Stevie Strickland
f31b7928ae
See https://github.com/tc39/proposal-regexp-lookbehind for a high-level description of the feature and examples. This is one of the features requested in https://github.com/dart-lang/sdk/issues/34935. This work takes the feature as present in the v8 engine and appropriately merges it into our irregexp fork. Notable changes to the irregexp codebase to introduce this feature: ----- We can no longer assume that all matching proceeds forwards, since lookbehind matching proceeds backwards. Similarly, we cannot assume that we can only be at the start of a string if we started matching from that point. The direction of matching must also be taken into consideration when doing bounds checking, which previously assumed the engine would never attempt to look before the start of a string. ----- We may now parse backreferences to captures before the capture they reference, since we parse regular expressions left to right, but lookbehinds perform captures as they evaluate the string from right to left. Since RegExpBackReference objects contain a pointer to their corresponding capture, this means that we may need to create RegExpCapture objects prior to the parsing of the corresponding captured subexpression. Thus, RegExpCapture objects are now only initialized with their index, and the body is set later when the subexpression is encountered and parsed. This means any method that operates on the body of a RegExpCapture can no longer be const, which also affects the rest of the RegExpTree class hierarchy. This also means that we don't have a valid max_match length for backreferences based off the capture body, and must assume they can end up being any length. ----- Change-Id: Iffe0e71b17b1a0c6fea77235e8aee5c093005811 Reviewed-on: https://dart-review.googlesource.com/c/sdk/+/94540 Commit-Queue: Stevie Strickland <sstrickl@google.com> Reviewed-by: Martin Kustermann <kustermann@google.com>
84 lines
5.1 KiB
C++
84 lines
5.1 KiB
C++
// Copyright (c) 2015, 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.
|
|
|
|
#ifndef RUNTIME_VM_REGEXP_BYTECODES_H_
|
|
#define RUNTIME_VM_REGEXP_BYTECODES_H_
|
|
|
|
namespace dart {
|
|
|
|
const int BYTECODE_MASK = 0xff;
|
|
// The first argument is packed in with the byte code in one word, but so it
|
|
// has 24 bits, but it can be positive and negative so only use 23 bits for
|
|
// positive values.
|
|
const unsigned int MAX_FIRST_ARG = 0x7fffffu;
|
|
const int BYTECODE_SHIFT = 8;
|
|
|
|
// clang-format off
|
|
#define BYTECODE_ITERATOR(V) \
|
|
V(BREAK, 0, 4) /* bc8 */ \
|
|
V(PUSH_CP, 1, 4) /* bc8 pad24 */ \
|
|
V(PUSH_BT, 2, 8) /* bc8 pad24 offset32 */ \
|
|
V(PUSH_REGISTER, 3, 4) /* bc8 reg_idx24 */ \
|
|
V(SET_REGISTER_TO_CP, 4, 8) /* bc8 reg_idx24 offset32 */ \
|
|
V(SET_CP_TO_REGISTER, 5, 4) /* bc8 reg_idx24 */ \
|
|
V(SET_REGISTER_TO_SP, 6, 4) /* bc8 reg_idx24 */ \
|
|
V(SET_SP_TO_REGISTER, 7, 4) /* bc8 reg_idx24 */ \
|
|
V(SET_REGISTER, 8, 8) /* bc8 reg_idx24 value32 */ \
|
|
V(ADVANCE_REGISTER, 9, 8) /* bc8 reg_idx24 value32 */ \
|
|
V(POP_CP, 10, 4) /* bc8 pad24 */ \
|
|
V(POP_BT, 11, 4) /* bc8 pad24 */ \
|
|
V(POP_REGISTER, 12, 4) /* bc8 reg_idx24 */ \
|
|
V(FAIL, 13, 4) /* bc8 pad24 */ \
|
|
V(SUCCEED, 14, 4) /* bc8 pad24 */ \
|
|
V(ADVANCE_CP, 15, 4) /* bc8 offset24 */ \
|
|
V(GOTO, 16, 8) /* bc8 pad24 addr32 */ \
|
|
V(LOAD_CURRENT_CHAR, 17, 8) /* bc8 offset24 addr32 */ \
|
|
V(LOAD_CURRENT_CHAR_UNCHECKED, 18, 4) /* bc8 offset24 */ \
|
|
V(LOAD_2_CURRENT_CHARS, 19, 8) /* bc8 offset24 addr32 */ \
|
|
V(LOAD_2_CURRENT_CHARS_UNCHECKED, 20, 4) /* bc8 offset24 */ \
|
|
V(LOAD_4_CURRENT_CHARS, 21, 8) /* bc8 offset24 addr32 */ \
|
|
V(LOAD_4_CURRENT_CHARS_UNCHECKED, 22, 4) /* bc8 offset24 */ \
|
|
V(CHECK_4_CHARS, 23, 12) /* bc8 pad24 uint32 addr32 */ \
|
|
V(CHECK_CHAR, 24, 8) /* bc8 pad8 uint16 addr32 */ \
|
|
V(CHECK_NOT_4_CHARS, 25, 12) /* bc8 pad24 uint32 addr32 */ \
|
|
V(CHECK_NOT_CHAR, 26, 8) /* bc8 pad8 uint16 addr32 */ \
|
|
V(AND_CHECK_4_CHARS, 27, 16) /* bc8 pad24 uint32 uint32 addr32 */ \
|
|
V(AND_CHECK_CHAR, 28, 12) /* bc8 pad8 uint16 uint32 addr32 */ \
|
|
V(AND_CHECK_NOT_4_CHARS, 29, 16) /* bc8 pad24 uint32 uint32 addr32 */ \
|
|
V(AND_CHECK_NOT_CHAR, 30, 12) /* bc8 pad8 uint16 uint32 addr32 */ \
|
|
V(MINUS_AND_CHECK_NOT_CHAR, 31, 12) /* bc8 pad8 uc16 uc16 uc16 addr32 */ \
|
|
V(CHECK_CHAR_IN_RANGE, 32, 12) /* bc8 pad24 uc16 uc16 addr32 */ \
|
|
V(CHECK_CHAR_NOT_IN_RANGE, 33, 12) /* bc8 pad24 uc16 uc16 addr32 */ \
|
|
V(CHECK_BIT_IN_TABLE, 34, 24) /* bc8 pad24 addr32 bits128 */ \
|
|
V(CHECK_LT, 35, 8) /* bc8 pad8 uc16 addr32 */ \
|
|
V(CHECK_GT, 36, 8) /* bc8 pad8 uc16 addr32 */ \
|
|
V(CHECK_NOT_BACK_REF, 37, 8) /* bc8 reg_idx24 addr32 */ \
|
|
V(CHECK_NOT_BACK_REF_NO_CASE, 38, 8) /* bc8 reg_idx24 addr32 */ \
|
|
V(CHECK_NOT_BACK_REF_BACKWARD, 39, 8) /* bc8 reg_idx24 addr32 */ \
|
|
V(CHECK_NOT_BACK_REF_NO_CASE_BACKWARD, 40, 8) /* bc8 reg_idx24 addr32 */ \
|
|
V(CHECK_NOT_REGS_EQUAL, 41, 12) /* bc8 regidx24 reg_idx32 addr32 */ \
|
|
V(CHECK_REGISTER_LT, 42, 12) /* bc8 reg_idx24 value32 addr32 */ \
|
|
V(CHECK_REGISTER_GE, 43, 12) /* bc8 reg_idx24 value32 addr32 */ \
|
|
V(CHECK_REGISTER_EQ_POS, 44, 8) /* bc8 reg_idx24 addr32 */ \
|
|
V(CHECK_AT_START, 45, 8) /* bc8 pad24 addr32 */ \
|
|
V(CHECK_NOT_AT_START, 46, 8) /* bc8 offset24 addr32 */ \
|
|
V(CHECK_GREEDY, 47, 8) /* bc8 pad24 addr32 */ \
|
|
V(ADVANCE_CP_AND_GOTO, 48, 8) /* bc8 offset24 addr32 */ \
|
|
V(SET_CURRENT_POSITION_FROM_END, 49, 4) /* bc8 idx24 */
|
|
|
|
// clang-format on
|
|
|
|
#define DECLARE_BYTECODES(name, code, length) static const int BC_##name = code;
|
|
BYTECODE_ITERATOR(DECLARE_BYTECODES)
|
|
#undef DECLARE_BYTECODES
|
|
|
|
#define DECLARE_BYTECODE_LENGTH(name, code, length) \
|
|
static const int BC_##name##_LENGTH = length;
|
|
BYTECODE_ITERATOR(DECLARE_BYTECODE_LENGTH)
|
|
#undef DECLARE_BYTECODE_LENGTH
|
|
|
|
} // namespace dart
|
|
|
|
#endif // RUNTIME_VM_REGEXP_BYTECODES_H_
|