feature/tree-sitter ac9bc819bc 6/6: Fix tree-sitter comment indentation for C-like languages

[Yuan Fu]

branch: feature/tree-sitter
commit ac9bc819bc438f21bd38a995812d756727ed8e2a
Author: Yuan Fu <casouri@gmail.com>
Commit: Yuan Fu <casouri@gmail.com>

    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.
---
 doc/lispref/modes.texi         | 22 +++++++++++++++++++++-
 doc/lispref/parsing.texi       | 14 ++++++++++++++
 lisp/progmodes/c-ts-mode.el    |  6 ++++--
 lisp/progmodes/java-ts-mode.el |  4 ++++
 lisp/progmodes/js.el           |  5 +++++
 lisp/progmodes/ts-mode.el      |  4 ++++
 lisp/treesit.el                | 42 +++++++++++++++++++++++++++++++++++++++++-
 7 files changed, 93 insertions(+), 4 deletions(-)

diff --git a/doc/lispref/modes.texi b/doc/lispref/modes.texi
index 8b20bc0b75..5e5eb45897 100644
--- a/doc/lispref/modes.texi
+++ b/doc/lispref/modes.texi
@@ -4964,6 +4964,12 @@ first child where parent is @code{argument_list}, use
 (match nil "argument_list" nil nil 0 0)
 @end example
 
+@item comment-end
+This matcher is a function of 3 arguments: @var{node}, @var{parent},
+and @var{bol}, and returns non-@code{nil} if point is before a comment
+ending token.  Comment ending tokens are defined by regular expression
+@code{treesit-comment-end}.
+
 @item first-sibling
 This anchor is a function that is called with 3 arguments: @var{node},
 @var{parent}, and @var{bol}, and returns the start of the first child
@@ -4996,8 +5002,22 @@ charater on the previous line.
 This anchor is a function is called with 3 arguments: @var{node},
 @var{parent}, and @var{bol}, and returns the beginning of the buffer.
 This is useful as the beginning of the buffer is always at column 0.
-@end ftable
 
+@item comment-start
+This anchor is a function is called with 3 arguments: @var{node},
+@var{parent}, and @var{bol}, and returns the position right after the
+opening comment token.  Opening comment tokens are defined by regular
+expression @code{treesit-comment-start}.  This function assumes
+@var{parent} is the comment node.
+
+@item coment-start-skip
+This anchor is a function is called with 3 arguments: @var{node},
+@var{parent}, and @var{bol}, and returns the position after the
+opening comment token, after skipping forward any whitespace
+characters.  Opening comment tokens are defined by regular expression
+@code{treesit-comment-start}.  This function assumes @var{parent} is
+the comment node.
+@end ftable
 @end defvar
 
 @heading Indentation utilities
diff --git a/doc/lispref/parsing.texi b/doc/lispref/parsing.texi
index feb92345ff..6a23b0feb3 100644
--- a/doc/lispref/parsing.texi
+++ b/doc/lispref/parsing.texi
@@ -1731,6 +1731,20 @@ For more information of these built-in tree-sitter 
features,
 For supporting mixing of multiple languages in a major mode,
 @pxref{Multiple Languages}.
 
+Setting the following local variables allows tree-sitter's indentation
+engine to correctly indent multi-line comments:
+
+@defvar treesit-comment-start
+This should be a regular expression matching an opening comment token.
+For example, it should match @samp{//}, @samp{////}, @samp{/*},
+@samp{/****}, etc., in C.
+@end defvar
+
+@defvar treesit-comment-end
+This should be a regular expression matching an closing comment token.
+For example, it should match @samp{*/}, @samp{****/}, etc., in C.
+@end defvar
+
 @node Tree-sitter C API
 @section Tree-sitter C API Correspondence
 
diff --git a/lisp/progmodes/c-ts-mode.el b/lisp/progmodes/c-ts-mode.el
index f8e809bb43..43668a56d9 100644
--- a/lisp/progmodes/c-ts-mode.el
+++ b/lisp/progmodes/c-ts-mode.el
@@ -84,8 +84,8 @@ MODE is either `c' or `cpp'."
            ((node-is "else") parent-bol 0)
            ((node-is "case") parent-bol 0)
            ((node-is "preproc_arg") no-indent)
-           ((node-is "comment") no-indent)
-           ((parent-is "comment") no-indent)
+           ((and (parent-is "comment") comment-end) comment-start -1)
+           ((parent-is "comment") comment-start-skip 0)
            ((node-is "labeled_statement") parent-bol 0)
            ((parent-is "labeled_statement") parent-bol c-ts-mode-indent-offset)
            ((match "preproc_ifdef" "compound_statement") point-min 0)
@@ -503,6 +503,8 @@ the subtrees."
   (setq-local comment-start "/* ")
   (setq-local comment-start-skip "\\(?://+\\|/\\*+\\)\\s *")
   (setq-local comment-end " */")
+  (setq-local treesit-comment-start (rx "/" (or (+ "/") (+ "*"))))
+  (setq-local treesit-comment-end (rx (+ (or "*")) "/"))
 
   (setq-local treesit-simple-indent-rules
               (c-ts-mode--set-indent-style 'c))
diff --git a/lisp/progmodes/java-ts-mode.el b/lisp/progmodes/java-ts-mode.el
index ee75753027..d3cae1dcca 100644
--- a/lisp/progmodes/java-ts-mode.el
+++ b/lisp/progmodes/java-ts-mode.el
@@ -61,6 +61,8 @@
      ((node-is "}") (and parent parent-bol) 0)
      ((node-is ")") parent-bol 0)
      ((node-is "]") parent-bol 0)
+     ((and (parent-is "comment") comment-end) comment-start -1)
+     ((parent-is "comment") comment-start-skip 0)
      ((parent-is "class_body") parent-bol java-ts-mode-indent-offset)
      ((parent-is "interface_body") parent-bol java-ts-mode-indent-offset)
      ((parent-is "constructor_body") parent-bol java-ts-mode-indent-offset)
@@ -284,6 +286,8 @@ the subtrees."
   (setq-local comment-start "// ")
   (setq-local comment-start-skip "\\(?://+\\|/\\*+\\)\\s *")
   (setq-local comment-end "")
+  (setq-local treesit-comment-start (rx "/" (or (+ "/") (+ "*"))))
+  (setq-local treesit-comment-end (rx (+ (or "*")) "/"))
 
   ;; Indent.
   (setq-local treesit-simple-indent-rules java-ts-mode--indent-rules)
diff --git a/lisp/progmodes/js.el b/lisp/progmodes/js.el
index c37cef977b..159c32ca2a 100644
--- a/lisp/progmodes/js.el
+++ b/lisp/progmodes/js.el
@@ -3412,6 +3412,9 @@ This function is intended for use in 
`after-change-functions'."
        ((node-is ")") parent-bol 0)
        ((node-is "]") parent-bol 0)
        ((node-is ">") parent-bol 0)
+       ((parent-is "comment") comment-start 0)
+       ((and (parent-is "comment") comment-end) comment-start -1)
+       ((parent-is "comment") comment-start-skip 0)
        ((parent-is "ternary_expression") parent-bol js-indent-level)
        ((parent-is "member_expression") parent-bol js-indent-level)
        ((node-is ,switch-case) parent-bol 0)
@@ -3807,6 +3810,8 @@ Currently there are `js-mode' and `js-ts-mode'."
     (setq-local comment-start-skip "\\(?://+\\|/\\*+\\)\\s *")
     (setq-local comment-end "")
     (setq-local comment-multi-line t)
+    (setq-local treesit-comment-start (rx "/" (or (+ "/") (+ "*"))))
+    (setq-local treesit-comment-end (rx (+ (or "*")) "/"))
     ;; Electric-indent.
     (setq-local electric-indent-chars
                (append "{}():;," electric-indent-chars)) ;FIXME: js2-mode adds 
"[]*".
diff --git a/lisp/progmodes/ts-mode.el b/lisp/progmodes/ts-mode.el
index c826302c7a..a6f8e0a65e 100644
--- a/lisp/progmodes/ts-mode.el
+++ b/lisp/progmodes/ts-mode.el
@@ -61,6 +61,8 @@
      ((node-is ")") parent-bol 0)
      ((node-is "]") parent-bol 0)
      ((node-is ">") parent-bol 0)
+     ((and (parent-is "comment") comment-end) comment-start -1)
+     ((parent-is "comment") comment-start-skip 0)
      ((parent-is "ternary_expression") parent-bol ts-mode-indent-offset)
      ((parent-is "member_expression") parent-bol ts-mode-indent-offset)
      ((parent-is "named_imports") parent-bol ts-mode-indent-offset)
@@ -273,6 +275,8 @@
     (setq-local comment-start "// ")
     (setq-local comment-start-skip "\\(?://+\\|/\\*+\\)\\s *")
     (setq-local comment-end "")
+    (setq-local treesit-comment-start (rx "/" (or (+ "/") (+ "*"))))
+    (setq-local treesit-comment-end (rx (+ (or "*")) "/"))
 
     ;; Electric
     (setq-local electric-indent-chars
diff --git a/lisp/treesit.el b/lisp/treesit.el
index 2ee9771522..0c98d3167d 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.