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));

     */
    @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)

            doColumn("createdBy");
        }

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

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

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

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

    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:

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.

            doColumn("createdBy");
        }

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

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

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

        public void columnExcludedDocUrls() {
            doColumn("excludedDocUrls");
        }

```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

				// that the MkdirAll is retried once for the parent
				// of dirPath.
				// Because it is worth a retry to skip a different
				// baseDir which is slightly higher up the depth.
				nbaseDir := path.Dir(baseDir)
				if baseDir != "" && nbaseDir != "" && nbaseDir != SlashSeparator {
					baseDir = nbaseDir
				}
				continue
			}
		}
		break
	}
	return err
}

            }

            @Override
            public Integer getDepth() {
                return null;
            }

            @Override
            public void setDepth(Integer depth) {
            }

            @Override
            public Long getLastModified() {
                return null;
            }

            @Override

| Collection | WebConfig or FileConfig |
| Start URLs | URLs field in crawl config |
| Good URL Pattern | Included URLs (regex) |
| Bad URL Pattern | Excluded URLs (regex) |
| Follow/Index Pattern | Config Depth and Filter settings |

**Implementation Details**

See the GSA parser implementation: [GsaConfigParser.java](/src/main/java/org/codelibs/fess/util/GsaConfigParser.java)

#### API Compatibility Mode