在javascript中将字符串转换为句子大小写

Convert string to sentence case in javascript

本文关键字:句子 大小写 转换 字符串 javascript      更新时间:2023-09-26

我希望输入的字符串在任何情况下都应转换为句子大小写。

喜欢

大家好,我是 DERP。 谢谢大家回答我的疑问。

转换为

大家好,这是德普。谢谢大家回答我的问题。

我想出了这种正则表达式:

var rg = /(^'w{1}|'.'s*'w{1})/gi;
var myString = "hi all, this is derp. thank you all to answer my query.";
myString = myString.replace(rg, function(toReplace) {
    return toReplace.toUpperCase();
});

试试这个,它会为你工作正常。它也适用于具有前导空格的字符串

var string="hi all, this is derp. thank you all to answer my query.";
var n=string.split(".");
var vfinal=""
for(i=0;i<n.length;i++)
{
   var spaceput=""
   var spaceCount=n[i].replace(/^('s*).*$/,"$1").length;
   n[i]=n[i].replace(/^'s+/,"");
   var newstring=n[i].charAt(n[i]).toUpperCase() + n[i].slice(1);
   for(j=0;j<spaceCount;j++)
   spaceput=spaceput+" ";
   vfinal=vfinal+spaceput+newstring+".";
 }
 vfinal=vfinal.substring(0, vfinal.length - 1);
 alert(vfinal);
这是我

对这篇文章的修改,用于更改为标题大小写。

您可以立即toLowerCase字符串,然后只需toUpperCase每个单词的第一个字母。成为一个非常简单的 1 衬里:

而不是每个字都做。此示例与多行和字符串(如 A.M.P.M.)兼容,当然,与句点和空格字符相关的任何单词兼容。

您可以在该toLowerCaseNames函数下方添加自己的自定义单词,并在下面的示例中toUpperCaseNames

// Based off this post: https://stackoverflow.com/a/40111894/8262102
var str = '-------------------'nhello world!'n'n2 Line Breaks. What is going on with this string. L.M.A.O.'n'nThee End...'nlower case example 1'nlower case example 2'n-------------------'nwait there''s more!'n-------------------'nhi all, this is derp. thank you all to answer my query.';
function toTitleCase(str) {
 return str.toLowerCase().replace(/'.'s*([a-z])|^[a-z]/gm, s => s.toUpperCase());
}
// Add your own names here to override to lower case
function toLowerCaseNames(str) {
  return str.replace(/'b(lower case example 1|lower case example 2)'b/gmi, s => s.toLowerCase());
}
// Add your own names here to override to UPPER CASE
function toUpperCaseNames(str) {
  return str.replace(/'b(hello|string)'b/gmi, s => s.toUpperCase());
}
console.log(toLowerCaseNames(toUpperCaseNames(toTitleCase(str))));

<小时 />

您可以将上面的所有这些正则表达式粘贴到 https://regexr.com/中,以分解它们的工作方式。

尝试演示

http://jsfiddle.net/devmgs/6hrv2/

function sentenceCase(strval){
 var newstrs = strval.split(".");
    var finalstr="";
    //alert(strval);
    for(var i=0;i<newstrs.length;i++)
        finalstr=finalstr+"."+ newstrs[i].substr(0,2).toUpperCase()+newstrs[i].substr(2);
    return finalstr.substr(1);
}

请注意,所有点并不总是代表行尾,可能是缩写等。也不确定是否在句号后键入空格。这些情况使此脚本容易受到攻击。

以下 SentenceCase 代码对我来说效果很好,还可以处理缩写,例如 a.m. 等。可能需要改进。

//=============================
// SentenceCase Function
// Copes with abbreviations
// Mohsen Alyafei (12-05-2017)
//=============================
function stringSentenceCase(str) {
  return str.replace(/'.'s+([a-z])[^'.]|^('s*[a-z])[^'.]/g, s => s.replace(/([a-z])/,s => s.toUpperCase()))
}
//=============================
console.log(stringSentenceCase(" start sentence.   second sentence . e.g. a.m. p.m."))
console.log(stringSentenceCase("first sentence. second sentence."))
console.log(stringSentenceCase("e.g. a.m. p.m. P.M. another sentence"))

你也可以试试这个

<script>
var name="hi all, this is derp. thank you all to answer my query.";
var n = name.split(".");
var newname="";
for(var i=0;i<n.length;i++)
{
var j=0;
while(j<n[i].length)
{
if(n[i].charAt(j)!= " ")
    {
        n[i] = n[i].replace(n[i].charAt(j),n[i].charAt(j).toUpperCase());
            break;
    }
else
  j++;
}
newname = newname.concat(n[i]+".");
 }
alert(newname);
 </script>

这是我最终使用的解决方案:

str = 'hi all, this is derp. thank you all to answer my query.';
temp_arr = str.split('.');
for (i = 0; i < temp_arr.length; i++) {
temp_arr[i]=temp_arr[i].trim()
temp_arr[i] = temp_arr[i].charAt(0).toUpperCase() + temp_arr[i].substr(1).toLowerCase();
}
str=temp_arr.join('. ') + '.';
return str;

下面的代码按预期为我工作。

   function toSentenceCase(inputString) {
        inputString = "." + inputString;
   var result = "";
   if (inputString.length == 0) {
       return result;
   }
   var terminalCharacterEncountered = false;
   var terminalCharacters = [".", "?", "!"];
   for (var i = 0; i < inputString.length; i++) {
       var currentChar = inputString.charAt(i);
       if (terminalCharacterEncountered) {
           if (currentChar == ' ') {
               result = result + currentChar;
           } else {
               var currentCharToUpperCase = currentChar.toUpperCase();
               result = result + currentCharToUpperCase;
               terminalCharacterEncountered = false;
           }
       } else {
           var currentCharToLowerCase = currentChar.toLowerCase();
           result = result + currentCharToLowerCase;
       }
       for (var j = 0; j < terminalCharacters.length; j++) {
           if (currentChar == terminalCharacters[j]) {
               terminalCharacterEncountered = true;
               break;
           }
       }
   }
        result = result.substring(1, result.length - 1);
   return result;
 }

我编写了一个基于 FSM 的函数来合并多个空格字符并将字符串转换为句子大小写。它应该很快,因为它不使用复杂的正则表达式或split并且假设您的 JavaScript 运行时具有有效的字符串连接,那么这应该是最快的方法。它还允许您轻松添加特殊情况的例外。

通过将空格正则表达式替换为比较字符代码的函数,可以进一步提高性能。

function toSentenceCase(str) {
    var states = {
        EndOfSentence  : 0,
        EndOfSentenceWS: 1, // in whitespace immediately after end-of-sentence
        Whitespace     : 2,
        Word           : 3
    };
    var state = states.EndOfSentence;
    var start = 0;
    var end   = 0;
    var output = "";
    var word = "";
    function specialCaseWords(word) {
        if( word == "i" ) return "I";
        if( word == "assy" ) return "assembly";
        if( word == "Assy" ) return "Assembly";
        return word;
    }
    for(var i = 0; i < str.length; i++) {
        var c = str.charAt(i);
        switch( state ) {
            case states.EndOfSentence:
                if( /'s/.test( c ) ) { // if char is whitespace
                    output += " "; // append a single space character
                    state = states.EndOfSentenceWS;
                }
                else {
                    word += c.toLocaleUpperCase();
                    state = states.Word;
                }
                break;
            case states.EndOfSentenceWS:
                if( !( /'s/.test( c ) ) ) { // if char is NOT whitespace
                    word += c.toLocaleUpperCase();
                    state = states.Word;
                }
                break;
            case states.Whitespace:
                if( !( /'s/.test( c ) ) ) { // if char is NOT whitespace
                    output += " "; // add a single whitespace character at the end of the current whitespace region only if there is non-whitespace text after.
                    word += c.toLocaleLowerCase();
                    state = states.Word;
                }
                break;
            case states.Word:
                if( c == "." ) {
                    word = specialCaseWords( word );
                    output += word;
                    output += c;
                    word = "";
                    state = states.EndOfSentence;
                } else if( !( /'s/.test( c ) ) ) { // if char is NOT whitespace
                    // TODO: See if `c` is punctuation, and if so, call specialCaseWords(word) and then add the puncutation
                    word += c.toLocaleLowerCase();
                }
                else {
                    // char IS whitespace (e.g. at-end-of-word):
                    // look at the word we just reconstituted and see if it needs any special rules
                    word = specialCaseWords( word );
                    output += word;
                    word = "";
                    state = states.Whitespace;
                }
                break;
        }//switch
    }//for
    output += word;
    return output;
}

在每一行上,此脚本将打印.....周日 周一 周二 周三 周四 周五 周六。

let rg = /(^'w{1}|'.'s*'w{1})/gi;
const days = ['sunday', 'monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday'];
for(let day of days) {
    console.log(day.replace(rg, function(toReplace) {
    return toReplace.toUpperCase();
}))
function toTitleCase(str) {
  if (!str) return "";
  return str
    .replace(/(?:^'w|[A-Z]|'b'w)/g, function (word, index) {
      return index === 0 ? word.toUpperCase() : word.toLowerCase();
    })
    .replace(/'s+/g, "");
}