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

[ruby/strscan] [CRuby] Optimize strscan_do_scan(): Remove

Browse Source 
unnecessary use of `rb_enc_get()`
(https://github.com/ruby/strscan/pull/108)

- before: #106

## Why?

In `rb_strseq_index()`, the result of `rb_enc_check()` is used.

-
6c7209cd37/string.c (L4335-L4368)
> enc = rb_enc_check(str, sub);

> return strseq_core(str_ptr, str_ptr_end, str_len, sub_ptr, sub_len,
offset, enc);

-
6c7209cd37/string.c (L4309-L4318)
```C
strseq_core(const char *str_ptr, const char *str_ptr_end, long str_len,
            const char *sub_ptr, long sub_len, long offset, rb_encoding *enc)
{
    const char *search_start = str_ptr;
    long pos, search_len = str_len - offset;

    for (;;) {
        const char *t;
        pos = rb_memsearch(sub_ptr, sub_len, search_start, search_len, enc);
```

## Benchmark

It shows String as a pattern is 1.24x faster than Regexp as a pattern.

```
$ benchmark-driver benchmark/check_until.yaml
Warming up --------------------------------------
              regexp     9.225M i/s -      9.328M times in 1.011068s (108.40ns/i)
          regexp_var     9.327M i/s -      9.413M times in 1.009214s (107.21ns/i)
              string     9.200M i/s -      9.355M times in 1.016840s (108.70ns/i)
          string_var    11.249M i/s -     11.255M times in 1.000578s (88.90ns/i)
Calculating -------------------------------------
              regexp     9.565M i/s -     27.676M times in 2.893476s (104.55ns/i)
          regexp_var    10.111M i/s -     27.982M times in 2.767496s (98.90ns/i)
              string    10.060M i/s -     27.600M times in 2.743465s (99.40ns/i)
          string_var    12.519M i/s -     33.746M times in 2.695615s (79.88ns/i)

Comparison:
          string_var:  12518707.2 i/s
          regexp_var:  10111089.6 i/s - 1.24x  slower
              string:  10060144.4 i/s - 1.24x  slower
              regexp:   9565124.4 i/s - 1.31x  slower
```

https://github.com/ruby/strscan/commit/ff2d7afa19
This commit is contained in:
NAITOH Jun 2024-10-16 09:59:44 +09:00 committed by Hiroshi SHIBATA
parent d6046bccb7
commit e73f35ddaf
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ext/strscan/strscan.c
View File

@ -709,7 +709,7 @@ strscan_do_scan(VALUE self, VALUE pattern, int succptr, int getstr, int headonly
} }
else { else {
StringValue(pattern); StringValue(pattern);
rb_enc_check(p->str, pattern); rb_encoding *enc = rb_enc_check(p->str, pattern);
if (S_RESTLEN(p) < RSTRING_LEN(pattern)) { if (S_RESTLEN(p) < RSTRING_LEN(pattern)) {
return Qnil; return Qnil;
} }
@ -719,9 +719,10 @@ strscan_do_scan(VALUE self, VALUE pattern, int succptr, int getstr, int headonly
return Qnil; return Qnil;
} }
set_registers(p, RSTRING_LEN(pattern)); set_registers(p, RSTRING_LEN(pattern));
} else { }
else {
long pos = rb_memsearch(RSTRING_PTR(pattern), RSTRING_LEN(pattern), long pos = rb_memsearch(RSTRING_PTR(pattern), RSTRING_LEN(pattern),
CURPTR(p), S_RESTLEN(p), rb_enc_get(pattern)); CURPTR(p), S_RESTLEN(p), enc);
if (pos == -1) { if (pos == -1) {
return Qnil; return Qnil;
} }