iOS-分词

分词是将一段string根据语法进行切分成若干个短语/词/字,多见于搜索中使用。

- (NSMutableArray *)participleWithString:(NSString *)originalString {
    
    CFLocaleRef locale; //分词工具
    CFRange range; //使用范围
    {
        if (!originalString.length) return nil;
        range = CFRangeMake(0, [originalString length]);
        locale = CFLocaleCopyCurrent(); //要CFRelease!
    }
    
    CFStringTokenizerRef tokenizer; // token解析 (要CFRelease!)
    tokenizer = CFStringTokenizerCreate(kCFAllocatorDefault, (CFStringRef)originalString, range, kCFStringTokenizerUnitWordBoundary, locale);   //初始化
    
    CFStringTokenizerTokenType tokenType; //token状态(监听分词进程)
    tokenType = CFStringTokenizerGoToTokenAtIndex(tokenizer, 0);
    NSMutableArray *participleArray = [NSMutableArray array];
    
    while (tokenType != kCFStringTokenizerTokenNone) {
        
        //获取当前使用范围
        range = CFStringTokenizerGetCurrentTokenRange(tokenizer);
        
        CFTypeRef tokenTag; //token标记 (要CFRelease!)
        //将标记存储
        tokenTag = CFStringTokenizerCopyCurrentTokenAttribute(tokenizer, kCFStringTokenizerAttributeLatinTranscription);
        
        [participleArray addObject:[originalString substringWithRange:NSMakeRange(range.location, range.length)]];
        
        CFRelease(tokenTag);
        
        //获取当前进程
        tokenType = CFStringTokenizerAdvanceToNextToken(tokenizer);
    }
    
    //释放
    CFRelease(locale);
    CFRelease(tokenizer);
    
    return participleArray;
}

你可能感兴趣的:(iOS-分词)