Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 12 for addExtractor (0.1 sec)

  1. 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");
    
        }
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  2. 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");
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.7K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/TextTransformerTest.java

            ExtractorFactory extractorFactory = container.getComponent("extractorFactory");
            TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
            extractorFactory.addExtractor("text/plain", tikaExtractor);
            extractorFactory.addExtractor("text/html", tikaExtractor);
        }
    
        public void test_name() {
            assertEquals("textTransformer", textTransformer.getName());
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
  4. 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");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 7.6K bytes
    - Viewed (0)
  5. 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);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.9K bytes
    - Viewed (0)
  6. 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.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 7.3K bytes
    - Viewed (0)
  7. 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");
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 3.7K bytes
    - Viewed (0)
  8. 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");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Aug 31 05:32:52 UTC 2025
    - 15.3K bytes
    - Viewed (0)
  9. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        factory.addExtractor("text/plain", tikaExtractor);
                        factory.addExtractor("text/html", tikaExtractor);
                    })//
                    .singleton("httpClient", HcHttpClient.class)//
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 19.1K bytes
    - Viewed (0)
  10. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java

                    .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                        factory.addExtractor("application/pdf", tikaExtractor);
                    });
            emlExtractor = container.getComponent("emlExtractor");
        }
    
        public void test_getText() throws IOException {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (0)
Back to top