csvExtractor.setMaxRows(2);
        final InputStream in = ResourceUtil.getResourceAsStream("extractor/csv/test.csv");
        final ExtractData extractData = csvExtractor.getText(in, null);
        CloseableUtil.closeQuietly(in);

        final String rowCount = extractData.getValues("row_count")[0];
        // Should extract 2 data rows (header doesn't count toward maxRows)
        assertEquals("2", rowCount);
    }

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.extractor.impl;

import java.util.regex.Pattern;

/**
 * Extracts text content from XML documents.
 */
public class XmlExtractor extends AbstractXmlExtractor {

    /**
     * Creates a new XmlExtractor instance.
     */

    /** The key of the message: Crawling/Displaying */
    public static final String LABELS_pathmap_pt_both = "{labels.pathmap_pt_both}";

    /** The key of the message: Extracted URL Conversion */
    public static final String LABELS_pathmap_pt_stored = "{labels.pathmap_pt_stored}";

    /** The key of the message: Regular Name */

```

4. **Add tests**: Unit + integration

### Adding a Content Extractor

1. **Implement `Extractor`**:
```java
public class MyExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(InputStream in, Map<String, String> params) {
        ExtractData data = new ExtractData();
        // Extract text
        data.setContent(extractedText);
        return data;
    }
}

import org.gradle.api.tasks.OutputFile
import org.gradle.api.tasks.PathSensitive
import org.gradle.api.tasks.PathSensitivity
import org.gradle.api.tasks.SourceTask
import org.gradle.api.tasks.TaskAction

/**
 * Extracts meta-data from the Groovy and Java source files which make up the Gradle API. Persists the meta-data to a file
 * for later use in generating documentation for the DSL, such as by {@link gradlebuild.docs.dsl.docbook.AssembleDslDocTask}.

        this.relatedQueryMap = relatedQueryMap;
        return relatedQueryMap.size();
    }

    /**
     * Extracts the virtual host key from a RelatedQuery entity.
     * If the virtual host is blank or null, returns an empty string.
     *
     * @param entity the RelatedQuery entity to extract the host key from
     * @return the virtual host key, or empty string if blank or null
     */

        if (result.errorCount() > 0) {
            context.info(result.errorCount() + " POM(s) had errors");
        }
        context.unindent();
    }

    /**
     * Extracts an Artifact from a POM document with parent resolution.
     * If groupId or version are missing, attempts to resolve from parent.
     *
     * <p>This method handles Maven's inheritance mechanism where groupId and version

    String getCrawlerDocumentHtmlPrunedTags();

    /**
     * Get the value for the key 'crawler.document.html.max.digest.length'. <br>
     * The value is, e.g. 120 <br>
     * comment: Maximum length of digest extracted from HTML documents.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */
    String getCrawlerDocumentHtmlMaxDigestLength();

    /**

            op.setRefreshPolicy(Constants.TRUE);
        });
        return failureUrl;
    }

    /**
     * Extracts and returns the stack trace from a throwable as a string.
     * The stack trace is abbreviated if it exceeds the configured maximum length.
     *
     * @param t the throwable to extract the stack trace from
     * @return the stack trace as a string, or empty string if extraction fails
     */

        assertContentType("application/pdf", "extractor/test.pdf", "hoge.pdf");

        assertContentType("application/gzip", "extractor/gz/test.tar.gz", "hoge.tar.gz");
        assertContentType("application/zip", "extractor/zip/test.zip", "hoge.zip");
        assertContentType("application/x-lharc", "extractor/lha/test.lzh", "hoge.lzh"); // TODO is it correct?

        assertContentType("application/xml", "extractor/test.mm", "hoge.mm");