def test_valid_file(self):
output = six.StringIO()
with open('examples/test.xls', 'rb') as f:
convert.convert(f, 'xls', output=output)
with open('examples/testxls_converted.csv', 'r') as f:
self.assertEquals(f.read(), output.getvalue())
def __init__(self, file_path, filename):
now = datetime.now().isoformat()
self.file_path = file_path
self.filename = filename
self.file_type = convert.guess_format(self.filename)
if self.file_type not in ["xls", "csv", "xlsx"]:
if client:
client.captureMessage(" %s Unsupported Format: %s, (%s)" % (now, self.file_type, self.filename))
raise DedupeFileError("%s is not a supported format" % self.file_type)
try:
self.converted = convert.convert(open(self.file_path, "rb"), self.file_type)
except UnicodeDecodeError:
if client:
client.captureException()
raise DedupeFileError(
"We had a problem with the file you uploaded. \
This might be related to encoding or the file name having the wrong file extension."
)
self.line_count = self.converted.count("\n")
if self.line_count > 10000:
if client:
client.captureMessage(" %s File too big: %s, (%s)" % (now, self.line_count, self.filename))
raise DedupeFileError("Your file has %s rows and we can only currently handle 10,000." % self.line_count)
if client:
client.captureMessage(" %s Format: %s, Line Count: %s" % (now, self.file_type, self.line_count))
def process_file(self):
'''
Here we will see if the input file is CSV, or if it is an understood
format that can be converted to CSV. Assuming it's one of those two,
we will pass the resulting CSV file over to the csv processor.
'''
for this_filename in self.filelist:
logger.debug('Filename processing is %s', this_filename)
self.format = convert.guess_format(this_filename)
logger.debug('Guessed format of %s', self.format)
if self.format == 'csv':
self.filename = this_filename
break
elif self.format:
# If it is not a CSV file, but some other
# understood format, we will convert it to a CSV and
# write it out to a temporary file.
fh, self.temp_file = tempfile.mkstemp(suffix='.csv')
os.close(fh)
self.filename = self.temp_file
try:
logger.debug(
'Attempting to convert to format CSV (from %s)',
self.format)
with open(self.temp_file, 'w') as fh:
fh.write(
convert.convert(open(this_filename, 'rb'),
self.format))
break
except Exception, e:
logger.exception('Failed to process %s to CSV: %s',
self.filename, e)
os.unlink(self.filename)
self.filename = None
def upload():
session_id = unicode(uuid4())
f = request.files['input_file']
flask_session['session_name'] = f.filename
file_type = f.filename.rsplit('.')[1]
u = StringIO(f.read())
u.seek(0)
if file_type != 'csv': # pragma: no cover
file_format = convert.guess_format(flask_session['session_name'])
u = StringIO(convert.convert(u, file_format))
fieldnames = [
slugify(unicode(i)) for i in u.next().strip('\r\n').split(',')
]
flask_session['fieldnames'] = fieldnames
user_id = flask_session['user_id']
user = db_session.query(User).get(user_id)
group = user.groups[0]
sess = DedupeSession(id=session_id,
name=request.form.get('name'),
description=request.form.get('description'),
filename=f.filename,
group=group,
status=STATUS_LIST[0]['machine_name'])
db_session.add(sess)
db_session.commit()
u.seek(0)
with open('/tmp/%s_raw.csv' % session_id, 'wb') as s:
s.write(u.getvalue())
del u
initializeSession.delay(session_id)
flask_session['session_id'] = session_id
return jsonify(ready=True, session_id=session_id)
def process_file(self):
'''
Here we will see if the input file is CSV, or if it is an understood
format that can be converted to CSV. Assuming it's one of those two,
we will pass the resulting CSV file over to the csv processor.
'''
for this_filename in self.filelist:
logger.debug('Filename processing is %s', this_filename)
self.format=convert.guess_format(this_filename)
logger.debug('Guessed format of %s', self.format)
if self.format == 'csv':
self.filename=this_filename
break
elif self.format:
# If it is not a CSV file, but some other
# understood format, we will convert it to a CSV and
# write it out to a temporary file.
fh, self.temp_file=tempfile.mkstemp(suffix='.csv')
os.close(fh)
self.filename=self.temp_file
try:
logger.debug('Attempting to convert to format CSV (from %s)',
self.format)
with open(self.temp_file,'w') as fh:
fh.write(convert.convert(open(this_filename,'rb'),
self.format))
break
except Exception, e:
logger.exception('Failed to process %s to CSV: %s',
self.filename, e)
os.unlink(self.filename)
self.filename=None
def upload():
context = {}
if request.method == 'POST':
big_file = False
try:
files = request.files
except RequestEntityTooLarge, e:
files = None
big_file = True
current_app.logger.info(e)
if files:
f = files['input_file']
if allowed_file(f.filename):
inp = StringIO(f.read())
file_format = convert.guess_format(f.filename)
try:
converted = convert.convert(inp, file_format)
except UnicodeDecodeError:
context['errors'] = [
'We had a problem with reading your file. \
This could have to do with the file encoding or format'
]
converted = None
f.seek(0)
if converted:
outp = StringIO(converted)
reader = UnicodeCSVReader(outp)
session['header_row'] = reader.next()
rows = []
columns = [[] for c in session['header_row']]
column_ids = range(len(session['header_row']))
for row in range(100):
try:
rows.append(reader.next())
except StopIteration:
break
for i, row in enumerate(rows):
for j, d in enumerate(row):
columns[j].append(row[column_ids[j]])
sample_data = []
guesses = {}
for index, header_val in enumerate(session['header_row']):
guesses[index] = guess_geotype(header_val,
columns[index])
sample_data.append((index, header_val, columns[index]))
session['sample_data'] = sample_data
session['guesses'] = json.dumps(guesses)
outp.seek(0)
session['file'] = outp.getvalue()
session['filename'] = f.filename
return redirect(url_for('views.select_geo'))
else:
context['errors'] = [
'Only .xls or .xlsx and .csv files are allowed.'
]
else:
context['errors'] = ['You must provide a file to upload.']
if big_file:
context['errors'] = ['Uploaded file must be 10mb or less.']
def main(self):
if self.args.filetype:
filetype = self.args.filetype
if filetype not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' % self.args.filetype)
elif self.args.schema:
filetype = 'fixed'
elif self.args.key:
filetype = 'json'
else:
if not self.args.input_path or self.args.input_path == '-':
self.argparser.error('You must specify a format when providing data via STDIN (pipe).')
filetype = convert.guess_format(self.args.input_path)
if not filetype:
self.argparser.error('Unable to automatically determine the format of the input file. Try specifying a format with --format.')
if filetype in ('xls', 'xlsx'):
self.input_file = open(self.args.input_path, 'rb')
else:
self.input_file = self._open_input_file(self.args.input_path)
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self._open_input_file(self.args.schema)
if self.args.key:
kwargs['key'] = self.args.key
if self.args.sniff_limit:
kwargs['sniff_limit'] = self.args.sniff_limit
if self.args.sheet:
kwargs['sheet'] = self.args.sheet
if self.args.no_inference:
kwargs['column_types'] = agate.TypeTester(limit=0)
if filetype == 'csv' and self.args.no_header_row:
kwargs['header'] = False
convert.convert(self.input_file, filetype, output=self.output_file, **kwargs)
def main(self):
if self.args.format:
format = self.args.format
if format not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' %
self.args.format)
elif self.args.schema:
format = 'fixed'
elif self.args.key:
format = 'json'
else:
if self.args.file == sys.stdin:
self.argparser.error(
'You must specify a format when providing data via STDIN (pipe).'
)
format = convert.guess_format(self.args.file)
if not format:
self.argparser.error(
'Unable to automatically determine the format of the input file. Try specifying a format with --format.'
)
if isinstance(self.args.file, file):
f = self.args.file
elif format in ('xls', 'xlsx'):
f = open(self.args.file, 'rb')
else:
f = open(self.args.file, 'rU')
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self.args.schema
if self.args.key:
kwargs['key'] = self.args.key
if self.args.snifflimit:
kwargs['snifflimit'] = self.args.snifflimit
if self.args.sheet:
kwargs['sheet'] = self.args.sheet
if self.args.no_inference:
kwargs['type_inference'] = False
if format == 'csv' and self.args.no_header_row:
kwargs['no_header_row'] = True
# Fixed width can be processed as a stream
if format == 'fixed':
kwargs['output'] = self.output_file
self.output_file.write(convert.convert(f, format, **kwargs))
def main(self):
if self.args.filetype:
filetype = self.args.filetype
if filetype not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' %
self.args.filetype)
elif self.args.schema:
filetype = 'fixed'
elif self.args.key:
filetype = 'json'
else:
if not self.args.input_path or self.args.input_path == '-':
self.argparser.error(
'You must specify a format when providing data via STDIN (pipe).'
)
filetype = convert.guess_format(self.args.input_path)
if not filetype:
self.argparser.error(
'Unable to automatically determine the format of the input file. Try specifying a format with --format.'
)
if filetype in ('xls', 'xlsx'):
self.input_file = open(self.args.input_path, 'rb')
else:
self.input_file = self._open_input_file(self.args.input_path)
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self._open_input_file(self.args.schema)
if self.args.key:
kwargs['key'] = self.args.key
if self.args.snifflimit:
kwargs['snifflimit'] = self.args.snifflimit
if self.args.sheet:
kwargs['sheet'] = self.args.sheet
if self.args.no_inference:
kwargs['type_inference'] = False
if filetype == 'csv' and self.args.no_header_row:
kwargs['no_header_row'] = True
# Fixed width can be processed as a stream
if filetype == 'fixed':
kwargs['output'] = self.output_file
data = convert.convert(self.input_file, filetype, **kwargs)
self.output_file.write(data)
def main(self):
if self.filetype:
filetype = self.filetype
if filetype not in convert.SUPPORTED_FORMATS:
self.csvResult = (_('"%s" is not a supported format') % self.filetype)
# elif self.args.schema:
# filetype = 'fixed'
# elif self.args.key:
# filetype = 'json'
else:
if not self.file_name or self.file_name == '-':
self.csvResult = _('You must specify a format.')
filetype = convert.guess_format(self.file_name)
if not filetype:
self.csvResult = _('Unable to automatically determine the format of the input file. Try specifying a format with --format.')
if filetype in ('xls', 'xlsx'):
self.input_file = open(self.file_name, 'rb')
else:
self.input_file = self._open_input_file(self.args.input_path)
kwargs = self.reader_kwargs
# if self.args.schema:
# kwargs['schema'] = self._open_input_file(self.args.schema)
#
# if self.args.key:
# kwargs['key'] = self.args.key
#
# if self.args.snifflimit:
# kwargs['snifflimit'] = self.args.snifflimit
#
# if self.args.sheet:
# kwargs['sheet'] = self.args.sheet
#
# if self.args.no_inference:
# kwargs['type_inference'] = False
#
# if filetype == 'csv' and self.args.no_header_row:
# kwargs['no_header_row'] = True
#
# # Fixed width can be processed as a stream
# if filetype == 'fixed':
# kwargs['output'] = self.output_file
data = convert.convert(self.input_file, filetype, **kwargs)
print 'out: '
out_file_opened = open(self.output_file,'w')
print out_file_opened
out_file_opened.write(data)
def main(self):
if self.args.filetype:
filetype = self.args.filetype
if filetype not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' % self.args.filetype)
elif self.args.schema:
filetype = 'fixed'
elif self.args.key:
filetype = 'json'
else:
if not self.args.input_path or self.args.input_path == '-':
self.argparser.error('You must specify a format when providing data via STDIN (pipe).')
filetype = convert.guess_format(self.args.input_path)
if not filetype:
self.argparser.error('Unable to automatically determine the format of the input file. Try specifying a format with --format.')
if filetype in ('xls', 'xlsx'):
self.input_file = open(self.args.input_path, 'rb')
else:
self.input_file = self._open_input_file(self.args.input_path)
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self._open_input_file(self.args.schema)
if self.args.key:
kwargs['key'] = self.args.key
if self.args.snifflimit:
kwargs['snifflimit'] = self.args.snifflimit
if self.args.export:
kwargs['export'] = self.args.export
if self.args.sheet:
kwargs['sheet'] = self.args.sheet
if self.args.no_inference:
kwargs['type_inference'] = False
if filetype == 'csv' and self.args.no_header_row:
kwargs['no_header_row'] = True
# Fixed width can be processed as a stream
if filetype == 'fixed':
kwargs['output'] = self.output_file
data = convert.convert(self.input_file, filetype, **kwargs)
self.output_file.write(data)
def upload():
context = {}
if request.method == 'POST':
f = request.files['input_file']
if f:
if allowed_file(f.filename):
inp = StringIO(f.read())
if sys.getsizeof(inp.getvalue()) <= MAX_CONTENT_LENGTH:
inp.seek(0)
file_format = convert.guess_format(f.filename)
try:
converted = convert.convert(inp, file_format)
except UnicodeDecodeError:
context['errors'] = [
'We had a problem with reading your file. \
This could have to do with the file encoding or format'
]
converted = None
f.seek(0)
if converted:
outp = StringIO(converted)
reader = UnicodeCSVReader(outp)
session['header_row'] = reader.next()
rows = []
columns = [[] for c in session['header_row']]
column_ids = range(len(session['header_row']))
for row in range(10):
try:
rows.append(reader.next())
except StopIteration:
break
for i, row in enumerate(rows):
for j, d in enumerate(row):
columns[j].append(row[column_ids[j]])
columns = [', '.join(c) for c in columns]
sample_data = []
for index, _ in enumerate(session['header_row']):
sample_data.append(
(index, session['header_row'][index],
columns[index]))
session['sample_data'] = sample_data
outp.seek(0)
session['file'] = outp.getvalue()
session['filename'] = f.filename
return redirect(url_for('views.select_geo'))
else:
context['errors'] = ['Uploaded file must be 10mb or less.']
else:
context['errors'] = [
'Only .xls or .xlsx and .csv files are allowed.'
]
else:
context['errors'] = ['You must provide a file to upload.']
return render_template('upload.html', **context)
def upload():
context = {}
if request.method == 'POST':
big_file = False
try:
files = request.files
except RequestEntityTooLarge, e:
files = None
big_file = True
current_app.logger.info(e)
if files:
f = files['input_file']
if allowed_file(f.filename):
inp = StringIO(f.read())
file_format = convert.guess_format(f.filename)
try:
converted = convert.convert(inp, file_format)
except UnicodeDecodeError:
context['errors'] = ['We had a problem with reading your file. \
This could have to do with the file encoding or format']
converted = None
f.seek(0)
if converted:
outp = StringIO(converted)
reader = UnicodeCSVReader(outp)
session['header_row'] = reader.next()
rows = []
columns = [[] for c in session['header_row']]
column_ids = range(len(session['header_row']))
for row in range(100):
try:
rows.append(reader.next())
except StopIteration:
break
for i, row in enumerate(rows):
for j,d in enumerate(row):
columns[j].append(row[column_ids[j]])
sample_data = []
guesses = {}
for index, header_val in enumerate(session['header_row']):
guesses[index] = guess_geotype(header_val, columns[index])
sample_data.append((index, header_val, columns[index]))
session['sample_data'] = sample_data
session['guesses'] = json.dumps(guesses)
outp.seek(0)
session['file'] = outp.getvalue()
session['filename'] = f.filename
return redirect(url_for('views.select_geo'))
else:
context['errors'] = ['Only .xls or .xlsx and .csv files are allowed.']
else:
context['errors'] = ['You must provide a file to upload.']
if big_file:
context['errors'] = ['Uploaded file must be 10mb or less.']
def convert_to_csv_reader(filename, sheet=None, infer_types=True):
format = convert.guess_format(filename)
f = open(filename, "rb")
convert_kwargs = {}
if sheet is not None:
# Only pass `sheet` to the `convert` function when its set to
# a non-None value. This is done to satisfy csvkit which checks
# for the presence of `sheet`, not whether it's valid.
convert_kwargs['sheet'] = sheet
converted = StringIO(convert.convert(f, format, infer_types=infer_types, **convert_kwargs))
reader = UnicodeCSVReader(converted)
return reader
def main(self):
if self.args.format:
format = self.args.format
if format not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' % self.args.format)
elif self.args.schema:
format = 'fixed'
elif self.args.key:
format = 'json'
else:
if self.args.file == sys.stdin:
self.argparser.error('You must specify a format when providing data via STDIN (pipe).')
format = convert.guess_format(self.args.file)
if not format:
self.argparser.error('Unable to automatically determine the format of the input file. Try specifying a format with --format.')
if isinstance(self.args.file, file):
f = self.args.file
elif format in ('xls', 'xlsx'):
f = open(self.args.file, 'rb')
else:
f = open(self.args.file, 'rU')
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self.args.schema
if self.args.key:
kwargs['key'] = self.args.key
if self.args.snifflimit:
kwargs['snifflimit'] = self.args.snifflimit
if self.args.sheet:
kwargs['sheet'] = self.args.sheet
if self.args.no_inference:
kwargs['type_inference'] = False
if format == 'csv' and self.args.no_header_row:
kwargs['no_header_row'] = True
# Fixed width can be processed as a stream
if format == 'fixed':
kwargs['output'] = self.output_file
self.output_file.write(convert.convert(f, format, **kwargs))
def __init__(self, file_path, filename):
now = datetime.now().isoformat()
self.file_path = file_path
self.filename = filename
self.file_type = convert.guess_format(self.filename)
if self.file_type not in ['xls', 'csv', 'xlsx']:
logger.warning(' %s Unsupported Format: %s, (%s)' % (now, self.file_type, self.filename))
raise DedupeFileError('%s is not a supported format' % self.file_type)
self.converted = convert.convert(open(self.file_path, 'rb'), self.file_type)
self.line_count = self.converted.count('\n')
if self.line_count > 10000:
logger.warning(' %s File too big: %s, (%s)' % (now, self.line_count, self.filename))
raise DedupeFileError('Your file has %s rows and we can only currently handle 10,000.' % self.line_count)
logger.warning(' %s Format: %s, Line Count: %s' % (now, self.file_type, self.line_count))
def upload():
context = {}
if request.method == 'POST':
f = request.files['input_file']
if f:
if allowed_file(f.filename):
inp = StringIO(f.read())
if sys.getsizeof(inp.getvalue()) <= MAX_CONTENT_LENGTH:
inp.seek(0)
file_format = convert.guess_format(f.filename)
try:
converted = convert.convert(inp, file_format)
except UnicodeDecodeError:
context['errors'] = ['We had a problem with reading your file. \
This could have to do with the file encoding or format']
converted = None
f.seek(0)
if converted:
outp = StringIO(converted)
reader = UnicodeCSVReader(outp)
session['header_row'] = reader.next()
rows = []
columns = [[] for c in session['header_row']]
column_ids = range(len(session['header_row']))
for row in range(10):
try:
rows.append(reader.next())
except StopIteration:
break
for i, row in enumerate(rows):
for j,d in enumerate(row):
columns[j].append(row[column_ids[j]])
columns = [', '.join(c) for c in columns]
sample_data = []
for index,_ in enumerate(session['header_row']):
sample_data.append((index, session['header_row'][index], columns[index]))
session['sample_data'] = sample_data
outp.seek(0)
session['file'] = outp.getvalue()
session['filename'] = f.filename
return redirect(url_for('views.select_geo'))
else:
context['errors'] = ['Uploaded file must be 10mb or less.']
else:
context['errors'] = ['Only .xls or .xlsx and .csv files are allowed.']
else:
context['errors'] = ['You must provide a file to upload.']
return render_template('upload.html', **context)
def hello_world():
url = request.values.get('url', None)
extension = request.values.get('ext', None)
if not url:
return "No file to convert. url="
u = urllib2.urlopen(url)
if not extension:
extension = u.headers.dict['content-disposition'].split('.')[-1][:-1]
#extension = re.search('\.(.*?)\"', u.headers.dict['content-disposition']).group(1)
if not extension:
return "Couldn't figure out extension. specify with ext="
output = convert.convert(u, extension)
return output
def main(self):
if self.args.format:
format = self.args.format
if format not in convert.SUPPORTED_FORMATS:
self.argparser.error('"%s" is not a supported format' % self.args.format)
elif self.args.schema:
format = "fixed"
elif self.args.key:
format = "json"
else:
if self.args.file == sys.stdin:
self.argparser.error("You must specify a format when providing data via STDIN (pipe).")
format = convert.guess_format(self.args.file)
if not format:
self.argparser.error(
"Unable to automatically determine the format of the input file. Try specifying a format with --format."
)
if isinstance(self.args.file, file):
f = self.args.file
elif format == "xls":
f = open(self.args.file, "rb")
else:
f = open(self.args.file, "rU")
kwargs = self.reader_kwargs
if self.args.schema:
kwargs["schema"] = self.args.schema
if self.args.key:
kwargs["key"] = self.args.key
if self.args.snifflimit:
kwargs["snifflimit"] = self.args.snifflimit
# Fixed width can be processed as a stream
if format == "fixed":
kwargs["output"] = self.output_file
self.output_file.write(convert.convert(f, format, **kwargs))
def main(self):
if self.args.format:
format = self.args.format
if format not in convert.SUPPORTED_FORMATS:
sys.exit('"%s" is not a supported format' % self.args.format)
elif self.args.schema:
format = 'fixed'
elif self.args.key:
format = 'json'
else:
if self.args.file == '<stdin>':
sys.exit('You must specify a format when providing data via STDIN (pipe).')
format = convert.guess_format(self.args.file)
if not format:
sys.exit('Unable to automatically determine the format of the input file. Try specifying a format with --format.')
if isinstance(self.args.file, file):
f = self.args.file
elif format == 'xls':
f = open(self.args.file, 'rb')
else:
f = open(self.args.file, 'rU')
kwargs = self.reader_kwargs
if self.args.schema:
kwargs['schema'] = self.args.schema
if self.args.key:
kwargs['key'] = self.args.key
if self.args.snifflimit:
kwargs['snifflimit'] = self.args.snifflimit
# Fixed width can be processed as a stream
if format == 'fixed':
kwargs['output'] = self.output_file
self.output_file.write(convert.convert(f, format, **kwargs))
def __init__(self, file_path, filename):
now = datetime.now().isoformat()
self.file_path = file_path
self.filename = filename
self.file_type = convert.guess_format(self.filename)
if self.file_type not in ['xls', 'csv', 'xlsx']:
client.captureMessage(' %s Unsupported Format: %s, (%s)' % (now, self.file_type, self.filename))
raise DedupeFileError('%s is not a supported format' % self.file_type)
try:
self.converted = convert.convert(open(self.file_path, 'rb'), self.file_type)
except UnicodeDecodeError:
client.captureException()
raise DedupeFileError('We had a problem with the file you uploaded. \
This might be related to encoding or the file name having the wrong file extension.')
self.line_count = self.converted.count('\n')
if self.line_count > 10000:
client.captureMessage(' %s File too big: %s, (%s)' % (now, self.line_count, self.filename))
raise DedupeFileError('Your file has %s rows and we can only currently handle 10,000.' % self.line_count)
client.captureMessage(' %s Format: %s, Line Count: %s' % (now, self.file_type, self.line_count))
def test_valid_file(self):
with open('examples/test.xls', 'r') as f:
output = convert.convert(f, 'xls')
with open('examples/testxls_converted.csv', 'r') as f:
self.assertEquals(f.read(), output)
def scrape(self):
seat_numbers = defaultdict(lambda: defaultdict(int))
extension = os.path.splitext(self.csv_url)[1]
if extension in ('.xls', '.xlsx'):
data = StringIO(
convert.convert(BytesIO(self.get(self.csv_url).content),
extension[1:]))
else:
data = None
reader = self.csv_reader(self.csv_url,
header=True,
encoding=self.encoding,
skip_rows=self.skip_rows,
data=data)
reader.fieldnames = [
self.header_converter(field) for field in reader.fieldnames
]
for row in reader:
if any(row.values()):
if row['last name'] == 'Vacant' or row[
'first name'] == 'Vacant':
continue
for key, corrections in self.corrections.items():
if row.get(key) and row[key] in corrections:
row[key] = corrections[row[key]]
role = row['primary role'].split(';', 1)[0]
name = '{} {}'.format(row['first name'], row['last name'])
province = row.get('province')
if self.district_name:
if row['district id']:
district = self.district_name.format(**row)
else:
district = self.jurisdiction.division_name
else:
district = row.get(
'district name') or self.jurisdiction.division_name
if self.many_posts_per_area and role not in ('Mayor',
'Regional Chair'):
seat_numbers[role][district] += 1
district = '{} (seat {})'.format(
district, seat_numbers[role][district])
lines = []
if row.get('address line 1'):
lines.append(row['address line 1'])
if row.get('address line 2'):
lines.append(row['address line 2'])
if row.get('locality'):
parts = [row['locality']]
if province:
parts.append(province)
if row.get('postal code'):
parts.extend(['', row['postal code']])
lines.append(' '.join(parts))
p = CanadianPerson(primary_org='legislature',
name=name,
district=district,
role=role)
p.add_source(self.csv_url)
if row.get('gender'):
p.gender = row['gender']
if row.get('photo url'):
p.image = row['photo url']
if row.get('source url'):
p.add_source(row['source url'])
if row.get('website'):
p.add_link(row['website'])
p.add_contact('email', row['email'])
if lines:
p.add_contact('address', '\n'.join(lines), 'legislature')
if row.get('phone'):
p.add_contact('voice', row['phone'].split(';', 1)[0],
'legislature')
if row.get('fax'):
p.add_contact('fax', row['fax'], 'legislature')
if row.get('cell'):
p.add_contact('cell', row['cell'], 'legislature')
if row.get('facebook'):
p.add_link(re.sub(r'[#?].+', '', row['facebook']))
if row.get('twitter'):
p.add_link(row['twitter'])
if name in self.other_names:
for other_name in self.other_names[name]:
p.add_name(other_name)
yield p
def test_valid_file(self):
with open('examples/test.xls', 'r') as f:
output = convert.convert(f, 'xls')
with open('examples/testxls_converted.csv', 'r') as f:
self.assertEquals(f.read(), output)
def index():
status_code = 200
error = None
return make_response(render_app_template('back_soon.html', error=error), status_code)
if flask_session.get('ga_cid') is None:
try:
flask_session['ga_cid'] = request.cookies['_ga']
except KeyError:
flask_session['ga_cid'] = str(uuid4())
if request.method == 'POST':
f = request.files['input_file']
if f and allowed_file(f.filename):
fname = secure_filename(str(time.time()) + "_" + f.filename)
file_path = os.path.abspath(os.path.join(UPLOAD_FOLDER, fname))
f.save(file_path)
file_type = convert.guess_format(f.filename)
f.seek(0)
try:
file_contents = convert.convert(f, file_type)
except UnicodeDecodeError:
file_contents = None
if sentry:
sentry.captureException()
status_code = 500
error = '''
We had a problem with the file you uploaded.
This might be related to encoding or the file
name having the wrong file extension.
'''
if file_contents:
with open('{0}-converted.csv'.format(file_path), 'wb') as o:
o.write(file_contents)
# Delete existing session keys
sess_keys = ['training_data', 'counter']
for k in sess_keys:
try:
del flask_session[k]
except KeyError:
pass
flask_session['last_interaction'] = datetime.now()
flask_session['raw_table'], \
flask_session['header'] = makeRawTable(file_contents)
old = datetime.now() - timedelta(seconds=60 * 30)
if flask_session['last_interaction'] < old:
del flask_session['raw_table']
flask_session['filename'] = f.filename
flask_session['file_path'] = file_path
flask_session['file_type'] = file_type
#send_ga_log(
# 'Row Count',
# flask_session['ga_cid'],
# value=inp_file.line_count
#)
#send_ga_log(
# 'File Type',
# flask_session['ga_cid'],
# label=inp_file.file_type,
#)
return redirect(url_for('select_fields'))
#except DedupeFileError as e:
# send_ga_log('Upload Error', flask_session['ga_cid'], label=e.message)
# error = e.message
# status_code = 500
else:
error = 'Error uploading file. Did you forget to select one?'
send_ga_log('Upload Error', flask_session['ga_cid'], label=error)
status_code = 500
return make_response(render_app_template('index.html', error=error), status_code)
def scrape(self):
seat_numbers = defaultdict(lambda: defaultdict(int))
extension = os.path.splitext(self.csv_url)[1]
if extension in ('.xls', '.xlsx'):
data = StringIO(convert.convert(BytesIO(self.get(self.csv_url).content), extension[1:]))
elif extension == '.zip':
basename = os.path.basename(self.csv_url)
if not self.encoding:
self.encoding = 'utf-8'
try:
response = requests.get(self.csv_url, stream=True)
with open(basename, 'wb') as f:
for chunk in response.iter_content():
f.write(chunk)
with ZipFile(basename).open(self.filename, 'r') as fp:
data = StringIO(fp.read().decode(self.encoding))
finally:
os.unlink(basename)
else:
data = None
reader = self.csv_reader(self.csv_url, header=True, encoding=self.encoding, skip_rows=self.skip_rows, data=data)
reader.fieldnames = [self.header_converter(field) for field in reader.fieldnames]
for row in reader:
if any(row.values()):
if row['last name'] == 'Vacant' or row['first name'] == 'Vacant':
continue
for key, corrections in self.corrections.items():
if row.get(key) and row[key] in corrections:
row[key] = corrections[row[key]]
role = re.split(r'(?: (?:and|et)\b|;)', row['primary role'], 1)[0].strip() # ca_on_newmarket, ca_qc_laval, ca_qc_montreal
name = '{} {}'.format(row['first name'], row['last name'])
province = row.get('province')
if not re.search(r'[A-Z]', role): # ca_qc_laval
role = role.capitalize()
if self.district_name_format_string:
if row['district id']:
district = self.district_name_format_string.format(**row)
else:
district = self.jurisdiction.division_name
else:
district = row.get('district name') or self.jurisdiction.division_name
if self.many_posts_per_area and role not in ('Mayor', 'Regional Chair'):
seat_numbers[role][district] += 1
district = '{} (seat {})'.format(district, seat_numbers[role][district])
lines = []
if row.get('address line 1'):
lines.append(row['address line 1'])
if row.get('address line 2'):
lines.append(row['address line 2'])
if row.get('locality'):
parts = [row['locality']]
if province:
parts.append(province)
if row.get('postal code'):
parts.extend(['', row['postal code']])
lines.append(' '.join(parts))
p = CanadianPerson(primary_org='legislature', name=name, district=district, role=role)
p.add_source(self.csv_url)
if row.get('gender'):
p.gender = row['gender']
if row.get('photo url'):
p.image = row['photo url']
if row.get('source url'):
p.add_source(row['source url'])
if row.get('website'):
p.add_link(row['website'], note='web site')
p.add_contact('email', row['email'])
if lines:
p.add_contact('address', '\n'.join(lines), 'legislature')
if row.get('phone'):
p.add_contact('voice', row['phone'].split(';', 1)[0], 'legislature') # ca_qc_montreal
if row.get('fax'):
p.add_contact('fax', row['fax'], 'legislature')
if row.get('cell'):
p.add_contact('cell', row['cell'], 'legislature')
if row.get('facebook'):
p.add_link(re.sub(r'[#?].+', '', row['facebook']))
if row.get('twitter'):
p.add_link(row['twitter'])
if name in self.other_names:
for other_name in self.other_names[name]:
p.add_name(other_name)
yield p
def scrape(self):
seat_numbers = defaultdict(lambda: defaultdict(int))
extension = os.path.splitext(self.csv_url)[1]
if extension in ('.xls', '.xlsx'):
data = StringIO(convert.convert(BytesIO(self.get(self.csv_url).content), extension[1:]))
else:
data = None
reader = self.csv_reader(self.csv_url, header=True, encoding=self.encoding, skip_rows=self.skip_rows, data=data)
reader.fieldnames = [self.header_converter(field) for field in reader.fieldnames]
for row in reader:
if any(row.values()):
if row['last name'] == 'Vacant' or row['first name'] == 'Vacant':
continue
for key, corrections in self.corrections.items():
if row.get(key) and row[key] in corrections:
row[key] = corrections[row[key]]
role = row['primary role'].split(';', 1)[0]
name = '{} {}'.format(row['first name'], row['last name'])
province = row.get('province')
if self.district_name:
if row['district id']:
district = self.district_name.format(**row)
else:
district = self.jurisdiction.division_name
else:
district = row.get('district name') or self.jurisdiction.division_name
if self.many_posts_per_area and role not in ('Mayor', 'Regional Chair'):
seat_numbers[role][district] += 1
district = '{} (seat {})'.format(district, seat_numbers[role][district])
lines = []
if row.get('address line 1'):
lines.append(row['address line 1'])
if row.get('address line 2'):
lines.append(row['address line 2'])
if row.get('locality'):
parts = [row['locality']]
if province:
parts.append(province)
if row.get('postal code'):
parts.extend(['', row['postal code']])
lines.append(' '.join(parts))
p = CanadianPerson(primary_org='legislature', name=name, district=district, role=role)
p.add_source(self.csv_url)
if row.get('gender'):
p.gender = row['gender']
if row.get('photo url'):
p.image = row['photo url']
if row.get('source url'):
p.add_source(row['source url'])
if row.get('website'):
p.add_link(row['website'], note='web site')
p.add_contact('email', row['email'])
if lines:
p.add_contact('address', '\n'.join(lines), 'legislature')
if row.get('phone'):
p.add_contact('voice', row['phone'].split(';', 1)[0], 'legislature')
if row.get('fax'):
p.add_contact('fax', row['fax'], 'legislature')
if row.get('cell'):
p.add_contact('cell', row['cell'], 'legislature')
if row.get('facebook'):
p.add_link(re.sub(r'[#?].+', '', row['facebook']))
if row.get('twitter'):
p.add_link(row['twitter'])
if name in self.other_names:
for other_name in self.other_names[name]:
p.add_name(other_name)
yield p