aboutsummaryrefslogtreecommitdiffstats
path: root/re.c
diff options
context:
space:
mode:
authornaruse <naruse@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-02-02 17:38:00 +0000
committernaruse <naruse@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2016-02-02 17:38:00 +0000
commit7ec0677b8cf7e55603da146360bb74853aabb3ec (patch)
tree845e54e5ce2f6004380b8a535367d4d484d609fc /re.c
parent618ba37563a79c3eddc4e6b7f5b81d10c9c88c88 (diff)
downloadruby-7ec0677b8cf7e55603da146360bb74853aabb3ec.tar.gz
* re.c (rb_reg_prepare_enc): use already compiled US-ASCII regexp
if given string is ASCII only. 121.2s to 113.9s on my x86_64-freebsd10.2 Intel Core i5 661 git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@53720 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 're.c')
-rw-r--r--re.c12
1 files changed, 9 insertions, 3 deletions
diff --git a/re.c b/re.c
index 3f7d227594..4036df2910 100644
--- a/re.c
+++ b/re.c
@@ -1374,8 +1374,9 @@ static rb_encoding*
rb_reg_prepare_enc(VALUE re, VALUE str, int warn)
{
rb_encoding *enc = 0;
+ int cr = rb_enc_str_coderange(str);
- if (rb_enc_str_coderange(str) == ENC_CODERANGE_BROKEN) {
+ if (cr == ENC_CODERANGE_BROKEN) {
rb_raise(rb_eArgError,
"invalid byte sequence in %s",
rb_enc_name(rb_enc_get(str)));
@@ -1391,14 +1392,19 @@ rb_reg_prepare_enc(VALUE re, VALUE str, int warn)
else if (rb_reg_fixed_encoding_p(re)) {
if (RREGEXP_PTR(re)->enc != enc &&
(!rb_enc_asciicompat(RREGEXP_PTR(re)->enc) ||
- rb_enc_str_coderange(str) != ENC_CODERANGE_7BIT)) {
+ cr != ENC_CODERANGE_7BIT)) {
reg_enc_error(re, str);
}
enc = RREGEXP_PTR(re)->enc;
}
+ else if (cr == ENC_CODERANGE_7BIT &&
+ (RREGEXP_PTR(re)->enc == rb_usascii_encoding()
+ )) {
+ enc = RREGEXP_PTR(re)->enc;
+ }
if (warn && (RBASIC(re)->flags & REG_ENCODING_NONE) &&
enc != rb_ascii8bit_encoding() &&
- rb_enc_str_coderange(str) != ENC_CODERANGE_7BIT) {
+ cr != ENC_CODERANGE_7BIT) {
rb_warn("regexp match /.../n against to %s string",
rb_enc_name(enc));
}