EBCDIC sanity - phase I

 - rename utf8/uv functions to indicate what sort of uv they provide (uvuni/uvchr)
 - use utf8n_xxxx (c.f. pvn) for forms which take length.
 - back out vN.N and $^V exceptions to e2a/a2e
 - make "locale" isxxx macros be uvchr (may be redundant?)

Not clear yet that toUPPER_uni et. al. return being handled correctly.
The tr// and rexexp stuff still needs an audit, assumption is they are working
in Unicode space.

Need to provide v5.6 names for XS modules (decide is uni or chr ?).

p4raw-id: //depot/perlio@9096

1 files changed, 30 insertions, 30 deletions

diff --git a/handy.h b/handy.h
index 1f1cc531bb..99cb5c6e74 100644
--- a/handy.h
+++ b/handy.h
@@ -423,21 +423,21 @@ Converts the specified character to lowercase.
 #define isPSXSPC_uni(c)		(isSPACE_uni(c) ||(c) == '\f')
 #define isBLANK_uni(c)		isBLANK(c) /* could be wrong */
 
-#define isALNUM_LC_uni(c)	(c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c))
-#define isIDFIRST_LC_uni(c)	(c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c))
-#define isALPHA_LC_uni(c)	(c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c))
-#define isSPACE_LC_uni(c)	(c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c))
-#define isDIGIT_LC_uni(c)	(c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c))
-#define isUPPER_LC_uni(c)	(c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c))
-#define isLOWER_LC_uni(c)	(c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c))
-#define isALNUMC_LC_uni(c)	(c < 256 ? isALNUMC_LC(c) : is_uni_alnumc_lc(c))
-#define isCNTRL_LC_uni(c)	(c < 256 ? isCNTRL_LC(c) : is_uni_cntrl_lc(c))
-#define isGRAPH_LC_uni(c)	(c < 256 ? isGRAPH_LC(c) : is_uni_graph_lc(c))
-#define isPRINT_LC_uni(c)	(c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c))
-#define isPUNCT_LC_uni(c)	(c < 256 ? isPUNCT_LC(c) : is_uni_punct_lc(c))
-#define toUPPER_LC_uni(c)	(c < 256 ? toUPPER_LC(c) : to_uni_upper_lc(c))
-#define toTITLE_LC_uni(c)	(c < 256 ? toUPPER_LC(c) : to_uni_title_lc(c))
-#define toLOWER_LC_uni(c)	(c < 256 ? toLOWER_LC(c) : to_uni_lower_lc(c))
+#define isALNUM_LC_uvchr(c)	(c < 256 ? isALNUM_LC(c) : is_uni_alnum_lc(c))
+#define isIDFIRST_LC_uvchr(c)	(c < 256 ? isIDFIRST_LC(c) : is_uni_idfirst_lc(c))
+#define isALPHA_LC_uvchr(c)	(c < 256 ? isALPHA_LC(c) : is_uni_alpha_lc(c))
+#define isSPACE_LC_uvchr(c)	(c < 256 ? isSPACE_LC(c) : is_uni_space_lc(c))
+#define isDIGIT_LC_uvchr(c)	(c < 256 ? isDIGIT_LC(c) : is_uni_digit_lc(c))
+#define isUPPER_LC_uvchr(c)	(c < 256 ? isUPPER_LC(c) : is_uni_upper_lc(c))
+#define isLOWER_LC_uvchr(c)	(c < 256 ? isLOWER_LC(c) : is_uni_lower_lc(c))
+#define isALNUMC_LC_uvchr(c)	(c < 256 ? isALNUMC_LC(c) : is_uni_alnumc_lc(c))
+#define isCNTRL_LC_uvchr(c)	(c < 256 ? isCNTRL_LC(c) : is_uni_cntrl_lc(c))
+#define isGRAPH_LC_uvchr(c)	(c < 256 ? isGRAPH_LC(c) : is_uni_graph_lc(c))
+#define isPRINT_LC_uvchr(c)	(c < 256 ? isPRINT_LC(c) : is_uni_print_lc(c))
+#define isPUNCT_LC_uvchr(c)	(c < 256 ? isPUNCT_LC(c) : is_uni_punct_lc(c))
+#define toUPPER_LC_uvchr(c)	(c < 256 ? toUPPER_LC(c) : to_uni_upper_lc(c))
+#define toTITLE_LC_uvchr(c)	(c < 256 ? toUPPER_LC(c) : to_uni_title_lc(c))
+#define toLOWER_LC_uvchr(c)	(c < 256 ? toLOWER_LC(c) : to_uni_lower_lc(c))
 
 #define isPSXSPC_LC_uni(c)	(isSPACE_LC_uni(c) ||(c) == '\f')
 #define isBLANK_LC_uni(c)	isBLANK(c) /* could be wrong */
@@ -463,21 +463,21 @@ Converts the specified character to lowercase.
 #define isPSXSPC_utf8(c)	(isSPACE_utf8(c) ||(c) == '\f')
 #define isBLANK_utf8(c)		isBLANK(c) /* could be wrong */
 
-#define isALNUM_LC_utf8(p)	isALNUM_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isIDFIRST_LC_utf8(p)	isIDFIRST_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isALPHA_LC_utf8(p)	isALPHA_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isSPACE_LC_utf8(p)	isSPACE_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isDIGIT_LC_utf8(p)	isDIGIT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isUPPER_LC_utf8(p)	isUPPER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isLOWER_LC_utf8(p)	isLOWER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isALNUMC_LC_utf8(p)	isALNUMC_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isCNTRL_LC_utf8(p)	isCNTRL_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isGRAPH_LC_utf8(p)	isGRAPH_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isPRINT_LC_utf8(p)	isPRINT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define isPUNCT_LC_utf8(p)	isPUNCT_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define toUPPER_LC_utf8(p)	toUPPER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define toTITLE_LC_utf8(p)	toTITLE_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
-#define toLOWER_LC_utf8(p)	toLOWER_LC_uni(utf8_to_uv(p, UTF8_MAXLEN, 0, 0))
+#define isALNUM_LC_utf8(p)	isALNUM_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isIDFIRST_LC_utf8(p)	isIDFIRST_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isALPHA_LC_utf8(p)	isALPHA_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isSPACE_LC_utf8(p)	isSPACE_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isDIGIT_LC_utf8(p)	isDIGIT_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isUPPER_LC_utf8(p)	isUPPER_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isLOWER_LC_utf8(p)	isLOWER_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isALNUMC_LC_utf8(p)	isALNUMC_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isCNTRL_LC_utf8(p)	isCNTRL_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isGRAPH_LC_utf8(p)	isGRAPH_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isPRINT_LC_utf8(p)	isPRINT_LC_uvchr(utf8_to_uvchr(p,  0))
+#define isPUNCT_LC_utf8(p)	isPUNCT_LC_uvchr(utf8_to_uvchr(p,  0))
+#define toUPPER_LC_utf8(p)	toUPPER_LC_uvchr(utf8_to_uvchr(p,  0))
+#define toTITLE_LC_utf8(p)	toTITLE_LC_uvchr(utf8_to_uvchr(p,  0))
+#define toLOWER_LC_utf8(p)	toLOWER_LC_uvchr(utf8_to_uvchr(p,  0))
 
 #define isPSXSPC_LC_utf8(c)	(isSPACE_LC_utf8(c) ||(c) == '\f')
 #define isBLANK_LC_utf8(c)	isBLANK(c) /* could be wrong */