java - 提取整数部分值，它只是给定文件中的 ID

Question

我编写了一个程序来提取文件中的所有整数值并找到重复的整数。但我只想要那些类似于 ID="****.."/id="****.." 的整数值。我不想考虑 "dependsOnPresenceOf" 值，无论它是什么。

我的文件是:例如

  <line id="24867948" dependsOnPresenceOf="7417840">
            <element text="Card Balance " id="18829409" dependsOnPresenceOf="28696224" />
  <line id="2597826922" dependsOnPresenceOf="200114712343">
            <methodElement fixedWidth="17" precededBySpace="false" id="418710522">
  <line id="24867948" dependsOnPresenceOf="10565536">
            <element text="  Cert. Number:" id="23917950" dependsOnPresenceOf="10565536" />
  <line id="24867948" dependsOnPresenceOf="10565536">
        <element text="  Cert. Number:" id="23917950" dependsOnPresenceOf="10565536" />

我的程序如下，我编写的程序仅提取整数值:

public class DuplicateIDPicker {

protected static final Logger logger = Logger
        .getLogger(com.aspire.pos.DuplicateIDPicker.class);

public static String finalContent = "";

public static void main(String[] args) throws FileNotFoundException {

    String content = "";
    /* Set location of the file as format below */
    String path = "D://TASK/DuplicateFinder/OriginalFile/";
    /* Set file name to be evaluate with extension */
    String fileName = "SSLItems.bpt";

    File f = new File(path.concat(fileName));

    try {
        content = readFile(f);
        String extractedInteger = content.replaceAll("\\D+", " ");
        String[] arrayOfID = findAllIDInArray(extractedInteger);

        System.out.println("***********************");

        HashSet<String> set    = new HashSet<String>();
        HashSet<String> newSet = new HashSet<String>();
        System.out.println("Duplicate ID's found :");
        for (String arrayElement : arrayOfID) {
            if (!set.add(arrayElement)) {
                // System.out.println("Duplicate Element is : "+arrayElement);
                newSet.add(arrayElement);
            }
        }

        System.out.println("-----------------------");
        /* here are all Duplicate Id */
        System.out.println(newSet);

    } catch (IOException e) {
        logger.error(e.getMessage());
    }

}

@SuppressWarnings("resource")
public static String readFile(File f) throws IOException {
    String data = "";

    FileReader fr = new FileReader(f);
    BufferedReader br = new BufferedReader(fr);

    while ((data = br.readLine()) != null) {
        // Print the content on the console
        finalContent = finalContent + data;
    }

    return finalContent;
}

public static String[] findAllIDInArray(String str) {
    String[] value = str.split(" ");
    return value;
}
}

Answer 1

您可以执行 content.replaceAll("dependsOnPresenceOf=\"\\d+\"", ""); 删除这些不需要的字符串