Java 使用StringTokenizer模拟String.split

我正在将现有应用程序中的代码转换为针对自定义硬件的Java1.1编译器进行编译。这意味着我不能使用

String.split（regex）

将现有字符串转换为数组

我创建了一个方法，它应该给出与

String.split（regex）

相同的结果，但是它有一些问题，我不知道是什么

代码：

private static String[] split(String delim, String line) {
  StringTokenizer tokens = new StringTokenizer(line, delim, true);
  String previous = "";
  Vector v = new Vector();

  while(tokens.hasMoreTokens()) {
    String token = tokens.nextToken();

    if(!",".equals(token)) {
      v.add(token);
    } else if(",".equals(previous)) {
      v.add("");
    } else {
      previous = token;
    }
  }

  return (String[]) v.toArray(new String[v.size()]);
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = split(",", line);

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = line.split(",");

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

样本输入：

private static String[] split(String delim, String line) {
  StringTokenizer tokens = new StringTokenizer(line, delim, true);
  String previous = "";
  Vector v = new Vector();

  while(tokens.hasMoreTokens()) {
    String token = tokens.nextToken();

    if(!",".equals(token)) {
      v.add(token);
    } else if(",".equals(previous)) {
      v.add("");
    } else {
      previous = token;
    }
  }

  return (String[]) v.toArray(new String[v.size()]);
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = split(",", line);

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = line.split(",");

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

地址：0013A2004081937F，邮编：90601234FF

样本输出：

private static String[] split(String delim, String line) {
  StringTokenizer tokens = new StringTokenizer(line, delim, true);
  String previous = "";
  Vector v = new Vector();

  while(tokens.hasMoreTokens()) {
    String token = tokens.nextToken();

    if(!",".equals(token)) {
      v.add(token);
    } else if(",".equals(previous)) {
      v.add("");
    } else {
      previous = token;
    }
  }

  return (String[]) v.toArray(new String[v.size()]);
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = split(",", line);

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = line.split(",");

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

[RM^RES][0013A2004081937F][9060][1234FF]

所需输出：

private static String[] split(String delim, String line) {
  StringTokenizer tokens = new StringTokenizer(line, delim, true);
  String previous = "";
  Vector v = new Vector();

  while(tokens.hasMoreTokens()) {
    String token = tokens.nextToken();

    if(!",".equals(token)) {
      v.add(token);
    } else if(",".equals(previous)) {
      v.add("");
    } else {
      previous = token;
    }
  }

  return (String[]) v.toArray(new String[v.size()]);
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = split(",", line);

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = line.split(",");

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

[RM^RES][0013A2004081937F][[9060][1234FF]

---

我试图转换的旧代码：

private static String[] split(String delim, String line) {
  StringTokenizer tokens = new StringTokenizer(line, delim, true);
  String previous = "";
  Vector v = new Vector();

  while(tokens.hasMoreTokens()) {
    String token = tokens.nextToken();

    if(!",".equals(token)) {
      v.add(token);
    } else if(",".equals(previous)) {
      v.add("");
    } else {
      previous = token;
    }
  }

  return (String[]) v.toArray(new String[v.size()]);
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = split(",", line);

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

String line = "RM^RES,0013A2004081937F,,9060,1234FF";
String[] items = line.split(",");

for(String s : items) {
    System.out.println(" [ " + s + " ] ");
}

[RM^RES][0013A2004081937F][[9060][1234FF]

---

几乎一切都是对的。几乎是，因为您忘记了“清除”上一个

的值。
试试这个：

if(!",".equals(token)) {
  v.add(token);
  previous = "";
} else if(",".equals(previous)) {
  v.add("");
  previous = "";
} else {
  previous = token;
}

完全不使用StringTokenizer如何：

private static String[] split(String delim, String line) {
    String current = line;
    int index = line.indexOf(delim);
    Vector vector = new Vector();
    while (index != -1) {
        vector.add(current.substring(0, index));
        current = current.substring(index + 1);
        index = current.indexOf(delim);
    }
    vector.add(current);

    return (String[]) vector.toArray(new String[vector.size()]);
}

你可以这样试试

 public static void main(String[] args) throws ParseException {
    for (String s : split(",", "RM^RES,0013A2004081937F, ,9060,1234FF")) {
        System.out.print(" [ " + s + " ] ");
    }
  }

private static String[] split(String delim, String line) {
    StringTokenizer tokens = new StringTokenizer(line, delim);
    String[] v = new String[tokens.countTokens()];
    int i = 0;
    while (tokens.hasMoreTokens()) {
        v[i] = tokens.nextToken();
        i++;
    }
    return v;
}

我认为您不应该对底层分隔符进行任何假设

    public static String[] split(String line, String delim) {
        Vector v = new Vector();
        final String EMPTY_STRING = "";
        StringTokenizer st = new StringTokenizer(line, delim, true);
        while (st.hasMoreTokens()) {
            String token = st.nextToken();

            if (token.equals(delim)) {
                if (v.isEmpty() || v.size() > 0 && !EMPTY_STRING.equals(v.get(v.size() - 1))) {
                    v.add(EMPTY_STRING);
                }
            } else {
                v.add(token);
            }
        }

        return (String[])v.toArray(new String[v.size()]);
    }

我修改了代码并进行了测试。它可以工作（不要忘了避免硬编码“，”以便您可以对任何分隔符使用该函数）：

这仍然给我不正确的输出
[RM^RES][0013A2004081937F][[9060][[1234FF]
尝试将
previous=token
放在{}中，如果{}之后可以工作，但Andrei M已经给出了更好的解决方案。无论如何，谢谢。如果您计划使用另一个分隔符，您可能想在拆分方法中将
“，”.equals（…）
替换为
delim.equals（…）
。@haraldK谢谢，这是一个很好的注释，可以把问题放在一边：）这不起作用，因为我的数组也将包含分隔符。它看起来是这样的：
[RM^RES][，][0013A2004081937F][，][，][，]
等等。此外，您将我的字符串更改为在逗号之间添加空格，我无法更改输入，因为这是必须遵循的协议。这不起作用，因为每次我获得分隔符时，它都会添加一个空字符串，我的数组将如下所示：
[RM^RES][[0013A2004081937F][[]
等。基本上，每个逗号都将成为一个空数组槽。