mirror of
https://github.com/alecthomas/chroma.git
synced 2025-11-23 22:24:39 +02:00
Add lexer for WebAssembly Text Format (#1161)
Adds a lexer for WebAssembly's text format based on [pygments' WatLexer](https://pygments.org/docs/lexers/#pygments.lexers.webassembly.WatLexer). Test data is the output of wasm2wat from a binary compiled from the following code using clang 21.1.2 and the wasm32-unknown-wasi target: ```c #include <stdio.h> int main() { puts("Hello World!"); return 0; } ``` Closes #754
This commit is contained in:
Marie
GitHub
149
lexers/embedded/wat.xml
Normal file
149
lexers/embedded/wat.xml
Normal file
@@ -0,0 +1,149 @@
|
||||
<lexer>
|
||||
<config>
|
||||
<name>WebAssembly Text Format</name>
|
||||
<alias>wast</alias>
|
||||
<alias>wat</alias>
|
||||
<filename>*.wat</filename>
|
||||
<filename>*.wast</filename>
|
||||
</config>
|
||||
<rules>
|
||||
<state name="root">
|
||||
<rule pattern="(module|import|func|funcref|start|param|local|type|result|export|memory|global|mut|data|table|elem|if|then|else|end|block|loop)(?=[^a-z_\.])">
|
||||
<token type="Keyword"/>
|
||||
</rule>
|
||||
<rule pattern="(unreachable|nop|block|loop|if|else|end|br(?:_if|_table)?|return|call(?:_indirect)?|drop|select|local\.get|local\.set|local\.tee|global\.get|global\.set|i32\.load(?:(?:8|16)_(?:u|s))?|i64\.load(?:(?:8|16|32)_(?:u|s))?|f32\.load|f64\.load|i32\.store(?:8|16)?|i64\.store(:?8|16|32)?|f32\.store|f64\.store|memory\.size|memory\.grow|memory\.fill|memory\.copy|memory\.init|i32\.const|i64\.const|f32\.const|f64\.const|i32\.eqz|i32\.eq|i32\.ne|i32\.lt_s|i32\.lt_u|i32\.gt_s|i32\.gt_u|i32\.le_s|i32\.le_u|i32\.ge_s|i32\.ge_u|i64\.eqz|i64\.eq|i64\.ne|i64\.lt_s|i64\.lt_u|i64\.gt_s|i64\.gt_u|i64\.le_s|i64\.le_u|i64\.ge_s|i64\.ge_u|f32\.eq|f32\.neg?|f32\.lt|f32\.gt|f32\.le|f32\.ge|f64\.eq|f64\.neg?|f64\.lt|f64\.gt|f64\.le|f64\.ge|i32\.clz|i32\.ctz|i32\.popcnt|i32\.add|i32\.sub|i32\.mul|i32\.div_s|i32\.div_u|i32\.rem_s|i32\.rem_u|i32\.and|i32\.or|i32\.xor|i32\.shl|i32\.shr_s|i32\.shr_u|i32\.rotl|i32\.rotr|i64\.clz|i64\.ctz|i64\.popcnt|i64\.add|i64\.sub|i64\.mul|i64\.div_s|i64\.div_u|i64\.rem_s|i64\.rem_u|i64\.and|i64\.or|i64\.xor|i64\.shl|i64\.shr_s|i64\.shr_u|i64\.rotl|i64\.rotr|f32\.abs|f32\.ceil|f32\.floor|f32\.trunc|f32\.nearest|f32\.sqrt|f32\.add|f32\.sub|f32\.mul|f32\.div|f32\.min|f32\.max|f32\.copysign|f64\.abs|f64\.ceil|f64\.floor|f64\.trunc|f64\.nearest|f64\.sqrt|f64\.add|f64\.sub|f64\.mul|f64\.div|f64\.min|f64\.max|f64\.copysign|i32\.wrap_i64|i32\.trunc_f32_s|i32\.trunc_f32_u|i32\.trunc_f64_s|i32\.trunc_f64_u|i64\.extend(?:(?:8|16|32)_s|_i(?:32|64)_(?:u|s))|i32\.extend(?:8|16)_s|(?:i32|i64)\.trunc(?:_sat)?_f(?:32|64)_(?:s|u)|f32\.convert_i32_s|f32\.convert_i32_u|f32\.convert_i64_s|f32\.convert_i64_u|f32\.demote_f64|f64\.convert_i32_s|f64\.convert_i32_u|f64\.convert_i64_s|f64\.convert_i64_u|f64\.promote_f32|i32\.reinterpret_f32|i64\.reinterpret_f64|f32\.reinterpret_i32|f64\.reinterpret_i64)">
|
||||
<token type="NameBuiltin"/>
|
||||
<push state="arguments"/>
|
||||
</rule>
|
||||
<rule pattern="(i32|i64|f32|f64)">
|
||||
<token type="KeywordType"/>
|
||||
</rule>
|
||||
<rule pattern="\$[A-Za-z0-9!#$%&\'*+./:<=>?@\\^_`|~-]+">
|
||||
<token type="NameVariable"/>
|
||||
</rule>
|
||||
<rule pattern=";;.*?$">
|
||||
<token type="CommentSingle"/>
|
||||
</rule>
|
||||
<rule pattern="\(;">
|
||||
<token type="CommentMultiline"/>
|
||||
<push state="nesting_comment"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?0x[\dA-Fa-f](_?[\dA-Fa-f])*(.([\dA-Fa-f](_?[\dA-Fa-f])*)?)?([pP][+-]?[\dA-Fa-f](_?[\dA-Fa-f])*)?">
|
||||
<token type="LiteralNumberFloat"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?\d.\d(_?\d)*[eE][+-]?\d(_?\d)*">
|
||||
<token type="LiteralNumberFloat"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?\d.\d(_?\d)*">
|
||||
<token type="LiteralNumberFloat"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?\d.[eE][+-]?\d(_?\d)*">
|
||||
<token type="LiteralNumberFloat"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?(inf|nan:0x[\dA-Fa-f](_?[\dA-Fa-f])*|nan)">
|
||||
<token type="LiteralNumberFloat"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?0x[\dA-Fa-f](_?[\dA-Fa-f])*">
|
||||
<token type="LiteralNumberHex"/>
|
||||
</rule>
|
||||
<rule pattern="[+-]?\d(_?\d)*">
|
||||
<token type="LiteralNumberInteger"/>
|
||||
</rule>
|
||||
<rule pattern="[\(\)]">
|
||||
<token type="Punctuation"/>
|
||||
</rule>
|
||||
<rule pattern=""">
|
||||
<token type="LiteralStringDouble"/>
|
||||
<push state="string"/>
|
||||
</rule>
|
||||
<rule pattern="\s+">
|
||||
<token type="Text"/>
|
||||
</rule>
|
||||
</state>
|
||||
<state name="nesting_comment">
|
||||
<rule pattern="\(;">
|
||||
<token type="CommentMultiline"/>
|
||||
<push/>
|
||||
</rule>
|
||||
<rule pattern=";\)">
|
||||
<token type="CommentMultiline"/>
|
||||
<pop depth="1"/>
|
||||
</rule>
|
||||
<rule pattern="[^;(]+">
|
||||
<token type="CommentMultiline"/>
|
||||
</rule>
|
||||
<rule pattern="[;(]">
|
||||
<token type="CommentMultiline"/>
|
||||
</rule>
|
||||
</state>
|
||||
<state name="string">
|
||||
<rule pattern="\\[\dA-Fa-f][\dA-Fa-f]">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\t">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\n">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\r">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\"">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\'">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\u\{[\dA-Fa-f](_?[\dA-Fa-f])*\}">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern="\\\\">
|
||||
<token type="LiteralStringEscape"/>
|
||||
</rule>
|
||||
<rule pattern=""">
|
||||
<token type="LiteralStringDouble"/>
|
||||
<pop depth="1"/>
|
||||
</rule>
|
||||
<rule pattern="[^"\\]+">
|
||||
<token type="LiteralStringDouble"/>
|
||||
</rule>
|
||||
</state>
|
||||
<state name="arguments">
|
||||
<rule pattern="\s+">
|
||||
<token type="Text"/>
|
||||
</rule>
|
||||
<rule pattern="(offset)(=)(0x[\dA-Fa-f](?:_?[\dA-Fa-f])*)">
|
||||
<bygroups>
|
||||
<token type="Keyword"/>
|
||||
<token type="Operator"/>
|
||||
<token type="LiteralNumberHex"/>
|
||||
</bygroups>
|
||||
</rule>
|
||||
<rule pattern="(offset)(=)(\d(?:_?\d)*)">
|
||||
<bygroups>
|
||||
<token type="Keyword"/>
|
||||
<token type="Operator"/>
|
||||
<token type="LiteralNumberInteger"/>
|
||||
</bygroups>
|
||||
</rule>
|
||||
<rule pattern="(align)(=)(0x[\dA-Fa-f](?:_?[\dA-Fa-f])*)">
|
||||
<bygroups>
|
||||
<token type="Keyword"/>
|
||||
<token type="Operator"/>
|
||||
<token type="LiteralNumberHex"/>
|
||||
</bygroups>
|
||||
</rule>
|
||||
<rule pattern="(align)(=)(\d(?:_?\d)*)">
|
||||
<bygroups>
|
||||
<token type="Keyword"/>
|
||||
<token type="Operator"/>
|
||||
<token type="LiteralNumberInteger"/>
|
||||
</bygroups>
|
||||
</rule>
|
||||
<rule>
|
||||
<pop depth="1"/>
|
||||
</rule>
|
||||
</state>
|
||||
</rules>
|
||||
</lexer>
|
||||
1033
lexers/testdata/wat.actual
vendored
Normal file
1033
lexers/testdata/wat.actual
vendored
Normal file
File diff suppressed because it is too large
Load Diff
4895
lexers/testdata/wat.expected
vendored
Normal file
4895
lexers/testdata/wat.expected
vendored
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user