Skip to content

Improved error reporting #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mafurst wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Improved error reporting #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d755cf8
Parse Error Reporting
mafurst Feb 15, 2018
22e21e7
Error Reporting Update
mafurst Feb 16, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified ._combine_trips_xml_into_scene.py
View file
Open in desktop
Binary file not shown.
Binary file modified ._parse_trips_xml.py
View file
Open in desktop
Binary file not shown.
29 changes: 25 additions & 4 deletions parse_trips_xml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,11 +21,22 @@ def get_clean_parse(fileName):
root_pattern = a.split("<rdf:RDF")[1].split("<rdf:Description")[0]
rdf_pattern = "<rdf:RDF " + root_pattern \
+ new_rdf_pattern + "</rdf:RDF>"
except IndexError:
out = "---------------------------------------"
except IndexError as iError:
out = "---------------------------------------\n"
out +="Affected file:\n"
out += fileName.split("/")[-1] + "\n"
out += "Error Args:\n"
for arg in iError.args:
out+=str(arg)+"\n"
out += "XML error info: \n"
root = ET.parse(fileName).getroot()
out += str(root.get('error'))+'\n'
if args.removeBadFiles != None:
if bool(args.removeBadFiles):
os.remove(fileName)
out += "Removed file because removeBadFiles flag was set to True\n"
error.write(out)
return
return 1

pattern = re.compile(r' input=".+\n')
if pattern.search(a):
Expand Down Expand Up @@ -127,6 +138,7 @@ def get_clean_parse(fileName):

with open(fileName + '.clean', 'w') as new:
new.write(myparse)
return 0


if __name__ == '__main__':
Expand All @@ -137,7 +149,14 @@ def get_clean_parse(fileName):
dest="path",
required=True,
help='path to the input directory containing all TRIPS XML parses')
parser.add_argument(
"--removeBadFiles",
dest="removeBadFiles",
required=False,
help='set to a True or False value to indicate if bad' +
'files should be removed when parsing the input directory')
args = parser.parse_args()
nFilesAffected=0

with open(time.strftime("%Y%m%d-%H%M") + '.err', 'a') as error:
error.write("The following files did not have a parse.\n\n")
Expand All @@ -148,5 +167,7 @@ def get_clean_parse(fileName):
if fileName.endswith(".xml"):
with open(os.path.join(args.path, dirName, fileName), 'r') as f:
a = f.read()
get_clean_parse(os.path.join(dirName, fileName))
nFilesAffected += get_clean_parse(os.path.join(dirName, fileName))
error.write("---------------------------------------\n")
error.write("Number of files affected: "+str(nFilesAffected)+"\n")
print("********************\nCleaned parses are in the same directory as the original parse files.\n\nfileName %s in the current directory contains the list of files that did not have parses to be cleaned.\n********************\n" % str(error).split("'")[1])