Merge branch 'NUTCH-2144' of https://github.com/thammegowda/nutch
Project: http://git-wip-us.apache.org/repos/asf/nutch/repo Commit: http://git-wip-us.apache.org/repos/asf/nutch/commit/906237ab Tree: http://git-wip-us.apache.org/repos/asf/nutch/tree/906237ab Diff: http://git-wip-us.apache.org/repos/asf/nutch/diff/906237ab Branch: refs/heads/master Commit: 906237ab6136a9118278430490a7e6914d69b286 Parents: f5e430e 9a284c0 Author: Chris Mattmann <[email protected]> Authored: Sun Feb 28 23:03:30 2016 -0800 Committer: Chris Mattmann <[email protected]> Committed: Sun Feb 28 23:03:30 2016 -0800 ---------------------------------------------------------------------- build.xml | 4 + conf/db-ignore-external-exemptions.txt | 33 ++++++ conf/nutch-default.xml | 8 ++ .../org/apache/nutch/fetcher/FetcherThread.java | 6 +- .../apache/nutch/net/URLExemptionFilter.java | 43 ++++++++ .../apache/nutch/net/URLExemptionFilters.java | 64 ++++++++++++ .../apache/nutch/parse/ParseOutputFormat.java | 28 +++-- .../org/apache/nutch/plugin/ExtensionPoint.java | 2 +- src/plugin/build.xml | 3 + src/plugin/nutch-extensionpoints/plugin.xml | 4 + src/plugin/urlfilter-ignoreexempt/README.md | 43 ++++++++ src/plugin/urlfilter-ignoreexempt/build.xml | 55 ++++++++++ .../urlfilter-ignoreexempt/data/.donotdelete | 0 src/plugin/urlfilter-ignoreexempt/ivy.xml | 41 ++++++++ src/plugin/urlfilter-ignoreexempt/plugin.xml | 45 +++++++++ .../ignoreexempt/ExemptionUrlFilter.java | 101 +++++++++++++++++++ .../urlfilter/ignoreexempt/package-info.java | 24 +++++ 17 files changed, 493 insertions(+), 11 deletions(-) ----------------------------------------------------------------------
