dualfroz
dc8e36e79b
the typescript lexer only had three number rules, so literals like 0b1010, 0o17, 0XFF, 1e5 and 1_000 were split into a number and a name. this ports the javascript number rules, with the float rule also keeping a fraction and an exponent together (1.5e10) as before, and adds a testdata/typescript/number_literals fixture.
309 lines
9.1 KiB
XML
309 lines
9.1 KiB
XML
<lexer>
|
|
<config>
|
|
<name>TypeScript</name>
|
|
<alias>ts</alias>
|
|
<alias>tsx</alias>
|
|
<alias>typescript</alias>
|
|
<filename>*.ts</filename>
|
|
<filename>*.tsx</filename>
|
|
<filename>*.mts</filename>
|
|
<filename>*.cts</filename>
|
|
<mime_type>text/x-typescript</mime_type>
|
|
<dot_all>true</dot_all>
|
|
<ensure_nl>true</ensure_nl>
|
|
</config>
|
|
<rules>
|
|
<state name="expression">
|
|
<rule pattern="{">
|
|
<token type="Punctuation" />
|
|
<push />
|
|
</rule>
|
|
<rule pattern="}">
|
|
<token type="Punctuation" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule>
|
|
<include state="root" />
|
|
</rule>
|
|
</state>
|
|
<state name="jsx">
|
|
<rule pattern="(<)(/?)(>)">
|
|
<bygroups>
|
|
<token type="Punctuation" />
|
|
<token type="Punctuation" />
|
|
<token type="Punctuation" />
|
|
</bygroups>
|
|
</rule>
|
|
<rule pattern="(<)([\w\.]+)">
|
|
<bygroups>
|
|
<token type="Punctuation" />
|
|
<token type="NameTag" />
|
|
</bygroups>
|
|
<push state="tag" />
|
|
</rule>
|
|
<rule pattern="(<)(/)([\w\.]*)(>)">
|
|
<bygroups>
|
|
<token type="Punctuation" />
|
|
<token type="Punctuation" />
|
|
<token type="NameTag" />
|
|
<token type="Punctuation" />
|
|
</bygroups>
|
|
</rule>
|
|
</state>
|
|
<state name="tag">
|
|
<rule>
|
|
<include state="jsx" />
|
|
</rule>
|
|
<rule pattern=",">
|
|
<token type="Punctuation" />
|
|
</rule>
|
|
<rule pattern=""(\\\\|\\"|[^"])*"">
|
|
<token type="LiteralStringDouble" />
|
|
</rule>
|
|
<rule pattern="'(\\\\|\\'|[^'])*'">
|
|
<token type="LiteralStringSingle" />
|
|
</rule>
|
|
<rule pattern="`">
|
|
<token type="LiteralStringBacktick" />
|
|
<push state="interp" />
|
|
</rule>
|
|
<rule>
|
|
<include state="commentsandwhitespace" />
|
|
</rule>
|
|
<rule pattern="\s+">
|
|
<token type="Text" />
|
|
</rule>
|
|
<rule pattern="([\w-]+\s*)(=)(\s*)">
|
|
<bygroups>
|
|
<token type="NameAttribute" />
|
|
<token type="Operator" />
|
|
<token type="Text" />
|
|
</bygroups>
|
|
<push state="attr" />
|
|
</rule>
|
|
<rule pattern="[{}]+">
|
|
<token type="Punctuation" />
|
|
</rule>
|
|
<rule pattern="[\w\.]+">
|
|
<token type="NameAttribute" />
|
|
</rule>
|
|
<rule pattern="(/?)(\s*)(>)">
|
|
<bygroups>
|
|
<token type="Punctuation" />
|
|
<token type="Text" />
|
|
<token type="Punctuation" />
|
|
</bygroups>
|
|
<pop depth="1" />
|
|
</rule>
|
|
</state>
|
|
<state name="comment">
|
|
<rule pattern="[^-]+">
|
|
<token type="Comment" />
|
|
</rule>
|
|
<rule pattern="-->">
|
|
<token type="Comment" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule pattern="-">
|
|
<token type="Comment" />
|
|
</rule>
|
|
</state>
|
|
<state name="commentsandwhitespace">
|
|
<rule pattern="\s+">
|
|
<token type="Text" />
|
|
</rule>
|
|
<rule pattern="<!--">
|
|
<token type="Comment" />
|
|
<push state="comment" />
|
|
</rule>
|
|
<rule pattern="//.*?\n">
|
|
<token type="CommentSingle" />
|
|
</rule>
|
|
<rule pattern="/\*.*?\*/">
|
|
<token type="CommentMultiline" />
|
|
</rule>
|
|
</state>
|
|
<state name="badregex">
|
|
<rule pattern="\n">
|
|
<token type="Text" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
</state>
|
|
<state name="interp">
|
|
<rule pattern="`">
|
|
<token type="LiteralStringBacktick" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule pattern="\\\\">
|
|
<token type="LiteralStringBacktick" />
|
|
</rule>
|
|
<rule pattern="\\`">
|
|
<token type="LiteralStringBacktick" />
|
|
</rule>
|
|
<rule pattern="\$\{">
|
|
<token type="LiteralStringInterpol" />
|
|
<push state="interp-inside" />
|
|
</rule>
|
|
<rule pattern="\$">
|
|
<token type="LiteralStringBacktick" />
|
|
</rule>
|
|
<rule pattern="[^`\\$]+">
|
|
<token type="LiteralStringBacktick" />
|
|
</rule>
|
|
</state>
|
|
<state name="attr">
|
|
<rule pattern="{">
|
|
<token type="Punctuation" />
|
|
<push state="expression" />
|
|
</rule>
|
|
<rule pattern="".*?"">
|
|
<token type="LiteralString" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule pattern="'.*?'">
|
|
<token type="LiteralString" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule>
|
|
<pop depth="1" />
|
|
</rule>
|
|
</state>
|
|
<state name="interp-inside">
|
|
<rule pattern="\}">
|
|
<token type="LiteralStringInterpol" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule>
|
|
<include state="root" />
|
|
</rule>
|
|
</state>
|
|
<state name="slashstartsregex">
|
|
<rule>
|
|
<include state="commentsandwhitespace" />
|
|
</rule>
|
|
<rule pattern="/(\\.|[^[/\\\n]|\[(\\.|[^\]\\\n])*])+/([gim]+\b|\B)">
|
|
<token type="LiteralStringRegex" />
|
|
<pop depth="1" />
|
|
</rule>
|
|
<rule pattern="(?=/)">
|
|
<token type="Text" />
|
|
<push state="badregex" />
|
|
</rule>
|
|
<rule>
|
|
<pop depth="1" />
|
|
</rule>
|
|
</state>
|
|
<state name="root">
|
|
<rule>
|
|
<include state="jsx" />
|
|
</rule>
|
|
<rule pattern="^(?=\s|/|<!--)">
|
|
<token type="Text" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule>
|
|
<include state="commentsandwhitespace" />
|
|
</rule>
|
|
<rule pattern="\+\+|--|~|&&|\?|:|\|\||\\(?=\n)|(<<|>>>?|==?|!=?|[-<>+*%&|^/])=?">
|
|
<token type="Operator" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="[{(\[;,]">
|
|
<token type="Punctuation" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="[})\].]">
|
|
<token type="Punctuation" />
|
|
</rule>
|
|
<rule
|
|
pattern="(for|in|of|while|do|break|return|yield|continue|switch|case|default|if|else|throw|try|catch|finally|new|delete|typeof|instanceof|keyof|asserts|is|infer|await|void|this)\b"
|
|
>
|
|
<token type="Keyword" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="(var|let|with|function)\b">
|
|
<token type="KeywordDeclaration" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule
|
|
pattern="(abstract|async|boolean|class|const|debugger|enum|export|extends|from|get|global|goto|implements|import|interface|namespace|package|private|protected|public|readonly|require|set|static|super|type|using)\b"
|
|
>
|
|
<token type="KeywordReserved" />
|
|
</rule>
|
|
<rule pattern="(true|false|null|NaN|Infinity|undefined)\b">
|
|
<token type="KeywordConstant" />
|
|
</rule>
|
|
<rule
|
|
pattern="(Array|Boolean|Date|Error|Function|Math|Number|Object|Packages|RegExp|String|decodeURI|decodeURIComponent|encodeURI|encodeURIComponent|eval|isFinite|isNaN|parseFloat|parseInt|document|this|window)\b"
|
|
>
|
|
<token type="NameBuiltin" />
|
|
</rule>
|
|
<rule pattern="\b(module)(\s+)("[\w\./@]+")(\s+)">
|
|
<bygroups>
|
|
<token type="KeywordReserved" />
|
|
<token type="Text" />
|
|
<token type="NameOther" />
|
|
<token type="Text" />
|
|
</bygroups>
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="\b(string|bool|number|any|never|object|symbol|unique|unknown|bigint)\b">
|
|
<token type="KeywordType" />
|
|
</rule>
|
|
<rule pattern="\b(constructor|declare|interface|as)\b">
|
|
<token type="KeywordReserved" />
|
|
</rule>
|
|
<rule pattern="(super)(\s*)(\([\w,?.$\s]+\s*\))">
|
|
<bygroups>
|
|
<token type="KeywordReserved" />
|
|
<token type="TextWhitespace" />
|
|
<token type="Text" />
|
|
</bygroups>
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="([a-zA-Z_?.$][\w?.$]*)\(\) \{">
|
|
<token type="NameOther" />
|
|
<push state="slashstartsregex" />
|
|
</rule>
|
|
<rule pattern="([\w?.$][\w?.$]*)(\s*:\s*)([\w?.$][\w?.$]*)">
|
|
<bygroups>
|
|
<token type="NameOther" />
|
|
<token type="Text" />
|
|
<token type="KeywordType" />
|
|
</bygroups>
|
|
</rule>
|
|
<rule pattern="[$a-zA-Z_]\w*">
|
|
<token type="NameOther" />
|
|
</rule>
|
|
<rule pattern="\d+(\.\d*([eE][+\-]?\d+)?|[eE][+\-]?\d+)">
|
|
<token type="LiteralNumberFloat" />
|
|
</rule>
|
|
<rule pattern="0[bB][01]+">
|
|
<token type="LiteralNumberBin" />
|
|
</rule>
|
|
<rule pattern="0[oO][0-7]+">
|
|
<token type="LiteralNumberOct" />
|
|
</rule>
|
|
<rule pattern="0[xX][0-9a-fA-F]+">
|
|
<token type="LiteralNumberHex" />
|
|
</rule>
|
|
<rule pattern="[0-9][0-9_]*">
|
|
<token type="LiteralNumberInteger" />
|
|
</rule>
|
|
<rule pattern=""(\\\\|\\"|[^"])*"">
|
|
<token type="LiteralStringDouble" />
|
|
</rule>
|
|
<rule pattern="'(\\\\|\\'|[^'])*'">
|
|
<token type="LiteralStringSingle" />
|
|
</rule>
|
|
<rule pattern="`">
|
|
<token type="LiteralStringBacktick" />
|
|
<push state="interp" />
|
|
</rule>
|
|
<rule pattern="@\w+">
|
|
<token type="KeywordDeclaration" />
|
|
</rule>
|
|
</state>
|
|
</rules>
|
|
</lexer>
|