New variable treesit-language-remap-alist (bug#72388)

* doc/lispref/parsing.texi (Using Parser): Manual entry for the new
variable.
* src/treesit.c (resolve_language_symbol): New function.
(Ftreesit_parser_create, Ftreesit_parser_list): Resolve language before
using it.
(Vtreesit_language_remap_alist): New variable.

(cherry picked from commit a7e3181e2f7adb928d63a8878a11849818ba321c)

diff --git a/doc/lispref/parsing.texi b/doc/lispref/parsing.texi
index a3d2a5ac71cc87ba8cb5b8424184c9d41671325e..ddf02d9283baa56823e5bf8a421af9319758d1d0 100644 (file)
--- a/doc/lispref/parsing.texi
+++ b/doc/lispref/parsing.texi
@@ -531,6 +531,30 @@ symbol, rather than a lambda function.
 This function returns the list of @var{parser}'s notifier functions.
 @end defun
 
+@heading Substitute parser for another language
+@cindex remap language grammar, tree-sitter
+@cindex replace language grammar, tree-sitter
+@cindex replace parser language, tree-sitter
+@cindex extended grammar, tree-sitter
+
+Sometimes, a grammar for language B is a strict superset of the grammar
+of another language A.  Then it makes sense to reuse configurations
+(font-lock rules, indentation rules, etc.) of language A for language B.
+For that purpose, @var{treesit-language-remap-alist} allows users to
+remap language A into language B.
+
+@defvar treesit-language-remap-alist
+The value of this variable should be an alist of
+@w{@code{(@var{language-a} . @var{language-b})}}.  When such pair exists
+in the alist, creating a parser for @var{language-a} actually creates a
+parser for @var{language-b}.  By extension, anything that creates a node
+or makes a query of @var{language-a} will be redirected to use
+@var{language-b} instead.
+
+Note that calling @code{treesit-parser-language} on a parser for
+@var{language-a} still returns @var{language-a}.
+@end defvar
+
 @node Retrieving Nodes
 @section Retrieving Nodes
 @cindex retrieve node, tree-sitter

diff --git a/src/treesit.c b/src/treesit.c
index 513d0d22c7faef55651554c687a007a0dd00790c..277796929230f66992bfe54d619ac046e4f03d2e 100644 (file)
--- a/src/treesit.c
+++ b/src/treesit.c
@@ -1326,6 +1326,17 @@ treesit_ensure_query_compiled (Lisp_Object query, Lisp_Object *signal_symbol,
   return treesit_query;
 }
 
+/* Resolve language symbol LANG according to
+   treesit-language-remap-alist.  */
+static
+Lisp_Object resolve_language_symbol (Lisp_Object lang)
+{
+  Lisp_Object res = Fassoc (lang, Vtreesit_language_remap_alist, Qeq);
+  if (NILP (res))
+    return lang;
+  return Fcdr (res);
+}
+
 \f
 /* Lisp definitions.  */
 
@@ -1442,6 +1453,9 @@ an indirect buffer.  */)
 
   treesit_check_buffer_size (buf);
 
+  language = resolve_language_symbol (language);
+  CHECK_SYMBOL (language);
+
   /* See if we can reuse a parser.  */
   if (NILP (no_reuse))
     {
@@ -1531,6 +1545,8 @@ tag.  */)
   if (buf->base_buffer)
     buf = buf->base_buffer;
 
+  language = resolve_language_symbol (language);
+
   /* Return a fresh list so messing with that list doesn't affect our
      internal data.  */
   Lisp_Object return_list = Qnil;
@@ -4157,6 +4173,19 @@ Finally, PRED can refer to other THINGs defined in this list by using
 the symbol of that THING.  For example, (or sexp sentence).  */);
   Vtreesit_thing_settings = Qnil;
 
+  DEFVAR_LISP ("treesit-language-remap-alist",
+              Vtreesit_language_remap_alist,
+              doc:
+              /* An alist remapping language symbols.
+
+The value should be an alist of (LANGUAGE-A . LANGUAGE-B).  When such
+pair exists in the alist, creating a parser for LANGUAGE-A actually
+creates a parser for LANGUAGE-B.  Basically, anything that requires or
+applies to LANGUAGE-A will be redirected to LANGUAGE-B instead.  */);
+  Vtreesit_language_remap_alist = Qnil;
+  DEFSYM (Qtreesit_language_remap_alist, "treesit-language-remap-alist");
+  Fmake_variable_buffer_local (Qtreesit_language_remap_alist);
+
   staticpro (&Vtreesit_str_libtree_sitter);
   Vtreesit_str_libtree_sitter = build_pure_c_string ("libtree-sitter-");
   staticpro (&Vtreesit_str_tree_sitter);