[Mlir-commits] [mlir] [MLIR][Pygments] Refine the pygments MLIR lexer (PR #166406)

llvmlistbot at llvm.org llvmlistbot at llvm.org
Fri Nov 7 02:39:46 PST 2025


https://github.com/PragmaTwice updated https://github.com/llvm/llvm-project/pull/166406

>From 94821d0f1afc07d853abcdb211729661924b04b9 Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Wed, 5 Nov 2025 01:08:09 +0800
Subject: [PATCH 1/6] [MLIR][Pygments] Refine the pygments MLIR lexer

---
 mlir/utils/pygments/mlir_lexer.py | 136 +++++++++++++++++++++++++-----
 1 file changed, 114 insertions(+), 22 deletions(-)

diff --git a/mlir/utils/pygments/mlir_lexer.py b/mlir/utils/pygments/mlir_lexer.py
index 179a058e9110c..ebe29e083387c 100644
--- a/mlir/utils/pygments/mlir_lexer.py
+++ b/mlir/utils/pygments/mlir_lexer.py
@@ -2,37 +2,129 @@
 # See https://llvm.org/LICENSE.txt for license information.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
-from pygments.lexer import RegexLexer
+from pygments.lexer import RegexLexer, bygroups, include, combined
 from pygments.token import *
+import re
 
 
 class MlirLexer(RegexLexer):
+    """Pygments lexer for MLIR.
+
+    This lexer focuses on accurate tokenization of common MLIR constructs:
+    - SSA values (%%... / %...)
+    - attribute and type aliases (#name =, !name =)
+    - types (builtin and dialect types, parametric types)
+    - attribute dictionaries and nested containers to a reasonable depth
+    - numbers (ints, floats with exponents, hex)
+    - strings with common escapes
+    - line comments (// ...)
+    - block labels (^foo) and operations
+    """
+
     name = "MLIR"
     aliases = ["mlir"]
     filenames = ["*.mlir"]
 
+    flags = re.MULTILINE
+
     tokens = {
         "root": [
-            (r"%[a-zA-Z0-9_]+", Name.Variable),
-            (r"@[a-zA-Z_][a-zA-Z0-9_]+", Name.Function),
-            (r"\^[a-zA-Z0-9_]+", Name.Label),
-            (r"#[a-zA-Z0-9_]+", Name.Constant),
-            (r"![a-zA-Z0-9_]+", Keyword.Type),
-            (r"[a-zA-Z_][a-zA-Z0-9_]*\.", Name.Entity),
-            (r"memref[^.]", Keyword.Type),
-            (r"index", Keyword.Type),
-            (r"i[0-9]+", Keyword.Type),
-            (r"f[0-9]+", Keyword.Type),
+            # Comments
+            (r"//.*?$", Comment.Single),
+
+            # Attribute alias definition:  #name =
+            (r"^\s*(#[_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+             bygroups(Name.Constant, Text, Operator)),
+
+            # Type alias definition: !name =
+            (r"^\s*(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+             bygroups(Keyword.Type, Text, Operator)),
+
+            # SSA values (results, uses) - allow many characters MLIR uses
+            (r"%[%_A-Za-z0-9\.\$:\-]+", Name.Variable),
+
+            # attribute refs, constants and named attributes
+            (r"#[_A-Za-z0-9\$\-\.]+\b", Name.Constant),
+
+            # symbol refs / function-like names
+            (r"@[_A-Za-z][_A-Za-z0-9\$\-\.]*\b", Name.Function),
+
+            # blocks
+            (r"\^[A-Za-z0-9_\$\.\-]+", Name.Label),
+
+            # types by exclamation or builtin names
+            (r"![_A-Za-z0-9\$\-\.]+\b", Keyword.Type),
+            (r"\b(bf16|f16|f32|f64|f80|f128|index|none|(u|s)?i[0-9]+)\b", Keyword.Type),
+
+            # container-like dialect types (tensor<...>, memref<...>, vector<...>)
+            (r"\b(complex|memref|tensor|tuple|vector)\s*(<)", bygroups(Keyword.Type, Punctuation), 'angled-type'),
+
+            # affine constructs
+            (r"\b(affine_map|affine_set)\b", Keyword.Reserved),
+
+            # common builtin operators / functions inside affine_map
+            (r"\b(ceildiv|floordiv|mod|symbol)\b", Name.Builtin),
+
+            # operation definitions with assignment: %... = op.name
+            (r"^\s*(%[\%_A-Za-z0-9\:\,\s]+)\s*(=)\s*([A-Za-z0-9_\.\$\-]+)\b",
+             bygroups(Name.Variable, Operator, Name.Function)),
+
+            # operation name without result
+            (r"^\s*([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", Name.Function),
+
+            # identifiers / bare words
+            (r"\b[_A-Za-z][_A-Za-z0-9\.-]*\b", Name.Other),
+
+            # numbers: hex, float (with exponent), integer
+            (r"\b0x[0-9A-Fa-f]+\b", Number.Hex),
+            (r"\b([0-9]+(\.[0-9]*)?|\.[0-9]+)([eE][+-]?[0-9]+)?\b", Number.Float),
+            (r"\b[0-9]+\b", Number.Integer),
+
+            # strings
+            (r'"', String.Double, 'string'),
+
+            # punctuation and arrow-like tokens
+            (r"->|>=|<=|\>=|\<=|\->|\=>", Operator),
+            (r"[()\[\]{}<>,.:=]", Punctuation),
+
+            # operators
+            (r"[-+*/%]", Operator),
+        ],
+
+        # string state with common escapes
+        'string': [
+            (r'\\[ntr"\\]', String.Escape),
+            (r'[^"\\]+', String.Double),
+            (r'"', String.Double, '#pop'),
+        ],
+
+        # angled-type content (simple nested handling)
+        'angled-type': [
+            # match nested '<' and '>'
+            (r"<", Punctuation, '#push'),
+            (r">", Punctuation, '#pop'),
+
+            # dimensions like 3x or 3x3x... and standalone numbers:
+            # - match numbers that are followed by an 'x' (dimension separator)
+            (r"([0-9]+)(?=(?:[xX]))", Number.Integer),
+            # - match bare numbers (sizes)
             (r"[0-9]+", Number.Integer),
-            (r"[0-9]*\.[0-9]*", Number.Float),
-            (r'"[^"]*"', String.Double),
-            (r"affine_map", Keyword.Reserved),
-            # TODO: this should be within affine maps only
-            (r"\+-\*\/", Operator),
-            (r"floordiv", Operator.Word),
-            (r"ceildiv", Operator.Word),
-            (r"mod", Operator.Word),
-            (r"()\[\]<>,{}", Punctuation),
-            (r"\/\/.*\n", Comment.Single),
-        ]
+            # dynamic dimension '?'
+            (r"\?", Name.Constant),
+
+            # the 'x' dimension separator (treat as punctuation)
+            (r"[xX]", Punctuation),
+
+            # element / builtin types inside angle brackets (no word-boundary)
+            (r"(?:bf16|f16|f32|f64|f80|f128|index|none|(?:[us]?i[0-9]+))",
+            Keyword.Type),
+
+            # also allow nested container-like types to be recognized
+            (r"\b(complex|memref|tensor|tuple|vector)\s*(<)",
+            bygroups(Keyword.Type, Punctuation), 'angled-type'),
+
+            # fall back to root rules for anything else
+            include('root'),
+        ],
+
     }

>From 72d7512400a63d3f680a87c1f2fc8792a7d1d8ba Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Wed, 5 Nov 2025 01:22:47 +0800
Subject: [PATCH 2/6] format

---
 mlir/utils/pygments/mlir_lexer.py | 76 ++++++++++++++-----------------
 1 file changed, 33 insertions(+), 43 deletions(-)

diff --git a/mlir/utils/pygments/mlir_lexer.py b/mlir/utils/pygments/mlir_lexer.py
index ebe29e083387c..ba0811ef2601b 100644
--- a/mlir/utils/pygments/mlir_lexer.py
+++ b/mlir/utils/pygments/mlir_lexer.py
@@ -31,79 +31,69 @@ class MlirLexer(RegexLexer):
         "root": [
             # Comments
             (r"//.*?$", Comment.Single),
-
             # Attribute alias definition:  #name =
-            (r"^\s*(#[_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
-             bygroups(Name.Constant, Text, Operator)),
-
+            (
+                r"^\s*(#[_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+                bygroups(Name.Constant, Text, Operator),
+            ),
             # Type alias definition: !name =
-            (r"^\s*(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
-             bygroups(Keyword.Type, Text, Operator)),
-
+            (
+                r"^\s*(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+                bygroups(Keyword.Type, Text, Operator),
+            ),
             # SSA values (results, uses) - allow many characters MLIR uses
             (r"%[%_A-Za-z0-9\.\$:\-]+", Name.Variable),
-
             # attribute refs, constants and named attributes
             (r"#[_A-Za-z0-9\$\-\.]+\b", Name.Constant),
-
             # symbol refs / function-like names
             (r"@[_A-Za-z][_A-Za-z0-9\$\-\.]*\b", Name.Function),
-
             # blocks
             (r"\^[A-Za-z0-9_\$\.\-]+", Name.Label),
-
             # types by exclamation or builtin names
             (r"![_A-Za-z0-9\$\-\.]+\b", Keyword.Type),
             (r"\b(bf16|f16|f32|f64|f80|f128|index|none|(u|s)?i[0-9]+)\b", Keyword.Type),
-
             # container-like dialect types (tensor<...>, memref<...>, vector<...>)
-            (r"\b(complex|memref|tensor|tuple|vector)\s*(<)", bygroups(Keyword.Type, Punctuation), 'angled-type'),
-
+            (
+                r"\b(complex|memref|tensor|tuple|vector)\s*(<)",
+                bygroups(Keyword.Type, Punctuation),
+                "angled-type",
+            ),
             # affine constructs
             (r"\b(affine_map|affine_set)\b", Keyword.Reserved),
-
             # common builtin operators / functions inside affine_map
             (r"\b(ceildiv|floordiv|mod|symbol)\b", Name.Builtin),
-
             # operation definitions with assignment: %... = op.name
-            (r"^\s*(%[\%_A-Za-z0-9\:\,\s]+)\s*(=)\s*([A-Za-z0-9_\.\$\-]+)\b",
-             bygroups(Name.Variable, Operator, Name.Function)),
-
+            (
+                r"^\s*(%[\%_A-Za-z0-9\:\,\s]+)\s*(=)\s*([A-Za-z0-9_\.\$\-]+)\b",
+                bygroups(Name.Variable, Operator, Name.Function),
+            ),
             # operation name without result
             (r"^\s*([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", Name.Function),
-
             # identifiers / bare words
             (r"\b[_A-Za-z][_A-Za-z0-9\.-]*\b", Name.Other),
-
             # numbers: hex, float (with exponent), integer
             (r"\b0x[0-9A-Fa-f]+\b", Number.Hex),
             (r"\b([0-9]+(\.[0-9]*)?|\.[0-9]+)([eE][+-]?[0-9]+)?\b", Number.Float),
             (r"\b[0-9]+\b", Number.Integer),
-
             # strings
-            (r'"', String.Double, 'string'),
-
+            (r'"', String.Double, "string"),
             # punctuation and arrow-like tokens
             (r"->|>=|<=|\>=|\<=|\->|\=>", Operator),
             (r"[()\[\]{}<>,.:=]", Punctuation),
-
             # operators
             (r"[-+*/%]", Operator),
         ],
-
         # string state with common escapes
-        'string': [
+        "string": [
             (r'\\[ntr"\\]', String.Escape),
             (r'[^"\\]+', String.Double),
-            (r'"', String.Double, '#pop'),
+            (r'"', String.Double, "#pop"),
         ],
-
         # angled-type content (simple nested handling)
-        'angled-type': [
+        "angled-type": [
             # match nested '<' and '>'
-            (r"<", Punctuation, '#push'),
-            (r">", Punctuation, '#pop'),
-
+            (r"<", Punctuation, "#push"),
+            (r">", Punctuation, "#pop"),
             # dimensions like 3x or 3x3x... and standalone numbers:
             # - match numbers that are followed by an 'x' (dimension separator)
             (r"([0-9]+)(?=(?:[xX]))", Number.Integer),
@@ -111,20 +101,20 @@ class MlirLexer(RegexLexer):
             (r"[0-9]+", Number.Integer),
             # dynamic dimension '?'
             (r"\?", Name.Constant),
-
             # the 'x' dimension separator (treat as punctuation)
             (r"[xX]", Punctuation),
-
             # element / builtin types inside angle brackets (no word-boundary)
-            (r"(?:bf16|f16|f32|f64|f80|f128|index|none|(?:[us]?i[0-9]+))",
-            Keyword.Type),
-
+            (
+                r"(?:bf16|f16|f32|f64|f80|f128|index|none|(?:[us]?i[0-9]+))",
+                Keyword.Type,
+            ),
             # also allow nested container-like types to be recognized
-            (r"\b(complex|memref|tensor|tuple|vector)\s*(<)",
-            bygroups(Keyword.Type, Punctuation), 'angled-type'),
-
+            (
+                r"\b(complex|memref|tensor|tuple|vector)\s*(<)",
+                bygroups(Keyword.Type, Punctuation),
+                "angled-type",
+            ),
             # fall back to root rules for anything else
-            include('root'),
+            include("root"),
         ],
-
     }

>From 11793af6742f0ba47becea38b8e5164f932d2a08 Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Wed, 5 Nov 2025 01:44:40 +0800
Subject: [PATCH 3/6] fix space

---
 mlir/utils/pygments/mlir_lexer.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mlir/utils/pygments/mlir_lexer.py b/mlir/utils/pygments/mlir_lexer.py
index ba0811ef2601b..fed54fadbed4b 100644
--- a/mlir/utils/pygments/mlir_lexer.py
+++ b/mlir/utils/pygments/mlir_lexer.py
@@ -64,11 +64,11 @@ class MlirLexer(RegexLexer):
             (r"\b(ceildiv|floordiv|mod|symbol)\b", Name.Builtin),
             # operation definitions with assignment: %... = op.name
             (
-                r"^\s*(%[\%_A-Za-z0-9\:\,\s]+)\s*(=)\s*([A-Za-z0-9_\.\$\-]+)\b",
-                bygroups(Name.Variable, Operator, Name.Function),
+                r"^(\s*)(%[\%_A-Za-z0-9\:\,\s]+)(\s*=\s*)([A-Za-z0-9_\.\$\-]+)\b",
+                bygroups(Text, Name.Variable, Operator, Name.Function),
             ),
             # operation name without result
-            (r"^\s*([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", Name.Function),
+            (r"^(\s*)([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", bygroups(Text, Name.Function)),
             # identifiers / bare words
             (r"\b[_A-Za-z][_A-Za-z0-9\.-]*\b", Name.Other),
             # numbers: hex, float (with exponent), integer

>From 49a5f16e78daa446d6aa90f066a97e8538e44375 Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Fri, 7 Nov 2025 12:29:35 +0800
Subject: [PATCH 4/6] fix issues in review

---
 mlir/utils/pygments/mlir_lexer.bak.py | 38 ++++++++++++++++++++++
 mlir/utils/pygments/mlir_lexer.py     | 47 +++++++++++++++++----------
 2 files changed, 67 insertions(+), 18 deletions(-)
 create mode 100644 mlir/utils/pygments/mlir_lexer.bak.py

diff --git a/mlir/utils/pygments/mlir_lexer.bak.py b/mlir/utils/pygments/mlir_lexer.bak.py
new file mode 100644
index 0000000000000..179a058e9110c
--- /dev/null
+++ b/mlir/utils/pygments/mlir_lexer.bak.py
@@ -0,0 +1,38 @@
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+from pygments.lexer import RegexLexer
+from pygments.token import *
+
+
+class MlirLexer(RegexLexer):
+    name = "MLIR"
+    aliases = ["mlir"]
+    filenames = ["*.mlir"]
+
+    tokens = {
+        "root": [
+            (r"%[a-zA-Z0-9_]+", Name.Variable),
+            (r"@[a-zA-Z_][a-zA-Z0-9_]+", Name.Function),
+            (r"\^[a-zA-Z0-9_]+", Name.Label),
+            (r"#[a-zA-Z0-9_]+", Name.Constant),
+            (r"![a-zA-Z0-9_]+", Keyword.Type),
+            (r"[a-zA-Z_][a-zA-Z0-9_]*\.", Name.Entity),
+            (r"memref[^.]", Keyword.Type),
+            (r"index", Keyword.Type),
+            (r"i[0-9]+", Keyword.Type),
+            (r"f[0-9]+", Keyword.Type),
+            (r"[0-9]+", Number.Integer),
+            (r"[0-9]*\.[0-9]*", Number.Float),
+            (r'"[^"]*"', String.Double),
+            (r"affine_map", Keyword.Reserved),
+            # TODO: this should be within affine maps only
+            (r"\+-\*\/", Operator),
+            (r"floordiv", Operator.Word),
+            (r"ceildiv", Operator.Word),
+            (r"mod", Operator.Word),
+            (r"()\[\]<>,{}", Punctuation),
+            (r"\/\/.*\n", Comment.Single),
+        ]
+    }
diff --git a/mlir/utils/pygments/mlir_lexer.py b/mlir/utils/pygments/mlir_lexer.py
index fed54fadbed4b..3e053a1dd2fa7 100644
--- a/mlir/utils/pygments/mlir_lexer.py
+++ b/mlir/utils/pygments/mlir_lexer.py
@@ -2,7 +2,7 @@
 # See https://llvm.org/LICENSE.txt for license information.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
-from pygments.lexer import RegexLexer, bygroups, include, combined
+from pygments.lexer import RegexLexer, bygroups, include, using
 from pygments.token import *
 import re
 
@@ -27,22 +27,40 @@ class MlirLexer(RegexLexer):
 
     flags = re.MULTILINE
 
+    class VariableList(RegexLexer):
+        """Lexer for lists of SSA variables separated by commas."""
+
+        tokens = {
+            "root": [
+                (r"\s+", Text),
+                (r",", Punctuation),
+                (r"%[_A-Za-z0-9\.\$\-:#]+", Name.Variable),
+            ]
+        }
+
     tokens = {
         "root": [
             # Comments
             (r"//.*?$", Comment.Single),
+            # operation name with assignment: %... = op.name
+            (
+                r"^(\s*)(%[\%_A-Za-z0-9\:#\,\s]+)(=)(\s*)([A-Za-z0-9_\.\$\-]+)\b",
+                bygroups(Text, using(VariableList), Operator, Text, Name.Builtin),
+            ),
+            # operation name without result
+            (r"^(\s*)([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", bygroups(Text, Name.Builtin)),
             # Attribute alias definition:  #name =
             (
-                r"^\s*(#[_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
-                bygroups(Name.Constant, Text, Operator),
+                r"^(\s*)(#[_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+                bygroups(Text, Name.Constant, Text, Operator),
             ),
             # Type alias definition: !name =
             (
-                r"^\s*(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
-                bygroups(Keyword.Type, Text, Operator),
+                r"^(\s*)(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
+                bygroups(Text, Keyword.Type, Text, Operator),
             ),
-            # SSA values (results, uses) - allow many characters MLIR uses
-            (r"%[%_A-Za-z0-9\.\$:\-]+", Name.Variable),
+            # SSA values (results, uses)
+            (r"%[_A-Za-z0-9\.\$\-:#]+", Name.Variable),
             # attribute refs, constants and named attributes
             (r"#[_A-Za-z0-9\$\-\.]+\b", Name.Constant),
             # symbol refs / function-like names
@@ -61,14 +79,7 @@ class MlirLexer(RegexLexer):
             # affine constructs
             (r"\b(affine_map|affine_set)\b", Keyword.Reserved),
             # common builtin operators / functions inside affine_map
-            (r"\b(ceildiv|floordiv|mod|symbol)\b", Name.Builtin),
-            # operation definitions with assignment: %... = op.name
-            (
-                r"^(\s*)(%[\%_A-Za-z0-9\:\,\s]+)(\s*=\s*)([A-Za-z0-9_\.\$\-]+)\b",
-                bygroups(Text, Name.Variable, Operator, Name.Function),
-            ),
-            # operation name without result
-            (r"^(\s*)([A-Za-z0-9_\.\$\-]+)\b(?=[^<:])", bygroups(Text, Name.Function)),
+            (r"\b(ceildiv|floordiv|mod|symbol)\b", Name.Other),
             # identifiers / bare words
             (r"\b[_A-Za-z][_A-Za-z0-9\.-]*\b", Name.Other),
             # numbers: hex, float (with exponent), integer
@@ -96,13 +107,13 @@ class MlirLexer(RegexLexer):
             (r">", Punctuation, "#pop"),
             # dimensions like 3x or 3x3x... and standalone numbers:
             # - match numbers that are followed by an 'x' (dimension separator)
-            (r"([0-9]+)(?=(?:[xX]))", Number.Integer),
+            (r"([0-9]+)(?=(?:x))", Number.Integer),
             # - match bare numbers (sizes)
             (r"[0-9]+", Number.Integer),
             # dynamic dimension '?'
-            (r"\?", Name.Constant),
+            (r"\?", Name.Integer),
             # the 'x' dimension separator (treat as punctuation)
-            (r"[xX]", Punctuation),
+            (r"x", Punctuation),
             # element / builtin types inside angle brackets (no word-boundary)
             (
                 r"(?:bf16|f16|f32|f64|f80|f128|index|none|(?:[us]?i[0-9]+))",

>From 0534a170c00bcdcbd78055ba4e3e7d59d088b748 Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Fri, 7 Nov 2025 12:37:23 +0800
Subject: [PATCH 5/6] remove useless file

---
 mlir/utils/pygments/mlir_lexer.bak.py | 38 ---------------------------
 1 file changed, 38 deletions(-)
 delete mode 100644 mlir/utils/pygments/mlir_lexer.bak.py

diff --git a/mlir/utils/pygments/mlir_lexer.bak.py b/mlir/utils/pygments/mlir_lexer.bak.py
deleted file mode 100644
index 179a058e9110c..0000000000000
--- a/mlir/utils/pygments/mlir_lexer.bak.py
+++ /dev/null
@@ -1,38 +0,0 @@
-# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-# See https://llvm.org/LICENSE.txt for license information.
-# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-
-from pygments.lexer import RegexLexer
-from pygments.token import *
-
-
-class MlirLexer(RegexLexer):
-    name = "MLIR"
-    aliases = ["mlir"]
-    filenames = ["*.mlir"]
-
-    tokens = {
-        "root": [
-            (r"%[a-zA-Z0-9_]+", Name.Variable),
-            (r"@[a-zA-Z_][a-zA-Z0-9_]+", Name.Function),
-            (r"\^[a-zA-Z0-9_]+", Name.Label),
-            (r"#[a-zA-Z0-9_]+", Name.Constant),
-            (r"![a-zA-Z0-9_]+", Keyword.Type),
-            (r"[a-zA-Z_][a-zA-Z0-9_]*\.", Name.Entity),
-            (r"memref[^.]", Keyword.Type),
-            (r"index", Keyword.Type),
-            (r"i[0-9]+", Keyword.Type),
-            (r"f[0-9]+", Keyword.Type),
-            (r"[0-9]+", Number.Integer),
-            (r"[0-9]*\.[0-9]*", Number.Float),
-            (r'"[^"]*"', String.Double),
-            (r"affine_map", Keyword.Reserved),
-            # TODO: this should be within affine maps only
-            (r"\+-\*\/", Operator),
-            (r"floordiv", Operator.Word),
-            (r"ceildiv", Operator.Word),
-            (r"mod", Operator.Word),
-            (r"()\[\]<>,{}", Punctuation),
-            (r"\/\/.*\n", Comment.Single),
-        ]
-    }

>From 47fac063762356ef78bce651a80a41af21a032a7 Mon Sep 17 00:00:00 2001
From: PragmaTwice <twice at apache.org>
Date: Fri, 7 Nov 2025 18:39:30 +0800
Subject: [PATCH 6/6] add change-sync notice

---
 mlir/utils/pygments/mlir_lexer.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mlir/utils/pygments/mlir_lexer.py b/mlir/utils/pygments/mlir_lexer.py
index 3e053a1dd2fa7..4cbe0fe236fc4 100644
--- a/mlir/utils/pygments/mlir_lexer.py
+++ b/mlir/utils/pygments/mlir_lexer.py
@@ -59,7 +59,7 @@ class VariableList(RegexLexer):
                 r"^(\s*)(![_A-Za-z0-9\$\-\.]+)(\b)(\s*=)",
                 bygroups(Text, Keyword.Type, Text, Operator),
             ),
-            # SSA values (results, uses)
+            # SSA values (uses)
             (r"%[_A-Za-z0-9\.\$\-:#]+", Name.Variable),
             # attribute refs, constants and named attributes
             (r"#[_A-Za-z0-9\$\-\.]+\b", Name.Constant),
@@ -69,6 +69,7 @@ class VariableList(RegexLexer):
             (r"\^[A-Za-z0-9_\$\.\-]+", Name.Label),
             # types by exclamation or builtin names
             (r"![_A-Za-z0-9\$\-\.]+\b", Keyword.Type),
+            # NOTE: please sync changes to corresponding builtin type rule in "angled-type"
             (r"\b(bf16|f16|f32|f64|f80|f128|index|none|(u|s)?i[0-9]+)\b", Keyword.Type),
             # container-like dialect types (tensor<...>, memref<...>, vector<...>)
             (
@@ -100,7 +101,7 @@ class VariableList(RegexLexer):
             (r'[^"\\]+', String.Double),
             (r'"', String.Double, "#pop"),
         ],
-        # angled-type content (simple nested handling)
+        # angled-type content
         "angled-type": [
             # match nested '<' and '>'
             (r"<", Punctuation, "#push"),
@@ -115,6 +116,7 @@ class VariableList(RegexLexer):
             # the 'x' dimension separator (treat as punctuation)
             (r"x", Punctuation),
             # element / builtin types inside angle brackets (no word-boundary)
+            # NOTE: please sync changes to corresponding builtin type rule in "root"
             (
                 r"(?:bf16|f16|f32|f64|f80|f128|index|none|(?:[us]?i[0-9]+))",
                 Keyword.Type,



More information about the Mlir-commits mailing list