You are viewing a plain text version of this content. The canonical link for it is here.
Posted to cvs@httpd.apache.org by pg...@apache.org on 2007/11/26 17:50:09 UTC
svn commit: r598339 [30/37] - in /httpd/httpd/vendor/pcre/current: ./ doc/
doc/html/ testdata/
Added: httpd/httpd/vendor/pcre/current/pcre_ucp_searchfuncs.c
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcre_ucp_searchfuncs.c?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcre_ucp_searchfuncs.c (added)
+++ httpd/httpd/vendor/pcre/current/pcre_ucp_searchfuncs.c Mon Nov 26 08:49:53 2007
@@ -0,0 +1,179 @@
+/*************************************************
+* 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) 1997-2007 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 code for searching the table of Unicode character
+properties. */
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "pcre_internal.h"
+
+#include "ucp.h" /* Category definitions */
+#include "ucpinternal.h" /* Internal table details */
+#include "ucptable.h" /* The table itself */
+
+
+/* Table to translate from particular type value to the general value. */
+
+static const int ucp_gentype[] = {
+ ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
+ ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
+ ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
+ ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
+ ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
+ ucp_P, ucp_P, /* Ps, Po */
+ ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
+ ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
+};
+
+
+
+/*************************************************
+* Search table and return type *
+*************************************************/
+
+/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed
+character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc.
+
+Arguments:
+ c the character value
+ type_ptr the detailed character type is returned here
+ script_ptr the script is returned here
+
+Returns: the character type category
+*/
+
+int
+_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr)
+{
+int bot = 0;
+int top = sizeof(ucp_table)/sizeof(cnode);
+int mid;
+
+/* The table is searched using a binary chop. You might think that using
+intermediate variables to hold some of the common expressions would speed
+things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
+makes things a lot slower. */
+
+for (;;)
+ {
+ if (top <= bot)
+ {
+ *type_ptr = ucp_Cn;
+ *script_ptr = ucp_Common;
+ return ucp_C;
+ }
+ mid = (bot + top) >> 1;
+ if (c == (ucp_table[mid].f0 & f0_charmask)) break;
+ if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
+ else
+ {
+ if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
+ c <= (ucp_table[mid].f0 & f0_charmask) +
+ (ucp_table[mid].f1 & f1_rangemask)) break;
+ bot = mid + 1;
+ }
+ }
+
+/* Found an entry in the table. Set the script and detailed type values, and
+return the general type. */
+
+*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift;
+*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift;
+
+return ucp_gentype[*type_ptr];
+}
+
+
+
+/*************************************************
+* Search table and return other case *
+*************************************************/
+
+/* If the given character is a letter, and there is another case for the
+letter, return the other case. Otherwise, return -1.
+
+Arguments:
+ c the character value
+
+Returns: the other case or NOTACHAR if none
+*/
+
+unsigned int
+_pcre_ucp_othercase(const unsigned int c)
+{
+int bot = 0;
+int top = sizeof(ucp_table)/sizeof(cnode);
+int mid, offset;
+
+/* The table is searched using a binary chop. You might think that using
+intermediate variables to hold some of the common expressions would speed
+things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
+makes things a lot slower. */
+
+for (;;)
+ {
+ if (top <= bot) return -1;
+ mid = (bot + top) >> 1;
+ if (c == (ucp_table[mid].f0 & f0_charmask)) break;
+ if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
+ else
+ {
+ if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
+ c <= (ucp_table[mid].f0 & f0_charmask) +
+ (ucp_table[mid].f1 & f1_rangemask)) break;
+ bot = mid + 1;
+ }
+ }
+
+/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise
+return the other case if there is one, else NOTACHAR. */
+
+if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR;
+
+offset = ucp_table[mid].f1 & f1_casemask;
+if ((offset & f1_caseneg) != 0) offset |= f1_caseneg;
+return (offset == 0)? NOTACHAR : c + offset;
+}
+
+
+/* End of pcre_ucp_searchfuncs.c */
Added: httpd/httpd/vendor/pcre/current/pcre_valid_utf8.c
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcre_valid_utf8.c?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcre_valid_utf8.c (added)
+++ httpd/httpd/vendor/pcre/current/pcre_valid_utf8.c Mon Nov 26 08:49:53 2007
@@ -0,0 +1,162 @@
+/*************************************************
+* 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) 1997-2007 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 for validating UTF-8 character
+strings. */
+
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+* Validate a UTF-8 string *
+*************************************************/
+
+/* This function is called (optionally) at the start of compile or match, to
+validate that a supposed UTF-8 string is actually valid. The early check means
+that subsequent code can assume it is dealing with a valid string. The check
+can be turned off for maximum performance, but the consequences of supplying
+an invalid string are then undefined.
+
+Originally, this function checked according to RFC 2279, allowing for values in
+the range 0 to 0x7fffffff, up to 6 bytes long, but ensuring that they were in
+the canonical format. Once somebody had pointed out RFC 3629 to me (it
+obsoletes 2279), additional restrictions were applies. The values are now
+limited to be between 0 and 0x0010ffff, no more than 4 bytes long, and the
+subrange 0xd000 to 0xdfff is excluded.
+
+Arguments:
+ string points to the string
+ length length of string, or -1 if the string is zero-terminated
+
+Returns: < 0 if the string is a valid UTF-8 string
+ >= 0 otherwise; the value is the offset of the bad byte
+*/
+
+int
+_pcre_valid_utf8(const uschar *string, int length)
+{
+#ifdef SUPPORT_UTF8
+register const uschar *p;
+
+if (length < 0)
+ {
+ for (p = string; *p != 0; p++);
+ length = p - string;
+ }
+
+for (p = string; length-- > 0; p++)
+ {
+ register int ab;
+ register int c = *p;
+ if (c < 128) continue;
+ if (c < 0xc0) return p - string;
+ ab = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */
+ if (length < ab || ab > 3) return p - string;
+ length -= ab;
+
+ /* Check top bits in the second byte */
+ if ((*(++p) & 0xc0) != 0x80) return p - string;
+
+ /* Check for overlong sequences for each different length, and for the
+ excluded range 0xd000 to 0xdfff. */
+
+ switch (ab)
+ {
+ /* Check for xx00 000x (overlong sequence) */
+
+ case 1:
+ if ((c & 0x3e) == 0) return p - string;
+ continue; /* We know there aren't any more bytes to check */
+
+ /* Check for 1110 0000, xx0x xxxx (overlong sequence) or
+ 1110 1101, 1010 xxxx (0xd000 - 0xdfff) */
+
+ case 2:
+ if ((c == 0xe0 && (*p & 0x20) == 0) ||
+ (c == 0xed && *p >= 0xa0))
+ return p - string;
+ break;
+
+ /* Check for 1111 0000, xx00 xxxx (overlong sequence) or
+ greater than 0x0010ffff (f4 8f bf bf) */
+
+ case 3:
+ if ((c == 0xf0 && (*p & 0x30) == 0) ||
+ (c > 0xf4 ) ||
+ (c == 0xf4 && *p > 0x8f))
+ return p - string;
+ break;
+
+#if 0
+ /* These cases can no longer occur, as we restrict to a maximum of four
+ bytes nowadays. Leave the code here in case we ever want to add an option
+ for longer sequences. */
+
+ /* Check for 1111 1000, xx00 0xxx */
+ case 4:
+ if (c == 0xf8 && (*p & 0x38) == 0) return p - string;
+ break;
+
+ /* Check for leading 0xfe or 0xff, and then for 1111 1100, xx00 00xx */
+ case 5:
+ if (c == 0xfe || c == 0xff ||
+ (c == 0xfc && (*p & 0x3c) == 0)) return p - string;
+ break;
+#endif
+
+ }
+
+ /* Check for valid bytes after the 2nd, if any; all must start 10 */
+ while (--ab > 0)
+ {
+ if ((*(++p) & 0xc0) != 0x80) return p - string;
+ }
+ }
+#endif
+
+return -1;
+}
+
+/* End of pcre_valid_utf8.c */
Added: httpd/httpd/vendor/pcre/current/pcre_version.c
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcre_version.c?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcre_version.c (added)
+++ httpd/httpd/vendor/pcre/current/pcre_version.c Mon Nov 26 08:49:53 2007
@@ -0,0 +1,90 @@
+/*************************************************
+* 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) 1997-2007 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 the external function pcre_version(), which returns a
+string that identifies the PCRE version that is in use. */
+
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "pcre_internal.h"
+
+
+/*************************************************
+* Return version string *
+*************************************************/
+
+/* These macros are the standard way of turning unquoted text into C strings.
+They allow macros like PCRE_MAJOR to be defined without quotes, which is
+convenient for user programs that want to test its value. */
+
+#define STRING(a) # a
+#define XSTRING(s) STRING(s)
+
+/* A problem turned up with PCRE_PRERELEASE, which is defined empty for
+production releases. Originally, it was used naively in this code:
+
+ return XSTRING(PCRE_MAJOR)
+ "." XSTRING(PCRE_MINOR)
+ XSTRING(PCRE_PRERELEASE)
+ " " XSTRING(PCRE_DATE);
+
+However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of
+STRING(). The C standard states: "If (before argument substitution) any
+argument consists of no preprocessing tokens, the behavior is undefined." It
+turns out the gcc treats this case as a single empty string - which is what we
+really want - but Visual C grumbles about the lack of an argument for the
+macro. Unfortunately, both are within their rights. To cope with both ways of
+handling this, I had resort to some messy hackery that does a test at run time.
+I could find no way of detecting that a macro is defined as an empty string at
+pre-processor time. This hack uses a standard trick for avoiding calling
+the STRING macro with an empty argument when doing the test. */
+
+PCRE_EXP_DEFN const char *
+pcre_version(void)
+{
+return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)?
+ XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) :
+ XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE);
+}
+
+/* End of pcre_version.c */
Added: httpd/httpd/vendor/pcre/current/pcre_xclass.c
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcre_xclass.c?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcre_xclass.c (added)
+++ httpd/httpd/vendor/pcre/current/pcre_xclass.c Mon Nov 26 08:49:53 2007
@@ -0,0 +1,148 @@
+/*************************************************
+* 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) 1997-2007 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 (one that contains characters whose values are > 255). 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.
+
+Arguments:
+ c the character
+ data points to the flag byte of the XCLASS data
+
+Returns: TRUE if character matches, else FALSE
+*/
+
+BOOL
+_pcre_xclass(int c, const uschar *data)
+{
+int t;
+BOOL negated = (*data & XCL_NOT) != 0;
+
+/* 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_MAP) != 0 && (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;
+
+while ((t = *data++) != XCL_END)
+ {
+ int x, y;
+ if (t == XCL_SINGLE)
+ {
+ GETCHARINC(x, data);
+ if (c == x) return !negated;
+ }
+ else if (t == XCL_RANGE)
+ {
+ GETCHARINC(x, data);
+ GETCHARINC(y, data);
+ if (c >= x && c <= y) return !negated;
+ }
+
+#ifdef SUPPORT_UCP
+ else /* XCL_PROP & XCL_NOTPROP */
+ {
+ int chartype, script;
+ int category = _pcre_ucp_findprop(c, &chartype, &script);
+
+ switch(*data)
+ {
+ case PT_ANY:
+ if (t == XCL_PROP) return !negated;
+ break;
+
+ case PT_LAMP:
+ if ((chartype == ucp_Lu || chartype == ucp_Ll || chartype == ucp_Lt) ==
+ (t == XCL_PROP)) return !negated;
+ break;
+
+ case PT_GC:
+ if ((data[1] == category) == (t == XCL_PROP)) return !negated;
+ break;
+
+ case PT_PC:
+ if ((data[1] == chartype) == (t == XCL_PROP)) return !negated;
+ break;
+
+ case PT_SC:
+ if ((data[1] == script) == (t == XCL_PROP)) 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 */
Added: httpd/httpd/vendor/pcre/current/pcrecpp.cc
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcrecpp.cc?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcrecpp.cc (added)
+++ httpd/httpd/vendor/pcre/current/pcrecpp.cc Mon Nov 26 08:49:53 2007
@@ -0,0 +1,857 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// 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 Google Inc. 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.
+//
+// Author: Sanjay Ghemawat
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <limits.h> /* for SHRT_MIN, USHRT_MAX, etc */
+#include <assert.h>
+#include <errno.h>
+#include <string>
+#include <algorithm>
+
+#include "pcrecpp_internal.h"
+#include "pcre.h"
+#include "pcrecpp.h"
+#include "pcre_stringpiece.h"
+
+
+namespace pcrecpp {
+
+// Maximum number of args we can set
+static const int kMaxArgs = 16;
+static const int kVecSize = (1 + kMaxArgs) * 3; // results + PCRE workspace
+
+// Special object that stands-in for no argument
+PCRECPP_EXP_DEFN Arg no_arg((void*)NULL);
+
+// If a regular expression has no error, its error_ field points here
+static const string empty_string;
+
+// If the user doesn't ask for any options, we just use this one
+static RE_Options default_options;
+
+void RE::Init(const string& pat, const RE_Options* options) {
+ pattern_ = pat;
+ if (options == NULL) {
+ options_ = default_options;
+ } else {
+ options_ = *options;
+ }
+ error_ = &empty_string;
+ re_full_ = NULL;
+ re_partial_ = NULL;
+
+ re_partial_ = Compile(UNANCHORED);
+ if (re_partial_ != NULL) {
+ re_full_ = Compile(ANCHOR_BOTH);
+ }
+}
+
+void RE::Cleanup() {
+ if (re_full_ != NULL) (*pcre_free)(re_full_);
+ if (re_partial_ != NULL) (*pcre_free)(re_partial_);
+ if (error_ != &empty_string) delete error_;
+}
+
+
+RE::~RE() {
+ Cleanup();
+}
+
+
+pcre* RE::Compile(Anchor anchor) {
+ // First, convert RE_Options into pcre options
+ int pcre_options = 0;
+ pcre_options = options_.all_options();
+
+ // Special treatment for anchoring. This is needed because at
+ // runtime pcre only provides an option for anchoring at the
+ // beginning of a string (unless you use offset).
+ //
+ // There are three types of anchoring we want:
+ // UNANCHORED Compile the original pattern, and use
+ // a pcre unanchored match.
+ // ANCHOR_START Compile the original pattern, and use
+ // a pcre anchored match.
+ // ANCHOR_BOTH Tack a "\z" to the end of the original pattern
+ // and use a pcre anchored match.
+
+ const char* compile_error;
+ int eoffset;
+ pcre* re;
+ if (anchor != ANCHOR_BOTH) {
+ re = pcre_compile(pattern_.c_str(), pcre_options,
+ &compile_error, &eoffset, NULL);
+ } else {
+ // Tack a '\z' at the end of RE. Parenthesize it first so that
+ // the '\z' applies to all top-level alternatives in the regexp.
+ string wrapped = "(?:"; // A non-counting grouping operator
+ wrapped += pattern_;
+ wrapped += ")\\z";
+ re = pcre_compile(wrapped.c_str(), pcre_options,
+ &compile_error, &eoffset, NULL);
+ }
+ if (re == NULL) {
+ if (error_ == &empty_string) error_ = new string(compile_error);
+ }
+ return re;
+}
+
+/***** Matching interfaces *****/
+
+bool RE::FullMatch(const StringPiece& text,
+ const Arg& ptr1,
+ const Arg& ptr2,
+ const Arg& ptr3,
+ const Arg& ptr4,
+ const Arg& ptr5,
+ const Arg& ptr6,
+ const Arg& ptr7,
+ const Arg& ptr8,
+ const Arg& ptr9,
+ const Arg& ptr10,
+ const Arg& ptr11,
+ const Arg& ptr12,
+ const Arg& ptr13,
+ const Arg& ptr14,
+ const Arg& ptr15,
+ const Arg& ptr16) const {
+ const Arg* args[kMaxArgs];
+ int n = 0;
+ if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
+ if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
+ if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
+ if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
+ if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
+ if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
+ if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
+ if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
+ if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
+ if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
+ if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
+ if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
+ if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
+ if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
+ if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
+ if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
+ done:
+
+ int consumed;
+ int vec[kVecSize];
+ return DoMatchImpl(text, ANCHOR_BOTH, &consumed, args, n, vec, kVecSize);
+}
+
+bool RE::PartialMatch(const StringPiece& text,
+ const Arg& ptr1,
+ const Arg& ptr2,
+ const Arg& ptr3,
+ const Arg& ptr4,
+ const Arg& ptr5,
+ const Arg& ptr6,
+ const Arg& ptr7,
+ const Arg& ptr8,
+ const Arg& ptr9,
+ const Arg& ptr10,
+ const Arg& ptr11,
+ const Arg& ptr12,
+ const Arg& ptr13,
+ const Arg& ptr14,
+ const Arg& ptr15,
+ const Arg& ptr16) const {
+ const Arg* args[kMaxArgs];
+ int n = 0;
+ if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
+ if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
+ if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
+ if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
+ if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
+ if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
+ if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
+ if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
+ if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
+ if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
+ if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
+ if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
+ if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
+ if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
+ if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
+ if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
+ done:
+
+ int consumed;
+ int vec[kVecSize];
+ return DoMatchImpl(text, UNANCHORED, &consumed, args, n, vec, kVecSize);
+}
+
+bool RE::Consume(StringPiece* input,
+ const Arg& ptr1,
+ const Arg& ptr2,
+ const Arg& ptr3,
+ const Arg& ptr4,
+ const Arg& ptr5,
+ const Arg& ptr6,
+ const Arg& ptr7,
+ const Arg& ptr8,
+ const Arg& ptr9,
+ const Arg& ptr10,
+ const Arg& ptr11,
+ const Arg& ptr12,
+ const Arg& ptr13,
+ const Arg& ptr14,
+ const Arg& ptr15,
+ const Arg& ptr16) const {
+ const Arg* args[kMaxArgs];
+ int n = 0;
+ if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
+ if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
+ if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
+ if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
+ if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
+ if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
+ if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
+ if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
+ if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
+ if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
+ if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
+ if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
+ if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
+ if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
+ if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
+ if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
+ done:
+
+ int consumed;
+ int vec[kVecSize];
+ if (DoMatchImpl(*input, ANCHOR_START, &consumed,
+ args, n, vec, kVecSize)) {
+ input->remove_prefix(consumed);
+ return true;
+ } else {
+ return false;
+ }
+}
+
+bool RE::FindAndConsume(StringPiece* input,
+ const Arg& ptr1,
+ const Arg& ptr2,
+ const Arg& ptr3,
+ const Arg& ptr4,
+ const Arg& ptr5,
+ const Arg& ptr6,
+ const Arg& ptr7,
+ const Arg& ptr8,
+ const Arg& ptr9,
+ const Arg& ptr10,
+ const Arg& ptr11,
+ const Arg& ptr12,
+ const Arg& ptr13,
+ const Arg& ptr14,
+ const Arg& ptr15,
+ const Arg& ptr16) const {
+ const Arg* args[kMaxArgs];
+ int n = 0;
+ if (&ptr1 == &no_arg) goto done; args[n++] = &ptr1;
+ if (&ptr2 == &no_arg) goto done; args[n++] = &ptr2;
+ if (&ptr3 == &no_arg) goto done; args[n++] = &ptr3;
+ if (&ptr4 == &no_arg) goto done; args[n++] = &ptr4;
+ if (&ptr5 == &no_arg) goto done; args[n++] = &ptr5;
+ if (&ptr6 == &no_arg) goto done; args[n++] = &ptr6;
+ if (&ptr7 == &no_arg) goto done; args[n++] = &ptr7;
+ if (&ptr8 == &no_arg) goto done; args[n++] = &ptr8;
+ if (&ptr9 == &no_arg) goto done; args[n++] = &ptr9;
+ if (&ptr10 == &no_arg) goto done; args[n++] = &ptr10;
+ if (&ptr11 == &no_arg) goto done; args[n++] = &ptr11;
+ if (&ptr12 == &no_arg) goto done; args[n++] = &ptr12;
+ if (&ptr13 == &no_arg) goto done; args[n++] = &ptr13;
+ if (&ptr14 == &no_arg) goto done; args[n++] = &ptr14;
+ if (&ptr15 == &no_arg) goto done; args[n++] = &ptr15;
+ if (&ptr16 == &no_arg) goto done; args[n++] = &ptr16;
+ done:
+
+ int consumed;
+ int vec[kVecSize];
+ if (DoMatchImpl(*input, UNANCHORED, &consumed,
+ args, n, vec, kVecSize)) {
+ input->remove_prefix(consumed);
+ return true;
+ } else {
+ return false;
+ }
+}
+
+bool RE::Replace(const StringPiece& rewrite,
+ string *str) const {
+ int vec[kVecSize];
+ int matches = TryMatch(*str, 0, UNANCHORED, vec, kVecSize);
+ if (matches == 0)
+ return false;
+
+ string s;
+ if (!Rewrite(&s, rewrite, *str, vec, matches))
+ return false;
+
+ assert(vec[0] >= 0);
+ assert(vec[1] >= 0);
+ str->replace(vec[0], vec[1] - vec[0], s);
+ return true;
+}
+
+// Returns PCRE_NEWLINE_CRLF, PCRE_NEWLINE_CR, or PCRE_NEWLINE_LF.
+// Note that PCRE_NEWLINE_CRLF is defined to be P_N_CR | P_N_LF.
+// Modified by PH to add PCRE_NEWLINE_ANY and PCRE_NEWLINE_ANYCRLF.
+
+static int NewlineMode(int pcre_options) {
+ // TODO: if we can make it threadsafe, cache this var
+ int newline_mode = 0;
+ /* if (newline_mode) return newline_mode; */ // do this once it's cached
+ if (pcre_options & (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|
+ PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF)) {
+ newline_mode = (pcre_options &
+ (PCRE_NEWLINE_CRLF|PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|
+ PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF));
+ } else {
+ int newline;
+ pcre_config(PCRE_CONFIG_NEWLINE, &newline);
+ if (newline == 10)
+ newline_mode = PCRE_NEWLINE_LF;
+ else if (newline == 13)
+ newline_mode = PCRE_NEWLINE_CR;
+ else if (newline == 3338)
+ newline_mode = PCRE_NEWLINE_CRLF;
+ else if (newline == -1)
+ newline_mode = PCRE_NEWLINE_ANY;
+ else if (newline == -2)
+ newline_mode = PCRE_NEWLINE_ANYCRLF;
+ else
+ assert("" == "Unexpected return value from pcre_config(NEWLINE)");
+ }
+ return newline_mode;
+}
+
+int RE::GlobalReplace(const StringPiece& rewrite,
+ string *str) const {
+ int count = 0;
+ int vec[kVecSize];
+ string out;
+ int start = 0;
+ int lastend = -1;
+
+ for (; start <= static_cast<int>(str->length()); count++) {
+ int matches = TryMatch(*str, start, UNANCHORED, vec, kVecSize);
+ if (matches <= 0)
+ break;
+ int matchstart = vec[0], matchend = vec[1];
+ assert(matchstart >= start);
+ assert(matchend >= matchstart);
+ if (matchstart == matchend && matchstart == lastend) {
+ // advance one character if we matched an empty string at the same
+ // place as the last match occurred
+ matchend = start + 1;
+ // If the current char is CR and we're in CRLF mode, skip LF too.
+ // Note it's better to call pcre_fullinfo() than to examine
+ // all_options(), since options_ could have changed bewteen
+ // compile-time and now, but this is simpler and safe enough.
+ // Modified by PH to add ANY and ANYCRLF.
+ if (start+1 < static_cast<int>(str->length()) &&
+ (*str)[start] == '\r' && (*str)[start+1] == '\n' &&
+ (NewlineMode(options_.all_options()) == PCRE_NEWLINE_CRLF ||
+ NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANY ||
+ NewlineMode(options_.all_options()) == PCRE_NEWLINE_ANYCRLF)
+ ) {
+ matchend++;
+ }
+ // We also need to advance more than one char if we're in utf8 mode.
+#ifdef SUPPORT_UTF8
+ if (options_.utf8()) {
+ while (matchend < static_cast<int>(str->length()) &&
+ ((*str)[matchend] & 0xc0) == 0x80)
+ matchend++;
+ }
+#endif
+ if (matchend <= static_cast<int>(str->length()))
+ out.append(*str, start, matchend - start);
+ start = matchend;
+ } else {
+ out.append(*str, start, matchstart - start);
+ Rewrite(&out, rewrite, *str, vec, matches);
+ start = matchend;
+ lastend = matchend;
+ count++;
+ }
+ }
+
+ if (count == 0)
+ return 0;
+
+ if (start < static_cast<int>(str->length()))
+ out.append(*str, start, str->length() - start);
+ swap(out, *str);
+ return count;
+}
+
+bool RE::Extract(const StringPiece& rewrite,
+ const StringPiece& text,
+ string *out) const {
+ int vec[kVecSize];
+ int matches = TryMatch(text, 0, UNANCHORED, vec, kVecSize);
+ if (matches == 0)
+ return false;
+ out->erase();
+ return Rewrite(out, rewrite, text, vec, matches);
+}
+
+/*static*/ string RE::QuoteMeta(const StringPiece& unquoted) {
+ string result;
+
+ // Escape any ascii character not in [A-Za-z_0-9].
+ //
+ // Note that it's legal to escape a character even if it has no
+ // special meaning in a regular expression -- so this function does
+ // that. (This also makes it identical to the perl function of the
+ // same name; see `perldoc -f quotemeta`.)
+ for (int ii = 0; ii < unquoted.size(); ++ii) {
+ // Note that using 'isalnum' here raises the benchmark time from
+ // 32ns to 58ns:
+ if ((unquoted[ii] < 'a' || unquoted[ii] > 'z') &&
+ (unquoted[ii] < 'A' || unquoted[ii] > 'Z') &&
+ (unquoted[ii] < '0' || unquoted[ii] > '9') &&
+ unquoted[ii] != '_' &&
+ // If this is the part of a UTF8 or Latin1 character, we need
+ // to copy this byte without escaping. Experimentally this is
+ // what works correctly with the regexp library.
+ !(unquoted[ii] & 128)) {
+ result += '\\';
+ }
+ result += unquoted[ii];
+ }
+
+ return result;
+}
+
+/***** Actual matching and rewriting code *****/
+
+int RE::TryMatch(const StringPiece& text,
+ int startpos,
+ Anchor anchor,
+ int *vec,
+ int vecsize) const {
+ pcre* re = (anchor == ANCHOR_BOTH) ? re_full_ : re_partial_;
+ if (re == NULL) {
+ //fprintf(stderr, "Matching against invalid re: %s\n", error_->c_str());
+ return 0;
+ }
+
+ pcre_extra extra = { 0, 0, 0, 0, 0, 0 };
+ if (options_.match_limit() > 0) {
+ extra.flags |= PCRE_EXTRA_MATCH_LIMIT;
+ extra.match_limit = options_.match_limit();
+ }
+ if (options_.match_limit_recursion() > 0) {
+ extra.flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION;
+ extra.match_limit_recursion = options_.match_limit_recursion();
+ }
+ int rc = pcre_exec(re, // The regular expression object
+ &extra,
+ (text.data() == NULL) ? "" : text.data(),
+ text.size(),
+ startpos,
+ (anchor == UNANCHORED) ? 0 : PCRE_ANCHORED,
+ vec,
+ vecsize);
+
+ // Handle errors
+ if (rc == PCRE_ERROR_NOMATCH) {
+ return 0;
+ } else if (rc < 0) {
+ //fprintf(stderr, "Unexpected return code: %d when matching '%s'\n",
+ // re, pattern_.c_str());
+ return 0;
+ } else if (rc == 0) {
+ // pcre_exec() returns 0 as a special case when the number of
+ // capturing subpatterns exceeds the size of the vector.
+ // When this happens, there is a match and the output vector
+ // is filled, but we miss out on the positions of the extra subpatterns.
+ rc = vecsize / 2;
+ }
+
+ return rc;
+}
+
+bool RE::DoMatchImpl(const StringPiece& text,
+ Anchor anchor,
+ int* consumed,
+ const Arg* const* args,
+ int n,
+ int* vec,
+ int vecsize) const {
+ assert((1 + n) * 3 <= vecsize); // results + PCRE workspace
+ int matches = TryMatch(text, 0, anchor, vec, vecsize);
+ assert(matches >= 0); // TryMatch never returns negatives
+ if (matches == 0)
+ return false;
+
+ *consumed = vec[1];
+
+ if (n == 0 || args == NULL) {
+ // We are not interested in results
+ return true;
+ }
+
+ if (NumberOfCapturingGroups() < n) {
+ // RE has fewer capturing groups than number of arg pointers passed in
+ return false;
+ }
+
+ // If we got here, we must have matched the whole pattern.
+ // We do not need (can not do) any more checks on the value of 'matches' here
+ // -- see the comment for TryMatch.
+ for (int i = 0; i < n; i++) {
+ const int start = vec[2*(i+1)];
+ const int limit = vec[2*(i+1)+1];
+ if (!args[i]->Parse(text.data() + start, limit-start)) {
+ // TODO: Should we indicate what the error was?
+ return false;
+ }
+ }
+
+ return true;
+}
+
+bool RE::DoMatch(const StringPiece& text,
+ Anchor anchor,
+ int* consumed,
+ const Arg* const args[],
+ int n) const {
+ assert(n >= 0);
+ size_t const vecsize = (1 + n) * 3; // results + PCRE workspace
+ // (as for kVecSize)
+ int space[21]; // use stack allocation for small vecsize (common case)
+ int* vec = vecsize <= 21 ? space : new int[vecsize];
+ bool retval = DoMatchImpl(text, anchor, consumed, args, n, vec, vecsize);
+ if (vec != space) delete [] vec;
+ return retval;
+}
+
+bool RE::Rewrite(string *out, const StringPiece &rewrite,
+ const StringPiece &text, int *vec, int veclen) const {
+ for (const char *s = rewrite.data(), *end = s + rewrite.size();
+ s < end; s++) {
+ int c = *s;
+ if (c == '\\') {
+ c = *++s;
+ if (isdigit(c)) {
+ int n = (c - '0');
+ if (n >= veclen) {
+ //fprintf(stderr, requested group %d in regexp %.*s\n",
+ // n, rewrite.size(), rewrite.data());
+ return false;
+ }
+ int start = vec[2 * n];
+ if (start >= 0)
+ out->append(text.data() + start, vec[2 * n + 1] - start);
+ } else if (c == '\\') {
+ out->push_back('\\');
+ } else {
+ //fprintf(stderr, "invalid rewrite pattern: %.*s\n",
+ // rewrite.size(), rewrite.data());
+ return false;
+ }
+ } else {
+ out->push_back(c);
+ }
+ }
+ return true;
+}
+
+// Return the number of capturing subpatterns, or -1 if the
+// regexp wasn't valid on construction.
+int RE::NumberOfCapturingGroups() const {
+ if (re_partial_ == NULL) return -1;
+
+ int result;
+ int pcre_retval = pcre_fullinfo(re_partial_, // The regular expression object
+ NULL, // We did not study the pattern
+ PCRE_INFO_CAPTURECOUNT,
+ &result);
+ assert(pcre_retval == 0);
+ return result;
+}
+
+/***** Parsers for various types *****/
+
+bool Arg::parse_null(const char* str, int n, void* dest) {
+ // We fail if somebody asked us to store into a non-NULL void* pointer
+ return (dest == NULL);
+}
+
+bool Arg::parse_string(const char* str, int n, void* dest) {
+ reinterpret_cast<string*>(dest)->assign(str, n);
+ return true;
+}
+
+bool Arg::parse_stringpiece(const char* str, int n, void* dest) {
+ reinterpret_cast<StringPiece*>(dest)->set(str, n);
+ return true;
+}
+
+bool Arg::parse_char(const char* str, int n, void* dest) {
+ if (n != 1) return false;
+ *(reinterpret_cast<char*>(dest)) = str[0];
+ return true;
+}
+
+bool Arg::parse_uchar(const char* str, int n, void* dest) {
+ if (n != 1) return false;
+ *(reinterpret_cast<unsigned char*>(dest)) = str[0];
+ return true;
+}
+
+// Largest number spec that we are willing to parse
+static const int kMaxNumberLength = 32;
+
+// REQUIRES "buf" must have length at least kMaxNumberLength+1
+// REQUIRES "n > 0"
+// Copies "str" into "buf" and null-terminates if necessary.
+// Returns one of:
+// a. "str" if no termination is needed
+// b. "buf" if the string was copied and null-terminated
+// c. "" if the input was invalid and has no hope of being parsed
+static const char* TerminateNumber(char* buf, const char* str, int n) {
+ if ((n > 0) && isspace(*str)) {
+ // We are less forgiving than the strtoxxx() routines and do not
+ // allow leading spaces.
+ return "";
+ }
+
+ // See if the character right after the input text may potentially
+ // look like a digit.
+ if (isdigit(str[n]) ||
+ ((str[n] >= 'a') && (str[n] <= 'f')) ||
+ ((str[n] >= 'A') && (str[n] <= 'F'))) {
+ if (n > kMaxNumberLength) return ""; // Input too big to be a valid number
+ memcpy(buf, str, n);
+ buf[n] = '\0';
+ return buf;
+ } else {
+ // We can parse right out of the supplied string, so return it.
+ return str;
+ }
+}
+
+bool Arg::parse_long_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ if (n == 0) return false;
+ char buf[kMaxNumberLength+1];
+ str = TerminateNumber(buf, str, n);
+ char* end;
+ errno = 0;
+ long r = strtol(str, &end, radix);
+ if (end != str + n) return false; // Leftover junk
+ if (errno) return false;
+ *(reinterpret_cast<long*>(dest)) = r;
+ return true;
+}
+
+bool Arg::parse_ulong_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ if (n == 0) return false;
+ char buf[kMaxNumberLength+1];
+ str = TerminateNumber(buf, str, n);
+ if (str[0] == '-') return false; // strtoul() on a negative number?!
+ char* end;
+ errno = 0;
+ unsigned long r = strtoul(str, &end, radix);
+ if (end != str + n) return false; // Leftover junk
+ if (errno) return false;
+ *(reinterpret_cast<unsigned long*>(dest)) = r;
+ return true;
+}
+
+bool Arg::parse_short_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ long r;
+ if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse
+ if (r < SHRT_MIN || r > SHRT_MAX) return false; // Out of range
+ *(reinterpret_cast<short*>(dest)) = static_cast<short>(r);
+ return true;
+}
+
+bool Arg::parse_ushort_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ unsigned long r;
+ if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse
+ if (r > USHRT_MAX) return false; // Out of range
+ *(reinterpret_cast<unsigned short*>(dest)) = static_cast<unsigned short>(r);
+ return true;
+}
+
+bool Arg::parse_int_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ long r;
+ if (!parse_long_radix(str, n, &r, radix)) return false; // Could not parse
+ if (r < INT_MIN || r > INT_MAX) return false; // Out of range
+ *(reinterpret_cast<int*>(dest)) = r;
+ return true;
+}
+
+bool Arg::parse_uint_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+ unsigned long r;
+ if (!parse_ulong_radix(str, n, &r, radix)) return false; // Could not parse
+ if (r > UINT_MAX) return false; // Out of range
+ *(reinterpret_cast<unsigned int*>(dest)) = r;
+ return true;
+}
+
+bool Arg::parse_longlong_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+#ifndef HAVE_LONG_LONG
+ return false;
+#else
+ if (n == 0) return false;
+ char buf[kMaxNumberLength+1];
+ str = TerminateNumber(buf, str, n);
+ char* end;
+ errno = 0;
+#if defined HAVE_STRTOQ
+ long long r = strtoq(str, &end, radix);
+#elif defined HAVE_STRTOLL
+ long long r = strtoll(str, &end, radix);
+#elif defined HAVE__STRTOI64
+ long long r = _strtoi64(str, &end, radix);
+#else
+#error parse_longlong_radix: cannot convert input to a long-long
+#endif
+ if (end != str + n) return false; // Leftover junk
+ if (errno) return false;
+ *(reinterpret_cast<long long*>(dest)) = r;
+ return true;
+#endif /* HAVE_LONG_LONG */
+}
+
+bool Arg::parse_ulonglong_radix(const char* str,
+ int n,
+ void* dest,
+ int radix) {
+#ifndef HAVE_UNSIGNED_LONG_LONG
+ return false;
+#else
+ if (n == 0) return false;
+ char buf[kMaxNumberLength+1];
+ str = TerminateNumber(buf, str, n);
+ if (str[0] == '-') return false; // strtoull() on a negative number?!
+ char* end;
+ errno = 0;
+#if defined HAVE_STRTOQ
+ unsigned long long r = strtouq(str, &end, radix);
+#elif defined HAVE_STRTOLL
+ unsigned long long r = strtoull(str, &end, radix);
+#elif defined HAVE__STRTOI64
+ unsigned long long r = _strtoui64(str, &end, radix);
+#else
+#error parse_ulonglong_radix: cannot convert input to a long-long
+#endif
+ if (end != str + n) return false; // Leftover junk
+ if (errno) return false;
+ *(reinterpret_cast<unsigned long long*>(dest)) = r;
+ return true;
+#endif /* HAVE_UNSIGNED_LONG_LONG */
+}
+
+bool Arg::parse_double(const char* str, int n, void* dest) {
+ if (n == 0) return false;
+ static const int kMaxLength = 200;
+ char buf[kMaxLength];
+ if (n >= kMaxLength) return false;
+ memcpy(buf, str, n);
+ buf[n] = '\0';
+ errno = 0;
+ char* end;
+ double r = strtod(buf, &end);
+ if (end != buf + n) return false; // Leftover junk
+ if (errno) return false;
+ *(reinterpret_cast<double*>(dest)) = r;
+ return true;
+}
+
+bool Arg::parse_float(const char* str, int n, void* dest) {
+ double r;
+ if (!parse_double(str, n, &r)) return false;
+ *(reinterpret_cast<float*>(dest)) = static_cast<float>(r);
+ return true;
+}
+
+
+#define DEFINE_INTEGER_PARSERS(name) \
+ bool Arg::parse_##name(const char* str, int n, void* dest) { \
+ return parse_##name##_radix(str, n, dest, 10); \
+ } \
+ bool Arg::parse_##name##_hex(const char* str, int n, void* dest) { \
+ return parse_##name##_radix(str, n, dest, 16); \
+ } \
+ bool Arg::parse_##name##_octal(const char* str, int n, void* dest) { \
+ return parse_##name##_radix(str, n, dest, 8); \
+ } \
+ bool Arg::parse_##name##_cradix(const char* str, int n, void* dest) { \
+ return parse_##name##_radix(str, n, dest, 0); \
+ }
+
+DEFINE_INTEGER_PARSERS(short) /* */
+DEFINE_INTEGER_PARSERS(ushort) /* */
+DEFINE_INTEGER_PARSERS(int) /* Don't use semicolons after these */
+DEFINE_INTEGER_PARSERS(uint) /* statements because they can cause */
+DEFINE_INTEGER_PARSERS(long) /* compiler warnings if the checking */
+DEFINE_INTEGER_PARSERS(ulong) /* level is turned up high enough. */
+DEFINE_INTEGER_PARSERS(longlong) /* */
+DEFINE_INTEGER_PARSERS(ulonglong) /* */
+
+#undef DEFINE_INTEGER_PARSERS
+
+} // namespace pcrecpp
Added: httpd/httpd/vendor/pcre/current/pcrecpp.h
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcrecpp.h?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcrecpp.h (added)
+++ httpd/httpd/vendor/pcre/current/pcrecpp.h Mon Nov 26 08:49:53 2007
@@ -0,0 +1,700 @@
+// Copyright (c) 2005, Google Inc.
+// All rights reserved.
+//
+// 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 Google Inc. 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.
+//
+// Author: Sanjay Ghemawat
+// Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005
+
+#ifndef _PCRECPP_H
+#define _PCRECPP_H
+
+// C++ interface to the pcre regular-expression library. RE supports
+// Perl-style regular expressions (with extensions like \d, \w, \s,
+// ...).
+//
+// -----------------------------------------------------------------------
+// REGEXP SYNTAX:
+//
+// This module is part of the pcre library and hence supports its syntax
+// for regular expressions.
+//
+// The syntax is pretty similar to Perl's. For those not familiar
+// with Perl's regular expressions, here are some examples of the most
+// commonly used extensions:
+//
+// "hello (\\w+) world" -- \w matches a "word" character
+// "version (\\d+)" -- \d matches a digit
+// "hello\\s+world" -- \s matches any whitespace character
+// "\\b(\\w+)\\b" -- \b matches empty string at a word boundary
+// "(?i)hello" -- (?i) turns on case-insensitive matching
+// "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible
+//
+// -----------------------------------------------------------------------
+// MATCHING INTERFACE:
+//
+// The "FullMatch" operation checks that supplied text matches a
+// supplied pattern exactly.
+//
+// Example: successful match
+// pcrecpp::RE re("h.*o");
+// re.FullMatch("hello");
+//
+// Example: unsuccessful match (requires full match):
+// pcrecpp::RE re("e");
+// !re.FullMatch("hello");
+//
+// Example: creating a temporary RE object:
+// pcrecpp::RE("h.*o").FullMatch("hello");
+//
+// You can pass in a "const char*" or a "string" for "text". The
+// examples below tend to use a const char*.
+//
+// You can, as in the different examples above, store the RE object
+// explicitly in a variable or use a temporary RE object. The
+// examples below use one mode or the other arbitrarily. Either
+// could correctly be used for any of these examples.
+//
+// -----------------------------------------------------------------------
+// MATCHING WITH SUB-STRING EXTRACTION:
+//
+// You can supply extra pointer arguments to extract matched subpieces.
+//
+// Example: extracts "ruby" into "s" and 1234 into "i"
+// int i;
+// string s;
+// pcrecpp::RE re("(\\w+):(\\d+)");
+// re.FullMatch("ruby:1234", &s, &i);
+//
+// Example: does not try to extract any extra sub-patterns
+// re.FullMatch("ruby:1234", &s);
+//
+// Example: does not try to extract into NULL
+// re.FullMatch("ruby:1234", NULL, &i);
+//
+// Example: integer overflow causes failure
+// !re.FullMatch("ruby:1234567891234", NULL, &i);
+//
+// Example: fails because there aren't enough sub-patterns:
+// !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s);
+//
+// Example: fails because string cannot be stored in integer
+// !pcrecpp::RE("(.*)").FullMatch("ruby", &i);
+//
+// The provided pointer arguments can be pointers to any scalar numeric
+// type, or one of
+// string (matched piece is copied to string)
+// StringPiece (StringPiece is mutated to point to matched piece)
+// T (where "bool T::ParseFrom(const char*, int)" exists)
+// NULL (the corresponding matched sub-pattern is not copied)
+//
+// CAVEAT: An optional sub-pattern that does not exist in the matched
+// string is assigned the empty string. Therefore, the following will
+// return false (because the empty string is not a valid number):
+// int number;
+// pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number);
+//
+// -----------------------------------------------------------------------
+// DO_MATCH
+//
+// The matching interface supports at most 16 arguments per call.
+// If you need more, consider using the more general interface
+// pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch.
+//
+// -----------------------------------------------------------------------
+// PARTIAL MATCHES
+//
+// You can use the "PartialMatch" operation when you want the pattern
+// to match any substring of the text.
+//
+// Example: simple search for a string:
+// pcrecpp::RE("ell").PartialMatch("hello");
+//
+// Example: find first number in a string:
+// int number;
+// pcrecpp::RE re("(\\d+)");
+// re.PartialMatch("x*100 + 20", &number);
+// assert(number == 100);
+//
+// -----------------------------------------------------------------------
+// UTF-8 AND THE MATCHING INTERFACE:
+//
+// By default, pattern and text are plain text, one byte per character.
+// The UTF8 flag, passed to the constructor, causes both pattern
+// and string to be treated as UTF-8 text, still a byte stream but
+// potentially multiple bytes per character. In practice, the text
+// is likelier to be UTF-8 than the pattern, but the match returned
+// may depend on the UTF8 flag, so always use it when matching
+// UTF8 text. E.g., "." will match one byte normally but with UTF8
+// set may match up to three bytes of a multi-byte character.
+//
+// Example:
+// pcrecpp::RE_Options options;
+// options.set_utf8();
+// pcrecpp::RE re(utf8_pattern, options);
+// re.FullMatch(utf8_string);
+//
+// Example: using the convenience function UTF8():
+// pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8());
+// re.FullMatch(utf8_string);
+//
+// NOTE: The UTF8 option is ignored if pcre was not configured with the
+// --enable-utf8 flag.
+//
+// -----------------------------------------------------------------------
+// PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE
+//
+// PCRE defines some modifiers to change the behavior of the regular
+// expression engine.
+// The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle
+// to pass such modifiers to a RE class.
+//
+// Currently, the following modifiers are supported
+//
+// modifier description Perl corresponding
+//
+// PCRE_CASELESS case insensitive match /i
+// PCRE_MULTILINE multiple lines match /m
+// PCRE_DOTALL dot matches newlines /s
+// PCRE_DOLLAR_ENDONLY $ matches only at end N/A
+// PCRE_EXTRA strict escape parsing N/A
+// PCRE_EXTENDED ignore whitespaces /x
+// PCRE_UTF8 handles UTF8 chars built-in
+// PCRE_UNGREEDY reverses * and *? N/A
+// PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*)
+//
+// (For a full account on how each modifier works, please check the
+// PCRE API reference manual).
+//
+// (*) Both Perl and PCRE allow non matching parentheses by means of the
+// "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not
+// capture, while (ab|cd) does.
+//
+// For each modifier, there are two member functions whose name is made
+// out of the modifier in lowercase, without the "PCRE_" prefix. For
+// instance, PCRE_CASELESS is handled by
+// bool caseless(),
+// which returns true if the modifier is set, and
+// RE_Options & set_caseless(bool),
+// which sets or unsets the modifier.
+//
+// Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the
+// set_match_limit() and match_limit() member functions.
+// Setting match_limit to a non-zero value will limit the executation of
+// pcre to keep it from doing bad things like blowing the stack or taking
+// an eternity to return a result. A value of 5000 is good enough to stop
+// stack blowup in a 2MB thread stack. Setting match_limit to zero will
+// disable match limiting. Alternately, you can set match_limit_recursion()
+// which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre
+// recurses. match_limit() caps the number of matches pcre does;
+// match_limit_recrusion() caps the depth of recursion.
+//
+// Normally, to pass one or more modifiers to a RE class, you declare
+// a RE_Options object, set the appropriate options, and pass this
+// object to a RE constructor. Example:
+//
+// RE_options opt;
+// opt.set_caseless(true);
+//
+// if (RE("HELLO", opt).PartialMatch("hello world")) ...
+//
+// RE_options has two constructors. The default constructor takes no
+// arguments and creates a set of flags that are off by default.
+//
+// The optional parameter 'option_flags' is to facilitate transfer
+// of legacy code from C programs. This lets you do
+// RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
+//
+// But new code is better off doing
+// RE(pattern,
+// RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
+// (See below)
+//
+// If you are going to pass one of the most used modifiers, there are some
+// convenience functions that return a RE_Options class with the
+// appropriate modifier already set:
+// CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED()
+//
+// If you need to set several options at once, and you don't want to go
+// through the pains of declaring a RE_Options object and setting several
+// options, there is a parallel method that give you such ability on the
+// fly. You can concatenate several set_xxxxx member functions, since each
+// of them returns a reference to its class object. e.g.: to pass
+// PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one
+// statement, you may write
+//
+// RE(" ^ xyz \\s+ .* blah$", RE_Options()
+// .set_caseless(true)
+// .set_extended(true)
+// .set_multiline(true)).PartialMatch(sometext);
+//
+// -----------------------------------------------------------------------
+// SCANNING TEXT INCREMENTALLY
+//
+// The "Consume" operation may be useful if you want to repeatedly
+// match regular expressions at the front of a string and skip over
+// them as they match. This requires use of the "StringPiece" type,
+// which represents a sub-range of a real string. Like RE, StringPiece
+// is defined in the pcrecpp namespace.
+//
+// Example: read lines of the form "var = value" from a string.
+// string contents = ...; // Fill string somehow
+// pcrecpp::StringPiece input(contents); // Wrap in a StringPiece
+//
+// string var;
+// int value;
+// pcrecpp::RE re("(\\w+) = (\\d+)\n");
+// while (re.Consume(&input, &var, &value)) {
+// ...;
+// }
+//
+// Each successful call to "Consume" will set "var/value", and also
+// advance "input" so it points past the matched text.
+//
+// The "FindAndConsume" operation is similar to "Consume" but does not
+// anchor your match at the beginning of the string. For example, you
+// could extract all words from a string by repeatedly calling
+// pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word)
+//
+// -----------------------------------------------------------------------
+// PARSING HEX/OCTAL/C-RADIX NUMBERS
+//
+// By default, if you pass a pointer to a numeric value, the
+// corresponding text is interpreted as a base-10 number. You can
+// instead wrap the pointer with a call to one of the operators Hex(),
+// Octal(), or CRadix() to interpret the text in another base. The
+// CRadix operator interprets C-style "0" (base-8) and "0x" (base-16)
+// prefixes, but defaults to base-10.
+//
+// Example:
+// int a, b, c, d;
+// pcrecpp::RE re("(.*) (.*) (.*) (.*)");
+// re.FullMatch("100 40 0100 0x40",
+// pcrecpp::Octal(&a), pcrecpp::Hex(&b),
+// pcrecpp::CRadix(&c), pcrecpp::CRadix(&d));
+// will leave 64 in a, b, c, and d.
+//
+// -----------------------------------------------------------------------
+// REPLACING PARTS OF STRINGS
+//
+// You can replace the first match of "pattern" in "str" with
+// "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9)
+// can be used to insert text matching corresponding parenthesized
+// group from the pattern. \0 in "rewrite" refers to the entire
+// matching text. E.g.,
+//
+// string s = "yabba dabba doo";
+// pcrecpp::RE("b+").Replace("d", &s);
+//
+// will leave "s" containing "yada dabba doo". The result is true if
+// the pattern matches and a replacement occurs, or false otherwise.
+//
+// GlobalReplace() is like Replace(), except that it replaces all
+// occurrences of the pattern in the string with the rewrite.
+// Replacements are not subject to re-matching. E.g.,
+//
+// string s = "yabba dabba doo";
+// pcrecpp::RE("b+").GlobalReplace("d", &s);
+//
+// will leave "s" containing "yada dada doo". It returns the number
+// of replacements made.
+//
+// Extract() is like Replace(), except that if the pattern matches,
+// "rewrite" is copied into "out" (an additional argument) with
+// substitutions. The non-matching portions of "text" are ignored.
+// Returns true iff a match occurred and the extraction happened
+// successfully. If no match occurs, the string is left unaffected.
+
+
+#include <string>
+#include <pcre.h>
+#include <pcrecpparg.h> // defines the Arg class
+// This isn't technically needed here, but we include it
+// anyway so folks who include pcrecpp.h don't have to.
+#include <pcre_stringpiece.h>
+
+namespace pcrecpp {
+
+#define PCRE_SET_OR_CLEAR(b, o) \
+ if (b) all_options_ |= (o); else all_options_ &= ~(o); \
+ return *this
+
+#define PCRE_IS_SET(o) \
+ (all_options_ & o) == o
+
+// We convert user-passed pointers into special Arg objects
+PCRECPP_EXP_DECL Arg no_arg;
+
+/***** Compiling regular expressions: the RE class *****/
+
+// RE_Options allow you to set options to be passed along to pcre,
+// along with other options we put on top of pcre.
+// Only 9 modifiers, plus match_limit and match_limit_recursion,
+// are supported now.
+class PCRECPP_EXP_DEFN RE_Options {
+ public:
+ // constructor
+ RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {}
+
+ // alternative constructor.
+ // To facilitate transfer of legacy code from C programs
+ //
+ // This lets you do
+ // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str);
+ // But new code is better off doing
+ // RE(pattern,
+ // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str);
+ RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0),
+ all_options_(option_flags) {}
+ // we're fine with the default destructor, copy constructor, etc.
+
+ // accessors and mutators
+ int match_limit() const { return match_limit_; };
+ RE_Options &set_match_limit(int limit) {
+ match_limit_ = limit;
+ return *this;
+ }
+
+ int match_limit_recursion() const { return match_limit_recursion_; };
+ RE_Options &set_match_limit_recursion(int limit) {
+ match_limit_recursion_ = limit;
+ return *this;
+ }
+
+ bool caseless() const {
+ return PCRE_IS_SET(PCRE_CASELESS);
+ }
+ RE_Options &set_caseless(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_CASELESS);
+ }
+
+ bool multiline() const {
+ return PCRE_IS_SET(PCRE_MULTILINE);
+ }
+ RE_Options &set_multiline(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE);
+ }
+
+ bool dotall() const {
+ return PCRE_IS_SET(PCRE_DOTALL);
+ }
+ RE_Options &set_dotall(bool x) {
+ PCRE_SET_OR_CLEAR(x,PCRE_DOTALL);
+ }
+
+ bool extended() const {
+ return PCRE_IS_SET(PCRE_EXTENDED);
+ }
+ RE_Options &set_extended(bool x) {
+ PCRE_SET_OR_CLEAR(x,PCRE_EXTENDED);
+ }
+
+ bool dollar_endonly() const {
+ return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY);
+ }
+ RE_Options &set_dollar_endonly(bool x) {
+ PCRE_SET_OR_CLEAR(x,PCRE_DOLLAR_ENDONLY);
+ }
+
+ bool extra() const {
+ return PCRE_IS_SET( PCRE_EXTRA);
+ }
+ RE_Options &set_extra(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_EXTRA);
+ }
+
+ bool ungreedy() const {
+ return PCRE_IS_SET(PCRE_UNGREEDY);
+ }
+ RE_Options &set_ungreedy(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY);
+ }
+
+ bool utf8() const {
+ return PCRE_IS_SET(PCRE_UTF8);
+ }
+ RE_Options &set_utf8(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_UTF8);
+ }
+
+ bool no_auto_capture() const {
+ return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE);
+ }
+ RE_Options &set_no_auto_capture(bool x) {
+ PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE);
+ }
+
+ RE_Options &set_all_options(int opt) {
+ all_options_ = opt;
+ return *this;
+ }
+ int all_options() const {
+ return all_options_ ;
+ }
+
+ // TODO: add other pcre flags
+
+ private:
+ int match_limit_;
+ int match_limit_recursion_;
+ int all_options_;
+};
+
+// These functions return some common RE_Options
+static inline RE_Options UTF8() {
+ return RE_Options().set_utf8(true);
+}
+
+static inline RE_Options CASELESS() {
+ return RE_Options().set_caseless(true);
+}
+static inline RE_Options MULTILINE() {
+ return RE_Options().set_multiline(true);
+}
+
+static inline RE_Options DOTALL() {
+ return RE_Options().set_dotall(true);
+}
+
+static inline RE_Options EXTENDED() {
+ return RE_Options().set_extended(true);
+}
+
+// Interface for regular expression matching. Also corresponds to a
+// pre-compiled regular expression. An "RE" object is safe for
+// concurrent use by multiple threads.
+class PCRECPP_EXP_DEFN RE {
+ public:
+ // We provide implicit conversions from strings so that users can
+ // pass in a string or a "const char*" wherever an "RE" is expected.
+ RE(const string& pat) { Init(pat, NULL); }
+ RE(const string& pat, const RE_Options& option) { Init(pat, &option); }
+ RE(const char* pat) { Init(pat, NULL); }
+ RE(const char* pat, const RE_Options& option) { Init(pat, &option); }
+ RE(const unsigned char* pat) {
+ Init(reinterpret_cast<const char*>(pat), NULL);
+ }
+ RE(const unsigned char* pat, const RE_Options& option) {
+ Init(reinterpret_cast<const char*>(pat), &option);
+ }
+
+ // Copy constructor & assignment - note that these are expensive
+ // because they recompile the expression.
+ RE(const RE& re) { Init(re.pattern_, &re.options_); }
+ const RE& operator=(const RE& re) {
+ if (this != &re) {
+ Cleanup();
+
+ // This is the code that originally came from Google
+ // Init(re.pattern_.c_str(), &re.options_);
+
+ // This is the replacement from Ari Pollak
+ Init(re.pattern_, &re.options_);
+ }
+ return *this;
+ }
+
+
+ ~RE();
+
+ // The string specification for this RE. E.g.
+ // RE re("ab*c?d+");
+ // re.pattern(); // "ab*c?d+"
+ const string& pattern() const { return pattern_; }
+
+ // If RE could not be created properly, returns an error string.
+ // Else returns the empty string.
+ const string& error() const { return *error_; }
+
+ /***** The useful part: the matching interface *****/
+
+ // This is provided so one can do pattern.ReplaceAll() just as
+ // easily as ReplaceAll(pattern-text, ....)
+
+ bool FullMatch(const StringPiece& text,
+ const Arg& ptr1 = no_arg,
+ const Arg& ptr2 = no_arg,
+ const Arg& ptr3 = no_arg,
+ const Arg& ptr4 = no_arg,
+ const Arg& ptr5 = no_arg,
+ const Arg& ptr6 = no_arg,
+ const Arg& ptr7 = no_arg,
+ const Arg& ptr8 = no_arg,
+ const Arg& ptr9 = no_arg,
+ const Arg& ptr10 = no_arg,
+ const Arg& ptr11 = no_arg,
+ const Arg& ptr12 = no_arg,
+ const Arg& ptr13 = no_arg,
+ const Arg& ptr14 = no_arg,
+ const Arg& ptr15 = no_arg,
+ const Arg& ptr16 = no_arg) const;
+
+ bool PartialMatch(const StringPiece& text,
+ const Arg& ptr1 = no_arg,
+ const Arg& ptr2 = no_arg,
+ const Arg& ptr3 = no_arg,
+ const Arg& ptr4 = no_arg,
+ const Arg& ptr5 = no_arg,
+ const Arg& ptr6 = no_arg,
+ const Arg& ptr7 = no_arg,
+ const Arg& ptr8 = no_arg,
+ const Arg& ptr9 = no_arg,
+ const Arg& ptr10 = no_arg,
+ const Arg& ptr11 = no_arg,
+ const Arg& ptr12 = no_arg,
+ const Arg& ptr13 = no_arg,
+ const Arg& ptr14 = no_arg,
+ const Arg& ptr15 = no_arg,
+ const Arg& ptr16 = no_arg) const;
+
+ bool Consume(StringPiece* input,
+ const Arg& ptr1 = no_arg,
+ const Arg& ptr2 = no_arg,
+ const Arg& ptr3 = no_arg,
+ const Arg& ptr4 = no_arg,
+ const Arg& ptr5 = no_arg,
+ const Arg& ptr6 = no_arg,
+ const Arg& ptr7 = no_arg,
+ const Arg& ptr8 = no_arg,
+ const Arg& ptr9 = no_arg,
+ const Arg& ptr10 = no_arg,
+ const Arg& ptr11 = no_arg,
+ const Arg& ptr12 = no_arg,
+ const Arg& ptr13 = no_arg,
+ const Arg& ptr14 = no_arg,
+ const Arg& ptr15 = no_arg,
+ const Arg& ptr16 = no_arg) const;
+
+ bool FindAndConsume(StringPiece* input,
+ const Arg& ptr1 = no_arg,
+ const Arg& ptr2 = no_arg,
+ const Arg& ptr3 = no_arg,
+ const Arg& ptr4 = no_arg,
+ const Arg& ptr5 = no_arg,
+ const Arg& ptr6 = no_arg,
+ const Arg& ptr7 = no_arg,
+ const Arg& ptr8 = no_arg,
+ const Arg& ptr9 = no_arg,
+ const Arg& ptr10 = no_arg,
+ const Arg& ptr11 = no_arg,
+ const Arg& ptr12 = no_arg,
+ const Arg& ptr13 = no_arg,
+ const Arg& ptr14 = no_arg,
+ const Arg& ptr15 = no_arg,
+ const Arg& ptr16 = no_arg) const;
+
+ bool Replace(const StringPiece& rewrite,
+ string *str) const;
+
+ int GlobalReplace(const StringPiece& rewrite,
+ string *str) const;
+
+ bool Extract(const StringPiece &rewrite,
+ const StringPiece &text,
+ string *out) const;
+
+ // Escapes all potentially meaningful regexp characters in
+ // 'unquoted'. The returned string, used as a regular expression,
+ // will exactly match the original string. For example,
+ // 1.5-2.0?
+ // may become:
+ // 1\.5\-2\.0\?
+ static string QuoteMeta(const StringPiece& unquoted);
+
+
+ /***** Generic matching interface *****/
+
+ // Type of match (TODO: Should be restructured as part of RE_Options)
+ enum Anchor {
+ UNANCHORED, // No anchoring
+ ANCHOR_START, // Anchor at start only
+ ANCHOR_BOTH // Anchor at start and end
+ };
+
+ // General matching routine. Stores the length of the match in
+ // "*consumed" if successful.
+ bool DoMatch(const StringPiece& text,
+ Anchor anchor,
+ int* consumed,
+ const Arg* const* args, int n) const;
+
+ // Return the number of capturing subpatterns, or -1 if the
+ // regexp wasn't valid on construction.
+ int NumberOfCapturingGroups() const;
+
+ private:
+
+ void Init(const string& pattern, const RE_Options* options);
+ void Cleanup();
+
+ // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with
+ // pairs of integers for the beginning and end positions of matched
+ // text. The first pair corresponds to the entire matched text;
+ // subsequent pairs correspond, in order, to parentheses-captured
+ // matches. Returns the number of pairs (one more than the number of
+ // the last subpattern with a match) if matching was successful
+ // and zero if the match failed.
+ // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching
+ // against "foo", "bar", and "baz" respectively.
+ // When matching RE("(foo)|hello") against "hello", it will return 1.
+ // But the values for all subpattern are filled in into "vec".
+ int TryMatch(const StringPiece& text,
+ int startpos,
+ Anchor anchor,
+ int *vec,
+ int vecsize) const;
+
+ // Append the "rewrite" string, with backslash subsitutions from "text"
+ // and "vec", to string "out".
+ bool Rewrite(string *out,
+ const StringPiece& rewrite,
+ const StringPiece& text,
+ int *vec,
+ int veclen) const;
+
+ // internal implementation for DoMatch
+ bool DoMatchImpl(const StringPiece& text,
+ Anchor anchor,
+ int* consumed,
+ const Arg* const args[],
+ int n,
+ int* vec,
+ int vecsize) const;
+
+ // Compile the regexp for the specified anchoring mode
+ pcre* Compile(Anchor anchor);
+
+ string pattern_;
+ RE_Options options_;
+ pcre* re_full_; // For full matches
+ pcre* re_partial_; // For partial matches
+ const string* error_; // Error indicator (or points to empty string)
+};
+
+} // namespace pcrecpp
+
+#endif /* _PCRECPP_H */
Added: httpd/httpd/vendor/pcre/current/pcrecpp_internal.h
URL: http://svn.apache.org/viewvc/httpd/httpd/vendor/pcre/current/pcrecpp_internal.h?rev=598339&view=auto
==============================================================================
--- httpd/httpd/vendor/pcre/current/pcrecpp_internal.h (added)
+++ httpd/httpd/vendor/pcre/current/pcrecpp_internal.h Mon Nov 26 08:49:53 2007
@@ -0,0 +1,68 @@
+/*************************************************
+* Perl-Compatible Regular Expressions *
+*************************************************/
+
+/*
+-----------------------------------------------------------------------------
+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.
+-----------------------------------------------------------------------------
+*/
+
+
+#ifndef PCRECPP_INTERNAL_H
+#define PCRECPP_INTERNAL_H
+
+/* When compiling a DLL for Windows, the exported symbols have to be declared
+using some MS magic. I found some useful information on this web page:
+http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the
+information there, using __declspec(dllexport) without "extern" we have a
+definition; with "extern" we have a declaration. The settings here override the
+setting in pcre.h. We use:
+
+ PCRECPP_EXP_DECL for declarations
+ PCRECPP_EXP_DEFN for definitions of exported functions
+
+*/
+
+#ifndef PCRECPP_EXP_DECL
+# ifdef _WIN32
+# ifndef PCRECPP_STATIC
+# define PCRECPP_EXP_DECL extern __declspec(dllexport)
+# define PCRECPP_EXP_DEFN __declspec(dllexport)
+# else
+# define PCRECPP_EXP_DECL extern
+# define PCRECPP_EXP_DEFN
+# endif
+# else
+# define PCRECPP_EXP_DECL extern
+# define PCRECPP_EXP_DEFN
+# endif
+#endif
+
+#endif /* PCRECPP_INTERNAL_H */
+
+/* End of pcrecpp_internal.h */