/* This is a helper macro to avoid preprocessor issues, replaced by nothing
* unless under DEBUGGING, where it expands to an assert of its argument,
* followed by a comma (hence the comma operator). If we just used a straight
- * assert(), we would get a comma with nothing before it when not DEBUGGING */
-#ifdef DEBUGGING
+ * assert(), we would get a comma with nothing before it when not DEBUGGING.
+ *
+ * We also use empty definition under Coverity since the __ASSERT__
+ * checks often check for things that Really Cannot Happen, and Coverity
+ * detects that and gets all excited. */
+
+#if defined(DEBUGGING) && !defined(__COVERITY__)
# define __ASSERT_(statement) assert(statement),
#else
# define __ASSERT_(statement)
=head1 SV-Body Allocation
=for apidoc Ama|SV*|newSVpvs|const char* s
-Like C<newSVpvn>, but takes a literal C<NUL>-terminated string instead of a
+Like C<newSVpvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|SV*|newSVpvs_flags|const char* s|U32 flags
-Like C<newSVpvn_flags>, but takes a literal C<NUL>-terminated string instead of
+Like C<newSVpvn_flags>, but takes a C<NUL>-terminated literal string instead of
a string/length pair.
=for apidoc Ama|SV*|newSVpvs_share|const char* s
-Like C<newSVpvn_share>, but takes a literal C<NUL>-terminated string instead of
+Like C<newSVpvn_share>, but takes a C<NUL>-terminated literal string instead of
a string/length pair and omits the hash parameter.
=for apidoc Am|void|sv_catpvs_flags|SV* sv|const char* s|I32 flags
-Like C<sv_catpvn_flags>, but takes a literal C<NUL>-terminated string instead
+Like C<sv_catpvn_flags>, but takes a C<NUL>-terminated literal string instead
of a string/length pair.
=for apidoc Am|void|sv_catpvs_nomg|SV* sv|const char* s
-Like C<sv_catpvn_nomg>, but takes a literal string instead of a
-string/length pair.
+Like C<sv_catpvn_nomg>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=for apidoc Am|void|sv_catpvs|SV* sv|const char* s
-Like C<sv_catpvn>, but takes a literal string instead of a string/length pair.
+Like C<sv_catpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|void|sv_catpvs_mg|SV* sv|const char* s
-Like C<sv_catpvn_mg>, but takes a literal string instead of a
+Like C<sv_catpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|void|sv_setpvs|SV* sv|const char* s
-Like C<sv_setpvn>, but takes a literal string instead of a string/length pair.
+Like C<sv_setpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|void|sv_setpvs_mg|SV* sv|const char* s
-Like C<sv_setpvn_mg>, but takes a literal string instead of a
+Like C<sv_setpvn_mg>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Am|SV *|sv_setref_pvs|const char* s
-Like C<sv_setref_pvn>, but takes a literal string instead of a
-string/length pair.
+Like C<sv_setref_pvn>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=head1 Memory Management
=for apidoc Ama|char*|savepvs|const char* s
-Like C<savepvn>, but takes a literal C<NUL>-terminated string instead of a
+Like C<savepvn>, but takes a C<NUL>-terminated literal string instead of a
string/length pair.
=for apidoc Ama|char*|savesharedpvs|const char* s
=head1 GV Functions
=for apidoc Am|HV*|gv_stashpvs|const char* name|I32 create
-Like C<gv_stashpvn>, but takes a literal string instead of a string/length pair.
+Like C<gv_stashpvn>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=head1 Hash Manipulation Functions
=for apidoc Am|SV**|hv_fetchs|HV* tb|const char* key|I32 lval
-Like C<hv_fetch>, but takes a literal string instead of a string/length pair.
+Like C<hv_fetch>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair.
=for apidoc Am|SV**|hv_stores|HV* tb|const char* key|NULLOK SV* val
-Like C<hv_store>, but takes a literal string instead of a string/length pair
+Like C<hv_store>, but takes a C<NUL>-terminated literal string instead of a
+string/length pair
and omits the hash parameter.
=head1 Lexer interface
=for apidoc Amx|void|lex_stuff_pvs|const char *pv|U32 flags
-Like L</lex_stuff_pvn>, but takes a literal string instead of a
-string/length pair.
+Like L</lex_stuff_pvn>, but takes a C<NUL>-terminated literal string instead of
+a string/length pair.
=cut
*/
=head1 Miscellaneous Functions
=for apidoc Am|bool|strNE|char* s1|char* s2
-Test two strings to see if they are different. Returns true or
-false.
+Test two C<NUL>-terminated strings to see if they are different. Returns true
+or false.
=for apidoc Am|bool|strEQ|char* s1|char* s2
-Test two strings to see if they are equal. Returns true or false.
+Test two C<NUL>-terminated strings to see if they are equal. Returns true or
+false.
=for apidoc Am|bool|strLT|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is less than the second,
-C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than the
+second, C<s2>. Returns true or false.
=for apidoc Am|bool|strLE|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is less than or equal to the
-second, C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is less than or
+equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGT|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is greater than the second,
-C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
+the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strGE|char* s1|char* s2
-Test two strings to see if the first, C<s1>, is greater than or equal to
-the second, C<s2>. Returns true or false.
+Test two C<NUL>-terminated strings to see if the first, C<s1>, is greater than
+or equal to the second, C<s2>. Returns true or false.
=for apidoc Am|bool|strnNE|char* s1|char* s2|STRLEN len
-Test two strings to see if they are different. The C<len> parameter
-indicates the number of bytes to compare. Returns true or false. (A
+Test two C<NUL>-terminated strings to see if they are different. The C<len>
+parameter indicates the number of bytes to compare. Returns true or false. (A
wrapper for C<strncmp>).
=for apidoc Am|bool|strnEQ|char* s1|char* s2|STRLEN len
-Test two strings to see if they are equal. The C<len> parameter indicates
-the number of bytes to compare. Returns true or false. (A wrapper for
-C<strncmp>).
+Test two C<NUL>-terminated strings to see if they are equal. The C<len>
+parameter indicates the number of bytes to compare. Returns true or false. (A
+wrapper for C<strncmp>).
=for apidoc Am|bool|memEQ|char* s1|char* s2|STRLEN len
Test two buffers (which may contain embedded C<NUL> characters, to see if they
true when called with the code point 0xDF, which is a word character in both
ASCII and EBCDIC (though it represents different characters in each).
-Variant C<isFOO_uni> is like the C<isFOO_L1> variant, but accepts any UV code
+Variant C<isFOO_uvchr> is like the C<isFOO_L1> variant, but accepts any UV code
point as input. If the code point is larger than 255, Unicode rules are used
to determine if it is in the character class. For example,
-C<isWORDCHAR_uni(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
+C<isWORDCHAR_uvchr(0x100)> returns TRUE, since 0x100 is LATIN CAPITAL LETTER A
WITH MACRON in Unicode, and is a word character.
-Variant C<isFOO_utf8> is like C<isFOO_uni>, but the input is a pointer to a
-(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
-classification of just the first (possibly multi-byte) character in the string
-is tested.
+Variant C<isFOO_utf8> is like C<isFOO_uvchr>, but the input is a pointer to a
+(known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
+possibly containing embedded C<NUL> characters). The classification of just
+the first (possibly multi-byte) character in the string is tested.
Variant C<isFOO_LC> is like the C<isFOO_A> and C<isFOO_L1> variants, but the
result is based on the current locale, which is what C<LC> in the name stands
returns the hard-coded, not-affected-by-locale, Unicode results for larger ones.
Variant C<isFOO_LC_utf8> is like C<isFOO_LC_uvchr>, but the input is a pointer
-to a (known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>). The
-classification of just the first (possibly multi-byte) character in the string
-is tested.
+to a (known to be well-formed) UTF-8 encoded string (C<U8*> or C<char*>, and
+possibly containing embedded C<NUL> characters). The classification of just
+the first (possibly multi-byte) character in the string is tested.
=for apidoc Am|bool|isALPHA|char ch
Returns a boolean indicating whether the specified character is an
alphabetic character, analogous to C<m/[[:alpha:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uni>, C<isALPHA_utf8>, C<isALPHA_LC>,
+C<isALPHA_A>, C<isALPHA_L1>, C<isALPHA_uvchr>, C<isALPHA_utf8>, C<isALPHA_LC>,
C<isALPHA_LC_uvchr>, and C<isALPHA_LC_utf8>.
=for apidoc Am|bool|isALPHANUMERIC|char ch
alphabetic character or decimal digit, analogous to C<m/[[:alnum:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uni>,
+C<isALPHANUMERIC_A>, C<isALPHANUMERIC_L1>, C<isALPHANUMERIC_uvchr>,
C<isALPHANUMERIC_utf8>, C<isALPHANUMERIC_LC>, C<isALPHANUMERIC_LC_uvchr>, and
C<isALPHANUMERIC_LC_utf8>.
C<isASCII_L1()> are identical to C<isASCII()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isASCII_uni>, C<isASCII_utf8>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
+C<isASCII_uvchr>, C<isASCII_utf8>, C<isASCII_LC>, C<isASCII_LC_uvchr>, and
C<isASCII_LC_utf8>. Note, however, that some platforms do not have the C
library routine C<isascii()>. In these cases, the variants whose names contain
C<LC> are the same as the corresponding ones without.
character considered to be a blank, analogous to C<m/[[:blank:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uni>, C<isBLANK_utf8>, C<isBLANK_LC>,
+C<isBLANK_A>, C<isBLANK_L1>, C<isBLANK_uvchr>, C<isBLANK_utf8>, C<isBLANK_LC>,
C<isBLANK_LC_uvchr>, and C<isBLANK_LC_utf8>. Note, however, that some
platforms do not have the C library routine C<isblank()>. In these cases, the
variants whose names contain C<LC> are the same as the corresponding ones
control character, analogous to C<m/[[:cntrl:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uni>, C<isCNTRL_utf8>, C<isCNTRL_LC>,
+C<isCNTRL_A>, C<isCNTRL_L1>, C<isCNTRL_uvchr>, C<isCNTRL_utf8>, C<isCNTRL_LC>,
C<isCNTRL_LC_uvchr>, and C<isCNTRL_LC_utf8>
On EBCDIC platforms, you almost always want to use the C<isCNTRL_L1> variant.
Variants C<isDIGIT_A> and C<isDIGIT_L1> are identical to C<isDIGIT>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isDIGIT_uni>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
+C<isDIGIT_uvchr>, C<isDIGIT_utf8>, C<isDIGIT_LC>, C<isDIGIT_LC_uvchr>, and
C<isDIGIT_LC_utf8>.
=for apidoc Am|bool|isGRAPH|char ch
graphic character, analogous to C<m/[[:graph:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uni>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
+C<isGRAPH_A>, C<isGRAPH_L1>, C<isGRAPH_uvchr>, C<isGRAPH_utf8>, C<isGRAPH_LC>,
C<isGRAPH_LC_uvchr>, and C<isGRAPH_LC_utf8>.
=for apidoc Am|bool|isLOWER|char ch
lowercase character, analogous to C<m/[[:lower:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uni>, C<isLOWER_utf8>, C<isLOWER_LC>,
+C<isLOWER_A>, C<isLOWER_L1>, C<isLOWER_uvchr>, C<isLOWER_utf8>, C<isLOWER_LC>,
C<isLOWER_LC_uvchr>, and C<isLOWER_LC_utf8>.
=for apidoc Am|bool|isOCTAL|char ch
Classes> for details.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uni>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
+C<isPUNCT_A>, C<isPUNCT_L1>, C<isPUNCT_uvchr>, C<isPUNCT_utf8>, C<isPUNCT_LC>,
C<isPUNCT_LC_uvchr>, and C<isPUNCT_LC_utf8>.
=for apidoc Am|bool|isSPACE|char ch
(See L</isPSXSPC> for a macro that matches a vertical tab in all releases.)
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uni>, C<isSPACE_utf8>, C<isSPACE_LC>,
+C<isSPACE_A>, C<isSPACE_L1>, C<isSPACE_uvchr>, C<isSPACE_utf8>, C<isSPACE_LC>,
C<isSPACE_LC_uvchr>, and C<isSPACE_LC_utf8>.
=for apidoc Am|bool|isPSXSPC|char ch
Otherwise they are identical. Thus this macro is analogous to what
C<m/[[:space:]]/> matches in a regular expression.
See the L<top of this section|/Character classification> for an explanation of
-variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uni>, C<isPSXSPC_utf8>,
+variants C<isPSXSPC_A>, C<isPSXSPC_L1>, C<isPSXSPC_uvchr>, C<isPSXSPC_utf8>,
C<isPSXSPC_LC>, C<isPSXSPC_LC_uvchr>, and C<isPSXSPC_LC_utf8>.
=for apidoc Am|bool|isUPPER|char ch
uppercase character, analogous to C<m/[[:upper:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uni>, C<isUPPER_utf8>, C<isUPPER_LC>,
+C<isUPPER_A>, C<isUPPER_L1>, C<isUPPER_uvchr>, C<isUPPER_utf8>, C<isUPPER_LC>,
C<isUPPER_LC_uvchr>, and C<isUPPER_LC_utf8>.
=for apidoc Am|bool|isPRINT|char ch
printable character, analogous to C<m/[[:print:]]/>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uni>, C<isPRINT_utf8>, C<isPRINT_LC>,
+C<isPRINT_A>, C<isPRINT_L1>, C<isPRINT_uvchr>, C<isPRINT_utf8>, C<isPRINT_LC>,
C<isPRINT_LC_uvchr>, and C<isPRINT_LC_utf8>.
=for apidoc Am|bool|isWORDCHAR|char ch
alphanumeric.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uni>, and C<isWORDCHAR_utf8>.
+C<isWORDCHAR_A>, C<isWORDCHAR_L1>, C<isWORDCHAR_uvchr>, and C<isWORDCHAR_utf8>.
C<isWORDCHAR_LC>, C<isWORDCHAR_LC_uvchr>, and C<isWORDCHAR_LC_utf8> are also as
described there, but additionally include the platform's native underscore.
and C<isXDIGIT_L1()> are identical to C<isXDIGIT()>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isXDIGIT_uni>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
+C<isXDIGIT_uvchr>, C<isXDIGIT_utf8>, C<isXDIGIT_LC>, C<isXDIGIT_LC_uvchr>, and
C<isXDIGIT_LC_utf8>.
=for apidoc Am|bool|isIDFIRST|char ch
returns true only if the input character also matches L</isWORDCHAR>.
See the L<top of this section|/Character classification> for an explanation of
variants
-C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uni>, C<isIDFIRST_utf8>,
+C<isIDFIRST_A>, C<isIDFIRST_L1>, C<isIDFIRST_uvchr>, C<isIDFIRST_utf8>,
C<isIDFIRST_LC>, C<isIDFIRST_LC_uvchr>, and C<isIDFIRST_LC_utf8>.
=for apidoc Am|bool|isIDCONT|char ch
difference is that this returns true only if the input character also matches
L</isWORDCHAR>. See the L<top of this section|/Character classification> for
an
-explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uni>,
+explanation of variants C<isIDCONT_A>, C<isIDCONT_L1>, C<isIDCONT_uvchr>,
C<isIDCONT_utf8>, C<isIDCONT_LC>, C<isIDCONT_LC_uvchr>, and
C<isIDCONT_LC_utf8>.
ASCII lowercase character, that input character itself is returned. Variant
C<toUPPER_A> is equivalent.
-=for apidoc Am|UV|toUPPER_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its uppercase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toUPPER_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its uppercase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
+point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the uppercase version may be longer than the original character.
Converts the specified character to foldcase. If the input is anything but an
ASCII uppercase character, that input character itself is returned. Variant
C<toFOLD_A> is equivalent. (There is no equivalent C<to_FOLD_L1> for the full
-Latin1 range, as the full generality of L</toFOLD_uni> is needed there.)
+Latin1 range, as the full generality of L</toFOLD_uvchr> is needed there.)
-=for apidoc Am|UV|toFOLD_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its foldcase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toFOLD_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its foldcase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
+point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the foldcase version may be longer than the original character.
Converts the specified character to lowercase using the current locale's rules,
if possible; otherwise returns the input character itself.
-=for apidoc Am|UV|toLOWER_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its lowercase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toLOWER_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its lowercase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
+point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the lowercase version may be longer than the original character.
Converts the specified character to titlecase. If the input is anything but an
ASCII lowercase character, that input character itself is returned. Variant
C<toTITLE_A> is equivalent. (There is no C<toTITLE_L1> for the full Latin1
-range, as the full generality of L</toTITLE_uni> is needed there. Titlecase is
+range, as the full generality of L</toTITLE_uvchr> is needed there. Titlecase is
not a concept used in locale handling, so there is no functionality for that.)
-=for apidoc Am|UV|toTITLE_uni|UV cp|U8* s|STRLEN* lenp
-Converts the Unicode code point C<cp> to its titlecase version, and
-stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. Note
+=for apidoc Am|UV|toTITLE_uvchr|UV cp|U8* s|STRLEN* lenp
+Converts the code point C<cp> to its titlecase version, and
+stores that in UTF-8 in C<s>, and its length in bytes in C<lenp>. The code
+point is interpreted as native if less than 256; otherwise as Unicode. Note
that the buffer pointed to by C<s> needs to be at least C<UTF8_MAXBYTES_CASE+1>
bytes since the titlecase version may be longer than the original character.
=cut
-XXX Still undocumented isVERTWS_uni and _utf8; it's unclear what their names
+XXX Still undocumented isVERTWS_uvchr and _utf8; it's unclear what their names
really should be. Also toUPPER_LC and toFOLD_LC, which are subject to change.
Note that these macros are repeated in Devel::PPPort, so should also be
* compiler to optimize it out if possible. This is because Configure makes
* sure that the machine has an 8-bit byte, so if c is stored in a byte, the
* sizeof() guarantees that this evaluates to a constant true at compile time.
+ *
+ * For Coverity, be always true, because otherwise Coverity thinks
+ * it finds several expressions that are always true, independent
+ * of operands. Well, they are, but that is kind of the point.
*/
+#ifndef __COVERITY__
#define FITS_IN_8_BITS(c) ((sizeof(c) == 1) || !(((WIDEST_UTYPE)(c)) & ~0xFF))
+#else
+#define FITS_IN_8_BITS(c) (1)
+#endif
#ifdef EBCDIC
# ifndef _ALL_SOURCE
#else
/* There is a simple definition of ASCII for ASCII platforms. But the
* EBCDIC one isn't so simple, so is defined using table look-up like the
- * other macros below */
-# define isASCII(c) ((WIDEST_UTYPE)(c) < 128)
+ * other macros below.
+ * The '| 0' part ensures that c is an integer (and not e.g. a pointer) */
+# define isASCII(c) ((WIDEST_UTYPE)((c) | 0) < 128)
#endif
/* The lower 3 bits in both the ASCII and EBCDIC representations of '0' are 0,
# define _CC_NON_FINAL_FOLD 21
# define _CC_IS_IN_SOME_FOLD 22
# define _CC_MNEMONIC_CNTRL 23
-/* Unused: 24-31
+
+/* This next group is only used on EBCDIC platforms, so theoretically could be
+ * shared with something entirely different that's only on ASCII platforms */
+# define _CC_UTF8_START_BYTE_IS_FOR_AT_LEAST_SURROGATE 28
+# define _CC_UTF8_IS_START 29
+# define _CC_UTF8_IS_DOWNGRADEABLE_START 30
+# define _CC_UTF8_IS_CONTINUATION 31
+/* Unused: 24-27
* If more bits are needed, one could add a second word for non-64bit
* QUAD_IS_INT systems, using some #ifdefs to distinguish between having a 2nd
* word or not. The IS_IN_SOME_FOLD bit is the most easily expendable, as it
* is used only for optimization (as of this writing), and differs in the
* Latin1 range from the ALPHA bit only in two relatively unimportant
* characters: the masculine and feminine ordinal indicators, so removing it
- * would just cause /i regexes which match them to run less efficiently */
+ * would just cause /i regexes which match them to run less efficiently.
+ * Similarly the EBCDIC-only bits are used just for speed, and could be
+ * replaced by other means */
#if defined(PERL_CORE) || defined(PERL_EXT)
/* An enum version of the character class numbers, to help compilers
#define isPSXSPC_LC(c) isSPACE_LC(c)
/* For internal core Perl use only: the base macros for defining macros like
- * isALPHA_uni. 'c' is the code point to check. 'classnum' is the POSIX class
- * number defined earlier in this file. _generic_uni() is used for POSIX
+ * isALPHA_uvchr. 'c' is the code point to check. 'classnum' is the POSIX class
+ * number defined earlier in this file. _generic_uvchr() is used for POSIX
* classes where there is a macro or function 'above_latin1' that takes the
* single argument 'c' and returns the desired value. These exist for those
* classes which have simple definitions, avoiding the overhead of a hash
- * lookup or inversion list binary search. _generic_swash_uni() can be used
+ * lookup or inversion list binary search. _generic_swash_uvchr() can be used
* for classes where that overhead is faster than a direct lookup.
- * _generic_uni() won't compile if 'c' isn't unsigned, as it won't match the
+ * _generic_uvchr() won't compile if 'c' isn't unsigned, as it won't match the
* 'above_latin1' prototype. _generic_isCC() macro does bounds checking, so
* have duplicate checks here, so could create versions of the macros that
* don't, but experiments show that gcc optimizes them out anyway. */
/* Note that all ignore 'use bytes' */
-#define _generic_uni(classnum, above_latin1, c) ((c) < 256 \
+#define _generic_uvchr(classnum, above_latin1, c) ((c) < 256 \
? _generic_isCC(c, classnum) \
: above_latin1(c))
-#define _generic_swash_uni(classnum, c) ((c) < 256 \
+#define _generic_swash_uvchr(classnum, c) ((c) < 256 \
? _generic_isCC(c, classnum) \
: _is_uni_FOO(classnum, c))
-#define isALPHA_uni(c) _generic_swash_uni(_CC_ALPHA, c)
-#define isALPHANUMERIC_uni(c) _generic_swash_uni(_CC_ALPHANUMERIC, c)
-#define isASCII_uni(c) isASCII(c)
-#define isBLANK_uni(c) _generic_uni(_CC_BLANK, is_HORIZWS_cp_high, c)
-#define isCNTRL_uni(c) isCNTRL_L1(c) /* All controls are in Latin1 */
-#define isDIGIT_uni(c) _generic_swash_uni(_CC_DIGIT, c)
-#define isGRAPH_uni(c) _generic_swash_uni(_CC_GRAPH, c)
-#define isIDCONT_uni(c) _generic_uni(_CC_WORDCHAR, _is_uni_perl_idcont, c)
-#define isIDFIRST_uni(c) _generic_uni(_CC_IDFIRST, _is_uni_perl_idstart, c)
-#define isLOWER_uni(c) _generic_swash_uni(_CC_LOWER, c)
-#define isPRINT_uni(c) _generic_swash_uni(_CC_PRINT, c)
-
-#define isPUNCT_uni(c) _generic_swash_uni(_CC_PUNCT, c)
-#define isSPACE_uni(c) _generic_uni(_CC_SPACE, is_XPERLSPACE_cp_high, c)
-#define isPSXSPC_uni(c) isSPACE_uni(c)
-
-#define isUPPER_uni(c) _generic_swash_uni(_CC_UPPER, c)
-#define isVERTWS_uni(c) _generic_uni(_CC_VERTSPACE, is_VERTWS_cp_high, c)
-#define isWORDCHAR_uni(c) _generic_swash_uni(_CC_WORDCHAR, c)
-#define isXDIGIT_uni(c) _generic_uni(_CC_XDIGIT, is_XDIGIT_cp_high, c)
-
-#define toFOLD_uni(c,s,l) to_uni_fold(c,s,l)
-#define toLOWER_uni(c,s,l) to_uni_lower(c,s,l)
-#define toTITLE_uni(c,s,l) to_uni_title(c,s,l)
-#define toUPPER_uni(c,s,l) to_uni_upper(c,s,l)
+#define isALPHA_uvchr(c) _generic_swash_uvchr(_CC_ALPHA, c)
+#define isALPHANUMERIC_uvchr(c) _generic_swash_uvchr(_CC_ALPHANUMERIC, c)
+#define isASCII_uvchr(c) isASCII(c)
+#define isBLANK_uvchr(c) _generic_uvchr(_CC_BLANK, is_HORIZWS_cp_high, c)
+#define isCNTRL_uvchr(c) isCNTRL_L1(c) /* All controls are in Latin1 */
+#define isDIGIT_uvchr(c) _generic_swash_uvchr(_CC_DIGIT, c)
+#define isGRAPH_uvchr(c) _generic_swash_uvchr(_CC_GRAPH, c)
+#define isIDCONT_uvchr(c) _generic_uvchr(_CC_WORDCHAR, _is_uni_perl_idcont, c)
+#define isIDFIRST_uvchr(c) _generic_uvchr(_CC_IDFIRST, _is_uni_perl_idstart, c)
+#define isLOWER_uvchr(c) _generic_swash_uvchr(_CC_LOWER, c)
+#define isPRINT_uvchr(c) _generic_swash_uvchr(_CC_PRINT, c)
+
+#define isPUNCT_uvchr(c) _generic_swash_uvchr(_CC_PUNCT, c)
+#define isSPACE_uvchr(c) _generic_uvchr(_CC_SPACE, is_XPERLSPACE_cp_high, c)
+#define isPSXSPC_uvchr(c) isSPACE_uvchr(c)
+
+#define isUPPER_uvchr(c) _generic_swash_uvchr(_CC_UPPER, c)
+#define isVERTWS_uvchr(c) _generic_uvchr(_CC_VERTSPACE, is_VERTWS_cp_high, c)
+#define isWORDCHAR_uvchr(c) _generic_swash_uvchr(_CC_WORDCHAR, c)
+#define isXDIGIT_uvchr(c) _generic_uvchr(_CC_XDIGIT, is_XDIGIT_cp_high, c)
+
+#define toFOLD_uvchr(c,s,l) to_uni_fold(c,s,l)
+#define toLOWER_uvchr(c,s,l) to_uni_lower(c,s,l)
+#define toTITLE_uvchr(c,s,l) to_uni_title(c,s,l)
+#define toUPPER_uvchr(c,s,l) to_uni_upper(c,s,l)
+
+/* For backwards compatibility, even though '_uni' should mean official Unicode
+ * code points, in Perl it means native for those below 256 */
+#define isALPHA_uni(c) isALPHA_uvchr(c)
+#define isALPHANUMERIC_uni(c) isALPHANUMERIC_uvchr(c)
+#define isASCII_uni(c) isASCII_uvchr(c)
+#define isBLANK_uni(c) isBLANK_uvchr(c)
+#define isCNTRL_uni(c) isCNTRL_uvchr(c)
+#define isDIGIT_uni(c) isDIGIT_uvchr(c)
+#define isGRAPH_uni(c) isGRAPH_uvchr(c)
+#define isIDCONT_uni(c) isIDCONT_uvchr(c)
+#define isIDFIRST_uni(c) isIDFIRST_uvchr(c)
+#define isLOWER_uni(c) isLOWER_uvchr(c)
+#define isPRINT_uni(c) isPRINT_uvchr(c)
+#define isPUNCT_uni(c) isPUNCT_uvchr(c)
+#define isSPACE_uni(c) isSPACE_uvchr(c)
+#define isPSXSPC_uni(c) isPSXSPC_uvchr(c)
+#define isUPPER_uni(c) isUPPER_uvchr(c)
+#define isVERTWS_uni(c) isVERTWS_uvchr(c)
+#define isWORDCHAR_uni(c) isWORDCHAR_uvchr(c)
+#define isXDIGIT_uni(c) isXDIGIT_uvchr(c)
+#define toFOLD_uni(c,s,l) toFOLD_uvchr(c,s,l)
+#define toLOWER_uni(c,s,l) toLOWER_uvchr(c,s,l)
+#define toTITLE_uni(c,s,l) toTITLE_uvchr(c,s,l)
+#define toUPPER_uni(c,s,l) toUPPER_uvchr(c,s,l)
/* For internal core Perl use only: the base macros for defining macros like
* isALPHA_LC_uvchr. These are like isALPHA_LC, but the input can be any code
- * point, not just 0-255. Like _generic_uni, there are two versions, one for
+ * point, not just 0-255. Like _generic_uvchr, there are two versions, one for
* simple class definitions; the other for more complex. These are like
- * _generic_uni, so see it for more info. */
+ * _generic_uvchr, so see it for more info. */
#define _generic_LC_uvchr(latin1, above_latin1, c) \
(c < 256 ? latin1(c) : above_latin1(c))
#define _generic_LC_swash_uvchr(latin1, classnum, c) \
=for apidoc Am|void|Newx|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<malloc> function.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
In 5.9.3, Newx() and friends replace the older New() API, and drops
the first parameter, I<x>, a debug aid which allowed callers to identify
The XSUB-writer's interface to the C C<malloc> function, with
cast. See also C<L</Newx>>.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Newxz|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<malloc> function. The allocated
memory is zeroed with C<memzero>. See also C<L</Newx>>.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Renew|void* ptr|int nitems|type
The XSUB-writer's interface to the C C<realloc> function.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Renewc|void* ptr|int nitems|type|cast
The XSUB-writer's interface to the C C<realloc> function, with
cast.
-Memory obtained by this should B<ONLY> be freed with L<"Safefree">.
+Memory obtained by this should B<ONLY> be freed with L</"Safefree">.
=for apidoc Am|void|Safefree|void* ptr
The XSUB-writer's interface to the C C<free> function.
-This should B<ONLY> be used on memory obtained using L<"Newx"> and friends.
+This should B<ONLY> be used on memory obtained using L</"Newx"> and friends.
=for apidoc Am|void|Move|void* src|void* dest|int nitems|type
The XSUB-writer's interface to the C C<memmove> function. The C<src> is the
* As well as avoiding the need for a run-time check in some cases, it's
* designed to avoid compiler warnings like:
* comparison is always false due to limited range of data type
+ * It's mathematically equivalent to
+ * max(n) * sizeof(t) > MEM_SIZE_MAX
*/
# define _MEM_WRAP_NEEDS_RUNTIME_CHECK(n,t) \
- (sizeof(t) > ((MEM_SIZE)1 << 8*(sizeof(MEM_SIZE) - sizeof(n))))
+ (8 * sizeof(n) + sizeof(t) > sizeof(MEM_SIZE))
/* This is written in a slightly odd way to avoid various spurious
* compiler warnings. We *want* to write the expression as
* - lots of ENV reads
*/
-PERL_CALLCONV Malloc_t Perl_mem_log_alloc(const UV n, const UV typesize, const char *type_name, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-
-PERL_CALLCONV Malloc_t Perl_mem_log_realloc(const UV n, const UV typesize, const char *type_name, Malloc_t oldalloc, Malloc_t newalloc, const char *filename, const int linenumber, const char *funcname);
-
-PERL_CALLCONV Malloc_t Perl_mem_log_free(Malloc_t oldalloc, const char *filename, const int linenumber, const char *funcname);
-
# ifdef PERL_CORE
# ifndef PERL_MEM_LOG_NOIMPL
enum mem_log_type {
https://perl5.git.perl.org / perl5.git / blobdiff