@@ -787,25 +787,49 @@ var Tokenizer_1 = class Tokenizer {
787787 }
788788 }
789789
790- strong ( src ) {
791- const cap = this . rules . inline . strong . exec ( src ) ;
792- if ( cap ) {
793- return {
794- type : 'strong' ,
795- raw : cap [ 0 ] ,
796- text : cap [ 4 ] || cap [ 3 ] || cap [ 2 ] || cap [ 1 ]
797- } ;
790+ strong ( src , maskedSrc , prevChar = '' ) {
791+ let match = this . rules . inline . strong . start . exec ( src ) ;
792+
793+ if ( match && ( ! match [ 1 ] || ( match [ 1 ] && ( prevChar === '' || this . rules . inline . punctuation . exec ( prevChar ) ) ) ) ) {
794+ maskedSrc = maskedSrc . slice ( - 1 * src . length ) ;
795+ const endReg = match [ 0 ] === '**' ? this . rules . inline . strong . endAst : this . rules . inline . strong . endUnd ;
796+
797+ endReg . lastIndex = 0 ;
798+
799+ let cap ;
800+ while ( ( match = endReg . exec ( maskedSrc ) ) != null ) {
801+ cap = this . rules . inline . strong . middle . exec ( maskedSrc . slice ( 0 , match . index + 3 ) ) ;
802+ if ( cap ) {
803+ return {
804+ type : 'strong' ,
805+ raw : src . slice ( 0 , cap [ 0 ] . length ) ,
806+ text : src . slice ( 2 , cap [ 0 ] . length - 2 )
807+ } ;
808+ }
809+ }
798810 }
799811 }
800812
801- em ( src ) {
802- const cap = this . rules . inline . em . exec ( src ) ;
803- if ( cap ) {
804- return {
805- type : 'em' ,
806- raw : cap [ 0 ] ,
807- text : cap [ 6 ] || cap [ 5 ] || cap [ 4 ] || cap [ 3 ] || cap [ 2 ] || cap [ 1 ]
808- } ;
813+ em ( src , maskedSrc , prevChar = '' ) {
814+ let match = this . rules . inline . em . start . exec ( src ) ;
815+
816+ if ( match && ( ! match [ 1 ] || ( match [ 1 ] && ( prevChar === '' || this . rules . inline . punctuation . exec ( prevChar ) ) ) ) ) {
817+ maskedSrc = maskedSrc . slice ( - 1 * src . length ) ;
818+ const endReg = match [ 0 ] === '*' ? this . rules . inline . em . endAst : this . rules . inline . em . endUnd ;
819+
820+ endReg . lastIndex = 0 ;
821+
822+ let cap ;
823+ while ( ( match = endReg . exec ( maskedSrc ) ) != null ) {
824+ cap = this . rules . inline . em . middle . exec ( maskedSrc . slice ( 0 , match . index + 2 ) ) ;
825+ if ( cap ) {
826+ return {
827+ type : 'em' ,
828+ raw : src . slice ( 0 , cap [ 0 ] . length ) ,
829+ text : src . slice ( 1 , cap [ 0 ] . length - 1 )
830+ } ;
831+ }
832+ }
809833 }
810834 }
811835
@@ -1101,19 +1125,74 @@ const inline = {
11011125 link : / ^ ! ? \[ ( l a b e l ) \] \( \s * ( h r e f ) (?: \s + ( t i t l e ) ) ? \s * \) / ,
11021126 reflink : / ^ ! ? \[ ( l a b e l ) \] \[ (? ! \s * \] ) ( (?: \\ [ \[ \] ] ? | [ ^ \[ \] \\ ] ) + ) \] / ,
11031127 nolink : / ^ ! ? \[ (? ! \s * \] ) ( (?: \[ [ ^ \[ \] ] * \] | \\ [ \[ \] ] | [ ^ \[ \] ] ) * ) \] (?: \[ \] ) ? / ,
1104- strong : / ^ _ _ ( [ ^ \s _ ] ) _ _ (? ! _ ) | ^ \* \* ( [ ^ \s * ] ) \* \* (? ! \* ) | ^ _ _ ( [ ^ \s ] [ \s \S ] * ?[ ^ \s ] ) _ _ (? ! _ ) | ^ \* \* ( [ ^ \s ] [ \s \S ] * ?[ ^ \s ] ) \* \* (? ! \* ) / ,
1105- em : / ^ _ ( [ ^ \s _ ] ) _ (? ! _ ) | ^ _ ( [ ^ \s _ < ] [ \s \S ] * ?[ ^ \s _ ] ) _ (? ! _ | [ ^ \s , p u n c t u a t i o n ] ) | ^ _ ( [ ^ \s _ < ] [ \s \S ] * ?[ ^ \s ] ) _ (? ! _ | [ ^ \s , p u n c t u a t i o n ] ) | ^ \* ( [ ^ \s * < \[ ] ) \* (? ! \* ) | ^ \* ( [ ^ \s < " ] [ \s \S ] * ?[ ^ \s \[ \* ] ) \* (? ! [ \] ` p u n c t u a t i o n ] ) | ^ \* ( [ ^ \s * " < \[ ] [ \s \S ] * [ ^ \s ] ) \* (? ! \* ) / ,
1128+ reflinkSearch : 'reflink|nolink(?!\\()' ,
1129+ strong : {
1130+ start : / ^ (?: ( \* \* (? = [ * p u n c t u a t i o n ] ) ) | \* \* ) (? ! [ \s ] ) | _ _ / , // (1) returns if starts w/ punctuation
1131+ middle : / ^ \* \* (?: (?: (? ! o v e r l a p S k i p ) (?: [ ^ * ] | \\ \* ) | o v e r l a p S k i p ) | \* (?: (? ! o v e r l a p S k i p ) (?: [ ^ * ] | \\ \* ) | o v e r l a p S k i p ) * ?\* ) + ?\* \* $ | ^ _ _ (? ! [ \s ] ) ( (?: (?: (? ! o v e r l a p S k i p ) (?: [ ^ _ ] | \\ _ ) | o v e r l a p S k i p ) | _ (?: (? ! o v e r l a p S k i p ) (?: [ ^ _ ] | \\ _ ) | o v e r l a p S k i p ) * ?_ ) + ?) _ _ $ / ,
1132+ endAst : / [ ^ p u n c t u a t i o n \s ] \* \* (? ! \* ) | [ p u n c t u a t i o n ] \* \* (? ! \* ) (?: (? = [ p u n c t u a t i o n \s ] | $ ) ) / , // last char can't be punct, or final * must also be followed by punct (or endline)
1133+ endUnd : / [ ^ \s ] _ _ (? ! _ ) (?: (? = [ p u n c t u a t i o n \s ] ) | $ ) / // last char can't be a space, and final _ must preceed punct or \s (or endline)
1134+ } ,
1135+ em : {
1136+ start : / ^ (?: ( \* (? = [ p u n c t u a t i o n ] ) ) | \* ) (? ! [ * \s ] ) | _ / , // (1) returns if starts w/ punctuation
1137+ middle : / ^ \* (?: (?: (? ! o v e r l a p S k i p ) (?: [ ^ * ] | \\ \* ) | o v e r l a p S k i p ) | \* (?: (? ! o v e r l a p S k i p ) (?: [ ^ * ] | \\ \* ) | o v e r l a p S k i p ) * ?\* ) + ?\* $ | ^ _ (? ! [ _ \s ] ) (?: (?: (? ! o v e r l a p S k i p ) (?: [ ^ _ ] | \\ _ ) | o v e r l a p S k i p ) | _ (?: (? ! o v e r l a p S k i p ) (?: [ ^ _ ] | \\ _ ) | o v e r l a p S k i p ) * ?_ ) + ?_ $ / ,
1138+ endAst : / [ ^ p u n c t u a t i o n \s ] \* (? ! \* ) | [ p u n c t u a t i o n ] \* (? ! \* ) (?: (? = [ p u n c t u a t i o n \s ] | $ ) ) / , // last char can't be punct, or final * must also be followed by punct (or endline)
1139+ endUnd : / [ ^ \s ] _ (? ! _ ) (?: (? = [ p u n c t u a t i o n \s ] ) | $ ) / // last char can't be a space, and final _ must preceed punct or \s (or endline)
1140+ } ,
11061141 code : / ^ ( ` + ) ( [ ^ ` ] | [ ^ ` ] [ \s \S ] * ?[ ^ ` ] ) \1(? ! ` ) / ,
11071142 br : / ^ ( { 2 , } | \\ ) \n (? ! \s * $ ) / ,
11081143 del : noopTest$1 ,
1109- text : / ^ ( ` + | [ ^ ` ] ) (?: [ \s \S ] * ?(?: (? = [ \\ < ! \[ ` * ] | \b _ | $ ) | [ ^ ] (? = { 2 , } \n ) ) | (? = { 2 , } \n ) ) /
1144+ text : / ^ ( ` + | [ ^ ` ] ) (?: [ \s \S ] * ?(?: (? = [ \\ < ! \[ ` * ] | \b _ | $ ) | [ ^ ] (? = { 2 , } \n ) ) | (? = { 2 , } \n ) ) / ,
1145+ punctuation : / ^ ( [ \s * p u n c t u a t i o n ] ) /
11101146} ;
11111147
11121148// list of punctuation marks from common mark spec
1113- // without ` and ] to workaround Rule 17 (inline code blocks/links)
1114- // without , to work around example 393
1115- inline . _punctuation = '!"#$%&\'()*+\\-./:;<=>?@\\[^_{|}~' ;
1116- inline . em = edit$1 ( inline . em ) . replace ( / p u n c t u a t i o n / g, inline . _punctuation ) . getRegex ( ) ;
1149+ // without * and _ to workaround cases with double emphasis
1150+ inline . _punctuation = '!"#$%&\'()+\\-.,/:;<=>?@\\[\\]`^{|}~' ;
1151+ inline . punctuation = edit$1 ( inline . punctuation ) . replace ( / p u n c t u a t i o n / g, inline . _punctuation ) . getRegex ( ) ;
1152+
1153+ // sequences em should skip over [title](link), `code`, <html>
1154+ inline . _blockSkip = '\\[[^\\]]*?\\]\\([^\\)]*?\\)|`[^`]*?`|<[^>]*?>' ;
1155+ inline . _overlapSkip = '__[^_]*?__|\\*\\*\\[^\\*\\]*?\\*\\*' ;
1156+
1157+ inline . em . start = edit$1 ( inline . em . start )
1158+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1159+ . getRegex ( ) ;
1160+
1161+ inline . em . middle = edit$1 ( inline . em . middle )
1162+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1163+ . replace ( / o v e r l a p S k i p / g, inline . _overlapSkip )
1164+ . getRegex ( ) ;
1165+
1166+ inline . em . endAst = edit$1 ( inline . em . endAst , 'g' )
1167+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1168+ . getRegex ( ) ;
1169+
1170+ inline . em . endUnd = edit$1 ( inline . em . endUnd , 'g' )
1171+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1172+ . getRegex ( ) ;
1173+
1174+ inline . strong . start = edit$1 ( inline . strong . start )
1175+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1176+ . getRegex ( ) ;
1177+
1178+ inline . strong . middle = edit$1 ( inline . strong . middle )
1179+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1180+ . replace ( / b l o c k S k i p / g, inline . _blockSkip )
1181+ . getRegex ( ) ;
1182+
1183+ inline . strong . endAst = edit$1 ( inline . strong . endAst , 'g' )
1184+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1185+ . getRegex ( ) ;
1186+
1187+ inline . strong . endUnd = edit$1 ( inline . strong . endUnd , 'g' )
1188+ . replace ( / p u n c t u a t i o n / g, inline . _punctuation )
1189+ . getRegex ( ) ;
1190+
1191+ inline . blockSkip = edit$1 ( inline . _blockSkip , 'g' )
1192+ . getRegex ( ) ;
1193+
1194+ inline . overlapSkip = edit$1 ( inline . _overlapSkip , 'g' )
1195+ . getRegex ( ) ;
11171196
11181197inline . _escapes = / \\ ( [ ! " # $ % & ' ( ) * + , \- . / : ; < = > ? @ \[ \] \\ ^ _ ` { | } ~ ] ) / g;
11191198
@@ -1145,6 +1224,11 @@ inline.reflink = edit$1(inline.reflink)
11451224 . replace ( 'label' , inline . _label )
11461225 . getRegex ( ) ;
11471226
1227+ inline . reflinkSearch = edit$1 ( inline . reflinkSearch , 'g' )
1228+ . replace ( 'reflink' , inline . reflink )
1229+ . replace ( 'nolink' , inline . nolink )
1230+ . getRegex ( ) ;
1231+
11481232/**
11491233 * Normal Inline Grammar
11501234 */
@@ -1156,8 +1240,18 @@ inline.normal = merge$1({}, inline);
11561240 */
11571241
11581242inline . pedantic = merge$1 ( { } , inline . normal , {
1159- strong : / ^ _ _ (? = \S ) ( [ \s \S ] * ?\S ) _ _ (? ! _ ) | ^ \* \* (? = \S ) ( [ \s \S ] * ?\S ) \* \* (? ! \* ) / ,
1160- em : / ^ _ (? = \S ) ( [ \s \S ] * ?\S ) _ (? ! _ ) | ^ \* (? = \S ) ( [ \s \S ] * ?\S ) \* (? ! \* ) / ,
1243+ strong : {
1244+ start : / ^ _ _ | \* \* / ,
1245+ middle : / ^ _ _ (? = \S ) ( [ \s \S ] * ?\S ) _ _ (? ! _ ) | ^ \* \* (? = \S ) ( [ \s \S ] * ?\S ) \* \* (? ! \* ) / ,
1246+ endAst : / \* \* (? ! \* ) / g,
1247+ endUnd : / _ _ (? ! _ ) / g
1248+ } ,
1249+ em : {
1250+ start : / ^ _ | \* / ,
1251+ middle : / ^ ( ) \* (? = \S ) ( [ \s \S ] * ?\S ) \* (? ! \* ) | ^ _ (? = \S ) ( [ \s \S ] * ?\S ) _ (? ! _ ) / ,
1252+ endAst : / \* (? ! \* ) / g,
1253+ endUnd : / _ (? ! _ ) / g
1254+ } ,
11611255 link : edit$1 ( / ^ ! ? \[ ( l a b e l ) \] \( ( .* ?) \) / )
11621256 . replace ( 'label' , inline . _label )
11631257 . getRegex ( ) ,
@@ -1516,9 +1610,29 @@ var Lexer_1 = class Lexer {
15161610 /**
15171611 * Lexing/Compiling
15181612 */
1519- inlineTokens ( src , tokens = [ ] , inLink = false , inRawBlock = false ) {
1613+ inlineTokens ( src , tokens = [ ] , inLink = false , inRawBlock = false , prevChar = '' ) {
15201614 let token ;
15211615
1616+ // String with links masked to avoid interference with em and strong
1617+ let maskedSrc = src ;
1618+ let match ;
1619+
1620+ // Mask out reflinks
1621+ if ( this . tokens . links ) {
1622+ const links = Object . keys ( this . tokens . links ) ;
1623+ if ( links . length > 0 ) {
1624+ while ( ( match = this . tokenizer . rules . inline . reflinkSearch . exec ( maskedSrc ) ) != null ) {
1625+ if ( links . includes ( match [ 0 ] . slice ( match [ 0 ] . lastIndexOf ( '[' ) + 1 , - 1 ) ) ) {
1626+ maskedSrc = maskedSrc . slice ( 0 , match . index ) + '[' + 'a' . repeat ( match [ 0 ] . length - 2 ) + ']' + maskedSrc . slice ( this . tokenizer . rules . inline . reflinkSearch . lastIndex ) ;
1627+ }
1628+ }
1629+ }
1630+ }
1631+ // Mask out other blocks
1632+ while ( ( match = this . tokenizer . rules . inline . blockSkip . exec ( maskedSrc ) ) != null ) {
1633+ maskedSrc = maskedSrc . slice ( 0 , match . index ) + '[' + 'a' . repeat ( match [ 0 ] . length - 2 ) + ']' + maskedSrc . slice ( this . tokenizer . rules . inline . blockSkip . lastIndex ) ;
1634+ }
1635+
15221636 while ( src ) {
15231637 // escape
15241638 if ( token = this . tokenizer . escape ( src ) ) {
@@ -1557,15 +1671,15 @@ var Lexer_1 = class Lexer {
15571671 }
15581672
15591673 // strong
1560- if ( token = this . tokenizer . strong ( src ) ) {
1674+ if ( token = this . tokenizer . strong ( src , maskedSrc , prevChar ) ) {
15611675 src = src . substring ( token . raw . length ) ;
15621676 token . tokens = this . inlineTokens ( token . text , [ ] , inLink , inRawBlock ) ;
15631677 tokens . push ( token ) ;
15641678 continue ;
15651679 }
15661680
15671681 // em
1568- if ( token = this . tokenizer . em ( src ) ) {
1682+ if ( token = this . tokenizer . em ( src , maskedSrc , prevChar ) ) {
15691683 src = src . substring ( token . raw . length ) ;
15701684 token . tokens = this . inlineTokens ( token . text , [ ] , inLink , inRawBlock ) ;
15711685 tokens . push ( token ) ;
@@ -1611,6 +1725,7 @@ var Lexer_1 = class Lexer {
16111725 // text
16121726 if ( token = this . tokenizer . inlineText ( src , inRawBlock , smartypants ) ) {
16131727 src = src . substring ( token . raw . length ) ;
1728+ prevChar = token . raw . slice ( - 1 ) ;
16141729 tokens . push ( token ) ;
16151730 continue ;
16161731 }
0 commit comments