nutch-1.4-tests.jar - Jar包及相关资源下载

>> Package Explorer

>>> Java Explorer <2.6.8>

Repositories

automaton-urlfilter.txt.template
configuration.xsl
domain-suffixes.xml
domain-suffixes.xsd
domain-urlfilter.txt
fetch-test-site
- dup_of_pagea.html
- exception.html
- index.html
- nested_spider_trap.html
- pagea.html
- pageb.html
- robots.txt
httpclient-auth.xml.template
log4j.properties
META-INF
- DEPENDENCIES
- LICENSE
- MANIFEST.MF
- maven
  - org.apache.nutch
    - nutch
      - pom.properties
      - pom.xml
- NOTICE
nutch-conf.xsl
nutch-default.xml
nutch-site.xml.template
org
- apache
  - nutch
    - crawl
      - CrawlDBTestUtil.java
      - DummyWritable.java
      - TestCrawlDbMerger.java
      - TestGenerator.java
      - TestInjector.java
      - TestLinkDbMerger.java
      - TestSignatureFactory.java
    - fetcher
      - TestFetcher.java
    - indexer
      - TestIndexingFilters.java
    - metadata
      - TestMetadata.java
      - TestSpellCheckedMetadata.java
    - net
      - TestURLFilters.java
      - TestURLNormalizers.java
    - parse
      - TestOutlinkExtractor.java
      - TestParseData.java
      - TestParserFactory.java
      - TestParseText.java
    - plugin
      - HelloWorldExtension.java
      - ITestExtension.java
      - SimpleTestPlugin.java
      - TestPluginSystem.java
    - protocol
      - TestContent.java
      - TestProtocolFactory.java
    - segment
      - TestSegmentMerger.java
    - util
      - TestEncodingDetector.java
      - TestGZIPUtils.java
      - TestNodeWalker.java
      - TestPrefixStringMatcher.java
      - TestStringUtil.java
      - TestSuffixStringMatcher.java
      - TestURLUtil.java
      - WritableTestUtils.java
parse-plugins.dtd
parse-plugins.xml
prefix-urlfilter.txt.template
regex-normalize.xml.template
regex-urlfilter.txt.template
schema-solr4.xml
schema.xml
solrindex-mapping.xml
subcollections.xml.template
suffix-urlfilter.txt.template
testcrawl
- crawldb
  - current
    - part-00000
      - .data.crc
      - .index.crc
      - data
      - index
- index
  - deletable
  - segments
  - _0.f0
  - _0.f1
  - _0.f2
  - _0.f3
  - _0.f4
  - _0.f5
  - _0.fdt
  - _0.fdx
  - _0.fnm
  - _0.frq
  - _0.prx
  - _0.tii
  - _0.tis
- indexes
  - part-00000
    - .index.done.crc
    - .segments.crc
    - commit.lock
    - deletable
    - index.done
    - segments
    - write.lock
    - _j.f0
    - _j.f1
    - _j.f2
    - _j.f3
    - _j.f4
    - _j.f5
    - _j.fdt
    - _j.fdx
    - _j.fnm
    - _j.frq
    - _j.prx
    - _j.tii
    - _j.tis
- linkdb
  - current
    - part-00000
      - .data.crc
      - .index.crc
      - data
      - index
- segments
  - 20060919213635
    - content
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - crawl_fetch
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - crawl_generate
      - .part-00000.crc
      - part-00000
    - crawl_parse
      - .part-00000.crc
      - part-00000
    - parse_data
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - parse_text
      - part-00000
        .data.crc
        .index.crc
        data
        index
  - 20060919213643
    - content
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - crawl_fetch
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - crawl_generate
      - .part-00000.crc
      - part-00000
    - crawl_parse
      - .part-00000.crc
      - part-00000
    - parse_data
      - part-00000
        .data.crc
        .index.crc
        data
        index
    - parse_text
      - part-00000
        .data.crc
        .index.crc
        data
        index