wuffsfmt: double-indents hanging lines

This commit is contained in:
Nigel Tao committed 2023-04-09 15:22:25 +10:00
1 parent d910658bce
commit 9c03b8c71d
40 files changed
+2579 -2571

No files matched your search

+434 -434
View File
@@ -13,52 +13,52 @@
// limitations under the License.
pub struct decoder? implements base.token_decoder(
quirks : array[QUIRKS_COUNT] base.bool,
quirks : array[QUIRKS_COUNT] base.bool,
allow_leading_ars : base.bool,
allow_leading_ubom : base.bool,
allow_leading_ars : base.bool,
allow_leading_ubom : base.bool,
end_of_data : base.bool,
end_of_data : base.bool,
trailer_stop : base.u8,
trailer_stop : base.u8,
// comment_type is set as a side-effect of decode_comment?.
// - 0 means no comment.
// - 1 means a block comment.
// - 2 means a line comment.
comment_type : base.u8,
// comment_type is set as a side-effect of decode_comment?.
// - 0 means no comment.
// - 1 means a block comment.
// - 2 means a line comment.
comment_type : base.u8,
util : base.utility,
util : base.utility,
)(
// stack is conceptually an array of bits, implemented as an array of u32.
// The N'th bit being 0 or 1 means that we're in an array or object, where
// N is the recursion depth.
//
// Parsing JSON involves recursion: containers (arrays and objects) can
// hold other containers. As child elements are completed, the parser needs
// to remember 1 bit of state per recursion depth: whether the parent
// container was an array or an object. When continuing to parse the
// parent's elements, `, "key": value` is only valid for objects.
//
// Note that we explicitly track our own stack and depth. We do not use the
// call stack to hold this state and the decoder.decode_tokens function is
// not recursive per se.
//
// Wuffs code does not have the capability to dynamically allocate memory,
// so the maximum depth is hard-coded at compile time. In this case, the
// maximum is 1024 (stack is 1024 bits or 128 bytes), also known as
// DECODER_DEPTH_MAX_INCL.
//
// The [JSON spec](https://www.ietf.org/rfc/rfc8259.txt) clearly states,
// "an implementation may set limits on the maximum depth of nesting".
//
// In comparison, as of February 2020, the Chromium web browser's JSON
// parser's maximum recursion depth is 200:
// https://source.chromium.org/chromium/chromium/src/+/3dece34cde622faa0daac07156c25d92c9897d1e:base/json/json_common.h;l=18
//
// Other languages and libraries' maximum depths (determined empirically)
// are listed at https://github.com/lovasoa/bad_json_parsers#results
stack : array[1024 / 32] base.u32,
// stack is conceptually an array of bits, implemented as an array of u32.
// The N'th bit being 0 or 1 means that we're in an array or object, where
// N is the recursion depth.
//
// Parsing JSON involves recursion: containers (arrays and objects) can
// hold other containers. As child elements are completed, the parser needs
// to remember 1 bit of state per recursion depth: whether the parent
// container was an array or an object. When continuing to parse the
// parent's elements, `, "key": value` is only valid for objects.
//
// Note that we explicitly track our own stack and depth. We do not use the
// call stack to hold this state and the decoder.decode_tokens function is
// not recursive per se.
//
// Wuffs code does not have the capability to dynamically allocate memory,
// so the maximum depth is hard-coded at compile time. In this case, the
// maximum is 1024 (stack is 1024 bits or 128 bytes), also known as
// DECODER_DEPTH_MAX_INCL.
//
// The [JSON spec](https://www.ietf.org/rfc/rfc8259.txt) clearly states,
// "an implementation may set limits on the maximum depth of nesting".
//
// In comparison, as of February 2020, the Chromium web browser's JSON
// parser's maximum recursion depth is 200:
// https://source.chromium.org/chromium/chromium/src/+/3dece34cde622faa0daac07156c25d92c9897d1e:base/json/json_common.h;l=18
//
// Other languages and libraries' maximum depths (determined empirically)
// are listed at https://github.com/lovasoa/bad_json_parsers#results
stack : array[1024 / 32] base.u32,
)
pub func decoder.set_quirk_enabled!(quirk: base.u32, enabled: base.bool) {
@@ -126,14 +126,14 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if this.quirks[QUIRK_EXPECT_TRAILING_NEW_LINE_OR_EOF - QUIRKS_BASE] {
if this.quirks[QUIRK_ALLOW_COMMENT_BLOCK - QUIRKS_BASE] or
this.quirks[QUIRK_ALLOW_COMMENT_LINE - QUIRKS_BASE] or
this.quirks[QUIRK_ALLOW_TRAILING_FILLER - QUIRKS_BASE] {
this.quirks[QUIRK_ALLOW_COMMENT_LINE - QUIRKS_BASE] or
this.quirks[QUIRK_ALLOW_TRAILING_FILLER - QUIRKS_BASE] {
return "#bad quirk combination"
}
}
if this.quirks[QUIRK_ALLOW_LEADING_ASCII_RECORD_SEPARATOR - QUIRKS_BASE] or
this.quirks[QUIRK_ALLOW_LEADING_UNICODE_BYTE_ORDER_MARK - QUIRKS_BASE] {
this.quirks[QUIRK_ALLOW_LEADING_UNICODE_BYTE_ORDER_MARK - QUIRKS_BASE] {
this.decode_leading?(dst: args.dst, src: args.src)
}
@@ -151,16 +151,16 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
c = 0
class = 0
while.ws true,
inv args.dst.length() > 0,
post args.src.length() > 0,
inv args.dst.length() > 0,
post args.src.length() > 0,
{
if args.src.length() <= 0 {
if whitespace_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: 0,
continued: 0,
length: whitespace_length)
value_major: 0,
value_minor: 0,
continued: 0,
length: whitespace_length)
whitespace_length = 0
}
if args.src.is_closed() {
@@ -179,10 +179,10 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if whitespace_length >= 0xFFFE {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: 0,
continued: 0,
length: 0xFFFF)
value_major: 0,
value_minor: 0,
continued: 0,
length: 0xFFFF)
whitespace_length = 0
continue.outer
}
@@ -192,10 +192,10 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// Emit whitespace.
if whitespace_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: 0,
continued: 0,
length: whitespace_length)
value_major: 0,
value_minor: 0,
continued: 0,
length: whitespace_length)
whitespace_length = 0
if args.dst.length() <= 0 {
continue.outer
@@ -218,14 +218,14 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// -------- BEGIN parse strings.
// Emit the leading '"'.
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__DEFINITELY_ASCII |
base.TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP,
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__DEFINITELY_ASCII |
base.TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP,
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
while.string_loop_outer true {
@@ -236,18 +236,18 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
string_length = 0
while.string_loop_inner true,
pre args.dst.length() > 0,
pre args.dst.length() > 0,
{
if args.src.length() <= 0 {
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
}
if args.src.is_closed() {
@@ -260,26 +260,26 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// As an optimization, consume non-special ASCII 4 bytes at
// a time.
while args.src.length() > 4,
inv args.dst.length() > 0,
inv args.src.length() > 0,
inv args.dst.length() > 0,
inv args.src.length() > 0,
{
c4 = args.src.peek_u32le()
if 0x00 <> (LUT_CHARS[0xFF & (c4 >> 0)] |
LUT_CHARS[0xFF & (c4 >> 8)] |
LUT_CHARS[0xFF & (c4 >> 16)] |
LUT_CHARS[0xFF & (c4 >> 24)]) {
LUT_CHARS[0xFF & (c4 >> 8)] |
LUT_CHARS[0xFF & (c4 >> 16)] |
LUT_CHARS[0xFF & (c4 >> 24)]) {
break
}
args.src.skip_u32_fast!(actual: 4, worst_case: 4)
if string_length > (0xFFFB - 4) {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 4)
string_length = 0
continue.string_loop_outer
}
@@ -293,13 +293,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if string_length >= 0xFFFB {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: 0xFFFC)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: 0xFFFC)
string_length = 0
continue.string_loop_outer
}
@@ -309,13 +309,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else if char == 0x01 { // '"'
if string_length <> 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
}
break.string_loop_outer
@@ -323,13 +323,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else if char == 0x02 { // '\\'.
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
if args.dst.length() <= 0 {
continue.string_loop_outer
@@ -349,22 +349,22 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if (backslash & 0x80) <> 0 {
args.src.skip_u32_fast!(actual: 2, worst_case: 2)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
((backslash & 0x7F) as base.u32),
continued: 1,
length: 2)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
((backslash & 0x7F) as base.u32),
continued: 1,
length: 2)
continue.string_loop_outer
} else if backslash <> 0 {
if this.quirks[LUT_QUIRKY_BACKSLASHES_QUIRKS[backslash & 7]] {
args.src.skip_u32_fast!(actual: 2, worst_case: 2)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(LUT_QUIRKY_BACKSLASHES_CHARS[backslash & 7] as base.u32),
continued: 1,
length: 2)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(LUT_QUIRKY_BACKSLASHES_CHARS[backslash & 7] as base.u32),
continued: 1,
length: 2)
continue.string_loop_outer
}
@@ -403,11 +403,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// Not a Unicode surrogate. We're good.
args.src.skip_u32_fast!(actual: 6, worst_case: 6)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
uni4_value,
continued: 1,
length: 6)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
uni4_value,
continued: 1,
length: 6)
continue.string_loop_outer
} else if uni4_value >= 0xDC00 {
@@ -425,11 +425,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.src.skip_u32_fast!(actual: 6, worst_case: 6)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 6)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 6)
continue.string_loop_outer
}
return "#bad backslash-escape"
@@ -441,13 +441,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// Look for the low surrogate's "\\u".
if ((0xFF & (uni4_string >> 0)) <> '\\') or
((0xFF & (uni4_string >> 8)) <> 'u') {
((0xFF & (uni4_string >> 8)) <> 'u') {
uni4_high_surrogate = 0
uni4_value = 0
uni4_ok = 0
} else {
uni4_high_surrogate =
0x1_0000 + ((uni4_value - 0xD800) << 10)
0x1_0000 + ((uni4_value - 0xD800) << 10)
uni4_value = 0
uni4_ok = 0x80
uni4_string >>= 16
@@ -467,18 +467,18 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
}
if (uni4_ok <> 0) and
(0xDC00 <= uni4_value) and (uni4_value <= 0xDFFF) {
(0xDC00 <= uni4_value) and (uni4_value <= 0xDFFF) {
// Emit a single token for the surrogate
// pair.
uni4_value -= 0xDC00
args.src.skip_u32_fast!(actual: 12, worst_case: 12)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
uni4_high_surrogate | uni4_value,
continued: 1,
length: 12)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
uni4_high_surrogate | uni4_value,
continued: 1,
length: 12)
continue.string_loop_outer
}
}
@@ -489,17 +489,17 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
}
args.src.skip_u32_fast!(actual: 6, worst_case: 6)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 6)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 6)
continue.string_loop_outer
}
// -------- END backslash-u.
} else if (c == 'U') and
this.quirks[QUIRK_ALLOW_BACKSLASH_CAPITAL_U - QUIRKS_BASE] {
this.quirks[QUIRK_ALLOW_BACKSLASH_CAPITAL_U - QUIRKS_BASE] {
// -------- BEGIN backslash-capital-u.
if args.src.length() < 10 {
if args.src.is_closed() {
@@ -542,30 +542,30 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
// fall through to "#bad backslash-escape").
} else if (uni8_value < 0xD800) or (
(0xDFFF < uni8_value) and (uni8_value <= 0x10_FFFF)) {
(0xDFFF < uni8_value) and (uni8_value <= 0x10_FFFF)) {
// Not a Unicode surrogate. We're good.
args.src.skip_u32_fast!(actual: 10, worst_case: 10)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(uni8_value & 0x1F_FFFF),
continued: 1,
length: 10)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(uni8_value & 0x1F_FFFF),
continued: 1,
length: 10)
continue.string_loop_outer
} else if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.src.skip_u32_fast!(actual: 10, worst_case: 10)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 10)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 10)
continue.string_loop_outer
}
// -------- END backslash-capital-u.
} else if (c == 'x') and
this.quirks[QUIRK_ALLOW_BACKSLASH_X_AS_CODE_POINTS - QUIRKS_BASE] {
this.quirks[QUIRK_ALLOW_BACKSLASH_X_AS_CODE_POINTS - QUIRKS_BASE] {
// -------- BEGIN backslash-x
if args.src.length() < 4 {
if args.src.is_closed() {
@@ -586,18 +586,18 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
backslash_x_value = (backslash_x_value | (c & 0x0F)) as base.u8
if (backslash_x_ok == 0) or
((backslash_x_string & 0xFFFF) <> 0x785C) {
((backslash_x_string & 0xFFFF) <> 0x785C) {
// It wasn't "\\x34", for some hexadecimal
// digits "34".
return "#bad backslash-escape"
}
args.src.skip_u32_fast!(actual: 4, worst_case: 4)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(backslash_x_value as base.u32),
continued: 1,
length: 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
(backslash_x_value as base.u32),
continued: 1,
length: 4)
continue.string_loop_outer
// -------- END backslash-x
}
@@ -608,13 +608,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.length() < 2 {
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
if args.dst.length() <= 0 {
continue.string_loop_outer
@@ -623,11 +623,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.is_closed() {
if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
continue.string_loop_outer
}
@@ -639,17 +639,17 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
multi_byte_utf8 = args.src.peek_u16le_as_u32()
if (multi_byte_utf8 & 0xC000) == 0x8000 {
multi_byte_utf8 = (0x00_07C0 & (multi_byte_utf8 ~mod<< 6)) |
(0x00_003F & (multi_byte_utf8 >> 8))
(0x00_003F & (multi_byte_utf8 >> 8))
args.src.skip_u32_fast!(actual: 2, worst_case: 2)
if string_length >= 0xFFF8 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 2)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 2)
string_length = 0
continue.string_loop_outer
}
@@ -661,13 +661,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.length() < 3 {
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
if args.dst.length() <= 0 {
continue.string_loop_outer
@@ -676,11 +676,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.is_closed() {
if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
continue.string_loop_outer
}
@@ -692,21 +692,21 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
multi_byte_utf8 = args.src.peek_u24le_as_u32()
if (multi_byte_utf8 & 0xC0_C000) == 0x80_8000 {
multi_byte_utf8 = (0x00_F000 & (multi_byte_utf8 ~mod<< 12)) |
(0x00_0FC0 & (multi_byte_utf8 >> 2)) |
(0x00_003F & (multi_byte_utf8 >> 16))
(0x00_0FC0 & (multi_byte_utf8 >> 2)) |
(0x00_003F & (multi_byte_utf8 >> 16))
if (0x07FF < multi_byte_utf8) and
((multi_byte_utf8 < 0xD800) or (0xDFFF < multi_byte_utf8)) {
((multi_byte_utf8 < 0xD800) or (0xDFFF < multi_byte_utf8)) {
args.src.skip_u32_fast!(actual: 3, worst_case: 3)
if string_length >= 0xFFF8 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 3)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 3)
string_length = 0
continue.string_loop_outer
}
@@ -719,13 +719,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.length() < 4 {
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
if args.dst.length() <= 0 {
continue.string_loop_outer
@@ -734,11 +734,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if args.src.is_closed() {
if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
continue.string_loop_outer
}
@@ -750,20 +750,20 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
multi_byte_utf8 = args.src.peek_u32le()
if (multi_byte_utf8 & 0xC0C0_C000) == 0x8080_8000 {
multi_byte_utf8 = (0x1C_0000 & (multi_byte_utf8 ~mod<< 18)) |
(0x03_F000 & (multi_byte_utf8 ~mod<< 4)) |
(0x00_0FC0 & (multi_byte_utf8 >> 10)) |
(0x00_003F & (multi_byte_utf8 >> 24))
(0x03_F000 & (multi_byte_utf8 ~mod<< 4)) |
(0x00_0FC0 & (multi_byte_utf8 >> 10)) |
(0x00_003F & (multi_byte_utf8 >> 24))
if (0xFFFF < multi_byte_utf8) and (multi_byte_utf8 <= 0x10_FFFF) {
args.src.skip_u32_fast!(actual: 4, worst_case: 4)
if string_length >= 0xFFF8 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length + 4)
string_length = 0
continue.string_loop_outer
}
@@ -775,13 +775,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if string_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__CONVERT_1_DST_1_SRC_COPY,
continued: 1,
length: string_length)
string_length = 0
if args.dst.length() <= 0 {
continue.string_loop_outer
@@ -790,11 +790,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
if (char & 0x80) <> 0 {
if this.quirks[QUIRK_ALLOW_ASCII_CONTROL_CODES - QUIRKS_BASE] {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
((char & 0x7F) as base.u32),
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
((char & 0x7F) as base.u32),
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
continue.string_loop_outer
}
@@ -805,11 +805,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
}
if this.quirks[QUIRK_REPLACE_INVALID_UNICODE - QUIRKS_BASE] {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__UNICODE_CODE_POINT << 21) |
base.UNICODE__REPLACEMENT_CHARACTER,
continued: 1,
length: 1)
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
continue.string_loop_outer
}
@@ -832,14 +832,14 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
}
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__DEFINITELY_ASCII |
base.TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRING << 21) |
base.TOKEN__VBD__STRING__DEFINITELY_UTF_8 |
base.TOKEN__VBD__STRING__CHAIN_MUST_BE_UTF_8 |
base.TOKEN__VBD__STRING__DEFINITELY_ASCII |
base.TOKEN__VBD__STRING__CONVERT_0_DST_1_SRC_DROP,
continued: 0,
length: 1)
break
} endwhile
@@ -857,11 +857,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
// The ',' is punctuation (filler).
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__PUNCTUATION,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__PUNCTUATION,
continued: 0,
length: 1)
// What's valid after a comma depends on whether or not we're in an
// array or an object.
if 0 == (expect & ((1 as base.u32) << CLASS_CLOSE_SQUARE_BRACKET)) {
@@ -883,37 +883,37 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
// The ':' is punctuation (filler).
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__PUNCTUATION,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__PUNCTUATION,
continued: 0,
length: 1)
expect = EXPECT_VALUE
continue.outer
} else if class == CLASS_NUMBER {
// -------- BEGIN parse numbers.
while true,
pre args.dst.length() > 0,
pre args.dst.length() > 0,
{
number_length = this.decode_number!(src: args.src)
number_status = number_length >> 8
vminor = (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_FLOATING_POINT |
base.TOKEN__VBD__NUMBER__CONTENT_INTEGER_SIGNED |
base.TOKEN__VBD__NUMBER__FORMAT_TEXT
base.TOKEN__VBD__NUMBER__CONTENT_FLOATING_POINT |
base.TOKEN__VBD__NUMBER__CONTENT_INTEGER_SIGNED |
base.TOKEN__VBD__NUMBER__FORMAT_TEXT
if (number_length & 0x80) <> 0 {
vminor = (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_FLOATING_POINT |
base.TOKEN__VBD__NUMBER__FORMAT_TEXT
base.TOKEN__VBD__NUMBER__CONTENT_FLOATING_POINT |
base.TOKEN__VBD__NUMBER__FORMAT_TEXT
}
number_length = number_length & 0x7F
if number_status == 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: vminor,
continued: 0,
length: number_length)
value_major: 0,
value_minor: vminor,
continued: 0,
length: number_length)
break
}
@@ -937,7 +937,7 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else {
yield? base."$short read"
while args.dst.length() <= 0,
post args.dst.length() > 0,
post args.dst.length() > 0,
{
yield? base."$short write"
} endwhile
@@ -948,21 +948,21 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else if class == CLASS_OPEN_CURLY_BRACE {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_NONE |
base.TOKEN__VBD__STRUCTURE__TO_DICT
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_NONE |
base.TOKEN__VBD__STRUCTURE__TO_DICT
if depth == 0 {
// No-op.
} else if 0 <> (expect_after_value & ((1 as base.u32) << CLASS_CLOSE_CURLY_BRACE)) {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_DICT
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_DICT
} else {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_DICT
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_DICT
}
if depth >= 1024 {
return "#unsupported recursion depth"
@@ -974,10 +974,10 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: vminor,
continued: 0,
length: 1)
value_major: 0,
value_minor: vminor,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_CURLY_BRACE | EXPECT_STRING
expect_after_value = EXPECT_CLOSE_CURLY_BRACE | EXPECT_COMMA
continue.outer
@@ -986,13 +986,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if depth <= 1 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_NONE,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_NONE,
continued: 0,
length: 1)
break.outer
}
depth -= 1
@@ -1000,24 +1000,24 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
stack_bit = (depth - 1) & 31
if 0 == (this.stack[stack_byte] & ((1 as base.u32) << stack_bit)) {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_LIST,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_LIST,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_COMMA
expect_after_value = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_COMMA
} else {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_DICT,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_DICT,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_CURLY_BRACE | EXPECT_COMMA
expect_after_value = EXPECT_CLOSE_CURLY_BRACE | EXPECT_COMMA
}
@@ -1025,21 +1025,21 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else if class == CLASS_OPEN_SQUARE_BRACKET {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_NONE |
base.TOKEN__VBD__STRUCTURE__TO_LIST
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_NONE |
base.TOKEN__VBD__STRUCTURE__TO_LIST
if depth == 0 {
// No-op.
} else if 0 <> (expect_after_value & ((1 as base.u32) << CLASS_CLOSE_CURLY_BRACE)) {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_LIST
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_DICT |
base.TOKEN__VBD__STRUCTURE__TO_LIST
} else {
vminor = (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_LIST
base.TOKEN__VBD__STRUCTURE__PUSH |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_LIST
}
if depth >= 1024 {
return "#unsupported recursion depth"
@@ -1051,10 +1051,10 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: vminor,
continued: 0,
length: 1)
value_major: 0,
value_minor: vminor,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_VALUE
expect_after_value = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_COMMA
continue.outer
@@ -1063,13 +1063,13 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if depth <= 1 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_NONE,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_NONE,
continued: 0,
length: 1)
break.outer
}
depth -= 1
@@ -1077,24 +1077,24 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
stack_bit = (depth - 1) & 31
if 0 == (this.stack[stack_byte] & ((1 as base.u32) << stack_bit)) {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_LIST,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_LIST,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_COMMA
expect_after_value = EXPECT_CLOSE_SQUARE_BRACKET | EXPECT_COMMA
} else {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_DICT,
continued: 0,
length: 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__STRUCTURE << 21) |
base.TOKEN__VBD__STRUCTURE__POP |
base.TOKEN__VBD__STRUCTURE__FROM_LIST |
base.TOKEN__VBD__STRUCTURE__TO_DICT,
continued: 0,
length: 1)
expect = EXPECT_CLOSE_CURLY_BRACE | EXPECT_COMMA
expect_after_value = EXPECT_CLOSE_CURLY_BRACE | EXPECT_COMMA
}
@@ -1104,11 +1104,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
match = args.src.match7(a: '\x05false'le)
if match == 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__FALSE,
continued: 0,
length: 5)
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__FALSE,
continued: 0,
length: 5)
if args.src.length() < 5 {
return "#internal error: inconsistent I/O"
}
@@ -1123,11 +1123,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
match = args.src.match7(a: '\x04true'le)
if match == 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__TRUE,
continued: 0,
length: 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__TRUE,
continued: 0,
length: 4)
if args.src.length() < 4 {
return "#internal error: inconsistent I/O"
}
@@ -1142,11 +1142,11 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
match = args.src.match7(a: '\x04null'le)
if match == 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__NULL,
continued: 0,
length: 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__LITERAL << 21) |
base.TOKEN__VBD__LITERAL__NULL,
continued: 0,
length: 4)
if args.src.length() < 4 {
return "#internal error: inconsistent I/O"
}
@@ -1164,7 +1164,7 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} else if class == CLASS_COMMENT {
if this.quirks[QUIRK_ALLOW_COMMENT_BLOCK - QUIRKS_BASE] or
this.quirks[QUIRK_ALLOW_COMMENT_LINE - QUIRKS_BASE] {
this.quirks[QUIRK_ALLOW_COMMENT_LINE - QUIRKS_BASE] {
this.decode_comment?(dst: args.dst, src: args.src)
if this.comment_type > 0 {
continue.outer
@@ -1184,7 +1184,7 @@ pub func decoder.decode_tokens?(dst: base.token_writer, src: base.io_reader, wor
} endwhile.outer
if this.quirks[QUIRK_ALLOW_TRAILING_FILLER - QUIRKS_BASE] or
this.quirks[QUIRK_EXPECT_TRAILING_NEW_LINE_OR_EOF - QUIRKS_BASE] {
this.quirks[QUIRK_EXPECT_TRAILING_NEW_LINE_OR_EOF - QUIRKS_BASE] {
this.decode_trailer?(dst: args.dst, src: args.src)
}
@@ -1371,9 +1371,9 @@ pri func decoder.decode_leading?(dst: base.token_writer, src: base.io_reader) {
var u : base.u32
this.allow_leading_ars =
this.quirks[QUIRK_ALLOW_LEADING_ASCII_RECORD_SEPARATOR - QUIRKS_BASE]
this.quirks[QUIRK_ALLOW_LEADING_ASCII_RECORD_SEPARATOR - QUIRKS_BASE]
this.allow_leading_ubom =
this.quirks[QUIRK_ALLOW_LEADING_UNICODE_BYTE_ORDER_MARK - QUIRKS_BASE]
this.quirks[QUIRK_ALLOW_LEADING_UNICODE_BYTE_ORDER_MARK - QUIRKS_BASE]
while this.allow_leading_ars or this.allow_leading_ubom {
if args.dst.length() <= 0 {
@@ -1392,7 +1392,7 @@ pri func decoder.decode_leading?(dst: base.token_writer, src: base.io_reader) {
this.allow_leading_ars = false
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
args.dst.write_simple_token_fast!(
value_major: 0, value_minor: 0, continued: 0, length: 1)
value_major: 0, value_minor: 0, continued: 0, length: 1)
continue
} else if (c == 0xEF) and this.allow_leading_ubom {
if args.src.length() < 3 {
@@ -1407,7 +1407,7 @@ pri func decoder.decode_leading?(dst: base.token_writer, src: base.io_reader) {
this.allow_leading_ubom = false
args.src.skip_u32_fast!(actual: 3, worst_case: 3)
args.dst.write_simple_token_fast!(
value_major: 0, value_minor: 0, continued: 0, length: 3)
value_major: 0, value_minor: 0, continued: 0, length: 3)
continue
}
}
@@ -1423,8 +1423,8 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
this.comment_type = 0
while (args.dst.length() <= 0) or (args.src.length() <= 1),
post args.dst.length() > 0,
post args.src.length() > 1,
post args.dst.length() > 0,
post args.src.length() > 1,
{
if args.dst.length() <= 0 {
yield? base."$short write"
@@ -1442,23 +1442,23 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
length = 2
while.comment_block true,
pre args.dst.length() > 0,
pre args.dst.length() > 0,
{
if args.src.length() <= 1 {
if length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 1,
length: length)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 1,
length: length)
}
if args.src.is_closed() {
return "#bad input"
}
yield? base."$short read"
while args.dst.length() <= 0,
post args.dst.length() > 0,
post args.dst.length() > 0,
{
yield? base."$short write"
} endwhile
@@ -1470,11 +1470,11 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
if c2 == '*/'le {
args.src.skip_u32_fast!(actual: 2, worst_case: 2)
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 0,
length: length + 2)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 0,
length: length + 2)
this.comment_type = 1
return ok
}
@@ -1482,13 +1482,13 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if length >= 0xFFFD {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 1,
length: length + 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_BLOCK,
continued: 1,
length: length + 1)
while args.dst.length() <= 0,
post args.dst.length() > 0,
post args.dst.length() > 0,
{
yield? base."$short write"
} endwhile
@@ -1503,29 +1503,29 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
length = 2
while.comment_line true,
pre args.dst.length() > 0,
pre args.dst.length() > 0,
{
if args.src.length() <= 0 {
if args.src.is_closed() {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 0,
length: length)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 0,
length: length)
this.comment_type = 2
return ok
} else if length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 1,
length: length)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 1,
length: length)
}
yield? base."$short read"
while args.dst.length() <= 0,
post args.dst.length() > 0,
post args.dst.length() > 0,
{
yield? base."$short write"
} endwhile
@@ -1536,11 +1536,11 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
c = args.src.peek_u8()
if c == '\n' {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 0,
length: length)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 0,
length: length)
this.comment_type = 2
return ok
}
@@ -1548,13 +1548,13 @@ pri func decoder.decode_comment?(dst: base.token_writer, src: base.io_reader) {
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if length >= 0xFFFD {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 1,
length: length + 1)
value_major: 0,
value_minor: (base.TOKEN__VBC__FILLER << 21) |
base.TOKEN__VBD__FILLER__COMMENT_LINE,
continued: 1,
length: length + 1)
while args.dst.length() <= 0,
post args.dst.length() > 0,
post args.dst.length() > 0,
{
yield? base."$short write"
} endwhile
@@ -1590,11 +1590,11 @@ pri func decoder.decode_inf_nan?(dst: base.token_writer, src: base.io_reader) {
if args.src.length() > 7 {
if (args.src.peek_u64le() | 0x2020_2020_2020_2020) == 'infinity'le {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_INF,
continued: 0,
length: 8)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_INF,
continued: 0,
length: 8)
args.src.skip_u32_fast!(actual: 8, worst_case: 8)
return ok
}
@@ -1603,21 +1603,21 @@ pri func decoder.decode_inf_nan?(dst: base.token_writer, src: base.io_reader) {
continue
}
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_INF,
continued: 0,
length: 3)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_INF,
continued: 0,
length: 3)
args.src.skip_u32_fast!(actual: 3, worst_case: 3)
return ok
} else if (c4 | 0x20_2020) == 'nan'le {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_NAN,
continued: 0,
length: 3)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
base.TOKEN__VBD__NUMBER__CONTENT_POS_NAN,
continued: 0,
length: 3)
args.src.skip_u32_fast!(actual: 3, worst_case: 3)
return ok
} else if (c4 & 0xFF) == '+' {
@@ -1641,11 +1641,11 @@ pri func decoder.decode_inf_nan?(dst: base.token_writer, src: base.io_reader) {
if args.src.length() > 8 {
if (args.src.peek_u64le_at(offset: 1) | 0x2020_2020_2020_2020) == 'infinity'le {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_INF >> neg),
continued: 0,
length: 9)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_INF >> neg),
continued: 0,
length: 9)
args.src.skip_u32_fast!(actual: 9, worst_case: 9)
return ok
}
@@ -1654,21 +1654,21 @@ pri func decoder.decode_inf_nan?(dst: base.token_writer, src: base.io_reader) {
continue
}
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_INF >> neg),
continued: 0,
length: 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_INF >> neg),
continued: 0,
length: 4)
args.src.skip_u32_fast!(actual: 4, worst_case: 4)
return ok
} else if (c4 | 0x20_2020) == 'nan'le {
args.dst.write_simple_token_fast!(
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_NAN >> neg),
continued: 0,
length: 4)
value_major: 0,
value_minor: (base.TOKEN__VBC__NUMBER << 21) |
(base.TOKEN__VBD__NUMBER__CONTENT_POS_NAN >> neg),
continued: 0,
length: 4)
args.src.skip_u32_fast!(actual: 4, worst_case: 4)
return ok
}
@@ -1695,12 +1695,12 @@ pri func decoder.decode_trailer?(dst: base.token_writer, src: base.io_reader) {
whitespace_length = 0
while.inner true,
pre args.dst.length() > 0,
pre args.dst.length() > 0,
{
if args.src.length() <= 0 {
if whitespace_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length)
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length)
}
if args.src.is_closed() {
break.outer
@@ -1713,7 +1713,7 @@ pri func decoder.decode_trailer?(dst: base.token_writer, src: base.io_reader) {
if LUT_CLASSES[c] <> CLASS_WHITESPACE {
if whitespace_length > 0 {
args.dst.write_simple_token_fast!(
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length)
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length)
}
if this.trailer_stop > 0 {
return "#bad input"
@@ -1728,7 +1728,7 @@ pri func decoder.decode_trailer?(dst: base.token_writer, src: base.io_reader) {
args.src.skip_u32_fast!(actual: 1, worst_case: 1)
if (whitespace_length >= 0xFFFE) or (c == this.trailer_stop) {
args.dst.write_simple_token_fast!(
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length + 1)
value_major: 0, value_minor: 0, continued: 0, length: whitespace_length + 1)
if c == this.trailer_stop {
return ok
}