asciidoctor 2.0.7 → 2.0.12

data/data/stylesheets/asciidoctor-default.css

@@ -1,10 +1,9 @@
 /* Asciidoctor default stylesheet | MIT License | https://asciidoctor.org */
-/* Uncomment @import statement when using as custom stylesheet */
+/* Uncomment @import statement to use as custom stylesheet */
 /*@import "https://fonts.googleapis.com/css?family=Open+Sans:300,300italic,400,400italic,600,600italic%7CNoto+Serif:400,400italic,700,700italic%7CDroid+Sans+Mono:400,700";*/
 article,aside,details,figcaption,figure,footer,header,hgroup,main,nav,section{display:block}
-audio,canvas,video{display:inline-block}
+audio,video{display:inline-block}
 audio:not([controls]){display:none;height:0}
-script{display:none!important}
 html{font-family:sans-serif;-ms-text-size-adjust:100%;-webkit-text-size-adjust:100%}
 a{background:none}
 a:focus{outline:thin dotted}
@@ -38,7 +37,7 @@ textarea{overflow:auto;vertical-align:top}
 table{border-collapse:collapse;border-spacing:0}
 *,*::before,*::after{-moz-box-sizing:border-box;-webkit-box-sizing:border-box;box-sizing:border-box}
 html,body{font-size:100%}
-body{background:#fff;color:rgba(0,0,0,.8);padding:0;margin:0;font-family:"Noto Serif","DejaVu Serif",serif;font-weight:400;font-style:normal;line-height:1;position:relative;cursor:auto;tab-size:4;-moz-osx-font-smoothing:grayscale;-webkit-font-smoothing:antialiased}
+body{background:#fff;color:rgba(0,0,0,.8);padding:0;margin:0;font-family:"Noto Serif","DejaVu Serif",serif;font-weight:400;font-style:normal;line-height:1;position:relative;cursor:auto;tab-size:4;word-wrap:anywhere;-moz-osx-font-smoothing:grayscale;-webkit-font-smoothing:antialiased}
 a:hover{cursor:pointer}
 img,object,embed{max-width:100%;height:auto}
 object,embed{height:100%}
@@ -53,10 +52,8 @@ img{-ms-interpolation-mode:bicubic}
 img,object,svg{display:inline-block;vertical-align:middle}
 textarea{height:auto;min-height:50px}
 select{width:100%}
-.center{margin-left:auto;margin-right:auto}
-.stretch{width:100%}
 .subheader,.admonitionblock td.content>.title,.audioblock>.title,.exampleblock>.title,.imageblock>.title,.listingblock>.title,.literalblock>.title,.stemblock>.title,.openblock>.title,.paragraph>.title,.quoteblock>.title,table.tableblock>.title,.verseblock>.title,.videoblock>.title,.dlist>.title,.olist>.title,.ulist>.title,.qlist>.title,.hdlist>.title{line-height:1.45;color:#7a2518;font-weight:400;margin-top:0;margin-bottom:.25em}
-div,dl,dt,dd,ul,ol,li,h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6,pre,form,p,blockquote,th,td{margin:0;padding:0;direction:ltr}
+div,dl,dt,dd,ul,ol,li,h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6,pre,form,p,blockquote,th,td{margin:0;padding:0}
 a{color:#2156a5;text-decoration:underline;line-height:inherit}
 a:hover,a:focus{color:#1d4b8f}
 a img{border:0}
@@ -96,19 +93,22 @@ h1{font-size:2.75em}
 h2{font-size:2.3125em}
 h3,#toctitle,.sidebarblock>.content>.title{font-size:1.6875em}
 h4{font-size:1.4375em}}
-table{background:#fff;margin-bottom:1.25em;border:solid 1px #dedede}
+table{background:#fff;margin-bottom:1.25em;border:solid 1px #dedede;word-wrap:normal}
 table thead,table tfoot{background:#f7f8f7}
 table thead tr th,table thead tr td,table tfoot tr th,table tfoot tr td{padding:.5em .625em .625em;font-size:inherit;color:rgba(0,0,0,.8);text-align:left}
 table tr th,table tr td{padding:.5625em .625em;font-size:inherit;color:rgba(0,0,0,.8)}
 table tr.even,table tr.alt{background:#f8f8f7}
-table thead tr th,table tfoot tr th,table tbody tr td,table tr td,table tfoot tr td{display:table-cell;line-height:1.6}
+table thead tr th,table tfoot tr th,table tbody tr td,table tr td,table tfoot tr td{line-height:1.6}
 h1,h2,h3,#toctitle,.sidebarblock>.content>.title,h4,h5,h6{line-height:1.2;word-spacing:-.05em}
 h1 strong,h2 strong,h3 strong,#toctitle strong,.sidebarblock>.content>.title strong,h4 strong,h5 strong,h6 strong{font-weight:400}
+.center{margin-left:auto;margin-right:auto}
+.stretch{width:100%}
 .clearfix::before,.clearfix::after,.float-group::before,.float-group::after{content:" ";display:table}
 .clearfix::after,.float-group::after{clear:both}
-:not(pre):not([class^=L])>code{font-size:.9375em;font-style:normal!important;letter-spacing:0;padding:.1em .5ex;word-spacing:-.15em;background:#f7f7f8;-webkit-border-radius:4px;border-radius:4px;line-height:1.45;text-rendering:optimizeSpeed;word-wrap:break-word}
-:not(pre)>code.nobreak{word-wrap:normal}
-:not(pre)>code.nowrap{white-space:nowrap}
+:not(pre).nobreak{word-wrap:normal}
+:not(pre).nowrap{white-space:nowrap}
+:not(pre).pre-wrap{white-space:pre-wrap}
+:not(pre):not([class^=L])>code{font-size:.9375em;font-style:normal!important;letter-spacing:0;padding:.1em .5ex;word-spacing:-.15em;background:#f7f7f8;-webkit-border-radius:4px;border-radius:4px;line-height:1.45;text-rendering:optimizeSpeed}
 pre{color:rgba(0,0,0,.9);font-family:"Droid Sans Mono","DejaVu Sans Mono",monospace;line-height:1.45;text-rendering:optimizeSpeed}
 pre code,pre pre{color:inherit;font-size:inherit;line-height:inherit}
 pre>code{display:block}
@@ -173,7 +173,7 @@ body.toc2.toc-right{padding-left:0;padding-right:20em}}
 #content #toc{border-style:solid;border-width:1px;border-color:#e0e0dc;margin-bottom:1.25em;padding:1.25em;background:#f8f8f7;-webkit-border-radius:4px;border-radius:4px}
 #content #toc>:first-child{margin-top:0}
 #content #toc>:last-child{margin-bottom:0}
-#footer{max-width:100%;background:rgba(0,0,0,.8);padding:1.25em}
+#footer{max-width:none;background:rgba(0,0,0,.8);padding:1.25em}
 #footer-text{color:rgba(255,255,255,.8);line-height:1.44}
 #content{margin-bottom:.625em}
 .sect1{padding-bottom:.625em}
@@ -196,7 +196,7 @@ table.tableblock #preamble>.sectionbody>[class="paragraph"]:first-of-type p{font
 .admonitionblock>table td.icon{text-align:center;width:80px}
 .admonitionblock>table td.icon img{max-width:none}
 .admonitionblock>table td.icon .title{font-weight:bold;font-family:"Open Sans","DejaVu Sans",sans-serif;text-transform:uppercase}
-.admonitionblock>table td.content{padding-left:1.125em;padding-right:1.25em;border-left:1px solid #dddddf;color:rgba(0,0,0,.6)}
+.admonitionblock>table td.content{padding-left:1.125em;padding-right:1.25em;border-left:1px solid #dddddf;color:rgba(0,0,0,.6);word-wrap:anywhere}
 .admonitionblock>table td.content>:last-child>:last-child{margin-bottom:0}
 .exampleblock>.content{border-style:solid;border-width:1px;border-color:#e6e6e6;margin-bottom:1.25em;padding:1.25em;background:#fff;-webkit-border-radius:4px;border-radius:4px}
 .exampleblock>.content>:first-child{margin-top:0}
@@ -206,11 +206,11 @@ table.tableblock #preamble>.sectionbody>[class="paragraph"]:first-of-type p{font
 .sidebarblock>:last-child{margin-bottom:0}
 .sidebarblock>.content>.title{color:#7a2518;margin-top:0;text-align:center}
 .exampleblock>.content>:last-child>:last-child,.exampleblock>.content .olist>ol>li:last-child>:last-child,.exampleblock>.content .ulist>ul>li:last-child>:last-child,.exampleblock>.content .qlist>ol>li:last-child>:last-child,.sidebarblock>.content>:last-child>:last-child,.sidebarblock>.content .olist>ol>li:last-child>:last-child,.sidebarblock>.content .ulist>ul>li:last-child>:last-child,.sidebarblock>.content .qlist>ol>li:last-child>:last-child{margin-bottom:0}
-.literalblock pre,.listingblock>.content>pre{-webkit-border-radius:4px;border-radius:4px;word-wrap:break-word;overflow-x:auto;padding:1em;font-size:.8125em}
+.literalblock pre,.listingblock>.content>pre{-webkit-border-radius:4px;border-radius:4px;overflow-x:auto;padding:1em;font-size:.8125em}
 @media screen and (min-width:768px){.literalblock pre,.listingblock>.content>pre{font-size:.90625em}}
 @media screen and (min-width:1280px){.literalblock pre,.listingblock>.content>pre{font-size:1em}}
+.literalblock pre,.listingblock>.content>pre:not(.highlight),.listingblock>.content>pre[class="highlight"],.listingblock>.content>pre[class^="highlight "]{background:#f7f7f8}
 .literalblock.output pre{color:#f7f7f8;background:rgba(0,0,0,.9)}
-.listingblock>.content>pre:not(.highlight),.listingblock>.content>pre[class="highlight"],.listingblock>.content>pre[class^="highlight "]{background:#f7f7f8}
 .listingblock>.content{position:relative}
 .listingblock code[data-lang]::before{display:none;content:attr(data-lang);position:absolute;font-size:.75em;top:.425rem;right:.5rem;line-height:1;text-transform:uppercase;color:inherit;opacity:.5}
 .listingblock:hover code[data-lang]::before{display:block}
@@ -231,7 +231,7 @@ table.linenotable td.linenos{border-right:1px solid currentColor;opacity:.35;pad
 pre.pygments .lineno{border-right:1px solid currentColor;opacity:.35;display:inline-block;margin-right:.75em}
 pre.pygments .lineno::before{content:"";margin-right:-.125em}
 .quoteblock{margin:0 1em 1.25em 1.5em;display:table}
-.quoteblock>.title{margin-left:-1.5em;margin-bottom:.75em}
+.quoteblock:not(.excerpt)>.title{margin-left:-1.5em;margin-bottom:.75em}
 .quoteblock blockquote,.quoteblock p{color:rgba(0,0,0,.85);font-size:1.15rem;line-height:1.75;word-spacing:.1em;letter-spacing:0;font-style:italic;text-align:justify}
 .quoteblock blockquote{margin:0;padding:0;border:0}
 .quoteblock blockquote::before{content:"\201c";float:left;font-size:2.75em;font-weight:bold;line-height:.6em;margin-left:-.6em;color:#7a2518;text-shadow:0 1px 2px rgba(0,0,0,.1)}
@@ -248,23 +248,24 @@ pre.pygments .lineno::before{content:"";margin-right:-.125em}
 .quoteblock.abstract blockquote,.quoteblock.abstract p,.quoteblock.excerpt blockquote,.quoteblock.excerpt p,.quoteblock .quoteblock blockquote,.quoteblock .quoteblock p{line-height:1.6;word-spacing:0}
 .quoteblock.abstract{margin:0 1em 1.25em;display:block}
 .quoteblock.abstract>.title{margin:0 0 .375em;font-size:1.15em;text-align:center}
-.quoteblock.excerpt,.quoteblock .quoteblock{margin:0 0 1.25em;padding:0 0 .25em 1em;border-left:.25em solid #dddddf}
+.quoteblock.excerpt>blockquote,.quoteblock .quoteblock{padding:0 0 .25em 1em;border-left:.25em solid #dddddf}
+.quoteblock.excerpt,.quoteblock .quoteblock{margin-left:0}
 .quoteblock.excerpt blockquote,.quoteblock.excerpt p,.quoteblock .quoteblock blockquote,.quoteblock .quoteblock p{color:inherit;font-size:1.0625rem}
 .quoteblock.excerpt .attribution,.quoteblock .quoteblock .attribution{color:inherit;text-align:left;margin-right:0}
-table.tableblock{max-width:100%;border-collapse:separate}
 p.tableblock:last-child{margin-bottom:0}
-td.tableblock>.content{margin-bottom:-1.25em}
+td.tableblock>.content{margin-bottom:1.25em;word-wrap:anywhere}
+td.tableblock>.content>:last-child{margin-bottom:-1.25em}
 table.tableblock,th.tableblock,td.tableblock{border:0 solid #dedede}
-table.grid-all>thead>tr>.tableblock,table.grid-all>tbody>tr>.tableblock{border-width:0 1px 1px 0}
-table.grid-all>tfoot>tr>.tableblock{border-width:1px 1px 0 0}
-table.grid-cols>*>tr>.tableblock{border-width:0 1px 0 0}
-table.grid-rows>thead>tr>.tableblock,table.grid-rows>tbody>tr>.tableblock{border-width:0 0 1px}
-table.grid-rows>tfoot>tr>.tableblock{border-width:1px 0 0}
-table.grid-all>*>tr>.tableblock:last-child,table.grid-cols>*>tr>.tableblock:last-child{border-right-width:0}
-table.grid-all>tbody>tr:last-child>.tableblock,table.grid-all>thead:last-child>tr>.tableblock,table.grid-rows>tbody>tr:last-child>.tableblock,table.grid-rows>thead:last-child>tr>.tableblock{border-bottom-width:0}
+table.grid-all>*>tr>*{border-width:1px}
+table.grid-cols>*>tr>*{border-width:0 1px}
+table.grid-rows>*>tr>*{border-width:1px 0}
 table.frame-all{border-width:1px}
+table.frame-ends{border-width:1px 0}
 table.frame-sides{border-width:0 1px}
-table.frame-topbot,table.frame-ends{border-width:1px 0}
+table.frame-none>colgroup+*>:first-child>*,table.frame-sides>colgroup+*>:first-child>*{border-top-width:0}
+table.frame-none>:last-child>:last-child>*,table.frame-sides>:last-child>:last-child>*{border-bottom-width:0}
+table.frame-none>*>tr>:first-child,table.frame-ends>*>tr>:first-child{border-left-width:0}
+table.frame-none>*>tr>:last-child,table.frame-ends>*>tr>:last-child{border-right-width:0}
 table.stripes-all tr,table.stripes-odd tr:nth-of-type(odd),table.stripes-even tr:nth-of-type(even),table.stripes-hover tr:hover{background:#f8f8f7}
 th.halign-left,td.halign-left{text-align:left}
 th.halign-right,td.halign-right{text-align:right}
@@ -273,7 +274,7 @@ th.valign-top,td.valign-top{vertical-align:top}
 th.valign-bottom,td.valign-bottom{vertical-align:bottom}
 th.valign-middle,td.valign-middle{vertical-align:middle}
 table thead th,table tfoot th{font-weight:bold}
-tbody tr th{display:table-cell;line-height:1.6;background:#f7f8f7}
+tbody tr th{background:#f7f8f7}
 tbody tr th,tbody tr th p,tfoot tr th,tfoot tr th p{color:rgba(0,0,0,.8);font-weight:bold}
 p.tableblock>code:only-child{background:none;padding:0}
 p.tableblock{font-size:1em}
@@ -302,6 +303,7 @@ ol.lowergreek{list-style-type:lower-greek}
 .hdlist>table>tbody>tr,.colist>table>tbody>tr{background:none}
 td.hdlist1,td.hdlist2{vertical-align:top;padding:0 .625em}
 td.hdlist1{font-weight:bold;padding-bottom:1.25em}
+td.hdlist2{word-wrap:anywhere}
 .literalblock+.colist,.listingblock+.colist{margin-top:-.5em}
 .colist td:not([class]):first-child{padding:.4em .75em 0;line-height:1;vertical-align:top}
 .colist td:not([class]):first-child img{max-width:none}
@@ -374,7 +376,7 @@ a span.icon>.fa{cursor:inherit}
 .admonitionblock td.icon .icon-warning::before{content:"\f071";color:#bf6900}
 .admonitionblock td.icon .icon-caution::before{content:"\f06d";color:#bf3400}
 .admonitionblock td.icon .icon-important::before{content:"\f06a";color:#bf0000}
-.conum[data-value]{display:inline-block;color:#fff!important;background:rgba(0,0,0,.8);-webkit-border-radius:100px;border-radius:100px;text-align:center;font-size:.75em;width:1.67em;height:1.67em;line-height:1.67em;font-family:"Open Sans","DejaVu Sans",sans-serif;font-style:normal;font-weight:bold}
+.conum[data-value]{display:inline-block;color:#fff!important;background:rgba(0,0,0,.8);-webkit-border-radius:50%;border-radius:50%;text-align:center;font-size:.75em;width:1.67em;height:1.67em;line-height:1.67em;font-family:"Open Sans","DejaVu Sans",sans-serif;font-style:normal;font-weight:bold}
 .conum[data-value] *{color:#fff!important}
 .conum[data-value]+b{display:none}
 .conum[data-value]::after{content:attr(data-value)}
@@ -401,6 +403,7 @@ thead{display:table-header-group}
 svg{max-width:100%}
 p,blockquote,dt,td.content{font-size:1em;orphans:3;widows:3}
 h2,h3,#toctitle,.sidebarblock>.content>.title{page-break-after:avoid}
+#header,#content,#footnotes,#footer{max-width:none}
 #toc,.sidebarblock,.exampleblock>.content{background:none!important}
 #toc{border-bottom:1px solid #dddddf!important;padding-bottom:0!important}
 body.book #header{text-align:center}

data/lib/asciidoctor.rb

@@ -148,7 +148,7 @@ module Asciidoctor
     # Compliance value: 'drop-line'
     define :attribute_missing, 'skip'
 
-    # AsciiDoc drops lines that contain an attribute unassignemnt.
+    # AsciiDoc drops lines that contain an attribute unassignment.
     # This behavior may need to be tuned depending on the circumstances.
     # Compliance value: 'drop-line'
     define :attribute_undefined, 'drop-line'
@@ -230,7 +230,7 @@ module Asciidoctor
 
   # Pointers to the preferred version for a given backend.
   BACKEND_ALIASES = {
-    'html'    => 'html5',
+    'html' => 'html5',
     'docbook' => 'docbook5'
   }
 
@@ -270,14 +270,14 @@ module Asciidoctor
 
   ADMONITION_STYLES = ['NOTE', 'TIP', 'IMPORTANT', 'WARNING', 'CAUTION'].to_set
 
-  ADMONITION_STYLE_HEADS = ['N', 'T', 'I', 'W', 'C'].to_set
+  ADMONITION_STYLE_HEADS = ::Set.new.tap {|accum| ADMONITION_STYLES.each {|s| accum << s.chr } }
 
   PARAGRAPH_STYLES = ['comment', 'example', 'literal', 'listing', 'normal', 'open', 'pass', 'quote', 'sidebar', 'source', 'verse', 'abstract', 'partintro'].to_set
 
   VERBATIM_STYLES = ['literal', 'listing', 'source', 'verse'].to_set
 
   DELIMITED_BLOCKS = {
-    '--'   => [:open, ['comment', 'example', 'literal', 'listing', 'pass', 'quote', 'sidebar', 'source', 'verse', 'admonition', 'abstract', 'partintro'].to_set],
+    '--' => [:open, ['comment', 'example', 'literal', 'listing', 'pass', 'quote', 'sidebar', 'source', 'verse', 'admonition', 'abstract', 'partintro'].to_set],
     '----' => [:listing, ['literal', 'source'].to_set],
     '....' => [:literal, ['listing', 'source'].to_set],
     '====' => [:example, ['admonition'].to_set],
@@ -289,24 +289,24 @@ module Asciidoctor
     ':===' => [:table, ::Set.new],
     '!===' => [:table, ::Set.new],
     '////' => [:comment, ::Set.new],
-    '```'  => [:fenced_code, ::Set.new]
+    '```' => [:fenced_code, ::Set.new]
   }
 
   DELIMITED_BLOCK_HEADS = {}.tap {|accum| DELIMITED_BLOCKS.each_key {|k| accum[k.slice 0, 2] = true } }
   DELIMITED_BLOCK_TAILS = {}.tap {|accum| DELIMITED_BLOCKS.each_key {|k| accum[k] = k[k.length - 1] if k.length == 4 } }
 
   # NOTE the 'figure' key as a string is historical and used by image blocks
-  CAPTION_ATTR_NAMES = { example: 'example-caption', 'figure' => 'figure-caption', listing: 'listing-caption', table: 'table-caption' }
+  CAPTION_ATTRIBUTE_NAMES = { example: 'example-caption', 'figure' => 'figure-caption', listing: 'listing-caption', table: 'table-caption' }
 
   LAYOUT_BREAK_CHARS = {
     '\'' => :thematic_break,
-    '<'  => :page_break
+    '<' => :page_break
   }
 
   MARKDOWN_THEMATIC_BREAK_CHARS = {
-    '-'  => :thematic_break,
-    '*'  => :thematic_break,
-    '_'  => :thematic_break
+    '-' => :thematic_break,
+    '*' => :thematic_break,
+    '_' => :thematic_break
   }
 
   HYBRID_LAYOUT_BREAK_CHARS = LAYOUT_BREAK_CHARS.merge MARKDOWN_THEMATIC_BREAK_CHARS
@@ -319,8 +319,8 @@ module Asciidoctor
   ORDERED_LIST_STYLES = [:arabic, :loweralpha, :lowerroman, :upperalpha, :upperroman] #, :lowergreek]
 
   ORDERED_LIST_KEYWORDS = {
-    #'arabic'     => '1',
-    #'decimal'    => '1',
+    #'arabic' => '1',
+    #'decimal' => '1',
     'loweralpha' => 'a',
     'lowerroman' => 'i',
     #'lowergreek' => 'a',
@@ -357,789 +357,86 @@ module Asciidoctor
 
   FONT_AWESOME_VERSION = '4.7.0'
 
-  HIGHLIGHT_JS_VERSION = '9.15.6'
-
-  MATHJAX_VERSION = '2.7.5'
+  HIGHLIGHT_JS_VERSION = '9.18.3'
+
+  MATHJAX_VERSION = '2.7.9'
+
+  DEFAULT_ATTRIBUTES = {
+    'appendix-caption' => 'Appendix',
+    'appendix-refsig' => 'Appendix',
+    'caution-caption' => 'Caution',
+    'chapter-refsig' => 'Chapter',
+    #'encoding' => 'UTF-8',
+    'example-caption' => 'Example',
+    'figure-caption' => 'Figure',
+    'important-caption' => 'Important',
+    'last-update-label' => 'Last updated',
+    #'listing-caption' => 'Listing',
+    'note-caption' => 'Note',
+    'part-refsig' => 'Part',
+    #'preface-title' => 'Preface',
+    'prewrap' => '',
+    'sectids' => '',
+    'section-refsig' => 'Section',
+    'table-caption' => 'Table',
+    'tip-caption' => 'Tip',
+    'toc-placement' => 'auto',
+    'toc-title' => 'Table of Contents',
+    'untitled-label' => 'Untitled',
+    'version-label' => 'Version',
+    'warning-caption' => 'Warning',
+  }
 
-  # attributes which be changed within the content of the document (but not
-  # header) because it has semantic meaning; ex. sectnums
+  # attributes which be changed throughout the flow of the document (e.g., sectnums)
   FLEXIBLE_ATTRIBUTES = ['sectnums']
 
-  # A collection of regular expressions used by the parser.
-  #
-  # NOTE The following pattern, which appears frequently, captures the
-  # contents between square brackets, ignoring escaped closing brackets
-  # (closing brackets prefixed with a backslash '\' character)
-  #
-  #   Pattern: \[(|#{CC_ALL}*?[^\\])\]
-  #   Matches: [enclosed text] and [enclosed [text\]], not [enclosed text \\] or [\\] (as these require a trailing space)
-  #
-  # NOTE \w only matches ASCII word characters, whereas [[:word:]] or \p{Word} matches any character in the Unicode word category.
-  #(pseudo)module Rx
-
-    ## Regular expression character classes (to ensure regexp compatibility between Ruby and JavaScript)
-    ## CC stands for "character class", CG stands for "character class group"
-
-    unless RUBY_ENGINE == 'opal'
-      # CC_ALL is any character, including newlines (must be accompanied by multiline regexp flag)
-      CC_ALL = '.'
-      # CC_ANY is any character except newlines
-      CC_ANY = '.'
-      CC_EOL = '$'
-      CC_ALPHA = CG_ALPHA = '\p{Alpha}'
-      CC_ALNUM = CG_ALNUM = '\p{Alnum}'
-      CG_BLANK = '\p{Blank}'
-      CC_WORD  = CG_WORD = '\p{Word}'
-    end
-
-    ## Document header
-
-    # Matches the author info line immediately following the document title.
-    #
-    # Examples
-    #
-    #   Doc Writer <doc@example.com>
-    #   Mary_Sue Brontë
-    #
-    AuthorInfoLineRx = /^(#{CG_WORD}[#{CC_WORD}\-'.]*)(?: +(#{CG_WORD}[#{CC_WORD}\-'.]*))?(?: +(#{CG_WORD}[#{CC_WORD}\-'.]*))?(?: +<([^>]+)>)?$/
-
-    # Matches the delimiter that separates multiple authors.
-    #
-    # Examples
-    #
-    #   Doc Writer; Junior Writer
-    #
-    AuthorDelimiterRx = /;(?: |$)/
-
-    # Matches the revision info line, which appears immediately following
-    # the author info line beneath the document title.
-    #
-    # Examples
-    #
-    #   v1.0
-    #   2013-01-01
-    #   v1.0, 2013-01-01: Ring in the new year release
-    #   1.0, Jan 01, 2013
-    #
-    RevisionInfoLineRx = /^(?:[^\d{]*(#{CC_ANY}*?),)? *(?!:)(#{CC_ANY}*?)(?: *(?!^),?: *(#{CC_ANY}*))?$/
-
-    # Matches the title and volnum in the manpage doctype.
-    #
-    # Examples
-    #
-    #   = asciidoctor(1)
-    #   = asciidoctor ( 1 )
-    #
-    ManpageTitleVolnumRx = /^(#{CC_ANY}+?) *\( *(#{CC_ANY}+?) *\)$/
-
-    # Matches the name and purpose in the manpage doctype.
-    #
-    # Examples
-    #
-    #   asciidoctor - converts AsciiDoc source files to HTML, DocBook and other formats
-    #
-    ManpageNamePurposeRx = /^(#{CC_ANY}+?) +- +(#{CC_ANY}+)$/
-
-    ## Preprocessor directives
-
-    # Matches a conditional preprocessor directive (e.g., ifdef, ifndef, ifeval and endif).
-    #
-    # Examples
-    #
-    #   ifdef::basebackend-html[]
-    #   ifndef::theme[]
-    #   ifeval::["{asciidoctor-version}" >= "0.1.0"]
-    #   ifdef::asciidoctor[Asciidoctor!]
-    #   endif::theme[]
-    #   endif::basebackend-html[]
-    #   endif::[]
-    #
-    ConditionalDirectiveRx = /^(\\)?(ifdef|ifndef|ifeval|endif)::(\S*?(?:([,+])\S*?)?)\[(#{CC_ANY}+)?\]$/
-
-    # Matches a restricted (read as safe) eval expression.
-    #
-    # Examples
-    #
-    #   "{asciidoctor-version}" >= "0.1.0"
-    #
-    EvalExpressionRx = /^(#{CC_ANY}+?) *([=!><]=|[><]) *(#{CC_ANY}+)$/
-
-    # Matches an include preprocessor directive.
-    #
-    # Examples
-    #
-    #   include::chapter1.ad[]
-    #   include::example.txt[lines=1;2;5..10]
-    #
-    IncludeDirectiveRx = /^(\\)?include::([^\[][^\[]*)\[(#{CC_ANY}+)?\]$/
-
-    # Matches a trailing tag directive in an include file.
-    #
-    # Examples
-    #
-    #   // tag::try-catch[]
-    #   try {
-    #     someMethod();
-    #   catch (Exception e) {
-    #     log(e);
-    #   }
-    #   // end::try-catch[]
-    # NOTE m flag is required for Asciidoctor.js
-    TagDirectiveRx = /\b(?:tag|(e)nd)::(\S+?)\[\](?=$|[ \r])/m
-
-    ## Attribute entries and references
-
-    # Matches a document attribute entry.
-    #
-    # Examples
-    #
-    #   :foo: bar
-    #   :First Name: Dan
-    #   :sectnums!:
-    #   :!toc:
-    #   :long-entry: Attribute value lines ending in ' \' \
-    #                are joined together as a single value, \
-    #                collapsing the line breaks and indentation to \
-    #                a single space.
-    #
-    AttributeEntryRx = /^:(!?#{CG_WORD}[^:]*):(?:[ \t]+(#{CC_ANY}*))?$/
-
-    # Matches invalid characters in an attribute name.
-    InvalidAttributeNameCharsRx = /[^-#{CC_WORD}]/
-
-    # Matches a pass inline macro that surrounds the value of an attribute
-    # entry once it has been parsed.
-    #
-    # Examples
-    #
-    #   pass:[text]
-    #   pass:a[{a} {b} {c}]
-    #
-    if RUBY_ENGINE == 'opal'
-      # NOTE In JavaScript, ^ and $ match the boundaries of the string when the m flag is not set
-      AttributeEntryPassMacroRx = /^pass:([a-z]+(?:,[a-z-]+)*)?\[(#{CC_ALL}*)\]$/
-    else
-      AttributeEntryPassMacroRx = /\Apass:([a-z]+(?:,[a-z-]+)*)?\[(.*)\]\Z/m
-    end
-
-    # Matches an inline attribute reference.
-    #
-    # Examples
-    #
-    #   {foobar} or {app_name} or {product-version}
-    #   {counter:sequence-name:1}
-    #   {set:foo:bar}
-    #   {set:name!}
-    #
-    AttributeReferenceRx = /(\\)?\{(#{CG_WORD}[-#{CC_WORD}]*|(set|counter2?):#{CC_ANY}+?)(\\)?\}/
-
-    ## Paragraphs and delimited blocks
-
-    # Matches an anchor (i.e., id + optional reference text) on a line above a block.
-    #
-    # Examples
-    #
-    #   [[idname]]
-    #   [[idname,Reference Text]]
-    #
-    BlockAnchorRx = /^\[\[(?:|([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+))?)\]\]$/
-
-    # Matches an attribute list above a block element.
-    #
-    # Examples
-    #
-    #   # strictly positional
-    #   [quote, Adam Smith, Wealth of Nations]
-    #
-    #   # name/value pairs
-    #   [NOTE, caption="Good to know"]
-    #
-    #   # as attribute reference
-    #   [{lead}]
-    #
-    BlockAttributeListRx = /^\[(|[#{CC_WORD}.#%{,"']#{CC_ANY}*)\]$/
-
-    # A combined pattern that matches either a block anchor or a block attribute list.
-    #
-    # TODO this one gets hit a lot, should be optimized as much as possible
-    BlockAttributeLineRx = /^\[(?:|[#{CC_WORD}.#%{,"']#{CC_ANY}*|\[(?:|[#{CC_ALPHA}_:][#{CC_WORD}:.-]*(?:, *#{CC_ANY}+)?)\])\]$/
-
-    # Matches a title above a block.
-    #
-    # Examples
-    #
-    #   .Title goes here
-    #
-    BlockTitleRx = /^\.(\.?[^ \t.]#{CC_ANY}*)$/
-
-    # Matches an admonition label at the start of a paragraph.
-    #
-    # Examples
-    #
-    #   NOTE: Just a little note.
-    #   TIP: Don't forget!
-    #
-    AdmonitionParagraphRx = /^(#{ADMONITION_STYLES.to_a.join '|'}):[ \t]+/
-
-    # Matches a literal paragraph, which is a line of text preceded by at least one space.
-    #
-    # Examples
-    #
-    #   <SPACE>Foo
-    #   <TAB>Foo
-    LiteralParagraphRx = /^([ \t]+#{CC_ANY}*)$/
-
-    # Matches a comment block.
-    #
-    # Examples
-    #
-    #   ////
-    #   This is a block comment.
-    #   It can span one or more lines.
-    #   ////
-    #CommentBlockRx = %r(^/{4,}$)
-
-    # Matches a comment line.
-    #
-    # Examples
-    #
-    #   // note to author
-    #
-    #CommentLineRx = %r(^//(?=[^/]|$))
-
-    ## Section titles
-
-    # Matches an Atx (single-line) section title.
-    #
-    # Examples
-    #
-    #   == Foo
-    #   // ^ a level 1 (h2) section title
-    #
-    #   == Foo ==
-    #   // ^ also a level 1 (h2) section title
-    #
-    AtxSectionTitleRx = /^(=={0,5})[ \t]+(#{CC_ANY}+?)(?:[ \t]+\1)?$/
-
-    # Matches an extended Atx section title that includes support for the Markdown variant.
-    ExtAtxSectionTitleRx = /^(=={0,5}|#\#{0,5})[ \t]+(#{CC_ANY}+?)(?:[ \t]+\1)?$/
-
-    # Matches the title only (first line) of an Setext (two-line) section title.
-    # The title cannot begin with a dot and must have at least one alphanumeric character.
-    SetextSectionTitleRx = /^((?!\.)#{CC_ANY}*?#{CG_ALNUM}#{CC_ANY}*)$/
-
-    # Matches an anchor (i.e., id + optional reference text) inside a section title.
-    #
-    # Examples
-    #
-    #   Section Title [[idname]]
-    #   Section Title [[idname,Reference Text]]
-    #
-    InlineSectionAnchorRx = / (\\)?\[\[([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+))?\]\]$/
-
-    # Matches invalid ID characters in a section title.
-    #
-    # NOTE uppercase chars not included since expression is only run on a lowercase string
-    InvalidSectionIdCharsRx = /<[^>]+>|&(?:[a-z][a-z]+\d{0,2}|#\d\d\d{0,4}|#x[\da-f][\da-f][\da-f]{0,3});|[^ #{CC_WORD}\-.]+?/
-
-    # Matches an explicit section level style like sect1
-    #
-    SectionLevelStyleRx = /^sect\d$/
-
-    ## Lists
-
-    # Detects the start of any list item.
-    #
-    # NOTE we only have to check as far as the blank character because we know it means non-whitespace follows.
-    # IMPORTANT if this regexp does not agree with the regexp for each list type, the parser will hang.
-    AnyListRx = %r(^(?:[ \t]*(?:-|\*\**|\.\.*|\u2022|\d+\.|[a-zA-Z]\.|[IVXivx]+\))[ \t]|(?!//[^/])[ \t]*[^ \t]#{CC_ANY}*?(?::::{0,2}|;;)(?:$|[ \t])|<?\d+>[ \t]))
-
-    # Matches an unordered list item (one level for hyphens, up to 5 levels for asterisks).
-    #
-    # Examples
-    #
-    #   * Foo
-    #   - Foo
-    #
-    # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
-    UnorderedListRx = /^[ \t]*(-|\*\**|\u2022)[ \t]+(#{CC_ANY}*)$/
-
-    # Matches an ordered list item (explicit numbering or up to 5 consecutive dots).
-    #
-    # Examples
-    #
-    #   . Foo
-    #   .. Foo
-    #   1. Foo (arabic, default)
-    #   a. Foo (loweralpha)
-    #   A. Foo (upperalpha)
-    #   i. Foo (lowerroman)
-    #   I. Foo (upperroman)
-    #
-    # NOTE leading space match is not always necessary, but is used for list reader
-    # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
-    OrderedListRx = /^[ \t]*(\.\.*|\d+\.|[a-zA-Z]\.|[IVXivx]+\))[ \t]+(#{CC_ANY}*)$/
-
-    # Matches the ordinals for each type of ordered list.
-    OrderedListMarkerRxMap = {
-      arabic: /\d+\./,
-      loweralpha: /[a-z]\./,
-      lowerroman: /[ivx]+\)/,
-      upperalpha: /[A-Z]\./,
-      upperroman: /[IVX]+\)/,
-      #lowergreek: /[a-z]\]/,
-    }
-
-    # Matches a description list entry.
-    #
-    # Examples
-    #
-    #   foo::
-    #   bar:::
-    #   baz::::
-    #   blah;;
-    #
-    #   # the term may be followed by a description on the same line...
-    #
-    #   foo:: The metasyntactic variable that commonly accompanies 'bar' (see also, <<bar>>).
-    #
-    #   # ...or on a separate line, which may optionally be indented
-    #
-    #   foo::
-    #     The metasyntactic variable that commonly accompanies 'bar' (see also, <<bar>>).
-    #
-    #   # attribute references may be used in both the term and the description
-    #
-    #   {foo-term}:: {foo-desc}
-    #
-    # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
-    # NOTE must skip line comment when looking for next list item inside list
-    DescriptionListRx = %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?)(:::{0,2}|;;)(?:$|[ \t]+(#{CC_ANY}*)$))
-
-    # Matches a sibling description list item (excluding the delimiter specified by the key).
-    # NOTE must skip line comment when looking for sibling list item
-    DescriptionListSiblingRx = {
-      '::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(::)(?:$|[ \t]+(#{CC_ANY}*)$)),
-      ':::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(:::)(?:$|[ \t]+(#{CC_ANY}*)$)),
-      '::::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(::::)(?:$|[ \t]+(#{CC_ANY}*)$)),
-      ';;' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?)(;;)(?:$|[ \t]+(#{CC_ANY}*)$))
-    }
-
-    # Matches a callout list item.
-    #
-    # Examples
-    #
-    #   <1> Explanation
-    #
-    # or
-    #
-    #   <.> Explanation with automatic number
-    #
-    # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
-    CalloutListRx = /^<(\d+|\.)>[ \t]+(#{CC_ANY}*)$/
-
-    # Matches a callout reference inside literal text.
-    #
-    # Examples
-    #   <1> (optionally prefixed by //, #, -- or ;; line comment chars)
-    #   <1> <2> (multiple callouts on one line)
-    #   <!--1--> (for XML-based languages)
-    #   <.> (auto-numbered)
-    #
-    # NOTE extract regexps are applied line-by-line, so we can use $ as end-of-line char
-    CalloutExtractRx = %r(((?://|#|--|;;) ?)?(\\)?<!?(|--)(\d+|\.)\3>(?=(?: ?\\?<!?\3(?:\d+|\.)\3>)*$))
-    CalloutExtractRxt = '(\\\\)?<()(\\d+|\\.)>(?=(?: ?\\\\?<(?:\\d+|\\.)>)*$)'
-    CalloutExtractRxMap = ::Hash.new {|h, k| h[k] = /(#{k.empty? ? '' : "#{::Regexp.escape k} ?"})?#{CalloutExtractRxt}/ }
-    # NOTE special characters have not been replaced when scanning
-    CalloutScanRx = /\\?<!?(|--)(\d+|\.)\1>(?=(?: ?\\?<!?\1(?:\d+|\.)\1>)*#{CC_EOL})/
-    # NOTE special characters have already been replaced when converting to an SGML format
-    CalloutSourceRx = %r(((?://|#|--|;;) ?)?(\\)?&lt;!?(|--)(\d+|\.)\3&gt;(?=(?: ?\\?&lt;!?\3(?:\d+|\.)\3&gt;)*#{CC_EOL}))
-    CalloutSourceRxt = "(\\\\)?&lt;()(\\d+|\\.)&gt;(?=(?: ?\\\\?&lt;(?:\\d+|\\.)&gt;)*#{CC_EOL})"
-    CalloutSourceRxMap = ::Hash.new {|h, k| h[k] = /(#{k.empty? ? '' : "#{::Regexp.escape k} ?"})?#{CalloutSourceRxt}/ }
-
-    # A Hash of regexps for lists used for dynamic access.
-    ListRxMap = {
-      ulist: UnorderedListRx,
-      olist: OrderedListRx,
-      dlist: DescriptionListRx,
-      colist: CalloutListRx,
-    }
-
-    ## Tables
-
-    # Parses the column spec (i.e., colspec) for a table.
-    #
-    # Examples
-    #
-    #   1*h,2*,^3e
-    #
-    ColumnSpecRx = /^(?:(\d+)\*)?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?(\d+%?|~)?([a-z])?$/
-
-    # Parses the start and end of a cell spec (i.e., cellspec) for a table.
-    #
-    # Examples
-    #
-    #   2.3+<.>m
-    #
-    # FIXME use step-wise scan (or treetop) rather than this mega-regexp
-    CellSpecStartRx = /^[ \t]*(?:(\d+(?:\.\d*)?|(?:\d*\.)?\d+)([*+]))?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?([a-z])?$/
-    CellSpecEndRx = /[ \t]+(?:(\d+(?:\.\d*)?|(?:\d*\.)?\d+)([*+]))?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?([a-z])?$/
-
-    # Block macros
-
-    # Matches the custom block macro pattern.
-    #
-    # Examples
-    #
-    #   gist::123456[]
-    #
-    #--
-    # NOTE we've relaxed the match for target to accomodate the short format (e.g., name::[attrlist])
-    CustomBlockMacroRx = /^(#{CG_WORD}[-#{CC_WORD}]*)::(|\S|\S#{CC_ANY}*?\S)\[(#{CC_ANY}+)?\]$/
-
-    # Matches an image, video or audio block macro.
-    #
-    # Examples
-    #
-    #   image::filename.png[Caption]
-    #   video::http://youtube.com/12345[Cats vs Dogs]
-    #
-    BlockMediaMacroRx = /^(image|video|audio)::(\S|\S#{CC_ANY}*?\S)\[(#{CC_ANY}+)?\]$/
-
-    # Matches the TOC block macro.
-    #
-    # Examples
-    #
-    #   toc::[]
-    #   toc::[levels=2]
-    #
-    BlockTocMacroRx = /^toc::\[(#{CC_ANY}+)?\]$/
-
-    ## Inline macros
-
-    # Matches an anchor (i.e., id + optional reference text) in the flow of text.
-    #
-    # Examples
-    #
-    #   [[idname]]
-    #   [[idname,Reference Text]]
-    #   anchor:idname[]
-    #   anchor:idname[Reference Text]
-    #
-    InlineAnchorRx = /(\\)?(?:\[\[([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+?))?\]\]|anchor:([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)\[(?:\]|(#{CC_ANY}*?[^\\])\]))/
-
-    # Scans for a non-escaped anchor (i.e., id + optional reference text) in the flow of text.
-    InlineAnchorScanRx = /(?:^|[^\\\[])\[\[([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+?))?\]\]|(?:^|[^\\])anchor:([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)\[(?:\]|(#{CC_ANY}*?[^\\])\])/
-
-    # Scans for a leading, non-escaped anchor (i.e., id + optional reference text).
-    LeadingInlineAnchorRx = /^\[\[([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+?))?\]\]/
-
-    # Matches a bibliography anchor at the start of the list item text (in a bibliography list).
-    #
-    # Examples
-    #
-    #   [[[Fowler_1997]]] Fowler M. ...
-    #
-    InlineBiblioAnchorRx = /^\[\[\[([#{CC_ALPHA}_:][#{CC_WORD}:.-]*)(?:, *(#{CC_ANY}+?))?\]\]\]/
-
-    # Matches an inline e-mail address.
-    #
-    #   doc.writer@example.com
-    #
-    InlineEmailRx = %r(([\\>:/])?#{CG_WORD}(?:&amp;|[#{CC_WORD}.%+-])*@#{CG_ALNUM}[#{CC_ALNUM}_.-]*\.[a-zA-Z]{2,5}\b)
-
-    # Matches an inline footnote macro, which is allowed to span multiple lines.
-    #
-    # Examples
-    #   footnote:[text] (not referenceable)
-    #   footnote:id[text] (referenceable)
-    #   footnote:id[] (reference)
-    #   footnoteref:[id,text] (legacy)
-    #   footnoteref:[id] (legacy)
-    #
-    InlineFootnoteMacroRx = /\\?footnote(?:(ref):|:([\w-]+)?)\[(?:|(#{CC_ALL}*?[^\\]))\]/m
-
-    # Matches an image or icon inline macro.
-    #
-    # Examples
-    #
-    #   image:filename.png[Alt Text]
-    #   image:http://example.com/images/filename.png[Alt Text]
-    #   image:filename.png[More [Alt\] Text] (alt text becomes "More [Alt] Text")
-    #   icon:github[large]
-    #
-    # NOTE be as non-greedy as possible by not allowing newline or left square bracket in target
-    InlineImageMacroRx = /\\?i(?:mage|con):([^:\s\[](?:[^\n\[]*[^\s\[])?)\[(|#{CC_ALL}*?[^\\])\]/m
-
-    # Matches an indexterm inline macro, which may span multiple lines.
-    #
-    # Examples
-    #
-    #   indexterm:[Tigers,Big cats]
-    #   (((Tigers,Big cats)))
-    #   indexterm2:[Tigers]
-    #   ((Tigers))
-    #
-    InlineIndextermMacroRx = /\\?(?:(indexterm2?):\[(#{CC_ALL}*?[^\\])\]|\(\((#{CC_ALL}+?)\)\)(?!\)))/m
-
-    # Matches either the kbd or btn inline macro.
-    #
-    # Examples
-    #
-    #   kbd:[F3]
-    #   kbd:[Ctrl+Shift+T]
-    #   kbd:[Ctrl+\]]
-    #   kbd:[Ctrl,T]
-    #   btn:[Save]
-    #
-    InlineKbdBtnMacroRx = /(\\)?(kbd|btn):\[(#{CC_ALL}*?[^\\])\]/m
-
-    # Matches an implicit link and some of the link inline macro.
-    #
-    # Examples
-    #
-    #   https://github.com
-    #   https://github.com[GitHub]
-    #   <https://github.com>
-    #   link:https://github.com[]
-    #
-    # FIXME revisit! the main issue is we need different rules for implicit vs explicit
-    InlineLinkRx = %r((^|link:|#{CG_BLANK}|&lt;|[>\(\)\[\];])(\\?(?:https?|file|ftp|irc)://[^\s\[\]<]*([^\s.,\[\]<]))(?:\[(|#{CC_ALL}*?[^\\])\])?)m
-
-    # Match a link or e-mail inline macro.
-    #
-    # Examples
-    #
-    #   link:path[label]
-    #   mailto:doc.writer@example.com[]
-    #
-    # NOTE be as non-greedy as possible by not allowing space or left square bracket in target
-    InlineLinkMacroRx = /\\?(?:link|(mailto)):(|[^:\s\[][^\s\[]*)\[(|#{CC_ALL}*?[^\\])\]/m
-
-    # Matches the name of a macro.
-    #
-    MacroNameRx = /^#{CG_WORD}[-#{CC_WORD}]*$/
-
-    # Matches a stem (and alternatives, asciimath and latexmath) inline macro, which may span multiple lines.
-    #
-    # Examples
-    #
-    #   stem:[x != 0]
-    #   asciimath:[x != 0]
-    #   latexmath:[\sqrt{4} = 2]
-    #
-    InlineStemMacroRx = /\\?(stem|(?:latex|ascii)math):([a-z]+(?:,[a-z-]+)*)?\[(#{CC_ALL}*?[^\\])\]/m
-
-    # Matches a menu inline macro.
-    #
-    # Examples
-    #
-    #   menu:File[Save As...]
-    #   menu:View[Page Style > No Style]
-    #   menu:View[Page Style, No Style]
-    #
-    InlineMenuMacroRx = /\\?menu:(#{CG_WORD}|[#{CC_WORD}&][^\n\[]*[^\s\[])\[ *(#{CC_ALL}*?[^\\])?\]/m
-
-    # Matches an implicit menu inline macro.
-    #
-    # Examples
-    #
-    #   "File > New..."
-    #
-    InlineMenuRx = /\\?"([#{CC_WORD}&][^"]*?[ \n]+&gt;[ \n]+[^"]*)"/
-
-    # Matches an inline passthrough, which may span multiple lines.
-    #
-    # Examples
-    #
-    #   +text+
-    #   `text` (compat)
-    #
-    # NOTE we always capture the attributes so we know when to use compatible (i.e., legacy) behavior
-    InlinePassRx = {
-      false => ['+', '`', /(^|[^#{CC_WORD};:])(?:\[([^\]]+)\])?(\\?(\+|`)(\S|\S#{CC_ALL}*?\S)\4)(?!#{CG_WORD})/m],
-      true  => ['`', nil, /(^|[^`#{CC_WORD}])(?:\[([^\]]+)\])?(\\?(`)([^`\s]|[^`\s]#{CC_ALL}*?\S)\4)(?![`#{CC_WORD}])/m]
-    }
-
-    # Matches an inline plus passthrough spanning multiple lines, but only when it occurs directly
-    # inside constrained monospaced formatting in non-compat mode.
-    #
-    # Examples
-    #
-    #   +text+
-    #
-    SinglePlusInlinePassRx = /^(\\)?\+(\S|\S#{CC_ALL}*?\S)\+$/m
-
-    # Matches several variants of the passthrough inline macro, which may span multiple lines.
-    #
-    # Examples
-    #
-    #   +++text+++
-    #   $$text$$
-    #   pass:quotes[text]
-    #
-    # NOTE we have to support an empty pass:[] for compatibility with AsciiDoc Python
-    InlinePassMacroRx = /(?:(?:(\\?)\[([^\]]+)\])?(\\{0,2})(\+\+\+?|\$\$)(#{CC_ALL}*?)\4|(\\?)pass:([a-z]+(?:,[a-z-]+)*)?\[(|#{CC_ALL}*?[^\\])\])/m
-
-    # Matches an xref (i.e., cross-reference) inline macro, which may span multiple lines.
-    #
-    # Examples
-    #
-    #   <<id,reftext>>
-    #   xref:id[reftext]
-    #
-    # NOTE special characters have already been escaped, hence the entity references
-    # NOTE { is included in start characters to support target that begins with attribute reference in title content
-    InlineXrefMacroRx = %r(\\?(?:&lt;&lt;([#{CC_WORD}#/.:{]#{CC_ALL}*?)&gt;&gt;|xref:([#{CC_WORD}#/.:{]#{CC_ALL}*?)\[(?:\]|(#{CC_ALL}*?[^\\])\])))m
-
-    ## Layout
-
-    # Matches a trailing + preceded by at least one space character,
-    # which forces a hard line break (<br> tag in HTML output).
-    #
-    # NOTE AsciiDoc Python allows + to be preceded by TAB; Asciidoctor does not
-    #
-    # Examples
-    #
-    #   Humpty Dumpty sat on a wall, +
-    #   Humpty Dumpty had a great fall.
-    #
-    if RUBY_ENGINE == 'opal'
-      # NOTE In JavaScript, ^ and $ only match the start and end of line if the multiline flag is present
-      HardLineBreakRx = /^(#{CC_ANY}*) \+$/m
-    else
-      # NOTE In Ruby, ^ and $ always match start and end of line
-      HardLineBreakRx = /^(.*) \+$/
-    end
-
-    # Matches a Markdown horizontal rule.
-    #
-    # Examples
-    #
-    #   --- or - - -
-    #   *** or * * *
-    #   ___ or _ _ _
-    #
-    MarkdownThematicBreakRx = /^ {0,3}([-*_])( *)\1\2\1$/
-
-    # Matches an AsciiDoc or Markdown horizontal rule or AsciiDoc page break.
-    #
-    # Examples
-    #
-    #   ''' (horizontal rule)
-    #   <<< (page break)
-    #   --- or - - - (horizontal rule, Markdown)
-    #   *** or * * * (horizontal rule, Markdown)
-    #   ___ or _ _ _ (horizontal rule, Markdown)
-    #
-    ExtLayoutBreakRx = /^(?:'{3,}|<{3,}|([-*_])( *)\1\2\1)$/
-
-    ## General
-
-    # Matches consecutive blank lines.
-    #
-    # Examples
-    #
-    #   one
-    #
-    #   two
-    #
-    BlankLineRx = /\n{2,}/
-
-    # Matches a comma or semi-colon delimiter.
-    #
-    # Examples
-    #
-    #   one,two
-    #   three;four
-    #
-    #DataDelimiterRx = /[,;]/
-
-    # Matches whitespace (space, tab, newline) escaped by a backslash.
-    #
-    # Examples
-    #
-    #   three\ blind\ mice
-    #
-    EscapedSpaceRx = /\\([ \t\n])/
-
-    # Detects if text is a possible candidate for the replacements substitution.
-    #
-    ReplaceableTextRx = /[&']|--|\.\.\.|\([CRT]M?\)/
-
-    # Matches a whitespace delimiter, a sequence of spaces, tabs, and/or newlines.
-    # Matches the parsing rules of %w strings in Ruby.
-    #
-    # Examples
-    #
-    #   one two	 three   four
-    #   five	six
-    #
-    # TODO change to /(?<!\\)[ \t\n]+/ once lookbehind assertions are implemented in all modern browsers
-    SpaceDelimiterRx = /([^\\])[ \t\n]+/
-
-    # Matches a + or - modifier in a subs list
-    #
-    SubModifierSniffRx = /[+-]/
-
-    # Matches one or more consecutive digits at the end of a line.
-    #
-    # Examples
-    #
-    #   docbook5
-    #   html5
-    #
-    TrailingDigitsRx = /\d+$/
-
-    # Detects strings that resemble URIs.
-    #
-    # Examples
-    #   http://domain
-    #   https://domain
-    #   file:///path
-    #   data:info
-    #
-    #   not c:/sample.adoc or c:\sample.adoc
-    #
-    UriSniffRx = %r(^#{CG_ALPHA}[#{CC_ALNUM}.+-]+:/{0,2})
-
-    # Detects XML tags
-    XmlSanitizeRx = /<[^>]+>/
-  #end
-
   INTRINSIC_ATTRIBUTES = {
-    'startsb'    => '[',
-    'endsb'      => ']',
-    'vbar'       => '|',
-    'caret'      => '^',
-    'asterisk'   => '*',
-    'tilde'      => '~',
-    'plus'       => '&#43;',
-    'backslash'  => '\\',
-    'backtick'   => '`',
-    'blank'      => '',
-    'empty'      => '',
-    'sp'         => ' ',
+    'startsb' => '[',
+    'endsb' => ']',
+    'vbar' => '|',
+    'caret' => '^',
+    'asterisk' => '*',
+    'tilde' => '~',
+    'plus' => '&#43;',
+    'backslash' => '\\',
+    'backtick' => '`',
+    'blank' => '',
+    'empty' => '',
+    'sp' => ' ',
     'two-colons' => '::',
     'two-semicolons' => ';;',
-    'nbsp'       => '&#160;',
-    'deg'        => '&#176;',
-    'zwsp'       => '&#8203;',
-    'quot'       => '&#34;',
-    'apos'       => '&#39;',
-    'lsquo'      => '&#8216;',
-    'rsquo'      => '&#8217;',
-    'ldquo'      => '&#8220;',
-    'rdquo'      => '&#8221;',
-    'wj'         => '&#8288;',
-    'brvbar'     => '&#166;',
-    'pp'         => '&#43;&#43;',
-    'cpp'        => 'C&#43;&#43;',
-    'amp'        => '&',
-    'lt'         => '<',
-    'gt'         => '>'
+    'nbsp' => '&#160;',
+    'deg' => '&#176;',
+    'zwsp' => '&#8203;',
+    'quot' => '&#34;',
+    'apos' => '&#39;',
+    'lsquo' => '&#8216;',
+    'rsquo' => '&#8217;',
+    'ldquo' => '&#8220;',
+    'rdquo' => '&#8221;',
+    'wj' => '&#8288;',
+    'brvbar' => '&#166;',
+    'pp' => '&#43;&#43;',
+    'cpp' => 'C&#43;&#43;',
+    'amp' => '&',
+    'lt' => '<',
+    'gt' => '>'
   }
 
+  # Regular expression character classes (to ensure regexp compatibility between Ruby and JavaScript)
+  # CC stands for "character class", CG stands for "character class group"
+  unless RUBY_ENGINE == 'opal'
+    # CC_ALL is any character, including newlines (must be accompanied by multiline regexp flag)
+    CC_ALL = '.'
+    # CC_ANY is any character except newlines
+    CC_ANY = '.'
+    CC_EOL = '$'
+    CC_ALPHA = CG_ALPHA = '\p{Alpha}'
+    CC_ALNUM = CG_ALNUM = '\p{Alnum}'
+    CG_BLANK = '\p{Blank}'
+    CC_WORD = CG_WORD = '\p{Word}'
+  end
+
   QUOTE_SUBS = {}.tap do |accum|
     # unconstrained quotes:: can appear anywhere
     # constrained quotes:: must be bordered by non-word characters
@@ -1198,8 +495,8 @@ module Asciidoctor
     # (TM)
     [/\\?\(TM\)/, '&#8482;', :none],
     # foo -- bar (where either space character can be a newline)
-    # NOTE this necessarily drops the newline if it appears at end of line
-    [/(^|\n| |\\)--( |\n|$)/, '&#8201;&#8212;&#8201;', :none],
+    # NOTE this necessarily drops the newline if replacement appears at end of line
+    [/(?: |\n|^|\\)--(?: |\n|$)/, '&#8201;&#8212;&#8201;', :none],
     # foo--bar
     [/(#{CG_WORD})\\?--(?=#{CG_WORD})/, '&#8212;&#8203;', :leading],
     # ellipsis
@@ -1240,8 +537,8 @@ module Asciidoctor
   end unless RUBY_ENGINE == 'opal'
 
   unless RUBY_ENGINE == 'opal'
-    autoload :SyntaxHighlighter, %(#{LIB_DIR}/asciidoctor/syntax_highlighter)
-    autoload :Timings, %(#{LIB_DIR}/asciidoctor/timings)
+    autoload :SyntaxHighlighter, %(#{__dir__}/asciidoctor/syntax_highlighter)
+    autoload :Timings, %(#{__dir__}/asciidoctor/timings)
   end
 end
 
@@ -1251,6 +548,7 @@ require_relative 'asciidoctor/core_ext'
 # modules and helpers
 require_relative 'asciidoctor/helpers'
 require_relative 'asciidoctor/logging'
+require_relative 'asciidoctor/rx'
 require_relative 'asciidoctor/substitutors'
 require_relative 'asciidoctor/version'