对鼠须管词库进行简单排序

在输入汉字时，会从这个文件 wubi86.dict.yaml中读取可输入的汉字以及自动造词生成的汉字，所以这个文件里的内容如果过多会影响输入效率，并且有些繁体字或者生僻字平时我们根本用不到，与其让其拖慢我们输入效率还不如写写代码排序，因为之前我已经把其中一些繁体字和者生僻字去除了，所以这次的需求是，降序排序，过一过里面输入次数较少的词。

image.png

直接上代码吧
oc版本

#import <Foundation/Foundation.h>
@interface LineObj :NSObject
@property (copy, nonatomic) NSString *outputValue;
@property (copy, nonatomic) NSString *outputKey;
@property(nonatomic, assign) NSUInteger inputNum;
@property (copy, nonatomic) NSString *otherOutputKey;
@property (copy, nonatomic) NSString *line;
@end
@implementation LineObj
- (NSString *)line {
    if (self.otherOutputKey && self.otherOutputKey.length) {
        
        return [NSString stringWithFormat:@"%@\t%@\t%tu\t%@\n", self.outputValue, self.outputKey,self.inputNum, self.otherOutputKey];
    }
    return [NSString stringWithFormat:@"%@\t%@\t%tu\n", self.outputValue, self.outputKey,self.inputNum];
}
@end

int main(int argc, const char * argv[]) {
    @autoreleasepool {
        
        
        NSError *encodeStringError ;
        unsigned long encode = CFStringConvertEncodingToNSStringEncoding(kCFStringEncodingUTF8);
        NSString *thesaurusFilePath = @"/Users/mac/Desktop/wubi86.dict.yaml";
        NSString *content = [NSString stringWithContentsOfFile:thesaurusFilePath encoding:encode error:&encodeStringError];
        if (encodeStringError) {
            
            NSLog(@"%@",encodeStringError);
        }
        
        NSData *thesaurusData = [content dataUsingEncoding:NSUTF8StringEncoding];
        NSString *thesaurusString = [[NSString alloc] initWithData:thesaurusData encoding:NSUTF8StringEncoding];
        NSArray<NSString *> *lineStrings = [thesaurusString componentsSeparatedByString:@"\n"];
        NSMutableArray *lineObjs = [NSMutableArray array];
        
        for (NSString *lineString in lineStrings) {
            
            NSArray<NSString *> *lineValues = [lineString componentsSeparatedByString:@"\t"];
            
            if (lineValues.count >= 3) {
            
                LineObj *lineObj = [[LineObj alloc] init];
                lineObj.outputValue = lineValues[0];
                lineObj.outputKey  = lineValues[1] ;
                lineObj.inputNum = [lineValues[2] integerValue];
                
                if (lineValues.count == 4) {
                    lineObj.otherOutputKey = lineValues[3];
                }
                
                [lineObjs addObject:lineObj];
            }
        }
        
        NSSortDescriptor *destor = [NSSortDescriptor sortDescriptorWithKey:@"inputNum" ascending:YES];
        lineObjs = [[lineObjs sortedArrayUsingDescriptors:@[destor]] mutableCopy];
        NSMutableString *outputMuString = [NSMutableString string];
        
        for (LineObj *obj in lineObjs) {
            [outputMuString appendString:obj.line];
        }
        
        NSLog(@"----%@---", outputMuString);
    }
    return 0;
}

然后 我看到了自己经常输入的不是词语，而是这些字

image.png

那么问题就来了，还是得注意，多打词语才能提升五笔的速度。

python版本

import operator
class LineObj(object):
    def __init__(self, outputValue, outputKey, outputNum, outputOtherKey=None):
        self.outputValue = outputValue
        self.outputKey = outputKey
        self.outputNum = int(outputNum)
        if outputOtherKey is not None:
            self.outputOtherKey = outputOtherKey
        else:
            self.outputOtherKey = ''

lineObjs = []
with open('wubi86.dict.yaml', 'rt') as f:
    for line in f:
        words = line.split('\t')
        if len(words) == 3:
            lineObj = LineObj(words[0], words[1], words[2])
            lineObjs.append(lineObj)
        elif len(words) == 4:
            lineObj = LineObj(words[0], words[1], words[2], words[3])
            lineObjs.append(lineObj)
cmpfun = operator.attrgetter('outputNum')
lineObjs.sort(key = cmpfun)
for lineObj in lineObjs:
    print lineObj.outputValue + '\t' + lineObj.outputKey + '\t' + str(lineObj.outputNum) + '\t' + lineObj.outputOtherKey

可见已排好序

image.png