no-misleading-character-class.js
6.24 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
/**
* @author Toru Nagashima <https://github.com/mysticatea>
*/
"use strict";
const { CALL, CONSTRUCT, ReferenceTracker, getStringIfConstant } = require("eslint-utils");
const { RegExpParser, visitRegExpAST } = require("regexpp");
const { isCombiningCharacter, isEmojiModifier, isRegionalIndicatorSymbol, isSurrogatePair } = require("./utils/unicode");
//------------------------------------------------------------------------------
// Helpers
//------------------------------------------------------------------------------
/**
* Iterate character sequences of a given nodes.
*
* CharacterClassRange syntax can steal a part of character sequence,
* so this function reverts CharacterClassRange syntax and restore the sequence.
* @param {regexpp.AST.CharacterClassElement[]} nodes The node list to iterate character sequences.
* @returns {IterableIterator<number[]>} The list of character sequences.
*/
function *iterateCharacterSequence(nodes) {
let seq = [];
for (const node of nodes) {
switch (node.type) {
case "Character":
seq.push(node.value);
break;
case "CharacterClassRange":
seq.push(node.min.value);
yield seq;
seq = [node.max.value];
break;
case "CharacterSet":
if (seq.length > 0) {
yield seq;
seq = [];
}
break;
// no default
}
}
if (seq.length > 0) {
yield seq;
}
}
const hasCharacterSequence = {
surrogatePairWithoutUFlag(chars) {
return chars.some((c, i) => i !== 0 && isSurrogatePair(chars[i - 1], c));
},
combiningClass(chars) {
return chars.some((c, i) => (
i !== 0 &&
isCombiningCharacter(c) &&
!isCombiningCharacter(chars[i - 1])
));
},
emojiModifier(chars) {
return chars.some((c, i) => (
i !== 0 &&
isEmojiModifier(c) &&
!isEmojiModifier(chars[i - 1])
));
},
regionalIndicatorSymbol(chars) {
return chars.some((c, i) => (
i !== 0 &&
isRegionalIndicatorSymbol(c) &&
isRegionalIndicatorSymbol(chars[i - 1])
));
},
zwj(chars) {
const lastIndex = chars.length - 1;
return chars.some((c, i) => (
i !== 0 &&
i !== lastIndex &&
c === 0x200d &&
chars[i - 1] !== 0x200d &&
chars[i + 1] !== 0x200d
));
}
};
const kinds = Object.keys(hasCharacterSequence);
//------------------------------------------------------------------------------
// Rule Definition
//------------------------------------------------------------------------------
module.exports = {
meta: {
type: "problem",
docs: {
description: "disallow characters which are made with multiple code points in character class syntax",
category: "Possible Errors",
recommended: true,
url: "https://eslint.org/docs/rules/no-misleading-character-class"
},
schema: [],
messages: {
surrogatePairWithoutUFlag: "Unexpected surrogate pair in character class. Use 'u' flag.",
combiningClass: "Unexpected combined character in character class.",
emojiModifier: "Unexpected modified Emoji in character class.",
regionalIndicatorSymbol: "Unexpected national flag in character class.",
zwj: "Unexpected joined character sequence in character class."
}
},
create(context) {
const parser = new RegExpParser();
/**
* Verify a given regular expression.
* @param {Node} node The node to report.
* @param {string} pattern The regular expression pattern to verify.
* @param {string} flags The flags of the regular expression.
* @returns {void}
*/
function verify(node, pattern, flags) {
const has = {
surrogatePairWithoutUFlag: false,
combiningClass: false,
variationSelector: false,
emojiModifier: false,
regionalIndicatorSymbol: false,
zwj: false
};
let patternNode;
try {
patternNode = parser.parsePattern(
pattern,
0,
pattern.length,
flags.includes("u")
);
} catch (e) {
// Ignore regular expressions with syntax errors
return;
}
visitRegExpAST(patternNode, {
onCharacterClassEnter(ccNode) {
for (const chars of iterateCharacterSequence(ccNode.elements)) {
for (const kind of kinds) {
has[kind] = has[kind] || hasCharacterSequence[kind](chars);
}
}
}
});
for (const kind of kinds) {
if (has[kind]) {
context.report({ node, messageId: kind });
}
}
}
return {
"Literal[regex]"(node) {
verify(node, node.regex.pattern, node.regex.flags);
},
"Program"() {
const scope = context.getScope();
const tracker = new ReferenceTracker(scope);
/*
* Iterate calls of RegExp.
* E.g., `new RegExp()`, `RegExp()`, `new window.RegExp()`,
* `const {RegExp: a} = window; new a()`, etc...
*/
for (const { node } of tracker.iterateGlobalReferences({
RegExp: { [CALL]: true, [CONSTRUCT]: true }
})) {
const [patternNode, flagsNode] = node.arguments;
const pattern = getStringIfConstant(patternNode, scope);
const flags = getStringIfConstant(flagsNode, scope);
if (typeof pattern === "string") {
verify(node, pattern, flags || "");
}
}
}
};
}
};