nutch-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Apache Wiki <wikidi...@apache.org>
Subject [Nutch Wiki] Trivial Update of "NutchFileFormats" by LewisJohnMcgibbney
Date Sat, 03 Oct 2015 01:09:57 GMT
Dear Wiki user,

You have subscribed to a wiki page or wiki category on "Nutch Wiki" for change notification.

The "NutchFileFormats" page has been changed by LewisJohnMcgibbney:
https://wiki.apache.org/nutch/NutchFileFormats?action=diff&rev1=12&rev2=13

  
  ||file||key datatype||value datatype||codec||
  ||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[https://builds.apache.org/job/nutch-trunk/javadoc/index.html?org/apache/nutch/crawl/CrawlDatum.html|org.apache.nutch.crawl.CrawlDatum]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  
  
  = LinkDB =
@@ -112, +112 @@

  
  ||file||key datatype||value datatype||codec||
  ||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.nutch.crawl.Inlinks||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  
  = Segments =
  
@@ -154, +154 @@

  == Description ==
  
  ||content||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.nutch.protocol.Content||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||content||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||content||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  ||crawl_fetch||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[https://builds.apache.org/job/nutch-trunk/javadoc/index.html?org/apache/nutch/crawl/CrawlDatum.html|org.apache.nutch.crawl.CrawlDatum]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||crawl_fetch||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||crawl_fetch||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  ||crawl_generate||part-0000||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[https://builds.apache.org/job/nutch-trunk/javadoc/index.html?org/apache/nutch/crawl/CrawlDatum.html|org.apache.nutch.crawl.CrawlDatum]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  ||crawl_parse||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[https://builds.apache.org/job/nutch-trunk/javadoc/index.html?org/apache/nutch/crawl/CrawlDatum.html|org.apache.nutch.crawl.CrawlDatum]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||crawl_parse||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||crawl_parse||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  ||parse_data||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.nutch.parse.ParseData||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||parse_data||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||parse_data||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  ||parse_text||data||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.nutch.parse.ParseText||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
- ||parse_text||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||org.apache.hadoop.io.LongWritable||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
+ ||parse_text||index||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/Text.html|org.apache.hadoop.io.Text]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/LongWritable.html|org.apache.hadoop.io.LongWritable]]||[[http://hadoop.apache.org/docs/current/api/index.html?org/apache/hadoop/io/compress/DefaultCodec.html|org.apache.hadoop.io.compress.DefaultCodec]]||
  
  = Old File Format Documentation =
  

Mime
View raw message