mirror/perl
1
0
Fork 0
mirror of https://github.com/Perl/perl5.git synced 2026-01-26 08:38:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add class for underscore character to l1_char_class_tab.h

Browse Source 
l1_char_class_tab.h categorizes characters in the Latin1 range into
various classes, mostly into the POSIX classes like [:word:].  Each
character has a bit set corresponding to every class it is a member of.
These values are placed in a 256-element array and the ordinal value of
a character is used as an index into it for quick determination of if a
character is a member of a given class.

Besides the POSIX classes, there are some classes that make it more
convenient and/or faster for our code.  For example, there is a class
that allows us to quickly know if a given character is one that needs to
be preceded by a backslash by quotemeta().

This commit adds a class for the single character underscore '_', and a
macro that allows for seeing if a character is either an underscore or a
member of any other class, using a single conditional.

This means code that checks for if character X is either an underscore
or a member of class Y can change to eliminate one conditional.

Thus the reason to do this is efficiency.  Currently, the only places
that do this explicitly are in non-hot code.  But I have wip that has
hot code that could benefit from this.

The only downside of doing this is that it uses up one bit of the 32
available (without shenanigans) for such classes, leaving 4 spare.  But
before this release, the last time any new bit had been used up was
5.32, so the rate of using these spare up is quite low.

This bit could be reclaimed because the IDFIRST class in the Latin1
range is identical to ALPHA plus the underscore, so it could be
rewritten as that combination and its bit freed up.  However, this would
require adding some macros that take two class parameters instead of
one.  I briefly thought about doing that now, but since we have spare
bits and the rate of using them up is low, I didn't think it was worth
it at this time.

\w in this range is ALPHANUMERIC plus underscore.  But its use is more
embedded than IDFIRST is, so an attempt to reclaim its bit would require
more effort.
This commit is contained in:
Karl Williamson 2026-01-08 10:43:12 -07:00 committed by Karl Williamson
parent b116971bb0
commit 31c9996116
8 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
charclass_invlists.inc
View File

@ -492661,6 +492661,6 @@ static const U8 WB_dfa_table[] = {
* 03640d8ad18fc65de766f2034a927f7442960e998d3243845ca9b9fe31bfe1ab lib/unicore/mktables
* 8c30575264b2772c7a69c5bb6069a28f0e0a7a0df735871bde2d99ee674316ac lib/unicore/version
* 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl
* 6c52efdee47313cfde75ff86376008ce53320ebc93176caab45c77ce086a256d regen/mk_PL_charclass.pl
* 8abaee16c84c1a61a69a77b6e8963675d99f515f3c2a34e449faeb9bfdec861a regen/mk_PL_charclass.pl
* 20a6e3d507a66f4594586485568134873485b08e23383f3dc4e6b3047569267b regen/mk_invlists.pl
* ex: set ro ft=c: */

2
embed.h
View File

@ -281,6 +281,8 @@
# undef case_98_SBOX32
# undef case_99_SBOX32
# undef case_9_SBOX32
# undef CC_UNDERSCORE_
# undef isFOO_or_UNDERSCORE_
# undef IV_BITS
# undef USE_STDIO
# undef UV_BITS

7
handy.h
View File

@ -1550,8 +1550,9 @@ or casts
# define CC_OCTDIGIT_ 24
# define CC_MNEMONIC_CNTRL_ 25
# define CC_MAGICAL_ 26
# define CC_UNDERSCORE_ 27
/* Unused: 27-31
/* Unused: 28-31
* 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
@ -1660,6 +1661,10 @@ END_EXTERN_C
# define isWORDCHAR_L1(c) generic_isCC_(c, CC_WORDCHAR_)
# define isIDFIRST_L1(c) generic_isCC_(c, CC_IDFIRST_)
#define isFOO_or_UNDERSCORE_(c, lookup_bit) \
(FITS_IN_8_BITS(c) && ( PL_charclass[(U8) (c)] \
& (CC_mask_(lookup_bit)|CC_mask_(CC_UNDERSCORE_))))
# ifdef EBCDIC
# define isASCII(c) generic_isCC_(c, CC_ASCII_)
# endif

6
l1_char_class_tab.h
View File

@ -103,7 +103,7 @@
/* U+5C '\' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* U+5D ']' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* U+5E '^' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_WORDCHAR_),
/* U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_UNDERSCORE_)|(1U<<CC_WORDCHAR_),
/* U+60 '`' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* U+61 'a' */ (1U<<CC_ALPHA_)|(1U<<CC_ALPHANUMERIC_)|(1U<<CC_ASCII_)|(1U<<CC_CASED_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_IS_IN_SOME_FOLD_)|(1U<<CC_LOWER_)|(1U<<CC_MAGICAL_)|(1U<<CC_NONLATIN1_FOLD_)|(1U<<CC_NON_FINAL_FOLD_)|(1U<<CC_PRINT_)|(1U<<CC_WORDCHAR_)|(1U<<CC_XDIGIT_),
/* U+62 'b' */ (1U<<CC_ALPHA_)|(1U<<CC_ALPHANUMERIC_)|(1U<<CC_ASCII_)|(1U<<CC_CASED_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_IS_IN_SOME_FOLD_)|(1U<<CC_LOWER_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_WORDCHAR_)|(1U<<CC_XDIGIT_),
@ -380,7 +380,7 @@
/* 0x6A U+A6 I8=BB BROKEN BAR */ (1U<<CC_GRAPH_)|(1U<<CC_PRINT_)|(1U<<CC_QUOTEMETA_),
/* 0x6B U+2C ',' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6C U+25 '%' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6D U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_WORDCHAR_),
/* 0x6D U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_UNDERSCORE_)|(1U<<CC_WORDCHAR_),
/* 0x6E U+3E '>' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6F U+3F '?' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x70 U+F8 I8=BC o with '/' */ (1U<<CC_ALPHA_)|(1U<<CC_ALPHANUMERIC_)|(1U<<CC_CASED_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_IS_IN_SOME_FOLD_)|(1U<<CC_LOWER_)|(1U<<CC_PRINT_)|(1U<<CC_WORDCHAR_),
@ -643,7 +643,7 @@
/* 0x6A U+A6 I8=BC BROKEN BAR */ (1U<<CC_GRAPH_)|(1U<<CC_PRINT_)|(1U<<CC_QUOTEMETA_),
/* 0x6B U+2C ',' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6C U+25 '%' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6D U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_WORDCHAR_),
/* 0x6D U+5F '_' */ (1U<<CC_ASCII_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_UNDERSCORE_)|(1U<<CC_WORDCHAR_),
/* 0x6E U+3E '>' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x6F U+3F '?' */ (1U<<CC_ASCII_)|(1U<<CC_GRAPH_)|(1U<<CC_MAGICAL_)|(1U<<CC_PRINT_)|(1U<<CC_PUNCT_)|(1U<<CC_QUOTEMETA_),
/* 0x70 U+F8 I8=BD o with '/' */ (1U<<CC_ALPHA_)|(1U<<CC_ALPHANUMERIC_)|(1U<<CC_CASED_)|(1U<<CC_CHARNAME_CONT_)|(1U<<CC_GRAPH_)|(1U<<CC_IDFIRST_)|(1U<<CC_IS_IN_SOME_FOLD_)|(1U<<CC_LOWER_)|(1U<<CC_PRINT_)|(1U<<CC_WORDCHAR_),

2
lib/unicore/uni_keywords.pl generated
View File

@ -1427,6 +1427,6 @@
# 03640d8ad18fc65de766f2034a927f7442960e998d3243845ca9b9fe31bfe1ab lib/unicore/mktables
# 8c30575264b2772c7a69c5bb6069a28f0e0a7a0df735871bde2d99ee674316ac lib/unicore/version
# 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl
# 6c52efdee47313cfde75ff86376008ce53320ebc93176caab45c77ce086a256d regen/mk_PL_charclass.pl
# 8abaee16c84c1a61a69a77b6e8963675d99f515f3c2a34e449faeb9bfdec861a regen/mk_PL_charclass.pl
# 20a6e3d507a66f4594586485568134873485b08e23383f3dc4e6b3047569267b regen/mk_invlists.pl
# ex: set ro ft=perl:

1
regen/mk_PL_charclass.pl
View File

@ -69,6 +69,7 @@ my %bit_names = (
ord(']'), ord('^'), ord('`'), ord('|'), ord('~'),
ord('$'),
],
UNDERSCORE => [ ord('_') ],
);
sub uniques {

2
regexp_constants.h
View File

@ -82,6 +82,6 @@
* 03640d8ad18fc65de766f2034a927f7442960e998d3243845ca9b9fe31bfe1ab lib/unicore/mktables
* 8c30575264b2772c7a69c5bb6069a28f0e0a7a0df735871bde2d99ee674316ac lib/unicore/version
* 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl
* 6c52efdee47313cfde75ff86376008ce53320ebc93176caab45c77ce086a256d regen/mk_PL_charclass.pl
* 8abaee16c84c1a61a69a77b6e8963675d99f515f3c2a34e449faeb9bfdec861a regen/mk_PL_charclass.pl
* 20a6e3d507a66f4594586485568134873485b08e23383f3dc4e6b3047569267b regen/mk_invlists.pl
* ex: set ro ft=c: */

2
uni_keywords.h generated
View File

@ -8174,7 +8174,7 @@ match_uniprop( const unsigned char * const key, const U16 key_len ) {
* 03640d8ad18fc65de766f2034a927f7442960e998d3243845ca9b9fe31bfe1ab lib/unicore/mktables
* 8c30575264b2772c7a69c5bb6069a28f0e0a7a0df735871bde2d99ee674316ac lib/unicore/version
* 0a6b5ab33bb1026531f816efe81aea1a8ffcd34a27cbea37dd6a70a63d73c844 regen/charset_translations.pl
* 6c52efdee47313cfde75ff86376008ce53320ebc93176caab45c77ce086a256d regen/mk_PL_charclass.pl
* 8abaee16c84c1a61a69a77b6e8963675d99f515f3c2a34e449faeb9bfdec861a regen/mk_PL_charclass.pl
* 20a6e3d507a66f4594586485568134873485b08e23383f3dc4e6b3047569267b regen/mk_invlists.pl
* d6987e01ad538d1567394851cf199f99815f7701bebd6092be4bc7a6d8f147c6 regen/mph.pl
* ex: set ro ft=c: */