Question

我收到错误，有人可以帮助我使用以下代码：它应该执行预处理

// program to perform preprocess

public static void main(String[] args) {

//public class PreProcess {

    // Read a file into a string. Takes file path, returns string

    /**
     *
     * @param path
     * @return
     */
    public String readFileIntoString(String path) {
    char[] line = new char[1024];
    StringBuilder dataString;
        dataString = new StringBuilder(5000);

    try {
            try (BufferedReader input = new BufferedReader(new FileReader(path))) {
                while (true) {
                    int readLength = input.read(line);
                    if (readLength == -1)
                        break;
                    dataString.append(line, 0, readLength);
                }
            }
        return dataString.toString();
    }
    catch (IOException e) {
        return " ";
    }
    }

    // Removes stop words from a string. Takes stop word file path and returns
    // string

    public static String removeStopWords(String fileData, String stopWordFilePath) {
    String newfile = fileData;
    String line;
    try {
        BufferedReader input = new BufferedReader(new FileReader(stopWordFilePath));
        while ((line = input.readLine()) != null) {
        if (line.compareTo("") == 0)
            continue;
        line = " " + line + " ";
        newfile = newfile.replaceAll(line, " ");
        }
        input.close();
    }
    catch (IOException e) {
        e.printStackTrace();
    }
    return newfile;
    }

    public static String removeHTMLTags(String fileData) {

    return strip(fileData);
    }

    // Filtering to a given windowsize for query terms. Takes query and size,
    // returns string

    public static String filterToWindow(String query, String fileData, int windowSize) {

    StringBuffer dataString = new StringBuffer(5000);
    String[] fileWords = fileData.split(" ");
    String[] queryWords = query.split(" ");
    int[] markWords = new int[fileWords.length];
    for (int i = 0; i < fileWords.length; i++) {
        markWords[i] = 0;
    }
    for (int i = 0; i < fileWords.length; i++) {
        for (int j = 0; j < queryWords.length; j++) {
        if (fileWords[i].compareTo(queryWords[j]) == 0) {
            for (int k = 0; k < windowSize; k++) {
            if (i + k < fileWords.length)
                markWords[i + k] = 1;
            if (i - k > 0)
                markWords[i - k] = 1;
            }
        }
        }
    }
    for (int i = 0; i < fileWords.length; i++) {
        if (markWords[i] == 1) {
        dataString.append(fileWords[i]);
        dataString.append(" ");
        }
    }
    return dataString.toString();
    }

    public static void extractMetaData(String fileData, String linkFilePath, int docId) {
    int urlEnd = 0, urlStart = 0;

    StringBuilder b3 = new StringBuilder();
    StringBuilder b2 = new StringBuilder();
    fileData = fileData.toLowerCase();
    try {
        String title = fileData.substring(fileData.indexOf("<title"), fileData.indexOf("</title>")).replaceAll("\\<.*?>", "");
        writeStringIntoFile(title, linkFilePath + docId + ".title");
    }
    catch (Exception e) {
    }
    while (true) {
        urlStart = fileData.indexOf("a href=\"", urlEnd) + 8;
        if (urlStart == 7)
        break;
        urlEnd = fileData.indexOf('\"', urlStart + 1);

        String link = fileData.substring(urlStart, urlEnd);
        int linkstart = 0;
        int linkend = link.length() - 1;
        if (link.startsWith("http"))
        link = link.substring(7);
        while (link.startsWith("/"))
        link = link.substring(1);
        if (!link.startsWith("#")) {
        if (link.indexOf('/') != -1)
            link = link.substring(0, link.indexOf('/'));
        if (!link.contains("wiki") && !link.contains("myspace.com") && !link.contains("javascript")) {
            b3.append(link);
            b3.append("\n");
        }
        }
    }
    writeStringIntoFile(b3.toString(), linkFilePath + docId + ".links");
    urlEnd = 0;
    while (true) {
        urlStart = fileData.indexOf("src=\"", urlEnd) + 5;
        if (urlStart == 4)
        break;
        urlEnd = fileData.indexOf('\"', urlStart + 1);
        String link = fileData.substring(urlStart, urlEnd);
        if (!link.startsWith("#")) {
        if (!link.startsWith("/")) {
            link = link.substring(0, link.lastIndexOf('/') + 1);
        }

        b2.append(link);
        b2.append("\n");
        }
    }
    writeStringIntoFile(b2.toString(), linkFilePath + docId + ".images");
    }

    // Saves a string to a file. Takes string and file path
    public static void writeStringIntoFile(String fileData, String path) {
    try {
            try (BufferedWriter output = new BufferedWriter(new FileWriter(path))) {
                output.write(fileData);
            }
    }
    catch (IOException e) {
    }
    }

    private static String strip(String inputString) {
    inputString = inputString.replaceAll("\\<style.*?</style>", " ");
    inputString = inputString.replaceAll("\\<script.*?</script>", " ");
    inputString = inputString.replaceAll("\\<.*?>", " ").replaceAll("[^A-Za-z]+", " ").replaceAll("\\s+", " ");
    inputString = inputString.trim();
    // inputString = PorterStemmer.applyStemmer(inputString);

    return inputString;
    }

}
    }

Answer 1

您已在main()

中声明了方法

public static void main(String[] args) {    

    public String readFileIntoString(String path) {
        char[] line = new char[1024];
        StringBuilder dataString;
        ...

你不能这样做。方法不能嵌套在方法中。拿出来

public static void main(String[] args) {    
   ...
}

public String readFileIntoString(String path) {
    char[] line = new char[1024];
    StringBuilder dataString;
    ...

线程“main”中的异常java.lang.RuntimeException：无法编译的源代码 - 非法的表达式启动

1 个答案: