From 65c601bb6fdb28e0ed9a1d5b2c6f48cb03901d0d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?KOBAYASHI=20Y=C5=AB?= <kb10uy@kb10uy.org>
Date: Thu, 6 Oct 2022 09:12:32 +0900
Subject: [PATCH] Add HLSL language support (#675)

---
 README.md                     |   2 +-
 lexers/embedded/hlsl.xml      | 107 ++++++++++++++++++++++++++++++++++
 lexers/testdata/hlsl.actual   |   3 +
 lexers/testdata/hlsl.expected |  40 +++++++++++++
 4 files changed, 151 insertions(+), 1 deletion(-)
 create mode 100644 lexers/embedded/hlsl.xml
 create mode 100644 lexers/testdata/hlsl.actual
 create mode 100644 lexers/testdata/hlsl.expected

diff --git a/README.md b/README.md
index ffaccb653..88b9e285c 100644
--- a/README.md
+++ b/README.md
@@ -43,7 +43,7 @@ D | D, Dart, Diff, Django/Jinja, Docker, DTD, Dylan
 E | EBNF, Elixir, Elm, EmacsLisp, Erlang
 F | Factor, Fish, Forth, Fortran, FSharp
 G | GAS, GDScript, Genshi, Genshi HTML, Genshi Text, Gherkin, GLSL, Gnuplot, Go, Go HTML Template, Go Text Template, GraphQL, Groff, Groovy
-H | Handlebars, Haskell, Haxe, HCL, Hexdump, HLB, HTML, HTTP, Hy
+H | Handlebars, Haskell, Haxe, HCL, Hexdump, HLB, HLSL, HTML, HTTP, Hy
 I | Idris, Igor, INI, Io
 J | J, Java, JavaScript, JSON, Julia, Jungle
 K | Kotlin
diff --git a/lexers/embedded/hlsl.xml b/lexers/embedded/hlsl.xml
new file mode 100644
index 000000000..774f53cf2
--- /dev/null
+++ b/lexers/embedded/hlsl.xml
@@ -0,0 +1,107 @@
+<lexer>
+  <config>
+    <name>HLSL</name>
+    <alias>hlsl</alias>
+    <filename>*.hlsl</filename>
+    <filename>*.hlsli</filename>
+    <mime_type>text/x-hlsl</mime_type>
+  </config>
+  <rules>
+    <state name="root">
+      <rule pattern="^#.*$">
+        <token type="CommentPreproc"/>
+      </rule>
+      <rule pattern="//.*$">
+        <token type="CommentSingle"/>
+      </rule>
+      <rule pattern="/(\\\n)?[*](.|\n)*?[*](\\\n)?/">
+        <token type="CommentMultiline"/>
+      </rule>
+      <rule pattern="\+|-|~|!=?|\*|/|%|&lt;&lt;|&gt;&gt;|&lt;=?|&gt;=?|==?|&amp;&amp;?|\^|\|\|?">
+        <token type="Operator"/>
+      </rule>
+      <rule pattern="[?:]">
+        <token type="Operator"/>
+      </rule>
+      <rule pattern="\bdefined\b">
+        <token type="Operator"/>
+      </rule>
+      <rule pattern="[;{}(),.\[\]]">
+        <token type="Punctuation"/>
+      </rule>
+      <rule pattern="[+-]?\d*\.\d+([eE][-+]?\d+)?f?">
+        <token type="LiteralNumberFloat"/>
+      </rule>
+      <rule pattern="[+-]?\d+\.\d*([eE][-+]?\d+)?f?">
+        <token type="LiteralNumberFloat"/>
+      </rule>
+      <rule pattern="0[xX][0-9a-fA-F]*">
+        <token type="LiteralNumberHex"/>
+      </rule>
+      <rule pattern="0[0-7]*">
+        <token type="LiteralNumberOct"/>
+      </rule>
+      <rule pattern="[1-9][0-9]*">
+        <token type="LiteralNumberInteger"/>
+      </rule>
+      <rule pattern="&quot;">
+        <token type="LiteralString"/>
+        <push state="string"/>
+      </rule>
+      <rule pattern="\b(asm|asm_fragment|break|case|cbuffer|centroid|class|column_major|compile|compile_fragment|const|continue|default|discard|do|else|export|extern|for|fxgroup|globallycoherent|groupshared|if|in|inline|inout|interface|line|lineadj|linear|namespace|nointerpolation|noperspective|NULL|out|packoffset|pass|pixelfragment|point|precise|return|register|row_major|sample|sampler|shared|stateblock|stateblock_state|static|struct|switch|tbuffer|technique|technique10|technique11|texture|typedef|triangle|triangleadj|uniform|vertexfragment|volatile|while)\b">
+        <token type="Keyword"/>
+      </rule>
+      <rule pattern="\b(true|false)\b">
+        <token type="KeywordConstant"/>
+      </rule>
+      <rule pattern="\b(auto|catch|char|const_cast|delete|dynamic_cast|enum|explicit|friend|goto|long|mutable|new|operator|private|protected|public|reinterpret_cast|short|signed|sizeof|static_cast|template|this|throw|try|typename|union|unsigned|using|virtual)\b">
+        <token type="KeywordReserved"/>
+      </rule>
+      <rule pattern="\b(dword|matrix|snorm|string|unorm|unsigned|void|vector|BlendState|Buffer|ByteAddressBuffer|ComputeShader|DepthStencilState|DepthStencilView|DomainShader|GeometryShader|HullShader|InputPatch|LineStream|OutputPatch|PixelShader|PointStream|RasterizerState|RenderTargetView|RasterizerOrderedBuffer|RasterizerOrderedByteAddressBuffer|RasterizerOrderedStructuredBuffer|RasterizerOrderedTexture1D|RasterizerOrderedTexture1DArray|RasterizerOrderedTexture2D|RasterizerOrderedTexture2DArray|RasterizerOrderedTexture3D|RWBuffer|RWByteAddressBuffer|RWStructuredBuffer|RWTexture1D|RWTexture1DArray|RWTexture2D|RWTexture2DArray|RWTexture3D|SamplerState|SamplerComparisonState|StructuredBuffer|Texture1D|Texture1DArray|Texture2D|Texture2DArray|Texture2DMS|Texture2DMSArray|Texture3D|TextureCube|TextureCubeArray|TriangleStream|VertexShader)\b">
+        <token type="KeywordType"/>
+      </rule>
+      <rule pattern="\b(bool|double|float|int|half|min16float|min10float|min16int|min12int|min16uint|uint)([1-4](x[1-4])?)?\b">
+        <token type="KeywordType"/>
+      </rule>
+      <rule pattern="\b(abort|abs|acos|all|AllMemoryBarrier|AllMemoryBarrierWithGroupSync|any|AppendStructuredBuffer|asdouble|asfloat|asin|asint|asuint|asuint|atan|atan2|ceil|CheckAccessFullyMapped|clamp|clip|CompileShader|ConsumeStructuredBuffer|cos|cosh|countbits|cross|D3DCOLORtoUBYTE4|ddx|ddx_coarse|ddx_fine|ddy|ddy_coarse|ddy_fine|degrees|determinant|DeviceMemoryBarrier|DeviceMemoryBarrierWithGroupSync|distance|dot|dst|errorf|EvaluateAttributeAtCentroid|EvaluateAttributeAtSample|EvaluateAttributeSnapped|exp|exp2|f16tof32|f32tof16|faceforward|firstbithigh|firstbitlow|floor|fma|fmod|frac|frexp|fwidth|GetRenderTargetSampleCount|GetRenderTargetSamplePosition|GlobalOrderedCountIncrement|GroupMemoryBarrier|GroupMemoryBarrierWithGroupSync|InterlockedAdd|InterlockedAnd|InterlockedCompareExchange|InterlockedCompareStore|InterlockedExchange|InterlockedMax|InterlockedMin|InterlockedOr|InterlockedXor|isfinite|isinf|isnan|ldexp|length|lerp|lit|log|log10|log2|mad|max|min|modf|msad4|mul|noise|normalize|pow|printf|Process2DQuadTessFactorsAvg|Process2DQuadTessFactorsMax|Process2DQuadTessFactorsMin|ProcessIsolineTessFactors|ProcessQuadTessFactorsAvg|ProcessQuadTessFactorsMax|ProcessQuadTessFactorsMin|ProcessTriTessFactorsAvg|ProcessTriTessFactorsMax|ProcessTriTessFactorsMin|QuadReadLaneAt|QuadSwapX|QuadSwapY|radians|rcp|reflect|refract|reversebits|round|rsqrt|saturate|sign|sin|sincos|sinh|smoothstep|sqrt|step|tan|tanh|tex1D|tex1D|tex1Dbias|tex1Dgrad|tex1Dlod|tex1Dproj|tex2D|tex2D|tex2Dbias|tex2Dgrad|tex2Dlod|tex2Dproj|tex3D|tex3D|tex3Dbias|tex3Dgrad|tex3Dlod|tex3Dproj|texCUBE|texCUBE|texCUBEbias|texCUBEgrad|texCUBElod|texCUBEproj|transpose|trunc|WaveAllBitAnd|WaveAllMax|WaveAllMin|WaveAllBitOr|WaveAllBitXor|WaveAllEqual|WaveAllProduct|WaveAllSum|WaveAllTrue|WaveAnyTrue|WaveBallot|WaveGetLaneCount|WaveGetLaneIndex|WaveGetOrderedIndex|WaveIsHelperLane|WaveOnce|WavePrefixProduct|WavePrefixSum|WaveReadFirstLane|WaveReadLaneAt)\b">
+        <token type="NameBuiltin"/>
+      </rule>
+      <rule pattern="\b(SV_ClipDistance|SV_ClipDistance0|SV_ClipDistance1|SV_Culldistance|SV_CullDistance0|SV_CullDistance1|SV_Coverage|SV_Depth|SV_DepthGreaterEqual|SV_DepthLessEqual|SV_DispatchThreadID|SV_DomainLocation|SV_GroupID|SV_GroupIndex|SV_GroupThreadID|SV_GSInstanceID|SV_InnerCoverage|SV_InsideTessFactor|SV_InstanceID|SV_IsFrontFace|SV_OutputControlPointID|SV_Position|SV_PrimitiveID|SV_RenderTargetArrayIndex|SV_SampleIndex|SV_StencilRef|SV_TessFactor|SV_VertexID|SV_ViewportArrayIndex)\b">
+        <token type="NameDecorator"/>
+      </rule>
+      <rule pattern="\bSV_Target[0-7]?\b">
+        <token type="NameDecorator"/>
+      </rule>
+      <rule pattern="\b(allow_uav_condition|branch|call|domain|earlydepthstencil|fastopt|flatten|forcecase|instance|loop|maxtessfactor|numthreads|outputcontrolpoints|outputtopology|partitioning|patchconstantfunc|unroll)\b">
+        <token type="NameDecorator"/>
+      </rule>
+      <rule pattern="[a-zA-Z_]\w*">
+        <token type="Name"/>
+      </rule>
+      <rule pattern="\\$">
+        <token type="CommentPreproc"/>
+      </rule>
+      <rule pattern="\s+">
+        <token type="Text"/>
+      </rule>
+    </state>
+    <state name="string">
+      <rule pattern="&quot;">
+        <token type="LiteralString"/>
+        <pop depth="1"/>
+      </rule>
+      <rule pattern="\\([\\abfnrtv&quot;\&#x27;]|x[a-fA-F0-9]{2,4}|u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})">
+        <token type="LiteralStringEscape"/>
+      </rule>
+      <rule pattern="[^\\&quot;\n]+">
+        <token type="LiteralString"/>
+      </rule>
+      <rule pattern="\\\n">
+        <token type="LiteralString"/>
+      </rule>
+      <rule pattern="\\">
+        <token type="LiteralString"/>
+      </rule>
+    </state>
+  </rules>
+</lexer>
\ No newline at end of file
diff --git a/lexers/testdata/hlsl.actual b/lexers/testdata/hlsl.actual
new file mode 100644
index 000000000..a84631c8a
--- /dev/null
+++ b/lexers/testdata/hlsl.actual
@@ -0,0 +1,3 @@
+float4 vertex(float3 position) {
+    return mul(projection, mul(view, mul(model, float4(position, 1.0))));
+}
diff --git a/lexers/testdata/hlsl.expected b/lexers/testdata/hlsl.expected
new file mode 100644
index 000000000..dcd0491e5
--- /dev/null
+++ b/lexers/testdata/hlsl.expected
@@ -0,0 +1,40 @@
+[
+  {"type":"KeywordType","value":"float4"},
+  {"type":"Text","value":" "},
+  {"type":"Name","value":"vertex"},
+  {"type":"Punctuation","value":"("},
+  {"type":"KeywordType","value":"float3"},
+  {"type":"Text","value":" "},
+  {"type":"Name","value":"position"},
+  {"type":"Punctuation","value":")"},
+  {"type":"Text","value":" "},
+  {"type":"Punctuation","value":"{"},
+  {"type":"Text","value":"\n    "},
+  {"type":"Keyword","value":"return"},
+  {"type":"Text","value":" "},
+  {"type":"NameBuiltin","value":"mul"},
+  {"type":"Punctuation","value":"("},
+  {"type":"Name","value":"projection"},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"NameBuiltin","value":"mul"},
+  {"type":"Punctuation","value":"("},
+  {"type":"Name","value":"view"},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"NameBuiltin","value":"mul"},
+  {"type":"Punctuation","value":"("},
+  {"type":"Name","value":"model"},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"KeywordType","value":"float4"},
+  {"type":"Punctuation","value":"("},
+  {"type":"Name","value":"position"},
+  {"type":"Punctuation","value":","},
+  {"type":"Text","value":" "},
+  {"type":"LiteralNumberFloat","value":"1.0"},
+  {"type":"Punctuation","value":"))));"},
+  {"type":"Text","value":"\n"},
+  {"type":"Punctuation","value":"}"},
+  {"type":"Text","value":"\n"}
+]
\ No newline at end of file