664 lines
16 KiB
JavaScript
664 lines
16 KiB
JavaScript
const { defaults } = require('./defaults.js');
|
|
const {
|
|
rtrim,
|
|
splitCells,
|
|
escape,
|
|
findClosingBracket
|
|
} = require('./helpers.js');
|
|
const { block, inline } = require('./rules.js');
|
|
|
|
function outputLink(cap, link, tokens, raw, lexer) {
|
|
const href = link.href;
|
|
const title = link.title ? escape(link.title) : null;
|
|
|
|
if (cap[0].charAt(0) !== '!') {
|
|
return {
|
|
type: 'link',
|
|
raw,
|
|
href,
|
|
title,
|
|
tokens: lexer.inlineTokens(cap[1])
|
|
};
|
|
} else {
|
|
return {
|
|
type: 'image',
|
|
raw,
|
|
text: escape(cap[1]),
|
|
href,
|
|
title
|
|
};
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Tokenizer
|
|
*/
|
|
module.exports = class Tokenizer {
|
|
constructor(options) {
|
|
this.options = options || defaults;
|
|
this.initialize();
|
|
}
|
|
|
|
initialize() {
|
|
this.inLink = false;
|
|
this.inRawBlock = false;
|
|
|
|
this.rules = {
|
|
block: block.normal,
|
|
inline: inline.normal
|
|
};
|
|
|
|
if (this.options.pedantic) {
|
|
this.rules.block = block.pedantic;
|
|
this.rules.inline = inline.pedantic;
|
|
} else if (this.options.gfm) {
|
|
this.rules.block = block.gfm;
|
|
if (this.options.breaks) {
|
|
this.rules.inline = inline.breaks;
|
|
} else {
|
|
this.rules.inline = inline.gfm;
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Expose Block Rules
|
|
*/
|
|
static get rules() {
|
|
return {
|
|
block,
|
|
inline
|
|
};
|
|
}
|
|
|
|
space(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.newline.exec(src);
|
|
if (cap) {
|
|
if (cap[0].length > 1) {
|
|
return {
|
|
type: 'space',
|
|
raw: cap[0]
|
|
};
|
|
}
|
|
return { raw: '\n' };
|
|
}
|
|
}
|
|
|
|
code(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.code.exec(src);
|
|
if (cap) {
|
|
const lastToken = tokens[tokens.length - 1];
|
|
// An indented code block cannot interrupt a paragraph.
|
|
if (lastToken && lastToken.type === 'paragraph') {
|
|
tokens.pop();
|
|
lastToken.text += '\n' + cap[0].trimRight();
|
|
lastToken.raw += '\n' + cap[0];
|
|
return lastToken;
|
|
} else {
|
|
const text = cap[0].replace(/^ {4}/gm, '');
|
|
return {
|
|
type: 'code',
|
|
raw: cap[0],
|
|
codeBlockStyle: 'indented',
|
|
text: !this.options.pedantic
|
|
? rtrim(text, '\n')
|
|
: text
|
|
};
|
|
}
|
|
}
|
|
}
|
|
|
|
fences(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.fences.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'code',
|
|
raw: cap[0],
|
|
lang: cap[2] ? cap[2].trim() : cap[2],
|
|
text: cap[3] || ''
|
|
};
|
|
}
|
|
}
|
|
|
|
heading(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.heading.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'heading',
|
|
raw: cap[0],
|
|
depth: cap[1].length,
|
|
text: cap[2]
|
|
};
|
|
}
|
|
}
|
|
|
|
nptable(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.nptable.exec(src);
|
|
if (cap) {
|
|
const item = {
|
|
type: 'table',
|
|
header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
|
|
align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
|
|
cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : [],
|
|
raw: cap[0]
|
|
};
|
|
|
|
if (item.header.length === item.align.length) {
|
|
let l = item.align.length;
|
|
let i;
|
|
for (i = 0; i < l; i++) {
|
|
if (/^ *-+: *$/.test(item.align[i])) {
|
|
item.align[i] = 'right';
|
|
} else if (/^ *:-+: *$/.test(item.align[i])) {
|
|
item.align[i] = 'center';
|
|
} else if (/^ *:-+ *$/.test(item.align[i])) {
|
|
item.align[i] = 'left';
|
|
} else {
|
|
item.align[i] = null;
|
|
}
|
|
}
|
|
|
|
l = item.cells.length;
|
|
for (i = 0; i < l; i++) {
|
|
item.cells[i] = splitCells(item.cells[i], item.header.length);
|
|
}
|
|
|
|
return item;
|
|
}
|
|
}
|
|
}
|
|
|
|
hr(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.hr.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'hr',
|
|
raw: cap[0]
|
|
};
|
|
}
|
|
}
|
|
|
|
blockquote(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.blockquote.exec(src);
|
|
if (cap) {
|
|
const text = cap[0].replace(/^ *> ?/gm, '');
|
|
|
|
return {
|
|
type: 'blockquote',
|
|
raw: cap[0],
|
|
tokens: lexer.blockTokens(text, [], top)
|
|
};
|
|
}
|
|
}
|
|
|
|
list(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.list.exec(src);
|
|
if (cap) {
|
|
let raw = cap[0];
|
|
const bull = cap[2];
|
|
const isordered = bull.length > 1;
|
|
|
|
const list = {
|
|
type: 'list',
|
|
raw,
|
|
ordered: isordered,
|
|
start: isordered ? +bull : '',
|
|
loose: false,
|
|
items: []
|
|
};
|
|
|
|
// Get each top-level item.
|
|
const itemMatch = cap[0].match(this.rules.block.item);
|
|
|
|
let next = false,
|
|
item,
|
|
space,
|
|
b,
|
|
addBack,
|
|
loose,
|
|
istask,
|
|
ischecked;
|
|
|
|
const l = itemMatch.length;
|
|
for (let i = 0; i < l; i++) {
|
|
item = itemMatch[i];
|
|
raw = item;
|
|
|
|
// Remove the list item's bullet
|
|
// so it is seen as the next token.
|
|
space = item.length;
|
|
item = item.replace(/^ *([*+-]|\d+\.) */, '');
|
|
|
|
// Outdent whatever the
|
|
// list item contains. Hacky.
|
|
if (~item.indexOf('\n ')) {
|
|
space -= item.length;
|
|
item = !this.options.pedantic
|
|
? item.replace(new RegExp('^ {1,' + space + '}', 'gm'), '')
|
|
: item.replace(/^ {1,4}/gm, '');
|
|
}
|
|
|
|
// Determine whether the next list item belongs here.
|
|
// Backpedal if it does not belong in this list.
|
|
if (i !== l - 1) {
|
|
b = this.rules.block.bullet.exec(itemMatch[i + 1])[0];
|
|
if (bull.length > 1 ? b.length === 1
|
|
: (b.length > 1 || (this.options.smartLists && b !== bull))) {
|
|
addBack = itemMatch.slice(i + 1).join('\n');
|
|
list.raw = list.raw.substring(0, list.raw.length - addBack.length);
|
|
i = l - 1;
|
|
}
|
|
}
|
|
|
|
// Determine whether item is loose or not.
|
|
// Use: /(^|\n)(?! )[^\n]+\n\n(?!\s*$)/
|
|
// for discount behavior.
|
|
loose = next || /\n\n(?!\s*$)/.test(item);
|
|
if (i !== l - 1) {
|
|
next = item.charAt(item.length - 1) === '\n';
|
|
if (!loose) loose = next;
|
|
}
|
|
|
|
if (loose) {
|
|
list.loose = true;
|
|
}
|
|
|
|
// Check for task list items
|
|
istask = /^\[[ xX]\] /.test(item);
|
|
ischecked = undefined;
|
|
if (istask) {
|
|
ischecked = item[1] !== ' ';
|
|
item = item.replace(/^\[[ xX]\] +/, '');
|
|
}
|
|
|
|
list.items.push({
|
|
raw,
|
|
task: istask,
|
|
checked: ischecked,
|
|
loose: loose,
|
|
tokens: lexer.blockTokens(item, [], false)
|
|
});
|
|
}
|
|
|
|
return list;
|
|
}
|
|
}
|
|
|
|
html(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.html.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: this.options.sanitize
|
|
? 'paragraph'
|
|
: 'html',
|
|
raw: cap[0],
|
|
pre: !this.options.sanitizer
|
|
&& (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'),
|
|
text: this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]
|
|
};
|
|
}
|
|
}
|
|
|
|
def(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.def.exec(src);
|
|
if (cap) {
|
|
if (cap[3]) cap[3] = cap[3].substring(1, cap[3].length - 1);
|
|
const tag = cap[1].toLowerCase().replace(/\s+/g, ' ');
|
|
return {
|
|
tag,
|
|
raw: cap[0],
|
|
href: cap[2],
|
|
title: cap[3]
|
|
};
|
|
}
|
|
}
|
|
|
|
table(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.table.exec(src);
|
|
if (cap) {
|
|
const item = {
|
|
type: 'table',
|
|
header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
|
|
align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
|
|
cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : []
|
|
};
|
|
|
|
if (item.header.length === item.align.length) {
|
|
item.raw = cap[0];
|
|
|
|
let l = item.align.length;
|
|
let i;
|
|
for (i = 0; i < l; i++) {
|
|
if (/^ *-+: *$/.test(item.align[i])) {
|
|
item.align[i] = 'right';
|
|
} else if (/^ *:-+: *$/.test(item.align[i])) {
|
|
item.align[i] = 'center';
|
|
} else if (/^ *:-+ *$/.test(item.align[i])) {
|
|
item.align[i] = 'left';
|
|
} else {
|
|
item.align[i] = null;
|
|
}
|
|
}
|
|
|
|
l = item.cells.length;
|
|
for (i = 0; i < l; i++) {
|
|
item.cells[i] = splitCells(
|
|
item.cells[i].replace(/^ *\| *| *\| *$/g, ''),
|
|
item.header.length);
|
|
}
|
|
|
|
return item;
|
|
}
|
|
}
|
|
}
|
|
|
|
lheading(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.lheading.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'heading',
|
|
raw: cap[0],
|
|
depth: cap[2].charAt(0) === '=' ? 1 : 2,
|
|
text: cap[1]
|
|
};
|
|
}
|
|
}
|
|
|
|
paragraph(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.paragraph.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'paragraph',
|
|
raw: cap[0],
|
|
text: cap[1].charAt(cap[1].length - 1) === '\n'
|
|
? cap[1].slice(0, -1)
|
|
: cap[1]
|
|
};
|
|
}
|
|
}
|
|
|
|
text(lexer, src, tokens, top) {
|
|
const cap = this.rules.block.text.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'text',
|
|
raw: cap[0],
|
|
text: cap[0]
|
|
};
|
|
}
|
|
}
|
|
|
|
escape(lexer, src, tokens) {
|
|
const cap = this.rules.inline.escape.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'escape',
|
|
raw: cap[0],
|
|
text: escape(cap[1])
|
|
};
|
|
}
|
|
}
|
|
|
|
tag(lexer, src, tokens) {
|
|
const cap = this.rules.inline.tag.exec(src);
|
|
if (cap) {
|
|
if (!this.inLink && /^<a /i.test(cap[0])) {
|
|
this.inLink = true;
|
|
} else if (this.inLink && /^<\/a>/i.test(cap[0])) {
|
|
this.inLink = false;
|
|
}
|
|
if (!this.inRawBlock && /^<(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
|
|
this.inRawBlock = true;
|
|
} else if (this.inRawBlock && /^<\/(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
|
|
this.inRawBlock = false;
|
|
}
|
|
|
|
return {
|
|
type: this.options.sanitize
|
|
? 'text'
|
|
: 'html',
|
|
raw: cap[0],
|
|
text: this.options.sanitize
|
|
? (this.options.sanitizer
|
|
? this.options.sanitizer(cap[0])
|
|
: escape(cap[0]))
|
|
: cap[0]
|
|
};
|
|
}
|
|
}
|
|
|
|
link(lexer, src, tokens) {
|
|
const cap = this.rules.inline.link.exec(src);
|
|
if (cap) {
|
|
const lastParenIndex = findClosingBracket(cap[2], '()');
|
|
if (lastParenIndex > -1) {
|
|
const start = cap[0].indexOf('!') === 0 ? 5 : 4;
|
|
const linkLen = start + cap[1].length + lastParenIndex;
|
|
cap[2] = cap[2].substring(0, lastParenIndex);
|
|
cap[0] = cap[0].substring(0, linkLen).trim();
|
|
cap[3] = '';
|
|
}
|
|
this.inLink = true;
|
|
let href = cap[2];
|
|
let title = '';
|
|
if (this.options.pedantic) {
|
|
const link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href);
|
|
|
|
if (link) {
|
|
href = link[1];
|
|
title = link[3];
|
|
} else {
|
|
title = '';
|
|
}
|
|
} else {
|
|
title = cap[3] ? cap[3].slice(1, -1) : '';
|
|
}
|
|
href = href.trim().replace(/^<([\s\S]*)>$/, '$1');
|
|
const token = outputLink(cap, {
|
|
href: href ? href.replace(this.rules.inline._escapes, '$1') : href,
|
|
title: title ? title.replace(this.rules.inline._escapes, '$1') : title
|
|
}, tokens, cap[0], lexer);
|
|
this.inLink = false;
|
|
return token;
|
|
}
|
|
}
|
|
|
|
reflink(lexer, src, tokens) {
|
|
let cap;
|
|
if ((cap = this.rules.inline.reflink.exec(src))
|
|
|| (cap = this.rules.inline.nolink.exec(src))) {
|
|
let link = (cap[2] || cap[1]).replace(/\s+/g, ' ');
|
|
link = lexer.tokens.links[link.toLowerCase()];
|
|
if (!link || !link.href) {
|
|
const text = cap[0].charAt(0);
|
|
return {
|
|
type: 'text',
|
|
raw: text,
|
|
text
|
|
};
|
|
}
|
|
this.inLink = true;
|
|
const token = outputLink(cap, link, tokens, cap[0], lexer);
|
|
this.inLink = false;
|
|
return token;
|
|
}
|
|
}
|
|
|
|
strong(lexer, src, tokens) {
|
|
const cap = this.rules.inline.strong.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'strong',
|
|
raw: cap[0],
|
|
tokens: lexer.inlineTokens(cap[4] || cap[3] || cap[2] || cap[1])
|
|
};
|
|
}
|
|
}
|
|
|
|
em(lexer, src, tokens) {
|
|
const cap = this.rules.inline.em.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'em',
|
|
raw: cap[0],
|
|
tokens: lexer.inlineTokens(cap[6] || cap[5] || cap[4] || cap[3] || cap[2] || cap[1])
|
|
};
|
|
}
|
|
}
|
|
|
|
codespan(lexer, src, tokens) {
|
|
const cap = this.rules.inline.code.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'codespan',
|
|
raw: cap[0],
|
|
text: escape(cap[2].trim(), true)
|
|
};
|
|
}
|
|
}
|
|
|
|
br(lexer, src, tokens) {
|
|
const cap = this.rules.inline.br.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'br',
|
|
raw: cap[0]
|
|
};
|
|
}
|
|
}
|
|
|
|
del(lexer, src, tokens) {
|
|
const cap = this.rules.inline.del.exec(src);
|
|
if (cap) {
|
|
return {
|
|
type: 'del',
|
|
raw: cap[0],
|
|
tokens: lexer.inlineTokens(cap[1])
|
|
};
|
|
}
|
|
}
|
|
|
|
autolink(lexer, src, tokens) {
|
|
const cap = this.rules.inline.autolink.exec(src);
|
|
if (cap) {
|
|
let text, href;
|
|
if (cap[2] === '@') {
|
|
text = escape(this.options.mangle ? this.mangle(cap[1]) : cap[1]);
|
|
href = 'mailto:' + text;
|
|
} else {
|
|
text = escape(cap[1]);
|
|
href = text;
|
|
}
|
|
|
|
return {
|
|
type: 'link',
|
|
raw: cap[0],
|
|
text,
|
|
href,
|
|
tokens: [
|
|
{
|
|
type: 'text',
|
|
raw: text,
|
|
text
|
|
}
|
|
]
|
|
};
|
|
}
|
|
}
|
|
|
|
url(lexer, src, tokens) {
|
|
let cap;
|
|
if (!this.inLink && (cap = this.rules.inline.url.exec(src))) {
|
|
let text, href;
|
|
if (cap[2] === '@') {
|
|
text = escape(this.options.mangle ? this.mangle(cap[0]) : cap[0]);
|
|
href = 'mailto:' + text;
|
|
} else {
|
|
// do extended autolink path validation
|
|
let prevCapZero;
|
|
do {
|
|
prevCapZero = cap[0];
|
|
cap[0] = this.rules.inline._backpedal.exec(cap[0])[0];
|
|
} while (prevCapZero !== cap[0]);
|
|
text = escape(cap[0]);
|
|
if (cap[1] === 'www.') {
|
|
href = 'http://' + text;
|
|
} else {
|
|
href = text;
|
|
}
|
|
}
|
|
return {
|
|
type: 'link',
|
|
raw: cap[0],
|
|
text,
|
|
href,
|
|
tokens: [
|
|
{
|
|
type: 'text',
|
|
raw: text,
|
|
text
|
|
}
|
|
]
|
|
};
|
|
}
|
|
}
|
|
|
|
inlineText(lexer, src, tokens) {
|
|
const cap = this.rules.inline.text.exec(src);
|
|
if (cap) {
|
|
let text;
|
|
if (this.inRawBlock) {
|
|
text = this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0];
|
|
} else {
|
|
text = escape(this.options.smartypants ? this.smartypants(cap[0]) : cap[0]);
|
|
}
|
|
return {
|
|
type: 'text',
|
|
raw: cap[0],
|
|
text
|
|
};
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Smartypants Transformations
|
|
*/
|
|
smartypants(text) {
|
|
return text
|
|
// em-dashes
|
|
.replace(/---/g, '\u2014')
|
|
// en-dashes
|
|
.replace(/--/g, '\u2013')
|
|
// opening singles
|
|
.replace(/(^|[-\u2014/(\[{"\s])'/g, '$1\u2018')
|
|
// closing singles & apostrophes
|
|
.replace(/'/g, '\u2019')
|
|
// opening doubles
|
|
.replace(/(^|[-\u2014/(\[{\u2018\s])"/g, '$1\u201c')
|
|
// closing doubles
|
|
.replace(/"/g, '\u201d')
|
|
// ellipses
|
|
.replace(/\.{3}/g, '\u2026');
|
|
}
|
|
|
|
/**
|
|
* Mangle Links
|
|
*/
|
|
mangle(text) {
|
|
let out = '',
|
|
i,
|
|
ch;
|
|
|
|
const l = text.length;
|
|
for (i = 0; i < l; i++) {
|
|
ch = text.charCodeAt(i);
|
|
if (Math.random() > 0.5) {
|
|
ch = 'x' + ch.toString(16);
|
|
}
|
|
out += '&#' + ch + ';';
|
|
}
|
|
|
|
return out;
|
|
}
|
|
};
|