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>
111 lines
5.2 KiB
Dart
111 lines
5.2 KiB
Dart
// Copyright (c) 2019, the Dart project authors. All rights reserved.
|
|
// Copyright 2016 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() {
|
|
void t(RegExp re, String s) {
|
|
assertTrue(re.hasMatch(s));
|
|
}
|
|
|
|
void f(RegExp re, String s) {
|
|
assertFalse(re.hasMatch(s));
|
|
}
|
|
|
|
t(RegExp(r"\p{ASCII}+", unicode: true), "abc123");
|
|
f(RegExp(r"\p{ASCII}+", unicode: true), "ⓐⓑⓒ①②③");
|
|
f(RegExp(r"\p{ASCII}+", unicode: true), "🄰🄱🄲①②③");
|
|
f(RegExp(r"\P{ASCII}+", unicode: true), "abcd123");
|
|
t(RegExp(r"\P{ASCII}+", unicode: true), "ⓐⓑⓒ①②③");
|
|
t(RegExp(r"\P{ASCII}+", unicode: true), "🄰🄱🄲①②③");
|
|
|
|
f(RegExp(r"[^\p{ASCII}]+", unicode: true), "abc123");
|
|
f(RegExp(r"[\p{ASCII}]+", unicode: true), "ⓐⓑⓒ①②③");
|
|
f(RegExp(r"[\p{ASCII}]+", unicode: true), "🄰🄱🄲①②③");
|
|
t(RegExp(r"[^\P{ASCII}]+", unicode: true), "abcd123");
|
|
t(RegExp(r"[\P{ASCII}]+", unicode: true), "ⓐⓑⓒ①②③");
|
|
f(RegExp(r"[^\P{ASCII}]+", unicode: true), "🄰🄱🄲①②③");
|
|
|
|
t(RegExp(r"\p{Any}+", unicode: true), "🄰🄱🄲①②③");
|
|
|
|
shouldBe(
|
|
RegExp(r"\p{Any}", unicode: true).firstMatch("\ud800\ud801"), ["\ud800"]);
|
|
shouldBe(
|
|
RegExp(r"\p{Any}", unicode: true).firstMatch("\udc00\udc01"), ["\udc00"]);
|
|
shouldBe(RegExp(r"\p{Any}", unicode: true).firstMatch("\ud800\udc01"),
|
|
["\ud800\udc01"]);
|
|
shouldBe(RegExp(r"\p{Any}", unicode: true).firstMatch("\udc01"), ["\udc01"]);
|
|
|
|
f(RegExp(r"\P{Any}+", unicode: true), "123");
|
|
f(RegExp(r"[\P{Any}]+", unicode: true), "123");
|
|
t(RegExp(r"[\P{Any}\d]+", unicode: true), "123");
|
|
t(RegExp(r"[^\P{Any}]+", unicode: true), "123");
|
|
|
|
t(RegExp(r"\p{Assigned}+", unicode: true), "123");
|
|
t(RegExp(r"\p{Assigned}+", unicode: true), "🄰🄱🄲");
|
|
f(RegExp(r"\p{Assigned}+", unicode: true), "\ufdd0");
|
|
f(RegExp(r"\p{Assigned}+", unicode: true), "\u{fffff}");
|
|
|
|
f(RegExp(r"\P{Assigned}+", unicode: true), "123");
|
|
f(RegExp(r"\P{Assigned}+", unicode: true), "🄰🄱🄲");
|
|
t(RegExp(r"\P{Assigned}+", unicode: true), "\ufdd0");
|
|
t(RegExp(r"\P{Assigned}+", unicode: true), "\u{fffff}");
|
|
f(RegExp(r"\P{Assigned}", unicode: true), "");
|
|
|
|
t(RegExp(r"[^\P{Assigned}]+", unicode: true), "123");
|
|
f(RegExp(r"[\P{Assigned}]+", unicode: true), "🄰🄱🄲");
|
|
f(RegExp(r"[^\P{Assigned}]+", unicode: true), "\ufdd0");
|
|
t(RegExp(r"[\P{Assigned}]+", unicode: true), "\u{fffff}");
|
|
f(RegExp(r"[\P{Assigned}]", unicode: true), "");
|
|
|
|
f(RegExp(r"[^\u1234\p{ASCII}]+", unicode: true), "\u1234");
|
|
t(RegExp(r"[x\P{ASCII}]+", unicode: true), "x");
|
|
t(RegExp(r"[\u1234\p{ASCII}]+", unicode: true), "\u1234");
|
|
|
|
// Contributory binary properties are not supported.
|
|
assertThrows(() => RegExp("\\p{Other_Alphabetic}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OAlpha}", unicode: true));
|
|
assertThrows(
|
|
() => RegExp("\\p{Other_Default_Ignorable_Code_Point}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{ODI}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_Grapheme_Extend}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OGr_Ext}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_ID_Continue}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OIDC}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_ID_Start}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OIDS}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_Lowercase}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OLower}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_Math}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OMath}", unicode: true));
|
|
assertThrows(() => RegExp("\\p{Other_Uppercase}", unicode: true));
|
|
assertThrows(() => RegExp("\\P{OUpper}", unicode: true));
|
|
}
|