Files
wuffs/std/brotli/decode_dictionary.wuffs
Claude b9be8feaee std/brotli: large-window mode, custom dictionaries and a fuzzer
Completes the decoder's feature set relative to libbrotlidec v1.2.1:

- QUIRK_LARGE_WINDOW mirrors BROTLI_DECODER_PARAM_LARGE_WINDOW: the
  large-window WBITS escape, window bits up to 30, the 544-symbol distance
  alphabet and 64-bit distance arithmetic, with workbuf_len growing to
  (1 << 30) + 542 when the quirk is set.
- decoder.add_dictionary! mirrors BrotliDecoderAttachDictionary for raw
  (LZ77 prefix) and serialized shared dictionaries: compound-dictionary
  distance mapping, the shared-dictionary parser (custom word lists,
  transform lists including the SHIFT transforms, context-dependent
  dictionary selection, prefix dictionaries) and all of its validation.
  Wuffs structs cannot hold slices, so the dictionary bytes are copied
  into the front of the caller's workbuf; the layout is documented in
  the README. Serialized dictionaries are accepted as in a
  BROTLI_EXPERIMENTAL build of libbrotli.
- fuzz/c/std/brotli_fuzzer.c, exercising the quirk, dictionaries and
  random I/O limits.

Tests: new golden vectors for large windows (including a 17 MiB
far-distance stream generated in the test), raw and serialized
dictionaries, nine more malformed inputs, and mimic comparisons that
attach the same dictionaries to libbrotlidec. Differential runs over
2.7 million mutated large-window and dictionary streams found no
divergence from libbrotlidec.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011NoosQNe7DKWnqDCBeqw1p
2026-10-26 23:45:06 +00:00

956 lines
33 KiB
Plaintext

// Copyright 2026 The Wuffs Authors.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
//
// SPDX-License-Identifier: Apache-2.0 OR MIT
// --------
// add_dictionary attaches a dictionary, like BrotliDecoderAttachDictionary in
// decode.c. It must be called before decoding starts (before the first
// transform_io call that consumes any input).
//
// args.dict_type is DICTIONARY_TYPE_RAW (a raw LZ77 prefix dictionary) or
// DICTIONARY_TYPE_SERIALIZED (a serialized shared dictionary).
//
// Wuffs structs cannot hold pointers, so the dictionary's bytes are copied
// into the workbuf: they are appended to the dictionaries added so far, which
// live at the start of the workbuf. args.workbuf must therefore be at least
// as long as the total length of all dictionaries added so far, including
// this one, and every later add_dictionary and transform_io call must be
// passed the same workbuf (or at least one whose prefix holds the same
// bytes). After the last add_dictionary call, workbuf_len gives the workbuf
// length that transform_io needs.
//
// On failure, the decoder's state is unchanged. The C code can leave its
// state partially updated when BrotliDecoderAttachDictionary fails.
pub func decoder.add_dictionary!(dict_type: base.u32, dict: roslice base.u8, workbuf: slice base.u8) base.status {
var status : base.status
var n : base.u64
var lo : base.u64
var hi : base.u64
var i : base.u32
if this.started {
return base."#bad call sequence"
}
n = args.dict.length()
if args.dict_type == DICTIONARY_TYPE_RAW {
// Mirrors the BROTLI_SHARED_DICTIONARY_RAW case of
// BrotliSharedDictionaryAttach in shared_dictionary.c and
// AttachCompoundDictionary in decode.c.
if this.num_chunks >= 15 {
return "#too many compound dictionaries"
}
} else if args.dict_type == DICTIONARY_TYPE_SERIALIZED {
// Mirrors DecodeSharedDictionary in shared_dictionary.c.
status = this.parse_shared_dictionary!(dict: args.dict, base_offset: this.dict_total)
if not status.is_ok() {
return status
}
} else {
return base."#bad argument"
}
// Copy the dictionary bytes into the workbuf.
if n > DICT_TOTAL_MAX {
return "#too much dictionary data"
}
lo = this.dict_total
hi = lo + n
if hi > DICT_TOTAL_MAX {
return "#too much dictionary data"
} else if hi > args.workbuf.length() {
return base."#bad workbuf length"
}
if lo > hi {
return "#too much dictionary data"
}
args.workbuf[lo .. hi].copy_from_slice!(s: args.dict)
// Commit.
if args.dict_type == DICTIONARY_TYPE_RAW {
this.add_chunk!(start: lo, size: n)
} else {
if this.sd_prefix_size > 0 {
this.add_chunk!(start: lo ~sat+ this.sd_prefix_pos, size: this.sd_prefix_size)
}
// Mirrors the end of ParseDictionary in shared_dictionary.c. If the
// serialized dictionary has no custom word lists or transform lists,
// the static dictionary is reset to the built-in one, even if an
// earlier serialized dictionary had custom lists.
this.sd_num_word_lists = this.stage_num_word_lists
this.sd_num_transform_lists = this.stage_num_transform_lists
if (this.stage_num_word_lists > 0) or (this.stage_num_transform_lists > 0) {
this.sd_context_based = this.stage_context_based
this.sd_num_dictionaries = this.stage_num_dictionaries
i = 0
while i < 64 {
this.sd_words[i] = this.stage_words[i].min(no_more_than: 64)
this.sd_transforms[i] = this.stage_transforms[i].min(no_more_than: 64)
this.sd_context_map[i] = this.stage_context_map[i] & 0x3F
i += 1
}
} else {
this.sd_context_based = false
this.sd_num_dictionaries = 1
this.sd_words[0] = 0
this.sd_transforms[0] = 0
}
}
if hi <= DICT_TOTAL_MAX {
this.dict_total = hi
}
return ok
}
// add_chunk adds a chunk to the compound dictionary. Mirrors
// AttachCompoundDictionary in decode.c.
pri func decoder.add_chunk!(start: base.u64, size: base.u64) {
var k : base.u32[..= 15]
k = this.num_chunks
if k >= 15 {
return nothing
}
this.chunk_starts[k] = (args.start & 0xFFFF_FFFF) as base.u32
this.chunk_offsets[k + 1] = this.chunk_offsets[k] ~mod+ ((args.size & 0xFFFF_FFFF) as base.u32)
this.num_chunks = k + 1
}
// parse_shared_dictionary parses and validates a serialized shared
// dictionary. Mirrors DecodeSharedDictionary, DryParseDictionary and
// ParseDictionary in shared_dictionary.c.
//
// It does not change the decoder's sd_etc fields, only the stage_etc fields
// (and the wl_etc and tl_etc fields, but only when there are no custom word
// lists or transform lists in use). The caller commits them.
//
// args.base_offset is where the serialized dictionary's bytes will be copied
// to, within the workbuf.
pri func decoder.parse_shared_dictionary!(dict: roslice base.u8, base_offset: base.u64) base.status {
var pos : base.u64
var chunk_size : base.u64
var prefix_pos : base.u64
var num_prefix : base.u32[..= 1]
var nwl : base.u32[..= 0xFF]
var ntl : base.u32[..= 0xFF]
var ndict : base.u32[..= 0xFF]
var is_custom : base.bool
var has_custom : base.bool
var i : base.u32
var v : base.u32[..= 0xFF]
var v2 : base.u32[..= 0xFF]
var status : base.status
// Check the magic header bytes.
if args.dict.length() < 2 {
return "#bad shared dictionary"
} else if (args.dict[0] <> 0x91) or (args.dict[1] <> 0x00) {
return "#bad shared dictionary"
}
// DryParseDictionary.
pos = 2
// LZ77_DICTIONARY_LENGTH. Mirrors ReadVarint32.
chunk_size = this.read_varint32!(dict: args.dict, pos: pos)
if chunk_size >= 0x1_0000_0000 {
return "#bad shared dictionary"
}
pos = this.parse_pos
prefix_pos = pos
num_prefix = 0
if chunk_size <> 0 {
// "This limitation is not specified but the 32-bit Brotli decoder for
// now".
if chunk_size > 1073_741823 {
return "#bad shared dictionary"
}
num_prefix = 1
if (pos ~sat+ chunk_size) > args.dict.length() {
return "#bad shared dictionary"
}
pos ~sat+= chunk_size
}
// NUM_WORD_LISTS and NUM_TRANSFORM_LISTS.
if (pos ~sat+ 2) > args.dict.length() {
return "#bad shared dictionary"
}
is_custom = false
if pos < args.dict.length() {
if args.dict[pos] > 0 {
is_custom = true
}
}
if (pos ~sat+ 1) < args.dict.length() {
if args.dict[pos ~sat+ 1] > 0 {
is_custom = true
}
}
if (num_prefix + this.num_chunks) > 15 {
return "#too many compound dictionaries"
}
// "Cannot combine different static dictionaries, only prefix
// dictionaries".
has_custom = (this.sd_num_word_lists > 0) or (this.sd_num_transform_lists > 0)
if has_custom and is_custom {
return "#unsupported multiple custom static dictionaries"
}
// ParseDictionary. The LZ77_DICTIONARY_LENGTH bytes were checked above.
// NUM_WORD_LISTS.
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
nwl = args.dict[pos] as base.u32
pos ~sat+= 1
if nwl > 64 {
return "#bad shared dictionary"
}
i = 0
while i < nwl,
inv nwl <= 64,
{
assert i < 64 via "a < b: a < c; c <= b"(c: nwl)
status = this.parse_word_list!(dict: args.dict, pos: pos, base_offset: args.base_offset, list: i)
if not status.is_ok() {
return status
}
pos = this.parse_pos
i += 1
}
// NUM_TRANSFORM_LISTS.
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
ntl = args.dict[pos] as base.u32
pos ~sat+= 1
if ntl > 64 {
return "#bad shared dictionary"
}
i = 0
while i < ntl,
inv ntl <= 64,
{
assert i < 64 via "a < b: a < c; c <= b"(c: ntl)
status = this.parse_transforms_list!(dict: args.dict, pos: pos, base_offset: args.base_offset, list: i)
if not status.is_ok() {
return status
}
pos = this.parse_pos
i += 1
}
this.stage_num_word_lists = nwl.min(no_more_than: 64)
this.stage_num_transform_lists = ntl.min(no_more_than: 64)
this.stage_num_dictionaries = 1
this.stage_context_based = false
i = 0
while i < 64 {
this.stage_words[i] = 0
this.stage_transforms[i] = 0
this.stage_context_map[i] = 0
i += 1
}
if (nwl <> 0) or (ntl <> 0) {
// NUM_DICTIONARIES.
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
ndict = args.dict[pos] as base.u32
pos ~sat+= 1
if (ndict == 0) or (ndict > 64) {
return "#bad shared dictionary"
}
this.stage_num_dictionaries = ndict.min(no_more_than: 64)
i = 0
while i < ndict,
inv ndict <= 64,
{
assert i < 64 via "a < b: a < c; c <= b"(c: ndict)
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
v = args.dict[pos] as base.u32
pos ~sat+= 1
if v > nwl {
return "#bad shared dictionary"
}
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
v2 = args.dict[pos] as base.u32
pos ~sat+= 1
if v2 > ntl {
return "#bad shared dictionary"
}
// Index nwl (or ntl) means the built-in list, which this.sd_words
// (or this.sd_transforms) represents as 0.
if v == nwl {
this.stage_words[i] = 0
} else {
this.stage_words[i] = ((v & 0x3F) + 1) as base.u8
}
if v2 == ntl {
this.stage_transforms[i] = 0
} else {
this.stage_transforms[i] = ((v2 & 0x3F) + 1) as base.u8
}
i += 1
}
// CONTEXT_ENABLED. Mirrors ReadBool.
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
v = args.dict[pos] as base.u32
pos ~sat+= 1
if v > 1 {
return "#bad shared dictionary"
}
this.stage_context_based = v == 1
// CONTEXT_MAP.
if this.stage_context_based {
i = 0
while i < 64 {
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
v = args.dict[pos] as base.u32
pos ~sat+= 1
if v >= ndict {
return "#bad shared dictionary"
}
this.stage_context_map[i] = (v & 0x3F) as base.u8
i += 1
}
}
}
this.sd_prefix_pos = prefix_pos
this.sd_prefix_size = chunk_size
return ok
}
// read_varint32 reads a varint at args.dict[args.pos ..]. It returns a value
// of 0x1_0000_0000 or more on failure. On success, it returns the value and
// stores the new position in this.parse_pos. Mirrors ReadVarint32 in
// shared_dictionary.c.
pri func decoder.read_varint32!(dict: roslice base.u8, pos: base.u64) base.u64 {
var pos : base.u64
var num : base.u32[..= 4]
var b : base.u64
var result : base.u64
pos = args.pos
result = 0
num = 0
while true {
if pos >= args.dict.length() {
return 0x1_0000_0000
}
b = args.dict[pos] as base.u64
pos ~sat+= 1
if (num == 4) and (b > 15) {
return 0x1_0000_0000
}
result |= (b & 127) << (7 * num)
if b < 128 {
break
}
if num >= 4 {
return 0x1_0000_0000
}
num += 1
}
this.parse_pos = pos
return result & 0xFFFF_FFFF
}
// parse_word_list parses the args.list'th custom word list, at
// args.dict[args.pos ..]. On success, it stores the new position in
// this.parse_pos. Mirrors ParseWordList and BrotliSizeBitsToOffsets in
// shared_dictionary.c.
pri func decoder.parse_word_list!(dict: roslice base.u8, pos: base.u64, base_offset: base.u64, list: base.u32[..= 63]) base.status {
var pos : base.u64
var len : base.u32
var v : base.u8
var offset : base.u32
var wpos : base.u64
pos = args.pos
if (pos ~sat+ 28) > args.dict.length() {
return "#bad shared dictionary"
}
len = 0
while len < 32 {
v = 0
if len >= 4 {
if (pos ~sat+ ((len - 4) as base.u64)) < args.dict.length() {
v = args.dict[pos ~sat+ ((len - 4) as base.u64)]
}
// BROTLI_MAX_SIZE_BITS.
if v > 15 {
return "#bad shared dictionary"
}
}
this.wl_size_bits[args.list][len] = v
len += 1
}
pos ~sat+= 28
offset = 0
len = 0
while len < 32 {
this.wl_offsets[args.list][len] = offset
v = this.wl_size_bits[args.list][len]
if v <> 0 {
offset ~mod+= len << (v & 15)
}
len += 1
}
wpos = args.base_offset ~sat+ pos
this.wl_data[args.list] = (wpos & 0xFFFF_FFFF) as base.u32
pos ~sat+= offset as base.u64
if pos > args.dict.length() {
return "#bad shared dictionary"
}
this.parse_pos = pos
return ok
}
// parse_transforms_list parses the args.list'th custom transform list, at
// args.dict[args.pos ..]. On success, it stores the new position in
// this.parse_pos. Mirrors ParseTransformsList and ParsePrefixSuffixTable
// in shared_dictionary.c.
pri func decoder.parse_transforms_list!(dict: roslice base.u8, pos: base.u64, base_offset: base.u64, list: base.u32[..= 63]) base.status {
var pos : base.u64
var data_length : base.u64
var ps_start : base.u64
var offset : base.u64
var stringlet_len : base.u64
var count : base.u32[..= 256]
var nt : base.u32[..= 0xFF]
var t : base.u32
var tpos : base.u64
var j : base.u64
var prefix_id : base.u32[..= 0xFF]
var t_type : base.u32[..= 0xFF]
var suffix_id : base.u32[..= 0xFF]
var has_params : base.bool
var p0 : base.u32
var p1 : base.u32
pos = args.pos
if pos >= args.dict.length() {
return "#bad shared dictionary"
}
// ParsePrefixSuffixTable. PREFIX_SUFFIX_LENGTH.
if (pos ~sat+ 2) > args.dict.length() {
return "#bad shared dictionary"
}
data_length = (this.byte_at(s: args.dict, i: pos) as base.u64) |
((this.byte_at(s: args.dict, i: pos ~sat+ 1) as base.u64) << 8)
pos ~sat+= 2
// It must at least have space for the NUL terminator.
if data_length < 1 {
return "#bad shared dictionary"
}
ps_start = pos
if (pos ~sat+ data_length) >= args.dict.length() {
return "#bad shared dictionary"
}
offset = 0
count = 0
while true {
// STRING_LENGTH.
j = ps_start ~sat+ offset
stringlet_len = 0
if j < args.dict.length() {
stringlet_len = args.dict[j] as base.u64
}
if count >= 256 {
return "#bad shared dictionary"
}
this.tl_map[args.list][count] = (offset & 0xFFFF) as base.u16
count += 1
offset ~sat+= 1
if stringlet_len == 0 {
if offset == data_length {
break
}
return "#bad shared dictionary"
}
if count > 255 {
return "#bad shared dictionary"
}
offset ~sat+= stringlet_len
if offset >= data_length {
return "#bad shared dictionary"
}
}
pos ~sat+= data_length
this.tl_prefix_suffix[args.list] = ((args.base_offset ~sat+ ps_start) & 0xFFFF_FFFF) as base.u32
// NUM_TRANSFORMS. The "(pos + data_length) >= length" check above means
// that this is in bounds.
nt = 0
if pos < args.dict.length() {
nt = args.dict[pos] as base.u32
}
pos ~sat+= 1
this.tl_num_transforms[args.list] = nt
tpos = pos
this.tl_transforms[args.list] = ((args.base_offset ~sat+ tpos) & 0xFFFF_FFFF) as base.u32
pos ~sat+= (nt as base.u64) * 3
if pos > args.dict.length() {
return "#bad shared dictionary"
}
// Check for errors and read extra parameters.
has_params = false
t = 0
while t < nt {
j = tpos ~sat+ ((t as base.u64) * 3)
prefix_id = this.byte_at(s: args.dict, i: j)
t_type = this.byte_at(s: args.dict, i: j ~sat+ 1)
suffix_id = this.byte_at(s: args.dict, i: j ~sat+ 2)
if prefix_id >= count {
return "#bad shared dictionary"
} else if t_type >= 23 {
// BROTLI_NUM_TRANSFORM_TYPES.
return "#bad shared dictionary"
} else if suffix_id >= count {
return "#bad shared dictionary"
}
// BROTLI_TRANSFORM_SHIFT_FIRST or BROTLI_TRANSFORM_SHIFT_ALL.
if (t_type == 21) or (t_type == 22) {
has_params = true
}
t ~mod+= 1
}
this.tl_params[args.list] = 0
if has_params {
this.tl_params[args.list] = ((args.base_offset ~sat+ pos) & 0xFFFF_FFFF) as base.u32
j = pos
pos ~sat+= (nt as base.u64) * 2
if pos > args.dict.length() {
return "#bad shared dictionary"
}
t = 0
while t < nt {
t_type = this.byte_at(s: args.dict, i: tpos ~sat+ (((t as base.u64) * 3) + 1))
if (t_type <> 21) and (t_type <> 22) {
p0 = this.byte_at(s: args.dict, i: j ~sat+ ((t as base.u64) * 2))
p1 = this.byte_at(s: args.dict, i: j ~sat+ (((t as base.u64) * 2) + 1))
if (p0 <> 0) or (p1 <> 0) {
return "#bad shared dictionary"
}
}
t ~mod+= 1
}
}
this.parse_pos = pos
return ok
}
// --------
// copy_dictionary_word writes a transformed static dictionary word to
// this.transformed_word and returns its length. It returns 0xFFFF_FFFE for a
// BROTLI_DECODER_ERROR_FORMAT_DICTIONARY error and 0xFFFF_FFFF for a
// BROTLI_DECODER_ERROR_FORMAT_TRANSFORM error. args.address is the C code's
// (distance_code - max_distance - 1 - compound_dictionary_size) and args.ctx
// is the C code's BROTLI_CONTEXT(p1, p2, s->context_lookup).
//
// Mirrors the static dictionary part of ProcessCommandsInternal in decode.c,
// including its selection of a word list and transform list from the shared
// dictionary.
pri func decoder.copy_dictionary_word!(dictbuf: roslice base.u8, address: base.u32, len: base.u32[..= 31], ctx: base.u32[..= 63]) base.u32 {
var dict_id : base.u32[..= 63]
var wsel : base.u32[..= 64]
var tsel : base.u32[..= 64]
var shift : base.u32[..= 24]
var nt : base.u32[..= 255]
var address : base.u32
var transform_idx : base.u32
var word_idx : base.u32
var offset : base.u32
var dist_remaining : base.u32
var d2 : base.u32
var w2 : base.u32[..= 64]
var t2 : base.u32[..= 64]
var shift2 : base.u32[..= 24]
var num : base.u32
dict_id = 0
if this.sd_context_based {
dict_id = (this.sd_context_map[args.ctx] & 0x3F) as base.u32
}
wsel = this.sd_words[dict_id] as base.u32
tsel = this.sd_transforms[dict_id] as base.u32
shift = this.word_list_size_bits(wsel: wsel, len: args.len)
nt = this.transform_list_length(tsel: tsel)
address = args.address
transform_idx = address >> shift
// If the distance is out of bound, select a next static dictionary if
// there exist multiple.
if ((transform_idx >= nt) or (shift == 0)) and (this.sd_num_dictionaries > 1) {
dist_remaining = address ~mod- ((((1 as base.u32) << shift) & 0xFFFF_FFFE) ~mod* nt)
d2 = 0
while d2 < this.sd_num_dictionaries {
assert d2 < 64 via "a < b: a < c; c <= b"(c: this.sd_num_dictionaries)
w2 = this.sd_words[d2] as base.u32
shift2 = this.word_list_size_bits(wsel: w2, len: args.len)
if (d2 <> dict_id) and (shift2 <> 0) {
t2 = this.sd_transforms[d2] as base.u32
num = (((1 as base.u32) << shift2) & 0xFFFF_FFFE) ~mod* this.transform_list_length(tsel: t2)
if dist_remaining < num {
wsel = w2
tsel = t2
address = dist_remaining
shift = shift2
nt = this.transform_list_length(tsel: tsel)
transform_idx = address >> shift
break
}
dist_remaining -= num
}
d2 += 1
}
}
if shift == 0 {
return 0xFFFF_FFFE
} else if transform_idx >= nt {
return 0xFFFF_FFFF
}
word_idx = address & (((1 as base.u32) << shift) - 1)
offset = this.word_list_offset(wsel: wsel, len: args.len) ~mod+ (word_idx ~mod* args.len)
num = this.transform_dictionary_word!(dictbuf: args.dictbuf,
wsel: wsel,
tsel: tsel,
offset: offset,
len: args.len,
transform_idx: transform_idx.min(no_more_than: 254))
return num
}
// word_list_size_bits returns the C code's size_bits_by_length[args.len] for
// the word list selected by args.wsel: 0 for the built-in list or (1 + j) for
// the j'th custom list.
pri func decoder.word_list_size_bits(wsel: base.u32[..= 64], len: base.u32[..= 31]) base.u32[..= 24] {
if args.wsel == 0 {
return DICTIONARY_SIZE_BITS_BY_LENGTH[args.len]
}
return (this.wl_size_bits[(args.wsel - 1) & 63][args.len] & 15) as base.u32
}
// word_list_offset returns the C code's offsets_by_length[args.len] for the
// word list selected by args.wsel.
pri func decoder.word_list_offset(wsel: base.u32[..= 64], len: base.u32[..= 31]) base.u32 {
if args.wsel == 0 {
return DICTIONARY_OFFSETS_BY_LENGTH[args.len]
}
return this.wl_offsets[(args.wsel - 1) & 63][args.len]
}
// transform_list_length returns the C code's num_transforms for the
// transform list selected by args.tsel: 0 for the built-in list or (1 + j)
// for the j'th custom list.
pri func decoder.transform_list_length(tsel: base.u32[..= 64]) base.u32[..= 255] {
if args.tsel == 0 {
return NUM_TRANSFORMS
}
return this.tl_num_transforms[(args.tsel - 1) & 63].min(no_more_than: 255)
}
// transform_dictionary_word writes the transformed word to
// this.transformed_word and returns its length. Mirrors
// BrotliTransformDictionaryWord in transform.c.
pri func decoder.transform_dictionary_word!(dictbuf: roslice base.u8, wsel: base.u32[..= 64], tsel: base.u32[..= 64], offset: base.u32, len: base.u32[..= 31], transform_idx: base.u32[..= 254]) base.u32 {
var idx : base.u32
var t : base.u32[..= 120]
var k : base.u32[..= 63]
var tpos : base.u64
var prefix_id : base.u32[..= 0xFF]
var t_type : base.u32[..= 0xFF]
var suffix_id : base.u32[..= 0xFF]
var param : base.u32
var word_start : base.u32
var word_len : base.u32
var skip : base.u32[..= 9]
var i : base.u32
var j : base.u64
var remaining : base.u32
var step : base.u32
// Look up the transform's prefix_id, type and suffix_id.
k = 0
tpos = 0
if args.tsel == 0 {
t = args.transform_idx.min(no_more_than: 120)
prefix_id = TRANSFORM_PREFIX_ID[t] as base.u32
t_type = TRANSFORM_TYPE[t] as base.u32
suffix_id = TRANSFORM_SUFFIX_ID[t] as base.u32
} else {
k = (args.tsel - 1) & 63
tpos = (this.tl_transforms[k] as base.u64) + ((args.transform_idx as base.u64) * 3)
prefix_id = this.byte_at(s: args.dictbuf, i: tpos)
t_type = this.byte_at(s: args.dictbuf, i: tpos + 1)
suffix_id = this.byte_at(s: args.dictbuf, i: tpos + 2)
}
// The prefix.
idx = this.append_affix!(dictbuf: args.dictbuf, tsel: args.tsel, id: prefix_id, idx: 0)
// The word, possibly with its first or last few bytes omitted.
word_len = args.len
skip = 0
if t_type <= 9 {
// BROTLI_TRANSFORM_OMIT_LAST_N.
if t_type < args.len {
word_len = args.len ~mod- t_type
} else {
word_len = 0
}
} else if (12 <= t_type) and (t_type <= 20) {
// BROTLI_TRANSFORM_OMIT_FIRST_N.
skip = t_type - 11
if skip < args.len {
word_len = args.len ~mod- skip
} else {
word_len = 0
}
}
word_start = idx
i = 0
while i < word_len {
if idx >= 1024 {
break
}
if args.wsel == 0 {
j = ((args.offset ~mod+ skip) ~mod+ i) as base.u64
if j < 122784 {
this.transformed_word[idx] = DICTIONARY[j]
}
} else {
j = (this.wl_data[(args.wsel - 1) & 63] as base.u64) +
(((args.offset ~mod+ skip) ~mod+ i) as base.u64)
if j < args.dictbuf.length() {
this.transformed_word[idx] = args.dictbuf[j]
}
}
idx ~mod+= 1
i ~mod+= 1
}
// Upper-casing and shifting. The C code's ToUpperCase can modify bytes
// after the word's end, but those bytes are either overwritten by the
// suffix or are past the transformed word's length, so we don't bother.
if t_type == 10 {
// BROTLI_TRANSFORM_UPPERCASE_FIRST.
this.to_upper_case!(p: word_start, end: idx)
} else if t_type == 11 {
// BROTLI_TRANSFORM_UPPERCASE_ALL.
i = word_start
while i < idx {
step = this.to_upper_case!(p: i, end: idx)
i ~mod+= step
}
} else if (t_type == 21) or (t_type == 22) {
// BROTLI_TRANSFORM_SHIFT_FIRST or BROTLI_TRANSFORM_SHIFT_ALL. Only
// custom transforms have these types, and their parameters exist.
j = (this.tl_params[k] as base.u64) + ((args.transform_idx as base.u64) * 2)
param = this.byte_at(s: args.dictbuf, i: j) |
(this.byte_at(s: args.dictbuf, i: j + 1) << 8)
if t_type == 21 {
this.shift!(p: word_start, word_len: idx ~mod- word_start, param: param)
} else {
i = word_start
remaining = idx ~mod- word_start
while remaining > 0 {
step = this.shift!(p: i, word_len: remaining, param: param)
if step >= remaining {
break
}
i ~mod+= step
remaining ~mod-= step
}
}
}
// The suffix.
idx = this.append_affix!(dictbuf: args.dictbuf, tsel: args.tsel, id: suffix_id, idx: idx)
return idx
}
// append_affix appends the args.id'th prefix or suffix of the transform list
// selected by args.tsel to this.transformed_word, starting at args.idx. It
// returns the new length.
pri func decoder.append_affix!(dictbuf: roslice base.u8, tsel: base.u32[..= 64], id: base.u32[..= 0xFF], idx: base.u32) base.u32 {
var idx : base.u32
var affix : base.u32[..= 216]
var affix_len : base.u32
var i : base.u32
var j : base.u32
var k : base.u32[..= 63]
var pos : base.u64
idx = args.idx
if args.tsel == 0 {
affix = PREFIX_SUFFIX_MAP[args.id.min(no_more_than: 49)]
affix_len = PREFIX_SUFFIX[affix] as base.u32
i = 0
while i < affix_len {
j = (affix ~mod+ 1) ~mod+ i
if (j >= 217) or (idx >= 1024) {
break
}
this.transformed_word[idx] = PREFIX_SUFFIX[j]
idx ~mod+= 1
i ~mod+= 1
}
return idx
}
k = (args.tsel - 1) & 63
pos = (this.tl_prefix_suffix[k] as base.u64) + (this.tl_map[k][args.id] as base.u64)
affix_len = 0
if pos < args.dictbuf.length() {
affix_len = args.dictbuf[pos] as base.u32
}
i = 0
while i < affix_len {
pos ~mod+= 1
if (pos >= args.dictbuf.length()) or (idx >= 1024) {
break
}
this.transformed_word[idx] = args.dictbuf[pos]
idx ~mod+= 1
i ~mod+= 1
}
return idx
}
// shift applies a shift transform to the (UTF-8 encoded) character at
// this.transformed_word[args.p ..], which is args.word_len bytes long. It
// returns the step: the number of bytes in the character. Mirrors Shift in
// transform.c.
pri func decoder.shift!(p: base.u32, word_len: base.u32, param: base.u32) base.u32 {
var p : base.u32[..= 1019]
var scalar : base.u32
var c0 : base.u32
var c1 : base.u32
var c2 : base.u32
var c3 : base.u32
if args.p > 1019 {
return 1
}
p = args.p
// Limited sign extension: scalar < (1 << 24).
scalar = (args.param & 0x7FFF) ~mod+ (0x100_0000 ~mod- (args.param & 0x8000))
c0 = this.transformed_word[p] as base.u32
if c0 < 0x80 {
// 1-byte rune / 0sssssss / 7 bit scalar (ASCII).
scalar ~mod+= c0
this.transformed_word[p] = (scalar & 0x7F) as base.u8
return 1
} else if c0 < 0xC0 {
// Continuation / 10AAAAAA.
return 1
} else if c0 < 0xE0 {
// 2-byte rune / 110sssss AAssssss / 11 bit scalar.
if args.word_len < 2 {
return 1
}
c1 = this.transformed_word[p + 1] as base.u32
scalar ~mod+= (c1 & 0x3F) | ((c0 & 0x1F) << 6)
this.transformed_word[p + 0] = (0xC0 | ((scalar >> 6) & 0x1F)) as base.u8
this.transformed_word[p + 1] = ((c1 & 0xC0) | (scalar & 0x3F)) as base.u8
return 2
} else if c0 < 0xF0 {
// 3-byte rune / 1110ssss AAssssss BBssssss / 16 bit scalar.
if args.word_len < 3 {
return args.word_len
}
c1 = this.transformed_word[p + 1] as base.u32
c2 = this.transformed_word[p + 2] as base.u32
scalar ~mod+= (c2 & 0x3F) | ((c1 & 0x3F) << 6) | ((c0 & 0x0F) << 12)
this.transformed_word[p + 0] = (0xE0 | ((scalar >> 12) & 0x0F)) as base.u8
this.transformed_word[p + 1] = ((c1 & 0xC0) | ((scalar >> 6) & 0x3F)) as base.u8
this.transformed_word[p + 2] = ((c2 & 0xC0) | (scalar & 0x3F)) as base.u8
return 3
} else if c0 < 0xF8 {
// 4-byte rune / 11110sss AAssssss BBssssss CCssssss / 21 bit scalar.
if args.word_len < 4 {
return args.word_len
}
c1 = this.transformed_word[p + 1] as base.u32
c2 = this.transformed_word[p + 2] as base.u32
c3 = this.transformed_word[p + 3] as base.u32
scalar ~mod+= (c3 & 0x3F) | ((c2 & 0x3F) << 6) | ((c1 & 0x3F) << 12) | ((c0 & 0x07) << 18)
this.transformed_word[p + 0] = (0xF0 | ((scalar >> 18) & 0x07)) as base.u8
this.transformed_word[p + 1] = ((c1 & 0xC0) | ((scalar >> 12) & 0x3F)) as base.u8
this.transformed_word[p + 2] = ((c2 & 0xC0) | ((scalar >> 6) & 0x3F)) as base.u8
this.transformed_word[p + 3] = ((c3 & 0xC0) | (scalar & 0x3F)) as base.u8
return 4
}
return 1
}
// Mirrors ToUpperCase in transform.c, except that it does not modify bytes at
// or after args.end. It returns the step: the number of bytes in the
// (overly simplified model of a) UTF-8 encoded character.
pri func decoder.to_upper_case!(p: base.u32, end: base.u32) base.u32 {
var c : base.u8
if args.p >= 1024 {
return 1
}
c = this.transformed_word[args.p]
if c < 0xC0 {
if ('a' <= c) and (c <= 'z') {
this.transformed_word[args.p] = c ^ 32
}
return 1
}
// An overly simplified uppercasing model for UTF-8.
if c < 0xE0 {
if ((args.p + 1) < args.end) and ((args.p + 1) < 1024) {
this.transformed_word[args.p + 1] ^= 32
}
return 2
}
// An arbitrary transform for three byte characters.
if ((args.p + 2) < args.end) and ((args.p + 2) < 1024) {
this.transformed_word[args.p + 2] ^= 5
}
return 3
}
// byte_at returns args.s[args.i], or 0 if args.i is out of bounds.
pri func decoder.byte_at(s: roslice base.u8, i: base.u64) base.u32[..= 0xFF] {
if args.i < args.s.length() {
return args.s[args.i] as base.u32
}
return 0
}