1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* re.c (rb_reg_prepare_enc): use already compiled US-ASCII regexp

Browse Source 
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
This commit is contained in:
naruse 2016-02-02 17:38:00 +00:00
parent 59e8cd3ea0
commit 7aefa7b89f
2 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ChangeLog
View File

@ -1,3 +1,9 @@
Wed Feb 3 02:33:39 2016 NARUSE, Yui <naruse@ruby-lang.org>
* 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
Tue Feb 2 13:02:03 2016 NARUSE, Yui <naruse@ruby-lang.org> Tue Feb 2 13:02:03 2016 NARUSE, Yui <naruse@ruby-lang.org>
* re.c: Introduce RREGEXP_PTR. * re.c: Introduce RREGEXP_PTR.

12
re.c
View File

@ -1374,8 +1374,9 @@ static rb_encoding*
rb_reg_prepare_enc(VALUE re, VALUE str, int warn) rb_reg_prepare_enc(VALUE re, VALUE str, int warn)
{ {
rb_encoding *enc = 0; 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, rb_raise(rb_eArgError,
"invalid byte sequence in %s", "invalid byte sequence in %s",
rb_enc_name(rb_enc_get(str))); 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)) { else if (rb_reg_fixed_encoding_p(re)) {
if (RREGEXP_PTR(re)->enc != enc && if (RREGEXP_PTR(re)->enc != enc &&
(!rb_enc_asciicompat(RREGEXP_PTR(re)->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); reg_enc_error(re, str);
} }
enc = RREGEXP_PTR(re)->enc; 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) && if (warn && (RBASIC(re)->flags & REG_ENCODING_NONE) &&
enc != rb_ascii8bit_encoding() && 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_warn("regexp match /.../n against to %s string",
rb_enc_name(enc)); rb_enc_name(enc));
} }