**Fess Crawler** is a Java-based web crawling framework for enterprise content extraction.

### Essential Info

- **Language**: Java 21+
- **Build**: Maven 3.x
- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+ and 5.x (switchable)
- **Extraction**: Apache Tika, POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Mockito, Testcontainers

        }

        return repository;
    }

    private boolean isLocalRepository(ArtifactRepository repository) {
        // unfortunately, the API doesn't allow to tell a remote repo and the local repo apart...
        return "local".equals(repository.getId());
    }

version: 2
updates:
# TODO(b/170636568): Enable Maven updates? Perhaps wait until we can more
# easily import the generated PRs into our internal repo.
#  - package-ecosystem: "maven"
#    directory: "/"
#    schedule:
#      interval: "weekly"
#    groups:
#      dependencies:
#        applies-to: version-updates
#        patterns:
#          - "*"
#  - package-ecosystem: "maven"
#    directory: "/android"
#    schedule:

    licenses {
      license {
        name.set("The Apache Software License, Version 2.0")
        url.set("https://www.apache.org/licenses/LICENSE-2.0.txt")
        distribution.set("repo")
      }
    }
    scm {
      connection.set("scm:git:https://github.com/square/okhttp.git")
      developerConnection.set("scm:git:ssh://******@****.***/square/okhttp.git")

                .artifactId("foo")
                .repositories(Collections.singletonList(org.apache.maven.api.model.Repository.newBuilder()
                        .url("file://localhost/${basedir}/temp-repo")
                        .build()))
                .build());

        ModelInterpolator interpolator = createInterpolator();

        final SimpleProblemCollector collector = new SimpleProblemCollector();

of the website repository and remove the `doc/next` directory in this repository.

To begin the next release development cycle, populate the contents of `next`
with those of `initial`. From the repo root:

    > cd doc
    > cp -R initial/ next

on: [pull_request]

jobs:
  run:
    name: Spell Check with Typos
    runs-on: ubuntu-latest
    steps:
    - name: Checkout Actions Repository
      uses: actions/checkout@v4

    - name: Check spelling of repo

          close-pr-message: "This PR was closed because it has been inactive for 14 days since being marked as stale. Please reopen if you'd like to work on this further."
          repo-token: ${{ secrets.GITHUB_TOKEN }}
      - name: Contribution issues
        uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # v10.1.1
        with:

     * <syntax>project.distributionManagementArtifactRepository</syntax>
     * <origin><![CDATA[
     * <distributionManagement>
     * <repository>
     * <id>some-repo</id>
     * <url>scp://host/path</url>
     * </repository>
     * <snapshotRepository>
     * <id>some-snap-repo</id>
     * <url>scp://host/snapshot-path</url>
     * </snapshotRepository>
     * </distributionManagement>
     * ]]></origin>
     * <usage><![CDATA[

            include("**/build/testclusters/**")
            exclude("**/build/testclusters/**/data/**")
            exclude("**/build/testclusters/**/distro/**")
            exclude("**/build/testclusters/**/repo/**")
            exclude("**/build/testclusters/**/extract/**")
          }
            .files
            .findAll { Files.isRegularFile(it.toPath()) }

          if (fileSet.empty) {