chrismattmann closed pull request #151: Fix for commandline drat URL: https://github.com/apache/drat/pull/151
This is a PR merged from a forked repository. As GitHub hides the original diff on merge, it is displayed below for the sake of provenance: As this is a foreign pull request (from a fork), the diff is supplied below (as it won't show otherwise due to GitHub magic): diff --git a/crawler/src/main/resources/bin/dump_repo_details.py b/crawler/src/main/resources/bin/dump_repo_details.py new file mode 100644 index 00000000..efaf64e3 --- /dev/null +++ b/crawler/src/main/resources/bin/dump_repo_details.py @@ -0,0 +1,33 @@ +import sys +import os +import json + +def main(argv=None): + if len(argv) == 0: + print "No Repo details to dump" + sys.exit() + + if os.getenv("DRAT_HOME")==None: + print "Please add DRAT_HOME environment variable and try again"; + sys.exit() + + default_repo_file_url = os.getenv("DRAT_HOME") + "/conf/repo.default.txt" + with open(default_repo_file_url,'rb')as repoFile: + data = '' + for line in repoFile: + data+=line + rep = eval(data) + + reponame = os.path.basename(os.path.normpath(argv[0])) + rep["repo"] = os.path.normpath(argv[0]) + rep["name"] = reponame + + outputfile = os.getenv("DRAT_HOME") + "/data/repo" + file = open(outputfile,"w") + file.write(json.dumps(rep)) + file.close() + + print rep + +if __name__ == "__main__": + main(sys.argv[1:]) diff --git a/distribution/src/main/resources/bin/drat b/distribution/src/main/resources/bin/drat index 00e79548..b3fe9d4a 100755 --- a/distribution/src/main/resources/bin/drat +++ b/distribution/src/main/resources/bin/drat @@ -59,7 +59,10 @@ function crawl { PRODUCT_PATH=$1 fi pushd $DRAT_HOME/crawler/bin >> $DRAT_HOME/logs/drat.log 2>&1 - + + python dump_repo_details.py $PRODUCT_PATH + + ./crawler_launcher --operation --metPC --metExtractorConfig \ $DRAT_HOME/extractors/code/default.cpr.conf --metExtractor org.apache.oodt.cas.metadata.extractors.CopyAndRewriteExtractor \ --filemgrUrl $FILEMGR_URL --clientTransferer org.apache.oodt.cas.filemgr.datatransfer.InPlaceDataTransferFactory \ diff --git a/distribution/src/main/resources/conf/repo.default.txt b/distribution/src/main/resources/conf/repo.default.txt new file mode 100644 index 00000000..341d53d1 --- /dev/null +++ b/distribution/src/main/resources/conf/repo.default.txt @@ -0,0 +1 @@ +{"id":"http://drat.apache.org/#","repo":"","name":"","loc_url":"http://drat.apache.org/#","description":"DRAT : Command line","type":"project"} ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services