Add missing escape characters to the new Regex::escape() function

The old AddFixedStringToRegEx() it was based on got away with this for the
longest time, but the problem became easy to spot after the cleanup in r197096.

Also add a quick unit test to cover regex escaping.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197121 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Alp Toker 2013-12-12 02:51:58 +00:00
parent dcdc5736ad
commit 22e0e0c1de
2 changed files with 11 additions and 21 deletions

View File

@ -169,37 +169,22 @@ std::string Regex::sub(StringRef Repl, StringRef String,
return Res;
}
// These are the special characters matched in functions like "p_ere_exp".
static const char RegexMetachars[] = "()^$|*+?.[]\\{}";
bool Regex::isLiteralERE(StringRef Str) {
// Check for regex metacharacters. This list was derived from our regex
// implementation in regcomp.c and double checked against the POSIX extended
// regular expression specification.
return Str.find_first_of("()^$|*+?.[]\\{}") == StringRef::npos;
return Str.find_first_of(RegexMetachars) == StringRef::npos;
}
std::string Regex::escape(StringRef String) {
std::string RegexStr;
for (unsigned i = 0, e = String.size(); i != e; ++i) {
switch (String[i]) {
// These are the special characters matched in "p_ere_exp".
case '(':
case ')':
case '^':
case '$':
case '|':
case '*':
case '+':
case '?':
case '.':
case '[':
case '\\':
case '{':
if (strchr(RegexMetachars, String[i]))
RegexStr += '\\';
// FALL THROUGH.
default:
RegexStr += String[i];
break;
}
RegexStr += String[i];
}
return RegexStr;

View File

@ -127,6 +127,11 @@ TEST_F(RegexTest, IsLiteralERE) {
EXPECT_FALSE(Regex::isLiteralERE("abc{1,2}"));
}
TEST_F(RegexTest, Escape) {
EXPECT_EQ(Regex::escape("a[bc]"), "a\\[bc\\]");
EXPECT_EQ(Regex::escape("abc{1\\,2}"), "abc\\{1\\\\,2\\}");
}
TEST_F(RegexTest, IsValid) {
std::string Error;
EXPECT_FALSE(Regex("(foo").isValid(Error));