1. <lexer>
    
  2.   <config>
    
  3.     <name>Perl</name>
    
  4.     <alias>perl</alias>
    
  5.     <alias>pl</alias>
    
  6.     <filename>*.pl</filename>
    
  7.     <filename>*.pm</filename>
    
  8.     <filename>*.t</filename>
    
  9.     <mime_type>text/x-perl</mime_type>
    
  10.     <mime_type>application/x-perl</mime_type>
    
  11.     <dot_all>true</dot_all>
    
  12.   </config>
    
  13.   <rules>
    
  14.     <state name="root">
    
  15.       <rule pattern="\A\#!.+?$">
    
  16.         <token type="CommentHashbang"/>
    
  17.       </rule>
    
  18.       <rule pattern="\#.*?$">
    
  19.         <token type="CommentSingle"/>
    
  20.       </rule>
    
  21.       <rule pattern="^=[a-zA-Z0-9]+\s+.*?\n=cut">
    
  22.         <token type="CommentMultiline"/>
    
  23.       </rule>
    
  24.       <rule pattern="(continue|foreach|unless|return|elsif|CHECK|while|BEGIN|reset|print|until|next|else|INIT|then|last|redo|case|our|new|for|END|if|do|my)\b">
    
  25.         <token type="Keyword"/>
    
  26.       </rule>
    
  27.       <rule pattern="(format)(\s+)(\w+)(\s*)(=)(\s*\n)">
    
  28.         <bygroups>
    
  29.           <token type="Keyword"/>
    
  30.           <token type="Text"/>
    
  31.           <token type="Name"/>
    
  32.           <token type="Text"/>
    
  33.           <token type="Punctuation"/>
    
  34.           <token type="Text"/>
    
  35.         </bygroups>
    
  36.         <push state="format"/>
    
  37.       </rule>
    
  38.       <rule pattern="(eq|lt|gt|le|ge|ne|not|and|or|cmp)\b">
    
  39.         <token type="OperatorWord"/>
    
  40.       </rule>
    
  41.       <rule pattern="s/(\\\\|\\[^\\]|[^\\/])*/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*">
    
  42.         <token type="LiteralStringRegex"/>
    
  43.       </rule>
    
  44.       <rule pattern="s!(\\\\|\\!|[^!])*!(\\\\|\\!|[^!])*![egimosx]*">
    
  45.         <token type="LiteralStringRegex"/>
    
  46.       </rule>
    
  47.       <rule pattern="s\\(\\\\|[^\\])*\\(\\\\|[^\\])*\\[egimosx]*">
    
  48.         <token type="LiteralStringRegex"/>
    
  49.       </rule>
    
  50.       <rule pattern="s@(\\\\|\\[^\\]|[^\\@])*@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*">
    
  51.         <token type="LiteralStringRegex"/>
    
  52.       </rule>
    
  53.       <rule pattern="s%(\\\\|\\[^\\]|[^\\%])*%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*">
    
  54.         <token type="LiteralStringRegex"/>
    
  55.       </rule>
    
  56.       <rule pattern="s\{(\\\\|\\[^\\]|[^\\}])*\}\s*">
    
  57.         <token type="LiteralStringRegex"/>
    
  58.         <push state="balanced-regex"/>
    
  59.       </rule>
    
  60.       <rule pattern="s&lt;(\\\\|\\[^\\]|[^\\&gt;])*&gt;\s*">
    
  61.         <token type="LiteralStringRegex"/>
    
  62.         <push state="balanced-regex"/>
    
  63.       </rule>
    
  64.       <rule pattern="s\[(\\\\|\\[^\\]|[^\\\]])*\]\s*">
    
  65.         <token type="LiteralStringRegex"/>
    
  66.         <push state="balanced-regex"/>
    
  67.       </rule>
    
  68.       <rule pattern="s\((\\\\|\\[^\\]|[^\\)])*\)\s*">
    
  69.         <token type="LiteralStringRegex"/>
    
  70.         <push state="balanced-regex"/>
    
  71.       </rule>
    
  72.       <rule pattern="m?/(\\\\|\\[^\\]|[^\\/\n])*/[gcimosx]*">
    
  73.         <token type="LiteralStringRegex"/>
    
  74.       </rule>
    
  75.       <rule pattern="m(?=[/!\\{&lt;\[(@%$])">
    
  76.         <token type="LiteralStringRegex"/>
    
  77.         <push state="balanced-regex"/>
    
  78.       </rule>
    
  79.       <rule pattern="((?&lt;==~)|(?&lt;=\())\s*/(\\\\|\\[^\\]|[^\\/])*/[gcimosx]*">
    
  80.         <token type="LiteralStringRegex"/>
    
  81.       </rule>
    
  82.       <rule pattern="\s+">
    
  83.         <token type="Text"/>
    
  84.       </rule>
    
  85.       <rule pattern="(getprotobynumber|getprotobyname|getservbyport|getservbyname|gethostbyname|gethostbyaddr|getnetbyaddr|getnetbyname|setprotoent|setpriority|getsockname|getprotoent|getpriority|getpeername|endprotoent|setsockopt|endhostent|setservent|socketpair|getsockopt|endservent|sethostent|getservent|gethostent|getnetent|wantarray|localtime|quotemeta|setnetent|prototype|endnetent|rewinddir|endpwent|endgrent|getpwent|getpwnam|getgrgid|dbmclose|continue|closedir|shutdown|setpwent|shmwrite|syswrite|truncate|formline|setgrent|getgrent|readpipe|getgrnam|readlink|readline|getpwuid|getlogin|telldir|opendir|shmread|readdir|getpgrp|getppid|waitpid|binmode|reverse|sprintf|unshift|symlink|seekdir|sysopen|defined|dbmopen|sysread|sysseek|connect|lcfirst|ucfirst|setpgrp|syscall|import|chroot|system|gmtime|unlink|unpack|semget|semctl|select|msgrcv|length|printf|listen|scalar|caller|rindex|substr|splice|rename|msgctl|msgget|delete|msgsnd|exists|values|socket|fileno|format|accept|shmget|shmctl|ioctl|alarm|atan2|utime|untie|bless|chdir|chmod|undef|umask|chomp|times|close|crypt|srand|split|mkdir|sleep|lstat|study|rmdir|local|fcntl|flock|write|shift|index|semop|chown|tell|join|send|warn|kill|wait|grep|glob|bind|last|pack|getc|fork|link|seek|push|rand|read|exit|sort|exec|open|eval|sqrt|redo|stat|chop|next|each|dump|time|recv|tied|goto|keys|pipe|map|tie|cos|die|eof|pop|sin|pos|oct|ref|exp|int|ord|log|our|hex|abs|vec|chr|uc|tr|my|lc)\b">
    
  86.         <token type="NameBuiltin"/>
    
  87.       </rule>
    
  88.       <rule pattern="((__(DATA|DIE|WARN)__)|(STD(IN|OUT|ERR)))\b">
    
  89.         <token type="NameBuiltinPseudo"/>
    
  90.       </rule>
    
  91.       <rule pattern="(&lt;&lt;)([\&#39;&#34;]?)([a-zA-Z_]\w*)(\2;?\n.*?\n)(\3)(\n)">
    
  92.         <bygroups>
    
  93.           <token type="LiteralString"/>
    
  94.           <token type="LiteralString"/>
    
  95.           <token type="LiteralStringDelimiter"/>
    
  96.           <token type="LiteralString"/>
    
  97.           <token type="LiteralStringDelimiter"/>
    
  98.           <token type="Text"/>
    
  99.         </bygroups>
    
  100.       </rule>
    
  101.       <rule pattern="__END__">
    
  102.         <token type="CommentPreproc"/>
    
  103.         <push state="end-part"/>
    
  104.       </rule>
    
  105.       <rule pattern="\$\^[ADEFHILMOPSTWX]">
    
  106.         <token type="NameVariableGlobal"/>
    
  107.       </rule>
    
  108.       <rule pattern="\$[\\\&#34;\[\]&#39;&amp;`+*.,;=%~?@$!&lt;&gt;(^|/-](?!\w)">
    
  109.         <token type="NameVariableGlobal"/>
    
  110.       </rule>
    
  111.       <rule pattern="[$@%#]+">
    
  112.         <token type="NameVariable"/>
    
  113.         <push state="varname"/>
    
  114.       </rule>
    
  115.       <rule pattern="0_?[0-7]+(_[0-7]+)*">
    
  116.         <token type="LiteralNumberOct"/>
    
  117.       </rule>
    
  118.       <rule pattern="0x[0-9A-Fa-f]+(_[0-9A-Fa-f]+)*">
    
  119.         <token type="LiteralNumberHex"/>
    
  120.       </rule>
    
  121.       <rule pattern="0b[01]+(_[01]+)*">
    
  122.         <token type="LiteralNumberBin"/>
    
  123.       </rule>
    
  124.       <rule pattern="(?i)(\d*(_\d*)*\.\d+(_\d*)*|\d+(_\d*)*\.\d+(_\d*)*)(e[+-]?\d+)?">
    
  125.         <token type="LiteralNumberFloat"/>
    
  126.       </rule>
    
  127.       <rule pattern="(?i)\d+(_\d*)*e[+-]?\d+(_\d*)*">
    
  128.         <token type="LiteralNumberFloat"/>
    
  129.       </rule>
    
  130.       <rule pattern="\d+(_\d+)*">
    
  131.         <token type="LiteralNumberInteger"/>
    
  132.       </rule>
    
  133.       <rule pattern="&#39;(\\\\|\\[^\\]|[^&#39;\\])*&#39;">
    
  134.         <token type="LiteralString"/>
    
  135.       </rule>
    
  136.       <rule pattern="&#34;(\\\\|\\[^\\]|[^&#34;\\])*&#34;">
    
  137.         <token type="LiteralString"/>
    
  138.       </rule>
    
  139.       <rule pattern="`(\\\\|\\[^\\]|[^`\\])*`">
    
  140.         <token type="LiteralStringBacktick"/>
    
  141.       </rule>
    
  142.       <rule pattern="&lt;([^\s&gt;]+)&gt;">
    
  143.         <token type="LiteralStringRegex"/>
    
  144.       </rule>
    
  145.       <rule pattern="(q|qq|qw|qr|qx)\{">
    
  146.         <token type="LiteralStringOther"/>
    
  147.         <push state="cb-string"/>
    
  148.       </rule>
    
  149.       <rule pattern="(q|qq|qw|qr|qx)\(">
    
  150.         <token type="LiteralStringOther"/>
    
  151.         <push state="rb-string"/>
    
  152.       </rule>
    
  153.       <rule pattern="(q|qq|qw|qr|qx)\[">
    
  154.         <token type="LiteralStringOther"/>
    
  155.         <push state="sb-string"/>
    
  156.       </rule>
    
  157.       <rule pattern="(q|qq|qw|qr|qx)\&lt;">
    
  158.         <token type="LiteralStringOther"/>
    
  159.         <push state="lt-string"/>
    
  160.       </rule>
    
  161.       <rule pattern="(q|qq|qw|qr|qx)([\W_])(.|\n)*?\2">
    
  162.         <token type="LiteralStringOther"/>
    
  163.       </rule>
    
  164.       <rule pattern="(package)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)">
    
  165.         <bygroups>
    
  166.           <token type="Keyword"/>
    
  167.           <token type="Text"/>
    
  168.           <token type="NameNamespace"/>
    
  169.         </bygroups>
    
  170.       </rule>
    
  171.       <rule pattern="(use|require|no)(\s+)([a-zA-Z_]\w*(?:::[a-zA-Z_]\w*)*)">
    
  172.         <bygroups>
    
  173.           <token type="Keyword"/>
    
  174.           <token type="Text"/>
    
  175.           <token type="NameNamespace"/>
    
  176.         </bygroups>
    
  177.       </rule>
    
  178.       <rule pattern="(sub)(\s+)">
    
  179.         <bygroups>
    
  180.           <token type="Keyword"/>
    
  181.           <token type="Text"/>
    
  182.         </bygroups>
    
  183.         <push state="funcname"/>
    
  184.       </rule>
    
  185.       <rule pattern="(package|require|use|no)\b">
    
  186.         <token type="Keyword"/>
    
  187.       </rule>
    
  188.       <rule pattern="(\[\]|\*\*|::|&lt;&lt;|&gt;&gt;|&gt;=|&lt;=&gt;|&lt;=|={3}|!=|=~|!~|&amp;&amp;?|\|\||\.{1,3})">
    
  189.         <token type="Operator"/>
    
  190.       </rule>
    
  191.       <rule pattern="[-+/*%=&lt;&gt;&amp;^|!\\~]=?">
    
  192.         <token type="Operator"/>
    
  193.       </rule>
    
  194.       <rule pattern="[()\[\]:;,&lt;&gt;/?{}]">
    
  195.         <token type="Punctuation"/>
    
  196.       </rule>
    
  197.       <rule pattern="(?=\w)">
    
  198.         <token type="Name"/>
    
  199.         <push state="name"/>
    
  200.       </rule>
    
  201.     </state>
    
  202.     <state name="cb-string">
    
  203.       <rule pattern="\\[{}\\]">
    
  204.         <token type="LiteralStringOther"/>
    
  205.       </rule>
    
  206.       <rule pattern="\\">
    
  207.         <token type="LiteralStringOther"/>
    
  208.       </rule>
    
  209.       <rule pattern="\{">
    
  210.         <token type="LiteralStringOther"/>
    
  211.         <push state="cb-string"/>
    
  212.       </rule>
    
  213.       <rule pattern="\}">
    
  214.         <token type="LiteralStringOther"/>
    
  215.         <pop depth="1"/>
    
  216.       </rule>
    
  217.       <rule pattern="[^{}\\]+">
    
  218.         <token type="LiteralStringOther"/>
    
  219.       </rule>
    
  220.     </state>
    
  221.     <state name="balanced-regex">
    
  222.       <rule pattern="/(\\\\|\\[^\\]|[^\\/])*/[egimosx]*">
    
  223.         <token type="LiteralStringRegex"/>
    
  224.         <pop depth="1"/>
    
  225.       </rule>
    
  226.       <rule pattern="!(\\\\|\\[^\\]|[^\\!])*![egimosx]*">
    
  227.         <token type="LiteralStringRegex"/>
    
  228.         <pop depth="1"/>
    
  229.       </rule>
    
  230.       <rule pattern="\\(\\\\|[^\\])*\\[egimosx]*">
    
  231.         <token type="LiteralStringRegex"/>
    
  232.         <pop depth="1"/>
    
  233.       </rule>
    
  234.       <rule pattern="\{(\\\\|\\[^\\]|[^\\}])*\}[egimosx]*">
    
  235.         <token type="LiteralStringRegex"/>
    
  236.         <pop depth="1"/>
    
  237.       </rule>
    
  238.       <rule pattern="&lt;(\\\\|\\[^\\]|[^\\&gt;])*&gt;[egimosx]*">
    
  239.         <token type="LiteralStringRegex"/>
    
  240.         <pop depth="1"/>
    
  241.       </rule>
    
  242.       <rule pattern="\[(\\\\|\\[^\\]|[^\\\]])*\][egimosx]*">
    
  243.         <token type="LiteralStringRegex"/>
    
  244.         <pop depth="1"/>
    
  245.       </rule>
    
  246.       <rule pattern="\((\\\\|\\[^\\]|[^\\)])*\)[egimosx]*">
    
  247.         <token type="LiteralStringRegex"/>
    
  248.         <pop depth="1"/>
    
  249.       </rule>
    
  250.       <rule pattern="@(\\\\|\\[^\\]|[^\\@])*@[egimosx]*">
    
  251.         <token type="LiteralStringRegex"/>
    
  252.         <pop depth="1"/>
    
  253.       </rule>
    
  254.       <rule pattern="%(\\\\|\\[^\\]|[^\\%])*%[egimosx]*">
    
  255.         <token type="LiteralStringRegex"/>
    
  256.         <pop depth="1"/>
    
  257.       </rule>
    
  258.       <rule pattern="\$(\\\\|\\[^\\]|[^\\$])*\$[egimosx]*">
    
  259.         <token type="LiteralStringRegex"/>
    
  260.         <pop depth="1"/>
    
  261.       </rule>
    
  262.     </state>
    
  263.     <state name="lt-string">
    
  264.       <rule pattern="\\[&lt;&gt;\\]">
    
  265.         <token type="LiteralStringOther"/>
    
  266.       </rule>
    
  267.       <rule pattern="\\">
    
  268.         <token type="LiteralStringOther"/>
    
  269.       </rule>
    
  270.       <rule pattern="\&lt;">
    
  271.         <token type="LiteralStringOther"/>
    
  272.         <push state="lt-string"/>
    
  273.       </rule>
    
  274.       <rule pattern="\&gt;">
    
  275.         <token type="LiteralStringOther"/>
    
  276.         <pop depth="1"/>
    
  277.       </rule>
    
  278.       <rule pattern="[^&lt;&gt;]+">
    
  279.         <token type="LiteralStringOther"/>
    
  280.       </rule>
    
  281.     </state>
    
  282.     <state name="format">
    
  283.       <rule pattern="\.\n">
    
  284.         <token type="LiteralStringInterpol"/>
    
  285.         <pop depth="1"/>
    
  286.       </rule>
    
  287.       <rule pattern="[^\n]*\n">
    
  288.         <token type="LiteralStringInterpol"/>
    
  289.       </rule>
    
  290.     </state>
    
  291.     <state name="funcname">
    
  292.       <rule pattern="[a-zA-Z_]\w*[!?]?">
    
  293.         <token type="NameFunction"/>
    
  294.       </rule>
    
  295.       <rule pattern="\s+">
    
  296.         <token type="Text"/>
    
  297.       </rule>
    
  298.       <rule pattern="(\([$@%]*\))(\s*)">
    
  299.         <bygroups>
    
  300.           <token type="Punctuation"/>
    
  301.           <token type="Text"/>
    
  302.         </bygroups>
    
  303.       </rule>
    
  304.       <rule pattern=";">
    
  305.         <token type="Punctuation"/>
    
  306.         <pop depth="1"/>
    
  307.       </rule>
    
  308.       <rule pattern=".*?\{">
    
  309.         <token type="Punctuation"/>
    
  310.         <pop depth="1"/>
    
  311.       </rule>
    
  312.     </state>
    
  313.     <state name="end-part">
    
  314.       <rule pattern=".+">
    
  315.         <token type="CommentPreproc"/>
    
  316.         <pop depth="1"/>
    
  317.       </rule>
    
  318.     </state>
    
  319.     <state name="varname">
    
  320.       <rule pattern="\s+">
    
  321.         <token type="Text"/>
    
  322.       </rule>
    
  323.       <rule pattern="\{">
    
  324.         <token type="Punctuation"/>
    
  325.         <pop depth="1"/>
    
  326.       </rule>
    
  327.       <rule pattern="\)|,">
    
  328.         <token type="Punctuation"/>
    
  329.         <pop depth="1"/>
    
  330.       </rule>
    
  331.       <rule pattern="\w+::">
    
  332.         <token type="NameNamespace"/>
    
  333.       </rule>
    
  334.       <rule pattern="[\w:]+">
    
  335.         <token type="NameVariable"/>
    
  336.         <pop depth="1"/>
    
  337.       </rule>
    
  338.     </state>
    
  339.     <state name="name">
    
  340.       <rule pattern="[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*(::)?(?=\s*-&gt;)">
    
  341.         <token type="NameNamespace"/>
    
  342.         <pop depth="1"/>
    
  343.       </rule>
    
  344.       <rule pattern="[a-zA-Z_]\w*(::[a-zA-Z_]\w*)*::">
    
  345.         <token type="NameNamespace"/>
    
  346.         <pop depth="1"/>
    
  347.       </rule>
    
  348.       <rule pattern="[\w:]+">
    
  349.         <token type="Name"/>
    
  350.         <pop depth="1"/>
    
  351.       </rule>
    
  352.       <rule pattern="[A-Z_]+(?=\W)">
    
  353.         <token type="NameConstant"/>
    
  354.         <pop depth="1"/>
    
  355.       </rule>
    
  356.       <rule pattern="(?=\W)">
    
  357.         <token type="Text"/>
    
  358.         <pop depth="1"/>
    
  359.       </rule>
    
  360.     </state>
    
  361.     <state name="rb-string">
    
  362.       <rule pattern="\\[()\\]">
    
  363.         <token type="LiteralStringOther"/>
    
  364.       </rule>
    
  365.       <rule pattern="\\">
    
  366.         <token type="LiteralStringOther"/>
    
  367.       </rule>
    
  368.       <rule pattern="\(">
    
  369.         <token type="LiteralStringOther"/>
    
  370.         <push state="rb-string"/>
    
  371.       </rule>
    
  372.       <rule pattern="\)">
    
  373.         <token type="LiteralStringOther"/>
    
  374.         <pop depth="1"/>
    
  375.       </rule>
    
  376.       <rule pattern="[^()]+">
    
  377.         <token type="LiteralStringOther"/>
    
  378.       </rule>
    
  379.     </state>
    
  380.     <state name="sb-string">
    
  381.       <rule pattern="\\[\[\]\\]">
    
  382.         <token type="LiteralStringOther"/>
    
  383.       </rule>
    
  384.       <rule pattern="\\">
    
  385.         <token type="LiteralStringOther"/>
    
  386.       </rule>
    
  387.       <rule pattern="\[">
    
  388.         <token type="LiteralStringOther"/>
    
  389.         <push state="sb-string"/>
    
  390.       </rule>
    
  391.       <rule pattern="\]">
    
  392.         <token type="LiteralStringOther"/>
    
  393.         <pop depth="1"/>
    
  394.       </rule>
    
  395.       <rule pattern="[^\[\]]+">
    
  396.         <token type="LiteralStringOther"/>
    
  397.       </rule>
    
  398.     </state>
    
  399.   </rules>
    
  400. </lexer>