num_leading_samples_known
: 1; /* the value of one indicates that the number of leading samples is known for each sample in this group,
1091 * and the number is specified by num_leading_samples. */
1092 unsigned num_leading_samples
: 7; /* the number of leading samples for each sample in this group
1093 * Note: when num_leading_samples_known is equal to 0, this field should be ignored. */
1096 /* Roll Recovery Entry
1097 * This grouping type is defined as that group of samples having the same roll distance. */
1100 /* grouping_type is 'roll' */
1101 uint32_t description_length
; /* This field is available only if version == 1 and default_length == 0. */
1102 int16_t roll_distance
; /* the number of samples that must be decoded in order for a sample to be decoded correctly
1103 * A positive value indicates post-roll, and a negative value indicates pre-roll.
1104 * The value zero must not be used. */
1105 } isom_roll_entry_t
;
1107 /* Sample to Group Box
1108 * This box is used to find the group that a sample belongs to and the associated description of that sample group. */
1111 ISOM_FULLBOX_COMMON
;
1112 uint32_t grouping_type
; /* Links it to its sample group description table with the same value for grouping type. */
1113 uint32_t grouping_type_parameter
; /* an indication of the sub-type of the grouping
1114 * This field is available only if version == 1. */
1115 lsmash_entry_list_t
*list
;
1120 uint32_t sample_count
; /* the number of consecutive samples with the same sample group descriptor */
1121 uint32_t group_description_index
; /* the index of the sample group entry which describes the samples in this group
1122 * The index ranges from 1 to the number of sample group entries in the Sample Group Description Box,
1123 * or takes the value 0 to indicate that this sample is a member of no group of this type.
1124 * Within the Sample to Group Box in movie fragment, the group description indexes for groups defined
1125 * within the same fragment start at 0x10001, i.e. the index value 1, with the value 1 in the top 16 bits. */
1126 } isom_group_assignment_entry_t
;
1128 /* Sample Table Box */
1129 struct isom_stbl_tag
1131 ISOM_BASEBOX_COMMON
;
1132 isom_stsd_t
*stsd
; /* Sample Description Box */
1133 isom_stts_t
*stts
; /* Decoding Time to Sample Box */
1134 isom_ctts_t
*ctts
; /* Composition Time to Sample Box */
1135 isom_cslg_t
*cslg
; /* ISOM: Composition to Decode Box / QTFF: Composition Shift Least Greatest Box */
1136 isom_stss_t
*stss
; /* Sync Sample Box */
1137 isom_stps_t
*stps
; /* ISOM: null / QTFF: Partial Sync Sample Box */
1138 isom_sdtp_t
*sdtp
; /* Independent and Disposable Samples Box */
1139 isom_stsc_t
*stsc
; /* Sample To Chunk Box */
1140 isom_stsz_t
*stsz
; /* Sample Size Box */
1141 isom_stz2_t
*stz2
; /* Compact Sample Size Box */
1142 isom_stco_t
*stco
; /* Chunk Offset Box */
1143 lsmash_entry_list_t sgpd_list
; /* Sample Group Description Boxes */
1144 lsmash_entry_list_t sbgp_list
; /* Sample To Group Boxes */
1146 /* Use 'stz2' instead of 'stsz' if possible. (write mode only) */
1147 int (*compress_sample_size_table
)( isom_stbl_t
*stbl
);
1148 /* Add independent and disposable info for each sample if possible. (write mode only) */
1149 int (*add_dependency_type
)( isom_stbl_t
*stbl
, lsmash_file_t
*file
, lsmash_sample_property_t
*prop
);
1152 /* Media Information Box */
1155 ISOM_BASEBOX_COMMON
;
1156 /* Media Information Header Boxes */
1157 isom_vmhd_t
*vmhd
; /* Video Media Header Box */
1158 isom_smhd_t
*smhd
; /* Sound Media Header Box */
1159 isom_hmhd_t
*hmhd
; /* ISOM: Hint Media Header Box / QTFF: null */
1160 isom_nmhd_t
*nmhd
; /* ISOM: Null Media Header Box / QTFF: null */
1161 isom_gmhd_t
*gmhd
; /* ISOM: null / QTFF: Generic Media Information Header Box */
1163 isom_hdlr_t
*hdlr
; /* ISOM: null / QTFF: Data Handler Reference Box
1164 * Note: this box must come before Data Information Box. */
1165 isom_dinf_t
*dinf
; /* Data Information Box */
1166 isom_stbl_t
*stbl
; /* Sample Table Box */
1172 ISOM_BASEBOX_COMMON
;
1173 isom_mdhd_t
*mdhd
; /* Media Header Box */
1174 isom_hdlr_t
*hdlr
; /* ISOM: Handler Reference Box / QTFF: Media Handler Reference Box
1175 * Note: this box must come before Media Information Box. */
1176 isom_minf_t
*minf
; /* Media Information Box */
1180 * This box defines overall information which is media-independent, and relevant to the entire presentation considered as a whole. */
1183 ISOM_FULLBOX_COMMON
; /* version is either 0 or 1 */
1184 /* version == 0: uint64_t -> uint32_t */
1185 uint64_t creation_time
; /* the creation time of the presentation (in seconds since midnight, Jan. 1, 1904, in UTC time) */
1186 uint64_t modification_time
; /* the most recent time the presentation was modified (in seconds since midnight, Jan. 1, 1904, in UTC time) */
1187 uint32_t timescale
; /* movie timescale: timescale for the entire presentation */
1188 uint64_t duration
; /* the duration, expressed in movie timescale, of the longest track */
1189 /* The following fields are treated as
1190 * ISOM: template fields.
1191 * MP41: reserved fields.
1192 * MP42: ignored fileds since compositions are done using BIFS system.
1193 * 3GPP: ignored fields.
1194 * QTFF: usable fields. */
1195 int32_t rate
; /* fixed point 16.16 number. 0x00010000 is normal forward playback. */
1196 int16_t volume
; /* fixed point 8.8 number. 0x0100 is full volume. */
1198 int32_t preferredLong
[2]; /* ISOM: reserved / QTFF: unknown */
1199 int32_t matrix
[9]; /* transformation matrix for the video */
1200 /* The following fields are defined in QuickTime file format.
1201 * In ISO Base Media file format, these fields are treated as pre_defined. */
1202 int32_t previewTime
; /* the time value in the movie at which the preview begins */
1203 int32_t previewDuration
; /* the duration of the movie preview in movie timescale units */
1204 int32_t posterTime
; /* the time value of the time of the movie poster */
1205 int32_t selectionTime
; /* the time value for the start time of the current selection */
1206 int32_t selectionDuration
; /* the duration of the current selection in movie timescale units */
1207 int32_t currentTime
; /* the time value for current time position within the movie */
1209 uint32_t next_track_ID
; /* larger than the largest track-ID in use */
1212 /* Object Descriptor Box
1213 * Note that this box is mandatory under 14496-1:2001 (mp41) while not mandatory under 14496-14:2003 (mp42). */
1214 struct mp4sys_ObjectDescriptor_t
; /* FIXME: I think these structs using mp4sys should be placed in isom.c */
1217 ISOM_FULLBOX_COMMON
;
1218 struct mp4sys_ObjectDescriptor_t
*OD
;
1222 * This box contains the media data.
1223 * A presentation may contain zero or more Media Data Boxes.*/
1226 ISOM_BASEBOX_COMMON
; /* If size is 0, then this box is the last box. */
1228 uint64_t media_size
; /* the total media size already written in this box */
1229 uint64_t reserved_size
; /* the reserved total media size in this box
1230 * If 'media_size' > 'reserved_size' occurs when finishing a non-fragmented movie,
1231 * rewrite the size of this box. */
1235 * The contents of a free-space box are irrelevant and may be ignored without affecting the presentation. */
1238 ISOM_BASEBOX_COMMON
; /* type is 'free' or 'skip' */
1243 typedef isom_free_t isom_skip_t
;
1246 * This box is NOT defined in the ISO/MPEG-4 specs.
1247 * Basically, this box exists in User Data Box inside Movie Box if present. */
1250 uint64_t start_time
; /* version = 0: expressed in movie timescale units
1251 * version = 1: expressed in 100 nanoseconds */
1252 /* Chapter name is Pascal string */
1253 uint8_t chapter_name_length
;
1255 } isom_chpl_entry_t
;
1259 ISOM_FULLBOX_COMMON
; /* version = 0 is defined in F4V file format. */
1260 uint8_t unknown
; /* only available under version = 1 */
1261 lsmash_entry_list_t
*list
; /* if version is set to 0, entry_count is uint8_t. */
1267 uint64_t start_time
;
1268 } isom_chapter_entry_t
;
1270 /* Metadata Item Keys Box */
1273 ISOM_FULLBOX_COMMON
;
1274 lsmash_entry_list_t
*list
;
1279 uint32_t key_size
; /* the size of the entire structure containing a key definition
1280 * key_size = sizeof(key_size) + sizeof(key_namespace) + sizeof(key_value) */
1281 uint32_t key_namespace
; /* a naming scheme used for metadata keys
1282 * Location metadata keys, for example, use the 'mdta' key namespace. */
1283 uint8_t *key_value
; /* the actual name of the metadata key
1284 * Keys with the 'mdta' namespace use a reverse DNS naming convention. */
1285 } isom_keys_entry_t
;
1290 ISOM_FULLBOX_COMMON
;
1291 uint8_t *meaning_string
; /* to fill the box */
1293 uint32_t meaning_string_length
;
1299 ISOM_FULLBOX_COMMON
;
1300 uint8_t *name
; /* to fill the box */
1302 uint32_t name_length
;
1308 ISOM_BASEBOX_COMMON
;
1309 /* type indicator */
1310 uint16_t reserved
; /* always 0 */
1311 uint8_t type_set_identifier
; /* 0: type set of the common basic data types */
1312 uint8_t type_code
; /* type of data code */
1314 uint32_t the_locale
; /* reserved to be 0 */
1315 uint8_t *value
; /* to fill the box */
1317 uint32_t value_length
;
1320 /* Metadata Item Box */
1323 ISOM_BASEBOX_COMMON
;
1324 isom_mean_t
*mean
; /* Meaning Box */
1325 isom_name_t
*name
; /* Name Box */
1326 isom_data_t
*data
; /* Data Box */
1329 /* Metadata Item List Box */
1332 ISOM_BASEBOX_COMMON
;
1333 lsmash_entry_list_t metaitem_list
; /* Metadata Item Box List
1334 * There is no entry_count field. */
1340 ISOM_FULLBOX_COMMON
; /* ISOM: FullBox / QTFF: BaseBox */
1341 isom_hdlr_t
*hdlr
; /* Metadata Handler Reference Box */
1342 isom_dinf_t
*dinf
; /* ISOM: Data Information Box / QTFF: null */
1343 isom_keys_t
*keys
; /* ISOM: null / QTFF: Metadata Item Keys Box */
1344 isom_ilst_t
*ilst
; /* Metadata Item List Box only defined in Apple MPEG-4 and QTFF */
1347 /* Window Location Box */
1350 ISOM_BASEBOX_COMMON
;
1351 /* default window location for movie */
1359 ISOM_BASEBOX_COMMON
;
1360 uint32_t looping_mode
; /* 0 for none, 1 for looping, 2 for palindromic looping */
1363 /* Play Selection Only Box */
1366 ISOM_BASEBOX_COMMON
;
1367 uint8_t selection_only
; /* whether only the selected area of the movie should be played */
1370 /* Play All Frames Box */
1373 ISOM_BASEBOX_COMMON
;
1374 uint8_t play_all_frames
; /* whether all frames of video should be played, regardless of timing */
1378 * The Copyright box contains a copyright declaration which applies to the entire presentation,
1379 * when contained within the Movie Box, or, when contained in a track, to that entire track.
1380 * There may be multiple copyright boxes using different language codes. */
1383 ISOM_FULLBOX_COMMON
;
1384 uint16_t language
; /* ISO-639-2/T language codes. Most significant 1-bit is 0.
1385 * Each character is packed as the difference between its ASCII value and 0x60. */
1386 uint8_t *notice
; /* a null-terminated string in either UTF-8 or UTF-16 characters, giving a copyright notice.
1387 * If UTF-16 is used, the string shall start with the BYTE ORDER MARK (0xFEFF), to distinguish it from a UTF-8 string.
1388 * This mark does not form part of the final string. */
1389 uint32_t notice_length
;
1393 * This box is a container box for informative user-data.
1394 * This user data is formatted as a set of boxes with more specific box types, which declare more precisely their content.
1395 * QTFF: for historical reasons, this box is optionally terminated by a 32-bit integer set to 0. */
1398 ISOM_BASEBOX_COMMON
;
1399 isom_chpl_t
*chpl
; /* Chapter List Box */
1400 isom_meta_t
*meta
; /* Meta Box extended by Apple for iTunes movie */
1401 /* QuickTime user data */
1402 isom_WLOC_t
*WLOC
; /* Window Location Box */
1403 isom_LOOP_t
*LOOP
; /* Looping Box */
1404 isom_SelO_t
*SelO
; /* Play Selection Only Box */
1405 isom_AllF_t
*AllF
; /* Play All Frames Box */
1406 /* Copyright Box List */
1407 lsmash_entry_list_t cprt_list
; /* Copyright Boxes is defined in ISO Base Media and 3GPP file format */
1410 /** Caches for handling tracks **/
1413 uint64_t alloc
; /* total buffer size for the pool */
1414 uint64_t size
; /* total size of samples in the pool */
1415 uint32_t sample_count
; /* number of samples in the pool */
1416 uint8_t *data
; /* actual data of samples in the pool */
1417 } isom_sample_pool_t
;
1421 uint32_t chunk_number
; /* chunk number */
1422 uint32_t sample_description_index
; /* sample description index */
1423 uint64_t first_dts
; /* the first DTS in chunk */
1424 isom_sample_pool_t
*pool
; /* samples pooled to interleave */
1436 isom_group_assignment_entry_t
*assignment
; /* the address corresponding to the entry in Sample to Group Box */
1437 isom_group_assignment_entry_t
*prev_assignment
; /* the address of the previous assignment */
1438 isom_rap_entry_t
*random_access
; /* the address corresponding to the random access entry in Sample Group Description Box */
1439 uint8_t is_prev_rap
; /* whether the previous sample is a random access point or not */
1444 isom_group_assignment_entry_t
*assignment
; /* the address corresponding to the entry in Sample to Group Box */
1445 isom_sgpd_t
*sgpd
; /* the address to the active Sample Group Description Box */
1446 uint32_t first_sample
; /* the number of the first sample of the group */
1447 uint32_t recovery_point
; /* the identifier necessary for the recovery from its starting point to be completed */
1448 uint64_t rp_cts
; /* the CTS of the recovery point */
1449 int16_t roll_distance
; /* the current roll_distance
1450 * The value may be updated when 'described' is set to ROLL_DISTANCE_INITIALIZED. */
1451 #define MAX_ROLL_WAIT_AND_SEE_COUNT 64
1452 uint8_t wait_and_see_count
; /* Wait-and-see after initialization of roll_distance until reaching MAX_ROLL_WAIT_AND_SEE. */
1453 uint8_t is_fragment
; /* the flag if the current group is in fragment */
1454 uint8_t prev_is_recovery_start
; /* whether the previous sample is a starting point of recovery or not */
1455 uint8_t delimited
; /* the flag if the sample_count is determined */
1456 #define ROLL_DISTANCE_INITIALIZED 1
1457 #define ROLL_DISTANCE_DETERMINED 2
1458 uint8_t described
; /* the status of the group description */
1459 } isom_roll_group_t
;
1463 lsmash_entry_list_t
*pool
; /* grouping pooled to delimit and describe */
1468 uint64_t segment_duration
; /* the sum of the subsegment_duration of preceeding subsegments */
1469 uint64_t largest_cts
; /* the largest CTS of a subsegment of the reference stream */
1470 uint64_t smallest_cts
; /* the smallest CTS of a subsegment of the reference stream */
1471 uint64_t first_sample_cts
; /* the CTS of the first sample of a subsegment of the reference stream */
1472 /* SAP related info within the active subsegment of the reference stream */
1473 uint64_t first_ed_cts
; /* the earliest CTS of decodable samples after the first recovery point */
1474 uint64_t first_rp_cts
; /* the CTS of the first recovery point */
1475 uint32_t first_rp_number
; /* the number of the first recovery point */
1476 uint32_t first_ra_number
; /* the number of the first random accessible sample */
1477 lsmash_random_access_flag first_ra_flags
; /* the flags of the first random accessible sample */
1478 int is_first_recovery_point
;
1480 } isom_subsegment_t
;
1484 uint8_t has_samples
; /* Whether whole movie has any sample or not. */
1485 uint8_t roll_grouping
;
1486 uint8_t rap_grouping
;
1487 uint32_t traf_number
;
1488 uint32_t last_duration
; /* the last sample duration in this track fragment */
1489 uint64_t largest_cts
; /* the largest CTS in this track fragment */
1490 uint32_t sample_count
; /* the number of samples in this track fragment */
1491 uint32_t output_sample_count
; /* the number of output samples in this track fragment */
1492 isom_subsegment_t subsegment
;
1497 uint8_t all_sync
; /* if all samples are sync sample */
1500 isom_timestamp_t timestamp
; /* Each field stores the last valid value. */
1501 isom_grouping_t roll
;
1502 isom_rap_group_t
*rap
;
1503 isom_fragment_t
*fragment
;
1506 /** Movie Fragments Boxes **/
1507 /* Track Fragments Flags ('tf_flags') */
1510 ISOM_TF_FLAGS_BASE_DATA_OFFSET_PRESENT
= 0x000001, /* base-data-offset-present:
1511 * This flag indicates the presence of the base_data_offset field.
1512 * The base_data_offset is the base offset to use when calculating data offsets.
1513 * Offsets are file offsets as like as chunk_offset in Chunk Offset Box.
1514 * If this flag is set and default-base-is-moof is not set, the base_data_offset
1515 * for the first track in the movie fragment is the position of the first byte
1516 * of the enclosing Movie Fragment Box, and for second and subsequent track
1517 * fragments, the default is the end of the data defined by the preceding fragment. */
1518 ISOM_TF_FLAGS_SAMPLE_DESCRIPTION_INDEX_PRESENT
= 0x000002, /* sample-description-index-present
1519 * This flag indicates the presence of the sample_description_index field. */
1520 ISOM_TF_FLAGS_DEFAULT_SAMPLE_DURATION_PRESENT
= 0x000008, /* default-sample-duration-present:
1521 * This flag indicates the presence of the default_sample_duration field. */
1522 ISOM_TF_FLAGS_DEFAULT_SAMPLE_SIZE_PRESENT
= 0x000010, /* default-sample-size-present:
1523 * This flag indicates the presence of the default_sample_size field. */
1524 ISOM_TF_FLAGS_DEFAULT_SAMPLE_FLAGS_PRESENT
= 0x000020, /* default-sample-flags-present:
1525 * This flag indicates the presence of the default_sample_flags field. */
1526 ISOM_TF_FLAGS_DURATION_IS_EMPTY
= 0x010000, /* duration-is-empty:
1527 * This flag indicates there are no samples for this time interval. */
1528 ISOM_TF_FLAGS_DEFAULT_BASE_IS_MOOF
= 0x020000, /* default-base-is-moof:
1529 * If base-data-offset-present is not set, this flag indicates the implicit
1530 * base_data_offset is always equal to the position of the first byte of the
1531 * enclosing Movie Fragment BOX.
1532 * This flag is only available under the 'iso5' or later brands and cannot be set
1533 * when earlier brands are included in the File Type box. */
1534 } isom_tf_flags_code
;
1536 /* Track Run Flags ('tr_flags') */
1539 ISOM_TR_FLAGS_DATA_OFFSET_PRESENT
= 0x000001, /* data-offset-present:
1540 * This flag indicates the presence of the data_offset field. */
1541 ISOM_TR_FLAGS_FIRST_SAMPLE_FLAGS_PRESENT
= 0x000004, /* first-sample-flags-present:
1542 * This flag indicates the presence of the first_sample_flags field. */
1543 ISOM_TR_FLAGS_SAMPLE_DURATION_PRESENT
= 0x000100, /* sample-duration-present:
1544 * This flag indicates the presence of the sample_duration field. */
1545 ISOM_TR_FLAGS_SAMPLE_SIZE_PRESENT
= 0x000200, /* sample-size-present:
1546 * This flag indicates the presence of the sample_size field. */
1547 ISOM_TR_FLAGS_SAMPLE_FLAGS_PRESENT
= 0x000400, /* sample-flags-present:
1548 * This flag indicates the presence of the sample_flags field. */
1549 ISOM_TR_FLAGS_SAMPLE_COMPOSITION_TIME_OFFSET_PRESENT
= 0x000800, /* sample-composition-time-offsets-present:
1550 * This flag indicates the presence of the sample_composition_time_offset field. */
1551 } isom_tr_flags_code
;
1556 unsigned reserved
: 4;
1557 /* The definition of the following fields is quite the same as Independent and Disposable Samples Box. */
1558 unsigned is_leading
: 2;
1559 unsigned sample_depends_on
: 2;
1560 unsigned sample_is_depended_on
: 2;
1561 unsigned sample_has_redundancy
: 2;
1563 unsigned sample_padding_value
: 3; /* the number of bits at the end of this sample */
1564 unsigned sample_is_non_sync_sample
: 1; /* 0 value means this sample is sync sample. */
1565 uint16_t sample_degradation_priority
;
1566 } isom_sample_flags_t
;
1568 /* Movie Extends Header Box
1569 * This box is omitted when used in live streaming.
1570 * If this box is not present, the overall duration must be computed by examining each fragment. */
1573 ISOM_FULLBOX_COMMON
;
1574 /* version == 0: uint64_t -> uint32_t */
1575 uint64_t fragment_duration
; /* the duration of the longest track, in the timescale indicated in the Movie Header Box, including movie fragments. */
1578 /* Track Extends Box
1579 * This box sets up default values used by the movie fragments. */
1582 ISOM_FULLBOX_COMMON
;
1583 uint32_t track_ID
; /* identifier of the track; this shall be the track ID of a track in the Movie Box */
1584 uint32_t default_sample_description_index
;
1585 uint32_t default_sample_duration
;
1586 uint32_t default_sample_size
;
1587 isom_sample_flags_t default_sample_flags
;
1590 /* Movie Extends Box
1591 * This box warns readers that there might be Movie Fragment Boxes in this file. */
1594 ISOM_BASEBOX_COMMON
;
1595 isom_mehd_t
*mehd
; /* Movie Extends Header Box / omitted when used in live streaming */
1596 lsmash_entry_list_t trex_list
; /* Track Extends Box */
1599 /* Movie Fragment Header Box
1600 * This box contains a sequence number, as a safety check.
1601 * The sequence number 'usually' starts at 1 and must increase for each movie fragment in the file, in the order in which they occur. */
1604 ISOM_FULLBOX_COMMON
;
1605 uint32_t sequence_number
; /* the ordinal number of this fragment, in increasing order */
1608 /* Track Fragment Header Box
1609 * Each movie fragment can contain zero or more fragments for each track;
1610 * and a track fragment can contain zero or more contiguous runs of samples.
1611 * This box sets up information and defaults used for those runs of samples. */
1614 ISOM_FULLBOX_COMMON
; /* flags field is used for 'tf_flags'. */
1616 /* all the following are optional fields */
1617 uint64_t base_data_offset
; /* an explicit anchor for the data offsets in each track run
1618 * To avoid the case this field might overflow, e.g. semi-permanent live streaming and broadcasting,
1619 * you shall not use this optional field. */
1620 uint32_t sample_description_index
; /* override default_sample_description_index in Track Extends Box */
1621 uint32_t default_sample_duration
; /* override default_sample_duration in Track Extends Box */
1622 uint32_t default_sample_size
; /* override default_sample_size in Track Extends Box */
1623 isom_sample_flags_t default_sample_flags
; /* override default_sample_flags in Track Extends Box */
1626 /* Track Fragment Base Media Decode Time Box
1627 * This box provides the absolute decode time, measured on the media timeline, of the first sample in decode order in the track fragment.
1628 * This can be useful, for example, when performing random access in a file;
1629 * it is not necessary to sum the sample durations of all preceding samples in previous fragments to find this value
1630 * (where the sample durations are the deltas in the Decoding Time to Sample Box and the sample_durations in the preceding track runs).
1631 * This box, if present, shall be positioned after the Track Fragment Header Box and before the first Track Fragment Run box. */
1634 ISOM_FULLBOX_COMMON
; /* version is either 0 or 1 */
1635 /* version == 0: 64bits -> 32bits */
1636 uint64_t baseMediaDecodeTime
; /* an integer equal to the sum of the decode durations of all earlier samples in the media, expressed in the media's timescale
1637 * It does not include the samples added in the enclosing track fragment.
1638 * NOTE: the decode timeline is a media timeline, established before any explicit or implied mapping of media time to presentation time,
1639 * for example by an edit list or similar structure. */
1642 /* Track Fragment Run Box
1643 * Within the Track Fragment Box, there are zero or more Track Fragment Run Boxes.
1644 * If the duration-is-empty flag is set in the tf_flags, there are no track runs.
1645 * A track run documents a contiguous set of samples for a track. */
1648 ISOM_FULLBOX_COMMON
; /* flags field is used for 'tr_flags'. */
1649 uint32_t sample_count
; /* the number of samples being added in this run; also the number of rows in the following table */
1650 /* The following are optional fields. */
1651 int32_t data_offset
; /* This value is added to the implicit or explicit data_offset established in the Track Fragment Header Box.
1652 * If this field is not present, then the data for this run starts immediately after the data of the previous run,
1653 * or at the base_data_offset defined by the Track Fragment Header Box if this is the first run in a track fragment. */
1654 isom_sample_flags_t first_sample_flags
; /* a set of flags for the first sample only of this run */
1655 lsmash_entry_list_t
*optional
; /* all fields in this array are optional. */
1660 /* If the following fields is present, each field overrides default value described in Track Fragment Header Box or Track Extends Box. */
1661 uint32_t sample_duration
; /* override default_sample_duration */
1662 uint32_t sample_size
; /* override default_sample_size */
1663 isom_sample_flags_t sample_flags
; /* override default_sample_flags */
1665 uint32_t sample_composition_time_offset
; /* composition time offset
1666 * If version == 0, unsigned 32-bit integer.
1667 * Otherwise, signed 32-bit integer. */
1668 } isom_trun_optional_row_t
;
1670 /* Track Fragment Box */
1673 ISOM_BASEBOX_COMMON
;
1674 isom_tfhd_t
*tfhd
; /* Track Fragment Header Box */
1675 isom_tfdt_t
*tfdt
; /* Track Fragment Base Media Decode Time Box */
1676 lsmash_entry_list_t trun_list
; /* Track Fragment Run Box List
1677 * If the duration-is-empty flag is set in the tf_flags, there are no track runs. */
1678 isom_sdtp_t
*sdtp
; /* Independent and Disposable Samples Box (available under Protected Interoperable File Format) */
1679 lsmash_entry_list_t sgpd_list
; /* Sample Group Description Boxes (available under ISO Base Media version 6 or later) */
1680 lsmash_entry_list_t sbgp_list
; /* Sample To Group Boxes */
1682 isom_cache_t
*cache
; /* taken over from corresponding 'trak' */
1685 /* Movie Fragment Box */
1688 ISOM_BASEBOX_COMMON
;
1689 isom_mfhd_t
*mfhd
; /* Movie Fragment Header Box */
1690 lsmash_entry_list_t traf_list
; /* Track Fragment Box List */
1693 /* Track Fragment Random Access Box
1694 * Each entry in this box contains the location and the presentation time of the sync sample.
1695 * Note that not every sync sample in the track needs to be listed in the table.
1696 * The absence of this box does not mean that all the samples are sync samples. */
1699 ISOM_FULLBOX_COMMON
;
1701 unsigned int reserved
: 26;
1702 unsigned int length_size_of_traf_num
: 2; /* the length in byte of the traf_number field minus one */
1703 unsigned int length_size_of_trun_num
: 2; /* the length in byte of the trun_number field minus one */
1704 unsigned int length_size_of_sample_num
: 2; /* the length in byte of the sample_number field minus one */
1705 uint32_t number_of_entry
; /* the number of the entries for this track
1706 * Value zero indicates that every sample is a sync sample and no table entry follows. */
1707 lsmash_entry_list_t
*list
; /* entry_count corresponds to number_of_entry. */
1712 /* version == 0: 64bits -> 32bits */
1713 uint64_t time
; /* the presentation time of the sync sample in units defined in the Media Header Box of the associated track
1714 * For segments based on movie sample tables or movie fragments, presentation times are in the movie timeline,
1715 * that is they are composition times after the application of any edit list for the track.
1716 * Note: the definition of segment is portion of an ISO base media file format file, consisting of either
1717 * (a) a movie box, with its associated media data (if any) and other associated boxes
1719 * (b) one or more movie fragment boxes, with their associated media data, and other associated boxes. */
1720 uint64_t moof_offset
; /* the offset of the Movie Fragment Box used in this entry
1721 * Offset is the byte-offset between the beginning of the file and the beginning of the Movie Fragment Box. */
1723 uint32_t traf_number
; /* the Track Fragment Box ('traf') number that contains the sync sample
1724 * The number ranges from 1 in each Movie Fragment Box ('moof'). */
1725 uint32_t trun_number
; /* the Track Fragment Run Box ('trun') number that contains the sync sample
1726 * The number ranges from 1 in each Track Fragment Box ('traf'). */
1727 uint32_t sample_number
; /* the sample number that contains the sync sample
1728 * The number ranges from 1 in each Track Fragment Run Box ('trun'). */
1729 } isom_tfra_location_time_entry_t
;
1731 /* Movie Fragment Random Access Offset Box
1732 * This box provides a copy of the length field from the enclosing Movie Fragment Random Access Box. */
1735 ISOM_FULLBOX_COMMON
;
1736 uint32_t length
; /* an integer gives the number of bytes of the enclosing Movie Fragment Random Access Box
1737 * This field is placed at the last of the enclosing box to assist readers scanning
1738 * from the end of the file in finding the Movie Fragment Random Access Box. */
1741 /* Movie Fragment Random Access Box
1742 * This box provides a table which may assist readers in finding sync samples in a file using movie fragments,
1743 * and is usually placed at or near the end of the file.
1744 * The last box within the Movie Fragment Random Access Box, which is called Movie Fragment Random Access Offset Box,
1745 * provides a copy of the length field from the Movie Fragment Random Access Box. */
1748 ISOM_BASEBOX_COMMON
;
1749 lsmash_entry_list_t tfra_list
; /* Track Fragment Random Access Box */
1750 isom_mfro_t
*mfro
; /* Movie Fragment Random Access Offset Box */
1753 /* Movie fragment manager
1754 * The presence of this means we use the structure of movie fragments. */
1757 #define FIRST_MOOF_POS_UNDETERMINED UINT64_MAX
1758 isom_moof_t
*movie
; /* the address corresponding to the current Movie Fragment Box */
1759 uint64_t first_moof_pos
;
1760 uint64_t pool_size
; /* the total sample size in the current movie fragment */
1761 uint64_t sample_count
; /* the number of samples within the current movie fragment */
1762 lsmash_entry_list_t
*pool
; /* samples pooled to interleave for the current movie fragment */
1763 } isom_fragment_manager_t
;
1770 ISOM_BASEBOX_COMMON
;
1771 isom_tkhd_t
*tkhd
; /* Track Header Box */
1772 isom_tapt_t
*tapt
; /* ISOM: null / QTFF: Track Aperture Mode Dimensions Box */
1773 isom_edts_t
*edts
; /* Edit Box */
1774 isom_tref_t
*tref
; /* Track Reference Box */
1775 isom_mdia_t
*mdia
; /* Media Box */
1776 isom_udta_t
*udta
; /* User Data Box */
1777 isom_meta_t
*meta
; /* Meta Box */
1779 isom_cache_t
*cache
;
1780 uint32_t related_track_ID
;
1787 ISOM_BASEBOX_COMMON
;
1788 isom_mvhd_t
*mvhd
; /* Movie Header Box */
1789 isom_iods_t
*iods
; /* MP4: Object Descriptor Box */
1790 lsmash_entry_list_t trak_list
; /* Track Box List */
1791 isom_udta_t
*udta
; /* User Data Box */
1792 isom_ctab_t
*ctab
; /* ISOM: null / QTFF: Color Table Box */
1793 isom_meta_t
*meta
; /* Meta Box */
1794 isom_mvex_t
*mvex
; /* Movie Extends Box */
1799 * portion of an ISO base media file format file, consisting of either (a) a movie box, with its associated media data
1800 * (if any) and other associated boxes or (b) one or more movie fragment boxes, with their associated media data, and
1801 * and other associated boxes
1803 * time interval of a segment formed from movie fragment boxes, that is also a valid segment
1804 * A subsegment is defined as a time interval of the containing (sub)segment, and corresponds to a single range of
1805 * bytes of the containing (sub)segment. The durations of all the subsegments sum to the duration of the containing
1809 * Media presentations may be divided into segments for delivery, for example, it is possible (e.g. in HTTP streaming) to
1810 * form files that contain a segment ? or concatenated segments ? which would not necessarily form ISO Base Media file
1811 * format compliant files (e.g. they do not contain a Movie Box).
1812 * If segments are stored in separate files (e.g. on a standard HTTP server) it is recommended that these 'segment files'
1813 * contain a Segment Type Box, which must be first if present, to enable identification of those files, and declaration of
1814 * the specifications with which they are compliant.
1815 * Segment Type Boxes that are not first in a file may be ignored.
1816 * Valid Segment Type Boxes shall be the first box in a segment.
1818 * The 'valid' here does not always mean that any brand of that segment has compatibility against other brands of it.
1819 * After concatenations of segments, the result file might contain incompatibilities among brands. */
1820 typedef isom_ftyp_t isom_styp_t
;
1822 /* Segment Index Box
1823 * This box provides a compact index of one media stream within the media segment to which it applies.
1825 * Each Segment Index Box documents how a (sub)segment is divided into one or more subsegments (which may themselves be
1826 * further subdivided using Segment Index boxes).
1828 * Each entry in the Segment Index Box contains a reference type that indicates whether the reference points directly to
1829 * the media bytes of a referenced leaf subsegment, which is a subsegment that does not contain any indexing information
1830 * that would enable its further division into subsegments, or to a Segment Index box that describes how the referenced
1831 * subsegment is further subdivided; as a result, the segment may be indexed in a 'hierarchical' or 'daisy-chain' or
1832 * other form by documenting time and byte offset information for other Segment Index Boxes applying to portions of the
1833 * same (sub)segment.
1835 * For segments based on ISO Base Media file format (i.e. based on movie sample tables or movie fragments):
1836 * ! an access unit is a sample;
1837 * ! a subsegment is a self-contained set of one or more consecutive movie fragments; a self-contained set contains
1838 * one or more Movie Fragment Boxes with the corresponding Media Data Box(es), and a Media Data Box containing data
1839 * referenced by a Movie Fragment Box must follow that Movie Fragment Box and precede the next Movie Fragment box
1840 * containing information about the same track;
1841 * ! Segment Index Boxes shall be placed before subsegment material they document, that is, before any Movie Fragment
1842 * Box of the documented material of the subsegment;
1843 * ! streams are tracks in the file format, and stream IDs are track IDs;
1844 * ! a subsegment contains a stream access point if a track fragment within the subsegment for the track with track_ID
1845 * equal to reference_ID contains a stream access point;
1846 * ! initialisation data for SAPs consists of the Movie Box;
1847 * ! presentation times are in the movie timeline, that is they are composition times after the application of any edit
1848 * list for the track;
1849 * ! the ISAP is a position exactly pointing to the start of a top-level box, such as a Movie Fragment Box;
1850 * ! a SAP of type 1 or type 2 is indicated as a sync sample;
1851 * ! a SAP of type 3 is marked as a member of a sample group of type 'rap ';
1852 * ! a SAP of type 4 is marked as a member of a sample group of type 'roll' where the value of the roll_distance field
1853 * is greater than 0.
1854 * For SAPs of type 5 and 6, no specific signalling in the ISO Base Media file format is supported. */
1857 unsigned int reference_type
: 1; /* 1: the reference is to a Segment Index Box
1858 * 0: the reference is to media content
1859 * For files based on the ISO Base Media file format, the reference is to a
1860 * Movie Fragment Box.
1861 * If a separate index segment is used, then entries with reference type 1 are
1862 * in the index segment, and entries with reference type 0 are in the media file. */
1863 unsigned int reference_size
: 31; /* the distance in bytes from the first byte of the referenced item to the first
1864 * byte of the next referenced item, or in the case of the last entry, the end of
1865 * the referenced material */
1866 uint32_t subsegment_duration
; /* when the reference is to Segment Index Box, i.e. reference_type is equal to 1:
1867 * this field carries the sum of the subsegment_duration fields in that box;
1868 * when the reference is to a subsegment:
1869 * this field carries the difference between the earliest presentation time of
1870 * any access unit of the reference stream in the next subsegment (or the first
1871 * subsegment of the next segment, if this is the last subsegment of the segment,
1872 * or the end presentation time of the reference stream if this is the last
1873 * subsegment of the stream) and the earliest presentation time of any access
1874 * unit of the reference stream in the referenced subsegment;
1875 * The duration is expressed in the timescale of the enclosing Segment Index Box. */
1876 unsigned int starts_with_SAP
: 1; /* whether the referenced subsegments start with a SAP */
1877 unsigned int SAP_type
: 3; /* a SAP type or the value 0
1878 * When starting with a SAP, the value 0 means a SAP may be of an unknown type.
1879 * Otherwise, the value 0 means no information of SAPs is provided. */
1880 unsigned int SAP_delta_time
: 28; /* TSAP of the first SAP, in decoding order, in the referenced subsegment for
1881 * the reference stream
1882 * If the referenced subsegments do not contain a SAP, SAP_delta_time is
1883 * reserved with the value 0, otherwise SAP_delta_time is the difference between
1884 * the earliest presentation time of the subsegment, and the TSAP.
1885 * Note that this difference may be zero, in the case that the subsegment starts
1887 } isom_sidx_referenced_item_t
;
1891 ISOM_FULLBOX_COMMON
;
1892 uint32_t reference_ID
; /* the stream ID for the reference stream
1893 * If this Segment Index box is referenced from a "parent" Segment Index box, the value
1894 * of the value of reference_ID shall be the same as the value of reference_ID of the
1895 * "parent" Segment Index Box. */
1896 uint32_t timescale
; /* the timescale, in ticks per second, for the time and duration fields within this box
1897 * It is recommended that this match the timescale of the reference stream or track.
1898 * For files based on the ISO Base Media file format, that is the timescale field of
1899 * the Media Header Box of the track. */
1900 /* version == 0: 64bits -> 32bits */
1901 uint64_t earliest_presentation_time
; /* the earliest presentation time of any access unit in the reference stream
1902 * in the first subsegment, in the timescale indicated in the timescale field */
1903 uint64_t first_offset
; /* the distance in bytes, in the file containing media, from the anchor point,
1904 * to the first byte of the indexed material */
1906 uint16_t reserved
; /* 0 */
1907 uint16_t reference_count
; /* the number of referenced items */
1908 lsmash_entry_list_t
*list
; /* entry_count corresponds to reference_count. */
1914 struct lsmash_file_tag
1916 ISOM_FULLBOX_COMMON
; /* The 'size' field indicates total file size.
1917 * The 'flags' field indicates file mode. */
1918 isom_ftyp_t
*ftyp
; /* File Type Box */
1919 lsmash_entry_list_t styp_list
; /* Segment Type Box List */
1920 isom_moov_t
*moov
; /* Movie Box */
1921 lsmash_entry_list_t sidx_list
; /* Segment Index Box List */
1922 lsmash_entry_list_t moof_list
; /* Movie Fragment Box List */
1923 isom_mdat_t
*mdat
; /* Media Data Box */
1924 isom_meta_t
*meta
; /* Meta Box */
1925 isom_mfra_t
*mfra
; /* Movie Fragment Random Access Box */
1927 lsmash_bs_t
*bs
; /* bytestream manager */
1928 isom_fragment_manager_t
*fragment
; /* movie fragment manager */
1929 lsmash_entry_list_t
*print
;
1930 lsmash_entry_list_t
*timeline
;
1931 lsmash_file_t
*initializer
; /* A file containing the initialization information of whole movie including subsequent segments
1932 * For ISOBMFF, an initializer corresponds to a file containing the 'moov' box.
1933 * ROOT-to-initializer is designed to be a one-to-one relationship while initializer-to-file
1934 * is designed to be a one-to-many relationship. */
1935 struct importer_tag
*importer
; /* An importer of this file
1936 * Importer-to-file is designed to be a one-to-one relationship. */
1937 uint64_t fragment_count
; /* the number of movie fragments we created */
1938 double max_chunk_duration
; /* max duration per chunk in seconds */
1939 double max_async_tolerance
; /* max tolerance, in seconds, for amount of interleaving asynchronization between tracks */
1940 uint64_t max_chunk_size
; /* max size per chunk in bytes. */
1941 uint32_t brand_count
;
1942 uint32_t *compatible_brands
; /* the backup of the compatible brands in the File Type Box or the valid Segment Type Box */
1943 uint8_t fake_file_mode
; /* If set to 1, the bytestream manager handles fake-file stream. */
1944 /* flags for compatibility */
1945 #define COMPAT_FLAGS_OFFSET offsetof( lsmash_file_t, qt_compatible )
1946 uint8_t qt_compatible
; /* compatibility with QuickTime file format */
1947 uint8_t isom_compatible
; /* compatibility with ISO Base Media file format */
1948 uint8_t avc_extensions
; /* compatibility with AVC extensions */
1949 uint8_t mp4_version1
; /* compatibility with MP4 ver.1 file format */
1950 uint8_t mp4_version2
; /* compatibility with MP4 ver.2 file format */
1951 uint8_t itunes_movie
; /* compatibility with iTunes Movie */
1952 uint8_t max_3gpp_version
; /* maximum 3GPP version */
1953 uint8_t max_isom_version
; /* maximum ISO Base Media file format version */
1954 uint8_t min_isom_version
; /* minimum ISO Base Media file format version */
1955 uint8_t forbid_tref
; /* If set to 1, track reference is forbidden. */
1956 uint8_t undefined_64_ver
; /* If set to 1, 64-bit version fields, e.g. duration, are undefined. */
1957 uint8_t allow_moof_base
; /* If set to 1, default-base-is-moof is available for muxing. */
1958 uint8_t media_segment
; /* If set to 1, this file is a media segment. */
1961 /* fake-file stream */
1967 } fake_file_stream_t
;
1970 struct lsmash_root_tag
1972 ISOM_FULLBOX_COMMON
; /* The 'file' field contains the address of the current active file. */
1973 lsmash_entry_list_t file_abstract_list
; /* the list of all files the ROOT contains */
1978 /* Pre-defined precedence */
1979 #define LSMASH_BOX_PRECEDENCE_ISOM_FTYP (LSMASH_BOX_PRECEDENCE_H - 0 * LSMASH_BOX_PRECEDENCE_S)
1980 #define LSMASH_BOX_PRECEDENCE_ISOM_STYP (LSMASH_BOX_PRECEDENCE_H - 0 * LSMASH_BOX_PRECEDENCE_S)
1981 #define LSMASH_BOX_PRECEDENCE_ISOM_SIDX (LSMASH_BOX_PRECEDENCE_N + 1 * LSMASH_BOX_PRECEDENCE_S) /* shall be placed before any 'moof' of the documented subsegments */
1982 #define LSMASH_BOX_PRECEDENCE_ISOM_MOOV (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
1983 #define LSMASH_BOX_PRECEDENCE_ISOM_MVHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
1984 #define LSMASH_BOX_PRECEDENCE_ISOM_IODS (LSMASH_BOX_PRECEDENCE_HM - 2 * LSMASH_BOX_PRECEDENCE_S)
1985 #define LSMASH_BOX_PRECEDENCE_ISOM_TRAK (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
1986 #define LSMASH_BOX_PRECEDENCE_ISOM_TKHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
1987 #define LSMASH_BOX_PRECEDENCE_QTFF_TAPT (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
1988 #define LSMASH_BOX_PRECEDENCE_QTFF_CLEF (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
1989 #define LSMASH_BOX_PRECEDENCE_QTFF_PROF (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
1990 #define LSMASH_BOX_PRECEDENCE_QTFF_ENOF (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
1991 #define LSMASH_BOX_PRECEDENCE_ISOM_EDTS (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
1992 #define LSMASH_BOX_PRECEDENCE_ISOM_ELST (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
1993 #define LSMASH_BOX_PRECEDENCE_ISOM_TREF (LSMASH_BOX_PRECEDENCE_N - 3 * LSMASH_BOX_PRECEDENCE_S)
1994 #define LSMASH_BOX_PRECEDENCE_ISOM_TREF_TYPE (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
1995 #define LSMASH_BOX_PRECEDENCE_ISOM_MDIA (LSMASH_BOX_PRECEDENCE_N - 4 * LSMASH_BOX_PRECEDENCE_S)
1996 #define LSMASH_BOX_PRECEDENCE_ISOM_MDHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
1997 #define LSMASH_BOX_PRECEDENCE_ISOM_HDLR (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
1998 #define LSMASH_BOX_PRECEDENCE_ISOM_MINF (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
1999 #define LSMASH_BOX_PRECEDENCE_ISOM_VMHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2000 #define LSMASH_BOX_PRECEDENCE_ISOM_SMHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2001 #define LSMASH_BOX_PRECEDENCE_ISOM_HMHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2002 #define LSMASH_BOX_PRECEDENCE_ISOM_NMHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2003 #define LSMASH_BOX_PRECEDENCE_QTFF_GMHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2004 #define LSMASH_BOX_PRECEDENCE_QTFF_GMIN (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2005 #define LSMASH_BOX_PRECEDENCE_QTFF_TEXT (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
2006 #define LSMASH_BOX_PRECEDENCE_ISOM_DINF (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
2007 #define LSMASH_BOX_PRECEDENCE_ISOM_DREF (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
2008 #define LSMASH_BOX_PRECEDENCE_ISOM_DREF_ENTRY (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2009 #define LSMASH_BOX_PRECEDENCE_ISOM_STBL (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
2010 #define LSMASH_BOX_PRECEDENCE_ISOM_STSD (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2011 #define LSMASH_BOX_PRECEDENCE_QTFF_GLBL (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2012 #define LSMASH_BOX_PRECEDENCE_ISOM_ESDS (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2013 #define LSMASH_BOX_PRECEDENCE_QTFF_ESDS (LSMASH_BOX_PRECEDENCE_HM - 1 * LSMASH_BOX_PRECEDENCE_S) /* preceded by 'frma' and 'mp4a' */
2014 #define LSMASH_BOX_PRECEDENCE_ISOM_BTRT (LSMASH_BOX_PRECEDENCE_HM - 1 * LSMASH_BOX_PRECEDENCE_S)
2015 #define LSMASH_BOX_PRECEDENCE_ISOM_COLR (LSMASH_BOX_PRECEDENCE_LP + 2 * LSMASH_BOX_PRECEDENCE_S)
2016 #define LSMASH_BOX_PRECEDENCE_QTFF_COLR (LSMASH_BOX_PRECEDENCE_LP + 2 * LSMASH_BOX_PRECEDENCE_S)
2017 #define LSMASH_BOX_PRECEDENCE_QTFF_GAMA (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2018 #define LSMASH_BOX_PRECEDENCE_QTFF_FIEL (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2019 #define LSMASH_BOX_PRECEDENCE_QTFF_CSPC (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2020 #define LSMASH_BOX_PRECEDENCE_QTFF_SGBT (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S) /* 'v216' specific */
2021 #define LSMASH_BOX_PRECEDENCE_ISOM_CLAP (LSMASH_BOX_PRECEDENCE_LP + 1 * LSMASH_BOX_PRECEDENCE_S)
2022 #define LSMASH_BOX_PRECEDENCE_ISOM_PASP (LSMASH_BOX_PRECEDENCE_LP - 0 * LSMASH_BOX_PRECEDENCE_S)
2023 #define LSMASH_BOX_PRECEDENCE_ISOM_STSL (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2024 #define LSMASH_BOX_PRECEDENCE_ISOM_CHAN (LSMASH_BOX_PRECEDENCE_LP - 0 * LSMASH_BOX_PRECEDENCE_S)
2025 #define LSMASH_BOX_PRECEDENCE_QTFF_CHAN (LSMASH_BOX_PRECEDENCE_LP - 0 * LSMASH_BOX_PRECEDENCE_S)
2026 #define LSMASH_BOX_PRECEDENCE_QTFF_WAVE (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2027 #define LSMASH_BOX_PRECEDENCE_QTFF_FRMA (LSMASH_BOX_PRECEDENCE_HM + 1 * LSMASH_BOX_PRECEDENCE_S) /* precede any as much as possible */
2028 #define LSMASH_BOX_PRECEDENCE_QTFF_ENDA (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2029 #define LSMASH_BOX_PRECEDENCE_QTFF_MP4A (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2030 #define LSMASH_BOX_PRECEDENCE_QTFF_TERMINATOR (LSMASH_BOX_PRECEDENCE_L - 0 * LSMASH_BOX_PRECEDENCE_S)
2031 #define LSMASH_BOX_PRECEDENCE_ISOM_SRAT (LSMASH_BOX_PRECEDENCE_LP - 1 * LSMASH_BOX_PRECEDENCE_S) /* place at the end for maximum compatibility */
2032 #define LSMASH_BOX_PRECEDENCE_ISOM_FTAB (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2033 #define LSMASH_BOX_PRECEDENCE_ISOM_STTS (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
2034 #define LSMASH_BOX_PRECEDENCE_ISOM_CTTS (LSMASH_BOX_PRECEDENCE_N - 4 * LSMASH_BOX_PRECEDENCE_S)
2035 #define LSMASH_BOX_PRECEDENCE_ISOM_CSLG (LSMASH_BOX_PRECEDENCE_N - 6 * LSMASH_BOX_PRECEDENCE_S)
2036 #define LSMASH_BOX_PRECEDENCE_ISOM_STSS (LSMASH_BOX_PRECEDENCE_N - 8 * LSMASH_BOX_PRECEDENCE_S)
2037 #define LSMASH_BOX_PRECEDENCE_QTFF_STPS (LSMASH_BOX_PRECEDENCE_N - 10 * LSMASH_BOX_PRECEDENCE_S)
2038 #define LSMASH_BOX_PRECEDENCE_ISOM_SDTP (LSMASH_BOX_PRECEDENCE_N - 12 * LSMASH_BOX_PRECEDENCE_S)
2039 #define LSMASH_BOX_PRECEDENCE_ISOM_STSC (LSMASH_BOX_PRECEDENCE_N - 14 * LSMASH_BOX_PRECEDENCE_S)
2040 #define LSMASH_BOX_PRECEDENCE_ISOM_STSZ (LSMASH_BOX_PRECEDENCE_N - 16 * LSMASH_BOX_PRECEDENCE_S)
2041 #define LSMASH_BOX_PRECEDENCE_ISOM_STZ2 (LSMASH_BOX_PRECEDENCE_N - 16 * LSMASH_BOX_PRECEDENCE_S)
2042 #define LSMASH_BOX_PRECEDENCE_ISOM_STCO (LSMASH_BOX_PRECEDENCE_N - 18 * LSMASH_BOX_PRECEDENCE_S)
2043 #define LSMASH_BOX_PRECEDENCE_ISOM_CO64 (LSMASH_BOX_PRECEDENCE_N - 18 * LSMASH_BOX_PRECEDENCE_S)
2044 #define LSMASH_BOX_PRECEDENCE_ISOM_SGPD (LSMASH_BOX_PRECEDENCE_N - 20 * LSMASH_BOX_PRECEDENCE_S)
2045 #define LSMASH_BOX_PRECEDENCE_ISOM_SBGP (LSMASH_BOX_PRECEDENCE_N - 22 * LSMASH_BOX_PRECEDENCE_S)
2046 #define LSMASH_BOX_PRECEDENCE_ISOM_UDTA (LSMASH_BOX_PRECEDENCE_N - 5 * LSMASH_BOX_PRECEDENCE_S)
2047 #define LSMASH_BOX_PRECEDENCE_ISOM_MEAN (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2048 #define LSMASH_BOX_PRECEDENCE_ISOM_NAME (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
2049 #define LSMASH_BOX_PRECEDENCE_ISOM_DATA (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
2050 #define LSMASH_BOX_PRECEDENCE_QTFF_KEYS (LSMASH_BOX_PRECEDENCE_N - 1 * LSMASH_BOX_PRECEDENCE_S)
2051 #define LSMASH_BOX_PRECEDENCE_ISOM_ILST (LSMASH_BOX_PRECEDENCE_N - 2 * LSMASH_BOX_PRECEDENCE_S)
2052 #define LSMASH_BOX_PRECEDENCE_ISOM_METAITEM (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2053 #define LSMASH_BOX_PRECEDENCE_ISOM_CHPL (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2054 #define LSMASH_BOX_PRECEDENCE_ISOM_META (LSMASH_BOX_PRECEDENCE_N - 7 * LSMASH_BOX_PRECEDENCE_S)
2055 #define LSMASH_BOX_PRECEDENCE_QTFF_WLOC (LSMASH_BOX_PRECEDENCE_N - 8 * LSMASH_BOX_PRECEDENCE_S)
2056 #define LSMASH_BOX_PRECEDENCE_QTFF_LOOP (LSMASH_BOX_PRECEDENCE_N - 9 * LSMASH_BOX_PRECEDENCE_S)
2057 #define LSMASH_BOX_PRECEDENCE_QTFF_SELO (LSMASH_BOX_PRECEDENCE_N - 10 * LSMASH_BOX_PRECEDENCE_S)
2058 #define LSMASH_BOX_PRECEDENCE_QTFF_ALLF (LSMASH_BOX_PRECEDENCE_N - 11 * LSMASH_BOX_PRECEDENCE_S)
2059 #define LSMASH_BOX_PRECEDENCE_ISOM_CPRT (LSMASH_BOX_PRECEDENCE_N - 12 * LSMASH_BOX_PRECEDENCE_S)
2060 #define LSMASH_BOX_PRECEDENCE_QTFF_CTAB (LSMASH_BOX_PRECEDENCE_N - 6 * LSMASH_BOX_PRECEDENCE_S)
2061 #define LSMASH_BOX_PRECEDENCE_ISOM_MVEX (LSMASH_BOX_PRECEDENCE_N - 8 * LSMASH_BOX_PRECEDENCE_S)
2062 #define LSMASH_BOX_PRECEDENCE_ISOM_MEHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2063 #define LSMASH_BOX_PRECEDENCE_ISOM_TREX (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2064 #define LSMASH_BOX_PRECEDENCE_ISOM_MOOF (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2065 #define LSMASH_BOX_PRECEDENCE_ISOM_MFHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2066 #define LSMASH_BOX_PRECEDENCE_ISOM_TRAF (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2067 #define LSMASH_BOX_PRECEDENCE_ISOM_TFHD (LSMASH_BOX_PRECEDENCE_HM - 0 * LSMASH_BOX_PRECEDENCE_S)
2068 #define LSMASH_BOX_PRECEDENCE_ISOM_TFDT (LSMASH_BOX_PRECEDENCE_HM - 1 * LSMASH_BOX_PRECEDENCE_S) /* shall be positioned after 'tfhd' and before 'trun' */
2069 #define LSMASH_BOX_PRECEDENCE_ISOM_TRUN (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2070 #define LSMASH_BOX_PRECEDENCE_ISOM_MFRA (LSMASH_BOX_PRECEDENCE_L - 0 * LSMASH_BOX_PRECEDENCE_S)
2071 #define LSMASH_BOX_PRECEDENCE_ISOM_TFRA (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2072 #define LSMASH_BOX_PRECEDENCE_ISOM_MFRO (LSMASH_BOX_PRECEDENCE_L - 0 * LSMASH_BOX_PRECEDENCE_S)
2073 #define LSMASH_BOX_PRECEDENCE_ISOM_MDAT (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2074 #define LSMASH_BOX_PRECEDENCE_ISOM_FREE (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2075 #define LSMASH_BOX_PRECEDENCE_ISOM_SKIP (LSMASH_BOX_PRECEDENCE_N - 0 * LSMASH_BOX_PRECEDENCE_S)
2077 /* Track reference types */
2080 ISOM_TREF_TYPE_AVCP
= LSMASH_4CC( 'a', 'v', 'c', 'p' ), /* AVC parameter set stream link */
2081 ISOM_TREF_TYPE_CDSC
= LSMASH_4CC( 'c', 'd', 's', 'c' ), /* This track describes the referenced track. */
2082 ISOM_TREF_TYPE_DPND
= LSMASH_4CC( 'd', 'p', 'n', 'd' ), /* This track has an MPEG-4 dependency on the referenced track. */
2083 ISOM_TREF_TYPE_HIND
= LSMASH_4CC( 'h', 'i', 'n', 'd' ), /* Hint dependency */
2084 ISOM_TREF_TYPE_HINT
= LSMASH_4CC( 'h', 'i', 'n', 't' ), /* Links hint track to original media track */
2085 ISOM_TREF_TYPE_IPIR
= LSMASH_4CC( 'i', 'p', 'i', 'r' ), /* This track contains IPI declarations for the referenced track. */
2086 ISOM_TREF_TYPE_MPOD
= LSMASH_4CC( 'm', 'p', 'o', 'd' ), /* This track is an OD track which uses the referenced track as an included elementary stream track. */
2087 ISOM_TREF_TYPE_SBAS
= LSMASH_4CC( 's', 'b', 'a', 's' ), /* Scalable base */
2088 ISOM_TREF_TYPE_SCAL
= LSMASH_4CC( 's', 'c', 'a', 'l' ), /* Scalable extraction */
2089 ISOM_TREF_TYPE_SWFR
= LSMASH_4CC( 's', 'w', 'f', 'r' ), /* AVC Switch from */
2090 ISOM_TREF_TYPE_SWTO
= LSMASH_4CC( 's', 'w', 't', 'o' ), /* AVC Switch to */
2091 ISOM_TREF_TYPE_SYNC
= LSMASH_4CC( 's', 'y', 'n', 'c' ), /* This track uses the referenced track as its synchronization source. */
2092 ISOM_TREF_TYPE_VDEP
= LSMASH_4CC( 'v', 'd', 'e', 'p' ), /* Auxiliary video depth */
2093 ISOM_TREF_TYPE_VPLX
= LSMASH_4CC( 'v', 'p', 'l', 'x' ), /* Auxiliary video parallax */
2095 QT_TREF_TYPE_CHAP
= LSMASH_4CC( 'c', 'h', 'a', 'p' ), /* Chapter or scene list. Usually references a text track. */
2096 QT_TREF_TYPE_SCPT
= LSMASH_4CC( 's', 'c', 'p', 't' ), /* Transcript. Usually references a text track. */
2097 QT_TREF_TYPE_SSRC
= LSMASH_4CC( 's', 's', 'r', 'c' ), /* Nonprimary source. Indicates that the referenced track should send its data to this track, rather than presenting it. */
2098 QT_TREF_TYPE_TMCD
= LSMASH_4CC( 't', 'm', 'c', 'd' ), /* Time code. Usually references a time code track. */
2099 } isom_track_reference_type
;
2102 enum isom_handler_type
2104 QT_HANDLER_TYPE_DATA
= LSMASH_4CC( 'd', 'h', 'l', 'r' ),
2105 QT_HANDLER_TYPE_MEDIA
= LSMASH_4CC( 'm', 'h', 'l', 'r' ),
2110 ISOM_META_HANDLER_TYPE_ITUNES_METADATA
= LSMASH_4CC( 'm', 'd', 'i', 'r' ),
2113 /* Data reference types */
2114 enum isom_data_reference_type
2116 ISOM_REFERENCE_HANDLER_TYPE_URL
= LSMASH_4CC( 'u', 'r', 'l', ' ' ),
2117 ISOM_REFERENCE_HANDLER_TYPE_URN
= LSMASH_4CC( 'u', 'r', 'n', ' ' ),
2119 QT_REFERENCE_HANDLER_TYPE_ALIAS
= LSMASH_4CC( 'a', 'l', 'i', 's' ),
2120 QT_REFERENCE_HANDLER_TYPE_RESOURCE
= LSMASH_4CC( 'r', 's', 'r', 'c' ),
2121 QT_REFERENCE_HANDLER_TYPE_URL
= LSMASH_4CC( 'u', 'r', 'l', ' ' ),
2131 static const isom_language_t isom_languages
[] =
2133 { 0, ISOM_LANGUAGE_CODE_ENGLISH
},
2134 { 1, ISOM_LANGUAGE_CODE_FRENCH
},
2135 { 2, ISOM_LANGUAGE_CODE_GERMAN
},
2136 { 3, ISOM_LANGUAGE_CODE_ITALIAN
},
2137 { 4, ISOM_LANGUAGE_CODE_DUTCH_M
},
2138 { 5, ISOM_LANGUAGE_CODE_SWEDISH
},
2139 { 6, ISOM_LANGUAGE_CODE_SPANISH
},
2140 { 7, ISOM_LANGUAGE_CODE_DANISH
},
2141 { 8, ISOM_LANGUAGE_CODE_PORTUGUESE
},
2142 { 9, ISOM_LANGUAGE_CODE_NORWEGIAN
},
2143 { 10, ISOM_LANGUAGE_CODE_HEBREW
},
2144 { 11, ISOM_LANGUAGE_CODE_JAPANESE
},
2145 { 12, ISOM_LANGUAGE_CODE_ARABIC
},
2146 { 13, ISOM_LANGUAGE_CODE_FINNISH
},
2147 { 14, ISOM_LANGUAGE_CODE_GREEK
},
2148 { 15, ISOM_LANGUAGE_CODE_ICELANDIC
},
2149 { 16, ISOM_LANGUAGE_CODE_MALTESE
},
2150 { 17, ISOM_LANGUAGE_CODE_TURKISH
},
2151 { 18, ISOM_LANGUAGE_CODE_CROATIAN
},
2152 { 19, ISOM_LANGUAGE_CODE_CHINESE
},
2153 { 20, ISOM_LANGUAGE_CODE_URDU
},
2154 { 21, ISOM_LANGUAGE_CODE_HINDI
},
2155 { 22, ISOM_LANGUAGE_CODE_THAI
},
2156 { 23, ISOM_LANGUAGE_CODE_KOREAN
},
2157 { 24, ISOM_LANGUAGE_CODE_LITHUANIAN
},
2158 { 25, ISOM_LANGUAGE_CODE_POLISH
},
2159 { 26, ISOM_LANGUAGE_CODE_HUNGARIAN
},
2160 { 27, ISOM_LANGUAGE_CODE_ESTONIAN
},
2161 { 28, ISOM_LANGUAGE_CODE_LATVIAN
},
2162 { 29, ISOM_LANGUAGE_CODE_SAMI
},
2163 { 30, ISOM_LANGUAGE_CODE_FAROESE
},
2164 { 32, ISOM_LANGUAGE_CODE_RUSSIAN
},
2165 { 33, ISOM_LANGUAGE_CODE_CHINESE
},
2166 { 34, ISOM_LANGUAGE_CODE_DUTCH
},
2167 { 35, ISOM_LANGUAGE_CODE_IRISH
},
2168 { 36, ISOM_LANGUAGE_CODE_ALBANIAN
},
2169 { 37, ISOM_LANGUAGE_CODE_ROMANIAN
},
2170 { 38, ISOM_LANGUAGE_CODE_CZECH
},
2171 { 39, ISOM_LANGUAGE_CODE_SLOVAK
},
2172 { 40, ISOM_LANGUAGE_CODE_SLOVENIA
},
2173 { 41, ISOM_LANGUAGE_CODE_YIDDISH
},
2174 { 42, ISOM_LANGUAGE_CODE_SERBIAN
},
2175 { 43, ISOM_LANGUAGE_CODE_MACEDONIAN
},
2176 { 44, ISOM_LANGUAGE_CODE_BULGARIAN
},
2177 { 45, ISOM_LANGUAGE_CODE_UKRAINIAN
},
2178 { 46, ISOM_LANGUAGE_CODE_BELARUSIAN
},
2179 { 47, ISOM_LANGUAGE_CODE_UZBEK
},
2180 { 48, ISOM_LANGUAGE_CODE_KAZAKH
},
2181 { 49, ISOM_LANGUAGE_CODE_AZERBAIJANI
},
2182 { 51, ISOM_LANGUAGE_CODE_ARMENIAN
},
2183 { 52, ISOM_LANGUAGE_CODE_GEORGIAN
},
2184 { 53, ISOM_LANGUAGE_CODE_MOLDAVIAN
},
2185 { 54, ISOM_LANGUAGE_CODE_KIRGHIZ
},
2186 { 55, ISOM_LANGUAGE_CODE_TAJIK
},
2187 { 56, ISOM_LANGUAGE_CODE_TURKMEN
},
2188 { 57, ISOM_LANGUAGE_CODE_MONGOLIAN
},
2189 { 59, ISOM_LANGUAGE_CODE_PASHTO
},
2190 { 60, ISOM_LANGUAGE_CODE_KURDISH
},
2191 { 61, ISOM_LANGUAGE_CODE_KASHMIRI
},
2192 { 62, ISOM_LANGUAGE_CODE_SINDHI
},
2193 { 63, ISOM_LANGUAGE_CODE_TIBETAN
},
2194 { 64, ISOM_LANGUAGE_CODE_NEPALI
},
2195 { 65, ISOM_LANGUAGE_CODE_SANSKRIT
},
2196 { 66, ISOM_LANGUAGE_CODE_MARATHI
},
2197 { 67, ISOM_LANGUAGE_CODE_BENGALI
},
2198 { 68, ISOM_LANGUAGE_CODE_ASSAMESE
},
2199 { 69, ISOM_LANGUAGE_CODE_GUJARATI
},
2200 { 70, ISOM_LANGUAGE_CODE_PUNJABI
},
2201 { 71, ISOM_LANGUAGE_CODE_ORIYA
},
2202 { 72, ISOM_LANGUAGE_CODE_MALAYALAM
},
2203 { 73, ISOM_LANGUAGE_CODE_KANNADA
},
2204 { 74, ISOM_LANGUAGE_CODE_TAMIL
},
2205 { 75, ISOM_LANGUAGE_CODE_TELUGU
},
2206 { 76, ISOM_LANGUAGE_CODE_SINHALESE
},
2207 { 77, ISOM_LANGUAGE_CODE_BURMESE
},
2208 { 78, ISOM_LANGUAGE_CODE_KHMER
},
2209 { 79, ISOM_LANGUAGE_CODE_LAO
},
2210 { 80, ISOM_LANGUAGE_CODE_VIETNAMESE
},
2211 { 81, ISOM_LANGUAGE_CODE_INDONESIAN
},
2212 { 82, ISOM_LANGUAGE_CODE_TAGALOG
},
2213 { 83, ISOM_LANGUAGE_CODE_MALAY_ROMAN
},
2214 { 84, ISOM_LANGUAGE_CODE_MAYAY_ARABIC
},
2215 { 85, ISOM_LANGUAGE_CODE_AMHARIC
},
2216 { 87, ISOM_LANGUAGE_CODE_OROMO
},
2217 { 88, ISOM_LANGUAGE_CODE_SOMALI
},
2218 { 89, ISOM_LANGUAGE_CODE_SWAHILI
},
2219 { 90, ISOM_LANGUAGE_CODE_KINYARWANDA
},
2220 { 91, ISOM_LANGUAGE_CODE_RUNDI
},
2221 { 92, ISOM_LANGUAGE_CODE_CHEWA
},
2222 { 93, ISOM_LANGUAGE_CODE_MALAGASY
},
2223 { 94, ISOM_LANGUAGE_CODE_ESPERANTO
},
2224 { 128, ISOM_LANGUAGE_CODE_WELSH
},
2225 { 129, ISOM_LANGUAGE_CODE_BASQUE
},
2226 { 130, ISOM_LANGUAGE_CODE_CATALAN
},
2227 { 131, ISOM_LANGUAGE_CODE_LATIN
},
2228 { 132, ISOM_LANGUAGE_CODE_QUECHUA
},
2229 { 133, ISOM_LANGUAGE_CODE_GUARANI
},
2230 { 134, ISOM_LANGUAGE_CODE_AYMARA
},
2231 { 135, ISOM_LANGUAGE_CODE_TATAR
},
2232 { 136, ISOM_LANGUAGE_CODE_UIGHUR
},
2233 { 137, ISOM_LANGUAGE_CODE_DZONGKHA
},
2234 { 138, ISOM_LANGUAGE_CODE_JAVANESE
},
2238 /* Color parameters */
2239 enum isom_color_patameter_type
2241 ISOM_COLOR_PARAMETER_TYPE_NCLX
= LSMASH_4CC( 'n', 'c', 'l', 'x' ), /* on-screen colours */
2242 ISOM_COLOR_PARAMETER_TYPE_RICC
= LSMASH_4CC( 'r', 'I', 'C', 'C' ), /* restricted ICC profile */
2243 ISOM_COLOR_PARAMETER_TYPE_PROF
= LSMASH_4CC( 'p', 'r', 'o', 'f' ), /* unrestricted ICC profile */
2245 QT_COLOR_PARAMETER_TYPE_NCLC
= LSMASH_4CC( 'n', 'c', 'l', 'c' ), /* NonConstant Luminance Coding */
2246 QT_COLOR_PARAMETER_TYPE_PROF
= LSMASH_4CC( 'p', 'r', 'o', 'f' ), /* ICC profile */
2249 /* Sample grouping types */
2252 ISOM_GROUP_TYPE_3GAG
= LSMASH_4CC( '3', 'g', 'a', 'g' ), /* Text track3GPP PSS Annex G video buffer parameters */
2253 ISOM_GROUP_TYPE_ALST
= LSMASH_4CC( 'a', 'l', 's', 't' ), /* Alternative startup sequence */
2254 ISOM_GROUP_TYPE_AVCB
= LSMASH_4CC( 'a', 'v', 'c', 'b' ), /* AVC HRD parameters */
2255 ISOM_GROUP_TYPE_AVLL
= LSMASH_4CC( 'a', 'v', 'l', 'l' ), /* AVC Layer */
2256 ISOM_GROUP_TYPE_AVSS
= LSMASH_4CC( 'a', 'v', 's', 's' ), /* AVC Sub Sequence */
2257 ISOM_GROUP_TYPE_DTRT
= LSMASH_4CC( 'd', 't', 'r', 't' ), /* Decode re-timing */
2258 ISOM_GROUP_TYPE_MVIF
= LSMASH_4CC( 'm', 'v', 'i', 'f' ), /* MVC Scalability Information */
2259 ISOM_GROUP_TYPE_PROL
= LSMASH_4CC( 'p', 'r', 'o', 'l' ), /* Pre-roll */
2260 ISOM_GROUP_TYPE_RAP
= LSMASH_4CC( 'r', 'a', 'p', ' ' ), /* Random Access Point */
2261 ISOM_GROUP_TYPE_RASH
= LSMASH_4CC( 'r', 'a', 's', 'h' ), /* Rate Share */
2262 ISOM_GROUP_TYPE_ROLL
= LSMASH_4CC( 'r', 'o', 'l', 'l' ), /* Pre-roll/Post-roll */
2263 ISOM_GROUP_TYPE_SCIF
= LSMASH_4CC( 's', 'c', 'i', 'f' ), /* SVC Scalability Information */
2264 ISOM_GROUP_TYPE_SCNM
= LSMASH_4CC( 's', 'c', 'n', 'm' ), /* AVC/SVC/MVC map groups */
2265 ISOM_GROUP_TYPE_VIPR
= LSMASH_4CC( 'v', 'i', 'p', 'r' ), /* View priority */
2266 } isom_grouping_type
;
2268 /* wrapper to avoid boring cast */
2269 #define isom_init_box_common( box, parent, box_type, precedence, destructor ) \
2270 isom_init_box_common_orig( box, parent, box_type, precedence, (isom_extension_destructor_t)(destructor) )
2272 void isom_init_box_common_orig
2276 lsmash_box_type_t box_type
,
2277 uint64_t precedence
,
2278 isom_extension_destructor_t destructor
2281 int isom_is_fullbox( void *box
);
2282 int isom_is_lpcm_audio( void *box
);
2283 int isom_is_qt_audio( lsmash_codec_type_t type
);
2284 int isom_is_uncompressed_ycbcr( lsmash_codec_type_t type
);
2285 int isom_is_waveform_audio( lsmash_box_type_t type
);
2287 size_t isom_skip_box_common
2292 uint8_t *isom_get_child_box_position
2294 uint8_t *parent_data
,
2295 uint32_t parent_size
,
2296 lsmash_box_type_t child_type
,
2297 uint32_t *child_size
2300 void isom_bs_put_basebox_common( lsmash_bs_t
*bs
, isom_box_t
*box
);
2301 void isom_bs_put_fullbox_common( lsmash_bs_t
*bs
, isom_box_t
*box
);
2302 void isom_bs_put_box_common( lsmash_bs_t
*bs
, void *box
);
2304 #define isom_is_printable_char( c ) ((c) >= 32 && (c) < 128)
2305 #define isom_is_printable_4cc( fourcc ) \
2306 (isom_is_printable_char( ((fourcc) >> 24) & 0xff ) \
2307 && isom_is_printable_char( ((fourcc) >> 16) & 0xff ) \
2308 && isom_is_printable_char( ((fourcc) >> 8) & 0xff ) \
2309 && isom_is_printable_char( (fourcc) & 0xff ))
2311 #define isom_4cc2str( fourcc ) (const char [5]){ (fourcc) >> 24, (fourcc) >> 16, (fourcc) >> 8, (fourcc), 0 }
2313 int isom_check_initializer_present( lsmash_root_t
*root
);
2315 isom_trak_t
*isom_get_trak( lsmash_file_t
*file
, uint32_t track_ID
);
2316 isom_trex_t
*isom_get_trex( isom_mvex_t
*mvex
, uint32_t track_ID
);
2317 isom_traf_t
*isom_get_traf( isom_moof_t
*moof
, uint32_t track_ID
);
2318 isom_tfra_t
*isom_get_tfra( isom_mfra_t
*mfra
, uint32_t track_ID
);
2319 isom_sgpd_t
*isom_get_sample_group_description( isom_stbl_t
*stbl
, uint32_t grouping_type
);
2320 isom_sbgp_t
*isom_get_sample_to_group( isom_stbl_t
*stbl
, uint32_t grouping_type
);
2321 isom_sgpd_t
*isom_get_roll_recovery_sample_group_description( lsmash_entry_list_t
*list
);
2322 isom_sbgp_t
*isom_get_roll_recovery_sample_to_group( lsmash_entry_list_t
*list
);
2323 isom_sgpd_t
*isom_get_fragment_sample_group_description( isom_traf_t
*traf
, uint32_t grouping_type
);
2324 isom_sbgp_t
*isom_get_fragment_sample_to_group( isom_traf_t
*traf
, uint32_t grouping_type
);
2326 isom_trak_t
*isom_track_create( lsmash_file_t
*file
, lsmash_media_type media_type
);
2327 isom_moov_t
*isom_movie_create( lsmash_file_t
*file
);
2329 int isom_setup_handler_reference( isom_hdlr_t
*hdlr
, uint32_t media_type
);
2330 int isom_setup_iods( isom_moov_t
*moov
);
2332 uint32_t isom_get_sample_count
2337 isom_sample_pool_t
*isom_create_sample_pool
2342 int isom_update_sample_tables
2345 lsmash_sample_t
*sample
,
2346 uint32_t *samples_per_packet
,
2347 isom_sample_entry_t
*sample_entry
2350 int isom_pool_sample
2352 isom_sample_pool_t
*pool
,
2353 lsmash_sample_t
*sample
,
2354 uint32_t samples_per_packet
2357 int isom_append_sample_by_type
2360 lsmash_sample_t
*sample
,
2361 isom_sample_entry_t
*sample_entry
,
2362 int (*func_append_sample
)( void *, lsmash_sample_t
*, isom_sample_entry_t
* )
2365 int isom_calculate_bitrate_description
2369 uint32_t *bufferSizeDB
,
2370 uint32_t *maxBitrate
,
2371 uint32_t *avgBitrate
,
2372 uint32_t sample_description_index
2375 int isom_is_variable_size
2380 uint32_t isom_get_first_sample_size
2386 void isom_update_cache_timestamp
2388 isom_cache_t
*cache
,
2392 uint32_t sample_duration
,
2393 int non_output_sample
2396 /* Make CTS from DTS and sample_offset.
2397 * This function does NOT add the value of composition to decode timeline shift to the result. */
2398 static inline uint64_t isom_make_cts
2401 uint32_t sample_offset
,
2405 if( sample_offset
!= ISOM_NON_OUTPUT_SAMPLE_OFFSET
)
2406 return ctd_shift
? (dts
+ (int32_t)sample_offset
) : (dts
+ sample_offset
);
2408 return LSMASH_TIMESTAMP_UNDEFINED
;
2411 /* Make CTS from DTS and sample_offset.
2412 * This function adds the value of composition to decode timeline shift to the result. */
2413 static inline uint64_t isom_make_cts_adjust
2416 uint32_t sample_offset
,
2420 if( sample_offset
!= ISOM_NON_OUTPUT_SAMPLE_OFFSET
)
2421 return ctd_shift
? (dts
+ (int32_t)sample_offset
+ ctd_shift
) : (dts
+ sample_offset
);
2423 return LSMASH_TIMESTAMP_UNDEFINED
;
2426 /* Utilities for sample entry type decision
2427 * NOTE: This implementation does not work when 'mdia' and/or 'hdlr' is stored as binary string. */
2428 static inline int isom_check_media_hdlr_from_stsd( isom_stsd_t
*stsd
)
2430 return ((isom_stbl_t
*)stsd
->parent
2431 && (isom_minf_t
*)stsd
->parent
->parent
2432 && (isom_mdia_t
*)stsd
->parent
->parent
->parent
2433 && ((isom_mdia_t
*)stsd
->parent
->parent
->parent
)->hdlr
);
2435 static inline lsmash_media_type
isom_get_media_type_from_stsd( isom_stsd_t
*stsd
)
2437 assert( isom_check_media_hdlr_from_stsd( stsd
) );
2438 return ((isom_mdia_t
*)stsd
->parent
->parent
->parent
)->hdlr
->componentSubtype
;
2441 int isom_add_sample_grouping( isom_box_t
*parent
, isom_grouping_type grouping_type
);
2442 int isom_group_random_access( isom_box_t
*parent
, isom_cache_t
*cache
, lsmash_sample_t
*sample
);
2443 int isom_group_roll_recovery( isom_box_t
*parent
, isom_cache_t
*cache
, lsmash_sample_t
*sample
);
2445 int isom_update_tkhd_duration( isom_trak_t
*trak
);
2446 int isom_update_bitrate_description( isom_mdia_t
*mdia
);
2447 int isom_complement_data_reference( isom_minf_t
*minf
);
2448 int isom_check_large_offset_requirement( isom_moov_t
*moov
, uint64_t meta_size
);
2449 void isom_add_preceding_box_size( isom_moov_t
*moov
, uint64_t preceding_size
);
2450 int isom_establish_movie( lsmash_file_t
*file
);
2451 int isom_rap_grouping_established( isom_rap_group_t
*group
, int num_leading_samples_known
, isom_sgpd_t
*sgpd
, int is_fragment
);
2452 int isom_all_recovery_completed( isom_sbgp_t
*sbgp
, lsmash_entry_list_t
*pool
);
2454 lsmash_file_t
*isom_add_file_abstract( lsmash_root_t
*root
);
2455 isom_ftyp_t
*isom_add_ftyp( lsmash_file_t
*file
);
2456 isom_moov_t
*isom_add_moov( lsmash_file_t
*file
);
2457 isom_mvhd_t
*isom_add_mvhd( isom_moov_t
*moov
);
2458 isom_iods_t
*isom_add_iods( isom_moov_t
*moov
);
2459 isom_ctab_t
*isom_add_ctab( void *parent_box
);
2460 isom_trak_t
*isom_add_trak( isom_moov_t
*moov
);
2461 isom_tkhd_t
*isom_add_tkhd( isom_trak_t
*trak
);
2462 isom_tapt_t
*isom_add_tapt( isom_trak_t
*trak
);
2463 isom_clef_t
*isom_add_clef( isom_tapt_t
*tapt
);
2464 isom_prof_t
*isom_add_prof( isom_tapt_t
*tapt
);
2465 isom_enof_t
*isom_add_enof( isom_tapt_t
*tapt
);
2466 isom_edts_t
*isom_add_edts( isom_trak_t
*trak
);
2467 isom_elst_t
*isom_add_elst( isom_edts_t
*edts
);
2468 isom_tref_t
*isom_add_tref( isom_trak_t
*trak
);
2469 isom_tref_type_t
*isom_add_track_reference_type( isom_tref_t
*tref
, isom_track_reference_type type
);
2470 isom_mdia_t
*isom_add_mdia( isom_trak_t
*trak
);
2471 isom_mdhd_t
*isom_add_mdhd( isom_mdia_t
*mdia
);
2472 isom_hdlr_t
*isom_add_hdlr( void *parent_box
);
2473 isom_minf_t
*isom_add_minf( isom_mdia_t
*mdia
);
2474 isom_vmhd_t
*isom_add_vmhd( isom_minf_t
*minf
);
2475 isom_smhd_t
*isom_add_smhd( isom_minf_t
*minf
);
2476 isom_hmhd_t
*isom_add_hmhd( isom_minf_t
*minf
);
2477 isom_nmhd_t
*isom_add_nmhd( isom_minf_t
*minf
);
2478 isom_gmhd_t
*isom_add_gmhd( isom_minf_t
*minf
);
2479 isom_gmin_t
*isom_add_gmin( isom_gmhd_t
*gmhd
);
2480 isom_text_t
*isom_add_text( isom_gmhd_t
*gmhd
);
2481 isom_dinf_t
*isom_add_dinf( void *parent_box
);
2482 isom_dref_t
*isom_add_dref( isom_dinf_t
*dinf
);
2483 isom_dref_entry_t
*isom_add_dref_entry( isom_dref_t
*dref
, lsmash_box_type_t type
);
2484 isom_stbl_t
*isom_add_stbl( isom_minf_t
*minf
);
2485 isom_stsd_t
*isom_add_stsd( isom_stbl_t
*stbl
);
2486 isom_visual_entry_t
*isom_add_visual_description( isom_stsd_t
*stsd
, lsmash_codec_type_t sample_type
);
2487 isom_audio_entry_t
*isom_add_audio_description( isom_stsd_t
*stsd
, lsmash_codec_type_t sample_type
);
2488 isom_qt_text_entry_t
*isom_add_qt_text_description( isom_stsd_t
*stsd
);
2489 isom_tx3g_entry_t
*isom_add_tx3g_description( isom_stsd_t
*stsd
);
2490 isom_esds_t
*isom_add_esds( void *parent_box
);
2491 isom_glbl_t
*isom_add_glbl( void *parent_box
);
2492 isom_clap_t
*isom_add_clap( isom_visual_entry_t
*visual
);
2493 isom_pasp_t
*isom_add_pasp( isom_visual_entry_t
*visual
);
2494 isom_colr_t
*isom_add_colr( isom_visual_entry_t
*visual
);
2495 isom_gama_t
*isom_add_gama( isom_visual_entry_t
*visual
);
2496 isom_fiel_t
*isom_add_fiel( isom_visual_entry_t
*visual
);
2497 isom_cspc_t
*isom_add_cspc( isom_visual_entry_t
*visual
);
2498 isom_sgbt_t
*isom_add_sgbt( isom_visual_entry_t
*visual
);
2499 isom_stsl_t
*isom_add_stsl( isom_visual_entry_t
*visual
);
2500 isom_btrt_t
*isom_add_btrt( isom_visual_entry_t
*visual
);
2501 isom_wave_t
*isom_add_wave( isom_audio_entry_t
*audio
);
2502 isom_frma_t
*isom_add_frma( isom_wave_t
*wave
);
2503 isom_enda_t
*isom_add_enda( isom_wave_t
*wave
);
2504 isom_mp4a_t
*isom_add_mp4a( isom_wave_t
*wave
);
2505 isom_terminator_t
*isom_add_terminator( isom_wave_t
*wave
);
2506 isom_chan_t
*isom_add_chan( isom_audio_entry_t
*audio
);
2507 isom_srat_t
*isom_add_srat( isom_audio_entry_t
*audio
);
2508 isom_ftab_t
*isom_add_ftab( isom_tx3g_entry_t
*tx3g
);
2509 isom_stts_t
*isom_add_stts( isom_stbl_t
*stbl
);
2510 isom_ctts_t
*isom_add_ctts( isom_stbl_t
*stbl
);
2511 isom_cslg_t
*isom_add_cslg( isom_stbl_t
*stbl
);
2512 isom_stsc_t
*isom_add_stsc( isom_stbl_t
*stbl
);
2513 isom_stsz_t
*isom_add_stsz( isom_stbl_t
*stbl
);
2514 isom_stz2_t
*isom_add_stz2( isom_stbl_t
*stbl
);
2515 isom_stss_t
*isom_add_stss( isom_stbl_t
*stbl
);
2516 isom_stps_t
*isom_add_stps( isom_stbl_t
*stbl
);
2517 isom_sdtp_t
*isom_add_sdtp( isom_box_t
*parent
);
2518 isom_sgpd_t
*isom_add_sgpd( void *parent_box
);
2519 isom_sbgp_t
*isom_add_sbgp( void *parent_box
);
2520 isom_stco_t
*isom_add_stco( isom_stbl_t
*stbl
);
2521 isom_stco_t
*isom_add_co64( isom_stbl_t
*stbl
);
2522 isom_udta_t
*isom_add_udta( void *parent_box
);
2523 isom_cprt_t
*isom_add_cprt( isom_udta_t
*udta
);
2524 isom_WLOC_t
*isom_add_WLOC( isom_udta_t
*udta
);
2525 isom_LOOP_t
*isom_add_LOOP( isom_udta_t
*udta
);
2526 isom_SelO_t
*isom_add_SelO( isom_udta_t
*udta
);
2527 isom_AllF_t
*isom_add_AllF( isom_udta_t
*udta
);
2528 isom_chpl_t
*isom_add_chpl( isom_udta_t
*udta
);
2529 isom_meta_t
*isom_add_meta( void *parent_box
);
2530 isom_keys_t
*isom_add_keys( isom_meta_t
*meta
);
2531 isom_ilst_t
*isom_add_ilst( isom_meta_t
*meta
);
2532 isom_metaitem_t
*isom_add_metaitem( isom_ilst_t
*ilst
, lsmash_itunes_metadata_item item
);
2533 isom_mean_t
*isom_add_mean( isom_metaitem_t
*metaitem
);
2534 isom_name_t
*isom_add_name( isom_metaitem_t
*metaitem
);
2535 isom_data_t
*isom_add_data( isom_metaitem_t
*metaitem
);
2536 isom_mvex_t
*isom_add_mvex( isom_moov_t
*moov
);
2537 isom_mehd_t
*isom_add_mehd( isom_mvex_t
*mvex
);
2538 isom_trex_t
*isom_add_trex( isom_mvex_t
*mvex
);
2539 isom_moof_t
*isom_add_moof( lsmash_file_t
*file
);
2540 isom_mfhd_t
*isom_add_mfhd( isom_moof_t
*moof
);
2541 isom_traf_t
*isom_add_traf( isom_moof_t
*moof
);
2542 isom_tfhd_t
*isom_add_tfhd( isom_traf_t
*traf
);
2543 isom_tfdt_t
*isom_add_tfdt( isom_traf_t
*traf
);
2544 isom_trun_t
*isom_add_trun( isom_traf_t
*traf
);
2545 isom_mfra_t
*isom_add_mfra( lsmash_file_t
*file
);
2546 isom_tfra_t
*isom_add_tfra( isom_mfra_t
*mfra
);
2547 isom_mfro_t
*isom_add_mfro( isom_mfra_t
*mfra
);
2548 isom_mdat_t
*isom_add_mdat( lsmash_file_t
*file
);
2549 isom_free_t
*isom_add_free( void *parent_box
);
2550 isom_styp_t
*isom_add_styp( lsmash_file_t
*file
);
2551 isom_sidx_t
*isom_add_sidx( lsmash_file_t
*file
);
2553 void isom_remove_sample_description( isom_sample_entry_t
*sample
);
2554 void isom_remove_unknown_box( isom_unknown_box_t
*unknown_box
);
2555 void isom_remove_sample_pool( isom_sample_pool_t
*pool
);
2557 uint64_t isom_update_box_size( void *box
);
2559 int isom_add_extension_binary( void *parent_box
, lsmash_box_type_t box_type
, uint64_t precedence
, uint8_t *box_data
, uint32_t box_size
);
2560 void isom_remove_all_extension_boxes( lsmash_entry_list_t
*extensions
);
2561 isom_box_t
*isom_get_extension_box( lsmash_entry_list_t
*extensions
, lsmash_box_type_t box_type
);
2562 void *isom_get_extension_box_format( lsmash_entry_list_t
*extensions
, lsmash_box_type_t box_type
);
2563 void isom_remove_box_by_itself( void *opaque_box
);