How to unescape backslashes on macOS? - objective-c

Question

Localized.strings files may contain escaped chars like \n and \".
How do I efficiently unescape them?
I know I could write my own function that looks for a \ and removes it and then keeps searching at the second-next character (so that I don't turn \\ into nothing), but that won't handle special escape methods such as an octal character numbers (e.g. \012 for a LF) and possibly other forms.
I'd think that NSString would offer a function for that but I can't find any.
Actually, this appears to be a duplicate of NSString strip regular \ escape characters how?, but that question has a lot of bad answers and not a single correct answer. And the user is not active any more, meaning no one will ever accept a correct answer there. How shall that be handled on SO?

Answer 1

Here's a self-written ObjC version that works for most cases. It defines an unescaped method for NSString.
#import <Cocoa/Cocoa.h>
#interface NSString (BackslashUnescaping)
- (NSString*) unescaped;
#end
#implementation NSString (BackslashUnescaping)
- (NSString*) unescaped
{
NSString *text = self;
NSInteger charIndex = 0;
while (true) {
NSInteger textLen = text.length;
if (charIndex >= textLen) {
break;
}
NSRange remainingRange = NSMakeRange (charIndex, textLen-charIndex);
NSRange charRange = [text rangeOfString:#"\\"options:0 range:remainingRange];
if (charRange.length == 0) {
// no more backslashes -> done
break;
}
charIndex = charRange.location + 1;
if (charIndex >= textLen) {
// reached end of string -> exit loop
break;
}
// check char following the backslash
unichar nextChar = [text characterAtIndex:charIndex];
unichar replacementChar;
NSInteger skipLen = 1;
if (nextChar >= 'a' && nextChar <= 'z') {
if (nextChar == 'n') {
replacementChar = '\n'; // LF
} else if (nextChar == 'r') {
replacementChar = '\r'; // CR
} else if (nextChar == 't') {
replacementChar = '\t'; // TAB
} else if (nextChar == 'x') {
// A hex char code
const NSInteger xtraLen = 2;
if (charIndex+xtraLen >= textLen) break;
// Note: Does not make sure that both chars are valid hex chars
NSString *code = [text substringWithRange:NSMakeRange(charIndex+1, 2)];
char ch = strtol(code.UTF8String, NULL, 16);
replacementChar = ch;
skipLen += xtraLen;
} else if (nextChar == 'u') {
// A unicode char code
const NSInteger xtraLen = 4;
if (charIndex+xtraLen >= textLen) break;
// Note: Does not make sure that all four chars are valid hex chars
NSString *code = [text substringWithRange:NSMakeRange(charIndex+1, 4)];
unichar ch = strtol(code.UTF8String, NULL, 16);
replacementChar = ch;
skipLen += xtraLen;
} else {
// an unknown escape code - this should be fixed
NSAssert(false, #"There's a case missing for escaping \\%c", nextChar);
}
} else if (nextChar >= '0' && nextChar <= '9') {
unichar nextChar2 = 0;
if (charIndex > textLen) { // get the second octal char
nextChar2 = [text characterAtIndex:charIndex+1];
}
if (nextChar == '0' && (nextChar2 < '0' || nextChar2 > '9')) {
// A short NUL (\0) char
replacementChar = 0;
} else {
// An octal char code
const NSInteger xtraLen = 2;
if (charIndex+xtraLen >= textLen) break;
// Note: Does not make sure that the last char is a valid octal char
NSString *code = [text substringWithRange:NSMakeRange(charIndex, 3)];
char ch = strtol(code.UTF8String, NULL, 8); // https://stackoverflow.com/a/12820646/43615
replacementChar = ch;
skipLen += xtraLen;
}
} else {
// Handle all generic escapes, like for \\ and \"
replacementChar = nextChar;
}
#if 0 // Use string concatenation
charIndex += skipLen-1;
NSString *head = [text substringToIndex:charRange.location];
NSString *tail = [text substringFromIndex:charIndex+1];
text = [NSString stringWithFormat:#"%#%C%#", head, replacementChar, tail];
#else // Use a mutable string
if (text == self) {
text = text.mutableCopy;
}
NSRange replacedRange = NSMakeRange(charRange.location, skipLen+1);
NSString *replacement = [NSString stringWithCharacters:&replacementChar length:1];
[(NSMutableString*)text replaceCharactersInRange:replacedRange withString:replacement];
charIndex += 1;
#endif
}
return text;
}
#end
int main(int argc, const char * argv[]) {
#autoreleasepool {
NSArray *testValues = #[
#"CR:\\rLF:\\n",
#"\\\"quoted\\\"",
#"Backslash: \\\\",
#"Octal x (\170):\\170",
#"Hex x (\x78):\\x78",
#"Unicode Ф (\u0424):\\u0424",
#"NUL char:\\0.",
#"Bad Hex:\\x7x", // this is not detected being invalid
#"Bad Hex:\\x7",
#"Incomplete :\\13"
];
for (NSString *s in testValues) {
NSString *s2 = [NSString stringWithFormat:#"Escaped: %#\nUnescaped: %#", s, s.unescaped];
printf("\n%s\n", s2.UTF8String);
}
}
return 0;
}