emacs-29 3b3c47d977b: (treesit_predicate_match): Match node text against regexp without consing

[Dmitry Gutov]

branch: emacs-29
commit 3b3c47d977bbe27f7157557b6b0e25d1dcf07640
Author: Dmitry Gutov <dgutov@yandex.ru>
Commit: Dmitry Gutov <dgutov@yandex.ru>

    (treesit_predicate_match): Match node text against regexp without consing
    
    * src/treesit.c (treesit_predicate_match): Match node text against
    regexp without creating a new string object (bug#60953).
    
    * src/search.c (search_buffer): Make not static.
    Delete declaration near the beginning of the file.
    
    * src/lisp.h: Declare it here.
    
    * lisp/progmodes/ruby-ts-mode.el (ruby-ts--builtin-method-p):
    Remove function.
    (ruby-ts--font-lock-settings): Use the regexp with :match directly.
---
 lisp/progmodes/ruby-ts-mode.el |  5 +----
 src/lisp.h                     |  3 +++
 src/search.c                   |  5 +----
 src/treesit.c                  | 36 ++++++++++++++++++++++++++++++++++--
 4 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/lisp/progmodes/ruby-ts-mode.el b/lisp/progmodes/ruby-ts-mode.el
index 60215978176..7725d0824e3 100644
--- a/lisp/progmodes/ruby-ts-mode.el
+++ b/lisp/progmodes/ruby-ts-mode.el
@@ -209,9 +209,6 @@ values of OVERRIDE"
     (treesit-fontify-with-override (max plus-1 start) (min node-end end)
                                    font-lock-comment-face override)))
 
-(defun ruby-ts--builtin-method-p (node)
-  (string-match-p ruby-ts--builtin-methods (treesit-node-text node t)))
-
 (defun ruby-ts--font-lock-settings (language)
   "Tree-sitter font-lock settings for Ruby."
   (treesit-font-lock-rules
@@ -340,7 +337,7 @@ values of OVERRIDE"
    :language language
    :feature 'builtin-function
    `((((identifier) @font-lock-builtin-face)
-      (:pred ruby-ts--builtin-method-p @font-lock-builtin-face)))
+      (:match ,ruby-ts--builtin-methods @font-lock-builtin-face)))
 
    ;; Yuan recommends also putting method definitions into the
    ;; 'function' category (thus keeping it in both).  I've opted to
diff --git a/src/lisp.h b/src/lisp.h
index 70555b3ce91..1276285e2f2 100644
--- a/src/lisp.h
+++ b/src/lisp.h
@@ -4802,6 +4802,9 @@ extern ptrdiff_t find_newline_no_quit (ptrdiff_t, 
ptrdiff_t,
                                       ptrdiff_t, ptrdiff_t *);
 extern ptrdiff_t find_before_next_newline (ptrdiff_t, ptrdiff_t,
                                           ptrdiff_t, ptrdiff_t *);
+extern EMACS_INT search_buffer (Lisp_Object, ptrdiff_t, ptrdiff_t,
+                               ptrdiff_t, ptrdiff_t, EMACS_INT,
+                               int, Lisp_Object, Lisp_Object, bool);
 extern void syms_of_search (void);
 extern void clear_regexp_cache (void);
 
diff --git a/src/search.c b/src/search.c
index dbc5a83946f..0bb52c03eef 100644
--- a/src/search.c
+++ b/src/search.c
@@ -68,9 +68,6 @@ static EMACS_INT simple_search (EMACS_INT, unsigned char *, 
ptrdiff_t,
 static EMACS_INT boyer_moore (EMACS_INT, unsigned char *, ptrdiff_t,
                               Lisp_Object, Lisp_Object, ptrdiff_t,
                               ptrdiff_t, int);
-static EMACS_INT search_buffer (Lisp_Object, ptrdiff_t, ptrdiff_t,
-                                ptrdiff_t, ptrdiff_t, EMACS_INT, int,
-                                Lisp_Object, Lisp_Object, bool);
 
 Lisp_Object re_match_object;
 
@@ -1510,7 +1507,7 @@ search_buffer_non_re (Lisp_Object string, ptrdiff_t pos,
   return result;
 }
 
-static EMACS_INT
+EMACS_INT
 search_buffer (Lisp_Object string, ptrdiff_t pos, ptrdiff_t pos_byte,
               ptrdiff_t lim, ptrdiff_t lim_byte, EMACS_INT n,
               int RE, Lisp_Object trt, Lisp_Object inverse_trt, bool posix)
diff --git a/src/treesit.c b/src/treesit.c
index 405aec1f47e..52953573061 100644
--- a/src/treesit.c
+++ b/src/treesit.c
@@ -2470,10 +2470,42 @@ treesit_predicate_match (Lisp_Object args, struct 
capture_range captures)
              build_string ("The second argument to `match' should "
                            "be a capture name, not a string"));
 
-  Lisp_Object text = treesit_predicate_capture_name_to_text (capture_name,
+  Lisp_Object node = treesit_predicate_capture_name_to_node (capture_name,
                                                             captures);
 
-  if (fast_string_match (regexp, text) >= 0)
+  struct buffer *old_buffer = current_buffer;
+  struct buffer *buffer = XBUFFER (XTS_PARSER (XTS_NODE 
(node)->parser)->buffer);
+  set_buffer_internal (buffer);
+
+  TSNode treesit_node = XTS_NODE (node)->node;
+  ptrdiff_t visible_beg = XTS_PARSER (XTS_NODE (node)->parser)->visible_beg;
+  uint32_t start_byte_offset = ts_node_start_byte (treesit_node);
+  uint32_t end_byte_offset = ts_node_end_byte (treesit_node);
+  ptrdiff_t start_byte = visible_beg + start_byte_offset;
+  ptrdiff_t end_byte = visible_beg + end_byte_offset;
+  ptrdiff_t start_pos = buf_bytepos_to_charpos (buffer, start_byte);
+  ptrdiff_t end_pos = buf_bytepos_to_charpos (buffer, end_byte);
+  ptrdiff_t old_begv = BEGV;
+  ptrdiff_t old_begv_byte = BEGV_BYTE;
+  ptrdiff_t old_zv = ZV;
+  ptrdiff_t old_zv_byte = ZV_BYTE;
+
+  BEGV = start_pos;
+  BEGV_BYTE = start_byte;
+  ZV = end_pos;
+  ZV_BYTE = end_byte;
+
+  ptrdiff_t val = search_buffer (regexp, start_pos, start_byte, end_pos, 
end_byte,
+                                1, 1, Qnil, Qnil, false);
+
+  BEGV = old_begv;
+  BEGV_BYTE = old_begv_byte;
+  ZV = old_zv;
+  ZV_BYTE = old_zv_byte;
+
+  set_buffer_internal (old_buffer);
+
+  if (val > 0)
     return true;
   else
     return false;