[文本处理] [已解决]批处理如何统计出文本中出现次数最多的一个字符？

//&cls&cscript -nologo -e:jscript "%~f0"<"文本.txt"&pause&exit
var arr={}, max=0;arr['list']=[];
var str=WSH.StdIn.ReadAll().replace(/[　\s]/g, '') //清除空白符
for (var i=0; i<str.length; i++){
    if(!arr[str.charAt(i)]){
        arr['list'].push(str.charAt(i));
        arr[str.charAt(i)]=1
    }else arr[str.charAt(i)]++;
}
arr['list'].sort(function(a, b){return arr[b]-arr[a]});
for(var i=0; i<arr['list'].length; i++){
    if(arr[arr['list'][i]]<max)break;
    WSH.echo(arr['list'][i]+':'+arr[arr['list'][i]]);
    max=arr[arr['list'][i]];
}
复制代码

@if (0)==(0) echo off
cscript //nologo //e:jscript "%~f0" < a.txt & pause & exit
@end

var s = WScript.StdIn.ReadAll().replace(/[\r\n]/g, '');
s = s.match(/./g).sort().join('');
var re = /(.)(\1)*/g, n = 0, map = {}, ar;
while(ar = re.exec(s)){
    if (ar[0].length >= n){
        n = ar[0].length;
        map[n]=map[n]?ar[1]+','+map[n]:ar[1];
    }
}
WScript.Echo('最多: ' + map[n] + '\n个数: ' + n)
复制代码

@if (0)==(0) echo off
cscript //nologo //e:jscript "%~f0" < %0 & pause & exit
@end

var s = WScript.StdIn.ReadAll();
s = s.match(/[^\r\n]/g).sort().join('');
var re = /(.)(\1)*/g, n = 0, ar = [];
s.replace(re,function($0,$1){
	n++;
	ar.length = ar.length > $0.length ? ar.length : $0.length;
	ar[$0.length-1] ? ar[$0.length-1].push($1) : ar[$0.length-1]=[$1];
})
WScript.Echo('最多: ' + ar.pop().join('\r\n') + '\n个数: ' + n);
复制代码

#&cls&@gawk -f %0 a.txt>con&pause>nul&exit
{
    for(i=1;i<=length($0);i++){
        arr[substr($0,i,1)]++
    }
}
END{
    for (x in arr){
	tmp="0000000000"arr[x]
        tmp=substr(tmp,length(arr[x])+1,10)
	arr[x]=tmp" "x
    }
	len=asort(arr,ta)
	for(i=len-19;i<=len;i++){
	    printf "%d %s\n",substr(ta[i],1,10),substr(ta[i],11,2)
	}
}
复制代码

# -*- coding: utf-8 -*-
"""
下面这个例子就是使用Counter模块统计一段句子里面所有字符出现次数
"""
from collections import Counter

s = '''A Counter is a dict subclass for counting hashable objects. It is an unordered collection where elements are stored as dictionary keys and their counts are stored as dictionary values. Counts are allowed to be any integer value including zero or negative counts. The Counter class is similar to bags or multisets in other languages.'''.lower()

c = Counter(s)
# 获取出现频率最高的5个字符
print c.most_common(5)


# Result:
[(' ', 54), ('e', 32), ('s', 25), ('a', 24), ('t', 24)]
复制代码

$s = 'A Counter is a dict subclass for counting hashable objects. It is an unordered collection where elements are stored as dictionary keys and their counts are stored as dictionary values. Counts are allowed to be any integer value including zero or negative counts. The Counter class is similar to bags or multisets in other languages.'

[char[]]$s | group-object | sort-object -desc count|select-object -first 5
复制代码

([char[]]$s|group|sort *)[-1..-5]
复制代码

#*&cls&@gawk -f "%~f0" "文本.txt">con&pause&exit
{
    gsub(/[[:space:]]/,"");
    for(i=1;i<=length($0);i++)a[substr($0,i,1)]++;
}
END{
    for(b in a){
        if(c[a[b]]){
            c[a[b]]=c[a[b]]" "b;
        }else{
            c[a[b]]=""b;
            d[a[b]]=a[b];
        }
    }
    for(i=asort(d);i>0;i--)print d[i]":"c[d[i]];
}
复制代码