Stevie Strickland
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>
57 lines
3.1 KiB
Dart
57 lines
3.1 KiB
Dart
// Copyright (c) 2019, the Dart project authors. All rights reserved.
|
|
// Copyright 2011 the V8 project authors. All rights reserved.
|
|
// Redistribution and use in source and binary forms, with or without
|
|
// modification, are permitted provided that the following conditions are
|
|
// met:
|
|
//
|
|
// * Redistributions of source code must retain the above copyright
|
|
// notice, this list of conditions and the following disclaimer.
|
|
// * Redistributions in binary form must reproduce the above
|
|
// copyright notice, this list of conditions and the following
|
|
// disclaimer in the documentation and/or other materials provided
|
|
// with the distribution.
|
|
// * Neither the name of Google Inc. nor the names of its
|
|
// contributors may be used to endorse or promote products derived
|
|
// from this software without specific prior written permission.
|
|
//
|
|
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
import 'package:expect/expect.dart';
|
|
|
|
import 'v8_regexp_utils.dart';
|
|
|
|
void main() {
|
|
assertThrows(() => RegExp("[\\p]", unicode: true));
|
|
assertThrows(() => RegExp("[\\p{garbage}]", unicode: true));
|
|
assertThrows(() => RegExp("[\\p{}]", unicode: true));
|
|
assertThrows(() => RegExp("[\\p{]", unicode: true));
|
|
assertThrows(() => RegExp("[\\p}]", unicode: true));
|
|
assertThrows(() => RegExp("^[\\p{Lu}-\\p{Ll}]+\$", unicode: true));
|
|
|
|
assertTrue(RegExp(r"^[\p{Lu}\p{Ll}]+$", unicode: true).hasMatch("ABCabc"));
|
|
assertTrue(RegExp(r"^[\p{Lu}-]+$", unicode: true).hasMatch("ABC-"));
|
|
assertFalse(RegExp(r"^[\P{Lu}\p{Ll}]+$", unicode: true).hasMatch("ABCabc"));
|
|
assertTrue(RegExp(r"^[\P{Lu}\p{Ll}]+$", unicode: true).hasMatch("abc"));
|
|
assertTrue(RegExp(r"^[\P{Lu}]+$", unicode: true).hasMatch("abc123"));
|
|
assertFalse(RegExp(r"^[\P{Lu}]+$", unicode: true).hasMatch("XYZ"));
|
|
assertTrue(RegExp(r"[\p{Math}]", unicode: true).hasMatch("+"));
|
|
assertTrue(RegExp(r"[\P{Bidi_M}]", unicode: true).hasMatch(" "));
|
|
assertTrue(RegExp(r"[\p{Hex}]", unicode: true).hasMatch("A"));
|
|
|
|
assertTrue(RegExp(r"^[^\P{Lu}]+$", unicode: true).hasMatch("XYZ"));
|
|
assertFalse(RegExp(r"^[^\p{Lu}\p{Ll}]+$", unicode: true).hasMatch("abc"));
|
|
assertFalse(RegExp(r"^[^\p{Lu}\p{Ll}]+$", unicode: true).hasMatch("ABC"));
|
|
assertTrue(RegExp(r"^[^\p{Lu}\p{Ll}]+$", unicode: true).hasMatch("123"));
|
|
assertTrue(RegExp(r"^[^\p{Lu}\P{Ll}]+$", unicode: true).hasMatch("abc"));
|
|
}
|