master 4ed3954 2/2: Avoid expensive recoding for ASCII identity cases (bug#40407)

[Mattias Engdegård]

branch: master
commit 4ed39549e3f9dbfeb2aea0e2674a7701dbc0e5ea
Author: Mattias Engdegård <address@hidden>
Commit: Mattias Engdegård <address@hidden>

    Avoid expensive recoding for ASCII identity cases (bug#40407)
    
    Optimise for the common case of encoding or decoding an ASCII-only
    string using an ASCII-compatible coding, for file names in particular.
    
    * src/coding.c (string_ascii_p): New function.
    (code_convert_string): Return the input string for ASCII-only inputs
    and ASCII-compatible codings.
    * test/src/coding-tests.el (coding-nocopy-ascii): New test.
---
 src/coding.c             | 27 ++++++++++++++++++++++++++-
 test/src/coding-tests.el | 11 +++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/src/coding.c b/src/coding.c
index 1049f1b..97a6eb9 100644
--- a/src/coding.c
+++ b/src/coding.c
@@ -9471,6 +9471,17 @@ not fully specified.)  */)
   return code_convert_region (start, end, coding_system, destination, 1, 0);
 }
 
+/* Whether a string only contains chars in the 0..127 range.  */
+static bool
+string_ascii_p (Lisp_Object str)
+{
+  ptrdiff_t nbytes = SBYTES (str);
+  for (ptrdiff_t i = 0; i < nbytes; i++)
+    if (SREF (str, i) > 127)
+      return false;
+  return true;
+}
+
 Lisp_Object
 code_convert_string (Lisp_Object string, Lisp_Object coding_system,
                     Lisp_Object dst_object, bool encodep, bool nocopy,
@@ -9502,7 +9513,21 @@ code_convert_string (Lisp_Object string, Lisp_Object 
coding_system,
   chars = SCHARS (string);
   bytes = SBYTES (string);
 
-  if (BUFFERP (dst_object))
+  if (EQ (dst_object, Qt))
+    {
+      /* Fast path for ASCII-only input and an ASCII-compatible coding:
+         act as identity.  */
+      Lisp_Object attrs = CODING_ID_ATTRS (coding.id);
+      if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))
+          && (STRING_MULTIBYTE (string)
+              ? (chars == bytes) : string_ascii_p (string)))
+       return (nocopy
+                ? string
+                : (encodep
+                   ? make_unibyte_string (SDATA (string), bytes)
+                   : make_multibyte_string (SDATA (string), bytes, bytes)));
+    }
+  else if (BUFFERP (dst_object))
     {
       struct buffer *buf = XBUFFER (dst_object);
       ptrdiff_t buf_pt = BUF_PT (buf);
diff --git a/test/src/coding-tests.el b/test/src/coding-tests.el
index 110ff12..93e6709 100644
--- a/test/src/coding-tests.el
+++ b/test/src/coding-tests.el
@@ -383,6 +383,17 @@
     (should-not (eq (encode-coding-string s nil nil) s))
     (should (eq (encode-coding-string s nil t) s))))
 
+(ert-deftest coding-nocopy-ascii ()
+  "Check that the NOCOPY parameter works for ASCII-only strings."
+  (let* ((uni (apply #'string (number-sequence 0 127)))
+         (multi (string-to-multibyte uni)))
+    (dolist (s (list uni multi))
+      (dolist (coding '(us-ascii iso-latin-1 utf-8))
+        (should-not (eq (decode-coding-string s coding nil) s))
+        (should-not (eq (encode-coding-string s coding nil) s))
+        (should (eq (decode-coding-string s coding t) s))
+        (should (eq (encode-coding-string s coding t) s))))))
+
 ;; Local Variables:
 ;; byte-compile-warnings: (not obsolete)
 ;; End: