Branch
Hash :
9ceafb57
Author :
Date :
2019-01-12T22:55:31
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Copyright (c) 1997-2013 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
/* This module contains an internal function that is used to match an extended
class. It is used by both pcre_exec() and pcre_def_exec(). */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre_internal.h"
/*************************************************
* Match character against an XCLASS *
*************************************************/
/* This function is called to match a character against an extended class that
might contain values > 255 and/or Unicode properties.
Arguments:
c the character
data points to the flag byte of the XCLASS data
Returns: TRUE if character matches, else FALSE
*/
BOOL
PRIV(xclass)(pcre_uint32 c, const pcre_uchar *data, BOOL utf)
{
pcre_uchar t;
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
not, we still carry on, because there may be ranges that start below 256 in the
additional data. */
if (c < 256)
{
if ((*data & XCL_HASPROP) == 0)
{
if ((*data & XCL_MAP) == 0) return negated;
return (((pcre_uint8 *)(data + 1))[c/8] & (1 << (c&7))) != 0;
}
if ((*data & XCL_MAP) != 0 &&
(((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
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. */
if ((*data++ & XCL_MAP) != 0) data += 32 / sizeof(pcre_uchar);
while ((t = *data++) != XCL_END)
{
pcre_uint32 x, y;
if (t == XCL_SINGLE)
{
#ifdef SUPPORT_UTF
if (utf)
{
GETCHARINC(x, data); /* macro generates multiple statements */
}
else
#endif
x = *data++;
if (c == x) return !negated;
}
else if (t == XCL_RANGE)
{
#ifdef SUPPORT_UTF
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;
}
#ifdef SUPPORT_UCP
else /* XCL_PROP & XCL_NOTPROP */
{
const ucd_record *prop = GET_UCD(c);
BOOL isprop = t == XCL_PROP;
switch(*data)
{
case PT_ANY:
if (isprop) return !negated;
break;
case PT_LAMP:
if ((prop->chartype == ucp_Lu || prop->chartype == ucp_Ll ||
prop->chartype == ucp_Lt) == isprop) return !negated;
break;
case PT_GC:
if ((data[1] == PRIV(ucp_gentype)[prop->chartype]) == isprop)
return !negated;
break;
case PT_PC:
if ((data[1] == prop->chartype) == isprop) return !negated;
break;
case PT_SC:
if ((data[1] == prop->script) == isprop) return !negated;
break;
case PT_ALNUM:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N) == isprop)
return !negated;
break;
/* Perl space used to exclude VT, but from Perl 5.18 it is included,
which means that Perl space and POSIX space are now identical. PCRE
was changed at release 8.34. */
case PT_SPACE: /* Perl space */
case PT_PXSPACE: /* POSIX space */
switch(c)
{
HSPACE_CASES:
VSPACE_CASES:
if (isprop) return !negated;
break;
default:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == isprop)
return !negated;
break;
}
break;
case PT_WORD:
if ((PRIV(ucp_gentype)[prop->chartype] == ucp_L ||
PRIV(ucp_gentype)[prop->chartype] == ucp_N || c == CHAR_UNDERSCORE)
== 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 < 128 && PRIV(ucp_gentype)[prop->chartype] == ucp_S)) == isprop)
return !negated;
break;
/* This should never occur, but compilers may mutter if there is no
default. */
default:
return FALSE;
}
data += 2;
}
#endif /* SUPPORT_UCP */
}
return negated; /* char did not match */
}
/* End of pcre_xclass.c */