diff options
| author | Karl Williamson <khw@cpan.org> | 2019-01-30 10:52:41 -0700 |
|---|---|---|
| committer | Karl Williamson <khw@cpan.org> | 2019-02-04 21:00:50 -0700 |
| commit | 93327b758a54c8e1ff7ee137a513caff4d077a7d (patch) | |
| tree | 887f6a4a0bd9b8209d21f400425709c5e769972a | |
| parent | 526f8cbff8ce0a6402d8eb64ac3970e48c8716c3 (diff) | |
| download | perl-93327b758a54c8e1ff7ee137a513caff4d077a7d.tar.gz | |
pp.c: Don't use function call for easy copy
This code is adding the UTF-8 for a Greek character to a string. It
previously used Copy, but this character is representable as two bytes
in both ASCII and EBCDIC UTF-8, the only character sets that Perl will
ever supports, so we can use the specialized code that is used most
everywhere else for two byte UTF-8 characters, avoiding the function
overhead, and having to treat this character as particularly special.
| -rw-r--r-- | pp.c | 6 | ||||
| -rw-r--r-- | regen/unicode_constants.pl | 1 | ||||
| -rw-r--r-- | unicode_constants.h | 3 |
3 files changed, 2 insertions, 8 deletions
@@ -31,9 +31,7 @@ #include "reentr.h" #include "regcharclass.h" -static const STRLEN small_mu_len = sizeof(GREEK_SMALL_LETTER_MU_UTF8) - 1; static const STRLEN capital_iota_len = sizeof(GREEK_CAPITAL_LETTER_IOTA_UTF8) - 1; - /* variations on pp_null */ PP(pp_stub) @@ -4549,8 +4547,8 @@ PP(pp_fc) (send -s) * 2 + 1); d = (U8*)SvPVX(dest) + len; - Copy(GREEK_SMALL_LETTER_MU_UTF8, d, small_mu_len, U8); - d += small_mu_len; + *d++ = UTF8_TWO_BYTE_HI(GREEK_SMALL_LETTER_MU); + *d++ = UTF8_TWO_BYTE_LO(GREEK_SMALL_LETTER_MU); s++; for (; s < send; s++) { diff --git a/regen/unicode_constants.pl b/regen/unicode_constants.pl index 3bddd90ff8..ee7bdb8dcb 100644 --- a/regen/unicode_constants.pl +++ b/regen/unicode_constants.pl @@ -242,7 +242,6 @@ U+017F string U+0300 string U+0399 string -U+03BC string U+1E9E string_skip_if_undef diff --git a/unicode_constants.h b/unicode_constants.h index d5a410fc48..dfeaacc7f0 100644 --- a/unicode_constants.h +++ b/unicode_constants.h @@ -56,7 +56,6 @@ bytes. # define COMBINING_GRAVE_ACCENT_UTF8 "\xCC\x80" /* U+0300 */ # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xCE\x99" /* U+0399 */ -# define GREEK_SMALL_LETTER_MU_UTF8 "\xCE\xBC" /* U+03BC */ # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xE1\xBA\x9E" /* U+1E9E */ @@ -101,7 +100,6 @@ bytes. # define COMBINING_GRAVE_ACCENT_UTF8 "\xAF\x41" /* U+0300 */ # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB3\x68" /* U+0399 */ -# define GREEK_SMALL_LETTER_MU_UTF8 "\xB4\x70" /* U+03BC */ # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x63\x72" /* U+1E9E */ @@ -146,7 +144,6 @@ bytes. # define COMBINING_GRAVE_ACCENT_UTF8 "\xAD\x41" /* U+0300 */ # define GREEK_CAPITAL_LETTER_IOTA_UTF8 "\xB2\x67" /* U+0399 */ -# define GREEK_SMALL_LETTER_MU_UTF8 "\xB3\x6A" /* U+03BC */ # define LATIN_CAPITAL_LETTER_SHARP_S_UTF8 "\xBF\x62\x71" /* U+1E9E */ |