4028fec3b5
This work pulls in v8 support for these features with appropriate changes for Dart and closes https://github.com/dart-lang/sdk/issues/34935. This adds support for the following features: * Interpreting patterns as Unicode patterns instead of BMP patterns * the dotAll flag (`/s`) for changing the behavior of '.' to also match line terminators * Escapes for character classes described by Unicode property groups (e.g., \p{Greek} to match all Greek characters, or \P{Greek} for all non-Greek characters). The following TC39 proposals describe some of the added features: * https://github.com/tc39/proposal-regexp-dotall-flag * https://github.com/tc39/proposal-regexp-unicode-property-escapes These additional changes are included: * Extends named capture group names to include the full range of identifier characters supported by ECMAScript, not just ASCII. * Changing the RegExp interface to return RegExpMatch objects, not Match objects, so that downcasting is not necessary to use named capture groups from Dart **Note**: The changes to the RegExp interface are a breaking change for implementers of the RegExp interface. Current users of the RegExp interface (i.e., code using Dart RegExp objects) will not be affected. Change-Id: Ie62e6082a0e2fedc1680ef2576ce0c6db80fc19a Reviewed-on: https://dart-review.googlesource.com/c/sdk/+/100641 Reviewed-by: Martin Kustermann <kustermann@google.com> Commit-Queue: Stevie Strickland <sstrickl@google.com>
130 lines
4.3 KiB
C++
130 lines
4.3 KiB
C++
// Copyright (c) 2014, the Dart project authors. Please see the AUTHORS file
|
|
// for details. All rights reserved. Use of this source code is governed by a
|
|
// BSD-style license that can be found in the LICENSE file.
|
|
|
|
#include "vm/regexp_assembler.h"
|
|
|
|
#include "unicode/uchar.h"
|
|
|
|
#include "platform/unicode.h"
|
|
|
|
#include "vm/flags.h"
|
|
#include "vm/regexp.h"
|
|
#include "vm/unibrow-inl.h"
|
|
|
|
namespace dart {
|
|
|
|
void PrintUtf16(uint16_t c) {
|
|
const char* format =
|
|
(0x20 <= c && c <= 0x7F) ? "%c" : (c <= 0xff) ? "\\x%02x" : "\\u%04x";
|
|
OS::PrintErr(format, c);
|
|
}
|
|
|
|
RawBool* CaseInsensitiveCompareUCS2(RawString* str_raw,
|
|
RawSmi* lhs_index_raw,
|
|
RawSmi* rhs_index_raw,
|
|
RawSmi* length_raw) {
|
|
const String& str = String::Handle(str_raw);
|
|
const Smi& lhs_index = Smi::Handle(lhs_index_raw);
|
|
const Smi& rhs_index = Smi::Handle(rhs_index_raw);
|
|
const Smi& length = Smi::Handle(length_raw);
|
|
|
|
// TODO(zerny): Optimize as single instance. V8 has this as an
|
|
// isolate member.
|
|
unibrow::Mapping<unibrow::Ecma262Canonicalize> canonicalize;
|
|
|
|
for (intptr_t i = 0; i < length.Value(); i++) {
|
|
int32_t c1 = str.CharAt(lhs_index.Value() + i);
|
|
int32_t c2 = str.CharAt(rhs_index.Value() + i);
|
|
if (c1 != c2) {
|
|
int32_t s1[1] = {c1};
|
|
canonicalize.get(c1, '\0', s1);
|
|
if (s1[0] != c2) {
|
|
int32_t s2[1] = {c2};
|
|
canonicalize.get(c2, '\0', s2);
|
|
if (s1[0] != s2[0]) {
|
|
return Bool::False().raw();
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return Bool::True().raw();
|
|
}
|
|
|
|
RawBool* CaseInsensitiveCompareUTF16(RawString* str_raw,
|
|
RawSmi* lhs_index_raw,
|
|
RawSmi* rhs_index_raw,
|
|
RawSmi* length_raw) {
|
|
const String& str = String::Handle(str_raw);
|
|
const Smi& lhs_index = Smi::Handle(lhs_index_raw);
|
|
const Smi& rhs_index = Smi::Handle(rhs_index_raw);
|
|
const Smi& length = Smi::Handle(length_raw);
|
|
|
|
for (intptr_t i = 0; i < length.Value(); i++) {
|
|
int32_t c1 = str.CharAt(lhs_index.Value() + i);
|
|
int32_t c2 = str.CharAt(rhs_index.Value() + i);
|
|
if (Utf16::IsLeadSurrogate(c1)) {
|
|
// Non-BMP characters do not have case-equivalents in the BMP.
|
|
// Both have to be non-BMP for them to be able to match.
|
|
if (!Utf16::IsLeadSurrogate(c2)) return Bool::False().raw();
|
|
if (i + 1 < length.Value()) {
|
|
uint16_t c1t = str.CharAt(lhs_index.Value() + i + 1);
|
|
uint16_t c2t = str.CharAt(rhs_index.Value() + i + 1);
|
|
if (Utf16::IsTrailSurrogate(c1t) && Utf16::IsTrailSurrogate(c2t)) {
|
|
c1 = Utf16::Decode(c1, c1t);
|
|
c2 = Utf16::Decode(c2, c2t);
|
|
i++;
|
|
}
|
|
}
|
|
}
|
|
c1 = u_foldCase(c1, U_FOLD_CASE_DEFAULT);
|
|
c2 = u_foldCase(c2, U_FOLD_CASE_DEFAULT);
|
|
if (c1 != c2) return Bool::False().raw();
|
|
}
|
|
return Bool::True().raw();
|
|
}
|
|
|
|
DEFINE_RAW_LEAF_RUNTIME_ENTRY(
|
|
CaseInsensitiveCompareUCS2,
|
|
4,
|
|
false /* is_float */,
|
|
reinterpret_cast<RuntimeFunction>(&CaseInsensitiveCompareUCS2));
|
|
|
|
DEFINE_RAW_LEAF_RUNTIME_ENTRY(
|
|
CaseInsensitiveCompareUTF16,
|
|
4,
|
|
false /* is_float */,
|
|
reinterpret_cast<RuntimeFunction>(&CaseInsensitiveCompareUTF16));
|
|
|
|
BlockLabel::BlockLabel()
|
|
: block_(NULL), is_bound_(false), is_linked_(false), pos_(-1) {
|
|
#if !defined(DART_PRECOMPILED_RUNTIME)
|
|
if (!FLAG_interpret_irregexp) {
|
|
// Only needed by the compiled IR backend.
|
|
block_ =
|
|
new JoinEntryInstr(-1, -1, CompilerState::Current().GetNextDeoptId());
|
|
}
|
|
#endif
|
|
}
|
|
|
|
RegExpMacroAssembler::RegExpMacroAssembler(Zone* zone)
|
|
: slow_safe_compiler_(false), global_mode_(NOT_GLOBAL), zone_(zone) {}
|
|
|
|
RegExpMacroAssembler::~RegExpMacroAssembler() {}
|
|
|
|
void RegExpMacroAssembler::CheckNotInSurrogatePair(intptr_t cp_offset,
|
|
BlockLabel* on_failure) {
|
|
BlockLabel ok;
|
|
// Check that current character is not a trail surrogate.
|
|
LoadCurrentCharacter(cp_offset, &ok);
|
|
CheckCharacterNotInRange(Utf16::kTrailSurrogateStart,
|
|
Utf16::kTrailSurrogateEnd, &ok);
|
|
// Check that previous character is not a lead surrogate.
|
|
LoadCurrentCharacter(cp_offset - 1, &ok);
|
|
CheckCharacterInRange(Utf16::kLeadSurrogateStart, Utf16::kLeadSurrogateEnd,
|
|
on_failure);
|
|
BindBlock(&ok);
|
|
}
|
|
|
|
} // namespace dart
|