Question

我正在编写一个JavaScript函数，用于在长字符串中查找重复的短语。该字符串将使用Unicode和非英语，这使我无法使用RegExps。在这99瓶啤酒的例子中，结果应该是“墙上的啤酒瓶”，“拿一个，传递它”等没有数字，只有重复的部分，但它给出了错误的结果：

window.findRepeats=function(){
 inputString=document.getElementById("txt1").value;
 
 outputArray=[];
 for(originalStart=0;originalStart<inputString.length;originalStart++){
  for(copyStart=originalStart+1;copyStart<inputString.length;copyStart++){
   if(inputString[originalStart]==inputString[copyStart]){
    for(windowByte=originalStart+1;windowByte<copyStart;windowByte++){
     if(inputString[windowByte]!=inputString[copyStart-originalStart+windowByte]){
      break;
      }
     if(windowByte>originalStart+1){
      outputArray.push([originalStart,windowByte]);
      }
     }
    }
   }
  }
 for(arrayCounter=0;arrayCounter<outputArray.length;arrayCounter++){
  outputArray[arrayCounter]+=":"+inputString.substring(outputArray[arrayCounter][0],outputArray[arrayCounter][1]);
  }
 document.getElementById("txt2").value=outputArray.join("\n");
 }

<textarea rows=9 id="txt1">
99 bottles of beer on the wall, 99 bottles of beer.
Take one down and pass it around, 98 bottles of beer on the wall.
98 bottles of beer on the wall, 98 bottles of beer.
Take one down and pass it around, 97 bottles of beer on the wall.
97 bottles of beer on the wall, 97 bottles of beer.
Take one down and pass it around, 96 bottles of beer on the wall.
96 bottles of beer on the wall, 96 bottles of beer.
Take one down and pass it around, 95 bottles of beer on the wall.
95 bottles of beer on the wall, 95 bottles of beer.
Take one down and pass it around, 94 bottles of beer on the wall.


</textarea>
<br>
    
<textarea rows=9 id="txt2">
    
</textarea>
<br>
<input type="button" value="go" onclick='findRepeats()'>
    
</input>

如果你查看结果，它会给出所有重复的子串，但不是最长的子串。我只想要最长的子串。至于后缀数组和树，到目前为止我都无法理解这些，所以我必须处理这种方法。

Answer 1

SOSO WORKING

这个怎么样？

显然，您的原始功能有错误，结果中的某些内容并不正确。我现在尝试简化代码。

＆＃13;

window.findRepeats=function(){
  var inputString = document.getElementById("txt1").value;
  var outputArray=[];
  for(originalStart=0;originalStart<inputString.length;originalStart++){
    for(copyStart=originalStart+1;copyStart<inputString.length;copyStart++){
      if(inputString[originalStart]==inputString[copyStart]){
        for(windowByte=originalStart+1;windowByte<copyStart;windowByte++){
          if(inputString[windowByte]!=inputString[copyStart-originalStart+windowByte]){
            break;
          }
          if(windowByte>originalStart+1){
            outputArray.push([originalStart,windowByte+1]);
          }
        }
      }
    }
  }
  var shorts = [];
  for(var i=0;i<outputArray.length;i++){
    var curString = inputString.substring(outputArray[i][0],outputArray[i][1]);
    if (curString[0] === " ")
      curString = curString.substr(1);
    if (curString.trim() != "")
      shorts.push(curString);
  }
  var uniq = removeDuplicate(shorts);
  for (var j=uniq.length-1;j>-1;j--){
    for (var k=uniq.length-1;k>-1;k--){
      if (uniq[j].indexOf(uniq[k]) > -1) {
        uniq[k]=uniq[j];
      }
    }
  }
  uniq = removeDuplicate(uniq);
  shorts = uniq;
  document.getElementById("txt2").value=shorts.join("\n----------------\n");
}
function removeDuplicate(arr) {
  return arr.slice().sort(function(a,b){return a > b}).reduce(function(a,b){if (a.slice(-1)[0] !== b) a.push(b);return a;},[]);
}

＆＃13;

<textarea rows=9 style="width:100%" id="txt1">3 bottles of beer on the wall, 3 bottles of beer.
Take one down and pass it around, 2 bottles of beer on the wall.

2 bottles of beer on the wall, 2 bottles of beer.
Take one down and pass it around, 1 bottle of beer on the wall.

1 bottle of beer on the wall, 1 bottle of beer.
Take one down and pass it around, no more bottles of beer on the wall.

No more bottles of beer on the wall, no more bottles of beer.
Go to the store and buy some more, 99 bottles of beer on the wall.</textarea>
<br>
    
<textarea rows=9 style="width:100%" id="txt2"></textarea>
<br>
<input type="button" value="go" onclick='findRepeats()'>

＆＃13;

错误导致重复的子串函数最长

1 个答案: