From ac9bc819bc438f21bd38a995812d756727ed8e2a Mon Sep 17 00:00:00 2001
From: Yuan Fu <casouri@gmail.com>
Date: Sat, 19 Nov 2022 17:59:14 -0800
Subject: Fix tree-sitter comment indentation for C-like languages

The goal is to indent like this:

/* comment
   comment  --> This line aligns with the beginning of the first line
 */         --> This line aligns with the opening comment token

* lisp/treesit.el (treesit-comment-start)
(treesit-comment-end): New variables.
(treesit-simple-indent-presets): New preset comment-end,
comment-start, comment-start-skip

* lisp/progmodes/c-ts-mode.el (c-ts-mode--indent-styles)
(c-ts-mode)
* lisp/progmodes/java-ts-mode.el (java-ts-mode--indent-rules)
(java-ts-mode)
* lisp/progmodes/js.el (js--treesit-indent-rules)
(js-ts-mode)
* lisp/progmodes/ts-mode.el (ts-mode--indent-rules)
(ts-mode): Add identical indent rules to each mode, and set identical
treesit-comment-start/end's.

* doc/lispref/modes.texi (Parser-based Indentation)
* doc/lispref/parsing.texi (Tree-sitter major modes): Update manual.
---
 lisp/treesit.el | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

(limited to 'lisp/treesit.el')

diff --git a/lisp/treesit.el b/lisp/treesit.el
index 2ee97715224..0c98d3167d9 100644
--- a/lisp/treesit.el
+++ b/lisp/treesit.el
@@ -851,6 +851,16 @@ parser notifying of the change."
 
 ;;; Indent
 
+;; `comment-start' and `comment-end' assumes there is only one type of
+;; comment and comment spans only one line.  So they are not
+;; sufficient for our purpose.
+
+(defvar-local treesit-comment-start nil
+  "Regular expression matching an opening comment token.")
+
+(defvar-local treesit-comment-end nil
+  "Regular expression matching an closing comment token.")
+
 (define-error 'treesit-indent-error
               "Generic tree-sitter indentation error"
               'treesit-error)
@@ -936,6 +946,8 @@ See `treesit-simple-indent-presets'.")
                           (lambda (node &rest _)
                             (string-match-p
                              name (or (treesit-node-field-name node) "")))))
+        (cons 'comment-end (lambda (&rest _)
+                             (looking-at-p treesit-comment-end)))
         ;; TODO: Document.
         (cons 'catch-all (lambda (&rest _) t))
 
@@ -957,6 +969,19 @@ See `treesit-simple-indent-presets'.")
                                 (treesit-node-child parent n named)))))
         (cons 'parent (lambda (_n parent &rest _)
                         (treesit-node-start parent)))
+        (cons 'comment-start
+              (lambda (_n parent &rest _)
+                (save-excursion
+                  (goto-char (treesit-node-start parent))
+                  (re-search-forward treesit-comment-start)
+                  (point))))
+        (cons 'comment-start-skip
+              (lambda (_n parent &rest _)
+                (save-excursion
+                  (goto-char (treesit-node-start parent))
+                  (re-search-forward treesit-comment-start)
+                  (skip-syntax-forward "-")
+                  (point))))
         ;; TODO: Document.
         (cons 'grand-parent
               (lambda (_n parent &rest _)
@@ -1036,6 +1061,10 @@ no-node
     Queries PARENT with QUERY, and checks if NODE is
     captured (by any capture name).
 
+comment-end
+
+    Matches if text after point matches `treesit-comment-end'.
+
 ANCHOR:
 
 first-sibling
@@ -1065,7 +1094,18 @@ prev-line
 
 point-min
 
-    Returns the beginning of buffer, which is always at column 0.")
+    Returns the beginning of buffer, which is always at column 0.
+
+comment-start
+
+    Returns the ending position after matching `treesit-comment-start'.
+    Assuming PARENT is a comment node.
+
+comment-start-skip
+
+    Goes to the position comment-start would return, skip
+    whitespaces forward, and return the resulting position.
+    Assuming PARENT is a comment node.")
 
 (defun treesit--simple-indent-eval (exp)
   "Evaluate EXP.
-- 
cgit v1.2.3