mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 04:30:12 +00:00
6b731486d4
appropriate unit tests. This change in itself is not expected to affect any functionality at this point, but it will serve as a stepping stone to improve FileCheck's variable matching capabilities. Luckily, our regex implementation already supports backreferences, although a bit of hacking is required to enable it. It supports both Basic Regular Expressions (BREs) and Extended Regular Expressions (EREs), without supporting backrefs for EREs, following POSIX strictly in this respect. And EREs is what we actually use (rightly). This is contrary to many implementations (including the default on Linux) of POSIX regexes, that do allow backrefs in EREs. Adding backref support to our EREs is a very simple change in the regcomp parsing code. I fail to think of significant cases where it would clash with existing things, and can bring more versatility to the regexes we write. There's always the danger of a backref in a specially crafted regex causing exponential matching times, but since we mainly use them for testing purposes I don't think it's a big problem. [it can also be placed behind a flag specific to FileCheck, if needed]. For more details, see: * http://lists.cs.uiuc.edu/pipermail/llvmdev/2012-November/055840.html * http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20121126/156878.html git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168802 91177308-0d34-0410-b5e6-96231b3b80d8
87 lines
3.2 KiB
C++
87 lines
3.2 KiB
C++
//===-- 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. Both Basic and
|
|
// Extended POSIX regular expressions (ERE) are supported. EREs were extended
|
|
// to support backreferences in matches.
|
|
// This implementation also supports matching strings with embedded NUL chars.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_SUPPORT_REGEX_H
|
|
#define LLVM_SUPPORT_REGEX_H
|
|
|
|
#include <string>
|
|
|
|
struct llvm_regex;
|
|
|
|
namespace llvm {
|
|
class StringRef;
|
|
template<typename T> class SmallVectorImpl;
|
|
|
|
class Regex {
|
|
public:
|
|
enum {
|
|
NoFlags=0,
|
|
/// Compile for matching that ignores upper/lower case distinctions.
|
|
IgnoreCase=1,
|
|
/// 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=2,
|
|
/// By default, the POSIX extended regular expression (ERE) syntax is
|
|
/// assumed. Pass this flag to turn on basic regular expressions (BRE)
|
|
/// instead.
|
|
BasicRegex=4
|
|
};
|
|
|
|
/// Compiles the given regular expression \p Regex.
|
|
Regex(StringRef Regex, unsigned Flags = NoFlags);
|
|
~Regex();
|
|
|
|
/// isValid - returns the error encountered during regex compilation, or
|
|
/// matching, if any.
|
|
bool isValid(std::string &Error);
|
|
|
|
/// getNumMatches - In a valid regex, return the number of parenthesized
|
|
/// matches it contains. The number filled in by match will include this
|
|
/// many entries plus one for the whole regex (as element 0).
|
|
unsigned getNumMatches() const;
|
|
|
|
/// matches - Match the regex against a given \p String.
|
|
///
|
|
/// \param Matches - If given, on a successful match this will be filled in
|
|
/// with references to the matched group expressions (inside \p String),
|
|
/// the first group is always the entire pattern.
|
|
///
|
|
/// This returns true on a successful match.
|
|
bool match(StringRef String, SmallVectorImpl<StringRef> *Matches = 0);
|
|
|
|
/// sub - Return the result of replacing the first match of the regex in
|
|
/// \p String with the \p Repl string. Backreferences like "\0" in the
|
|
/// replacement string are replaced with the appropriate match substring.
|
|
///
|
|
/// Note that the replacement string has backslash escaping performed on
|
|
/// it. Invalid backreferences are ignored (replaced by empty strings).
|
|
///
|
|
/// \param Error If non-null, any errors in the substitution (invalid
|
|
/// backreferences, trailing backslashes) will be recorded as a non-empty
|
|
/// string.
|
|
std::string sub(StringRef Repl, StringRef String, std::string *Error = 0);
|
|
|
|
private:
|
|
struct llvm_regex *preg;
|
|
int error;
|
|
};
|
|
}
|
|
|
|
#endif // LLVM_SUPPORT_REGEX_H
|