typohero 0.0.1 → 0.0.2

data/bench/profile.rb

@@ -0,0 +1,8 @@
+require 'typohero'
+require 'perftools'
+
+text = File.read('bench.txt')
+
+PerfTools::CpuProfiler.start('/tmp/profile') do
+  10.times { TypoHero.enhance(text) }
+end

data/latex.pl

@@ -0,0 +1,16 @@
+use strict;
+use LaTeX::Decode::Data;
+
+my %WORDMAC = ( %WORDMACROS, %WORDMACROSEXTRA, %PUNCTUATION, %SYMBOLS,
+            %GREEK );
+
+print "module TypoHero\n  LATEX = {\n";
+foreach (keys(%WORDMAC)) {
+    my $v = sprintf('\\u%04x', ord($WORDMAC{$_}));
+    print "   '\\\\$_' => \"$v\",\n";
+}
+foreach (keys(%NEGATEDSYMBOLS)) {
+    my $v = sprintf('\\u%04x', ord($NEGATEDSYMBOLS{$_}));
+    print "   '\\\\not\\\\$_' => \"$v\",\n";
+}
+print "  }\nend\n";

data/lib/typohero.rb

@@ -1,106 +1,123 @@
-module TypoHero
-  VERSION = '0.0.1'
+require 'typohero/version'
+require 'typohero/latex'
 
+module TypoHero
   extend self
 
   EXCLUDED_TAGS = %w(head pre code kbd math script textarea)
-  EXCLUDED_TAGS_RE = /\A<(\/)?(?:#{EXCLUDED_TAGS.join('|')})/im
+  EXCLUDED_TAGS_RE = /\A<(\/)?(?:#{EXCLUDED_TAGS.join('|')})[\p{Space}\/>]/im
 
-  TOKENIZER_RE = /<[^>]+>|[^<]+|\\[\(\[\)\]]|\$\$/im
+  TOKENIZER_RE = /<[^>]+>|\\[\(\)\[\]]|\$\$|(?:[^<\$\\]|\$(?:[^$]|\Z)|\\(?:[^\(\)\[\]]|\Z))+/im
 
   ESCAPE = {
     '\\\\'   => '&#92;',
     '\"'     => '&#34;',
     "\\\'"   => '&#39;',
     '\.'     => '&#46;',
+    '\,'     => '&#44;',
     '\-'     => '&#45;',
-    '\`'     => '&#96;'
+    '\`'     => '&#96;',
+    '\('     => '&#40',
   }
   ESCAPE_RE = Regexp.union(*ESCAPE.keys)
 
-  EM_DASH      = '&#8212;'
-  EN_DASH      = '&#8211;'
-  ELLIPSIS     = '&#8230;'
-  LEFT_DQUOTE  = '&#8220;'
-  RIGHT_DQUOTE = '&#8221;'
-  LEFT_QUOTE   = '&#8216;'
-  RIGHT_QUOTE  = '&#8217;'
+  NBSP  = "\u00a0"
+  MDASH = "\u2014"
+  NDASH = "\u2013"
+  LDQUO = "\u201C"
+  RDQUO = "\u201D"
+  LSQUO = "\u2018"
+  RSQUO = "\u2019"
+  BDQUO = "\u201E"
 
   SPECIAL = {
     # enhance!
-    '---'      => EM_DASH,
-    '--'       => EN_DASH,
-    '...'      => ELLIPSIS,
-    '. . .'    => ELLIPSIS,
-    '``'       => LEFT_DQUOTE,
-    "''"       => RIGHT_DQUOTE,
-    '`'        => LEFT_QUOTE,
-    ',,'       => '&#8222;',
-    '-&gt;'    => '&rarr;',
-    '&lt;-'    => '&larr;',
-    '=&gt;'    => '&rArr;',
-    '&lt;='    => '&lArr;',
-    '&gt;&gt;' => '&raquo;',
-    '&lt;&lt;' => '&laquo;',
-    '(c)'      => '&copy;',
-    '(C)'      => '&copy;',
-    '(r)'      => '&reg;',
-    '(R)'      => '&reg;',
-    '(tm)'     => '&trade;',
-    '(TM)'     => '&trade;',
+    '---'      => MDASH,
+    '--'       => NDASH,
+    '...'      => "\u2026",
+    '. . .'    => "\u2026",
+    '``'       => LDQUO,
+    "''"       => RDQUO,
+    '`'        => LSQUO,
+    ',,'       => BDQUO,
+    '(c)'      => "\u00A9",
+    '(C)'      => "\u00A9",
+    '(r)'      => "\u00AE",
+    '(R)'      => "\u00AE",
+    '(tm)'     => "\u2122",
+    '(TM)'     => "\u2122",
     # normalize for further processing
-    '&ldquo;'  => LEFT_DQUOTE,
-    '&lsquo;'  => LEFT_QUOTE,
-    '&rdquo;'  => RIGHT_DQUOTE,
-    '&rsquo;'  => RIGHT_QUOTE,
-    '&#160;'   => '&nbsp',
-    '&#xA0;'   => '&nbsp',
-    '&#x2013;' => EN_DASH,
-    '&#x2014;' => EM_DASH,
-    '&mdash;'  => EM_DASH,
-    '&ndash;'  => EN_DASH,
+    '&ldquo;'  => LDQUO,
+    '&#8220;'  => LDQUO,
+    '&#x201C;' => LDQUO,
+    '&rdquo;'  => RDQUO,
+    '&#8221;'  => RDQUO,
+    '&#x201D;' => RDQUO,
+    '&lsquo;'  => LSQUO,
+    '&#8216;'  => LSQUO,
+    '&#x2018;' => LSQUO,
+    '&rsquo;'  => RSQUO,
+    '&#8217;'  => RSQUO,
+    '&#x2019;' => RSQUO,
+    '&#160;'   => NBSP,
+    '&#xA0;'   => NBSP,
+    '&nbsp;'   => NBSP,
+    '&ndash;'  => NDASH,
+    '&#x2013;' => NDASH,
+    '&#8211;'  => NDASH,
+    '&#x2014;' => MDASH,
+    '&mdash;'  => MDASH,
+    '&#8212;'  => MDASH,
     '&#38;'    => '&amp;',
     '&#x26;'   => '&amp;',
   }
   SPECIAL_RE = Regexp.union(*SPECIAL.keys)
+  LATEX_RE = /(#{Regexp.union *LATEX.keys})(?=\p{Space}|$)/
 
-  SPACE_RE = '\s|&nbsp;|&#8201;'
-  DASH_RE  = '&#821[12];'
+  DASH_RE  = "[#{MDASH}#{NDASH}]"
   AMP_RE   = '&(?:amp;)?'
+  LEFT_QUOTE_RE = "[#{LDQUO}#{LSQUO}#{BDQUO}]"
 
-  PRIME_RE = /(?<=\d)(''?)(?=#{SPACE_RE}|\d|$)/
+  PRIME_RE = /(?<=\d)(''?)(?=\p{Space}|\d|$)/
   PRIMES = {
-   "'" => '&prime;',
-   "''" => '&Prime;',
+   "'"   => "\u2032",
+   "''"  => "\u2033",
+   "'''" => "\u2034",
   }
-  ORDINAL_RE = /(?<=\d)(st|nd|rd|th)(?=#{SPACE_RE}|$)/
+  ORDINAL_RE = /(?<=\d)(st|nd|rd|th)(?=\p{Space}|$)/
 
-  EM_DASH_SPACE_RE = /\s*(#{EM_DASH})\s*/
-  EN_DASH_SPACE_RE = /\s*(#{EN_DASH})\s*/
+  MDASH_SPACE_RE = /\p{Space}*(#{MDASH})\p{Space}*/
+  NDASH_SPACE_RE = /\p{Space}*(#{NDASH})\p{Space}*/
 
-  REPLACE_AMP_RE  = /(?<=#{SPACE_RE})#{AMP_RE}(?=#{SPACE_RE})/m
+  REPLACE_AMP_RE  = /(?<=\p{Space})#{AMP_RE}(?=\p{Space})/m
 
-  CAPS_BEGIN_RE   = "(^|#{SPACE_RE}|#{LEFT_DQUOTE}|#{LEFT_QUOTE})"
-  CAPS_INNER_RE   = "(?:#{AMP_RE}|[A-Z\\d\\.]|#{RIGHT_QUOTE})*" # right quote for posession (e.g. JIMMY'S)
+  CAPS_BEGIN_RE   = "(^|\\p{Space}|#{LEFT_QUOTE_RE})"
+  CAPS_INNER_RE   = "(?:#{AMP_RE}|[A-Z\\d\\.]|#{RSQUO})*" # right quote for posession (e.g. JIMMY'S)
   REPLACE_CAPS_RE = /#{CAPS_BEGIN_RE}([A-Z\d]#{CAPS_INNER_RE}[A-Z]#{CAPS_INNER_RE}|[A-Z]#{CAPS_INNER_RE}[A-Z\d]#{CAPS_INNER_RE})/m
 
   PUNCT_CLASS = '[!"#\$\%\'()*+,\-.\/:;<=>?\@\[\\\\\]\^_`{|}~]'
-  PUNCT_QUOTE_RE  = /^['"](?=#{PUNCT_CLASS})\B/m
-  RIGHT_QUOTE_RE  = /(?<!^|#{DASH_RE}|#{SPACE_RE}|[\[\{\(\-])['"]|['"](?=\s|s\b|$)|(?<=#{DASH_RE})['"](?=#{PUNCT_CLASS})/m
+  RIGHT_QUOTE_RE  = %r{
+    ^['"](?=#{PUNCT_CLASS})\B|                  # Very first character is a closing quote followed by punctuation at a non-word-break
+    (?<!^|#{DASH_RE}|\p{Space}|[\[\{\(\-])['"]| # Not after dash, space or opening parentheses
+    ['"](?=\p{Space}|$)|                        # Followed by space or end of line
+    's\b|                                       # Apostrophe
+    (?<=#{DASH_RE})['"](?=#{PUNCT_CLASS})|      # Dash quote punctuation (e.g. --'!), for quotations
+    '(?=(\d\d(?:s|\p{Space}|$)))                # Decade abbreviations (the '80s)
+  }xm
 
   LEFT_QUOTES = {
-    "'" => LEFT_QUOTE,
-    '"' => LEFT_DQUOTE,
+    "'" => LSQUO,
+    '"' => LDQUO,
   }
 
   RIGHT_QUOTES = {
-    "'" => RIGHT_QUOTE,
-    '"' => RIGHT_DQUOTE,
+    "'" => RSQUO,
+    '"' => RDQUO,
   }
 
   TWO_QUOTES = {
-    '"\'' => LEFT_DQUOTE + LEFT_QUOTE,
-    '\'"' => LEFT_QUOTE + LEFT_DQUOTE
+    '"\'' => LDQUO + LSQUO,
+    '\'"' => LSQUO + LDQUO
   }
 
   PARAGRAPH_RE = 'h[1-6]|p|li|dt|dd|div'
@@ -108,11 +125,13 @@ module TypoHero
 
   WIDONT_PARAGRAPH_RE = /\A<\/(?:#{PARAGRAPH_RE})>\Z/im
   WIDONT_INLINE_RE = /\A<\/?(?:#{INLINE_RE})[^>]*>\Z/im
+  WIDONT_NBSP_RE = /#{NBSP}|<|>/
 
-  INITIAL_QUOTE_RE = /(?=(?:<(?:#{PARAGRAPH_RE})[^>]*>|^)(?:<(?:#{INLINE_RE})[^>]*>|\s)*)&#(8216|8220);/
+  INITIAL_QUOTE_RE = /(?=(?:<(?:#{PARAGRAPH_RE})[^>]*>|^)(?:<(?:#{INLINE_RE})[^>]*>|\p{Space})*)#{LEFT_QUOTE_RE}/
   INITIAL_QUOTES = {
-    LEFT_QUOTE => "<span class=\"quo\">#{LEFT_QUOTE}</span>",
-    LEFT_DQUOTE => "<span class=\"dquo\">#{LEFT_DQUOTE}</span>",
+    LSQUO => "<span class=\"quo\">#{LSQUO}</span>",
+    LDQUO => "<span class=\"dquo\">#{LDQUO}</span>",
+    BDQUO => "<span class=\"bdquo\">#{BDQUO}</span>",
   }
 
   def tokenize(input)
@@ -143,6 +162,7 @@ module TypoHero
         escape(s)
         primes(s)
         special(s)
+        latex(s)
         quotes(s, prev_last_char)
         dash_spaces(s)
         prev_last_char = last_char
@@ -166,12 +186,12 @@ module TypoHero
       if tokens[i] =~ WIDONT_PARAGRAPH_RE
         state = 1
       elsif tokens[i] !~ WIDONT_INLINE_RE
-        if tokens[i] =~ /&nbsp;|<|>/
+        if tokens[i] =~ WIDONT_NBSP_RE
           state = 0
         elsif state == 1 || state == 3
-          if tokens[i] =~ (state == 1 ? /(\S+)?(\s+)?(\S+\s*)\Z/m : /(\S+)?(\s+)(\S*)\Z/m)
+          if tokens[i] =~ (state == 1 ? /(\P{Space}+)?(\p{Space}+)?(\P{Space}+\p{Space}*)\Z/m : /(\P{Space}+)?(\p{Space}+)(\P{Space}*)\Z/m)
             if $1 && $2
-              tokens[i].replace "#{$`}#{$1}&nbsp;#{$3}"
+              tokens[i].replace "#{$`}#{$1}#{NBSP}#{$3}"
               state = 0
             elsif $2
               state = 2
@@ -180,8 +200,8 @@ module TypoHero
               state = 3
             end
           end
-        elsif state == 2 && tokens[i] =~ /(\S+\s*)\Z/m
-          widow.sub!(/\A\s*/, '&nbsp;')
+        elsif state == 2 && tokens[i] =~ /(\P{Space}+\p{Space}*)\Z/m
+          widow.sub!(/\A\p{Space}*/, NBSP)
           state = 0
         end
       end
@@ -197,9 +217,13 @@ module TypoHero
     s.gsub!(SPECIAL_RE, SPECIAL)
   end
 
+  def latex(s)
+    s.gsub!(LATEX_RE, LATEX)
+  end
+
   def dash_spaces(s)
-    s.gsub!(EM_DASH_SPACE_RE, '&#8201;\1&#8201;')
-    s.gsub!(EN_DASH_SPACE_RE, ' \1 ')
+    s.gsub!(MDASH_SPACE_RE, "\u2009\\1\u2009")
+    s.gsub!(NDASH_SPACE_RE, ' \1 ')
   end
 
   def amp(s)
@@ -225,21 +249,13 @@ module TypoHero
 
   def quotes(s, prev_last_char)
     if s =~ /\A['"]\Z/
-      s.replace(prev_last_char =~ /\S/ ? RIGHT_QUOTES[s] : LEFT_QUOTES[s])
+      s.replace(prev_last_char =~ /\P{Space}/ ? RIGHT_QUOTES[s] : LEFT_QUOTES[s])
       return
     end
 
-    # Special case if the very first character is a closing
-    # quote followed by punctuation at a non-word-break
-    s.gsub!(PUNCT_QUOTE_RE, RIGHT_QUOTES)
-
     # Special case for double sets of quotes, e.g.
     #   <p>He said, "'Quoted' words in a larger quote."</p>
     s.gsub!(/(?:"'|'")(?=\p{Word})/, TWO_QUOTES)
-
-    # Special case for decade abbreviations (the '80s)
-    s.gsub!(/'(?=(\d{2}(?:s|\s|$)))/, RIGHT_QUOTES)
-
     s.gsub!(RIGHT_QUOTE_RE, RIGHT_QUOTES)
     s.gsub!(/['"]/,         LEFT_QUOTES)
   end

data/lib/typohero/latex.rb

@@ -0,0 +1,537 @@
+module TypoHero
+  LATEX = {
+   '\\textasteriskcentered' => "\u002a",
+   '\\nless' => "\u226e",
+   '\\textquoteright' => "\u2019",
+   '\\subset' => "\u2282",
+   '\\guilsinglright' => "\u203a",
+   '\\OHORN' => "\u01a0",
+   '\\textltailn' => "\u0272",
+   '\\bumpeq' => "\u224f",
+   '\\textcloserevepsilon' => "\u025e",
+   '\\lneqq' => "\u2268",
+   '\\prec' => "\u227a",
+   '\\gnsim' => "\u22e7",
+   '\\forall' => "\u2200",
+   '\\textrtaild' => "\u0256",
+   '\\textampersand' => "\u0026",
+   '\\rightarrow' => "\u2192",
+   '\\textbari' => "\u0268",
+   '\\surd' => "\u221a",
+   '\\sqcup' => "\u2294",
+   '\\textdong' => "\u20ab",
+   '\\tone5' => "\u02e5",
+   '\\textdollar' => "\u0024",
+   '\\Epsilon' => "\u0395",
+   '\\uparrow' => "\u2191",
+   '\\guilsinglleft' => "\u2039",
+   '\\dh' => "\u00f0",
+   '\\Thorn' => "\u00de",
+   '\\chi' => "\u03c7",
+   '\\textrhookrevepsilon' => "\u025d",
+   '\\oe' => "\u0153",
+   '\\AA' => "\u00c5",
+   '\\fallingdotseq' => "\u2252",
+   '\\textendash' => "\u2013",
+   '\\hamza' => "\u02be",
+   '\\ayn' => "\u02bf",
+   '\\texthtq' => "\u02a0",
+   '\\varphi' => "\u03c6",
+   '\\unlhd' => "\u22b4",
+   '\\textturnscripta' => "\u0252",
+   '\\nabla' => "\u2207",
+   '\\textnumero' => "\u2116",
+   '\\textbackslash' => "\u005c",
+   '\\exists' => "\u2203",
+   '\\textthornvariii' => "\u00fe",
+   '\\otimes' => "\u2297",
+   '\\odot' => "\u2299",
+   '\\textrtailn' => "\u0273",
+   '\\texthtd' => "\u0257",
+   '\\kappa' => "\u03ba",
+   '\\copyright' => "\u00a9",
+   '\\in' => "\u2208",
+   '\\Nu' => "\u039d",
+   '\\textTstroke' => "\u0166",
+   '\\texththeng' => "\u0267",
+   '\\lessgtr' => "\u2276",
+   '\\lesseqgtr' => "\u22da",
+   '\\textkhook' => "\u0199",
+   '\\textTbar' => "\u0166",
+   '\\doteqdot' => "\u2251",
+   '\\textquotedbl' => "\u0022",
+   '\\quotedblbase' => "\u201e",
+   '\\diamond' => "\u22c4",
+   '\\textscn' => "\u0274",
+   '\\mid' => "\u2223",
+   '\\setminus' => "\u2216",
+   '\\sqcap' => "\u2293",
+   '\\hv' => "\u0195",
+   '\\textEopen' => "\u0190",
+   '\\euro' => "\u20ac",
+   '\\varrho' => "\u03c1",
+   '\\texthbar' => "\u0127",
+   '\\doteq' => "\u2250",
+   '\\eta' => "\u03b7",
+   '\\guillemotright' => "\u00bb",
+   '\\rightthreetimes' => "\u22cc",
+   '\\textemdash' => "\u2014",
+   '\\ngtr' => "\u226f",
+   '\\precnsim' => "\u22e8",
+   '\\textthornvari' => "\u00fe",
+   '\\textasciimacron' => "\u00af",
+   '\\iota' => "\u03b9",
+   '\\textcolonmonetary' => "\u20a1",
+   '\\neq' => "\u2260",
+   '\\clubsuit' => "\u2663",
+   '\\gamma' => "\u03b3",
+   '\\top' => "\u22a4",
+   '\\textthreesuperior' => "\u00b3",
+   '\\textHbar' => "\u0126",
+   '\\curlyeqprec' => "\u22de",
+   '\\Alpha' => "\u0391",
+   '\\Tau' => "\u03a4",
+   '\\bigcup' => "\u22c3",
+   '\\textsch' => "\u029c",
+   '\\int' => "\u222b",
+   '\\textGammaafrican' => "\u0194",
+   '\\textquotedblleft' => "\u201c",
+   '\\textmu' => "\u00b5",
+   '\\texttretroflexhook' => "\u0288",
+   '\\Pi' => "\u03a0",
+   '\\textkra' => "\u0138",
+   '\\Delta' => "\u0394",
+   '\\textlonglegr' => "\u027c",
+   '\\Rightarrow' => "\u21d2",
+   '\\circ' => "\u2218",
+   '\\textKhook' => "\u0198",
+   '\\unrhd' => "\u22b5",
+   '\\Rho' => "\u03a1",
+   '\\multimap' => "\u22b8",
+   '\\propto' => "\u221d",
+   '\\textperiodcentered' => "\u00b7",
+   '\\rfloor' => "\u230b",
+   '\\vartheta' => "\u03b8",
+   '\\textgreater' => "\u003e",
+   '\\textcrh' => "\u0127",
+   '\\varsigma' => "\u03c2",
+   '\\textbar' => "\u007c",
+   '\\simeq' => "\u2243",
+   '\\textchook' => "\u0188",
+   '\\textpertenthousand' => "\u2031",
+   '\\textbardotlessj' => "\u025f",
+   '\\textonequarter' => "\u00bc",
+   '\\texthtp' => "\u01a5",
+   '\\flat' => "\u266d",
+   '\\texthtscg' => "\u029b",
+   '\\therefore' => "\u2234",
+   '\\leftarrow' => "\u2190",
+   '\\textEsh' => "\u01a9",
+   '\\vdots' => "\u22ee",
+   '\\textless' => "\u003c",
+   '\\texteuro' => "\u20ac",
+   '\\Cap' => "\u22d2",
+   '\\textgamma' => "\u0263",
+   '\\textcloseomega' => "\u0277",
+   '\\textDhook' => "\u018a",
+   '\\texttbar' => "\u0167",
+   '\\sphericalangle' => "\u2222",
+   '\\textlogicalnot' => "\u00ac",
+   '\\textphi' => "\u0278",
+   '\\dj' => "\u0111",
+   '\\S' => "\u00a7",
+   '\\textiotalatin' => "\u0269",
+   '\\textopeno' => "\u0254",
+   '\\IJ' => "\u0132",
+   '\\textctyogh' => "\u0293",
+   '\\nparallel' => "\u2226",
+   '\\textlyoghlig' => "\u026e",
+   '\\textthorn' => "\u00fe",
+   '\\textordfeminine' => "\u00aa",
+   '\\ll' => "\u226a",
+   '\\texthtg' => "\u0260",
+   '\\downarrow' => "\u2193",
+   '\\texteopen' => "\u025b",
+   '\\ncong' => "\u2247",
+   '\\guillemotleft' => "\u00ab",
+   '\\textinterrobang' => "\u203d",
+   '\\boxdot' => "\u22a1",
+   '\\texttstroke' => "\u0167",
+   '\\textteshlig' => "\u02a7",
+   '\\ESH' => "\u01a9",
+   '\\textflorin' => "\u0192",
+   '\\langle' => "\u27e8",
+   '\\textrevglotstop' => "\u0295",
+   '\\textltilde' => "\u026b",
+   '\\textiota' => "\u0269",
+   '\\ng' => "\u014b",
+   '\\textBhook' => "\u0181",
+   '\\texttrademark' => "\u2122",
+   '\\nsubseteq' => "\u2288",
+   '\\ltimes' => "\u22c9",
+   '\\textturna' => "\u0250",
+   '\\textquotesingle' => "\u0027",
+   '\\oplus' => "\u2295",
+   '\\varepsilon' => "\u03b5",
+   '\\boxplus' => "\u229e",
+   '\\textscg' => "\u0262",
+   '\\textquotedblright' => "\u201d",
+   '\\Beta' => "\u0392",
+   '\\textdctzlig' => "\u02a5",
+   '\\textctesh' => "\u0286",
+   '\\iint' => "\u222c",
+   '\\textPhook' => "\u01a4",
+   '\\textturnh' => "\u0265",
+   '\\textnaira' => "\u20a6",
+   '\\pm' => "\u00b1",
+   '\\ggg' => "\u22d9",
+   '\\texteturned' => "\u01dd",
+   '\\textscripta' => "\u0251",
+   '\\OE' => "\u0152",
+   '\\wedge' => "\u2227",
+   '\\ominus' => "\u2296",
+   '\\textordmasculine' => "\u00ba",
+   '\\nexists' => "\u2204",
+   '\\ntrianglerighteq' => "\u22ed",
+   '\\textdzlig' => "\u02a3",
+   '\\Theta' => "\u0398",
+   '\\textturnv' => "\u028c",
+   '\\lesssim' => "\u2272",
+   '\\Psi' => "\u03a8",
+   '\\tone3' => "\u02e7",
+   '\\lnsim' => "\u22e6",
+   '\\nprec' => "\u2280",
+   '\\gtreqless' => "\u22db",
+   '\\texttctclig' => "\u02a8",
+   '\\bigwedge' => "\u22c0",
+   '\\textscriptv' => "\u028b",
+   '\\upsilon' => "\u03c5",
+   '\\subseteq' => "\u2286",
+   '\\lessdot' => "\u22d6",
+   '\\bullet' => "\u2219",
+   '\\textpm' => "\u00b1",
+   '\\textrevepsilon' => "\u025c",
+   '\\textYhook' => "\u01b3",
+   '\\textphook' => "\u01a5",
+   '\\alpha' => "\u03b1",
+   '\\textglotstop' => "\u0294",
+   '\\mu' => "\u03bc",
+   '\\L' => "\u0141",
+   '\\set' => "\u2205",
+   '\\nobreakspace' => "\u00a0",
+   '\\angle' => "\u2220",
+   '\\ddag' => "\u2021",
+   '\\updownarrow' => "\u2195",
+   '\\psi' => "\u03c8",
+   '\\asymp' => "\u224d",
+   '\\cdot' => "\u22c5",
+   '\\supset' => "\u2283",
+   '\\nsim' => "\u2241",
+   '\\supseteq' => "\u2287",
+   '\\ast' => "\u2217",
+   '\\lhd' => "\u22b2",
+   '\\ss' => "\u00df",
+   '\\textasciitilde' => "\u007e",
+   '\\textdegree' => "\u00b0",
+   '\\textTretroflexhook' => "\u01ae",
+   '\\textasciicedilla' => "\u00b8",
+   '\\spadesuit' => "\u2660",
+   '\\th' => "\u00fe",
+   '\\ntrianglelefteq' => "\u22ec",
+   '\\textyen' => "\u00a5",
+   '\\cup' => "\u222a",
+   '\\textoopen' => "\u0254",
+   '\\Upsilon' => "\u03a5",
+   '\\leftrightarrow' => "\u2194",
+   '\\textasciiacute' => "\u00b4",
+   '\\textinvscr' => "\u0281",
+   '\\textcrd' => "\u0111",
+   '\\sqsubset' => "\u228f",
+   '\\precsim' => "\u227e",
+   '\\textIotaafrican' => "\u0196",
+   '\\textonesuperior' => "\u00b9",
+   '\\textDafrican' => "\u0189",
+   '\\textbarl' => "\u0142",
+   '\\between' => "\u226c",
+   '\\textThook' => "\u01ac",
+   '\\textrtaill' => "\u026d",
+   '\\complement' => "\u2201",
+   '\\lfloor' => "\u230a",
+   '\\succ' => "\u227b",
+   '\\textcloseepsilon' => "\u029a",
+   '\\Zeta' => "\u0396",
+   '\\textcent' => "\u00a2",
+   '\\l' => "\u0142",
+   '\\texttslig' => "\u02a6",
+   '\\gtrless' => "\u2277",
+   '\\ij' => "\u0133",
+   '\\textoverline' => "\u203e",
+   '\\Subset' => "\u22d0",
+   '\\gg' => "\u226b",
+   '\\DJ' => "\u0110",
+   '\\parallel' => "\u2225",
+   '\\textthornvarii' => "\u00fe",
+   '\\lll' => "\u22d8",
+   '\\texthash' => "\u0023",
+   '\\leftthreetimes' => "\u22cb",
+   '\\textequals' => "\u003d",
+   '\\leqq' => "\u2266",
+   '\\vdash' => "\u22a2",
+   '\\textschwa' => "\u0259",
+   '\\rtimes' => "\u22ca",
+   '\\delta' => "\u03b4",
+   '\\textdiv' => "\u00f7",
+   '\\equiv' => "\u2261",
+   '\\textdyoghlig' => "\u02a4",
+   '\\curlywedge' => "\u22cf",
+   '\\textEreversed' => "\u018e",
+   '\\sigma' => "\u03c3",
+   '\\ohorn' => "\u01a1",
+   '\\texthtk' => "\u0199",
+   '\\nmid' => "\u2224",
+   '\\textOopen' => "\u0186",
+   '\\leq' => "\u2264",
+   '\\tone2' => "\u02e8",
+   '\\diamondsuit' => "\u2662",
+   '\\omicron' => "\u03bf",
+   '\\textupsilon' => "\u028a",
+   '\\AE' => "\u00c6",
+   '\\succsim' => "\u227f",
+   '\\TH' => "\u00de",
+   '\\curlyvee' => "\u22ce",
+   '\\Leftrightarrow' => "\u21d4",
+   '\\infty' => "\u221e",
+   '\\Iota' => "\u0399",
+   '\\textbhook' => "\u0253",
+   '\\zeta' => "\u03b6",
+   '\\NG' => "\u014a",
+   '\\textwon' => "\u20a9",
+   '\\textscoelig' => "\u0276",
+   '\\Xi' => "\u039e",
+   '\\bigvee' => "\u22c1",
+   '\\UHORN' => "\u01af",
+   '\\textturnk' => "\u029e",
+   '\\circeq' => "\u2257",
+   '\\div' => "\u00f7",
+   '\\textturnlonglegr' => "\u027a",
+   '\\Box' => "\u25a1",
+   '\\textrtailt' => "\u0288",
+   '\\textdtail' => "\u0256",
+   '\\Phi' => "\u03a6",
+   '\\textlooptoprevesh' => "\u01aa",
+   '\\textthornvariv' => "\u00fe",
+   '\\textcopyright' => "\u00a9",
+   '\\approx' => "\u2248",
+   '\\subsetneq' => "\u228a",
+   '\\textstretchc' => "\u0297",
+   '\\textturnt' => "\u0287",
+   '\\wr' => "\u2240",
+   '\\ae' => "\u00e6",
+   '\\textbeltl' => "\u026c",
+   '\\dag' => "\u2020",
+   '\\o' => "\u00f8",
+   '\\notin' => "\u2209",
+   '\\Supset' => "\u22d1",
+   '\\textscriptg' => "\u0261",
+   '\\supsetneq' => "\u228b",
+   '\\Cup' => "\u22d3",
+   '\\triangleq' => "\u225c",
+   '\\textepsilon' => "\u025b",
+   '\\textreferencemark' => "\u203b",
+   '\\nsupseteq' => "\u2289",
+   '\\textquestiondown' => "\u00bf",
+   '\\textonehalf' => "\u00bd",
+   '\\ntriangleright' => "\u22eb",
+   '\\oslash' => "\u2298",
+   '\\dotplus' => "\u2214",
+   '\\succcurlyeq' => "\u227d",
+   '\\textbarrevglotstop' => "\u02a2",
+   '\\P' => "\u00b6",
+   '\\cdots' => "\u22ef",
+   '\\texttesh' => "\u02a7",
+   '\\coprod' => "\u2210",
+   '\\textsection' => "\u00a7",
+   '\\sim' => "\u223c",
+   '\\textpercent' => "\u0025",
+   '\\pounds' => "\u00a3",
+   '\\textturnmrleg' => "\u0270",
+   '\\tau' => "\u03c4",
+   '\\Lambda' => "\u039b",
+   '\\textezh' => "\u0292",
+   '\\textctc' => "\u0255",
+   '\\textlira' => "\u20a4",
+   '\\textthook' => "\u01ad",
+   '\\lnot' => "\u00ac",
+   '\\gneqq' => "\u2269",
+   '\\textsterling' => "\u00a3",
+   '\\textpalhookbelow' => "\u01ab",
+   '\\tone1' => "\u02e9",
+   '\\textregistered' => "\u00ae",
+   '\\textbraceright' => "\u007d",
+   '\\risingdotseq' => "\u2253",
+   '\\textdhook' => "\u0257",
+   '\\textbrokenbar' => "\u00a6",
+   '\\circledast' => "\u229b",
+   '\\textcrb' => "\u0180",
+   '\\nsucc' => "\u2281",
+   '\\textcurrency' => "\u00a4",
+   '\\textminus' => "\u2212",
+   '\\gtrdot' => "\u22d7",
+   '\\textthreequarters' => "\u00be",
+   '\\textbarglotstop' => "\u02a1",
+   '\\textrtails' => "\u0282",
+   '\\textesh' => "\u0283",
+   '\\circledcirc' => "\u229a",
+   '\\Sigma' => "\u03a3",
+   '\\bowtie' => "\u22c8",
+   '\\texttwosuperior' => "\u00b2",
+   '\\textrtailz' => "\u0290",
+   '\\boxtimes' => "\u22a0",
+   '\\rhd' => "\u22b3",
+   '\\xi' => "\u03be",
+   '\\nu' => "\u03bd",
+   '\\textnhookleft' => "\u0272",
+   '\\omega' => "\u03c9",
+   '\\textcrlambda' => "\u019b",
+   '\\ain' => "\u02bf",
+   '\\textctz' => "\u0291",
+   '\\dots' => "\u2026",
+   '\\textturny' => "\u028e",
+   '\\textscy' => "\u028f",
+   '\\textrtailr' => "\u027d",
+   '\\Omega' => "\u03a9",
+   '\\textbraceleft' => "\u007b",
+   '\\textsci' => "\u026a",
+   '\\textasciigrave' => "\u0060",
+   '\\rceil' => "\u2309",
+   '\\textbullseye' => "\u0298",
+   '\\textrhookschwa' => "\u025a",
+   '\\textcentereddot' => "\u00b7",
+   '\\uplus' => "\u228e",
+   '\\tone4' => "\u02e6",
+   '\\approxeq' => "\u224a",
+   '\\texttimes' => "\u00d7",
+   '\\measuredangle' => "\u2221",
+   '\\textraisevibyi' => "\u0285",
+   '\\Bumpeq' => "\u224e",
+   '\\succnsim' => "\u22e9",
+   '\\vee' => "\u2228",
+   '\\textparagraph' => "\u00b6",
+   '\\geq' => "\u2265",
+   '\\natural' => "\u266e",
+   '\\textturnrrtail' => "\u027b",
+   '\\textbaru' => "\u0289",
+   '\\textquoteleft' => "\u2018",
+   '\\textunderscore' => "\u005f",
+   '\\heartsuit' => "\u2661",
+   '\\leadsto' => "\u219d",
+   '\\lceil' => "\u2308",
+   '\\rightleftharpoons' => "\u21cc",
+   '\\star' => "\u22c6",
+   '\\Kappa' => "\u039a",
+   '\\textfishhookr' => "\u027e",
+   '\\quotesinglbase' => "\u201a",
+   '\\circleddash' => "\u229d",
+   '\\textctj' => "\u029d",
+   '\\uhorn' => "\u01b0",
+   '\\textlhti' => "\u027f",
+   '\\textChook' => "\u0187",
+   '\\textvhook' => "\u028b",
+   '\\veebar' => "\u22bb",
+   '\\textturnm' => "\u026f",
+   '\\Vvdash' => "\u22aa",
+   '\\textg' => "\u0067",
+   '\\partial' => "\u2202",
+   '\\Vdash' => "\u22a9",
+   '\\sqsubseteq' => "\u2291",
+   '\\textFhook' => "\u0191",
+   '\\textexclamdown' => "\u00a1",
+   '\\Eta' => "\u0397",
+   '\\textturnr' => "\u0279",
+   '\\backsimeq' => "\u22cd",
+   '\\Omicron' => "\u039f",
+   '\\texthtb' => "\u0253",
+   '\\i' => "\u0131",
+   '\\textreve' => "\u0258",
+   '\\eqcirc' => "\u2256",
+   '\\textNhookleft' => "\u019d",
+   '\\textscr' => "\u0280",
+   '\\because' => "\u2235",
+   '\\texthtt' => "\u01ad",
+   '\\bot' => "\u22a5",
+   '\\ngeq' => "\u2271",
+   '\\sharp' => "\u266f",
+   '\\aa' => "\u00e5",
+   '\\sum' => "\u2211",
+   '\\divideontimes' => "\u22c7",
+   '\\dashv' => "\u22a3",
+   '\\cap' => "\u2229",
+   '\\textasciicircum' => "\u005e",
+   '\\pitchfork' => "\u22d4",
+   '\\textramshorns' => "\u0264",
+   '\\lambda' => "\u03bb",
+   '\\mp' => "\u2213",
+   '\\sqsupset' => "\u2290",
+   '\\textbullet' => "\u2022",
+   '\\rangle' => "\u27e9",
+   '\\DH' => "\u00d0",
+   '\\ni' => "\u220b",
+   '\\texthth' => "\u0266",
+   '\\textscl' => "\u029f",
+   '\\textyogh' => "\u0292",
+   '\\beta' => "\u03b2",
+   '\\textyhook' => "\u01b4",
+   '\\textasciidieresis' => "\u00a8",
+   '\\ntriangleleft' => "\u22ea",
+   '\\curlyeqsucc' => "\u22df",
+   '\\prod' => "\u220f",
+   '\\Gamma' => "\u0393",
+   '\\textbaro' => "\u0275",
+   '\\gtrsim' => "\u2273",
+   '\\bigcap' => "\u22c2",
+   '\\times' => "\u00d7",
+   '\\backsim' => "\u223d",
+   '\\Mu' => "\u039c",
+   '\\texthvlig' => "\u0195",
+   '\\textperthousand' => "\u2030",
+   '\\oint' => "\u222e",
+   '\\nVdash' => "\u22ae",
+   '\\Chi' => "\u03a7",
+   '\\textltailm' => "\u0271",
+   '\\cong' => "\u2245",
+   '\\texthtbardotlessj' => "\u0284",
+   '\\iiint' => "\u222d",
+   '\\textinvglotstop' => "\u0296",
+   '\\nleq' => "\u2270",
+   '\\preccurlyeq' => "\u227c",
+   '\\intercal' => "\u22ba",
+   '\\texthtc' => "\u0188",
+   '\\textscb' => "\u0299",
+   '\\sqsupseteq' => "\u2292",
+   '\\textprimstress' => "\u02c8",
+   '\\textturnw' => "\u028d",
+   '\\textVhook' => "\u01b2",
+   '\\boxminus' => "\u229f",
+   '\\pi' => "\u03c0",
+   '\\geqq' => "\u2267",
+   '\\O' => "\u00d8",
+   '\\textEzh' => "\u01b7",
+   '\\barwedge' => "\u22bc",
+   '\\textgammalatinsmall' => "\u0263",
+   '\\ddots' => "\u22f1",
+   '\\textlengthmark' => "\u02d0",
+   '\\not\\equiv' => "\u2262",
+   '\\not\\approx' => "\u2249",
+   '\\not\\simeq' => "\u2244",
+   '\\not\\sqsupseteq' => "\u22e3",
+   '\\not\\sqsubseteq' => "\u22e2",
+   '\\not\\preccurlyeq' => "\u22e0",
+   '\\not\\subset' => "\u2284",
+   '\\not\\gtrsim' => "\u2275",
+   '\\not\\asymp' => "\u226d",
+   '\\not\\lesssim' => "\u2274",
+   '\\not\\succcurlyeq' => "\u22e1",
+   '\\not\\ni' => "\u220c",
+   '\\not\\supset' => "\u2285",
+  }
+end