forked from highlightjs/highlight.js
-
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
split code into modules and simplify (highlightjs#2402)
* remove dead code * pull out deep freeze * move out escapeRe * move out reStr to source * move out countMatchGroups * move reTest to regex.startsWith * move escape to escapeHTML * move inherit to utils * move MODES out * simplify defining API * simplify, use `find` * remove useless constant * use rollup to build the UMB browser build also * fix markdown to be strict safe * no more need for worker stub * move nodestream to utils * Cleaner code with ES2015 tricks * reduce use of lodash * we do not need arrays here * simplify * remove dead config
- Loading branch information
1 parent
6870e0c
commit cab7d36
Showing
22 changed files
with
441 additions
and
606 deletions.
There are no files selected for viewing
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,114 @@ | ||
| import {inherit} from './utils'; | ||
|
|
||
| // Common regexps | ||
| export const IDENT_RE = '[a-zA-Z]\\w*'; | ||
| export const UNDERSCORE_IDENT_RE = '[a-zA-Z_]\\w*'; | ||
| export const NUMBER_RE = '\\b\\d+(\\.\\d+)?'; | ||
| export const C_NUMBER_RE = '(-?)(\\b0[xX][a-fA-F0-9]+|(\\b\\d+(\\.\\d*)?|\\.\\d+)([eE][-+]?\\d+)?)'; // 0x..., 0..., decimal, float | ||
| export const BINARY_NUMBER_RE = '\\b(0b[01]+)'; // 0b... | ||
| export const RE_STARTERS_RE = '!|!=|!==|%|%=|&|&&|&=|\\*|\\*=|\\+|\\+=|,|-|-=|/=|/|:|;|<<|<<=|<=|<|===|==|=|>>>=|>>=|>=|>>>|>>|>|\\?|\\[|\\{|\\(|\\^|\\^=|\\||\\|=|\\|\\||~'; | ||
|
|
||
| // Common modes | ||
| export const BACKSLASH_ESCAPE = { | ||
| begin: '\\\\[\\s\\S]', relevance: 0 | ||
| }; | ||
| export const APOS_STRING_MODE = { | ||
| className: 'string', | ||
| begin: '\'', end: '\'', | ||
| illegal: '\\n', | ||
| contains: [BACKSLASH_ESCAPE] | ||
| }; | ||
| export const QUOTE_STRING_MODE = { | ||
| className: 'string', | ||
| begin: '"', end: '"', | ||
| illegal: '\\n', | ||
| contains: [BACKSLASH_ESCAPE] | ||
| }; | ||
| export const PHRASAL_WORDS_MODE = { | ||
| begin: /\b(a|an|the|are|I'm|isn't|don't|doesn't|won't|but|just|should|pretty|simply|enough|gonna|going|wtf|so|such|will|you|your|they|like|more)\b/ | ||
| }; | ||
| export const COMMENT = function (begin, end, inherits) { | ||
| var mode = inherit( | ||
| { | ||
| className: 'comment', | ||
| begin: begin, end: end, | ||
| contains: [] | ||
| }, | ||
| inherits || {} | ||
| ); | ||
| mode.contains.push(PHRASAL_WORDS_MODE); | ||
| mode.contains.push({ | ||
| className: 'doctag', | ||
| begin: '(?:TODO|FIXME|NOTE|BUG|XXX):', | ||
| relevance: 0 | ||
| }); | ||
| return mode; | ||
| }; | ||
| export const C_LINE_COMMENT_MODE = COMMENT('//', '$'); | ||
| export const C_BLOCK_COMMENT_MODE = COMMENT('/\\*', '\\*/'); | ||
| export const HASH_COMMENT_MODE = COMMENT('#', '$'); | ||
| export const NUMBER_MODE = { | ||
| className: 'number', | ||
| begin: NUMBER_RE, | ||
| relevance: 0 | ||
| }; | ||
| export const C_NUMBER_MODE = { | ||
| className: 'number', | ||
| begin: C_NUMBER_RE, | ||
| relevance: 0 | ||
| }; | ||
| export const BINARY_NUMBER_MODE = { | ||
| className: 'number', | ||
| begin: BINARY_NUMBER_RE, | ||
| relevance: 0 | ||
| }; | ||
| export const CSS_NUMBER_MODE = { | ||
| className: 'number', | ||
| begin: NUMBER_RE + '(' + | ||
| '%|em|ex|ch|rem' + | ||
| '|vw|vh|vmin|vmax' + | ||
| '|cm|mm|in|pt|pc|px' + | ||
| '|deg|grad|rad|turn' + | ||
| '|s|ms' + | ||
| '|Hz|kHz' + | ||
| '|dpi|dpcm|dppx' + | ||
| ')?', | ||
| relevance: 0 | ||
| }; | ||
| export const REGEXP_MODE = { | ||
| // this outer rule makes sure we actually have a WHOLE regex and not simply | ||
| // an expression such as: | ||
| // | ||
| // 3 / something | ||
| // | ||
| // (which will then blow up when regex's `illegal` sees the newline) | ||
| begin: /(?=\/[^\/\n]*\/)/, | ||
| contains: [{ | ||
| className: 'regexp', | ||
| begin: /\//, end: /\/[gimuy]*/, | ||
| illegal: /\n/, | ||
| contains: [ | ||
| BACKSLASH_ESCAPE, | ||
| { | ||
| begin: /\[/, end: /\]/, | ||
| relevance: 0, | ||
| contains: [BACKSLASH_ESCAPE] | ||
| } | ||
| ] | ||
| }] | ||
| }; | ||
| export const TITLE_MODE = { | ||
| className: 'title', | ||
| begin: IDENT_RE, | ||
| relevance: 0 | ||
| }; | ||
| export const UNDERSCORE_TITLE_MODE = { | ||
| className: 'title', | ||
| begin: UNDERSCORE_IDENT_RE, | ||
| relevance: 0 | ||
| }; | ||
| export const METHOD_GUARD = { | ||
| // excludes method names from keyword processing | ||
| begin: '\\.\\s*' + UNDERSCORE_IDENT_RE, | ||
| relevance: 0 | ||
| }; |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,65 @@ | ||
| export function escape(value) { | ||
| return new RegExp(value.replace(/[-\/\\^$*+?.()|[\]{}]/g, '\\$&'), 'm'); | ||
| } | ||
|
|
||
| export function source(re) { | ||
| // if it's a regex get it's source, | ||
| // otherwise it's a string already so just return it | ||
| return (re && re.source) || re; | ||
| } | ||
|
|
||
| export function countMatchGroups(re) { | ||
| return (new RegExp(re.toString() + '|')).exec('').length - 1; | ||
| } | ||
|
|
||
| export function startsWith(re, lexeme) { | ||
| var match = re && re.exec(lexeme); | ||
| return match && match.index === 0; | ||
| } | ||
|
|
||
| // join logically computes regexps.join(separator), but fixes the | ||
| // backreferences so they continue to match. | ||
| // it also places each individual regular expression into it's own | ||
| // match group, keeping track of the sequencing of those match groups | ||
| // is currently an exercise for the caller. :-) | ||
| export function join(regexps, separator) { | ||
| // backreferenceRe matches an open parenthesis or backreference. To avoid | ||
| // an incorrect parse, it additionally matches the following: | ||
| // - [...] elements, where the meaning of parentheses and escapes change | ||
| // - other escape sequences, so we do not misparse escape sequences as | ||
| // interesting elements | ||
| // - non-matching or lookahead parentheses, which do not capture. These | ||
| // follow the '(' with a '?'. | ||
| var backreferenceRe = /\[(?:[^\\\]]|\\.)*\]|\(\??|\\([1-9][0-9]*)|\\./; | ||
| var numCaptures = 0; | ||
| var ret = ''; | ||
| for (var i = 0; i < regexps.length; i++) { | ||
| numCaptures += 1; | ||
| var offset = numCaptures; | ||
| var re = source(regexps[i]); | ||
| if (i > 0) { | ||
| ret += separator; | ||
| } | ||
| ret += "("; | ||
| while (re.length > 0) { | ||
| var match = backreferenceRe.exec(re); | ||
| if (match == null) { | ||
| ret += re; | ||
| break; | ||
| } | ||
| ret += re.substring(0, match.index); | ||
| re = re.substring(match.index + match[0].length); | ||
| if (match[0][0] == '\\' && match[1]) { | ||
| // Adjust the backreference. | ||
| ret += '\\' + String(Number(match[1]) + offset); | ||
| } else { | ||
| ret += match[0]; | ||
| if (match[0] == '(') { | ||
| numCaptures++; | ||
| } | ||
| } | ||
| } | ||
| ret += ")"; | ||
| } | ||
| return ret; | ||
| } |
Oops, something went wrong.