diff options
-rw-r--r-- | pod/perldebguts.pod | 37 | ||||
-rw-r--r-- | regcomp.sym | 20 | ||||
-rw-r--r-- | regnodes.h | 20 |
3 files changed, 37 insertions, 40 deletions
diff --git a/pod/perldebguts.pod b/pod/perldebguts.pod index 2aa906e903..ff2eaed89b 100644 --- a/pod/perldebguts.pod +++ b/pod/perldebguts.pod @@ -587,7 +587,7 @@ will be lost. BOUNDL no Like BOUND/BOUNDU, but \w and \W are defined by current locale BOUNDU no Match "" at any boundary of a given type - using Unicode rules + using /u rules. BOUNDA no Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] NBOUND no Like NBOUNDA for non-utf8, otherwise match @@ -595,7 +595,7 @@ will be lost. NBOUNDL no Like NBOUND/NBOUNDU, but \w and \W are defined by current locale NBOUNDU no Match "" at any non-boundary of a given - type using using Unicode rules + type using using /u rules. NBOUNDA no Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] @@ -720,28 +720,25 @@ will be lost. SRCLOSE none Close preceding SROPEN REF num 1 Match some already matched string - REFF num 1 Match already matched string, folded using - native charset rules for non-utf8 - REFFL num 1 Match already matched string, folded in - loc. - REFFU num 1 Match already matched string, folded using - unicode rules for non-utf8 - REFFA num 1 Match already matched string, folded using - unicode rules for non-utf8, no mixing - ASCII, non-ASCII + REFF num 1 Match already matched string, using /di + rules. + REFFL num 1 Match already matched string, using /li + rules. + REFFU num 1 Match already matched string, usng /ui. + REFFA num 1 Match already matched string, using /aai + rules. # Named references. Code in regcomp.c assumes that these all are after # the numbered references NREF no-sv 1 Match some already matched string - NREFF no-sv 1 Match already matched string, folded using - native charset rules for non-utf8 - NREFFL no-sv 1 Match already matched string, folded in - loc. - NREFFU num 1 Match already matched string, folded using - unicode rules for non-utf8 - NREFFA num 1 Match already matched string, folded using - unicode rules for non-utf8, no mixing - ASCII, non-ASCII + NREFF no-sv 1 Match already matched string, using /di + rules. + NREFFL no-sv 1 Match already matched string, using /li + rules. + NREFFU num 1 Match already matched string, using /ui + rules. + NREFFA num 1 Match already matched string, using /aai + rules. # Support for long RE LONGJMP off 1 1 Jump far away. diff --git a/regcomp.sym b/regcomp.sym index 09a21e9cc0..4b9a42c338 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -47,12 +47,12 @@ GPOS GPOS, no ; Matches where last m//g left off. # BOUND, POSIX and their complements are affected, as well as EXACTF. BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale -BOUNDU BOUND, no ; Match "" at any boundary of a given type using Unicode rules +BOUNDU BOUND, no ; Match "" at any boundary of a given type using /u rules. BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] # All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale -NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using Unicode rules +NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using /u rules. NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] #* [Special] alternatives: @@ -156,21 +156,21 @@ SROPEN SROPEN, none ; Same as OPEN, but for script run SRCLOSE SRCLOSE, none ; Close preceding SROPEN REF REF, num 1 V ; Match some already matched string -REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8 -REFFL REF, num 1 V ; Match already matched string, folded in loc. +REFF REF, num 1 V ; Match already matched string, using /di rules. +REFFL REF, num 1 V ; Match already matched string, using /li rules. # N?REFF[AU] could have been implemented using the FLAGS field of the # regnode, but by having a separate node type, we can use the existing switch # statement to avoid some tests -REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 -REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII +REFFU REF, num 1 V ; Match already matched string, usng /ui. +REFFA REF, num 1 V ; Match already matched string, using /aai rules. #*Named references. Code in regcomp.c assumes that these all are after #*the numbered references NREF REF, no-sv 1 V ; Match some already matched string -NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8 -NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc. -NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 -NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII +NREFF REF, no-sv 1 V ; Match already matched string, using /di rules. +NREFFL REF, no-sv 1 V ; Match already matched string, using /li rules. +NREFFU REF, num 1 V ; Match already matched string, using /ui rules. +NREFFA REF, num 1 V ; Match already matched string, using /aai rules. #*Support for long RE LONGJMP LONGJMP, off 1 . 1 ; Jump far away. diff --git a/regnodes.h b/regnodes.h index 412a630561..3b53c1715f 100644 --- a/regnodes.h +++ b/regnodes.h @@ -21,11 +21,11 @@ #define GPOS 7 /* 0x07 Matches where last m//g left off. */ #define BOUND 8 /* 0x08 Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w */ #define BOUNDL 9 /* 0x09 Like BOUND/BOUNDU, but \w and \W are defined by current locale */ -#define BOUNDU 10 /* 0x0a Match "" at any boundary of a given type using Unicode rules */ +#define BOUNDU 10 /* 0x0a Match "" at any boundary of a given type using /u rules. */ #define BOUNDA 11 /* 0x0b Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] */ #define NBOUND 12 /* 0x0c Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W */ #define NBOUNDL 13 /* 0x0d Like NBOUND/NBOUNDU, but \w and \W are defined by current locale */ -#define NBOUNDU 14 /* 0x0e Match "" at any non-boundary of a given type using using Unicode rules */ +#define NBOUNDU 14 /* 0x0e Match "" at any non-boundary of a given type using using /u rules. */ #define NBOUNDA 15 /* 0x0f Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] */ #define REG_ANY 16 /* 0x10 Match any one character (except newline). */ #define SANY 17 /* 0x11 Match any one character. */ @@ -72,15 +72,15 @@ #define SROPEN 58 /* 0x3a Same as OPEN, but for script run */ #define SRCLOSE 59 /* 0x3b Close preceding SROPEN */ #define REF 60 /* 0x3c Match some already matched string */ -#define REFF 61 /* 0x3d Match already matched string, folded using native charset rules for non-utf8 */ -#define REFFL 62 /* 0x3e Match already matched string, folded in loc. */ -#define REFFU 63 /* 0x3f Match already matched string, folded using unicode rules for non-utf8 */ -#define REFFA 64 /* 0x40 Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ +#define REFF 61 /* 0x3d Match already matched string, using /di rules. */ +#define REFFL 62 /* 0x3e Match already matched string, using /li rules. */ +#define REFFU 63 /* 0x3f Match already matched string, usng /ui. */ +#define REFFA 64 /* 0x40 Match already matched string, using /aai rules. */ #define NREF 65 /* 0x41 Match some already matched string */ -#define NREFF 66 /* 0x42 Match already matched string, folded using native charset rules for non-utf8 */ -#define NREFFL 67 /* 0x43 Match already matched string, folded in loc. */ -#define NREFFU 68 /* 0x44 Match already matched string, folded using unicode rules for non-utf8 */ -#define NREFFA 69 /* 0x45 Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ +#define NREFF 66 /* 0x42 Match already matched string, using /di rules. */ +#define NREFFL 67 /* 0x43 Match already matched string, using /li rules. */ +#define NREFFU 68 /* 0x44 Match already matched string, using /ui rules. */ +#define NREFFA 69 /* 0x45 Match already matched string, using /aai rules. */ #define LONGJMP 70 /* 0x46 Jump far away. */ #define BRANCHJ 71 /* 0x47 BRANCH with long offset. */ #define IFMATCH 72 /* 0x48 Succeeds if the following matches; non-zero flags "f" means lookbehind assertion starting "f" characters before current */ |