@markuplint/parser-utils 5.0.0-rc.0 → 5.0.0-rc.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +24 -0
- package/SKILL.md +1 -0
- package/docs/maintenance.ja.md +21 -0
- package/docs/maintenance.md +21 -0
- package/docs/parser-class.ja.md +11 -0
- package/docs/parser-class.md +11 -0
- package/lib/attr-tokenizer.d.ts +1 -0
- package/lib/attr-tokenizer.js +6 -1
- package/lib/const.js +1 -0
- package/lib/debugger.js +1 -1
- package/lib/get-location.d.ts +0 -8
- package/lib/get-location.js +0 -13
- package/lib/get-namespace.js +1 -1
- package/lib/ignore-block.js +4 -0
- package/lib/parser-error.d.ts +2 -43
- package/lib/parser-error.js +2 -47
- package/lib/parser.js +28 -11
- package/package.json +13 -9
package/CHANGELOG.md
CHANGED
|
@@ -3,6 +3,30 @@
|
|
|
3
3
|
All notable changes to this project will be documented in this file.
|
|
4
4
|
See [Conventional Commits](https://conventionalcommits.org) for commit guidelines.
|
|
5
5
|
|
|
6
|
+
# [5.0.0-rc.2](https://github.com/markuplint/markuplint/compare/v5.0.0-rc.1...v5.0.0-rc.2) (2026-04-15)
|
|
7
|
+
|
|
8
|
+
- fix(parser-utils)!: align unquoted attribute value tokenizer with HTML spec ([5168c04](https://github.com/markuplint/markuplint/commit/5168c041a1d37a7080f12e3c7569b5bbacd5a2f1))
|
|
9
|
+
- build!: remove ESLint and replace with oxlint ([1e0a337](https://github.com/markuplint/markuplint/commit/1e0a337707f76b903b16beeeb8c4d4fc0d8fc9e4))
|
|
10
|
+
- feat(parser-utils)!: remove deprecated getLine and getCol functions ([51cd7a2](https://github.com/markuplint/markuplint/commit/51cd7a28b7fcdd4a9d52d57f35c55b97b3b196fe))
|
|
11
|
+
|
|
12
|
+
### BREAKING CHANGES
|
|
13
|
+
|
|
14
|
+
- The default `endOfUnquotedValueChars` no longer includes `/`.
|
|
15
|
+
Unquoted attribute values preserve `/` as part of the value, matching the
|
|
16
|
+
WHATWG HTML "attribute value (unquoted) state". Consumers that relied on `/`
|
|
17
|
+
as a terminator must pass `endOfUnquotedValueChars: ['\t', '\n', '\f', '\r',
|
|
18
|
+
' ', '/', '>']` explicitly to `visitAttr()` / `attrTokenizer()`.
|
|
19
|
+
|
|
20
|
+
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
|
21
|
+
|
|
22
|
+
- ESLint is no longer used. Use oxlint instead.
|
|
23
|
+
- getLine() and getCol() have been removed.
|
|
24
|
+
Use getPosition() instead.
|
|
25
|
+
|
|
26
|
+
# [5.0.0-rc.1](https://github.com/markuplint/markuplint/compare/v5.0.0-rc.0...v5.0.0-rc.1) (2026-03-27)
|
|
27
|
+
|
|
28
|
+
**Note:** Version bump only for package @markuplint/parser-utils
|
|
29
|
+
|
|
6
30
|
# [5.0.0-rc.0](https://github.com/markuplint/markuplint/compare/v5.0.0-alpha.3...v5.0.0-rc.0) (2026-03-12)
|
|
7
31
|
|
|
8
32
|
**Note:** Version bump only for package @markuplint/parser-utils
|
package/SKILL.md
CHANGED
|
@@ -101,6 +101,7 @@ Customize attribute parsing behavior for a specific parser. Follow recipe #4 in
|
|
|
101
101
|
- `quoteSet` -- custom quote delimiters (e.g., `{` `}` for JSX)
|
|
102
102
|
- `startState` -- initial AttrState (usually `BeforeName`)
|
|
103
103
|
- `noQuoteValueType` -- value type for unquoted values
|
|
104
|
+
- `endOfUnquotedValueChars` -- characters that terminate an unquoted value (default: whitespace and `>`, matching the WHATWG HTML spec)
|
|
104
105
|
|
|
105
106
|
### Step 2: Post-process
|
|
106
107
|
|
package/docs/maintenance.ja.md
CHANGED
|
@@ -120,6 +120,27 @@ visitAttr(token: Token) {
|
|
|
120
120
|
}
|
|
121
121
|
```
|
|
122
122
|
|
|
123
|
+
#### 引用符なし属性値の終端文字のカスタマイズ
|
|
124
|
+
|
|
125
|
+
`endOfUnquotedValueChars` のデフォルトは WHATWG HTML の "attribute value (unquoted) state" に準拠し、空白類と `>` のみが値を終端する。`/` は値の一部として扱われる。
|
|
126
|
+
|
|
127
|
+
ホスト言語が異なる規則を要求する場合はカスタムリストを渡す:
|
|
128
|
+
|
|
129
|
+
```ts
|
|
130
|
+
// Pug: 文字による終端を無効化 — Pug レクサが属性境界を既に区切っている
|
|
131
|
+
super.visitAttr(token, {
|
|
132
|
+
quoteSet: [],
|
|
133
|
+
endOfUnquotedValueChars: [],
|
|
134
|
+
});
|
|
135
|
+
```
|
|
136
|
+
|
|
137
|
+
```ts
|
|
138
|
+
// `/` を終端文字として扱う(例: `a=x/>` を属性 `a="x"` + 自己閉じ `/>` として読む)
|
|
139
|
+
super.visitAttr(token, {
|
|
140
|
+
endOfUnquotedValueChars: ['\t', '\n', '\f', '\r', ' ', '/', '>'],
|
|
141
|
+
});
|
|
142
|
+
```
|
|
143
|
+
|
|
123
144
|
### 5. IDL属性マッピングの追加
|
|
124
145
|
|
|
125
146
|
IDL属性マップは `src/idl-attributes.ts` で定義されています。新しいマッピングを追加するには:
|
package/docs/maintenance.md
CHANGED
|
@@ -120,6 +120,27 @@ visitAttr(token: Token) {
|
|
|
120
120
|
}
|
|
121
121
|
```
|
|
122
122
|
|
|
123
|
+
#### Customizing Unquoted Value Terminators
|
|
124
|
+
|
|
125
|
+
The default `endOfUnquotedValueChars` follows the WHATWG HTML "attribute value (unquoted) state": only whitespace and `>` terminate the value. `/` is part of the value.
|
|
126
|
+
|
|
127
|
+
Pass a custom list when the host language requires different rules:
|
|
128
|
+
|
|
129
|
+
```ts
|
|
130
|
+
// Pug: never terminate by character — the Pug lexer already delimits attrs
|
|
131
|
+
super.visitAttr(token, {
|
|
132
|
+
quoteSet: [],
|
|
133
|
+
endOfUnquotedValueChars: [],
|
|
134
|
+
});
|
|
135
|
+
```
|
|
136
|
+
|
|
137
|
+
```ts
|
|
138
|
+
// Treat `/` as a terminator (e.g., to read `a=x/>` as attribute `a="x"` + self-closing `/>`)
|
|
139
|
+
super.visitAttr(token, {
|
|
140
|
+
endOfUnquotedValueChars: ['\t', '\n', '\f', '\r', ' ', '/', '>'],
|
|
141
|
+
});
|
|
142
|
+
```
|
|
143
|
+
|
|
123
144
|
### 5. Adding an IDL Attribute Mapping
|
|
124
145
|
|
|
125
146
|
The IDL attribute map is defined in `src/idl-attributes.ts`. To add a new mapping:
|
package/docs/parser-class.ja.md
CHANGED
|
@@ -282,6 +282,17 @@ visitAttr(
|
|
|
282
282
|
|
|
283
283
|
また、`visitSpreadAttr()` を通じてスプレッド属性の検出も試みます。
|
|
284
284
|
|
|
285
|
+
#### オプション
|
|
286
|
+
|
|
287
|
+
| オプション | デフォルト | 説明 |
|
|
288
|
+
| ------------------------- | -------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
289
|
+
| `quoteSet` | `[{ start: '"', end: '"', type: 'string' }, { start: "'", end: "'", type: 'string' }]` | 属性値として認識される引用符のセット。JSX / Vue / Svelte / Astro / MDX では `{` `}` を `type: 'script'` として追加する。 |
|
|
290
|
+
| `noQuoteValueType` | `'string'` | 引用符で囲まれていない値に割り当てられる値の型。 |
|
|
291
|
+
| `endOfUnquotedValueChars` | `['\t', '\n', '\f', '\r', ' ', '>']` | 引用符なし属性値を終端する文字。WHATWG HTML の "attribute value (unquoted) state" に準拠し、空白類と `>` のみ。`/` は終端ではなく値に含まれる(自己閉じの `/` は前段の before/after attribute name state で処理される)。終端判定を完全に無効化するには `[]` を渡す(Pug で利用)。 |
|
|
292
|
+
| `startState` | `AttrState.BeforeName` | 属性トークナイザの初期状態。JSX の `{...spread}` のような式のみの属性を扱う場合は `AttrState.BeforeValue` を指定する。 |
|
|
293
|
+
|
|
294
|
+
> 参照: [WHATWG HTML — attribute value (unquoted) state](<https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state>)
|
|
295
|
+
|
|
285
296
|
### visitSpreadAttr()
|
|
286
297
|
|
|
287
298
|
```ts
|
package/docs/parser-class.md
CHANGED
|
@@ -282,6 +282,17 @@ If the raw string contains multiple attributes, only the first is parsed and the
|
|
|
282
282
|
|
|
283
283
|
Also attempts to detect spread attributes via `visitSpreadAttr()`.
|
|
284
284
|
|
|
285
|
+
#### Options
|
|
286
|
+
|
|
287
|
+
| Option | Default | Description |
|
|
288
|
+
| ------------------------- | -------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
289
|
+
| `quoteSet` | `[{ start: '"', end: '"', type: 'string' }, { start: "'", end: "'", type: 'string' }]` | Quote delimiters recognized for the attribute value. Override to add expression delimiters such as `{` `}` (JSX / Vue / Svelte / Astro / MDX) with `type: 'script'`. |
|
|
290
|
+
| `noQuoteValueType` | `'string'` | Value type assigned when the value is unquoted. |
|
|
291
|
+
| `endOfUnquotedValueChars` | `['\t', '\n', '\f', '\r', ' ', '>']` | Characters that terminate an unquoted attribute value. Matches the WHATWG HTML "attribute value (unquoted) state" — whitespace and `>` only. `/` is NOT a terminator and is included in the value (self-closing `/` is handled earlier, in the before/after attribute name state). Pass `[]` to disable termination entirely (used by Pug). |
|
|
292
|
+
| `startState` | `AttrState.BeforeName` | Initial state of the attribute tokenizer. Use `AttrState.BeforeValue` to start directly at the value (e.g., for bare expression attributes like JSX `{...spread}`). |
|
|
293
|
+
|
|
294
|
+
> See: [WHATWG HTML — attribute value (unquoted) state](<https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state>)
|
|
295
|
+
|
|
285
296
|
### visitSpreadAttr()
|
|
286
297
|
|
|
287
298
|
```ts
|
package/lib/attr-tokenizer.d.ts
CHANGED
|
@@ -4,6 +4,7 @@ import { AttrState } from './enums.js';
|
|
|
4
4
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state
|
|
5
5
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state
|
|
6
6
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
|
|
7
|
+
* @see https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state
|
|
7
8
|
*/
|
|
8
9
|
export declare function attrTokenizer(raw: string, quoteSet?: readonly QuoteSet[], startState?: AttrState, noQuoteValueType?: ValueType, endOfUnquotedValueChars?: ReadonlyArray<string>): {
|
|
9
10
|
spacesBeforeAttrName: string;
|
package/lib/attr-tokenizer.js
CHANGED
|
@@ -11,8 +11,13 @@ const EQUAL = '=';
|
|
|
11
11
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#tag-name-state
|
|
12
12
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#before-attribute-name-state
|
|
13
13
|
* @see https://html.spec.whatwg.org/multipage/parsing.html#attribute-name-state
|
|
14
|
+
* @see https://html.spec.whatwg.org/multipage/parsing.html#attribute-value-(unquoted)-state
|
|
14
15
|
*/
|
|
15
|
-
export function attrTokenizer(raw, quoteSet = defaultQuoteSet, startState = AttrState.BeforeName, noQuoteValueType = 'string',
|
|
16
|
+
export function attrTokenizer(raw, quoteSet = defaultQuoteSet, startState = AttrState.BeforeName, noQuoteValueType = 'string',
|
|
17
|
+
// Default follows the spec referenced above: only whitespace and `>` terminate
|
|
18
|
+
// the value. `/` is handled by the outer tag tokenizer (before/after attribute
|
|
19
|
+
// name state), not here.
|
|
20
|
+
endOfUnquotedValueChars = [...defaultSpaces, '>']) {
|
|
16
21
|
let state = startState;
|
|
17
22
|
let spacesBeforeAttrName = '';
|
|
18
23
|
let attrName = '';
|
package/lib/const.js
CHANGED
|
@@ -94,6 +94,7 @@ export const svgElementList = [
|
|
|
94
94
|
'tref',
|
|
95
95
|
'vkern',
|
|
96
96
|
];
|
|
97
|
+
// eslint-disable-next-line no-control-regex -- WHATWG HTML spec requires matching NULL character
|
|
97
98
|
export const reTagName = /^[a-z][^\0\t\n\f />]*/i;
|
|
98
99
|
export const reSplitterTag = /<[^>]+>/g;
|
|
99
100
|
/**
|
package/lib/debugger.js
CHANGED
|
@@ -70,7 +70,7 @@ export function nodeTreeDebugView(nodeTree, idFilter = false) {
|
|
|
70
70
|
return;
|
|
71
71
|
}
|
|
72
72
|
lines.push(`${i.toString().padStart(3, '0')}: [${filter(n.uuid)}] ${' '.repeat(Math.max(n.depth, 0))}${n.type === 'endtag' ? '/' : ''}${n.nodeName}(${filter(n.uuid)})${n.type === 'starttag' && n.isGhost ? '[👻]' : ''}${n.type === 'starttag'
|
|
73
|
-
? ` => ${n.
|
|
73
|
+
? ` => ${n.pairNodeUuid ? `/${nodeTree.find(p => p.uuid === n.pairNodeUuid)?.nodeName ?? '?'}(${filter(n.pairNodeUuid)})` : '💀'}`
|
|
74
74
|
: ''}`);
|
|
75
75
|
if (n.type === 'starttag' || n.type === 'psblock') {
|
|
76
76
|
for (const c of n.childNodes ?? []) {
|
package/lib/get-location.d.ts
CHANGED
|
@@ -1,12 +1,4 @@
|
|
|
1
1
|
export { getPosition } from '@markuplint/shared';
|
|
2
|
-
/**
|
|
3
|
-
* @deprecated Use {@link getPosition} instead. Will be removed in v5.0.0.
|
|
4
|
-
*/
|
|
5
|
-
export declare function getLine(rawCodeFragment: string, startOffset: number): number;
|
|
6
|
-
/**
|
|
7
|
-
* @deprecated Use {@link getPosition} instead. Will be removed in v5.0.0.
|
|
8
|
-
*/
|
|
9
|
-
export declare function getCol(rawCodeFragment: string, startOffset: number): number;
|
|
10
2
|
export declare function getEndLine(rawCodeFragment: string, startLine: number): number;
|
|
11
3
|
export declare function getEndCol(rawCodeFragment: string, startCol: number): number;
|
|
12
4
|
/**
|
package/lib/get-location.js
CHANGED
|
@@ -1,18 +1,5 @@
|
|
|
1
1
|
export { getPosition } from '@markuplint/shared';
|
|
2
2
|
const LINE_BREAK = '\n';
|
|
3
|
-
/**
|
|
4
|
-
* @deprecated Use {@link getPosition} instead. Will be removed in v5.0.0.
|
|
5
|
-
*/
|
|
6
|
-
export function getLine(rawCodeFragment, startOffset) {
|
|
7
|
-
return rawCodeFragment.slice(0, startOffset).split(LINE_BREAK).length;
|
|
8
|
-
}
|
|
9
|
-
/**
|
|
10
|
-
* @deprecated Use {@link getPosition} instead. Will be removed in v5.0.0.
|
|
11
|
-
*/
|
|
12
|
-
export function getCol(rawCodeFragment, startOffset) {
|
|
13
|
-
const lines = rawCodeFragment.slice(0, startOffset).split(LINE_BREAK);
|
|
14
|
-
return (lines.at(-1) ?? '').length + 1;
|
|
15
|
-
}
|
|
16
3
|
export function getEndLine(rawCodeFragment, startLine) {
|
|
17
4
|
return rawCodeFragment.split(LINE_BREAK).length - 1 + startLine;
|
|
18
5
|
}
|
package/lib/get-namespace.js
CHANGED
package/lib/ignore-block.js
CHANGED
|
@@ -75,6 +75,7 @@ ignoreBlock, throwErrorWhenTagHasUnresolved = true) {
|
|
|
75
75
|
type: 'psblock',
|
|
76
76
|
depth: node.depth,
|
|
77
77
|
nodeName: `#ps:${tag.type}`,
|
|
78
|
+
parentNodeUuid: node.parentNode?.uuid ?? null,
|
|
78
79
|
parentNode: node.parentNode,
|
|
79
80
|
childNodes: [],
|
|
80
81
|
blockBehavior: null,
|
|
@@ -94,6 +95,7 @@ ignoreBlock, throwErrorWhenTagHasUnresolved = true) {
|
|
|
94
95
|
...token,
|
|
95
96
|
nodeName: '#text',
|
|
96
97
|
type: 'text',
|
|
98
|
+
parentNodeUuid: node.parentNode?.uuid ?? null,
|
|
97
99
|
parentNode: node.parentNode,
|
|
98
100
|
depth: node.depth,
|
|
99
101
|
};
|
|
@@ -106,6 +108,7 @@ ignoreBlock, throwErrorWhenTagHasUnresolved = true) {
|
|
|
106
108
|
type: 'psblock',
|
|
107
109
|
depth: node.depth,
|
|
108
110
|
nodeName: `#ps:${tag.type}`,
|
|
111
|
+
parentNodeUuid: node.parentNode?.uuid ?? null,
|
|
109
112
|
parentNode: node.parentNode,
|
|
110
113
|
childNodes: [],
|
|
111
114
|
blockBehavior: null,
|
|
@@ -120,6 +123,7 @@ ignoreBlock, throwErrorWhenTagHasUnresolved = true) {
|
|
|
120
123
|
...token,
|
|
121
124
|
nodeName: '#text',
|
|
122
125
|
type: 'text',
|
|
126
|
+
parentNodeUuid: node.parentNode?.uuid ?? null,
|
|
123
127
|
parentNode: node.parentNode,
|
|
124
128
|
depth: node.depth,
|
|
125
129
|
};
|
package/lib/parser-error.d.ts
CHANGED
|
@@ -1,43 +1,2 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
* used to construct meaningful error messages with source locations.
|
|
4
|
-
*/
|
|
5
|
-
export type ParserErrorInfo = {
|
|
6
|
-
readonly line?: number;
|
|
7
|
-
readonly col?: number;
|
|
8
|
-
readonly raw?: string;
|
|
9
|
-
readonly stack?: string;
|
|
10
|
-
};
|
|
11
|
-
/**
|
|
12
|
-
* An error that occurs during parsing, carrying the source line, column,
|
|
13
|
-
* and raw text where the error was encountered.
|
|
14
|
-
*/
|
|
15
|
-
export declare class ParserError extends Error {
|
|
16
|
-
readonly col: number;
|
|
17
|
-
readonly line: number;
|
|
18
|
-
name: string;
|
|
19
|
-
readonly raw: string;
|
|
20
|
-
constructor(message: string, info: ParserErrorInfo);
|
|
21
|
-
}
|
|
22
|
-
/**
|
|
23
|
-
* A parser error specific to a particular HTML element, including
|
|
24
|
-
* the node name of the element that caused the error in the message.
|
|
25
|
-
*/
|
|
26
|
-
export declare class TargetParserError extends ParserError {
|
|
27
|
-
name: string;
|
|
28
|
-
readonly nodeName: string | null;
|
|
29
|
-
constructor(message: string, info: ParserErrorInfo & {
|
|
30
|
-
readonly nodeName?: string | null;
|
|
31
|
-
});
|
|
32
|
-
}
|
|
33
|
-
/**
|
|
34
|
-
* A parser error that occurs while reading a configuration file,
|
|
35
|
-
* including the file path in the error message for easier debugging.
|
|
36
|
-
*/
|
|
37
|
-
export declare class ConfigParserError extends ParserError {
|
|
38
|
-
readonly filePath: string;
|
|
39
|
-
name: string;
|
|
40
|
-
constructor(message: string, info: ParserErrorInfo & {
|
|
41
|
-
readonly filePath: string;
|
|
42
|
-
});
|
|
43
|
-
}
|
|
1
|
+
export { ConfigParserError, ParserError, TargetParserError } from '@markuplint/shared';
|
|
2
|
+
export type { ParserErrorInfo } from '@markuplint/shared';
|
package/lib/parser-error.js
CHANGED
|
@@ -1,47 +1,2 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
* and raw text where the error was encountered.
|
|
4
|
-
*/
|
|
5
|
-
export class ParserError extends Error {
|
|
6
|
-
col;
|
|
7
|
-
line;
|
|
8
|
-
name = 'ParserError';
|
|
9
|
-
raw;
|
|
10
|
-
constructor(message, info) {
|
|
11
|
-
super(message);
|
|
12
|
-
this.line = info.line ?? 1;
|
|
13
|
-
this.col = info.col ?? 0;
|
|
14
|
-
this.raw = info.raw ?? '';
|
|
15
|
-
this.stack = info.stack ?? this.stack;
|
|
16
|
-
}
|
|
17
|
-
}
|
|
18
|
-
/**
|
|
19
|
-
* A parser error specific to a particular HTML element, including
|
|
20
|
-
* the node name of the element that caused the error in the message.
|
|
21
|
-
*/
|
|
22
|
-
export class TargetParserError extends ParserError {
|
|
23
|
-
name = 'TargetParserError';
|
|
24
|
-
nodeName;
|
|
25
|
-
constructor(message, info) {
|
|
26
|
-
const errMsg = info.nodeName
|
|
27
|
-
? `The ${info.nodeName} is invalid element (${info.line}:${info.col}): ${message}`
|
|
28
|
-
: message;
|
|
29
|
-
super(errMsg, info);
|
|
30
|
-
this.nodeName = info.nodeName ?? null;
|
|
31
|
-
}
|
|
32
|
-
}
|
|
33
|
-
/**
|
|
34
|
-
* A parser error that occurs while reading a configuration file,
|
|
35
|
-
* including the file path in the error message for easier debugging.
|
|
36
|
-
*/
|
|
37
|
-
export class ConfigParserError extends ParserError {
|
|
38
|
-
filePath;
|
|
39
|
-
name = 'ConfigParserError';
|
|
40
|
-
constructor(message, info) {
|
|
41
|
-
const pos = info.line != null && info.line != null ? `(${info.line}:${info.col})` : '';
|
|
42
|
-
const file = ` in ${info.filePath}${pos}`;
|
|
43
|
-
const errMsg = `${message}${file}`;
|
|
44
|
-
super(errMsg, info);
|
|
45
|
-
this.filePath = info.filePath;
|
|
46
|
-
}
|
|
47
|
-
}
|
|
1
|
+
// Re-export from @markuplint/shared — these classes are now defined there.
|
|
2
|
+
export { ConfigParserError, ParserError, TargetParserError } from '@markuplint/shared';
|
package/lib/parser.js
CHANGED
|
@@ -196,6 +196,13 @@ export class Parser {
|
|
|
196
196
|
}
|
|
197
197
|
nodeList = [fmNode, ...newNodeList];
|
|
198
198
|
}
|
|
199
|
+
timer.push('removeCircularRefs');
|
|
200
|
+
// Remove circular object references (parentNodeUuid/pairNodeUuid are already set)
|
|
201
|
+
for (const node of nodeList) {
|
|
202
|
+
const n = node;
|
|
203
|
+
delete n.parentNode;
|
|
204
|
+
delete n.pairNode;
|
|
205
|
+
}
|
|
199
206
|
timer.log();
|
|
200
207
|
domLog(nodeList);
|
|
201
208
|
this.#reset();
|
|
@@ -381,6 +388,7 @@ export class Parser {
|
|
|
381
388
|
...this.createToken(token),
|
|
382
389
|
type: 'doctype',
|
|
383
390
|
nodeName: '#doctype',
|
|
391
|
+
parentNodeUuid: token.parentNode?.uuid ?? null,
|
|
384
392
|
};
|
|
385
393
|
return [node];
|
|
386
394
|
}
|
|
@@ -401,6 +409,7 @@ export class Parser {
|
|
|
401
409
|
type: 'comment',
|
|
402
410
|
nodeName: '#comment',
|
|
403
411
|
isBogus,
|
|
412
|
+
parentNodeUuid: token.parentNode?.uuid ?? null,
|
|
404
413
|
};
|
|
405
414
|
return [node];
|
|
406
415
|
}
|
|
@@ -419,6 +428,7 @@ export class Parser {
|
|
|
419
428
|
...this.createToken(token),
|
|
420
429
|
type: 'text',
|
|
421
430
|
nodeName: '#text',
|
|
431
|
+
parentNodeUuid: token.parentNode?.uuid ?? null,
|
|
422
432
|
};
|
|
423
433
|
if (options?.researchTags) {
|
|
424
434
|
const nodes = this.parseCodeFragment(token);
|
|
@@ -457,7 +467,9 @@ export class Parser {
|
|
|
457
467
|
childNodes: [],
|
|
458
468
|
blockBehavior: null,
|
|
459
469
|
parentNode: token.parentNode,
|
|
470
|
+
parentNodeUuid: token.parentNode?.uuid ?? null,
|
|
460
471
|
pairNode: null,
|
|
472
|
+
pairNodeUuid: null,
|
|
461
473
|
tagCloseChar: '',
|
|
462
474
|
tagOpenChar: '',
|
|
463
475
|
isGhost: true,
|
|
@@ -504,6 +516,7 @@ export class Parser {
|
|
|
504
516
|
nodeName: `#ps:${token.nodeName}`,
|
|
505
517
|
childNodes: [],
|
|
506
518
|
isBogus: false,
|
|
519
|
+
parentNodeUuid: token.parentNode?.uuid ?? null,
|
|
507
520
|
};
|
|
508
521
|
const siblings = this.visitChildren(childNodes, block);
|
|
509
522
|
return [block, ...siblings];
|
|
@@ -664,6 +677,7 @@ export class Parser {
|
|
|
664
677
|
depth,
|
|
665
678
|
nodeName: '#text',
|
|
666
679
|
parentNode: null,
|
|
680
|
+
parentNodeUuid: null,
|
|
667
681
|
};
|
|
668
682
|
nodes.push(textNode);
|
|
669
683
|
}
|
|
@@ -853,7 +867,7 @@ export class Parser {
|
|
|
853
867
|
const newChildNodes = [...parentNode.childNodes];
|
|
854
868
|
for (const appendingChild of childNodes) {
|
|
855
869
|
const currentIndex = parentNode.childNodes.findIndex(n => n.uuid === appendingChild.uuid);
|
|
856
|
-
Object.assign(appendingChild, { parentNode });
|
|
870
|
+
Object.assign(appendingChild, { parentNode, parentNodeUuid: parentNode.uuid });
|
|
857
871
|
if (currentIndex === -1) {
|
|
858
872
|
newChildNodes.push(appendingChild);
|
|
859
873
|
continue;
|
|
@@ -921,9 +935,9 @@ export class Parser {
|
|
|
921
935
|
raw: nodes.map(n => n.raw).join(''),
|
|
922
936
|
};
|
|
923
937
|
for (const node of nodes) {
|
|
924
|
-
this.#removeChild(node.parentNode, node);
|
|
938
|
+
this.#removeChild(node.parentNode ?? null, node);
|
|
925
939
|
}
|
|
926
|
-
this.appendChild(textNode.parentNode, textNode);
|
|
940
|
+
this.appendChild(textNode.parentNode ?? null, textNode);
|
|
927
941
|
return textNode;
|
|
928
942
|
}
|
|
929
943
|
#convertIntoInvalidNode(node) {
|
|
@@ -986,7 +1000,7 @@ export class Parser {
|
|
|
986
1000
|
const prevEndOffset = sequentailPrevNode
|
|
987
1001
|
? sequentailPrevNode.offset + sequentailPrevNode.raw.length
|
|
988
1002
|
: 0;
|
|
989
|
-
const remnantNodes = this.#createRemnantNode(prevEndOffset, node.offset, node.depth, node.parentNode, invalidNode, whitespace);
|
|
1003
|
+
const remnantNodes = this.#createRemnantNode(prevEndOffset, node.offset, node.depth, node.parentNode ?? null, invalidNode, whitespace);
|
|
990
1004
|
if (remnantNodes) {
|
|
991
1005
|
newNodeList.push(...remnantNodes);
|
|
992
1006
|
}
|
|
@@ -997,7 +1011,7 @@ export class Parser {
|
|
|
997
1011
|
if (!lastNode) {
|
|
998
1012
|
return newNodeList;
|
|
999
1013
|
}
|
|
1000
|
-
const remnantNodes = this.#createRemnantNode(lastNode.offset + lastNode.raw.length, undefined, lastNode.depth, lastNode.parentNode, invalidNode, whitespace);
|
|
1014
|
+
const remnantNodes = this.#createRemnantNode(lastNode.offset + lastNode.raw.length, undefined, lastNode.depth, lastNode.parentNode ?? null, invalidNode, whitespace);
|
|
1001
1015
|
if (!remnantNodes) {
|
|
1002
1016
|
return newNodeList;
|
|
1003
1017
|
}
|
|
@@ -1020,12 +1034,12 @@ export class Parser {
|
|
|
1020
1034
|
* @returns `true` if `node` is a descendant of `potentialAncestor`.
|
|
1021
1035
|
*/
|
|
1022
1036
|
#isDescendantOf(node, potentialAncestor) {
|
|
1023
|
-
let current = 'parentNode' in node ? node.parentNode : null;
|
|
1037
|
+
let current = 'parentNode' in node ? (node.parentNode ?? null) : null;
|
|
1024
1038
|
while (current) {
|
|
1025
1039
|
if (current === potentialAncestor) {
|
|
1026
1040
|
return true;
|
|
1027
1041
|
}
|
|
1028
|
-
current = current.parentNode;
|
|
1042
|
+
current = current.parentNode ?? null;
|
|
1029
1043
|
}
|
|
1030
1044
|
return false;
|
|
1031
1045
|
}
|
|
@@ -1034,7 +1048,7 @@ export class Parser {
|
|
|
1034
1048
|
for (let node of nodeList) {
|
|
1035
1049
|
if (node.type === 'endtag') {
|
|
1036
1050
|
const endTagUUID = node.uuid;
|
|
1037
|
-
const openTag = newNodeList.findLast((n) => n.type === 'starttag' && !n.isGhost ? n.
|
|
1051
|
+
const openTag = newNodeList.findLast((n) => n.type === 'starttag' && !n.isGhost ? n.pairNodeUuid === endTagUUID : false);
|
|
1038
1052
|
if (!openTag) {
|
|
1039
1053
|
node = this.#convertIntoInvalidNode(node);
|
|
1040
1054
|
}
|
|
@@ -1044,9 +1058,9 @@ export class Parser {
|
|
|
1044
1058
|
return newNodeList;
|
|
1045
1059
|
}
|
|
1046
1060
|
#pairing(startTag, endTag) {
|
|
1047
|
-
Object.assign(startTag, { pairNode: endTag });
|
|
1048
|
-
Object.assign(endTag, { pairNode: startTag });
|
|
1049
|
-
this.appendChild(startTag.parentNode, endTag);
|
|
1061
|
+
Object.assign(startTag, { pairNode: endTag, pairNodeUuid: endTag.uuid });
|
|
1062
|
+
Object.assign(endTag, { pairNode: startTag, pairNodeUuid: startTag.uuid });
|
|
1063
|
+
this.appendChild(startTag.parentNode ?? null, endTag);
|
|
1050
1064
|
}
|
|
1051
1065
|
#parseEndTag(token, namelessFragment) {
|
|
1052
1066
|
const parsed = this.#parseTag(token, true, false, namelessFragment);
|
|
@@ -1219,6 +1233,7 @@ export class Parser {
|
|
|
1219
1233
|
depth,
|
|
1220
1234
|
nodeName: isFragment ? '#jsx-fragment' : tagName,
|
|
1221
1235
|
parentNode: null,
|
|
1236
|
+
parentNodeUuid: null,
|
|
1222
1237
|
};
|
|
1223
1238
|
const tag = isOpenTag
|
|
1224
1239
|
? {
|
|
@@ -1232,6 +1247,7 @@ export class Parser {
|
|
|
1232
1247
|
attributes: attrs,
|
|
1233
1248
|
childNodes: [],
|
|
1234
1249
|
pairNode: null,
|
|
1250
|
+
pairNodeUuid: null,
|
|
1235
1251
|
tagOpenChar: '<',
|
|
1236
1252
|
tagCloseChar: selfClosingSolidusChar + '>',
|
|
1237
1253
|
blockBehavior: null,
|
|
@@ -1243,6 +1259,7 @@ export class Parser {
|
|
|
1243
1259
|
...commons,
|
|
1244
1260
|
type: 'endtag',
|
|
1245
1261
|
pairNode: {},
|
|
1262
|
+
pairNodeUuid: null,
|
|
1246
1263
|
tagOpenChar: '</',
|
|
1247
1264
|
tagCloseChar: '>',
|
|
1248
1265
|
};
|
package/package.json
CHANGED
|
@@ -1,8 +1,12 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@markuplint/parser-utils",
|
|
3
|
-
"version": "5.0.0-rc.
|
|
3
|
+
"version": "5.0.0-rc.2",
|
|
4
4
|
"description": "Utility module for markuplint parser plugin",
|
|
5
|
-
"repository":
|
|
5
|
+
"repository": {
|
|
6
|
+
"type": "git",
|
|
7
|
+
"url": "https://github.com/markuplint/markuplint.git",
|
|
8
|
+
"directory": "packages/@markuplint/parser-utils"
|
|
9
|
+
},
|
|
6
10
|
"author": "Yusuke Hirao <yusukehirao@me.com>",
|
|
7
11
|
"license": "MIT",
|
|
8
12
|
"engines": {
|
|
@@ -31,16 +35,16 @@
|
|
|
31
35
|
"clean": "tsc --build --clean tsconfig.build.json"
|
|
32
36
|
},
|
|
33
37
|
"dependencies": {
|
|
34
|
-
"@markuplint/ml-ast": "5.0.0-rc.
|
|
35
|
-
"@markuplint/ml-spec": "5.0.0-rc.
|
|
36
|
-
"@markuplint/shared": "5.0.0-rc.
|
|
37
|
-
"@markuplint/types": "5.0.0-rc.
|
|
38
|
+
"@markuplint/ml-ast": "5.0.0-rc.2",
|
|
39
|
+
"@markuplint/ml-spec": "5.0.0-rc.2",
|
|
40
|
+
"@markuplint/shared": "5.0.0-rc.2",
|
|
41
|
+
"@markuplint/types": "5.0.0-rc.2",
|
|
38
42
|
"debug": "4.4.3",
|
|
39
43
|
"espree": "11.2.0",
|
|
40
|
-
"type-fest": "5.
|
|
44
|
+
"type-fest": "5.5.0"
|
|
41
45
|
},
|
|
42
46
|
"devDependencies": {
|
|
43
|
-
"@typescript-eslint/typescript-estree": "8.
|
|
47
|
+
"@typescript-eslint/typescript-estree": "8.58.2"
|
|
44
48
|
},
|
|
45
|
-
"gitHead": "
|
|
49
|
+
"gitHead": "e43763858d9234c417053becc73dbd088c1e7ea6"
|
|
46
50
|
}
|