/**
 * Abstract base class for XML extractors.
 * Provides common functionality for extracting text content from XML-like documents.
 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */

        assertNotNull(encrypted, "Encrypted long password should not be null");
        assertTrue(encrypted.length > plaintext.length, "Encrypted data should be larger due to IV and auth tag");

        char[] decrypted = storage.decryptCredentials(encrypted);
        assertArrayEquals(plaintext, decrypted, "Decrypted long password should match original");

        // Clean up

    /**
     * Gets the pattern used for matching HTML tags.
     *
     * @return the HTML tag pattern
     */
    public Pattern getHtmlTagPattern() {
        return htmlTagPattern;
    }

    /**
     * Sets the pattern used for matching HTML tags.
     *
     * @param htmlTagPattern the HTML tag pattern to set
     */
    public void setHtmlTagPattern(final Pattern htmlTagPattern) {

      # Upload additional logs
      - google-cloud-storage:
          credentials-id: 'elasticsearch-ci-gcs-plugin'
          uploads:
            - classic:
                file-pattern: 'build/*.tar.bz2'
                storage-location: 'gs://elasticsearch-ci-artifacts/jobs/$JOB_NAME'
                share-publicly: false
                upload-for-failed-jobs: true
                show-inline: true
      # Notify homer

        assertEquals("\\share\\document.docx", validator.validatePath("\\share\\document.docx"));
        assertEquals("\\share\\archive.tar.gz", validator.validatePath("\\share\\archive.tar.gz"));
    }

    @Test
    public void testInternationalCharacters() throws Exception {
        // Should allow international characters in paths

mar
mo
mé
na
nach
naoi
naonúr
ná
ní
níor
nó
nócha
ocht
ochtar
os
roimh
sa
seacht
seachtar
seachtó
seasca
seisear
siad
sibh
sinn
sna
sé
sí
tar
thar
thú
triúr
trí
trína
trínár
tríocha
tú
um
ár
é
éis
í
ó
ón
óna

labels.storage_bucket_name=Nama Bucket
labels.storage_file=Berkas
labels.storage_folder_name=Nama Folder
labels.storage_button_download=Unduh
labels.storage_button_tags=Tag
labels.storage_title_tag=Tag:
labels.storage_tag_key=Kunci Tag
labels.storage_tag_value=Nilai Tag
labels.login.newpassword=Anda perlu memperbarui kata sandi Anda
labels.login.placeholder_new_password=Kata Sandi Baru

        @ParameterizedTest
        @DisplayName("Should return correct mime type for multiple extensions")
        @CsvSource({ "txt, text/plain", "css, text/css", "js, application/x-javascript", "zip, application/zip", "tar, application/x-tar",
                "gz, application/x-gzip", "tiff, image/tiff", "tif, image/tiff" })
        void testVariousExtensions(String extension, String expectedMimeType) throws IOException {

    public SuggestIndexer setSupportedFields(final String[] supportedFields) {
        this.supportedFields = supportedFields;
        return this;
    }

    /**
     * Sets the tag field names.
     * @param tagFieldNames The tag field names.
     * @return This SuggestIndexer instance.
     */
    public SuggestIndexer setTagFieldNames(final String[] tagFieldNames) {
        this.tagFieldNames = tagFieldNames;

     */
    private String contentLoc;

    /**
     * A URL pointing to a player for a specific video.
     * Usually this is the information in the src element of an <embed> tag.
     */
    private String playerLoc;

    /**
     * The duration of the video in seconds.
     * Value must be from 1 to 28800 (8 hours).
     */
    private String duration;

    /**