</exclusion>
				<exclusion>
					<groupId>org.slf4j</groupId>
					<artifactId>jcl-over-slf4j</artifactId>
				</exclusion>
				<exclusion>
					<groupId>javax.activation</groupId>
					<artifactId>activation</artifactId>
				</exclusion>
				<exclusion>
					<groupId>javax.activation</groupId>
					<artifactId>javax.activation-api</artifactId>
				</exclusion>
				<exclusion>

			<artifactId>poi-ooxml</artifactId>
			<version>${poi.version}</version>
			<exclusions>
				<exclusion>
					<groupId>stax</groupId>
					<artifactId>stax-api</artifactId>
				</exclusion>
				<exclusion>
					<groupId>xml-apis</groupId>
					<artifactId>xml-apis</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>

     * @param includes the patterns of files to include, or null/empty for including all files
     * @param excludes the patterns of files to exclude, or null/empty for no exclusion
     * @param useDefaultExcludes whether to augment excludes with default SCM exclusion patterns
     * @return a PathMatcher that can be used to test if paths should be included
     * @throws NullPointerException if baseDirectory is null
     */
    @Nonnull

      <version>${truth.version}</version>
      <classifier>gwt</classifier>
      <scope>test</scope>
      <exclusions>
        <exclusion>
          <!-- use the guava we're building. -->
          <groupId>com.google.guava</groupId>
          <artifactId>guava</artifactId>
        </exclusion>
      </exclusions>
    </dependency>
    <dependency>
      <groupId>com.google.truth.extensions</groupId>

    // ----------------------------------------------------------------------

    /**
     * How the test project is set up:
     *
     * 1. dependencyManagement lists dependencies on a & b,
     *    with an exclusion on c in b.
     * 2. the child project lists a dependency on project a only
     * 3. a depends on b (which is transitive to the child project),
     *    and b depends on c.
     *

			<groupId>org.junit.platform</groupId>
			<artifactId>junit-platform-runner</artifactId>
			<version>1.10.3</version>
			<scope>test</scope>
			<exclusions>
				<exclusion>
					<groupId>junit</groupId>
					<artifactId>junit</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>org.hamcrest</groupId>
			<artifactId>hamcrest</artifactId>
			<version>2.2</version>

        }
    }

    /**
     * Determines whether the specified URL is crawlable based on the exclusion pattern
     * provided in the {@code paramMap}. If the {@code URL_EXCLUDE_PATTERN} key exists in
     * the parameter map, its value is used as a regular expression pattern to match against
     * the given URL. If the URL matches the exclusion pattern, the method returns {@code false},

 * with {@link PopularWordsResponse}. It allows specifying various criteria for retrieving popular words,
 * such as index, size, tags, roles, fields, languages, and exclusion words.
 *
 * <p>Key functionalities include:</p>
 * <ul>
 *   <li>Setting the target index for the search.</li>
 *   <li>Limiting the number of results (size).</li>

- **Extensible Architecture**: Plugin system for custom extractors, transformers, and clients
- **Rate Limiting**: Politeness policies and interval controllers
- **URL Filtering**: Regex-based inclusion/exclusion patterns
- **Data Persistence**: Multiple backend options including OpenSearch integration

## Technology Stack

- **Java**: 21+ (requires Java 21 or higher)
- **Build System**: Maven 3.x

            </jdkToolchain>
            <includes>
              <include>${test.include}</include>
            </includes>
            <!-- By having our own entries here, we also override the default exclusion filter, which excludes all nested classes. -->
            <excludes>
              <!-- https://github.com/google/guava/issues/2840 -->
              <exclude>%regex[.*PackageSanityTests.*.class]</exclude>