You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@community.apache.org by se...@apache.org on 2016/01/06 13:56:20 UTC
svn commit: r1723308 -
/comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py
Author: sebb
Date: Wed Jan 6 12:56:20 2016
New Revision: 1723308
URL: http://svn.apache.org/viewvc?rev=1723308&view=rev
Log:
Detect syntax error in rdf:about for PMC RDFs
Modified:
comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py
Modified: comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py
URL: http://svn.apache.org/viewvc/comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py?rev=1723308&r1=1723307&r2=1723308&view=diff
==============================================================================
--- comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py (original)
+++ comdev/projects.apache.org/scripts/cronjobs/parsecommitteeinfo.py Wed Jan 6 12:56:20 2016
@@ -84,7 +84,7 @@ pmcs = {}
pmcDataUrls = {} # id -> url
# get PMC Data from /data/committees.xml
-print("reading PMC Data (/data/committees.xml)")
+print("Reading PMC Data (/data/committees.xml)")
with open("../../data/committees.xml", "r") as f:
xmldoc = minidom.parseString(f.read())
f.close()
@@ -101,6 +101,8 @@ for loc in xmldoc.getElementsByTagName('
rdfxml = ET.fromstring(rdf)
rdfdata = rdfxml[0]
committeeId = rdfdata.attrib['{http://www.w3.org/1999/02/22-rdf-syntax-ns#}about']
+ if re.match("https?:", committeeId):
+ print("ERROR: unexpected rdf:about value '%s' in '%s'" % (committeeId, url), file=sys.stderr)
pmcDataUrls[committeeId] = url
# transform PMC data RDF to json