From db0a4d9045892e9f8b5760267dc80ff51cac4d22 Mon Sep 17 00:00:00 2001
From: KOBAYASHI Shuji <shuujii@gmail.com>
Date: Sat, 26 Oct 2019 22:19:04 +0900
Subject: Optimize `chars2bytes` with `MRB_UTF8_STRING` to ASCII only string

### Benchmark (with `MRB_UTF8_STRING`)

  ```
  $ mruby -e '
    COUNT = 150000
    SIZE = 10000
    strs = Array.new(COUNT) do
      s = "a" * SIZE
      s.size  # set `MRB_STR_ASCII` flag
      s
    end
    i = 0
    t = Time.now
    while i < COUNT
      strs[i][-2..-1] = ""
      i += 1
    end
    printf "%.2f sec\n", Time.now - t
  '

  1.10 sec  # before
  0.07 sec  # after
  ```
---
 src/string.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

(limited to 'src/string.c')

diff --git a/src/string.c b/src/string.c
index 518b62ea3..e5c3a3843 100644
--- a/src/string.c
+++ b/src/string.c
@@ -330,16 +330,21 @@ utf8_strlen(mrb_value str)
 static mrb_int
 chars2bytes(mrb_value s, mrb_int off, mrb_int idx)
 {
-  mrb_int i, b, n;
-  const char *p = RSTRING_PTR(s) + off;
-  const char *e = RSTRING_END(s);
+  if (RSTR_ASCII_P(mrb_str_ptr(s))) {
+    return idx;
+  }
+  else {
+    mrb_int i, b, n;
+    const char *p = RSTRING_PTR(s) + off;
+    const char *e = RSTRING_END(s);
 
-  for (b=i=0; p<e && i<idx; i++) {
-    n = utf8len(p, e);
-    b += n;
-    p += n;
+    for (b=i=0; p<e && i<idx; i++) {
+      n = utf8len(p, e);
+      b += n;
+      p += n;
+    }
+    return b;
   }
-  return b;
 }
 
 /* map byte offset to character index */
@@ -603,7 +608,7 @@ str_range_to_bytes(mrb_value str, mrb_int *pos, mrb_int *len)
 static inline mrb_value
 str_subseq(mrb_state *mrb, mrb_value str, mrb_int beg, mrb_int len)
 {
-  if (!RSTR_ASCII_P(mrb_str_ptr(str))) str_range_to_bytes(str, &beg, &len);
+  str_range_to_bytes(str, &beg, &len);
   return mrb_str_byte_subseq(mrb, str, beg, len);
 }
 #else
-- 
cgit v1.2.3