version 1.1.1.2, 2012/02/21 23:50:25
|
version 1.1.1.4, 2014/06/15 19:46:03
|
Line 6
|
Line 6
|
and semantics are as close as possible to those of the Perl 5 language. |
and semantics are as close as possible to those of the Perl 5 language. |
|
|
Written by Philip Hazel |
Written by Philip Hazel |
Copyright (c) 1997-2012 University of Cambridge | Copyright (c) 1997-2013 University of Cambridge |
|
|
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
Redistribution and use in source and binary forms, with or without |
Redistribution and use in source and binary forms, with or without |
Line 64 Returns: TRUE if character matches, else FALSE
|
Line 64 Returns: TRUE if character matches, else FALSE
|
*/ |
*/ |
|
|
BOOL |
BOOL |
PRIV(xclass)(int c, const pcre_uchar *data, BOOL utf) | PRIV(xclass)(pcre_uint32 c, const pcre_uchar *data, BOOL utf) |
{ |
{ |
int t; | pcre_uchar t; |
BOOL negated = (*data & XCL_NOT) != 0; |
BOOL negated = (*data & XCL_NOT) != 0; |
|
|
(void)utf; |
(void)utf; |
Line 94 if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre
|
Line 94 if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre
|
|
|
while ((t = *data++) != XCL_END) |
while ((t = *data++) != XCL_END) |
{ |
{ |
int x, y; | pcre_uint32 x, y; |
if (t == XCL_SINGLE) |
if (t == XCL_SINGLE) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 128 while ((t = *data++) != XCL_END)
|
Line 128 while ((t = *data++) != XCL_END)
|
else /* XCL_PROP & XCL_NOTPROP */ |
else /* XCL_PROP & XCL_NOTPROP */ |
{ |
{ |
const ucd_record *prop = GET_UCD(c); |
const ucd_record *prop = GET_UCD(c); |
|
BOOL isprop = t == XCL_PROP; |
|
|
switch(*data) |
switch(*data) |
{ |
{ |
case PT_ANY: |
case PT_ANY: |
if (t == XCL_PROP) return !negated; | if (isprop) return !negated; |
break; |
break; |
|
|
case PT_LAMP: |
case PT_LAMP: |
if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || |
if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll || |
prop->chartype == ucp_Lt) == (t == XCL_PROP)) return !negated; | prop->chartype == ucp_Lt) == isprop) return !negated; |
break; |
break; |
|
|
case PT_GC: |
case PT_GC: |
if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == (t == XCL_PROP)) | if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop) |
return !negated; |
return !negated; |
break; |
break; |
|
|
case PT_PC: |
case PT_PC: |
if ((data[1] == prop->chartype) == (t == XCL_PROP)) return !negated; | if ((data[1] == prop->chartype) == isprop) return !negated; |
break; |
break; |
|
|
case PT_SC: |
case PT_SC: |
if ((data[1] == prop->script) == (t == XCL_PROP)) return !negated; | if ((data[1] == prop->script) == isprop) return !negated; |
break; |
break; |
|
|
case PT_ALNUM: |
case PT_ALNUM: |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (t == XCL_PROP)) | PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop) |
return !negated; |
return !negated; |
break; |
break; |
|
|
case PT_SPACE: /* Perl space */ | /* Perl space used to exclude VT, but from Perl 5.18 it is included, |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z || | which means that Perl space and POSIX space are now identical. PCRE |
c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR) | was changed at release 8.34. */ |
== (t == XCL_PROP)) | |
return !negated; | |
break; | |
|
|
|
case PT_SPACE: /* Perl space */ |
case PT_PXSPACE: /* POSIX space */ |
case PT_PXSPACE: /* POSIX space */ |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z || | switch(c) |
c == CHAR_HT || c == CHAR_NL || c == CHAR_VT || | { |
c == CHAR_FF || c == CHAR_CR) == (t == XCL_PROP)) | HSPACE_CASES: |
return !negated; | VSPACE_CASES: |
| if (isprop) return !negated; |
| break; |
| |
| default: |
| if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop) |
| return !negated; |
| break; |
| } |
break; |
break; |
|
|
case PT_WORD: |
case PT_WORD: |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) |
PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) |
== (t == XCL_PROP)) | == isprop) |
| return !negated; |
| break; |
| |
| case PT_UCNC: |
| if (c < 0xa0) |
| { |
| if ((c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || |
| c == CHAR_GRAVE_ACCENT) == isprop) |
| return !negated; |
| } |
| else |
| { |
| if ((c < 0xd800 || c > 0xdfff) == isprop) |
| return !negated; |
| } |
| break; |
| |
| /* The following three properties can occur only in an XCLASS, as there |
| is no \p or \P coding for them. */ |
| |
| /* Graphic character. Implement this as not Z (space or separator) and |
| not C (other), except for Cf (format) with a few exceptions. This seems |
| to be what Perl does. The exceptional characters are: |
| |
| U+061C Arabic Letter Mark |
| U+180E Mongolian Vowel Separator |
| U+2066 - U+2069 Various "isolate"s |
| */ |
| |
| case PT_PXGRAPH: |
| if ((PRIV(ucp_gentype)[prop->chartype] != ucp_Z && |
| (PRIV(ucp_gentype)[prop->chartype] != ucp_C || |
| (prop->chartype == ucp_Cf && |
| c != 0x061c && c != 0x180e && (c < 0x2066 || c > 0x2069)) |
| )) == isprop) |
| return !negated; |
| break; |
| |
| /* Printable character: same as graphic, with the addition of Zs, i.e. |
| not Zl and not Zp, and U+180E. */ |
| |
| case PT_PXPRINT: |
| if ((prop->chartype != ucp_Zl && |
| prop->chartype != ucp_Zp && |
| (PRIV(ucp_gentype)[prop->chartype] != ucp_C || |
| (prop->chartype == ucp_Cf && |
| c != 0x061c && (c < 0x2066 || c > 0x2069)) |
| )) == isprop) |
| return !negated; |
| break; |
| |
| /* Punctuation: all Unicode punctuation, plus ASCII characters that |
| Unicode treats as symbols rather than punctuation, for Perl |
| compatibility (these are $+<=>^`|~). */ |
| |
| case PT_PXPUNCT: |
| if ((PRIV(ucp_gentype)[prop->chartype] == ucp_P || |
| (c < 256 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop) |
return !negated; |
return !negated; |
break; |
break; |
|
|