2009-08-30 16:24:09 +08:00
|
|
|
//===-- 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.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
2009-09-25 04:15:51 +08:00
|
|
|
|
2009-08-30 16:24:09 +08:00
|
|
|
#include "llvm/Support/Regex.h"
|
2012-12-04 00:50:05 +08:00
|
|
|
#include "regex_impl.h"
|
|
|
|
#include "llvm/ADT/SmallVector.h"
|
2015-03-24 02:07:13 +08:00
|
|
|
#include "llvm/ADT/StringRef.h"
|
2015-03-30 23:42:36 +08:00
|
|
|
#include "llvm/ADT/Twine.h"
|
2009-08-30 16:24:09 +08:00
|
|
|
#include <string>
|
|
|
|
using namespace llvm;
|
2009-09-25 04:15:51 +08:00
|
|
|
|
2010-07-15 06:38:02 +08:00
|
|
|
Regex::Regex(StringRef regex, unsigned Flags) {
|
2009-08-30 16:24:09 +08:00
|
|
|
unsigned flags = 0;
|
2009-09-25 05:47:32 +08:00
|
|
|
preg = new llvm_regex();
|
2009-08-30 16:24:09 +08:00
|
|
|
preg->re_endp = regex.end();
|
|
|
|
if (Flags & IgnoreCase)
|
|
|
|
flags |= REG_ICASE;
|
|
|
|
if (Flags & Newline)
|
|
|
|
flags |= REG_NEWLINE;
|
Add backreference matching capabilities to Support/Regex, with
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
llvm-svn: 168802
2012-11-29 03:00:02 +08:00
|
|
|
if (!(Flags & BasicRegex))
|
|
|
|
flags |= REG_EXTENDED;
|
|
|
|
error = llvm_regcomp(preg, regex.data(), flags|REG_PEND);
|
2009-08-30 16:24:09 +08:00
|
|
|
}
|
|
|
|
|
2009-09-27 05:27:04 +08:00
|
|
|
Regex::~Regex() {
|
2014-01-03 03:04:59 +08:00
|
|
|
if (preg) {
|
|
|
|
llvm_regfree(preg);
|
|
|
|
delete preg;
|
|
|
|
}
|
2009-09-27 05:27:04 +08:00
|
|
|
}
|
|
|
|
|
2009-09-25 04:15:51 +08:00
|
|
|
bool Regex::isValid(std::string &Error) {
|
2009-08-30 16:24:09 +08:00
|
|
|
if (!error)
|
|
|
|
return true;
|
2009-09-27 05:27:04 +08:00
|
|
|
|
2014-04-07 12:17:22 +08:00
|
|
|
size_t len = llvm_regerror(error, preg, nullptr, 0);
|
2009-09-25 04:15:51 +08:00
|
|
|
|
2013-08-09 01:32:45 +08:00
|
|
|
Error.resize(len - 1);
|
2009-09-25 04:15:51 +08:00
|
|
|
llvm_regerror(error, preg, &Error[0], len);
|
2009-08-30 16:24:09 +08:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2009-09-27 05:27:04 +08:00
|
|
|
/// getNumMatches - In a valid regex, return the number of parenthesized
|
|
|
|
/// matches it contains.
|
|
|
|
unsigned Regex::getNumMatches() const {
|
|
|
|
return preg->re_nsub;
|
2009-08-30 16:24:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-15 06:38:02 +08:00
|
|
|
bool Regex::match(StringRef String, SmallVectorImpl<StringRef> *Matches){
|
2009-08-30 16:24:09 +08:00
|
|
|
unsigned nmatch = Matches ? preg->re_nsub+1 : 0;
|
|
|
|
|
|
|
|
// pmatch needs to have at least one element.
|
2009-09-25 05:47:32 +08:00
|
|
|
SmallVector<llvm_regmatch_t, 8> pm;
|
2009-08-30 16:24:09 +08:00
|
|
|
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
|
2009-09-27 05:27:04 +08:00
|
|
|
Matches->clear();
|
|
|
|
|
2009-09-25 04:15:51 +08:00
|
|
|
for (unsigned i = 0; i != nmatch; ++i) {
|
2009-08-30 16:24:09 +08:00
|
|
|
if (pm[i].rm_so == -1) {
|
|
|
|
// this group didn't match
|
|
|
|
Matches->push_back(StringRef());
|
|
|
|
continue;
|
|
|
|
}
|
2011-04-09 14:29:24 +08:00
|
|
|
assert(pm[i].rm_eo >= pm[i].rm_so);
|
2009-08-30 16:24:09 +08:00
|
|
|
Matches->push_back(StringRef(String.data()+pm[i].rm_so,
|
|
|
|
pm[i].rm_eo-pm[i].rm_so));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
2010-02-18 04:08:42 +08:00
|
|
|
|
|
|
|
std::string Regex::sub(StringRef Repl, StringRef String,
|
|
|
|
std::string *Error) {
|
|
|
|
SmallVector<StringRef, 8> Matches;
|
|
|
|
|
|
|
|
// Reset error, if given.
|
|
|
|
if (Error && !Error->empty()) *Error = "";
|
|
|
|
|
|
|
|
// Return the input if there was no match.
|
|
|
|
if (!match(String, &Matches))
|
|
|
|
return String;
|
|
|
|
|
|
|
|
// Otherwise splice in the replacement string, starting with the prefix before
|
|
|
|
// the match.
|
|
|
|
std::string Res(String.begin(), Matches[0].begin());
|
|
|
|
|
|
|
|
// Then the replacement string, honoring possible substitutions.
|
|
|
|
while (!Repl.empty()) {
|
|
|
|
// Skip to the next escape.
|
|
|
|
std::pair<StringRef, StringRef> Split = Repl.split('\\');
|
|
|
|
|
|
|
|
// Add the skipped substring.
|
|
|
|
Res += Split.first;
|
|
|
|
|
|
|
|
// Check for terminimation and trailing backslash.
|
|
|
|
if (Split.second.empty()) {
|
|
|
|
if (Repl.size() != Split.first.size() &&
|
|
|
|
Error && Error->empty())
|
|
|
|
*Error = "replacement string contained trailing backslash";
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Otherwise update the replacement string and interpret escapes.
|
|
|
|
Repl = Split.second;
|
|
|
|
|
|
|
|
// FIXME: We should have a StringExtras function for mapping C99 escapes.
|
|
|
|
switch (Repl[0]) {
|
|
|
|
// Treat all unrecognized characters as self-quoting.
|
|
|
|
default:
|
|
|
|
Res += Repl[0];
|
|
|
|
Repl = Repl.substr(1);
|
|
|
|
break;
|
|
|
|
|
|
|
|
// Single character escapes.
|
|
|
|
case 't':
|
|
|
|
Res += '\t';
|
|
|
|
Repl = Repl.substr(1);
|
|
|
|
break;
|
|
|
|
case 'n':
|
|
|
|
Res += '\n';
|
|
|
|
Repl = Repl.substr(1);
|
|
|
|
break;
|
|
|
|
|
|
|
|
// Decimal escapes are backreferences.
|
|
|
|
case '0': case '1': case '2': case '3': case '4':
|
|
|
|
case '5': case '6': case '7': case '8': case '9': {
|
|
|
|
// Extract the backreference number.
|
|
|
|
StringRef Ref = Repl.slice(0, Repl.find_first_not_of("0123456789"));
|
|
|
|
Repl = Repl.substr(Ref.size());
|
|
|
|
|
|
|
|
unsigned RefValue;
|
|
|
|
if (!Ref.getAsInteger(10, RefValue) &&
|
|
|
|
RefValue < Matches.size())
|
|
|
|
Res += Matches[RefValue];
|
|
|
|
else if (Error && Error->empty())
|
2015-03-30 23:42:36 +08:00
|
|
|
*Error = ("invalid backreference string '" + Twine(Ref) + "'").str();
|
2010-02-18 04:08:42 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// And finally the suffix.
|
|
|
|
Res += StringRef(Matches[0].end(), String.end() - Matches[0].end());
|
|
|
|
|
|
|
|
return Res;
|
|
|
|
}
|
2013-08-06 01:47:59 +08:00
|
|
|
|
2013-12-12 10:51:58 +08:00
|
|
|
// These are the special characters matched in functions like "p_ere_exp".
|
|
|
|
static const char RegexMetachars[] = "()^$|*+?.[]\\{}";
|
|
|
|
|
2013-08-06 01:47:59 +08:00
|
|
|
bool Regex::isLiteralERE(StringRef Str) {
|
|
|
|
// Check for regex metacharacters. This list was derived from our regex
|
|
|
|
// implementation in regcomp.c and double checked against the POSIX extended
|
|
|
|
// regular expression specification.
|
2013-12-12 10:51:58 +08:00
|
|
|
return Str.find_first_of(RegexMetachars) == StringRef::npos;
|
2013-08-06 01:47:59 +08:00
|
|
|
}
|
2013-12-12 08:06:41 +08:00
|
|
|
|
|
|
|
std::string Regex::escape(StringRef String) {
|
|
|
|
std::string RegexStr;
|
|
|
|
for (unsigned i = 0, e = String.size(); i != e; ++i) {
|
2013-12-12 10:51:58 +08:00
|
|
|
if (strchr(RegexMetachars, String[i]))
|
2013-12-12 08:06:41 +08:00
|
|
|
RegexStr += '\\';
|
2013-12-12 10:51:58 +08:00
|
|
|
RegexStr += String[i];
|
2013-12-12 08:06:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return RegexStr;
|
|
|
|
}
|