fix: update punctuation regex syntax to fix babel mistaken transpile

markedjs#3540 (comment)
BlueCat0 · Nov 26, 2024 · 6d827c8 · 6d827c8
1 parent 1521756
commit 6d827c8
Showing 1 changed file with 40 additions and 34 deletions.
diff --git a/src/rules.ts b/src/rules.ts
@@ -114,15 +114,15 @@ const _tag = 'address|article|aside|base|basefont|blockquote|body|caption'
 const _comment = /<!--(?:-?>|[\s\S]*?(?:-->|$))/;
 const html = edit(
   '^ {0,3}(?:' // optional indentation
-+ '<(script|pre|style|textarea)[\\s>][\\s\\S]*?(?:</\\1>[^\\n]*\\n+|$)' // (1)
-+ '|comment[^\\n]*(\\n+|$)' // (2)
-+ '|<\\?[\\s\\S]*?(?:\\?>\\n*|$)' // (3)
-+ '|<![A-Z][\\s\\S]*?(?:>\\n*|$)' // (4)
-+ '|<!\\[CDATA\\[[\\s\\S]*?(?:\\]\\]>\\n*|$)' // (5)
-+ '|</?(tag)(?: +|\\n|/?>)[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (6)
-+ '|<(?!script|pre|style|textarea)([a-z][\\w-]*)(?:attribute)*? */?>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (7) open tag
-+ '|</(?!script|pre|style|textarea)[a-z][\\w-]*\\s*>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (7) closing tag
-+ ')', 'i')
+  + '<(script|pre|style|textarea)[\\s>][\\s\\S]*?(?:</\\1>[^\\n]*\\n+|$)' // (1)
+  + '|comment[^\\n]*(\\n+|$)' // (2)
+  + '|<\\?[\\s\\S]*?(?:\\?>\\n*|$)' // (3)
+  + '|<![A-Z][\\s\\S]*?(?:>\\n*|$)' // (4)
+  + '|<!\\[CDATA\\[[\\s\\S]*?(?:\\]\\]>\\n*|$)' // (5)
+  + '|</?(tag)(?: +|\\n|/?>)[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (6)
+  + '|<(?!script|pre|style|textarea)([a-z][\\w-]*)(?:attribute)*? */?>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (7) open tag
+  + '|</(?!script|pre|style|textarea)[a-z][\\w-]*\\s*>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n[ \t]*)+\\n|$)' // (7) closing tag
+  + ')', 'i')
   .replace('comment', _comment)
   .replace('tag', _tag)
   .replace('attribute', / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/)
@@ -172,8 +172,8 @@ type BlockKeys = keyof typeof blockNormal;
 
 const gfmTable = edit(
   '^ *([^\\n ].*)\\n' // Header
-+ ' {0,3}((?:\\| *)?:?-+:? *(?:\\| *:?-+:? *)*(?:\\| *)?)' // Align
-+ '(?:\\n((?:(?! *\\n|hr|heading|blockquote|code|fences|list|html).*(?:\\n|$))*)\\n*|$)') // Cells
+  + ' {0,3}((?:\\| *)?:?-+:? *(?:\\| *:?-+:? *)*(?:\\| *)?)' // Align
+  + '(?:\\n((?:(?! *\\n|hr|heading|blockquote|code|fences|list|html).*(?:\\n|$))*)\\n*|$)') // Cells
   .replace('hr', hr)
   .replace('heading', ' {0,3}#{1,6}(?:\\s|$)')
   .replace('blockquote', ' {0,3}>')
@@ -243,42 +243,48 @@ const br = /^( {2,}|\\)\n(?!\s*$)/;
 const inlineText = /^(`+|[^`])(?:(?= {2,}\n)|[\s\S]*?(?:(?=[\\<!\[`*_]|\b_|$)|[^ ](?= {2,}\n)))/;
 
 // list of unicode punctuation marks, plus any missing characters from CommonMark spec
-const _punctuation = /\p{P}\p{S}/u;
-const punctuation = edit(/^((?![*_])[\spunctuation])/, 'u')
-  .replace(/punctuation/g, _punctuation).getRegex();
+const _punctuation = /[\p{P}\p{S}]/u;
+const _punctuationOrSpace = /[\s\p{P}\p{S}]/u;
+const _notPunctuationOrSpace = /[^\s\p{P}\p{S}]/u;
+const punctuation = edit(/^((?![*_])punctSpace)/, 'u')
+  .replace(/punctSpace/g, _punctuationOrSpace).getRegex();
 
 // sequences em should skip over [title](link), `code`, <html>
 const blockSkip = /\[[^[\]]*?\]\((?:\\.|[^\\\(\)]|\((?:\\.|[^\\\(\)])*\))*\)|`[^`]*?`|<[^<>]*?>/g;
 
-const emStrongLDelim = edit(/^(?:\*+(?:((?!\*)[punct])|[^\s*]))|^_+(?:((?!_)[punct])|([^\s_]))/, 'u')
+const emStrongLDelim = edit(/^(?:\*+(?:((?!\*)punct)|[^\s*]))|^_+(?:((?!_)punct)|([^\s_]))/, 'u')
   .replace(/punct/g, _punctuation)
   .getRegex();
 
 const emStrongRDelimAst = edit(
   '^[^_*]*?__[^_*]*?\\*[^_*]*?(?=__)' // Skip orphan inside strong
-+ '|[^*]+(?=[^*])' // Consume to delim
-+ '|(?!\\*)[punct](\\*+)(?=[\\s]|$)' // (1) #*** can only be a Right Delimiter
-+ '|[^punct\\s](\\*+)(?!\\*)(?=[punct\\s]|$)' // (2) a***#, a*** can only be a Right Delimiter
-+ '|(?!\\*)[punct\\s](\\*+)(?=[^punct\\s])' // (3) #***a, ***a can only be Left Delimiter
-+ '|[\\s](\\*+)(?!\\*)(?=[punct])' // (4) ***# can only be Left Delimiter
-+ '|(?!\\*)[punct](\\*+)(?!\\*)(?=[punct])' // (5) #***# can be either Left or Right Delimiter
-+ '|[^punct\\s](\\*+)(?=[^punct\\s])', 'gu') // (6) a***a can be either Left or Right Delimiter
+  + '|[^*]+(?=[^*])' // Consume to delim
+  + '|(?!\\*)punct(\\*+)(?=[\\s]|$)' // (1) #*** can only be a Right Delimiter
+  + '|notPunctSpace(\\*+)(?!\\*)(?=punctSpace|$)' // (2) a***#, a*** can only be a Right Delimiter
+  + '|(?!\\*)punctSpace(\\*+)(?=notPunctSpace)' // (3) #***a, ***a can only be Left Delimiter
+  + '|[\\s](\\*+)(?!\\*)(?=punct)' // (4) ***# can only be Left Delimiter
+  + '|(?!\\*)punct(\\*+)(?!\\*)(?=punct)' // (5) #***# can be either Left or Right Delimiter
+  + '|notPunctSpace(\\*+)(?=notPunctSpace)', 'gu') // (6) a***a can be either Left or Right Delimiter
+  .replace(/notPunctSpace/g, _notPunctuationOrSpace)
+  .replace(/punctSpace/g, _punctuationOrSpace)
   .replace(/punct/g, _punctuation)
   .getRegex();
 
 // (6) Not allowed for _
 const emStrongRDelimUnd = edit(
   '^[^_*]*?\\*\\*[^_*]*?_[^_*]*?(?=\\*\\*)' // Skip orphan inside strong
-+ '|[^_]+(?=[^_])' // Consume to delim
-+ '|(?!_)[punct](_+)(?=[\\s]|$)' // (1) #___ can only be a Right Delimiter
-+ '|[^punct\\s](_+)(?!_)(?=[punct\\s]|$)' // (2) a___#, a___ can only be a Right Delimiter
-+ '|(?!_)[punct\\s](_+)(?=[^punct\\s])' // (3) #___a, ___a can only be Left Delimiter
-+ '|[\\s](_+)(?!_)(?=[punct])' // (4) ___# can only be Left Delimiter
-+ '|(?!_)[punct](_+)(?!_)(?=[punct])', 'gu') // (5) #___# can be either Left or Right Delimiter
+  + '|[^_]+(?=[^_])' // Consume to delim
+  + '|(?!_)punct(_+)(?=[\\s]|$)' // (1) #___ can only be a Right Delimiter
+  + '|notPunctSpace(_+)(?!_)(?=punctSpace|$)' // (2) a___#, a___ can only be a Right Delimiter
+  + '|(?!_)punctSpace(_+)(?=notPunctSpace)' // (3) #___a, ___a can only be Left Delimiter
+  + '|[\\s](_+)(?!_)(?=punct)' // (4) ___# can only be Left Delimiter
+  + '|(?!_)punct(_+)(?!_)(?=punct)', 'gu') // (5) #___# can be either Left or Right Delimiter
+  .replace(/notPunctSpace/g, _notPunctuationOrSpace)
+  .replace(/punctSpace/g, _punctuationOrSpace)
   .replace(/punct/g, _punctuation)
   .getRegex();
 
-const anyPunctuation = edit(/\\([punct])/, 'gu')
+const anyPunctuation = edit(/\\(punct)/, 'gu')
   .replace(/punct/g, _punctuation)
   .getRegex();
 
@@ -290,11 +296,11 @@ const autolink = edit(/^<(scheme:[^\s\x00-\x1f<>]*|email)>/)
 const _inlineComment = edit(_comment).replace('(?:-->|$)', '-->').getRegex();
 const tag = edit(
   '^comment'
-    + '|^</[a-zA-Z][\\w:-]*\\s*>' // self-closing tag
-    + '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag
-    + '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. <?php ?>
-    + '|^<![a-zA-Z]+\\s[\\s\\S]*?>' // declaration, e.g. <!DOCTYPE html>
-    + '|^<!\\[CDATA\\[[\\s\\S]*?\\]\\]>') // CDATA section
+  + '|^</[a-zA-Z][\\w:-]*\\s*>' // self-closing tag
+  + '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag
+  + '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. <?php ?>
+  + '|^<![a-zA-Z]+\\s[\\s\\S]*?>' // declaration, e.g. <!DOCTYPE html>
+  + '|^<!\\[CDATA\\[[\\s\\S]*?\\]\\]>') // CDATA section
   .replace('comment', _inlineComment)
   .replace('attribute', /\s+[a-zA-Z:_][\w.:-]*(?:\s*=\s*"[^"]*"|\s*=\s*'[^']*'|\s*=\s*[^\s"'=<>`]+)?/)
   .getRegex();