On 3/7/2013 5:10 AM, Dave Angel wrote:
> On 03/07/2013 01:33 AM, John Nagle wrote:
>> Here's a traceback that's not helping:
>>
>
> A bit more context would be helpful. Starting with Python version.
Sorry, Python 2.7.
>
> If that isn't enough, then please give the whole context, such as where
> zipelt and filename came from. And don't forget to specify Python
> version. Version 3.x treats nonbinary files very differently than 2.x
Here it is, with some email wrap problems.
John Nagle
def dofilecsv(self, infilename, infdraw) :
"""
Loader for Companies House company data, with files already open.
"""
self.logger.info('Converting "%s"' % (infilename, )) # log
(pathpart, filepart) = os.path.split(infilename) #
split off file part to construct outputfile)
(outfile, ext) = os.path.splitext(filepart) #
remove extension
outfile += ".sql" #
add SQL suffix
outfilename = os.path.abspath(os.path.join(self.options.destdir,
outfile))
# ***NEED TO INSURE UNIQUE OUTFILENAME EVEN IF DUPLICATED IN
ZIP FILES***
decoder = codecs.getreader('utf-8') #
UTF-8 reader
with decoder(infdraw,errors="replace") as infd :
with codecs.open(outfilename, encoding='utf-8', mode='w') as
outfd :
headerline = infd.readline() #
read header line
self.doheaderline(headerline) #
process header line
reader = csv.reader(infd, delimiter=',', quotechar='"')
# CSV file
for fields in reader : #
read entire CSV file
self.doline(outfd, fields) #
copy fields
self.logstats(infilename) #
log statistics of this file
def dofilezip(self, infilename) :
"""
Do a ZIP file containing CSV files.
"""
try :
inzip = zipfile.ZipFile(infilename, "r", allowZip64=True)
# try to open
zipdir = inzip.infolist() # get
objects in file
for zipelt in zipdir : # for all
objects in file
self.logger.debug('ZIP file "%s" contains "%s".' %
(infilename, zipelt.filename))
(infile, ext) = os.path.splitext(zipelt.filename) #
remove extension
if ext.lower() == ".csv" : # if a CSV file
with inzip.open(zipelt.filename,"r") as infd :
# do this file
self.dofilecsv(infile, infd) # as a CSV file
else :
self.logger.error('Non-CSV file in ZIP file: "%s"' %
(zipelt.filename,))
self.errorcount += 1 # tally
except zipfile.BadZipfile as message : # if trouble
self.logger.error('Bad ZIP file: "%s"' % (infilename,)) #
note trouble
self.errorcount += 1 # tally
def dofile(self, infilename) :
"""
Loader for Companies House company data
"""
(sink, ext) = os.path.splitext(infilename) # get extension
if ext == ".zip" : # if .ZIP file
self.dofilezip(infilename) # do ZIP file
elif ext == ".csv" :
self.logger.info('Converting "%s"' % (infilename,))# log
with open(infilename, "rb") as infd :
self.dofilecsv(infilename, infd) # do
self.logstats(infilename) # log statistics
of this file
else :
self.logger.error('File of unexpected type (not .csv or
.zip): %s ' % (infilename,))
self.errorcount += 1
--
http://mail.python.org/mailman/listinfo/python-list
