site/node_modules/micromark-core-commonmark/lib/html-text.js
2024-10-14 08:09:33 +02:00

714 lines
13 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/**
* @typedef {import('micromark-util-types').Code} Code
* @typedef {import('micromark-util-types').Construct} Construct
* @typedef {import('micromark-util-types').State} State
* @typedef {import('micromark-util-types').TokenizeContext} TokenizeContext
* @typedef {import('micromark-util-types').Tokenizer} Tokenizer
*/
import {factorySpace} from 'micromark-factory-space'
import {
asciiAlpha,
asciiAlphanumeric,
markdownLineEnding,
markdownLineEndingOrSpace,
markdownSpace
} from 'micromark-util-character'
/** @type {Construct} */
export const htmlText = {
name: 'htmlText',
tokenize: tokenizeHtmlText
}
/**
* @this {TokenizeContext}
* @type {Tokenizer}
*/
function tokenizeHtmlText(effects, ok, nok) {
const self = this
/** @type {NonNullable<Code> | undefined} */
let marker
/** @type {number} */
let index
/** @type {State} */
let returnState
return start
/**
* Start of HTML (text).
*
* ```markdown
* > | a <b> c
* ^
* ```
*
* @type {State}
*/
function start(code) {
effects.enter('htmlText')
effects.enter('htmlTextData')
effects.consume(code)
return open
}
/**
* After `<`, at tag name or other stuff.
*
* ```markdown
* > | a <b> c
* ^
* > | a <!doctype> c
* ^
* > | a <!--b--> c
* ^
* ```
*
* @type {State}
*/
function open(code) {
if (code === 33) {
effects.consume(code)
return declarationOpen
}
if (code === 47) {
effects.consume(code)
return tagCloseStart
}
if (code === 63) {
effects.consume(code)
return instruction
}
// ASCII alphabetical.
if (asciiAlpha(code)) {
effects.consume(code)
return tagOpen
}
return nok(code)
}
/**
* After `<!`, at declaration, comment, or CDATA.
*
* ```markdown
* > | a <!doctype> c
* ^
* > | a <!--b--> c
* ^
* > | a <![CDATA[>&<]]> c
* ^
* ```
*
* @type {State}
*/
function declarationOpen(code) {
if (code === 45) {
effects.consume(code)
return commentOpenInside
}
if (code === 91) {
effects.consume(code)
index = 0
return cdataOpenInside
}
if (asciiAlpha(code)) {
effects.consume(code)
return declaration
}
return nok(code)
}
/**
* In a comment, after `<!-`, at another `-`.
*
* ```markdown
* > | a <!--b--> c
* ^
* ```
*
* @type {State}
*/
function commentOpenInside(code) {
if (code === 45) {
effects.consume(code)
return commentEnd
}
return nok(code)
}
/**
* In comment.
*
* ```markdown
* > | a <!--b--> c
* ^
* ```
*
* @type {State}
*/
function comment(code) {
if (code === null) {
return nok(code)
}
if (code === 45) {
effects.consume(code)
return commentClose
}
if (markdownLineEnding(code)) {
returnState = comment
return lineEndingBefore(code)
}
effects.consume(code)
return comment
}
/**
* In comment, after `-`.
*
* ```markdown
* > | a <!--b--> c
* ^
* ```
*
* @type {State}
*/
function commentClose(code) {
if (code === 45) {
effects.consume(code)
return commentEnd
}
return comment(code)
}
/**
* In comment, after `--`.
*
* ```markdown
* > | a <!--b--> c
* ^
* ```
*
* @type {State}
*/
function commentEnd(code) {
return code === 62
? end(code)
: code === 45
? commentClose(code)
: comment(code)
}
/**
* After `<![`, in CDATA, expecting `CDATA[`.
*
* ```markdown
* > | a <![CDATA[>&<]]> b
* ^^^^^^
* ```
*
* @type {State}
*/
function cdataOpenInside(code) {
const value = 'CDATA['
if (code === value.charCodeAt(index++)) {
effects.consume(code)
return index === value.length ? cdata : cdataOpenInside
}
return nok(code)
}
/**
* In CDATA.
*
* ```markdown
* > | a <![CDATA[>&<]]> b
* ^^^
* ```
*
* @type {State}
*/
function cdata(code) {
if (code === null) {
return nok(code)
}
if (code === 93) {
effects.consume(code)
return cdataClose
}
if (markdownLineEnding(code)) {
returnState = cdata
return lineEndingBefore(code)
}
effects.consume(code)
return cdata
}
/**
* In CDATA, after `]`, at another `]`.
*
* ```markdown
* > | a <![CDATA[>&<]]> b
* ^
* ```
*
* @type {State}
*/
function cdataClose(code) {
if (code === 93) {
effects.consume(code)
return cdataEnd
}
return cdata(code)
}
/**
* In CDATA, after `]]`, at `>`.
*
* ```markdown
* > | a <![CDATA[>&<]]> b
* ^
* ```
*
* @type {State}
*/
function cdataEnd(code) {
if (code === 62) {
return end(code)
}
if (code === 93) {
effects.consume(code)
return cdataEnd
}
return cdata(code)
}
/**
* In declaration.
*
* ```markdown
* > | a <!b> c
* ^
* ```
*
* @type {State}
*/
function declaration(code) {
if (code === null || code === 62) {
return end(code)
}
if (markdownLineEnding(code)) {
returnState = declaration
return lineEndingBefore(code)
}
effects.consume(code)
return declaration
}
/**
* In instruction.
*
* ```markdown
* > | a <?b?> c
* ^
* ```
*
* @type {State}
*/
function instruction(code) {
if (code === null) {
return nok(code)
}
if (code === 63) {
effects.consume(code)
return instructionClose
}
if (markdownLineEnding(code)) {
returnState = instruction
return lineEndingBefore(code)
}
effects.consume(code)
return instruction
}
/**
* In instruction, after `?`, at `>`.
*
* ```markdown
* > | a <?b?> c
* ^
* ```
*
* @type {State}
*/
function instructionClose(code) {
return code === 62 ? end(code) : instruction(code)
}
/**
* After `</`, in closing tag, at tag name.
*
* ```markdown
* > | a </b> c
* ^
* ```
*
* @type {State}
*/
function tagCloseStart(code) {
// ASCII alphabetical.
if (asciiAlpha(code)) {
effects.consume(code)
return tagClose
}
return nok(code)
}
/**
* After `</x`, in a tag name.
*
* ```markdown
* > | a </b> c
* ^
* ```
*
* @type {State}
*/
function tagClose(code) {
// ASCII alphanumerical and `-`.
if (code === 45 || asciiAlphanumeric(code)) {
effects.consume(code)
return tagClose
}
return tagCloseBetween(code)
}
/**
* In closing tag, after tag name.
*
* ```markdown
* > | a </b> c
* ^
* ```
*
* @type {State}
*/
function tagCloseBetween(code) {
if (markdownLineEnding(code)) {
returnState = tagCloseBetween
return lineEndingBefore(code)
}
if (markdownSpace(code)) {
effects.consume(code)
return tagCloseBetween
}
return end(code)
}
/**
* After `<x`, in opening tag name.
*
* ```markdown
* > | a <b> c
* ^
* ```
*
* @type {State}
*/
function tagOpen(code) {
// ASCII alphanumerical and `-`.
if (code === 45 || asciiAlphanumeric(code)) {
effects.consume(code)
return tagOpen
}
if (code === 47 || code === 62 || markdownLineEndingOrSpace(code)) {
return tagOpenBetween(code)
}
return nok(code)
}
/**
* In opening tag, after tag name.
*
* ```markdown
* > | a <b> c
* ^
* ```
*
* @type {State}
*/
function tagOpenBetween(code) {
if (code === 47) {
effects.consume(code)
return end
}
// ASCII alphabetical and `:` and `_`.
if (code === 58 || code === 95 || asciiAlpha(code)) {
effects.consume(code)
return tagOpenAttributeName
}
if (markdownLineEnding(code)) {
returnState = tagOpenBetween
return lineEndingBefore(code)
}
if (markdownSpace(code)) {
effects.consume(code)
return tagOpenBetween
}
return end(code)
}
/**
* In attribute name.
*
* ```markdown
* > | a <b c> d
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeName(code) {
// ASCII alphabetical and `-`, `.`, `:`, and `_`.
if (
code === 45 ||
code === 46 ||
code === 58 ||
code === 95 ||
asciiAlphanumeric(code)
) {
effects.consume(code)
return tagOpenAttributeName
}
return tagOpenAttributeNameAfter(code)
}
/**
* After attribute name, before initializer, the end of the tag, or
* whitespace.
*
* ```markdown
* > | a <b c> d
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeNameAfter(code) {
if (code === 61) {
effects.consume(code)
return tagOpenAttributeValueBefore
}
if (markdownLineEnding(code)) {
returnState = tagOpenAttributeNameAfter
return lineEndingBefore(code)
}
if (markdownSpace(code)) {
effects.consume(code)
return tagOpenAttributeNameAfter
}
return tagOpenBetween(code)
}
/**
* Before unquoted, double quoted, or single quoted attribute value, allowing
* whitespace.
*
* ```markdown
* > | a <b c=d> e
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeValueBefore(code) {
if (
code === null ||
code === 60 ||
code === 61 ||
code === 62 ||
code === 96
) {
return nok(code)
}
if (code === 34 || code === 39) {
effects.consume(code)
marker = code
return tagOpenAttributeValueQuoted
}
if (markdownLineEnding(code)) {
returnState = tagOpenAttributeValueBefore
return lineEndingBefore(code)
}
if (markdownSpace(code)) {
effects.consume(code)
return tagOpenAttributeValueBefore
}
effects.consume(code)
return tagOpenAttributeValueUnquoted
}
/**
* In double or single quoted attribute value.
*
* ```markdown
* > | a <b c="d"> e
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeValueQuoted(code) {
if (code === marker) {
effects.consume(code)
marker = undefined
return tagOpenAttributeValueQuotedAfter
}
if (code === null) {
return nok(code)
}
if (markdownLineEnding(code)) {
returnState = tagOpenAttributeValueQuoted
return lineEndingBefore(code)
}
effects.consume(code)
return tagOpenAttributeValueQuoted
}
/**
* In unquoted attribute value.
*
* ```markdown
* > | a <b c=d> e
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeValueUnquoted(code) {
if (
code === null ||
code === 34 ||
code === 39 ||
code === 60 ||
code === 61 ||
code === 96
) {
return nok(code)
}
if (code === 47 || code === 62 || markdownLineEndingOrSpace(code)) {
return tagOpenBetween(code)
}
effects.consume(code)
return tagOpenAttributeValueUnquoted
}
/**
* After double or single quoted attribute value, before whitespace or the end
* of the tag.
*
* ```markdown
* > | a <b c="d"> e
* ^
* ```
*
* @type {State}
*/
function tagOpenAttributeValueQuotedAfter(code) {
if (code === 47 || code === 62 || markdownLineEndingOrSpace(code)) {
return tagOpenBetween(code)
}
return nok(code)
}
/**
* In certain circumstances of a tag where only an `>` is allowed.
*
* ```markdown
* > | a <b c="d"> e
* ^
* ```
*
* @type {State}
*/
function end(code) {
if (code === 62) {
effects.consume(code)
effects.exit('htmlTextData')
effects.exit('htmlText')
return ok
}
return nok(code)
}
/**
* At eol.
*
* > 👉 **Note**: we cant have blank lines in text, so no need to worry about
* > empty tokens.
*
* ```markdown
* > | a <!--a
* ^
* | b-->
* ```
*
* @type {State}
*/
function lineEndingBefore(code) {
effects.exit('htmlTextData')
effects.enter('lineEnding')
effects.consume(code)
effects.exit('lineEnding')
return lineEndingAfter
}
/**
* After eol, at optional whitespace.
*
* > 👉 **Note**: we cant have blank lines in text, so no need to worry about
* > empty tokens.
*
* ```markdown
* | a <!--a
* > | b-->
* ^
* ```
*
* @type {State}
*/
function lineEndingAfter(code) {
// Always populated by defaults.
return markdownSpace(code)
? factorySpace(
effects,
lineEndingAfterPrefix,
'linePrefix',
self.parser.constructs.disable.null.includes('codeIndented')
? undefined
: 4
)(code)
: lineEndingAfterPrefix(code)
}
/**
* After eol, after optional whitespace.
*
* > 👉 **Note**: we cant have blank lines in text, so no need to worry about
* > empty tokens.
*
* ```markdown
* | a <!--a
* > | b-->
* ^
* ```
*
* @type {State}
*/
function lineEndingAfterPrefix(code) {
effects.enter('htmlTextData')
return returnState(code)
}
}