6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-26 05:32:25 +00:00
Code Issues Projects Releases Wiki Activity

Add regular expression matching support, based on OpenBSD regexec()/regcomp()

Browse Source 
implementation.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@80493 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Torok Edwin 2009-08-30 08:24:09 +00:00
parent 7438106207
commit ce0c81e7dd
18 changed files with 4532 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
LICENSE.TXT
View File

@ -66,3 +66,4 @@ Autoconf llvm/autoconf
llvm/projects/sample/autoconf
CellSPU backend llvm/lib/Target/CellSPU/README.txt
Google Test llvm/utils/unittest/googletest
OpenBSD regex llvm/lib/Support/{reg*, COPYRIGHT.regex}

756
docs/re_format.7 Normal file
View File

@ -0,0 +1,756 @@
.\" $OpenBSD: re_format.7,v 1.14 2007/05/31 19:19:30 jmc Exp $
.\"
.\" Copyright (c) 1997, Phillip F Knaack. All rights reserved.
.\"
.\" Copyright (c) 1992, 1993, 1994 Henry Spencer.
.\" Copyright (c) 1992, 1993, 1994
.\" The Regents of the University of California. All rights reserved.
.\"
.\" This code is derived from software contributed to Berkeley by
.\" Henry Spencer.
.\"
.\" Redistribution and use in source and binary forms, with or without
.\" modification, are permitted provided that the following conditions
.\" are met:
.\" 1. Redistributions of source code must retain the above copyright
.\" notice, this list of conditions and the following disclaimer.
.\" 2. 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.
.\" 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
.\"
.\" @(#)re_format.7 8.3 (Berkeley) 3/20/94
.\"
.Dd $Mdocdate: May 31 2007 $
.Dt RE_FORMAT 7
.Os
.Sh NAME
.Nm re_format
.Nd POSIX regular expressions
.Sh DESCRIPTION
Regular expressions (REs),
as defined in
.St -p1003.1-2004 ,
come in two forms:
basic regular expressions
(BREs)
and extended regular expressions
(EREs).
Both forms of regular expressions are supported
by the interfaces described in
.Xr regex 3 .
Applications dealing with regular expressions
may use one or the other form
(or indeed both).
For example,
.Xr ed 1
uses BREs,
whilst
.Xr egrep 1
talks EREs.
Consult the manual page for the specific application to find out which
it uses.
.Pp
POSIX leaves some aspects of RE syntax and semantics open;
.Sq **
marks decisions on these aspects that
may not be fully portable to other POSIX implementations.
.Pp
This manual page first describes regular expressions in general,
specifically extended regular expressions,
and then discusses differences between them and basic regular expressions.
.Sh EXTENDED REGULAR EXPRESSIONS
An ERE is one** or more non-empty**
.Em branches ,
separated by
.Sq \*(Ba .
It matches anything that matches one of the branches.
.Pp
A branch is one** or more
.Em pieces ,
concatenated.
It matches a match for the first, followed by a match for the second, etc.
.Pp
A piece is an
.Em atom
possibly followed by a single**
.Sq * ,
.Sq + ,
.Sq ?\& ,
or
.Em bound .
An atom followed by
.Sq *
matches a sequence of 0 or more matches of the atom.
An atom followed by
.Sq +
matches a sequence of 1 or more matches of the atom.
An atom followed by
.Sq ?\&
matches a sequence of 0 or 1 matches of the atom.
.Pp
A bound is
.Sq {
followed by an unsigned decimal integer,
possibly followed by
.Sq ,\&
possibly followed by another unsigned decimal integer,
always followed by
.Sq } .
The integers must lie between 0 and
.Dv RE_DUP_MAX
(255**) inclusive,
and if there are two of them, the first may not exceed the second.
An atom followed by a bound containing one integer
.Ar i
and no comma matches
a sequence of exactly
.Ar i
matches of the atom.
An atom followed by a bound
containing one integer
.Ar i
and a comma matches
a sequence of
.Ar i
or more matches of the atom.
An atom followed by a bound
containing two integers
.Ar i
and
.Ar j
matches a sequence of
.Ar i
through
.Ar j
(inclusive) matches of the atom.
.Pp
An atom is a regular expression enclosed in
.Sq ()
(matching a part of the regular expression),
an empty set of
.Sq ()
(matching the null string)**,
a
.Em bracket expression
(see below),
.Sq .\&
(matching any single character),
.Sq ^
(matching the null string at the beginning of a line),
.Sq $
(matching the null string at the end of a line),
a
.Sq \e
followed by one of the characters
.Sq ^.[$()|*+?{\e
(matching that character taken as an ordinary character),
a
.Sq \e
followed by any other character**
(matching that character taken as an ordinary character,
as if the
.Sq \e
had not been present**),
or a single character with no other significance (matching that character).
A
.Sq {
followed by a character other than a digit is an ordinary character,
not the beginning of a bound**.
It is illegal to end an RE with
.Sq \e .
.Pp
A bracket expression is a list of characters enclosed in
.Sq [] .
It normally matches any single character from the list (but see below).
If the list begins with
.Sq ^ ,
it matches any single character
.Em not
from the rest of the list
(but see below).
If two characters in the list are separated by
.Sq - ,
this is shorthand for the full
.Em range
of characters between those two (inclusive) in the
collating sequence, e.g.\&
.Sq [0-9]
in ASCII matches any decimal digit.
It is illegal** for two ranges to share an endpoint, e.g.\&
.Sq a-c-e .
Ranges are very collating-sequence-dependent,
and portable programs should avoid relying on them.
.Pp
To include a literal
.Sq ]\&
in the list, make it the first character
(following a possible
.Sq ^ ) .
To include a literal
.Sq - ,
make it the first or last character,
or the second endpoint of a range.
To use a literal
.Sq -
as the first endpoint of a range,
enclose it in
.Sq [.
and
.Sq .]
to make it a collating element (see below).
With the exception of these and some combinations using
.Sq [
(see next paragraphs),
all other special characters, including
.Sq \e ,
lose their special significance within a bracket expression.
.Pp
Within a bracket expression, a collating element
(a character,
a multi-character sequence that collates as if it were a single character,
or a collating-sequence name for either)
enclosed in
.Sq [.
and
.Sq .]
stands for the sequence of characters of that collating element.
The sequence is a single element of the bracket expression's list.
A bracket expression containing a multi-character collating element
can thus match more than one character,
e.g. if the collating sequence includes a
.Sq ch
collating element,
then the RE
.Sq [[.ch.]]*c
matches the first five characters of
.Sq chchcc .
.Pp
Within a bracket expression, a collating element enclosed in
.Sq [=
and
.Sq =]
is an equivalence class, standing for the sequences of characters
of all collating elements equivalent to that one, including itself.
(If there are no other equivalent collating elements,
the treatment is as if the enclosing delimiters were
.Sq [.
and
.Sq .] . )
For example, if
.Sq x
and
.Sq y
are the members of an equivalence class,
then
.Sq [[=x=]] ,
.Sq [[=y=]] ,
and
.Sq [xy]
are all synonymous.
An equivalence class may not** be an endpoint of a range.
.Pp
Within a bracket expression, the name of a
.Em character class
enclosed
in
.Sq [:
and
.Sq :]
stands for the list of all characters belonging to that class.
Standard character class names are:
.Bd -literal -offset indent
alnum digit punct
alpha graph space
blank lower upper
cntrl print xdigit
.Ed
.Pp
These stand for the character classes defined in
.Xr ctype 3 .
A locale may provide others.
A character class may not be used as an endpoint of a range.
.Pp
There are two special cases** of bracket expressions:
the bracket expressions
.Sq [[:<:]]
and
.Sq [[:>:]]
match the null string at the beginning and end of a word, respectively.
A word is defined as a sequence of
characters starting and ending with a word character
which is neither preceded nor followed by
word characters.
A word character is an
.Em alnum
character (as defined by
.Xr ctype 3 )
or an underscore.
This is an extension,
compatible with but not specified by POSIX,
and should be used with
caution in software intended to be portable to other systems.
.Pp
In the event that an RE could match more than one substring of a given
string,
the RE matches the one starting earliest in the string.
If the RE could match more than one substring starting at that point,
it matches the longest.
Subexpressions also match the longest possible substrings, subject to
the constraint that the whole match be as long as possible,
with subexpressions starting earlier in the RE taking priority over
ones starting later.
Note that higher-level subexpressions thus take priority over
their lower-level component subexpressions.
.Pp
Match lengths are measured in characters, not collating elements.
A null string is considered longer than no match at all.
For example,
.Sq bb*
matches the three middle characters of
.Sq abbbc ;
.Sq (wee|week)(knights|nights)
matches all ten characters of
.Sq weeknights ;
when
.Sq (.*).*
is matched against
.Sq abc ,
the parenthesized subexpression matches all three characters;
and when
.Sq (a*)*
is matched against
.Sq bc ,
both the whole RE and the parenthesized subexpression match the null string.
.Pp
If case-independent matching is specified,
the effect is much as if all case distinctions had vanished from the
alphabet.
When an alphabetic that exists in multiple cases appears as an
ordinary character outside a bracket expression, it is effectively
transformed into a bracket expression containing both cases,
e.g.\&
.Sq x
becomes
.Sq [xX] .
When it appears inside a bracket expression,
all case counterparts of it are added to the bracket expression,
so that, for example,
.Sq [x]
becomes
.Sq [xX]
and
.Sq [^x]
becomes
.Sq [^xX] .
.Pp
No particular limit is imposed on the length of REs**.
Programs intended to be portable should not employ REs longer
than 256 bytes,
as an implementation can refuse to accept such REs and remain
POSIX-compliant.
.Pp
The following is a list of extended regular expressions:
.Bl -tag -width Ds
.It Ar c
Any character
.Ar c
not listed below matches itself.
.It \e Ns Ar c
Any backslash-escaped character
.Ar c
matches itself.
.It \&.
Matches any single character that is not a newline
.Pq Sq \en .
.It Bq Ar char-class
Matches any single character in
.Ar char-class .
To include a
.Ql \&]
in
.Ar char-class ,
it must be the first character.
A range of characters may be specified by separating the end characters
of the range with a
.Ql - ;
e.g.\&
.Ar a-z
specifies the lower case characters.
The following literal expressions can also be used in
.Ar char-class
to specify sets of characters:
.Bd -unfilled -offset indent
[:alnum:] [:cntrl:] [:lower:] [:space:]
[:alpha:] [:digit:] [:print:] [:upper:]
[:blank:] [:graph:] [:punct:] [:xdigit:]
.Ed
.Pp
If
.Ql -
appears as the first or last character of
.Ar char-class ,
then it matches itself.
All other characters in
.Ar char-class
match themselves.
.Pp
Patterns in
.Ar char-class
of the form
.Eo [.
.Ar col-elm
.Ec .]\&
or
.Eo [=
.Ar col-elm
.Ec =]\& ,
where
.Ar col-elm
is a collating element, are interpreted according to
.Xr setlocale 3
.Pq not currently supported .
.It Bq ^ Ns Ar char-class
Matches any single character, other than newline, not in
.Ar char-class .
.Ar char-class
is defined as above.
.It ^
If
.Sq ^
is the first character of a regular expression, then it
anchors the regular expression to the beginning of a line.
Otherwise, it matches itself.
.It $
If
.Sq $
is the last character of a regular expression,
it anchors the regular expression to the end of a line.
Otherwise, it matches itself.
.It [[:<:]]
Anchors the single character regular expression or subexpression
immediately following it to the beginning of a word.
.It [[:>:]]
Anchors the single character regular expression or subexpression
immediately following it to the end of a word.
.It Pq Ar re
Defines a subexpression
.Ar re .
Any set of characters enclosed in parentheses
matches whatever the set of characters without parentheses matches
(that is a long-winded way of saying the constructs
.Sq (re)
and
.Sq re
match identically).
.It *
Matches the single character regular expression or subexpression
immediately preceding it zero or more times.
If
.Sq *
is the first character of a regular expression or subexpression,
then it matches itself.
The
.Sq *
operator sometimes yields unexpected results.
For example, the regular expression
.Ar b*
matches the beginning of the string
.Qq abbb
(as opposed to the substring
.Qq bbb ) ,
since a null match is the only leftmost match.
.It +
Matches the singular character regular expression
or subexpression immediately preceding it
one or more times.
.It ?
Matches the singular character regular expression
or subexpression immediately preceding it
0 or 1 times.
.Sm off
.It Xo
.Pf { Ar n , m No }\ \&
.Pf { Ar n , No }\ \&
.Pf { Ar n No }
.Xc
.Sm on
Matches the single character regular expression or subexpression
immediately preceding it at least
.Ar n
and at most
.Ar m
times.
If
.Ar m
is omitted, then it matches at least
.Ar n
times.
If the comma is also omitted, then it matches exactly
.Ar n
times.
.It \*(Ba
Used to separate patterns.
For example,
the pattern
.Sq cat\*(Badog
matches either
.Sq cat
or
.Sq dog .
.El
.Sh BASIC REGULAR EXPRESSIONS
Basic regular expressions differ in several respects:
.Bl -bullet -offset 3n
.It
.Sq \*(Ba ,
.Sq + ,
and
.Sq ?\&
are ordinary characters and there is no equivalent
for their functionality.
.It
The delimiters for bounds are
.Sq \e{
and
.Sq \e} ,
with
.Sq {
and
.Sq }
by themselves ordinary characters.
.It
The parentheses for nested subexpressions are
.Sq \e(
and
.Sq \e) ,
with
.Sq (
and
.Sq )\&
by themselves ordinary characters.
.It
.Sq ^
is an ordinary character except at the beginning of the
RE or** the beginning of a parenthesized subexpression.
.It
.Sq $
is an ordinary character except at the end of the
RE or** the end of a parenthesized subexpression.
.It
.Sq *
is an ordinary character if it appears at the beginning of the
RE or the beginning of a parenthesized subexpression
(after a possible leading
.Sq ^ ) .
.It
Finally, there is one new type of atom, a
.Em back-reference :
.Sq \e
followed by a non-zero decimal digit
.Ar d
matches the same sequence of characters matched by the
.Ar d Ns th
parenthesized subexpression
(numbering subexpressions by the positions of their opening parentheses,
left to right),
so that, for example,
.Sq \e([bc]\e)\e1
matches
.Sq bb\&
or
.Sq cc
but not
.Sq bc .
.El
.Pp
The following is a list of basic regular expressions:
.Bl -tag -width Ds
.It Ar c
Any character
.Ar c
not listed below matches itself.
.It \e Ns Ar c
Any backslash-escaped character
.Ar c ,
except for
.Sq { ,
.Sq } ,
.Sq \&( ,
and
.Sq \&) ,
matches itself.
.It \&.
Matches any single character that is not a newline
.Pq Sq \en .
.It Bq Ar char-class
Matches any single character in
.Ar char-class .
To include a
.Ql \&]
in
.Ar char-class ,
it must be the first character.
A range of characters may be specified by separating the end characters
of the range with a
.Ql - ;
e.g.\&
.Ar a-z
specifies the lower case characters.
The following literal expressions can also be used in
.Ar char-class
to specify sets of characters:
.Bd -unfilled -offset indent
[:alnum:] [:cntrl:] [:lower:] [:space:]
[:alpha:] [:digit:] [:print:] [:upper:]
[:blank:] [:graph:] [:punct:] [:xdigit:]
.Ed
.Pp
If
.Ql -
appears as the first or last character of
.Ar char-class ,
then it matches itself.
All other characters in
.Ar char-class
match themselves.
.Pp
Patterns in
.Ar char-class
of the form
.Eo [.
.Ar col-elm
.Ec .]\&
or
.Eo [=
.Ar col-elm
.Ec =]\& ,
where
.Ar col-elm
is a collating element, are interpreted according to
.Xr setlocale 3
.Pq not currently supported .
.It Bq ^ Ns Ar char-class
Matches any single character, other than newline, not in
.Ar char-class .
.Ar char-class
is defined as above.
.It ^
If
.Sq ^
is the first character of a regular expression, then it
anchors the regular expression to the beginning of a line.
Otherwise, it matches itself.
.It $
If
.Sq $
is the last character of a regular expression,
it anchors the regular expression to the end of a line.
Otherwise, it matches itself.
.It [[:<:]]
Anchors the single character regular expression or subexpression
immediately following it to the beginning of a word.
.It [[:>:]]
Anchors the single character regular expression or subexpression
immediately following it to the end of a word.
.It \e( Ns Ar re Ns \e)
Defines a subexpression
.Ar re .
Subexpressions may be nested.
A subsequent backreference of the form
.Pf \e Ns Ar n ,
where
.Ar n
is a number in the range [1,9], expands to the text matched by the
.Ar n Ns th
subexpression.
For example, the regular expression
.Ar \e(.*\e)\e1
matches any string consisting of identical adjacent substrings.
Subexpressions are ordered relative to their left delimiter.
.It *
Matches the single character regular expression or subexpression
immediately preceding it zero or more times.
If
.Sq *
is the first character of a regular expression or subexpression,
then it matches itself.
The
.Sq *
operator sometimes yields unexpected results.
For example, the regular expression
.Ar b*
matches the beginning of the string
.Qq abbb
(as opposed to the substring
.Qq bbb ) ,
since a null match is the only leftmost match.
.Sm off
.It Xo
.Pf \e{ Ar n , m No \e}\ \&
.Pf \e{ Ar n , No \e}\ \&
.Pf \e{ Ar n No \e}
.Xc
.Sm on
Matches the single character regular expression or subexpression
immediately preceding it at least
.Ar n
and at most
.Ar m
times.
If
.Ar m
is omitted, then it matches at least
.Ar n
times.
If the comma is also omitted, then it matches exactly
.Ar n
times.
.El
.Sh SEE ALSO
.Xr ctype 3 ,
.Xr regex 3
.Sh STANDARDS
.St -p1003.1-2004 :
Base Definitions, Chapter 9 (Regular Expressions).
.Sh BUGS
Having two kinds of REs is a botch.
.Pp
The current POSIX spec says that
.Sq )\&
is an ordinary character in the absence of an unmatched
.Sq ( ;
this was an unintentional result of a wording error,
and change is likely.
Avoid relying on it.
.Pp
Back-references are a dreadful botch,
posing major problems for efficient implementations.
They are also somewhat vaguely defined
(does
.Sq a\e(\e(b\e)*\e2\e)*d
match
.Sq abbbd ? ) .
Avoid using them.
.Pp
POSIX's specification of case-independent matching is vague.
The
.Dq one case implies all cases
definition given above
is the current consensus among implementors as to the right interpretation.
.Pp
The syntax for word boundaries is incredibly ugly.

64
include/llvm/Support/Regex.h Normal file
View File

@ -0,0 +1,64 @@
//===-- Regex.h - Regular Expression matcher implementation -*- C++ -*-----===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements a POSIX regular expression matcher.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
struct llvm_regex;
namespace llvm {
class Regex {
public:
enum {
/// Compile with support for subgroup matches, this is just to make
/// constructs like Regex("...", 0) more readable as Regex("...", Sub).
Sub=0,
/// Compile for matching that ignores upper/lower case distinctions.
IgnoreCase=1,
/// Compile for matching that need only report success or failure,
/// not what was matched.
NoSub=2,
/// Compile for newline-sensitive matching. With this flag '[^' bracket
/// expressions and '.' never match newline. A ^ anchor matches the
/// null string after any newline in the string in addition to its normal
/// function, and the $ anchor matches the null string before any
/// newline in the string in addition to its normal function.
Newline=4
};
/// Compiles the given POSIX Extended Regular Expression \arg Regex.
/// This implementation supports regexes and matching strings with embedded
/// NUL characters.
Regex(const StringRef &Regex, unsigned Flags=NoSub);
~Regex();
/// isValid - returns the error encountered during regex compilation, or
/// matching, if any.
bool isValid(std::string &Error);
/// matches - Match the regex against a given \arg String.
///
/// \param Matches - If given, on a succesful match this will be filled in
/// with references to the matched group expressions (inside \arg String),
/// the first group is always the entire pattern.
/// By default the regex is compiled with NoSub, which disables support for
/// Matches.
/// For this feature to be enabled you must construct the regex using
/// Regex("...", Regex::Sub) constructor.
bool match(const StringRef &String, SmallVectorImpl<StringRef> *Matches=0);
private:
struct llvm_regex *preg;
int error;
bool sub;
};
}

6
lib/Support/CMakeLists.txt
View File

@ -32,6 +32,12 @@ add_llvm_library(LLVMSupport
Twine.cpp
raw_os_ostream.cpp
raw_ostream.cpp
Regex.cpp
regcomp.c
regerror.c
regexec.c
regfree.c
regstrlcpy.c
)
target_link_libraries (LLVMSupport LLVMSystem)

54
lib/Support/COPYRIGHT.regex Normal file
View File

@ -0,0 +1,54 @@
$OpenBSD: COPYRIGHT,v 1.3 2003/06/02 20:18:36 millert Exp $
Copyright 1992, 1993, 1994 Henry Spencer. All rights reserved.
This software is not subject to any license of the American Telephone
and Telegraph Company or of the Regents of the University of California.
Permission is granted to anyone to use this software for any purpose on
any computer system, and to alter it and redistribute it, subject
to the following restrictions:
1. The author is not responsible for the consequences of use of this
software, no matter how awful, even if they arise from flaws in it.
2. The origin of this software must not be misrepresented, either by
explicit claim or by omission. Since few users ever read sources,
credits must appear in the documentation.
3. Altered versions must be plainly marked as such, and must not be
misrepresented as being the original software. Since few users
ever read sources, credits must appear in the documentation.
4. This notice may not be removed or altered.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
/*-
* Copyright (c) 1994
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)COPYRIGHT 8.1 (Berkeley) 3/16/94
*/

97
lib/Support/Regex.cpp Normal file
View File

@ -0,0 +1,97 @@
//===-- Regex.cpp - Regular Expression matcher implementation -------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements a POSIX regular expression matcher.
//
//===----------------------------------------------------------------------===//
#include "llvm/Support/Regex.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include "regex_impl.h"
#include <string>
using namespace llvm;
Regex::Regex(const StringRef &regex, unsigned Flags)
{
unsigned flags = 0;
preg = new struct llvm_regex;
preg->re_endp = regex.end();
if (Flags & IgnoreCase)
flags |= REG_ICASE;
if (Flags & NoSub) {
flags |= REG_NOSUB;
sub = false;
} else {
sub = true;
}
if (Flags & Newline)
flags |= REG_NEWLINE;
error = llvm_regcomp(preg, regex.data(), flags|REG_EXTENDED|REG_PEND);
}
bool Regex::isValid(std::string &Error)
{
if (!error)
return true;
size_t len = llvm_regerror(error, preg, NULL, 0);
char *errbuff = new char[len];
llvm_regerror(error, preg, errbuff, len);
Error.assign(errbuff);
return false;
}
Regex::~Regex()
{
llvm_regfree(preg);
delete preg;
}
bool Regex::match(const StringRef &String, SmallVectorImpl<StringRef> *Matches)
{
unsigned nmatch = Matches ? preg->re_nsub+1 : 0;
if (Matches) {
assert(sub && "Substring matching requested but pattern compiled without");
Matches->clear();
}
// pmatch needs to have at least one element.
SmallVector<llvm_regmatch_t, 2> pm;
pm.resize(nmatch > 0 ? nmatch : 1);
pm[0].rm_so = 0;
pm[0].rm_eo = String.size();
int rc = llvm_regexec(preg, String.data(), nmatch, pm.data(), REG_STARTEND);
if (rc == REG_NOMATCH)
return false;
if (rc != 0) {
// regexec can fail due to invalid pattern or running out of memory.
error = rc;
return false;
}
// There was a match.
if (Matches) { // match position requested
for (unsigned i=0;i<nmatch; i++) {
if (pm[i].rm_so == -1) {
// this group didn't match
Matches->push_back(StringRef());
continue;
}
assert(pm[i].rm_eo > pm[i].rm_so);
Matches->push_back(StringRef(String.data()+pm[i].rm_so,
pm[i].rm_eo-pm[i].rm_so));
}
}
return true;
}

70
lib/Support/regcclass.h Normal file
View File

@ -0,0 +1,70 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)cclass.h 8.3 (Berkeley) 3/20/94
*/
/* character-class table */
static struct cclass {
const char *name;
const char *chars;
const char *multis;
} cclasses[] = {
{ "alnum", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\
0123456789", ""} ,
{ "alpha", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
""} ,
{ "blank", " \t", ""} ,
{ "cntrl", "\007\b\t\n\v\f\r\1\2\3\4\5\6\16\17\20\21\22\23\24\
\25\26\27\30\31\32\33\34\35\36\37\177", ""} ,
{ "digit", "0123456789", ""} ,
{ "graph", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\
0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
""} ,
{ "lower", "abcdefghijklmnopqrstuvwxyz",
""} ,
{ "print", "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\
0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~ ",
""} ,
{ "punct", "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
""} ,
{ "space", "\t\n\v\f\r ", ""} ,
{ "upper", "ABCDEFGHIJKLMNOPQRSTUVWXYZ",
""} ,
{ "xdigit", "0123456789ABCDEFabcdef",
""} ,
{ NULL, 0, "" }
};

139
lib/Support/regcname.h Normal file
View File

@ -0,0 +1,139 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)cname.h 8.3 (Berkeley) 3/20/94
*/
/* character-name table */
static struct cname {
const char *name;
char code;
} cnames[] = {
{ "NUL", '\0' },
{ "SOH", '\001' },
{ "STX", '\002' },
{ "ETX", '\003' },
{ "EOT", '\004' },
{ "ENQ", '\005' },
{ "ACK", '\006' },
{ "BEL", '\007' },
{ "alert", '\007' },
{ "BS", '\010' },
{ "backspace", '\b' },
{ "HT", '\011' },
{ "tab", '\t' },
{ "LF", '\012' },
{ "newline", '\n' },
{ "VT", '\013' },
{ "vertical-tab", '\v' },
{ "FF", '\014' },
{ "form-feed", '\f' },
{ "CR", '\015' },
{ "carriage-return", '\r' },
{ "SO", '\016' },
{ "SI", '\017' },
{ "DLE", '\020' },
{ "DC1", '\021' },
{ "DC2", '\022' },
{ "DC3", '\023' },
{ "DC4", '\024' },
{ "NAK", '\025' },
{ "SYN", '\026' },
{ "ETB", '\027' },
{ "CAN", '\030' },
{ "EM", '\031' },
{ "SUB", '\032' },
{ "ESC", '\033' },
{ "IS4", '\034' },
{ "FS", '\034' },
{ "IS3", '\035' },
{ "GS", '\035' },
{ "IS2", '\036' },
{ "RS", '\036' },
{ "IS1", '\037' },
{ "US", '\037' },
{ "space", ' ' },
{ "exclamation-mark", '!' },
{ "quotation-mark", '"' },
{ "number-sign", '#' },
{ "dollar-sign", '$' },
{ "percent-sign", '%' },
{ "ampersand", '&' },
{ "apostrophe", '\'' },
{ "left-parenthesis", '(' },
{ "right-parenthesis", ')' },
{ "asterisk", '*' },
{ "plus-sign", '+' },
{ "comma", ',' },
{ "hyphen", '-' },
{ "hyphen-minus", '-' },
{ "period", '.' },
{ "full-stop", '.' },
{ "slash", '/' },
{ "solidus", '/' },
{ "zero", '0' },
{ "one", '1' },
{ "two", '2' },
{ "three", '3' },
{ "four", '4' },
{ "five", '5' },
{ "six", '6' },
{ "seven", '7' },
{ "eight", '8' },
{ "nine", '9' },
{ "colon", ':' },
{ "semicolon", ';' },
{ "less-than-sign", '<' },
{ "equals-sign", '=' },
{ "greater-than-sign", '>' },
{ "question-mark", '?' },
{ "commercial-at", '@' },
{ "left-square-bracket", '[' },
{ "backslash", '\\' },
{ "reverse-solidus", '\\' },
{ "right-square-bracket", ']' },
{ "circumflex", '^' },
{ "circumflex-accent", '^' },
{ "underscore", '_' },
{ "low-line", '_' },
{ "grave-accent", '`' },
{ "left-brace", '{' },
{ "left-curly-bracket", '{' },
{ "vertical-line", '|' },
{ "right-brace", '}' },
{ "right-curly-bracket", '}' },
{ "tilde", '~' },
{ "DEL", '\177' },
{ NULL, 0 }
};

1524
lib/Support/regcomp.c Normal file
View File

File diff suppressed because it is too large Load Diff

1021
lib/Support/regengine.inc Normal file
View File

File diff suppressed because it is too large Load Diff

131
lib/Support/regerror.c Normal file
View File

@ -0,0 +1,131 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)regerror.c 8.4 (Berkeley) 3/20/94
*/
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>
#include <stdlib.h>
#include "regex_impl.h"
#include "regutils.h"
static const char *regatoi(const llvm_regex_t *, char *, int);
static struct rerr {
int code;
const char *name;
const char *explain;
} rerrs[] = {
{ REG_NOMATCH, "REG_NOMATCH", "llvm_regexec() failed to match" },
{ REG_BADPAT, "REG_BADPAT", "invalid regular expression" },
{ REG_ECOLLATE, "REG_ECOLLATE", "invalid collating element" },
{ REG_ECTYPE, "REG_ECTYPE", "invalid character class" },
{ REG_EESCAPE, "REG_EESCAPE", "trailing backslash (\\)" },
{ REG_ESUBREG, "REG_ESUBREG", "invalid backreference number" },
{ REG_EBRACK, "REG_EBRACK", "brackets ([ ]) not balanced" },
{ REG_EPAREN, "REG_EPAREN", "parentheses not balanced" },
{ REG_EBRACE, "REG_EBRACE", "braces not balanced" },
{ REG_BADBR, "REG_BADBR", "invalid repetition count(s)" },
{ REG_ERANGE, "REG_ERANGE", "invalid character range" },
{ REG_ESPACE, "REG_ESPACE", "out of memory" },
{ REG_BADRPT, "REG_BADRPT", "repetition-operator operand invalid" },
{ REG_EMPTY, "REG_EMPTY", "empty (sub)expression" },
{ REG_ASSERT, "REG_ASSERT", "\"can't happen\" -- you found a bug" },
{ REG_INVARG, "REG_INVARG", "invalid argument to regex routine" },
{ 0, "", "*** unknown regexp error code ***" }
};
/*
- llvm_regerror - the interface to error numbers
= extern size_t llvm_regerror(int, const llvm_regex_t *, char *, size_t);
*/
/* ARGSUSED */
size_t
llvm_regerror(int errcode, const llvm_regex_t *preg, char *errbuf, size_t errbuf_size)
{
struct rerr *r;
size_t len;
int target = errcode &~ REG_ITOA;
const char *s;
char convbuf[50];
if (errcode == REG_ATOI)
s = regatoi(preg, convbuf, sizeof convbuf);
else {
for (r = rerrs; r->code != 0; r++)
if (r->code == target)
break;
if (errcode&REG_ITOA) {
if (r->code != 0) {
assert(strlen(r->name) < sizeof(convbuf));
(void) llvm_strlcpy(convbuf, r->name, sizeof convbuf);
} else
(void)snprintf(convbuf, sizeof convbuf,
"REG_0x%x", target);
s = convbuf;
} else
s = r->explain;
}
len = strlen(s) + 1;
if (errbuf_size > 0) {
llvm_strlcpy(errbuf, s, errbuf_size);
}
return(len);
}
/*
- regatoi - internal routine to implement REG_ATOI
*/
static const char *
regatoi(const llvm_regex_t *preg, char *localbuf, int localbufsize)
{
struct rerr *r;
for (r = rerrs; r->code != 0; r++)
if (strcmp(r->name, preg->re_endp) == 0)
break;
if (r->code == 0)
return("0");
(void)snprintf(localbuf, localbufsize, "%d", r->code);
return(localbuf);
}

157
lib/Support/regex2.h Normal file
View File

@ -0,0 +1,157 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)regex2.h 8.4 (Berkeley) 3/20/94
*/
/*
* internals of regex_t
*/
#define MAGIC1 ((('r'^0200)<<8) | 'e')
/*
* The internal representation is a *strip*, a sequence of
* operators ending with an endmarker. (Some terminology etc. is a
* historical relic of earlier versions which used multiple strips.)
* Certain oddities in the representation are there to permit running
* the machinery backwards; in particular, any deviation from sequential
* flow must be marked at both its source and its destination. Some
* fine points:
*
* - OPLUS_ and O_PLUS are *inside* the loop they create.
* - OQUEST_ and O_QUEST are *outside* the bypass they create.
* - OCH_ and O_CH are *outside* the multi-way branch they create, while
* OOR1 and OOR2 are respectively the end and the beginning of one of
* the branches. Note that there is an implicit OOR2 following OCH_
* and an implicit OOR1 preceding O_CH.
*
* In state representations, an operator's bit is on to signify a state
* immediately *preceding* "execution" of that operator.
*/
typedef unsigned long sop; /* strip operator */
typedef long sopno;
#define OPRMASK 0xf8000000LU
#define OPDMASK 0x07ffffffLU
#define OPSHIFT ((unsigned)27)
#define OP(n) ((n)&OPRMASK)
#define OPND(n) ((n)&OPDMASK)
#define SOP(op, opnd) ((op)|(opnd))
/* operators meaning operand */
/* (back, fwd are offsets) */
#define OEND (1LU<<OPSHIFT) /* endmarker - */
#define OCHAR (2LU<<OPSHIFT) /* character unsigned char */
#define OBOL (3LU<<OPSHIFT) /* left anchor - */
#define OEOL (4LU<<OPSHIFT) /* right anchor - */
#define OANY (5LU<<OPSHIFT) /* . - */
#define OANYOF (6LU<<OPSHIFT) /* [...] set number */
#define OBACK_ (7LU<<OPSHIFT) /* begin \d paren number */
#define O_BACK (8LU<<OPSHIFT) /* end \d paren number */
#define OPLUS_ (9LU<<OPSHIFT) /* + prefix fwd to suffix */
#define O_PLUS (10LU<<OPSHIFT) /* + suffix back to prefix */
#define OQUEST_ (11LU<<OPSHIFT) /* ? prefix fwd to suffix */
#define O_QUEST (12LU<<OPSHIFT) /* ? suffix back to prefix */
#define OLPAREN (13LU<<OPSHIFT) /* ( fwd to ) */
#define ORPAREN (14LU<<OPSHIFT) /* ) back to ( */
#define OCH_ (15LU<<OPSHIFT) /* begin choice fwd to OOR2 */
#define OOR1 (16LU<<OPSHIFT) /* | pt. 1 back to OOR1 or OCH_ */
#define OOR2 (17LU<<OPSHIFT) /* | pt. 2 fwd to OOR2 or O_CH */
#define O_CH (18LU<<OPSHIFT) /* end choice back to OOR1 */
#define OBOW (19LU<<OPSHIFT) /* begin word - */
#define OEOW (20LU<<OPSHIFT) /* end word - */
/*
* Structure for [] character-set representation. Character sets are
* done as bit vectors, grouped 8 to a byte vector for compactness.
* The individual set therefore has both a pointer to the byte vector
* and a mask to pick out the relevant bit of each byte. A hash code
* simplifies testing whether two sets could be identical.
*
* This will get trickier for multicharacter collating elements. As
* preliminary hooks for dealing with such things, we also carry along
* a string of multi-character elements, and decide the size of the
* vectors at run time.
*/
typedef struct {
uch *ptr; /* -> uch [csetsize] */
uch mask; /* bit within array */
uch hash; /* hash code */
size_t smultis;
char *multis; /* -> char[smulti] ab\0cd\0ef\0\0 */
} cset;
/* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
#define CHadd(cs, c) ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
#define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
#define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask)
#define MCadd(p, cs, cp) mcadd(p, cs, cp) /* llvm_regcomp() internal fns */
#define MCsub(p, cs, cp) mcsub(p, cs, cp)
#define MCin(p, cs, cp) mcin(p, cs, cp)
/* stuff for character categories */
typedef unsigned char cat_t;
/*
* main compiled-expression structure
*/
struct re_guts {
int magic;
# define MAGIC2 ((('R'^0200)<<8)|'E')
sop *strip; /* malloced area for strip */
int csetsize; /* number of bits in a cset vector */
int ncsets; /* number of csets in use */
cset *sets; /* -> cset [ncsets] */
uch *setbits; /* -> uch[csetsize][ncsets/CHAR_BIT] */
int cflags; /* copy of llvm_regcomp() cflags argument */
sopno nstates; /* = number of sops */
sopno firststate; /* the initial OEND (normally 0) */
sopno laststate; /* the final OEND */
int iflags; /* internal flags */
# define USEBOL 01 /* used ^ */
# define USEEOL 02 /* used $ */
# define REGEX_BAD 04 /* something wrong */
int nbol; /* number of ^ used */
int neol; /* number of $ used */
int ncategories; /* how many character categories */
cat_t *categories; /* ->catspace[-CHAR_MIN] */
char *must; /* match must contain this string */
int mlen; /* length of must */
size_t nsub; /* copy of re_nsub */
int backrefs; /* does it use back references? */
sopno nplus; /* how deep does it nest +s? */
/* catspace must be last */
cat_t catspace[1]; /* actually [NC] */
};
/* misc utilities */
#define OUT (CHAR_MAX+1) /* a non-character value */
#define ISWORD(c) (isalnum(c&0xff) || (c) == '_')

108
lib/Support/regex_impl.h Normal file
View File

@ -0,0 +1,108 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992 Henry Spencer.
* Copyright (c) 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer of the University of Toronto.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)regex.h 8.1 (Berkeley) 6/2/93
*/
#ifndef _REGEX_H_
#define _REGEX_H_
#include <sys/types.h>
typedef off_t llvm_regoff_t;
typedef struct {
llvm_regoff_t rm_so; /* start of match */
llvm_regoff_t rm_eo; /* end of match */
} llvm_regmatch_t;
typedef struct llvm_regex {
int re_magic;
size_t re_nsub; /* number of parenthesized subexpressions */
const char *re_endp; /* end pointer for REG_PEND */
struct re_guts *re_g; /* none of your business :-) */
} llvm_regex_t;
/* llvm_regcomp() flags */
#define REG_BASIC 0000
#define REG_EXTENDED 0001
#define REG_ICASE 0002
#define REG_NOSUB 0004
#define REG_NEWLINE 0010
#define REG_NOSPEC 0020
#define REG_PEND 0040
#define REG_DUMP 0200
/* llvm_regerror() flags */
#define REG_NOMATCH 1
#define REG_BADPAT 2
#define REG_ECOLLATE 3
#define REG_ECTYPE 4
#define REG_EESCAPE 5
#define REG_ESUBREG 6
#define REG_EBRACK 7
#define REG_EPAREN 8
#define REG_EBRACE 9
#define REG_BADBR 10
#define REG_ERANGE 11
#define REG_ESPACE 12
#define REG_BADRPT 13
#define REG_EMPTY 14
#define REG_ASSERT 15
#define REG_INVARG 16
#define REG_ATOI 255 /* convert name to number (!) */
#define REG_ITOA 0400 /* convert number to name (!) */
/* llvm_regexec() flags */
#define REG_NOTBOL 00001
#define REG_NOTEOL 00002
#define REG_STARTEND 00004
#define REG_TRACE 00400 /* tracing of execution */
#define REG_LARGE 01000 /* force large representation */
#define REG_BACKR 02000 /* force use of backref code */
#ifdef __cplusplus
extern "C" {
#endif
int llvm_regcomp(llvm_regex_t *, const char *, int);
size_t llvm_regerror(int, const llvm_regex_t *, char *, size_t);
int llvm_regexec(const llvm_regex_t *, const char *, size_t,
llvm_regmatch_t [], int);
void llvm_regfree(llvm_regex_t *);
size_t llvm_strlcpy(char *dst, const char *src, size_t siz);
#ifdef __cplusplus
}
#endif
#endif /* !_REGEX_H_ */

161
lib/Support/regexec.c Normal file
View File

@ -0,0 +1,161 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)regexec.c 8.3 (Berkeley) 3/20/94
*/
/*
* the outer shell of llvm_regexec()
*
* This file includes engine.inc *twice*, after muchos fiddling with the
* macros that code uses. This lets the same code operate on two different
* representations for state sets.
*/
#include <sys/types.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>
#include <ctype.h>
#include "regex_impl.h"
#include "regutils.h"
#include "regex2.h"
/* macros for manipulating states, small version */
#define states long
#define states1 states /* for later use in llvm_regexec() decision */
#define CLEAR(v) ((v) = 0)
#define SET0(v, n) ((v) &= ~((unsigned long)1 << (n)))
#define SET1(v, n) ((v) |= (unsigned long)1 << (n))
#define ISSET(v, n) (((v) & ((unsigned long)1 << (n))) != 0)
#define ASSIGN(d, s) ((d) = (s))
#define EQ(a, b) ((a) == (b))
#define STATEVARS long dummy /* dummy version */
#define STATESETUP(m, n) /* nothing */
#define STATETEARDOWN(m) /* nothing */
#define SETUP(v) ((v) = 0)
#define onestate long
#define INIT(o, n) ((o) = (unsigned long)1 << (n))
#define INC(o) ((o) <<= 1)
#define ISSTATEIN(v, o) (((v) & (o)) != 0)
/* some abbreviations; note that some of these know variable names! */
/* do "if I'm here, I can also be there" etc without branches */
#define FWD(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) << (n))
#define BACK(dst, src, n) ((dst) |= ((unsigned long)(src)&(here)) >> (n))
#define ISSETBACK(v, n) (((v) & ((unsigned long)here >> (n))) != 0)
/* function names */
#define SNAMES /* engine.inc looks after details */
#include "regengine.inc"
/* now undo things */
#undef states
#undef CLEAR
#undef SET0
#undef SET1
#undef ISSET
#undef ASSIGN
#undef EQ
#undef STATEVARS
#undef STATESETUP
#undef STATETEARDOWN
#undef SETUP
#undef onestate
#undef INIT
#undef INC
#undef ISSTATEIN
#undef FWD
#undef BACK
#undef ISSETBACK
#undef SNAMES
/* macros for manipulating states, large version */
#define states char *
#define CLEAR(v) memset(v, 0, m->g->nstates)
#define SET0(v, n) ((v)[n] = 0)
#define SET1(v, n) ((v)[n] = 1)
#define ISSET(v, n) ((v)[n])
#define ASSIGN(d, s) memmove(d, s, m->g->nstates)
#define EQ(a, b) (memcmp(a, b, m->g->nstates) == 0)
#define STATEVARS long vn; char *space
#define STATESETUP(m, nv) { (m)->space = malloc((nv)*(m)->g->nstates); \
if ((m)->space == NULL) return(REG_ESPACE); \
(m)->vn = 0; }
#define STATETEARDOWN(m) { free((m)->space); }
#define SETUP(v) ((v) = &m->space[m->vn++ * m->g->nstates])
#define onestate long
#define INIT(o, n) ((o) = (n))
#define INC(o) ((o)++)
#define ISSTATEIN(v, o) ((v)[o])
/* some abbreviations; note that some of these know variable names! */
/* do "if I'm here, I can also be there" etc without branches */
#define FWD(dst, src, n) ((dst)[here+(n)] |= (src)[here])
#define BACK(dst, src, n) ((dst)[here-(n)] |= (src)[here])
#define ISSETBACK(v, n) ((v)[here - (n)])
/* function names */
#define LNAMES /* flag */
#include "regengine.inc"
/*
- llvm_regexec - interface for matching
*
* We put this here so we can exploit knowledge of the state representation
* when choosing which matcher to call. Also, by this point the matchers
* have been prototyped.
*/
int /* 0 success, REG_NOMATCH failure */
llvm_regexec(const llvm_regex_t *preg, const char *string, size_t nmatch,
llvm_regmatch_t pmatch[], int eflags)
{
struct re_guts *g = preg->re_g;
#ifdef REDEBUG
# define GOODFLAGS(f) (f)
#else
# define GOODFLAGS(f) ((f)&(REG_NOTBOL|REG_NOTEOL|REG_STARTEND))
#endif
if (preg->re_magic != MAGIC1 || g->magic != MAGIC2)
return(REG_BADPAT);
assert(!(g->iflags&REGEX_BAD));
if (g->iflags&REGEX_BAD) /* backstop for no-debug case */
return(REG_BADPAT);
eflags = GOODFLAGS(eflags);
if (g->nstates <= (long)(CHAR_BIT*sizeof(states1)) && !(eflags&REG_LARGE))
return(smatcher(g, (char *)string, nmatch, pmatch, eflags));
else
return(lmatcher(g, (char *)string, nmatch, pmatch, eflags));
}

72
lib/Support/regfree.c Normal file
View File

@ -0,0 +1,72 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)regfree.c 8.3 (Berkeley) 3/20/94
*/
#include <sys/types.h>
#include <stdio.h>
#include <stdlib.h>
#include "regex_impl.h"
#include "regutils.h"
#include "regex2.h"
/*
- llvm_regfree - free everything
*/
void
llvm_regfree(llvm_regex_t *preg)
{
struct re_guts *g;
if (preg->re_magic != MAGIC1) /* oops */
return; /* nice to complain, but hard */
g = preg->re_g;
if (g == NULL || g->magic != MAGIC2) /* oops again */
return;
preg->re_magic = 0; /* mark it invalid */
g->magic = 0; /* mark it invalid */
if (g->strip != NULL)
free((char *)g->strip);
if (g->sets != NULL)
free((char *)g->sets);
if (g->setbits != NULL)
free((char *)g->setbits);
if (g->must != NULL)
free(g->must);
free((char *)g);
}

52
lib/Support/regstrlcpy.c Normal file
View File

@ -0,0 +1,52 @@
/*
* This code is derived from OpenBSD's libc, original license follows:
*
* Copyright (c) 1998 Todd C. Miller <Todd.Miller@courtesan.com>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
#include <sys/types.h>
#include <string.h>
#include "regex_impl.h"
/*
* Copy src to string dst of size siz. At most siz-1 characters
* will be copied. Always NUL terminates (unless siz == 0).
* Returns strlen(src); if retval >= siz, truncation occurred.
*/
size_t
llvm_strlcpy(char *dst, const char *src, size_t siz)
{
char *d = dst;
const char *s = src;
size_t n = siz;
/* Copy as many bytes as will fit */
if (n != 0) {
while (--n != 0) {
if ((*d++ = *s++) == '\0')
break;
}
}
/* Not enough room in dst, add NUL and traverse rest of src */
if (n == 0) {
if (siz != 0)
*d = '\0'; /* NUL-terminate dst */
while (*s++)
;
}
return(s - src - 1); /* count does not include NUL */
}

55
lib/Support/regutils.h Normal file
View File

@ -0,0 +1,55 @@
/*-
* This code is derived from OpenBSD's libc/regex, original license follows:
*
* Copyright (c) 1992, 1993, 1994 Henry Spencer.
* Copyright (c) 1992, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Henry Spencer.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. 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.
* 3. Neither the name of the University 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 REGENTS 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 REGENTS 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.
*
* @(#)utils.h 8.3 (Berkeley) 3/20/94
*/
/* utility definitions */
#define DUPMAX _POSIX2_RE_DUP_MAX /* xxx is this right? */
#define INFINITY (DUPMAX + 1)
#define NC (CHAR_MAX - CHAR_MIN + 1)
typedef unsigned char uch;
/* switch off assertions (if not already off) if no REDEBUG */
#ifndef REDEBUG
#ifndef NDEBUG
#define NDEBUG /* no assertions please */
#endif
#endif
#include <assert.h>
/* for old systems with bcopy() but no memmove() */
#ifdef USEBCOPY
#define memmove(d, s, c) bcopy(s, d, c)
#endif

64
unittests/Support/RegexTest.cpp Normal file
View File

@ -0,0 +1,64 @@
//===- llvm/unittest/Support/RegexTest.cpp - Regex tests --===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "gtest/gtest.h"
#include "llvm/Support/Regex.h"
#include <cstring>
using namespace llvm;
namespace {
class RegexTest : public ::testing::Test {
};
TEST_F(RegexTest, Basics) {
Regex r1("^[0-9]+$");
EXPECT_TRUE(r1.match("916"));
EXPECT_TRUE(r1.match("9"));
EXPECT_FALSE(r1.match("9a"));
SmallVector<StringRef, 1> Matches;
Regex r2("[0-9]+", Regex::Sub);
EXPECT_TRUE(r2.match("aa216b", &Matches));
EXPECT_EQ(1u, Matches.size());
EXPECT_EQ("216", Matches[0].str());
Regex r3("[0-9]+([a-f])?:([0-9]+)", Regex::Sub);
EXPECT_TRUE(r3.match("9a:513b", &Matches));
EXPECT_EQ(3u, Matches.size());
EXPECT_EQ("9a:513", Matches[0].str());
EXPECT_EQ("a", Matches[1].str());
EXPECT_EQ("513", Matches[2].str());
EXPECT_TRUE(r3.match("9:513b", &Matches));
EXPECT_EQ(3u, Matches.size());
EXPECT_EQ("9:513", Matches[0].str());
EXPECT_EQ("", Matches[1].str());
EXPECT_EQ("513", Matches[2].str());
Regex r4("a[^b]+b", Regex::Sub);
std::string String="axxb";
String[2] = '\0';
EXPECT_FALSE(r4.match("abb"));
EXPECT_TRUE(r4.match(String, &Matches));
EXPECT_EQ(1u, Matches.size());
EXPECT_EQ(String, Matches[0].str());
std::string NulPattern="X[0-9]+X([a-f])?:([0-9]+)";
String="YX99a:513b";
NulPattern[7] = '\0';
Regex r5(NulPattern, Regex::Sub);
EXPECT_FALSE(r5.match(String));
EXPECT_FALSE(r5.match("X9"));
String[3]='\0';
EXPECT_TRUE(r5.match(String));
}
}