*/
    protected Pattern xmlEncodingPattern =
            Pattern.compile("<\\?xml.*encoding\\s*=\\s*['\"]([\\w\\d\\-_]*)['\"]\\s*\\?>", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for XML tags.
     */
    protected Pattern xmlTagPattern = Pattern.compile("<[^>]+>");

    /**
     * Returns the encoding pattern.
     * @return The encoding pattern.
     */
    @Override

labels.search=Ara
labels.similar_doc_result_status=Benzer sonuçlar gösteriliyor.
labels.search_result_status=<b>{0}</b> için <b>{2}</b> - <b>{3}</b> arası sonuçlar (toplam <b>{1}</b>)
labels.search_result_status_over=<b>{0}</b> için <b>{2}</b> - <b>{3}</b> arası sonuçlar (<b>{1}</b> üzerinde)
labels.search_result_time=({0} saniye)
labels.prev_page=Önceki
labels.next_page=Sonraki

        } catch (final Exception e) {
            throw new StorageException("Failed to get tags from " + objectName, e);
        }
    }

    @Override
    public void setObjectTags(final String objectName, final Map<String, String> tags) {
        try {
            final List<Tag> tagList = tags.entrySet()
                    .stream()

---
title: Sample Markdown Document
author: John Doe
date: 2025-01-15
tags:
  - crawler
  - extractor
  - markdown
---

# Introduction

This is a sample Markdown document for testing the MarkdownExtractor.

## Features

The extractor should handle:

- YAML front matter extraction
- Heading structure
- **Bold text** and *italic text*
- Lists and other formatting

### Code Examples

        minioClient.setObjectTags(
                SetObjectTagsArgs.builder().bucket(bucketName).object("dir1/file2.txt").tags(Map.of("label", "label2")).build());
        minioClient.setObjectTags(
                SetObjectTagsArgs.builder().bucket(bucketName).object("dir1/dir2/file3.txt").tags(Map.of("label", "label3")).build());

teihin
teillä
teiltä
teille
he
heidän
heidät
heitä
heissä
heistä
heihin
heillä
heiltä
heille
tämä
tämän
tätä
tässä
tästä
tähän
tallä
tältä
tälle
tänä
täksi
tuo
tuon
tuotä
tuossa
tuosta
tuohon
tuolla
tuolta
tuolle
tuona
tuoksi
se
sen
sitä
siinä
siitä
siihen
sillä
siltä
sille
sinä
siksi

            public static final String HTML_CANONICAL_XPATH = "html.canonical.xpath";
            public static final String HTML_PRUNED_TAGS = "html.pruned.tags";
            public static final String PIPELINE = "pipeline";
            public static final String IGNORE_ROBOTS_TAGS = "ignore.robots.tags";
            public static final String SCRIPT_TYPE = "script.type";
            public static final String HTML_CHILD_URL_RULES = "html.child.url.rules";

     * @param fields The fields.
     * @param tags The tags.
     * @param roles The roles.
     * @param num The number.
     * @param langs The languages.
     * @return The SuggestIndexResponse.
     */
    public SuggestIndexResponse indexFromSearchWord(final String searchWord, final String[] fields, final String[] tags,
            final String[] roles, final int num, final String[] langs) {

{
  "title": "Sample Document",
  "author": "John Doe",
  "version": "1.0",
  "published": "2025-01-15",
  "tags": ["crawler", "extractor", "json"],
  "content": {
    "summary": "This is a sample JSON document for testing",
    "body": "The extractor should handle nested objects and arrays properly"
  },
  "metadata": {
    "created_at": "2025-01-01T00:00:00Z",
    "updated_at": "2025-01-15T12:00:00Z"
  }

    "queryFreq": {
      "type": "long"
    },
    "roles": {
      "type": "keyword"
    },
    "languages": {
      "type": "keyword"
    },
    "score": {
      "type": "double"
    },
    "tags": {
      "type": "keyword"
    },
    "text": {
      "type": "keyword"
    },
    "userBoost": {
      "type": "double"
    }
  }