Objective-C中的NSString标记化

请注意,componentsSeparatedByCharactersInSet如果连续遇到charSet的多个成员,将生成空字符串,因此您可能希望测试长度小于1的长度.

如果您想在保留“带引号的短语”的同时将字符串标记为搜索词，则此NSString类别应尊重各种类型的引号对："" '' ‘’ “”

用法：

NSArray *terms = [@"This is my \"search phrase\" I want to split" searchTerms];
// results in: ["This", "is", "my", "search phrase", "I", "want", "to", "split"]

码：

@interface NSString (Search)
- (NSArray *)searchTerms;
@end

@implementation NSString (Search)

- (NSArray *)searchTerms {

    // Strip whitespace and setup scanner
    NSCharacterSet *whitespace = [NSCharacterSet whitespaceAndNewlineCharacterSet];
    NSString *searchString = [self stringByTrimmingCharactersInSet:whitespace];
    NSScanner *scanner = [NSScanner scannerWithString:searchString];
    [scanner setCharactersToBeSkipped:nil]; // we'll handle whitespace ourselves

    // A few types of quote pairs to check
    NSDictionary *quotePairs = @{@"\"": @"\"",
                                 @"'": @"'",
                                 @"\u2018": @"\u2019",
                                 @"\u201C": @"\u201D"};

    // Scan
    NSMutableArray *results = [[NSMutableArray alloc] init];
    NSString *substring = nil;
    while (scanner.scanLocation < searchString.length) {
        // Check for quote at beginning of string
        unichar unicharacter = [self characterAtIndex:scanner.scanLocation];
        NSString *startQuote = [NSString stringWithFormat:@"%C", unicharacter];
        NSString *endQuote = [quotePairs objectForKey:startQuote];
        if (endQuote != nil) { // if it's a valid start quote we'll have an end quote
            // Scan quoted phrase into substring (skipping start & end quotes)
            [scanner scanString:startQuote intoString:nil];
            [scanner scanUpToString:endQuote intoString:&substring];
            [scanner scanString:endQuote intoString:nil];
        } else {
            // Single word that is non-quoted
            [scanner scanUpToCharactersFromSet:whitespace intoString:&substring];
        }
        // Process and add the substring to results
        if (substring) {
            substring = [substring stringByTrimmingCharactersInSet:whitespace];
            if (substring.length) [results addObject:substring];
        }
        // Skip to next word
        [scanner scanCharactersFromSet:whitespace intoString:nil];
    }

    // Return non-mutable array
    return results.copy;

}

@end