mirror of
https://github.com/Funkoala14/knowledgebase_law.git
synced 2025-06-08 20:48:15 +08:00
241 lines
7.0 KiB
JavaScript
241 lines
7.0 KiB
JavaScript
/**
|
||
* @import {
|
||
* Code,
|
||
* Construct,
|
||
* Event,
|
||
* Point,
|
||
* Resolver,
|
||
* State,
|
||
* TokenizeContext,
|
||
* Tokenizer,
|
||
* Token
|
||
* } from 'micromark-util-types'
|
||
*/
|
||
|
||
import { push, splice } from 'micromark-util-chunked';
|
||
import { classifyCharacter } from 'micromark-util-classify-character';
|
||
import { resolveAll } from 'micromark-util-resolve-all';
|
||
/** @type {Construct} */
|
||
export const attention = {
|
||
name: 'attention',
|
||
resolveAll: resolveAllAttention,
|
||
tokenize: tokenizeAttention
|
||
};
|
||
|
||
/**
|
||
* Take all events and resolve attention to emphasis or strong.
|
||
*
|
||
* @type {Resolver}
|
||
*/
|
||
// eslint-disable-next-line complexity
|
||
function resolveAllAttention(events, context) {
|
||
let index = -1;
|
||
/** @type {number} */
|
||
let open;
|
||
/** @type {Token} */
|
||
let group;
|
||
/** @type {Token} */
|
||
let text;
|
||
/** @type {Token} */
|
||
let openingSequence;
|
||
/** @type {Token} */
|
||
let closingSequence;
|
||
/** @type {number} */
|
||
let use;
|
||
/** @type {Array<Event>} */
|
||
let nextEvents;
|
||
/** @type {number} */
|
||
let offset;
|
||
|
||
// Walk through all events.
|
||
//
|
||
// Note: performance of this is fine on an mb of normal markdown, but it’s
|
||
// a bottleneck for malicious stuff.
|
||
while (++index < events.length) {
|
||
// Find a token that can close.
|
||
if (events[index][0] === 'enter' && events[index][1].type === 'attentionSequence' && events[index][1]._close) {
|
||
open = index;
|
||
|
||
// Now walk back to find an opener.
|
||
while (open--) {
|
||
// Find a token that can open the closer.
|
||
if (events[open][0] === 'exit' && events[open][1].type === 'attentionSequence' && events[open][1]._open &&
|
||
// If the markers are the same:
|
||
context.sliceSerialize(events[open][1]).charCodeAt(0) === context.sliceSerialize(events[index][1]).charCodeAt(0)) {
|
||
// If the opening can close or the closing can open,
|
||
// and the close size *is not* a multiple of three,
|
||
// but the sum of the opening and closing size *is* multiple of three,
|
||
// then don’t match.
|
||
if ((events[open][1]._close || events[index][1]._open) && (events[index][1].end.offset - events[index][1].start.offset) % 3 && !((events[open][1].end.offset - events[open][1].start.offset + events[index][1].end.offset - events[index][1].start.offset) % 3)) {
|
||
continue;
|
||
}
|
||
|
||
// Number of markers to use from the sequence.
|
||
use = events[open][1].end.offset - events[open][1].start.offset > 1 && events[index][1].end.offset - events[index][1].start.offset > 1 ? 2 : 1;
|
||
const start = {
|
||
...events[open][1].end
|
||
};
|
||
const end = {
|
||
...events[index][1].start
|
||
};
|
||
movePoint(start, -use);
|
||
movePoint(end, use);
|
||
openingSequence = {
|
||
type: use > 1 ? "strongSequence" : "emphasisSequence",
|
||
start,
|
||
end: {
|
||
...events[open][1].end
|
||
}
|
||
};
|
||
closingSequence = {
|
||
type: use > 1 ? "strongSequence" : "emphasisSequence",
|
||
start: {
|
||
...events[index][1].start
|
||
},
|
||
end
|
||
};
|
||
text = {
|
||
type: use > 1 ? "strongText" : "emphasisText",
|
||
start: {
|
||
...events[open][1].end
|
||
},
|
||
end: {
|
||
...events[index][1].start
|
||
}
|
||
};
|
||
group = {
|
||
type: use > 1 ? "strong" : "emphasis",
|
||
start: {
|
||
...openingSequence.start
|
||
},
|
||
end: {
|
||
...closingSequence.end
|
||
}
|
||
};
|
||
events[open][1].end = {
|
||
...openingSequence.start
|
||
};
|
||
events[index][1].start = {
|
||
...closingSequence.end
|
||
};
|
||
nextEvents = [];
|
||
|
||
// If there are more markers in the opening, add them before.
|
||
if (events[open][1].end.offset - events[open][1].start.offset) {
|
||
nextEvents = push(nextEvents, [['enter', events[open][1], context], ['exit', events[open][1], context]]);
|
||
}
|
||
|
||
// Opening.
|
||
nextEvents = push(nextEvents, [['enter', group, context], ['enter', openingSequence, context], ['exit', openingSequence, context], ['enter', text, context]]);
|
||
|
||
// Always populated by defaults.
|
||
|
||
// Between.
|
||
nextEvents = push(nextEvents, resolveAll(context.parser.constructs.insideSpan.null, events.slice(open + 1, index), context));
|
||
|
||
// Closing.
|
||
nextEvents = push(nextEvents, [['exit', text, context], ['enter', closingSequence, context], ['exit', closingSequence, context], ['exit', group, context]]);
|
||
|
||
// If there are more markers in the closing, add them after.
|
||
if (events[index][1].end.offset - events[index][1].start.offset) {
|
||
offset = 2;
|
||
nextEvents = push(nextEvents, [['enter', events[index][1], context], ['exit', events[index][1], context]]);
|
||
} else {
|
||
offset = 0;
|
||
}
|
||
splice(events, open - 1, index - open + 3, nextEvents);
|
||
index = open + nextEvents.length - offset - 2;
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
// Remove remaining sequences.
|
||
index = -1;
|
||
while (++index < events.length) {
|
||
if (events[index][1].type === 'attentionSequence') {
|
||
events[index][1].type = 'data';
|
||
}
|
||
}
|
||
return events;
|
||
}
|
||
|
||
/**
|
||
* @this {TokenizeContext}
|
||
* Context.
|
||
* @type {Tokenizer}
|
||
*/
|
||
function tokenizeAttention(effects, ok) {
|
||
const attentionMarkers = this.parser.constructs.attentionMarkers.null;
|
||
const previous = this.previous;
|
||
const before = classifyCharacter(previous);
|
||
|
||
/** @type {NonNullable<Code>} */
|
||
let marker;
|
||
return start;
|
||
|
||
/**
|
||
* Before a sequence.
|
||
*
|
||
* ```markdown
|
||
* > | **
|
||
* ^
|
||
* ```
|
||
*
|
||
* @type {State}
|
||
*/
|
||
function start(code) {
|
||
marker = code;
|
||
effects.enter('attentionSequence');
|
||
return inside(code);
|
||
}
|
||
|
||
/**
|
||
* In a sequence.
|
||
*
|
||
* ```markdown
|
||
* > | **
|
||
* ^^
|
||
* ```
|
||
*
|
||
* @type {State}
|
||
*/
|
||
function inside(code) {
|
||
if (code === marker) {
|
||
effects.consume(code);
|
||
return inside;
|
||
}
|
||
const token = effects.exit('attentionSequence');
|
||
|
||
// To do: next major: move this to resolver, just like `markdown-rs`.
|
||
const after = classifyCharacter(code);
|
||
|
||
// Always populated by defaults.
|
||
|
||
const open = !after || after === 2 && before || attentionMarkers.includes(code);
|
||
const close = !before || before === 2 && after || attentionMarkers.includes(previous);
|
||
token._open = Boolean(marker === 42 ? open : open && (before || !close));
|
||
token._close = Boolean(marker === 42 ? close : close && (after || !open));
|
||
return ok(code);
|
||
}
|
||
}
|
||
|
||
/**
|
||
* Move a point a bit.
|
||
*
|
||
* Note: `move` only works inside lines! It’s not possible to move past other
|
||
* chunks (replacement characters, tabs, or line endings).
|
||
*
|
||
* @param {Point} point
|
||
* Point.
|
||
* @param {number} offset
|
||
* Amount to move.
|
||
* @returns {undefined}
|
||
* Nothing.
|
||
*/
|
||
function movePoint(point, offset) {
|
||
point.column += offset;
|
||
point.offset += offset;
|
||
point._bufferIndex += offset;
|
||
} |