Example usage for java.util.regex Matcher replaceAll

Introduction

In this page you can find the example usage for java.util.regex Matcher replaceAll.

Prototype

public String replaceAll(Function<MatchResult, String> replacer)

Source Link

Document

Replaces every subsequence of the input sequence that matches the pattern with the result of applying the given replacer function to the match result of this matcher corresponding to that subsequence.

Usage

From source file:opennlp.tools.similarity.apps.utils.Utils.java

public static String stripHTMLMultiLine(String text) {
    Pattern p = java.util.regex.Pattern.compile("\\<.*?>", Pattern.DOTALL);
    Matcher matcher = p.matcher(text);
    String tmp = matcher.replaceAll("");
    return tmp;/*from  ww w  . j  a  v a2 s  .c om*/
}

From source file:opennlp.tools.similarity.apps.utils.Utils.java

public static String stripHTMLCommentsMultiLine(String text) {
    Pattern p = java.util.regex.Pattern.compile("\\<!--.*?-->", Pattern.DOTALL);
    Matcher matcher = p.matcher(text);
    String tmp = matcher.replaceAll("");
    return tmp;//from  ww  w.  j  a v  a 2s  . co  m
}

From source file:opennlp.tools.similarity.apps.utils.Utils.java

public static String stripScriptTags(String text) {
    Pattern p = java.util.regex.Pattern.compile("\\<SCRIPT.*?</SCRIPT>",
            Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
    Matcher matcher = p.matcher(text);
    String tmp = matcher.replaceAll("");
    return tmp;/*from   w ww.j  a  va 2s . c  o  m*/
}

From source file:opennlp.tools.similarity.apps.utils.Utils.java

public static String stripNoScriptTags(String text) {
    Pattern p = java.util.regex.Pattern.compile("\\<NOSCRIPT.*?</NOSCRIPT>",
            Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
    Matcher matcher = p.matcher(text);
    String tmp = matcher.replaceAll("");
    return tmp;//from   w ww .j av  a2 s .c  o  m
}

From source file:opennlp.tools.similarity.apps.utils.Utils.java

public static String stripStyleTags(String text) {
    Pattern p = java.util.regex.Pattern.compile("\\<STYLE.*?</STYLE>",
            Pattern.DOTALL | Pattern.CASE_INSENSITIVE);
    Matcher matcher = p.matcher(text);
    String tmp = matcher.replaceAll("");
    return tmp;// www . ja v  a2  s  .c om
}

From source file:com.bizosys.dataservice.util.StringUtils.java

public static String stripExtraSpace(String input) {
    Matcher matcher = pattern.matcher(input);
    return matcher.replaceAll(" ");
}

From source file:com.sfs.Formatter.java

/**
 * Gets the numeric phone./*  w w  w.ja  va  2  s  .c o  m*/
 *
 * @param countryCode the country code
 * @param areaCode the area code
 * @param phoneNumber the phone number
 *
 * @return the numeric phone
 */
public static String getNumericPhone(final int countryCode, final int areaCode, final String phoneNumber) {
    StringBuffer phone = new StringBuffer();

    int intPhoneNumber = 0;
    try {
        intPhoneNumber = Integer.parseInt(phoneNumber);
    } catch (NumberFormatException nfe) {
        intPhoneNumber = 0;
    }

    if (intPhoneNumber == 0 && StringUtils.isNotBlank(phoneNumber)) {
        // An integer has not been parsed, but a phone number
        // has been supplied. This means it probably contains
        // some non-numeric characters.
        Pattern pattern = Pattern.compile("[^\\d]");
        Matcher match = pattern.matcher(phoneNumber);
        String onlyDigits = match.replaceAll("");

        try {
            intPhoneNumber = Integer.parseInt(onlyDigits);
        } catch (NumberFormatException nfe) {
            intPhoneNumber = 0;
        }
    }

    // Build the phone numeric string
    phone.append("+");
    phone.append(countryCode);
    phone.append(" ");
    phone.append(areaCode);
    phone.append(" ");
    phone.append(intPhoneNumber);

    return phone.toString();
}

From source file:org.opencron.common.utils.StringUtils.java

/**
 * script//w w  w.ja  v a  2 s .c om
 *
 * @param htmlStr
 * @return writer:<a href="mailto:benjobs@qq.com">benjobs</a> 2012.2.1
 */
public static String replaceScript(String htmlStr) {
    if (htmlStr == null || "".equals(htmlStr)) {
        return "";
    }
    String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // script?
    Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
    Matcher m_script = p_script.matcher(htmlStr);
    htmlStr = m_script.replaceAll(""); // script
    return htmlStr.trim(); // 
}

From source file:org.geopublishing.atlasViewer.GpCoreUtil.java

/**
 * This method converts backslashes to forwardslashes in any html document.
 * Backslashes dont work in linux environments and when using the atlas out
 * of a .jar geopublisher expects forwardslashes
 * /*w w w .  ja  va  2  s .com*/
 * @param url
 * @return
 */
public static URL convertWindowsToLinuxSlashesInHtmlSrcTags(URL url) {
    String htmlString = IOUtil.readURLasString(url);
    File tempFile = null;
    Pattern p = Pattern.compile("(<[^>]+(?:src|href)=\"[^\"]*)\\\\([^\"]*\"[^>]*>)",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);
    Matcher m = p.matcher(htmlString);

    while (m.find()) {
        htmlString = m.replaceAll("$1/$2");
        m = p.matcher(htmlString);
    }
    try {
        tempFile = IOUtil.createTemporaryFile("tmp", ".html", true);
        InputStream bais = new ByteArrayInputStream(htmlString.getBytes());
        IOUtil.writeStreamToFile(bais, tempFile);
        IOUtil.copyFileNoException(null, tempFile, IOUtil.urlToFile(url), false);
    } catch (IOException e) {
    }

    return url;

}

From source file:org.opencron.common.utils.StringUtils.java

/**
 * html//from   w w w. j a v  a2  s.com
 *
 * @param htmlStr
 * @return writer:<a href="mailto:benjobs@qq.com">benjobs</a> 2012.2.1
 */
public static String replaceHtml(String htmlStr) {
    if (htmlStr == null || "".equals(htmlStr)) {
        return "";
    }
    String regEx_script = "<script[^>]*?>[\\s\\S]*?</script>"; // script?
    String regEx_style = "<style[^>]*?>[\\s\\S]*?</style>"; // style?
    String regEx_html = "<[^>]+>"; // HTML?

    Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
    Matcher m_script = p_script.matcher(htmlStr);
    htmlStr = m_script.replaceAll(""); // script

    Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
    Matcher m_style = p_style.matcher(htmlStr);
    htmlStr = m_style.replaceAll(""); // style

    Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
    Matcher m_html = p_html.matcher(htmlStr);
    htmlStr = m_html.replaceAll(""); // html

    return htmlStr.trim(); // 
}