// Add file URL
crawler.addUrl("file:///path/to/directory");
crawler.urlFilter.addInclude("file:///path/to/directory/.*");
```

## Configuration

### XML Configuration

Fess Crawler uses XML-based configuration with LastaFlute DI. Place configuration files in your classpath:

```xml
<!-- crawler.xml -->
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"

# architectures.
#
# Originally the Go build system used it as a smoke test to quickly
# flag portability issues in builders named "misc-compile" or "all-compile".
# As of CL 464955, the build system uses make.bash -compile-only instead,
# so this script no longer runs in any automated fashion.
#
# Options:
#   -e: stop at first failure

if [ ! -f run.bash ]; then
	echo 'buildall.bash must be run from $GOROOT/src' 1>&2

 * in descending order. The {@link #getExtractor(String)} method returns a composite
 * extractor that iterates through the available extractors until one successfully
 * extracts the data.
 * </p>
 *
 * <p>
 * The class uses a {@link CrawlerContainer} for managing crawler components and
 * supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

    /** Logger instance for this class */

			Typeflag:   '0',
			Uname:      "alex",
			Gname:      "wheel",
			AccessTime: time.Unix(1389782991, 419875220),
			ChangeTime: time.Unix(1389782956, 794414986),
			Xattrs: map[string]string{
				"user.key":  "value",
				"user.key2": "value2",
				// Interestingly, selinux encodes the terminating null inside the xattr
				"security.selinux": "unconfined_u:object_r:default_t:s0\x00",
			},
			PAXRecords: map[string]string{

fi

# Note on gsutil commands:
# "gsutil cp" always "copies into". It cannot act on the contents of a directory
# and it does not seem possible to e.g. copy "gs://foo/bar" as anything other than
# "/path/bar". This script uses "gsutil rsync" instead, which acts on directory
# contents. About arguments to gsutil:
# "gsutil -m rsync" runs in parallel.
# "gsutil rsync -r" is recursive and makes directories work.

warn(String); } org/apache/maven/wrapper/MavenWrapperMain.class package org.apache.maven.wrapper; public synchronized class MavenWrapperMain { public static final String DEFAULT_MAVEN_USER_HOME; public static final String MAVEN_USER_HOME_PROPERTY_KEY = maven.user.home; public static final String MAVEN_USER_HOME_ENV_KEY = MAVEN_USER_HOME; public static final String MVNW_VERBOSE = MVNW_VERBOSE; public static final String MVNW_USERNAME = MVNW_USERNAME; public static final String MVNW_PASSWORD = MVNW_PASSWORD;...

# NOTE: This Dockerfile is no longer in use.
# It is kept just in case, but it's recommended to use the 2022 version,
# and that is what internal CI uses as well.

# This Dockerfile creates an image that has:
# - the correct MTU setting for networking from inside the container to work.
# - Visual Studio 2022 Build Tools
# - MSVC 14.39
# - LLVM/Clang 18.1.4
# - MSYS2 + curl, git, patch, vim, unzip, zip
# - Python 3.12.3
# - Bazelisk 1.19.0

 * It stores URL queues, access results, and URL patterns for inclusion and exclusion.
 * This class is designed to be used in a single-threaded environment or with external synchronization.
 *
 * <p>It uses {@code Map} and {@code Queue} data structures to hold the data. The class provides
 * methods to add, remove, clear, and retrieve data from these structures.
 *

import com.google.common.cache.LoadingCache;

import jakarta.annotation.Resource;

/**
 * <p>
 * XmlTransformer is a class that extends AbstractTransformer to transform XML documents into a specific format for indexing.
 * It uses XPath expressions to extract data from the XML and stores it in a ResultData object.
 * </p>
 *
 * <p>
 * This class provides several configuration options to customize the XML parsing process, such as:
 * </p>
 * <ul>

            return (T) Long.valueOf(value.longValue());
        }
        return (T) field;
    }

    /**
     * Iterates through all access results for a session, calling the callback for each result.
     * Uses OpenSearch scroll API for efficient iteration over large result sets.
     *
     * @param sessionId The session ID.
     * @param callback The callback to execute for each access result.
     */
    @Override