Reputation: 375
I'm busy working on a tool for tagging documents. I can't seem to solve an issue im having. See the code below, these are 2 functions that are a small part of my code:
def runSearch():
time.sleep(1)
#checkt of de lengte van de list keywords groter is dan 0, zo niet, moet je eerst keywords opgeven
if len(keywords) > 0:
path_input = raw_input('Give path to check for documents(e.g. /Users/Frank/Desktop): ')
errCounter = 0
#hier word gekeken of de opgegeven directory bestaat
if os.path.isdir(path_input):
for root, dirs, files in os.walk(path_input):
for file in files:
fullFile = os.path.join(root, file)
if os.path.splitext(fullFile)[1].lower() == ('.docx') or \
os.path.splitext(file)[1].lower() == ('.doc') or \
os.path.splitext(file)[1].lower() == ('.pptx') or \
os.path.splitext(file)[1].lower() == ('.txt') or \
os.path.splitext(file)[1].lower() == ('.xlsx') or \
os.path.splitext(file)[1].lower() == ('.xls') or \
os.path.splitext(file)[1].lower() == ('.odt') or \
os.path.splitext(file)[1].lower() == ('.rtf') or \
os.path.splitext(file)[1].lower() == ('.csv') or \
os.path.splitext(file)[1].lower() == ('.html') or \
os.path.splitext(file)[1].lower() == ('.htm') or \
os.path.splitext(file)[1].lower() == ('.pdf'):
tagDocs(fullFile)
print ('\nSearch for keyword(s) completed.')
time.sleep(1)
else:
print("\nPlease enter a valid path, for example: '/Users/Frank/Documents'")
else:
print('\nNo keywords were defined, use menu option 2 first.')
raw_input("\nPress Enter to continue...")
menu()
def tagDocs(fullFile):
try:
content = textract.process(os.path.abspath(fullFile))
# contentList.append(content)
words = content.split()
words = [words.lower() for words in words]
tagCounter = 0
for item in enumerate(words):
for index, value in enumerate(keywords):
if value in item:
tagDocuments.append(fullFile)
tagCounter += 1
if tagCounter != 0:
print ("\nIn the file '" + os.path.abspath(fullFile) + "' the tag(s)" + " was found: " +
str(tagCounter) + " time(s).")
except Exception, e:
errorLog(e)
pass
Every time there's an error passed to errorLog() it print the error 4 times in the error.log. I know what's causing this, it's because it loops 4 times, because there are 4 files, if I add a file into the folder im scanning, it will print the error 5 times. So my question, how can I make it only print the error 1 time? Now it prints the error 1 time for every file it finds.
update #2
def errorLogOnce(err):
if not err in reported_errors:
reported_errors.append(err)
errorLog(err)
def errorLog(e):
errCounter = 0
errCounter += 1
logging.basicConfig(filename='error.log',level=logging.DEBUG)
logging.debug(e)
Upvotes: 1
Views: 332
Reputation: 5243
If you want less lines of code, without classes, you can also do this:
reported_errors = []
def errorLogOnce(err):
if not err in reported_errors:
reported_errors.append(err)
errorLog(err)
And then call errorLogOnce instead of calling errorLog
Upvotes: 1
Reputation: 5243
So you want a logger that never repeats a log of the same error? If so, define a class
class MyLogger(object):
def __init__(self):
self.reported_errors = []
def log(self,err):
if not err in self.reported_errors:
self.repoted_errors.add(err)
errorLog(err)
And call this logger instead of directly calling errorLog(e) directly
def runSearch():
logger = MyLogger()
....
tagDocs(fullFile,logger)
....
def tagDocs(fullFile,logger):
try:
...
except Exception, e:
logger.log(e)
pass
Upvotes: 0