CmsHtmlExtractor
Code IndexAdd Codota to your IDE (free)

Best Java code snippets using org.opencms.util.CmsHtmlExtractor (Showing top 13 results out of 315)

origin: org.opencms/opencms-solr

return extractText(in, encoding);
origin: org.opencms/opencms-core

return extractText(in, encoding);
origin: org.opencms/opencms-core

/**
 * @see org.opencms.xml.types.I_CmsXmlContentValue#getPlainText(org.opencms.file.CmsObject)
 */
@Override
public String getPlainText(CmsObject cms) {
  try {
    return CmsHtmlExtractor.extractText(getStringValue(cms), m_document.getEncoding());
  } catch (Exception exc) {
    return null;
  }
}
origin: org.opencms/opencms-solr

/**
 * @see org.opencms.xml.types.I_CmsXmlContentValue#getPlainText(org.opencms.file.CmsObject)
 */
@Override
public String getPlainText(CmsObject cms) {
  try {
    return CmsHtmlExtractor.extractText(this.getStringValue(cms), m_document.getEncoding());
  } catch (Exception exc) {
    return null;
  }
}
origin: org.opencms/opencms-core

/**
 * @see org.opencms.xml.types.I_CmsXmlContentValue#getPlainText(org.opencms.file.CmsObject)
 */
@Override
public String getPlainText(CmsObject cms) {
  if (m_plainTextValue == null) {
    try {
      m_plainTextValue = CmsHtmlExtractor.extractText(getStringValue(cms), m_document.getEncoding());
    } catch (Exception exc) {
      m_plainTextValue = NULL_VALUE;
    }
  }
  if (m_plainTextValue == NULL_VALUE) {
    return null;
  }
  return m_plainTextValue;
}
origin: org.opencms/opencms-solr

if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(value)) {
  try {
    value = CmsHtmlExtractor.extractText(value, CmsEncoder.ENCODING_UTF_8);
  } catch (ParserException e) {
    if (LOG.isErrorEnabled()) {
origin: org.opencms/opencms-core

  /**
   * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
   */
  @Override
  public I_CmsExtractionResult extractText(InputStream in, String encoding) throws Exception {

    String result = "";
    try {
      if (CmsStringUtil.isEmpty(encoding)) {
        encoding = OpenCms.getSystemInfo().getDefaultEncoding();
      }
      result = CmsHtmlExtractor.extractText(in, encoding);
      result = removeControlChars(result);
    } catch (Exception e) {
      if (LOG.isErrorEnabled()) {
        LOG.error(Messages.get().container(Messages.LOG_EXTRACT_TEXT_ERROR_0), e);
      }
    }
    return new CmsExtractionResult(result);
  }
}
origin: org.opencms/opencms-core

String elementName = i.next();
String value = page.getStringValue(cms, elementName, locale);
String extracted = CmsHtmlExtractor.extractText(value, page.getEncoding());
if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(extracted)) {
  items.put(elementName, extracted);
origin: org.opencms/opencms-core

if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(value)) {
  try {
    value = CmsHtmlExtractor.extractText(value, CmsEncoder.ENCODING_UTF_8);
  } catch (ParserException e) {
    if (LOG.isErrorEnabled()) {
origin: org.opencms/opencms-core

if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(value)) {
  try {
    value = CmsHtmlExtractor.extractText(value, CmsEncoder.ENCODING_UTF_8);
  } catch (ParserException e) {
    if (LOG.isErrorEnabled()) {
origin: org.opencms/opencms-solr

  /**
   * @see org.opencms.search.extractors.I_CmsTextExtractor#extractText(java.io.InputStream, java.lang.String)
   */
  @Override
  public I_CmsExtractionResult extractText(InputStream in, String encoding) throws Exception {

    String result = "";
    try {
      if (CmsStringUtil.isEmpty(encoding)) {
        encoding = OpenCms.getSystemInfo().getDefaultEncoding();
      }
      result = CmsHtmlExtractor.extractText(in, encoding);
      result = removeControlChars(result);
    } catch (Exception e) {
      if (LOG.isErrorEnabled()) {
        LOG.error(Messages.get().container(Messages.LOG_EXTRACT_TEXT_ERROR_0), e);
      }
    }
    return new CmsExtractionResult(result);
  }
}
origin: org.opencms/opencms-solr

if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(value)) {
  try {
    value = CmsHtmlExtractor.extractText(value, CmsEncoder.ENCODING_UTF_8);
  } catch (ParserException e) {
    if (LOG.isErrorEnabled()) {
origin: org.opencms/opencms-solr

String elementName = i.next();
String value = page.getStringValue(cms, elementName, locale);
String extracted = CmsHtmlExtractor.extractText(value, page.getEncoding());
if (CmsStringUtil.isNotEmptyOrWhitespaceOnly(extracted)) {
  items.put(elementName, extracted);
org.opencms.utilCmsHtmlExtractor

Javadoc

Extracts plain text from HTML.

Most used methods

  • extractText
    Extract the text from a HTML page.

Popular in Java

  • Parsing JSON documents to java classes using gson
  • getOriginalFilename (MultipartFile)
    Return the original filename in the client's filesystem.This may contain path information depending
  • getResourceAsStream (ClassLoader)
  • notifyDataSetChanged (ArrayAdapter)
  • Rectangle (java.awt)
    A Rectangle specifies an area in a coordinate space that is enclosed by the Rectangle object's top-
  • URI (java.net)
    A Uniform Resource Identifier that identifies an abstract or physical resource, as specified by RFC
  • Permission (java.security)
    Legacy security code; do not use.
  • ResultSet (java.sql)
    An interface for an object which represents a database table entry, returned as the result of the qu
  • ArrayList (java.util)
    ArrayList is an implementation of List, backed by an array. All optional operations including adding
  • DateTimeFormat (org.joda.time.format)
    Factory that creates instances of DateTimeFormatter from patterns and styles. Datetime formatting i

For IntelliJ IDEA,
Android Studio or Eclipse

  • Search for JavaScript code betaCodota IntelliJ IDEA pluginCodota Android Studio pluginCode IndexSign in
  • EnterpriseFAQAboutBlogContact Us
  • Plugin user guideTerms of usePrivacy policyCodeboxFind Usages
Add Codota to your IDE (free)