Search Options

Display Count
Sort
Preferred Language
Advanced Search

Results 1 - 10 of 14 for addExtractor (0.49 seconds)

The search processing time has exceeded the limit. The displayed results may be partial.

  2. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/LhaExtractorTest.java 

                        LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/x-lha", lhaExtractor);

                })//
        ;

        lhaExtractor = container.getComponent("lhaExtractor");

    }
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Thu Aug 07 02:55:08 GMT 2025
    - 3.4K bytes
    - Click Count (0)
  3. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ZipExtractorTest.java 

                        ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

                })//
        ;

        zipExtractor = container.getComponent("zipExtractor");
    }
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Thu Aug 07 02:55:08 GMT 2025
    - 3.7K bytes
    - Click Count (0)
  4. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/PdfExtractorTest.java 

                        PdfExtractor pdfExtractor = container.getComponent("pdfExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/pdf", pdfExtractor);
                });
        pdfExtractor = container.getComponent("pdfExtractor");
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Sat Mar 15 06:52:00 GMT 2025
    - 7.6K bytes
    - Click Count (0)
  5. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/ExtractorFactoryTest.java 

            extractorFactory.addExtractor("application/msword", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-excel", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.ms-powerpoint", tikaExtractor);
        extractorFactory.addExtractor("application/vnd.visio", tikaExtractor);
        extractorFactory.addExtractor("application/pdf", pdfExtractor);
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Sat Mar 15 06:52:00 GMT 2025
    - 6.9K bytes
    - Click Count (0)
  6. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/ExtractorFactory.java 

         */
    public void addExtractor(final List<String> keyList, final Extractor extractor) {
        if (keyList == null || keyList.isEmpty()) {
            throw new CrawlerSystemException("The key list is empty.");
        }
        keyList.stream().distinct().forEach(key -> addExtractor(key, extractor));
    }

    /**
     * Retrieves an extractor for the specified key.
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Sun Nov 23 12:19:14 GMT 2025
    - 7.4K bytes
    - Click Count (0)
  7. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/TarExtractorTest.java 

                        TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

        tarExtractor = container.getComponent("tarExtractor");
    }
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Thu Aug 07 02:55:08 GMT 2025
    - 3.7K bytes
    - Click Count (0)
  8. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/ArchiveExtractorErrorHandlingTest.java 

                        final TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", textExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);
                    factory.addExtractor("application/x-tar", tarExtractor);
                });
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Mon Nov 24 03:59:47 GMT 2025
    - 12.6K bytes
    - Click Count (0)
  9. github.com/codelibs/fess-crawler

    CLAUDE.md 

    `TikaExtractor` (1000+ formats), `PdfExtractor`, `MsWordExtractor`, `MsExcelExtractor`, `MsPowerPointExtractor`, `ZipExtractor`, `HtmlExtractor`, etc.

**Registration**:
```java
extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Fri Nov 28 17:31:34 GMT 2025
    - 10.7K bytes
    - Click Count (0)
  10. github.com/codelibs/fess-crawler

    README.md 

    // Configure content extraction
container.singleton("tikaExtractor", TikaExtractor.class);
container.singleton("extractorFactory", ExtractorFactory.class, factory -> {
    factory.addExtractor("text/html", container.getComponent("tikaExtractor"));
    factory.addExtractor("application/pdf", container.getComponent("tikaExtractor"));
});

Crawler crawler = container.getComponent("crawler");
crawler.addUrl("https://example.com");
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Sun Aug 31 05:32:52 GMT 2025
    - 15.3K bytes
    - Click Count (0)
  11. github.com/codelibs/fess-crawler

    fess-crawler-lasta/src/main/resources/crawler/extractor.xml 

    		<postConstruct name="addExtractor">
			<arg>[
				"application/pdf"
				]</arg>
			<arg>pdfExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"application/x-lha",
				"application/x-lharc"
				]</arg>
			<arg>lhaExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"message/rfc822"
				]</arg>
			<arg>emlExtractor</arg>
    Created: Sat Dec 20 11:21:39 GMT 2025
    - Last Modified: Sun Nov 23 03:46:53 GMT 2025
    - 50.1K bytes
    - Click Count (0)
Back to Top