|
version 1.1, 2012/02/21 23:05:51
|
version 1.1.1.2, 2012/02/21 23:50:25
|
|
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) 1997-2010 University of Cambridge | Copyright (c) 1997-2012 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 |
| _pcre_xclass(int c, const uschar *data) | PRIV(xclass)(int c, const pcre_uchar *data, BOOL utf) |
| { |
{ |
| int t; |
int t; |
| BOOL negated = (*data & XCL_NOT) != 0; |
BOOL negated = (*data & XCL_NOT) != 0; |
| |
|
| |
(void)utf; |
| |
#ifdef COMPILE_PCRE8 |
| |
/* In 8 bit mode, this must always be TRUE. Help the compiler to know that. */ |
| |
utf = TRUE; |
| |
#endif |
| |
|
| /* Character values < 256 are matched against a bitmap, if one is present. If |
/* Character values < 256 are matched against a bitmap, if one is present. If |
| not, we still carry on, because there may be ranges that start below 256 in the |
not, we still carry on, because there may be ranges that start below 256 in the |
| additional data. */ |
additional data. */ |
| |
|
| if (c < 256) |
if (c < 256) |
| { |
{ |
| if ((*data & XCL_MAP) != 0 && (data[1 + c/8] & (1 << (c&7))) != 0) | if ((*data & XCL_MAP) != 0 && |
| return !negated; /* char found */ | (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0) |
| | return !negated; /* char found */ |
| } |
} |
| |
|
| /* First skip the bit map if present. Then match against the list of Unicode |
/* First skip the bit map if present. Then match against the list of Unicode |
| properties or large chars or ranges that end with a large char. We won't ever |
properties or large chars or ranges that end with a large char. We won't ever |
| encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ |
encounter XCL_PROP or XCL_NOTPROP when UCP support is not compiled. */ |
| |
|
| if ((*data++ & XCL_MAP) != 0) data += 32; | if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar); |
| |
|
| while ((t = *data++) != XCL_END) |
while ((t = *data++) != XCL_END) |
| { |
{ |
| int x, y; |
int x, y; |
| if (t == XCL_SINGLE) |
if (t == XCL_SINGLE) |
| { |
{ |
| GETCHARINC(x, data); | #ifdef SUPPORT_UTF |
| | if (utf) |
| | { |
| | GETCHARINC(x, data); /* macro generates multiple statements */ |
| | } |
| | else |
| | #endif |
| | x = *data++; |
| if (c == x) return !negated; |
if (c == x) return !negated; |
| } |
} |
| else if (t == XCL_RANGE) |
else if (t == XCL_RANGE) |
| { |
{ |
| GETCHARINC(x, data); | #ifdef SUPPORT_UTF |
| GETCHARINC(y, data); | if (utf) |
| | { |
| | GETCHARINC(x, data); /* macro generates multiple statements */ |
| | GETCHARINC(y, data); /* macro generates multiple statements */ |
| | } |
| | else |
| | #endif |
| | { |
| | x = *data++; |
| | y = *data++; |
| | } |
| if (c >= x && c <= y) return !negated; |
if (c >= x && c <= y) return !negated; |
| } |
} |
| |
|
|
Line 117 while ((t = *data++) != XCL_END)
|
Line 141 while ((t = *data++) != XCL_END)
|
| break; |
break; |
| |
|
| case PT_GC: |
case PT_GC: |
| if ((data[1] == _pcre_ucp_gentype[prop->chartype]) == (t == XCL_PROP)) | if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == (t == XCL_PROP)) |
| return !negated; |
return !negated; |
| break; |
break; |
| |
|
|
Line 130 while ((t = *data++) != XCL_END)
|
Line 154 while ((t = *data++) != XCL_END)
|
| break; |
break; |
| |
|
| case PT_ALNUM: |
case PT_ALNUM: |
| if ((_pcre_ucp_gentype[prop->chartype] == ucp_L || | if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
| _pcre_ucp_gentype[prop->chartype] == ucp_N) == (t == XCL_PROP)) | PRIV(ucp_gentype)[prop->chartype] == ucp_N) == (t == XCL_PROP)) |
| return !negated; |
return !negated; |
| break; |
break; |
| |
|
| case PT_SPACE: /* Perl space */ |
case PT_SPACE: /* Perl space */ |
| if ((_pcre_ucp_gentype[prop->chartype] == ucp_Z || | if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z || |
| c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR) |
c == CHAR_HT || c == CHAR_NL || c == CHAR_FF || c == CHAR_CR) |
| == (t == XCL_PROP)) |
== (t == XCL_PROP)) |
| return !negated; |
return !negated; |
| break; |
break; |
| |
|
| case PT_PXSPACE: /* POSIX space */ |
case PT_PXSPACE: /* POSIX space */ |
| if ((_pcre_ucp_gentype[prop->chartype] == ucp_Z || | if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z || |
| c == CHAR_HT || c == CHAR_NL || c == CHAR_VT || |
c == CHAR_HT || c == CHAR_NL || c == CHAR_VT || |
| c == CHAR_FF || c == CHAR_CR) == (t == XCL_PROP)) |
c == CHAR_FF || c == CHAR_CR) == (t == XCL_PROP)) |
| return !negated; |
return !negated; |
| break; |
break; |
| |
|
| case PT_WORD: |
case PT_WORD: |
| if ((_pcre_ucp_gentype[prop->chartype] == ucp_L || | if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L || |
| _pcre_ucp_gentype[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) | PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE) |
| == (t == XCL_PROP)) |
== (t == XCL_PROP)) |
| return !negated; |
return !negated; |
| break; |
break; |