In perl.git, the branch blead has been updated <http://perl5.git.perl.org/perl.git/commitdiff/dc2e544e7f6b9c92650110831cb474944d022ca5?hp=8bed4564ff8c76dca8a43f80873148de2591c1ee>
- Log ----------------------------------------------------------------- commit dc2e544e7f6b9c92650110831cb474944d022ca5 Author: Karl Williamson <[email protected]> Date: Sat Jan 4 22:21:14 2014 -0700 utf8.c: Move a bunch of deprecated fcns to mathoms.c These functions will be out of the way in mathoms. There were a few that could not be moved, as-is, so I left them. M mathoms.c M utf8.c commit 0324dadaebed3376a82581ec86490ede0d85ceb1 Author: Karl Williamson <[email protected]> Date: Sat Jan 4 20:28:24 2014 -0700 utf8.c: Use existing macros instead of duplicate code In all these cases, there is an already existing macro that does exactly the same thing as the code that this commit replaces. No sense duplicating logic. M utf8.c ----------------------------------------------------------------------- Summary of changes: mathoms.c | 395 +++++++++++++++++++++++++++++++++++++++++++++++++++++ utf8.c | 463 -------------------------------------------------------------- 2 files changed, 395 insertions(+), 463 deletions(-) diff --git a/mathoms.c b/mathoms.c index 60f5a96..592116a 100644 --- a/mathoms.c +++ b/mathoms.c @@ -1227,6 +1227,401 @@ ASCII_TO_NEED(const UV enc, const UV ch) return ch; } +bool +Perl_is_uni_alnum(pTHX_ UV c) +{ + return isWORDCHAR_uni(c); +} + +bool +Perl_is_uni_alnumc(pTHX_ UV c) +{ + return isALNUM_uni(c); +} + +bool +Perl_is_uni_alpha(pTHX_ UV c) +{ + return isALPHA_uni(c); +} + +bool +Perl_is_uni_ascii(pTHX_ UV c) +{ + return isASCII_uni(c); +} + +bool +Perl_is_uni_blank(pTHX_ UV c) +{ + return isBLANK_uni(c); +} + +bool +Perl_is_uni_space(pTHX_ UV c) +{ + return isSPACE_uni(c); +} + +bool +Perl_is_uni_digit(pTHX_ UV c) +{ + return isDIGIT_uni(c); +} + +bool +Perl_is_uni_upper(pTHX_ UV c) +{ + return isUPPER_uni(c); +} + +bool +Perl_is_uni_lower(pTHX_ UV c) +{ + return isLOWER_uni(c); +} + +bool +Perl_is_uni_cntrl(pTHX_ UV c) +{ + return isCNTRL_L1(c); +} + +bool +Perl_is_uni_graph(pTHX_ UV c) +{ + return isGRAPH_uni(c); +} + +bool +Perl_is_uni_print(pTHX_ UV c) +{ + return isPRINT_uni(c); +} + +bool +Perl_is_uni_punct(pTHX_ UV c) +{ + return isPUNCT_uni(c); +} + +bool +Perl_is_uni_xdigit(pTHX_ UV c) +{ + return isXDIGIT_uni(c); +} + +bool +Perl_is_uni_alnum_lc(pTHX_ UV c) +{ + return isWORDCHAR_LC_uvchr(c); +} + +bool +Perl_is_uni_alnumc_lc(pTHX_ UV c) +{ + return isALPHANUMERIC_LC_uvchr(c); +} + +bool +Perl_is_uni_idfirst_lc(pTHX_ UV c) +{ + /* XXX Should probably be something that resolves to the old IDFIRST, but + * this function is deprecated, so not bothering */ + return isIDFIRST_LC_uvchr(c); +} + +bool +Perl_is_uni_alpha_lc(pTHX_ UV c) +{ + return isALPHA_LC_uvchr(c); +} + +bool +Perl_is_uni_ascii_lc(pTHX_ UV c) +{ + return isASCII_LC_uvchr(c); +} + +bool +Perl_is_uni_blank_lc(pTHX_ UV c) +{ + return isBLANK_LC_uvchr(c); +} + +bool +Perl_is_uni_space_lc(pTHX_ UV c) +{ + return isSPACE_LC_uvchr(c); +} + +bool +Perl_is_uni_digit_lc(pTHX_ UV c) +{ + return isDIGIT_LC_uvchr(c); +} + +bool +Perl_is_uni_upper_lc(pTHX_ UV c) +{ + return isUPPER_LC_uvchr(c); +} + +bool +Perl_is_uni_lower_lc(pTHX_ UV c) +{ + return isLOWER_LC_uvchr(c); +} + +bool +Perl_is_uni_cntrl_lc(pTHX_ UV c) +{ + return isCNTRL_LC_uvchr(c); +} + +bool +Perl_is_uni_graph_lc(pTHX_ UV c) +{ + return isGRAPH_LC_uvchr(c); +} + +bool +Perl_is_uni_print_lc(pTHX_ UV c) +{ + return isPRINT_LC_uvchr(c); +} + +bool +Perl_is_uni_punct_lc(pTHX_ UV c) +{ + return isPUNCT_LC_uvchr(c); +} + +bool +Perl_is_uni_xdigit_lc(pTHX_ UV c) +{ + return isXDIGIT_LC_uvchr(c); +} + +U32 +Perl_to_uni_upper_lc(pTHX_ U32 c) +{ + /* XXX returns only the first character -- do not use XXX */ + /* XXX no locale support yet */ + STRLEN len; + U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; + return (U32)to_uni_upper(c, tmpbuf, &len); +} + +U32 +Perl_to_uni_title_lc(pTHX_ U32 c) +{ + /* XXX returns only the first character XXX -- do not use XXX */ + /* XXX no locale support yet */ + STRLEN len; + U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; + return (U32)to_uni_title(c, tmpbuf, &len); +} + +U32 +Perl_to_uni_lower_lc(pTHX_ U32 c) +{ + /* XXX returns only the first character -- do not use XXX */ + /* XXX no locale support yet */ + STRLEN len; + U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; + return (U32)to_uni_lower(c, tmpbuf, &len); +} + +bool +Perl_is_utf8_alnum(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_ALNUM; + + /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true + * descendant of isalnum(3), in other words, it doesn't + * contain the '_'. --jhi */ + return isWORDCHAR_utf8(p); +} + +bool +Perl_is_utf8_alnumc(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_ALNUMC; + + return isALPHANUMERIC_utf8(p); +} + +bool +Perl_is_utf8_alpha(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_ALPHA; + + return isALPHA_utf8(p); +} + +bool +Perl_is_utf8_ascii(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_ASCII; + + return isASCII_utf8(p); +} + +bool +Perl_is_utf8_blank(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_BLANK; + + return isBLANK_utf8(p); +} + +bool +Perl_is_utf8_space(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_SPACE; + + return isSPACE_utf8(p); +} + +bool +Perl_is_utf8_perl_space(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_PERL_SPACE; + + /* Only true if is an ASCII space-like character, and ASCII is invariant + * under utf8, so can just use the macro */ + return isSPACE_A(*p); +} + +bool +Perl_is_utf8_perl_word(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_PERL_WORD; + + /* Only true if is an ASCII word character, and ASCII is invariant + * under utf8, so can just use the macro */ + return isWORDCHAR_A(*p); +} + +bool +Perl_is_utf8_digit(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_DIGIT; + + return isDIGIT_utf8(p); +} + +bool +Perl_is_utf8_posix_digit(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_POSIX_DIGIT; + + /* Only true if is an ASCII digit character, and ASCII is invariant + * under utf8, so can just use the macro */ + return isDIGIT_A(*p); +} + +bool +Perl_is_utf8_upper(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_UPPER; + + return isUPPER_utf8(p); +} + +bool +Perl_is_utf8_lower(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_LOWER; + + return isLOWER_utf8(p); +} + +bool +Perl_is_utf8_cntrl(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_CNTRL; + + return isCNTRL_utf8(p); +} + +bool +Perl_is_utf8_graph(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_GRAPH; + + return isGRAPH_utf8(p); +} + +bool +Perl_is_utf8_print(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_PRINT; + + return isPRINT_utf8(p); +} + +bool +Perl_is_utf8_punct(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_PUNCT; + + return isPUNCT_utf8(p); +} + +bool +Perl_is_utf8_xdigit(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_XDIGIT; + + return isXDIGIT_utf8(p); +} + +bool +Perl_is_utf8_mark(pTHX_ const U8 *p) +{ + dVAR; + + PERL_ARGS_ASSERT_IS_UTF8_MARK; + + return _is_utf8_mark(p); +} + END_EXTERN_C #endif /* NO_MATHOMS */ diff --git a/utf8.c b/utf8.c index 8dc69bb..b4a688a 100644 --- a/utf8.c +++ b/utf8.c @@ -1535,26 +1535,6 @@ Perl__is_uni_FOO(pTHX_ const U8 classnum, const UV c) return _is_utf8_FOO(classnum, tmpbuf); } -/* for now these are all defined (inefficiently) in terms of the utf8 versions. - * Note that the macros in handy.h that call these short-circuit calling them - * for Latin-1 range inputs */ - -bool -Perl_is_uni_alnum(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_WORDCHAR, tmpbuf); -} - -bool -Perl_is_uni_alnumc(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_ALPHANUMERIC, tmpbuf); -} - /* Internal function so we can deprecate the external one, and call this one from other deprecated functions in this file */ @@ -1593,92 +1573,6 @@ Perl__is_uni_perl_idstart(pTHX_ UV c) return _is_utf8_perl_idstart(tmpbuf); } -bool -Perl_is_uni_alpha(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_ALPHA, tmpbuf); -} - -bool -Perl_is_uni_ascii(pTHX_ UV c) -{ - return isASCII(c); -} - -bool -Perl_is_uni_blank(pTHX_ UV c) -{ - return isBLANK_uni(c); -} - -bool -Perl_is_uni_space(pTHX_ UV c) -{ - return isSPACE_uni(c); -} - -bool -Perl_is_uni_digit(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_DIGIT, tmpbuf); -} - -bool -Perl_is_uni_upper(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_UPPER, tmpbuf); -} - -bool -Perl_is_uni_lower(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_LOWER, tmpbuf); -} - -bool -Perl_is_uni_cntrl(pTHX_ UV c) -{ - return isCNTRL_L1(c); -} - -bool -Perl_is_uni_graph(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_GRAPH, tmpbuf); -} - -bool -Perl_is_uni_print(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_PRINT, tmpbuf); -} - -bool -Perl_is_uni_punct(pTHX_ UV c) -{ - U8 tmpbuf[UTF8_MAXBYTES+1]; - uvchr_to_utf8(tmpbuf, c); - return _is_utf8_FOO(_CC_PUNCT, tmpbuf); -} - -bool -Perl_is_uni_xdigit(pTHX_ UV c) -{ - return isXDIGIT_uni(c); -} - UV Perl__to_upper_title_latin1(pTHX_ const U8 c, U8* p, STRLEN *lenp, const char S_or_s) { @@ -1914,171 +1808,6 @@ Perl__to_uni_fold_flags(pTHX_ UV c, U8* p, STRLEN *lenp, const U8 flags) } } -bool -Perl_is_uni_alnum_lc(pTHX_ UV c) -{ - if (c < 256) { - return isALNUM_LC(c); - } - return _is_uni_FOO(_CC_WORDCHAR, c); -} - -bool -Perl_is_uni_alnumc_lc(pTHX_ UV c) -{ - if (c < 256) { - return isALPHANUMERIC_LC(c); - } - return _is_uni_FOO(_CC_ALPHANUMERIC, c); -} - -bool -Perl_is_uni_idfirst_lc(pTHX_ UV c) -{ - if (c < 256) { - return isIDFIRST_LC(c); - } - return _is_uni_perl_idstart(c); -} - -bool -Perl_is_uni_alpha_lc(pTHX_ UV c) -{ - if (c < 256) { - return isALPHA_LC(c); - } - return _is_uni_FOO(_CC_ALPHA, c); -} - -bool -Perl_is_uni_ascii_lc(pTHX_ UV c) -{ - if (c < 256) { - return isASCII_LC(c); - } - return 0; -} - -bool -Perl_is_uni_blank_lc(pTHX_ UV c) -{ - if (c < 256) { - return isBLANK_LC(c); - } - return isBLANK_uni(c); -} - -bool -Perl_is_uni_space_lc(pTHX_ UV c) -{ - if (c < 256) { - return isSPACE_LC(c); - } - return isSPACE_uni(c); -} - -bool -Perl_is_uni_digit_lc(pTHX_ UV c) -{ - if (c < 256) { - return isDIGIT_LC(c); - } - return _is_uni_FOO(_CC_DIGIT, c); -} - -bool -Perl_is_uni_upper_lc(pTHX_ UV c) -{ - if (c < 256) { - return isUPPER_LC(c); - } - return _is_uni_FOO(_CC_UPPER, c); -} - -bool -Perl_is_uni_lower_lc(pTHX_ UV c) -{ - if (c < 256) { - return isLOWER_LC(c); - } - return _is_uni_FOO(_CC_LOWER, c); -} - -bool -Perl_is_uni_cntrl_lc(pTHX_ UV c) -{ - if (c < 256) { - return isCNTRL_LC(c); - } - return 0; -} - -bool -Perl_is_uni_graph_lc(pTHX_ UV c) -{ - if (c < 256) { - return isGRAPH_LC(c); - } - return _is_uni_FOO(_CC_GRAPH, c); -} - -bool -Perl_is_uni_print_lc(pTHX_ UV c) -{ - if (c < 256) { - return isPRINT_LC(c); - } - return _is_uni_FOO(_CC_PRINT, c); -} - -bool -Perl_is_uni_punct_lc(pTHX_ UV c) -{ - if (c < 256) { - return isPUNCT_LC(c); - } - return _is_uni_FOO(_CC_PUNCT, c); -} - -bool -Perl_is_uni_xdigit_lc(pTHX_ UV c) -{ - if (c < 256) { - return isXDIGIT_LC(c); - } - return isXDIGIT_uni(c); -} - -U32 -Perl_to_uni_upper_lc(pTHX_ U32 c) -{ - /* XXX returns only the first character -- do not use XXX */ - /* XXX no locale support yet */ - STRLEN len; - U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; - return (U32)to_uni_upper(c, tmpbuf, &len); -} - -U32 -Perl_to_uni_title_lc(pTHX_ U32 c) -{ - /* XXX returns only the first character XXX -- do not use XXX */ - /* XXX no locale support yet */ - STRLEN len; - U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; - return (U32)to_uni_title(c, tmpbuf, &len); -} - -U32 -Perl_to_uni_lower_lc(pTHX_ U32 c) -{ - /* XXX returns only the first character -- do not use XXX */ - /* XXX no locale support yet */ - STRLEN len; - U8 tmpbuf[UTF8_MAXBYTES_CASE+1]; - return (U32)to_uni_lower(c, tmpbuf, &len); -} - PERL_STATIC_INLINE bool S_is_utf8_common(pTHX_ const U8 *const p, SV **swash, const char *const swashname) @@ -2135,29 +1864,6 @@ Perl__is_utf8_FOO(pTHX_ const U8 classnum, const U8 *p) } bool -Perl_is_utf8_alnum(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_ALNUM; - - /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true - * descendant of isalnum(3), in other words, it doesn't - * contain the '_'. --jhi */ - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_WORDCHAR], "IsWord"); -} - -bool -Perl_is_utf8_alnumc(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_ALNUMC; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_ALPHANUMERIC], "IsAlnum"); -} - -bool Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */ { dVAR; @@ -2222,164 +1928,6 @@ Perl_is_utf8_xidcont(pTHX_ const U8 *p) } bool -Perl_is_utf8_alpha(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_ALPHA; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_ALPHA], "IsAlpha"); -} - -bool -Perl_is_utf8_ascii(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_ASCII; - - /* ASCII characters are the same whether in utf8 or not. So the macro - * works on both utf8 and non-utf8 representations. */ - return isASCII(*p); -} - -bool -Perl_is_utf8_blank(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_BLANK; - - return isBLANK_utf8(p); -} - -bool -Perl_is_utf8_space(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_SPACE; - - return isSPACE_utf8(p); -} - -bool -Perl_is_utf8_perl_space(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_PERL_SPACE; - - /* Only true if is an ASCII space-like character, and ASCII is invariant - * under utf8, so can just use the macro */ - return isSPACE_A(*p); -} - -bool -Perl_is_utf8_perl_word(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_PERL_WORD; - - /* Only true if is an ASCII word character, and ASCII is invariant - * under utf8, so can just use the macro */ - return isWORDCHAR_A(*p); -} - -bool -Perl_is_utf8_digit(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_DIGIT; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_DIGIT], "IsDigit"); -} - -bool -Perl_is_utf8_posix_digit(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_POSIX_DIGIT; - - /* Only true if is an ASCII digit character, and ASCII is invariant - * under utf8, so can just use the macro */ - return isDIGIT_A(*p); -} - -bool -Perl_is_utf8_upper(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_UPPER; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_UPPER], "IsUppercase"); -} - -bool -Perl_is_utf8_lower(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_LOWER; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_LOWER], "IsLowercase"); -} - -bool -Perl_is_utf8_cntrl(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_CNTRL; - - return isCNTRL_utf8(p); -} - -bool -Perl_is_utf8_graph(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_GRAPH; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_GRAPH], "IsGraph"); -} - -bool -Perl_is_utf8_print(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_PRINT; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_PRINT], "IsPrint"); -} - -bool -Perl_is_utf8_punct(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_PUNCT; - - return is_utf8_common(p, &PL_utf8_swash_ptrs[_CC_PUNCT], "IsPunct"); -} - -bool -Perl_is_utf8_xdigit(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_XDIGIT; - - return is_XDIGIT_utf8(p); -} - -bool Perl__is_utf8_mark(pTHX_ const U8 *p) { dVAR; @@ -2389,17 +1937,6 @@ Perl__is_utf8_mark(pTHX_ const U8 *p) return is_utf8_common(p, &PL_utf8_mark, "IsM"); } - -bool -Perl_is_utf8_mark(pTHX_ const U8 *p) -{ - dVAR; - - PERL_ARGS_ASSERT_IS_UTF8_MARK; - - return _is_utf8_mark(p); -} - /* =for apidoc to_utf8_case -- Perl5 Master Repository
