</mime-type>

  <mime-type type="text/csv">
    <glob pattern="*.csv"/>
    <sub-class-of type="text/plain"/>
  </mime-type>

  <mime-type type="text/directory"/>
  <mime-type type="text/dns"/>
  <mime-type type="text/ecmascript"/>
  <mime-type type="text/enriched"/>
  <mime-type type="text/example"/>

  <mime-type type="text/html">

     *
     * @param outputFile the converted output file
     * @param outExt the output file extension
     * @return the extracted text content
     * @throws ExtractException if an error occurs while reading the file
     */
    protected String getOutputContent(final File outputFile, final String outExt) {
        final Extractor extractor = getExtractor(outExt);
        if (extractor != null) {

        if (text == null) {
            return null;
        }
        if (suffix == null) {
            return text;
        }
        if (text.endsWith(suffix)) {
            return text.substring(0, text.length() - suffix.length());
        }
        return text;
    }

    /**
     * Removes the prefix from the string if it is present.
     *
     * @param text

        final FessConfig fessConfig = createFessConfigWithResponseHeaders("*=X-Def:def\ntext/html=X-Html:htmlval");
        FessActionAdjustmentProvider provider = new FessActionAdjustmentProvider(fessConfig);
        final Map<String, String> headerMap = new HashMap<>();
        provider.adjustActionResponseHeaders("text/html", (k, v) -> headerMap.put(k, v));
        assertEquals(2, headerMap.size());

image/x-xwindowdump            xwd              #
text/css                       css              # Cascading Style Sheet
text/html                      html htm         # HTML Document
text/plain                     txt ini log in cfg m4 sh     # Plain Text File
text/richtext                  rtx              # Rich Text File
text/tab-separated-values      tsv              #
text/x-setext                  etx              #

- **Type Safe** - Comprehensive use of generics and modern Java type system features

### Additional Components
- **Text Processing** (`org.codelibs.core.text`) - JSON utilities, tokenization, decimal formatting, and text manipulation
- **Logging Abstraction** (`org.codelibs.core.log`) - Flexible logging system supporting JCL (Jakarta Commons Logging) and JUL (Java Util Logging)

- **Smart Query Suggestions**: Real-time auto-completion and search suggestions
- **Multi-language Support**: Built-in support for Japanese text processing with Kuromoji analyzer
- **Popular Words Analytics**: Track and analyze frequently searched terms
- **Flexible Text Processing**: Configurable converters and normalizers for text transformation
- **OpenSearch Integration**: Seamless integration with OpenSearch/Elasticsearch clusters

        .addEqualityGroup(
            MediaType.create("text", "plain"),
            MediaType.create("TEXT", "PLAIN"),
            MediaType.parse("text/plain"),
            MediaType.parse("TEXT/PLAIN"),
            MediaType.parse("text /plain"),
            MediaType.parse("TEXT/ plain"),
            MediaType.parse("text / plain"),
            MediaType.create("text", "plain").withParameter("a", "1").withoutParameters())

		delete(hexByLine, p.Line())
		if text == nil {
			t.Errorf("%s: instruction outside TEXT", p)
		}
		size := int64(len(text.P)) - p.Pc
		if p.Link != nil {
			size = p.Link.Pc - p.Pc
		} else if p.Isize != 0 {
			size = int64(p.Isize)
		}
		var code []byte
		if p.Pc < int64(len(text.P)) {
			code = text.P[p.Pc:]
			if size < int64(len(code)) {
				code = code[:size]
			}
		}

# Run static analysis
mvn spotbugs:check
```

### Running Tests

```bash
# Run all tests
mvn test

# Run specific test class
mvn test -Dtest=CrawlerTest

# Run specific test method
mvn test -Dtest=CrawlerTest#test_execute_web

# Run tests for specific module
mvn test -pl fess-crawler
```

## Examples

### Web Crawling with Custom Rules

```java