volatile CrawlerStatus status   // DONE, RUNNING
AtomicLong accessCount          // Thread-safe counter
int numOfThread = 10            // Crawler threads
int maxDepth = -1               // Max depth (-1 = unlimited)
long maxAccessCount = 0         // Max URLs (0 = unlimited)
```

### CrawlerThread (`CrawlerThread.java`)

Worker thread for crawling.

                wConfig.setBoost(1.0f);
                wConfig.setCreatedBy(username);
                wConfig.setCreatedTime(now);
                if (form.depth != null) {
                    wConfig.setDepth(form.depth);
                }
                wConfig.setExcludedDocUrls(getDefaultString("default.config.web.excludedDocUrls", StringUtil.EMPTY));

      },
      "includedDocPaths": {
        "type": "keyword"
      },
      "excludedDocPaths": {
        "type": "keyword"
      },
      "configParameter": {
        "type": "keyword"
      },
      "depth": {
        "type": "integer"
      },
      "maxAccessCount": {
        "type": "long"
      },
      "numOfThread": {
        "type": "integer"
      },
      "intervalTime": {
        "type": "integer"

      },
      "includedDocUrls": {
        "type": "keyword"
      },
      "excludedDocUrls": {
        "type": "keyword"
      },
      "configParameter": {
        "type": "keyword"
      },
      "depth": {
        "type": "integer"
      },
      "maxAccessCount": {
        "type": "long"
      },
      "userAgent": {
        "type": "keyword"
      },
      "numOfThread": {
        "type": "integer"

        document.traverse(new NodeVisitor() {
            @Override
            public void head(Node node, int depth) {
                if (node.nodeName().equals("#comment")) {
                    node.remove();
                }
            }

            @Override
            public void tail(Node node, int depth) {
                // Do nothing
            }
        });
    }

    steps:
      - name: Dump GitHub context
        env:
          GITHUB_CONTEXT: ${{ toJson(github) }}
        run: echo "$GITHUB_CONTEXT"
      - uses: actions/checkout@v6
        with:
          fetch-depth: 0
      - name: Set up Python
        uses: actions/setup-python@v6
        with:
          python-version: "3.11"
      - name: Setup uv
        uses: astral-sh/setup-uv@v7
        with:

     */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String configParameter;

    /**
     * The maximum crawling depth from the starting URLs.
     */
    @Min(value = 0)
    @Max(value = 2147483647)
    @ValidateTypeFailure
    public Integer depth;

    /**
     * The maximum number of URLs to access during crawling.
     */
    @Min(value = 0)
    @Max(value = 9223372036854775807L)

    steps:
      - name: Checkout repository
        uses: actions/checkout@v6
        with:
          ref: devprod/upgrade-to-latest-wrapper
          token: ${{ secrets.GITHUB_TOKEN }}
          fetch-depth: 0
      - name: Setup java
        uses: actions/setup-java@v5
        with:
          distribution: temurin
          java-version: 17

            doColumn("createdBy");
        }

        public void columnCreatedTime() {
            doColumn("createdTime");
        }

        public void columnDepth() {
            doColumn("depth");
        }

        public void columnDescription() {
            doColumn("description");
        }

        public void columnExcludedDocPaths() {
            doColumn("excludedDocPaths");

```java
// Set maximum number of URLs to crawl
crawler.crawlerContext.setMaxAccessCount(1000);

// Set number of crawler threads
crawler.crawlerContext.setNumOfThread(10);

// Set maximum crawl depth
crawler.crawlerContext.setMaxDepth(3);

// Set request interval (politeness)
crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

### URL Filtering

```java
// Include patterns