Merge branch 'more_lexers'

This commit is contained in:
Roberto Alsina 2024-08-23 10:34:17 -03:00
commit 06556877ef
16 changed files with 1599 additions and 1146 deletions

1
.gitignore vendored
View File

@ -8,3 +8,4 @@ pygments/
shard.lock
.vscode/
.crystal/
venv/

View File

@ -9,4 +9,4 @@
* ✅ Implement lexer loader by file extension
* ✅ Add --line-numbers to terminal formatter
* Implement lexer loader by mime type
* Implement Delegating lexers
* Implement Delegating lexers

130
lexers/LiquidLexer.xml Normal file
View File

@ -0,0 +1,130 @@
<lexer>
<config>
<name>liquid</name>
<alias>liquid</alias>
<filename>*.liquid</filename>
</config>
<rules>
<state name="root">
<rule pattern="[^{]+"><token type="Text"/></rule>
<rule pattern="(\{%)(\s*)"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="tag-or-block"/></rule>
<rule pattern="(\{\{)(\s*)([^\s}]+)"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><usingself state="generic"/></bygroups><push state="output"/></rule>
<rule pattern="\{"><token type="Text"/></rule>
</state>
<state name="tag-or-block">
<rule pattern="(if|unless|elsif|case)(?=\s+)"><token type="KeywordReserved"/><push state="condition"/></rule>
<rule pattern="(when)(\s+)"><bygroups><token type="KeywordReserved"/><token type="TextWhitespace"/></bygroups><combined state="end-of-block" state="whitespace" state="generic"/></rule>
<rule pattern="(else)(\s*)(%\})"><bygroups><token type="KeywordReserved"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
<rule pattern="(capture)(\s+)([^\s%]+)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><usingself state="variable"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
<rule pattern="(comment)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="comment"/></rule>
<rule pattern="(raw)(\s*)(%\})"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="raw"/></rule>
<rule pattern="(end(case|unless|if))(\s*)(%\})"><bygroups><token type="KeywordReserved"/>None<token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
<rule pattern="(end([^\s%]+))(\s*)(%\})"><bygroups><token type="NameTag"/>None<token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
<rule pattern="(cycle)(\s+)(?:([^\s:]*)(:))?(\s*)"><bygroups><token type="NameTag"/><token type="TextWhitespace"/><usingself state="generic"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="variable-tag-markup"/></rule>
<rule pattern="([^\s%]+)(\s*)"><bygroups><token type="NameTag"/><token type="TextWhitespace"/></bygroups><push state="tag-markup"/></rule>
</state>
<state name="output">
<rule><include state="whitespace"/></rule>
<rule pattern="\}\}"><token type="Punctuation"/><pop depth="1"/></rule>
<rule pattern="\|"><token type="Punctuation"/><push state="filters"/></rule>
</state>
<state name="filters">
<rule><include state="whitespace"/></rule>
<rule pattern="\}\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
<rule pattern="([^\s|:]+)(:?)(\s*)"><bygroups><token type="NameFunction"/><token type="Punctuation"/><token type="TextWhitespace"/></bygroups><push state="filter-markup"/></rule>
</state>
<state name="filter-markup">
<rule pattern="\|"><token type="Punctuation"/><pop depth="1"/></rule>
<rule><include state="end-of-tag"/></rule>
<rule><include state="default-param-markup"/></rule>
</state>
<state name="condition">
<rule><include state="end-of-block"/></rule>
<rule><include state="whitespace"/></rule>
<rule pattern="([^\s=!&gt;&lt;]+)(\s*)([=!&gt;&lt;]=?)(\s*)(\S+)(\s*)(%\})"><bygroups><usingself state="generic"/><token type="TextWhitespace"/><token type="Operator"/><token type="TextWhitespace"/><usingself state="generic"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
<rule pattern="\b!"><token type="Operator"/></rule>
<rule pattern="\bnot\b"><token type="OperatorWord"/></rule>
<rule pattern="([\w.\&#x27;&quot;]+)(\s+)(contains)(\s+)([\w.\&#x27;&quot;]+)"><bygroups><usingself state="generic"/><token type="TextWhitespace"/><token type="OperatorWord"/><token type="TextWhitespace"/><usingself state="generic"/></bygroups></rule>
<rule><include state="generic"/></rule>
<rule><include state="whitespace"/></rule>
</state>
<state name="generic-value">
<rule><include state="generic"/></rule>
<rule><include state="end-at-whitespace"/></rule>
</state>
<state name="operator">
<rule pattern="(\s*)((=|!|&gt;|&lt;)=?)(\s*)"><bygroups><token type="TextWhitespace"/><token type="Operator"/>None<token type="TextWhitespace"/></bygroups><pop depth="1"/></rule>
<rule pattern="(\s*)(\bcontains\b)(\s*)"><bygroups><token type="TextWhitespace"/><token type="OperatorWord"/><token type="TextWhitespace"/></bygroups><pop depth="1"/></rule>
</state>
<state name="end-of-tag">
<rule pattern="\}\}"><token type="Punctuation"/><pop depth="1"/></rule>
</state>
<state name="end-of-block">
<rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
</state>
<state name="end-at-whitespace">
<rule pattern="\s+"><token type="TextWhitespace"/><pop depth="1"/></rule>
</state>
<state name="param-markup">
<rule><include state="whitespace"/></rule>
<rule pattern="([^\s=:]+)(\s*)(=|:)"><bygroups><token type="NameAttribute"/><token type="TextWhitespace"/><token type="Operator"/></bygroups></rule>
<rule pattern="(\{\{)(\s*)([^\s}])(\s*)(\}\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><usingself state="variable"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups></rule>
<rule><include state="string"/></rule>
<rule><include state="number"/></rule>
<rule><include state="keyword"/></rule>
<rule pattern=","><token type="Punctuation"/></rule>
</state>
<state name="default-param-markup">
<rule><include state="param-markup"/></rule>
<rule pattern="."><token type="Text"/></rule>
</state>
<state name="variable-param-markup">
<rule><include state="param-markup"/></rule>
<rule><include state="variable"/></rule>
<rule pattern="."><token type="Text"/></rule>
</state>
<state name="tag-markup">
<rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
<rule><include state="default-param-markup"/></rule>
</state>
<state name="variable-tag-markup">
<rule pattern="%\}"><token type="Punctuation"/><push state="#pop" state="#pop"/></rule>
<rule><include state="variable-param-markup"/></rule>
</state>
<state name="keyword">
<rule pattern="\b(false|true)\b"><token type="KeywordConstant"/></rule>
</state>
<state name="variable">
<rule pattern="[a-zA-Z_]\w*"><token type="NameVariable"/></rule>
<rule pattern="(?&lt;=\w)\.(?=\w)"><token type="Punctuation"/></rule>
</state>
<state name="string">
<rule pattern="&#x27;[^&#x27;]*&#x27;"><token type="LiteralStringSingle"/></rule>
<rule pattern="&quot;[^&quot;]*&quot;"><token type="LiteralStringDouble"/></rule>
</state>
<state name="number">
<rule pattern="\d+\.\d+"><token type="LiteralNumberFloat"/></rule>
<rule pattern="\d+"><token type="LiteralNumberInteger"/></rule>
</state>
<state name="generic">
<rule><include state="keyword"/></rule>
<rule><include state="string"/></rule>
<rule><include state="number"/></rule>
<rule><include state="variable"/></rule>
</state>
<state name="whitespace">
<rule pattern="[ \t]+"><token type="TextWhitespace"/></rule>
</state>
<state name="comment">
<rule pattern="(\{%)(\s*)(endcomment)(\s*)(%\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><push state="#pop" state="#pop"/></rule>
<rule pattern="."><token type="Comment"/></rule>
</state>
<state name="raw">
<rule pattern="[^{]+"><token type="Text"/></rule>
<rule pattern="(\{%)(\s*)(endraw)(\s*)(%\})"><bygroups><token type="Punctuation"/><token type="TextWhitespace"/><token type="NameTag"/><token type="TextWhitespace"/><token type="Punctuation"/></bygroups><pop depth="1"/></rule>
<rule pattern="\{"><token type="Text"/></rule>
</state>
</rules>
</lexer>

47
lexers/TwigLexer.xml Normal file
View File

@ -0,0 +1,47 @@
<lexer>
<config>
<name>Twig</name>
<alias>twig</alias>
<mime_type>application/x-twig</mime_type>
<dot_all>true</dot_all>
</config>
<rules>
<state name="root">
<rule pattern="[^{]+"><token type="Other"/></rule>
<rule pattern="\{\{"><token type="CommentPreproc"/><push state="var"/></rule>
<rule pattern="\{\#.*?\#\}"><token type="Comment"/></rule>
<rule pattern="(\{%)(-?\s*)(raw)(\s*-?)(%\})(.*?)(\{%)(-?\s*)(endraw)(\s*-?)(%\})"><bygroups><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="CommentPreproc"/><token type="Other"/><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="CommentPreproc"/></bygroups></rule>
<rule pattern="(\{%)(-?\s*)(verbatim)(\s*-?)(%\})(.*?)(\{%)(-?\s*)(endverbatim)(\s*-?)(%\})"><bygroups><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="CommentPreproc"/><token type="Other"/><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="CommentPreproc"/></bygroups></rule>
<rule pattern="(\{%)(-?\s*)(filter)(\s+)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w-]|[^\x00-\x7f])*)"><bygroups><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="NameFunction"/></bygroups><push state="tag"/></rule>
<rule pattern="(\{%)(-?\s*)([a-zA-Z_]\w*)"><bygroups><token type="CommentPreproc"/><token type="Text"/><token type="Keyword"/></bygroups><push state="tag"/></rule>
<rule pattern="\{"><token type="Other"/></rule>
</state>
<state name="varnames">
<rule pattern="(\|)(\s*)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w-]|[^\x00-\x7f])*)"><bygroups><token type="Operator"/><token type="Text"/><token type="NameFunction"/></bygroups></rule>
<rule pattern="(is)(\s+)(not)?(\s*)((?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w-]|[^\x00-\x7f])*)"><bygroups><token type="Keyword"/><token type="Text"/><token type="Keyword"/><token type="Text"/><token type="NameFunction"/></bygroups></rule>
<rule pattern="(?i)(true|false|none|null)\b"><token type="KeywordPseudo"/></rule>
<rule pattern="(in|not|and|b-and|or|b-or|b-xor|isif|elseif|else|importconstant|defined|divisibleby|empty|even|iterable|odd|sameasmatches|starts\s+with|ends\s+with)\b"><token type="Keyword"/></rule>
<rule pattern="(loop|block|parent)\b"><token type="NameBuiltin"/></rule>
<rule pattern="(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w-]|[^\x00-\x7f])*"><token type="NameVariable"/></rule>
<rule pattern="\.(?:[\\_a-z]|[^\x00-\x7f])(?:[\\\w-]|[^\x00-\x7f])*"><token type="NameVariable"/></rule>
<rule pattern="\.[0-9]+"><token type="LiteralNumber"/></rule>
<rule pattern=":?&quot;(\\\\|\\[^\\]|[^&quot;\\])*&quot;"><token type="LiteralStringDouble"/></rule>
<rule pattern=":?&#x27;(\\\\|\\[^\\]|[^&#x27;\\])*&#x27;"><token type="LiteralStringSingle"/></rule>
<rule pattern="([{}()\[\]+\-*/,:~%]|\.\.|\?|:|\*\*|\/\/|!=|[&gt;&lt;=]=?)"><token type="Operator"/></rule>
<rule pattern="[0-9](\.[0-9]*)?(eE[+-][0-9])?[flFLdD]?|0[xX][0-9a-fA-F]+[Ll]?"><token type="LiteralNumber"/></rule>
</state>
<state name="var">
<rule pattern="\s+"><token type="Text"/></rule>
<rule pattern="(-?)(\}\})"><bygroups><token type="Text"/><token type="CommentPreproc"/></bygroups><pop depth="1"/></rule>
<rule><include state="varnames"/></rule>
</state>
<state name="tag">
<rule pattern="\s+"><token type="Text"/></rule>
<rule pattern="(-?)(%\})"><bygroups><token type="Text"/><token type="CommentPreproc"/></bygroups><pop depth="1"/></rule>
<rule><include state="varnames"/></rule>
<rule pattern="."><token type="Punctuation"/></rule>
</state>
</rules>
</lexer>

55
lexers/VelocityLexer.xml Normal file
View File

@ -0,0 +1,55 @@
<lexer>
<config>
<name>Velocity</name>
<alias>velocity</alias>
<filename>*.vm</filename>
<filename>*.fhtml</filename>
<dot_all>true</dot_all>
</config>
<rules>
<state name="root">
<rule pattern="[^{#$]+"><token type="Other"/></rule>
<rule pattern="(#)(\*.*?\*)(#)"><bygroups><token type="CommentPreproc"/><token type="Comment"/><token type="CommentPreproc"/></bygroups></rule>
<rule pattern="(##)(.*?$)"><bygroups><token type="CommentPreproc"/><token type="Comment"/></bygroups></rule>
<rule pattern="(#\{?)([a-zA-Z_]\w*)(\}?)(\s?\()"><bygroups><token type="CommentPreproc"/><token type="NameFunction"/><token type="CommentPreproc"/><token type="Punctuation"/></bygroups><push state="directiveparams"/></rule>
<rule pattern="(#\{?)([a-zA-Z_]\w*)(\}|\b)"><bygroups><token type="CommentPreproc"/><token type="NameFunction"/><token type="CommentPreproc"/></bygroups></rule>
<rule pattern="\$!?\{?"><token type="Punctuation"/><push state="variable"/></rule>
</state>
<state name="variable">
<rule pattern="[a-zA-Z_]\w*"><token type="NameVariable"/></rule>
<rule pattern="\("><token type="Punctuation"/><push state="funcparams"/></rule>
<rule pattern="(\.)([a-zA-Z_]\w*)"><bygroups><token type="Punctuation"/><token type="NameVariable"/></bygroups><push/></rule>
<rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
<rule><pop depth="1"/></rule>
</state>
<state name="directiveparams">
<rule pattern="(&amp;&amp;|\|\||==?|!=?|[-&lt;&gt;+*%&amp;|^/])|\b(eq|ne|gt|lt|ge|le|not|in)\b"><token type="Operator"/></rule>
<rule pattern="\["><token type="Operator"/><push state="rangeoperator"/></rule>
<rule pattern="\b[a-zA-Z_]\w*\b"><token type="NameFunction"/></rule>
<rule><include state="funcparams"/></rule>
</state>
<state name="rangeoperator">
<rule pattern="\.\."><token type="Operator"/></rule>
<rule><include state="funcparams"/></rule>
<rule pattern="\]"><token type="Operator"/><pop depth="1"/></rule>
</state>
<state name="funcparams">
<rule pattern="\$!?\{?"><token type="Punctuation"/><push state="variable"/></rule>
<rule pattern="\s+"><token type="Text"/></rule>
<rule pattern="[,:]"><token type="Punctuation"/></rule>
<rule pattern="&quot;(\\\\|\\[^\\]|[^&quot;\\])*&quot;"><token type="LiteralStringDouble"/></rule>
<rule pattern="&#x27;(\\\\|\\[^\\]|[^&#x27;\\])*&#x27;"><token type="LiteralStringSingle"/></rule>
<rule pattern="0[xX][0-9a-fA-F]+[Ll]?"><token type="LiteralNumber"/></rule>
<rule pattern="\b[0-9]+\b"><token type="LiteralNumber"/></rule>
<rule pattern="(true|false|null)\b"><token type="KeywordConstant"/></rule>
<rule pattern="\("><token type="Punctuation"/><push/></rule>
<rule pattern="\)"><token type="Punctuation"/><pop depth="1"/></rule>
<rule pattern="\{"><token type="Punctuation"/><push/></rule>
<rule pattern="\}"><token type="Punctuation"/><pop depth="1"/></rule>
<rule pattern="\["><token type="Punctuation"/><push/></rule>
<rule pattern="\]"><token type="Punctuation"/><pop depth="1"/></rule>
</state>
</rules>
</lexer>

22
lexers/bbcode.xml Normal file
View File

@ -0,0 +1,22 @@
<lexer>
<config>
<name>BBCode</name>
<alias>bbcode</alias>
<mime_type>text/x-bbcode</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="[^[]+"><token type="Text"/></rule>
<rule pattern="\[/?\w+"><token type="Keyword"/><push state="tag"/></rule>
<rule pattern="\["><token type="Text"/></rule>
</state>
<state name="tag">
<rule pattern="\s+"><token type="Text"/></rule>
<rule pattern="(\w+)(=)(&quot;?[^\s&quot;\]]+&quot;?)"><bygroups><token type="NameAttribute"/><token type="Operator"/><token type="LiteralString"/></bygroups></rule>
<rule pattern="(=)(&quot;?[^\s&quot;\]]+&quot;?)"><bygroups><token type="Operator"/><token type="LiteralString"/></bygroups></rule>
<rule pattern="\]"><token type="Keyword"/><pop depth="1"/></rule>
</state>
</rules>
</lexer>

56
lexers/markdown.xml Normal file
View File

@ -0,0 +1,56 @@
<lexer>
<config>
<name>Markdown</name>
<alias>markdown</alias>
<alias>md</alias>
<filename>*.md</filename>
<filename>*.markdown</filename>
<mime_type>text/x-markdown</mime_type>
</config>
<rules>
<state name="root">
<rule pattern="(^#[^#].+)(\n)"><bygroups><token type="GenericHeading"/><token type="Text"/></bygroups></rule>
<rule pattern="(^#{2,6}[^#].+)(\n)"><bygroups><token type="GenericSubheading"/><token type="Text"/></bygroups></rule>
<rule pattern="^(.+)(\n)(=+)(\n)"><bygroups><token type="GenericHeading"/><token type="Text"/><token type="GenericHeading"/><token type="Text"/></bygroups></rule>
<rule pattern="^(.+)(\n)(-+)(\n)"><bygroups><token type="GenericSubheading"/><token type="Text"/><token type="GenericSubheading"/><token type="Text"/></bygroups></rule>
<rule pattern="^(\s*)([*-] )(\[[ xX]\])( .+\n)"><bygroups><token type="TextWhitespace"/><token type="Keyword"/><token type="Keyword"/><usingself state="inline"/></bygroups></rule>
<rule pattern="^(\s*)([*-])(\s)(.+\n)"><bygroups><token type="TextWhitespace"/><token type="Keyword"/><token type="TextWhitespace"/><usingself state="inline"/></bygroups></rule>
<rule pattern="^(\s*)([0-9]+\.)( .+\n)"><bygroups><token type="TextWhitespace"/><token type="Keyword"/><usingself state="inline"/></bygroups></rule>
<rule pattern="^(\s*&gt;\s)(.+\n)"><bygroups><token type="Keyword"/><token type="GenericEmph"/></bygroups></rule>
<rule pattern="^(```\n)([\w\W]*?)(^```$)">
<bygroups>
<token type="LiteralStringBacktick"/>
<token type="Text"/>
<token type="LiteralStringBacktick"/>
</bygroups>
</rule>
<rule pattern="^(```)(\w+)(\n)([\w\W]*?)(^```$)">
<bygroups>
<token type="LiteralStringBacktick"/>
<token type="NameLabel"/>
<token type="TextWhitespace"/>
<UsingByGroup lexer="2" content="4"/>
<token type="LiteralStringBacktick"/>
</bygroups>
</rule>
<rule><include state="inline"/></rule>
</state>
<state name="inline">
<rule pattern="\\."><token type="Text"/></rule>
<rule pattern="([^`]?)(`[^`\n]+`)"><bygroups><token type="Text"/><token type="LiteralStringBacktick"/></bygroups></rule>
<rule pattern="([^\*]?)(\*\*[^* \n][^*\n]*\*\*)"><bygroups><token type="Text"/><token type="GenericStrong"/></bygroups></rule>
<rule pattern="([^_]?)(__[^_ \n][^_\n]*__)"><bygroups><token type="Text"/><token type="GenericStrong"/></bygroups></rule>
<rule pattern="([^\*]?)(\*[^* \n][^*\n]*\*)"><bygroups><token type="Text"/><token type="GenericEmph"/></bygroups></rule>
<rule pattern="([^_]?)(_[^_ \n][^_\n]*_)"><bygroups><token type="Text"/><token type="GenericEmph"/></bygroups></rule>
<rule pattern="([^~]?)(~~[^~ \n][^~\n]*~~)"><bygroups><token type="Text"/><token type="GenericDeleted"/></bygroups></rule>
<rule pattern="[@#][\w/:]+"><token type="NameEntity"/></rule>
<rule pattern="(!?\[)([^]]+)(\])(\()([^)]+)(\))"><bygroups><token type="Text"/><token type="NameTag"/><token type="Text"/><token type="Text"/><token type="NameAttribute"/><token type="Text"/></bygroups></rule>
<rule pattern="(\[)([^]]+)(\])(\[)([^]]*)(\])"><bygroups><token type="Text"/><token type="NameTag"/><token type="Text"/><token type="Text"/><token type="NameLabel"/><token type="Text"/></bygroups></rule>
<rule pattern="^(\s*\[)([^]]*)(\]:\s*)(.+)"><bygroups><token type="Text"/><token type="NameLabel"/><token type="Text"/><token type="NameAttribute"/></bygroups></rule>
<rule pattern="[^\\\s]+"><token type="Text"/></rule>
<rule pattern="."><token type="Text"/></rule>
</state>
</rules>
</lexer>

34
lexers/moinwiki.xml Normal file
View File

@ -0,0 +1,34 @@
<lexer>
<config>
<name>MoinMoin/Trac Wiki markup</name>
<alias>trac-wiki</alias>
<alias>moin</alias>
<mime_type>text/x-trac-wiki</mime_type>
<case_insensitive>true</case_insensitive>
</config>
<rules>
<state name="root">
<rule pattern="^#.*$"><token type="Comment"/></rule>
<rule pattern="(!)(\S+)"><bygroups><token type="Keyword"/><token type="Text"/></bygroups></rule>
<rule pattern="^(=+)([^=]+)(=+)(\s*#.+)?$"><bygroups><token type="GenericHeading"/><usingself state="root"/><token type="GenericHeading"/><token type="LiteralString"/></bygroups></rule>
<rule pattern="(\{\{\{)(\n#!.+)?"><bygroups><token type="NameBuiltin"/><token type="NameNamespace"/></bygroups><push state="codeblock"/></rule>
<rule pattern="(\&#x27;\&#x27;\&#x27;?|\|\||`|__|~~|\^|,,|::)"><token type="Comment"/></rule>
<rule pattern="^( +)([.*-])( )"><bygroups><token type="Text"/><token type="NameBuiltin"/><token type="Text"/></bygroups></rule>
<rule pattern="^( +)([a-z]{1,5}\.)( )"><bygroups><token type="Text"/><token type="NameBuiltin"/><token type="Text"/></bygroups></rule>
<rule pattern="\[\[\w+.*?\]\]"><token type="Keyword"/></rule>
<rule pattern="(\[[^\s\]]+)(\s+[^\]]+?)?(\])"><bygroups><token type="Keyword"/><token type="LiteralString"/><token type="Keyword"/></bygroups></rule>
<rule pattern="^----+$"><token type="Keyword"/></rule>
<rule pattern="[^\n\&#x27;\[{!_~^,|]+"><token type="Text"/></rule>
<rule pattern="\n"><token type="Text"/></rule>
<rule pattern="."><token type="Text"/></rule>
</state>
<state name="codeblock">
<rule pattern="\}\}\}"><token type="NameBuiltin"/><pop depth="1"/></rule>
<rule pattern="\{\{\{"><token type="Text"/><push/></rule>
<rule pattern="[^{}]+"><token type="CommentPreproc"/></rule>
<rule pattern="."><token type="CommentPreproc"/></rule>
</state>
</rules>
</lexer>

View File

@ -40,15 +40,18 @@ for fname in glob.glob("lexers/*.xml"):
with open("src/constants/lexers.cr", "w") as f:
f.write("module Tartrazine\n")
f.write(" LEXERS_BY_NAME = {\n")
for k, v in lexer_by_name.items():
for k in sorted(lexer_by_name.keys()):
v = lexer_by_name[k]
f.write(f'"{k}" => "{v}", \n')
f.write("}\n")
f.write(" LEXERS_BY_MIMETYPE = {\n")
for k, v in lexer_by_mimetype.items():
for k in sorted(lexer_by_mimetype.keys()):
v = lexer_by_mimetype[k]
f.write(f'"{k}" => "{v}", \n')
f.write("}\n")
f.write(" LEXERS_BY_FILENAME = {\n")
for k, v in lexer_by_filename.items():
for k in sorted(lexer_by_filename.keys()):
v = lexer_by_filename[k]
f.write(f'"{k}" => {str(list(v)).replace("'", "\"")}, \n')
f.write("}\n")
f.write("end\n")

View File

@ -72,8 +72,7 @@ end
# Helper that creates lexer and tokenizes
def tokenize(lexer_name, text)
lexer = Tartrazine.lexer(lexer_name)
tokenizer = Tartrazine::Tokenizer.new(lexer, text)
tokenizer = Tartrazine.lexer(lexer_name).tokenizer(text)
Tartrazine::Lexer.collapse_tokens(tokenizer.to_a)
end

View File

@ -16,13 +16,16 @@ module Tartrazine
Push
Token
Using
Usingbygroup
Usingself
end
struct Action
property actions : Array(Action) = [] of Action
@content_index : Int32 = 0
@depth : Int32 = 0
@lexer_index : Int32 = 0
@lexer_name : String = ""
@states : Array(String) = [] of String
@states_to_push : Array(String) = [] of String
@ -62,6 +65,9 @@ module Tartrazine
@states = xml.attributes.select { |attrib|
attrib.name == "state"
}.map &.content
when ActionType::Usingbygroup
@lexer_index = xml["lexer"].to_i
@content_index = xml["content"].to_i
end
end
@ -115,15 +121,13 @@ module Tartrazine
when ActionType::Using
# Shunt to another lexer entirely
return [] of Token if match.empty?
Tokenizer.new(
Tartrazine.lexer(@lexer_name),
Tartrazine.lexer(@lexer_name).tokenizer(
String.new(match[match_group].value),
secondary: true).to_a
when ActionType::Usingself
# Shunt to another copy of this lexer
return [] of Token if match.empty?
Tokenizer.new(
tokenizer.lexer,
tokenizer.lexer.tokenizer(
String.new(match[match_group].value),
secondary: true).to_a
when ActionType::Combined
@ -136,6 +140,12 @@ module Tartrazine
tokenizer.lexer.states[new_state.name] = new_state
tokenizer.state_stack << new_state.name
[] of Token
when ActionType::Usingbygroup
# Shunt to content-specified lexer
return [] of Token if match.empty?
Tartrazine.lexer(String.new(match[@lexer_index].value)).tokenizer(
String.new(match[@content_index].value),
secondary: true).to_a
else
raise Exception.new("Unknown action type: #{@type}")
end

File diff suppressed because it is too large Load Diff

View File

@ -17,8 +17,8 @@ module Tartrazine
outp.to_s
end
def format(text : String, lexer : Lexer, outp : IO) : Nil
tokenizer = Tokenizer.new(lexer, text)
def format(text : String, lexer : BaseLexer, outp : IO) : Nil
tokenizer = lexer.tokenizer(text)
i = 0
outp << line_label(i) if line_numbers?
tokenizer.each do |token|

View File

@ -40,7 +40,7 @@ module Tartrazine
outp.to_s
end
def format(text : String, lexer : Lexer, io : IO) : Nil
def format(text : String, lexer : BaseLexer, io : IO) : Nil
pre, post = wrap_standalone
io << pre if standalone?
format_text(text, lexer, io)
@ -64,8 +64,8 @@ module Tartrazine
"<span #{line_id} #{line_class} style=\"user-select: none;\">#{line_label} </span>"
end
def format_text(text : String, lexer : Lexer, outp : IO)
tokenizer = Tokenizer.new(lexer, text)
def format_text(text : String, lexer : BaseLexer, outp : IO)
tokenizer = lexer.tokenizer(text)
i = 0
if surrounding_pre?
pre_style = wrap_long_lines? ? "style=\"white-space: pre-wrap; word-break: break-word;\"" : ""

View File

@ -4,14 +4,14 @@ module Tartrazine
class Json < Formatter
property name = "json"
def format(text : String, lexer : Lexer) : String
def format(text : String, lexer : BaseLexer) : String
outp = String::Builder.new("")
format(text, lexer, outp)
outp.to_s
end
def format(text : String, lexer : Lexer, io : IO) : Nil
tokenizer = Tokenizer.new(lexer, text)
def format(text : String, lexer : BaseLexer, io : IO) : Nil
tokenizer = lexer.tokenizer(text)
io << Tartrazine::Lexer.collapse_tokens(tokenizer.to_a).to_json
end
end

View File

@ -9,29 +9,46 @@ module Tartrazine
# Get the lexer object for a language name
# FIXME: support mimetypes
def self.lexer(name : String? = nil, filename : String? = nil) : Lexer
if name.nil? && filename.nil?
lexer_file_name = LEXERS_BY_NAME["plaintext"]
elsif name && name != "autodetect"
lexer_file_name = LEXERS_BY_NAME[name.downcase]
else
# Guess by filename
candidates = Set(String).new
LEXERS_BY_FILENAME.each do |k, v|
candidates += v.to_set if File.match?(k, File.basename(filename.to_s))
end
case candidates.size
when 0
lexer_file_name = LEXERS_BY_NAME["plaintext"]
when 1
lexer_file_name = candidates.first
else
raise Exception.new("Multiple lexers match the filename: #{candidates.to_a.join(", ")}")
end
end
def self.lexer(name : String? = nil, filename : String? = nil) : BaseLexer
return lexer_by_name(name) if name && name != "autodetect"
return lexer_by_filename(filename) if filename
Lexer.from_xml(LexerFiles.get("/#{LEXERS_BY_NAME["plaintext"]}.xml").gets_to_end)
end
private def self.lexer_by_name(name : String) : BaseLexer
lexer_file_name = LEXERS_BY_NAME.fetch(name.downcase, nil)
return create_delegating_lexer(name) if lexer_file_name.nil? && name.includes? "+"
raise Exception.new("Unknown lexer: #{name}") if lexer_file_name.nil?
Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
end
private def self.lexer_by_filename(filename : String) : BaseLexer
candidates = Set(String).new
LEXERS_BY_FILENAME.each do |k, v|
candidates += v.to_set if File.match?(k, File.basename(filename))
end
case candidates.size
when 0
lexer_file_name = LEXERS_BY_NAME["plaintext"]
when 1
lexer_file_name = candidates.first
else
raise Exception.new("Multiple lexers match the filename: #{candidates.to_a.join(", ")}")
end
Lexer.from_xml(LexerFiles.get("/#{lexer_file_name}.xml").gets_to_end)
end
private def self.create_delegating_lexer(name : String) : BaseLexer
language, root = name.split("+", 2)
language_lexer = lexer(language)
root_lexer = lexer(root)
DelegatingLexer.new(language_lexer, root_lexer)
end
# Return a list of all lexers
def self.lexers : Array(String)
LEXERS_BY_NAME.keys.sort!
@ -40,15 +57,18 @@ module Tartrazine
# A token, the output of the tokenizer
alias Token = NamedTuple(type: String, value: String)
struct Tokenizer
abstract class BaseTokenizer
end
class Tokenizer < BaseTokenizer
include Iterator(Token)
property lexer : Lexer
property lexer : BaseLexer
property text : Bytes
property pos : Int32 = 0
@dq = Deque(Token).new
property state_stack = ["root"]
def initialize(@lexer : Lexer, text : String, secondary = false)
def initialize(@lexer : BaseLexer, text : String, secondary = false)
# Respect the `ensure_nl` config option
if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
text += "\n"
@ -106,13 +126,7 @@ module Tartrazine
end
end
# This implements a lexer for Pygments RegexLexers as expressed
# in Chroma's XML serialization.
#
# For explanations on what actions and states do
# the Pygments documentation is a good place to start.
# https://pygments.org/docs/lexerdevelopment/
struct Lexer
abstract class BaseLexer
property config = {
name: "",
priority: 0.0,
@ -123,6 +137,18 @@ module Tartrazine
}
property states = {} of String => State
def tokenizer(text : String, secondary = false) : BaseTokenizer
Tokenizer.new(self, text, secondary)
end
end
# This implements a lexer for Pygments RegexLexers as expressed
# in Chroma's XML serialization.
#
# For explanations on what actions and states do
# the Pygments documentation is a good place to start.
# https://pygments.org/docs/lexerdevelopment/
class Lexer < BaseLexer
# Collapse consecutive tokens of the same type for easier comparison
# and smaller output
def self.collapse_tokens(tokens : Array(Tartrazine::Token)) : Array(Tartrazine::Token)
@ -204,6 +230,60 @@ module Tartrazine
end
end
# A lexer that takes two lexers as arguments. A root lexer
# and a language lexer. Everything is scalled using the
# language lexer, afterwards all `Other` tokens are lexed
# using the root lexer.
#
# This is useful for things like template languages, where
# you have Jinja + HTML or Jinja + CSS and so on.
class DelegatingLexer < BaseLexer
property language_lexer : BaseLexer
property root_lexer : BaseLexer
def initialize(@language_lexer : BaseLexer, @root_lexer : BaseLexer)
end
def tokenizer(text : String, secondary = false) : DelegatingTokenizer
DelegatingTokenizer.new(self, text, secondary)
end
end
# This Tokenizer works with a DelegatingLexer. It first tokenizes
# using the language lexer, and "Other" tokens are tokenized using
# the root lexer.
class DelegatingTokenizer < BaseTokenizer
include Iterator(Token)
@dq = Deque(Token).new
@language_tokenizer : BaseTokenizer
def initialize(@lexer : DelegatingLexer, text : String, secondary = false)
# Respect the `ensure_nl` config option
if text.size > 0 && text[-1] != '\n' && @lexer.config[:ensure_nl] && !secondary
text += "\n"
end
@language_tokenizer = @lexer.language_lexer.tokenizer(text, true)
end
def next : Iterator::Stop | Token
if @dq.size > 0
return @dq.shift
end
token = @language_tokenizer.next
if token.is_a? Iterator::Stop
return stop
elsif token.as(Token).[:type] == "Other"
root_tokenizer = @lexer.root_lexer.tokenizer(token.as(Token).[:value], true)
root_tokenizer.each do |root_token|
@dq << root_token
end
else
@dq << token.as(Token)
end
self.next
end
end
# A Lexer state. A state has a name and a list of rules.
# The state machine has a state stack containing references
# to states to decide which rules to apply.