我有以下类型的字符串

var string = "'string, duppi, du', 23, lala"

string.split(/,/)

["'string", " duppi", " du'", " 23", " lala"]

["string, duppi, du", "23", "lala"]

最佳答案

免责声明
2014-12-01 更新:以下答案仅适用于一种非常特定的 CSV 格式。正如正确指出的by DG in the comments ，此解决方案不符合 CSV 的 RFC 4180 定义，也不符合 Microsoft Excel 格式。该解决方案简单地演示了如何解析包含混合字符串类型的一个(非标准)CSV 输入行，其中字符串可能包含转义引号和逗号。
一个非标准的CSV解决方案
如 austincheney correctly points out ，如果您希望正确处理可能包含转义字符的带引号的字符串，您确实需要从头到尾解析字符串。此外，OP 没有明确定义“CSV 字符串”到底是什么。首先，我们必须定义什么构成有效的 CSV 字符串及其各个值。
给定:“CSV 字符串”定义
出于本次讨论的目的，“CSV 字符串”由零个或多个值组成，其中多个值用逗号分隔。每个值可能包括:

re_valid = r"""
# Validate a CSV string having single, double or un-quoted values.
^                                   # Anchor to start of string.
\s*                                 # Allow whitespace before value.
(?:                                 # Group for value alternatives.
  '[^'\\]*(?:\\[\S\s][^'\\]*)*'     # Either Single quoted string,
| "[^"\\]*(?:\\[\S\s][^"\\]*)*"     # or Double quoted string,
| [^,'"\s\\]*(?:\s+[^,'"\s\\]+)*    # or Non-comma, non-quote stuff.
)                                   # End group of value alternatives.
\s*                                 # Allow whitespace after value.
(?:                                 # Zero or more additional values
  ,                                 # Values separated by a comma.
  \s*                               # Allow whitespace before value.
  (?:                               # Group for value alternatives.
    '[^'\\]*(?:\\[\S\s][^'\\]*)*'   # Either Single quoted string,
  | "[^"\\]*(?:\\[\S\s][^"\\]*)*"   # or Double quoted string,
  | [^,'"\s\\]*(?:\s+[^,'"\s\\]+)*  # or Non-comma, non-quote stuff.
  )                                 # End group of value alternatives.
  \s*                               # Allow whitespace after value.
)*                                  # Zero or more additional values
$                                   # Anchor to end of string.
"""

re_value = r"""
# Match one value in valid CSV string.
(?!\s*$)                            # Don't match empty last value.
\s*                                 # Strip whitespace before value.
(?:                                 # Group for value alternatives.
  '([^'\\]*(?:\\[\S\s][^'\\]*)*)'   # Either $1: Single quoted string,
| "([^"\\]*(?:\\[\S\s][^"\\]*)*)"   # or $2: Double quoted string,
| ([^,'"\s\\]*(?:\s+[^,'"\s\\]+)*)  # or $3: Non-comma, non-quote stuff.
)                                   # End group of value alternatives.
\s*                                 # Strip whitespace after value.
(?:,|$)                             # Field ends on comma or EOS.
"""

// Return array of string values, or NULL if CSV string not well formed.
function CSVtoArray(text) {
    var re_valid = /^\s*(?:'[^'\\]*(?:\\[\S\s][^'\\]*)*'|"[^"\\]*(?:\\[\S\s][^"\\]*)*"|[^,'"\s\\]*(?:\s+[^,'"\s\\]+)*)\s*(?:,\s*(?:'[^'\\]*(?:\\[\S\s][^'\\]*)*'|"[^"\\]*(?:\\[\S\s][^"\\]*)*"|[^,'"\s\\]*(?:\s+[^,'"\s\\]+)*)\s*)*$/;
    var re_value = /(?!\s*$)\s*(?:'([^'\\]*(?:\\[\S\s][^'\\]*)*)'|"([^"\\]*(?:\\[\S\s][^"\\]*)*)"|([^,'"\s\\]*(?:\s+[^,'"\s\\]+)*))\s*(?:,|$)/g;

    // Return NULL if input string is not well formed CSV string.
    if (!re_valid.test(text)) return null;

    var a = []; // Initialize array to receive values.
    text.replace(re_value, // "Walk" the string using replace with callback.
        function(m0, m1, m2, m3) {

            // Remove backslash from \' in single quoted values.
            if (m1 !== undefined) a.push(m1.replace(/\\'/g, "'"));

            // Remove backslash from \" in double quoted values.
            else if (m2 !== undefined) a.push(m2.replace(/\\"/g, '"'));
            else if (m3 !== undefined) a.push(m3);
            return ''; // Return empty string.
        });

    // Handle special case of empty last value.
    if (/,\s*$/.test(text)) a.push('');
    return a;
};

// Test 1: Test string from original question.
var test = "'string, duppi, du', 23, lala";
var a = CSVtoArray(test);
/* Array has three elements:
    a[0] = {string, duppi, du}
    a[1] = {23}
    a[2] = {lala} */

// Test 2: Empty CSV string.
var test = "";
var a = CSVtoArray(test);
/* Array has zero elements: */

// Test 3: CSV string with two empty values.
var test = ",";
var a = CSVtoArray(test);
/* Array has two elements:
    a[0] = {}
    a[1] = {} */

// Test 4: Double quoted CSV string having single quoted values.
var test = "'one','two with escaped \' single quote', 'three, with, commas'";
var a = CSVtoArray(test);
/* Array has three elements:
    a[0] = {one}
    a[1] = {two with escaped ' single quote}
    a[2] = {three, with, commas} */

// Test 5: Single quoted CSV string having double quoted values.
var test = '"one","two with escaped \" double quote", "three, with, commas"';
var a = CSVtoArray(test);
/* Array has three elements:
    a[0] = {one}
    a[1] = {two with escaped " double quote}
    a[2] = {three, with, commas} */

// Test 6: CSV string with whitespace in and around empty and non-empty values.
var test = "   one  ,  'two'  ,  , ' four' ,, 'six ', ' seven ' ,  ";
var a = CSVtoArray(test);
/* Array has eight elements:
    a[0] = {one}
    a[1] = {two}
    a[2] = {}
    a[3] = { four}
    a[4] = {}
    a[5] = {six }
    a[6] = { seven }
    a[7] = {} */

var invalid1 = "one, that's me!, escaped \, comma"

关于javascript - 如何使用 JavaScript 解析数据中包含逗号的 CSV 字符串？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/8493195/