diff options
| author | Karl Williamson <public@khwilliamson.com> | 2011-11-11 10:28:44 -0700 |
|---|---|---|
| committer | Karl Williamson <public@khwilliamson.com> | 2011-11-11 13:30:59 -0700 |
| commit | 3e16b0e6b272793e45264c51c808855983e8c26d (patch) | |
| tree | fac10a5d80acde421ef5fda67aee8895a30dfb1b /pp.c | |
| parent | e67da29c79beab5029f45b828e2315759ffca351 (diff) | |
| download | perl-3e16b0e6b272793e45264c51c808855983e8c26d.tar.gz | |
pp.c: Call subroutine instead of repeat code
Now that toUPPER_utf8() has the intelligence to skip going out to
swashes for Latin1 code points, it's not so critical to bypass calling
it for these (for speed). It simplifies things not to have the
intelligence repeated. There is the additional overhead of two function
calls (minus the branches saved), but these could be avoided if it comes
down to it by making them in-line.
Diffstat (limited to 'pp.c')
| -rw-r--r-- | pp.c | 32 |
1 files changed, 8 insertions, 24 deletions
@@ -3867,7 +3867,11 @@ PP(pp_uc) bool in_iota_subscript = FALSE; while (s < send) { + STRLEN u; + STRLEN ulen; + UV uv; if (in_iota_subscript && ! is_utf8_mark(s)) { + /* A non-mark. Time to output the iota subscript */ #define GREEK_CAPITAL_LETTER_IOTA 0x0399 #define COMBINING_GREEK_YPOGEGRAMMENI 0x0345 @@ -3876,30 +3880,11 @@ PP(pp_uc) in_iota_subscript = FALSE; } - /* If the UTF-8 character is invariant, then it is in the range - * known by the standard macro; result is only one byte long */ - if (UTF8_IS_INVARIANT(*s)) { - *d++ = toUPPER(*s); - s++; - } - else if (UTF8_IS_DOWNGRADEABLE_START(*s)) { - - /* Likewise, if it fits in a byte, its case change is in our - * table */ - U8 orig = TWO_BYTE_UTF8_TO_UNI(*s, *(s+1)); - U8 upper = toUPPER_LATIN1_MOD(orig); - CAT_TWO_BYTE_UNI_UPPER_MOD(d, orig, upper); - s += 2; - } - else { - - /* Otherwise, need the general UTF-8 case. Get the changed - * case value and copy it to the output buffer */ + /* Then handle the current character. Get the changed case + * value and copy it to the output buffer */ - const STRLEN u = UTF8SKIP(s); - STRLEN ulen; - - const UV uv = toUPPER_utf8(s, tmpbuf, &ulen); + u = UTF8SKIP(s); + uv = toUPPER_utf8(s, tmpbuf, &ulen); if (uv == GREEK_CAPITAL_LETTER_IOTA && utf8_to_uvchr(s, 0) == COMBINING_GREEK_YPOGEGRAMMENI) { @@ -3923,7 +3908,6 @@ PP(pp_uc) d += ulen; } s += u; - } } if (in_iota_subscript) { CAT_UNI_TO_UTF8_TWO_BYTE(d, GREEK_CAPITAL_LETTER_IOTA); |