emacs-29 1df2826639 1/4: Add c-or-c++-ts-mode (bug#59613)

[Yuan Fu]

branch: emacs-29
commit 1df2826639c912396fac0af108301533dac71406
Author: Yuan Fu <casouri@gmail.com>
Commit: Yuan Fu <casouri@gmail.com>

    Add c-or-c++-ts-mode (bug#59613)
    
    * lisp/progmodes/c-ts-mode.el
    (c-ts-mode--c-or-c++-regexp): New variable.
    (c-or-c++-ts-mode): New mode.
    * etc/NEWS: Mention c-or-c++-ts-mode.
---
 etc/NEWS                    |  5 +++++
 lisp/progmodes/c-ts-mode.el | 44 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/etc/NEWS b/etc/NEWS
index 5901b2718e..c7cfead5fd 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -3210,6 +3210,11 @@ programs in the C language.
 An optional major mode based on the tree-sitter library for editing
 programs in the C++ language.
 
++++
+*** New major mode 'c-or-c++-ts-mode'.
+A function that automatically guesses the language of a header file,
+and enables either 'c-ts-mode' or 'c++-ts-mode' accordingly.
+
 +++
 *** New major mode 'java-ts-mode'.
 An optional major mode based on the tree-sitter library for editing
diff --git a/lisp/progmodes/c-ts-mode.el b/lisp/progmodes/c-ts-mode.el
index 30a14ecdfa..b8c4313c0f 100644
--- a/lisp/progmodes/c-ts-mode.el
+++ b/lisp/progmodes/c-ts-mode.el
@@ -822,6 +822,50 @@ Set up:
 
   (treesit-major-mode-setup))
 
+;; We could alternatively use parsers, but if this works well, I don't
+;; see the need to change.  This is copied verbatim from cc-guess.el.
+(defconst c-ts-mode--c-or-c++-regexp
+  (eval-when-compile
+    (let ((id "[a-zA-Z_][a-zA-Z0-9_]*") (ws "[ \t]+") (ws-maybe "[ \t]*")
+          (headers '("string" "string_view" "iostream" "map" "unordered_map"
+                     "set" "unordered_set" "vector" "tuple")))
+      (concat "^" ws-maybe "\\(?:"
+              "using"     ws "\\(?:namespace" ws
+              "\\|" id "::"
+              "\\|" id ws-maybe "=\\)"
+              "\\|" "\\(?:inline" ws "\\)?namespace"
+              "\\(:?" ws "\\(?:" id "::\\)*" id "\\)?" ws-maybe "{"
+              "\\|" "class"     ws id
+              "\\(?:" ws "final" "\\)?" ws-maybe "[:{;\n]"
+              "\\|" "struct"     ws id "\\(?:" ws "final" ws-maybe "[:{\n]"
+              "\\|" ws-maybe ":\\)"
+              "\\|" "template"  ws-maybe "<.*?>"
+              "\\|" "#include"  ws-maybe "<" (regexp-opt headers) ">"
+              "\\)")))
+  "A regexp applied to C header files to check if they are really C++.")
+
+;;;###autoload
+(defun c-or-c++-ts-mode ()
+  "Analyze buffer and enable either C or C++ mode.
+
+Some people and projects use .h extension for C++ header files
+which is also the one used for C header files.  This makes
+matching on file name insufficient for detecting major mode that
+should be used.
+
+This function attempts to use file contents to determine whether
+the code is C or C++ and based on that chooses whether to enable
+`c-ts-mode' or `c++-ts-mode'."
+  (interactive)
+  (if (save-excursion
+        (save-restriction
+          (save-match-data ; Why `save-match-data'?
+            (widen)
+            (goto-char (point-min))
+            (re-search-forward c-ts-mode--c-or-c++-regexp nil t))))
+      (c++-ts-mode)
+    (c-ts-mode)))
+
 (provide 'c-ts-mode)
 
 ;;; c-ts-mode.el ends here