This is an automated email from the ASF dual-hosted git repository.

markus pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/nutch.git

commit 0085ee740e78b58091d1aa39614277f1a612810c
Merge: 3fa2f4a 78af89f
Author: Markus Jelsma <mar...@apache.org>
AuthorDate: Fri Feb 22 16:48:45 2019 +0100

    Merge branch 'master' of https://gitbox.apache.org/repos/asf/nutch

 conf/nutch-default.xml                             | 18 ++++-
 src/java/org/apache/nutch/crawl/CrawlDbReader.java |  2 +-
 .../org/apache/nutch/crawl/CrawlDbReducer.java     |  4 +-
 src/java/org/apache/nutch/crawl/Generator.java     |  8 +-
 src/java/org/apache/nutch/fetcher/QueueFeeder.java | 91 ++++++++++++++++------
 .../apache/nutch/hostdb/UpdateHostDbMapper.java    |  3 -
 .../apache/nutch/hostdb/UpdateHostDbReducer.java   |  2 -
 .../nutch/indexer/IndexingFiltersChecker.java      |  2 +-
 .../org/apache/nutch/net/protocols/Response.java   |  2 +-
 .../org/apache/nutch/parse/OutlinkExtractor.java   |  2 +-
 src/java/org/apache/nutch/parse/ParseData.java     | 18 +----
 .../org/apache/nutch/parse/ParsePluginsReader.java |  2 +-
 .../org/apache/nutch/segment/SegmentMerger.java    |  4 +-
 .../org/apache/nutch/service/impl/LinkReader.java  |  8 +-
 .../org/apache/nutch/service/impl/NodeReader.java  |  8 +-
 .../service/impl/NutchServerPoolExecutor.java      |  2 +-
 .../apache/nutch/service/impl/SequenceReader.java  |  8 +-
 .../org/apache/nutch/tools/arc/ArcInputFormat.java |  4 +-
 .../apache/nutch/tools/arc/ArcRecordReader.java    |  2 +-
 .../apache/nutch/tools/arc/ArcSegmentCreator.java  |  4 +-
 .../org/apache/nutch/util/EncodingDetector.java    |  6 +-
 src/java/org/apache/nutch/util/MimeUtil.java       |  3 +-
 src/plugin/indexer-cloudsearch/README.md           | 54 ++++++-------
 src/plugin/indexer-csv/README.md                   | 42 ++++++++++
 .../nutch/indexwriter/csv/CSVIndexWriter.java      |  4 +-
 src/plugin/indexer-dummy/README.md                 | 34 ++++++++
 src/plugin/indexer-elastic-rest/README.md          | 45 +++++++++++
 src/plugin/indexer-elastic/README.md               | 41 ++++++++++
 src/plugin/indexer-rabbit/README.md                | 44 +++++++++++
 src/plugin/indexer-solr/README.md                  | 40 ++++++++++
 .../apache/nutch/parse/html/HTMLMetaProcessor.java | 45 +++++------
 .../apache/nutch/parse/tika/HTMLMetaProcessor.java | 45 +++++------
 .../apache/nutch/protocol/http/HttpResponse.java   |  4 +-
 .../org/apache/nutch/protocol/okhttp/OkHttp.java   | 22 +++---
 .../nutch/scoring/orphan/OrphanScoringFilter.java  | 12 ++-
 .../scoring/orphan/TestOrphanScoringFilter.java    |  4 +-
 src/test/org/apache/nutch/crawl/TestGenerator.java |  6 +-
 37 files changed, 463 insertions(+), 182 deletions(-)


Reply via email to