［程序员日记］NSLinguisticTagger分词

NSLinguisticTagger是iOS自然语言处理工具，支持中文简体，繁体，日文，英文等多种语言。使用期做了一个分词的功能，结果很准确。连南京市长江大桥这样易混淆的句子都能够分的很准确。

NSString *string = self.text.text;
NSLinguisticTaggerOptions options = NSLinguisticTaggerOmitWhitespace | NSLinguisticTaggerJoinNames |NSLinguisticTaggerOmitPunctuation;
NSArray *arr = [NSLinguisticTagger availableTagSchemesForUnit:NSLinguisticTaggerUnitWord|NSLinguisticTaggerUnitDocument language:@"zh-Hans"];
NSLinguisticTagger * tagger = [[NSLinguisticTagger alloc]initWithTagSchemes:arr options:options];
tagger.string = string;


NSMutableArray *array = [[NSMutableArray alloc]init];
NSString *printStr = @"";

[tagger enumerateTagsInRange:NSMakeRange(0, string.length) scheme:NSLinguisticTagSchemeScript  options:options usingBlock:^(NSString * _Nonnull tag, NSRange tokenRange, NSRange sentenceRange, BOOL * _Nonnull stop) {
    NSString *token = [string substringWithRange:tokenRange];
    
    [array addObject:token];
    
    //[str stringByAppendingFormat:token];
    //NSLog(@"%@",array);

}];

for(int i = 0; i < [array count]; i++){
    printStr = [printStr stringByAppendingFormat:@"%@\n", [array objectAtIndex:i]];
}

效果如图