[llvm] [emacs] Handle vector types, arbitary integer types and function names (PR #88246)

[Luke Lau via llvm-commits]

https://github.com/lukel97 created https://github.com/llvm/llvm-project/pull/88246

Resurrecting this patch from https://reviews.llvm.org/D158321

This adds a few more regexp patterns for llvm-mode-syntax-table. The primitive type regexp was split out so it could be reused when handling vectors. Also worth noting is that the vector regexp needs to come before the primitive types, otherwise they will match first.

@goldsteinn I was able to address your review comments, turns out you can set a font-face for a specific match group. And < 2x i64> should be accepted now.

<img width="260" alt="screenshot of new font faces matched" src="https://github.com/llvm/llvm-project/assets/2488460/f2428f55-a616-4351-9035-e87e263826ab">


>From 18e2504b7a586f29eff7780cebe671aa22500cf7 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Wed, 10 Apr 2024 17:10:34 +0800
Subject: [PATCH] [emacs] Handle vector types, arbitary integer types and
 function names

Resurrecting this patch from https://reviews.llvm.org/D158321

This adds a few more regexp patterns for llvm-mode-syntax-table. The primitive type regexp was split out so it could be reused when handling vectors. Also worth noting is that the vector regexp needs to come before the primitive types, otherwise they will match first.

@goldsteinn I was able to address your review comments, turns out you can set a font-face for a specific match group. And < 2x i64> should be accepted now.
---
 llvm/utils/emacs/llvm-mode.el | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/llvm/utils/emacs/llvm-mode.el b/llvm/utils/emacs/llvm-mode.el
index 5264ea260f57c1..a74fd2194072de 100644
--- a/llvm/utils/emacs/llvm-mode.el
+++ b/llvm/utils/emacs/llvm-mode.el
@@ -18,6 +18,14 @@
     table)
   "Syntax table used while in LLVM mode.")
 
+(defconst llvm-mode-primitive-type-regexp
+  (concat
+   "\\(i[0-9]+\\|"
+   (regexp-opt
+    '("void" "half" "bfloat" "float" "double" "fp128" "x86_fp80" "ppc_fp128"
+      "x86_mmx" "x86_amx" "ptr" "type" "label" "opaque" "token") t)
+   "\\)"))
+
 (defvar llvm-font-lock-keywords
   (list
    ;; Attributes
@@ -34,10 +42,23 @@
    '("[-a-zA-Z$._0-9]+:" . font-lock-variable-name-face)
    ;; Unnamed variable slots
    '("%[-]?[0-9]+" . font-lock-variable-name-face)
-   ;; Types
-   `(,(regexp-opt
-       '("void" "i1" "i8" "i16" "i32" "i64" "i128" "half" "bfloat" "float" "double" "fp128" "x86_fp80" "ppc_fp128" "x86_mmx" "x86_amx" "ptr"
-         "type" "label" "opaque" "token") 'symbols) . font-lock-type-face)
+   ;; Function names
+   '("@[-a-zA-Z$._][-a-zA-Z$._0-9]*" . font-lock-function-name-face)
+   ;; Fixed vector types
+   `(,(concat "<[ \t]*\\([0-9]+\\)[ \t]*x[ \t]+"
+	      llvm-mode-primitive-type-regexp
+	      "[ \t]*>")
+     (1 'font-lock-preprocessor-face)
+     (2 'font-lock-type-face))
+   ;; Scalable vector types
+   `(,(concat "<[ \t]*\\(vscale[ \t]\\)+x[ \t]+\\([0-9]+\\)[ \t]*x[ \t]+"
+	      llvm-mode-primitive-type-regexp
+	      "[ \t]*>")
+     (1 'font-lock-keyword-face)
+     (2 'font-lock-type-face)
+     (3 'font-lock-type-face))
+   ;; Primitive types
+   `(,(concat "\\<" llvm-mode-primitive-type-regexp "\\>") . font-lock-type-face)
    ;; Integer literals
    '("\\b[-]?[0-9]+\\b" . font-lock-preprocessor-face)
    ;; Floating point constants