def row_iter(rows, reader):
for row in rows:
yield quoteRow(row, take, map_column2type,
options.missing_values,
null=options.null,
string_value=options.string_value)
for data in reader:
yield quoteRow(CSV.ConvertDictionary(data, map=options.map),
take,
map_column2type,
options.missing_values,
null=options.null,
string_value=options.string_value)
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: csv_intersection.py 2782 2009-09-10 11:40:29Z andreas $"
)
parser.add_option("-u",
"--unique",
dest="unique",
action="store_true",
help="output rows are uniq.")
parser.set_defaults(
remove=False,
unique=False,
)
(options, args) = E.Start(parser, add_csv_options=True)
if len(args) != 2:
raise "please specify two files to join."
options.filename1, options.filename2 = args
table1 = CSV.ReadTable(open(options.filename1, "r"))
table2 = CSV.ReadTable(open(options.filename2, "r"))
if options.unique:
outfile = UniqueBuffer(sys.stdout)
else:
outfile = options.stdout
# build new field list
new_fields = []
for x in options.join_fields1:
new_fields.append(x)
for x in fields1:
if x not in options.join_fields1:
new_fields.append(x)
if x not in options.join_fields2:
new_fields.append(x)
writer = csv.DictWriter(outfile,
fields,
dialect=options.csv_dialect,
lineterminator=options.csv_lineterminator,
extrasaction='ignore')
if len(lines) > 0:
old_fields = lines[0][:-1].split("\t")
if options.remove:
fields = []
for x in old_fields:
if x not in input_fields:
fields.append(x)
else:
fields = input_fields
reader = csv.DictReader(lines, dialect=options.csv_dialect)
print "\t".join(fields)
first_row = True
for row in reader:
row = CSV.ConvertDictionary(row)
writer.writerow(row)
E.Stop()
dialect=options.dialect,
fieldnames=options.header)
if options.replace_header:
reader.next()
E.info("reading %i columns to guess column types" % options.guess_size)
rows = []
for row in reader:
if None in row:
raise ValueError("undefined columns in input file at row: %s" %
row)
try:
rows.append(CSV.ConvertDictionary(row, map=options.map))
except TypeError, msg:
E.warn("incomplete line? Type error in conversion: "
"'%s' with data: %s" % (msg, str(row)))
except ValueError, msg:
E.warn("incomplete line? Type error in conversion: "
"'%s' with data: %s" % (msg, str(row)))
if len(rows) >= options.guess_size:
break
E.info("read %i rows for type guessing" % len(rows))
E.info("creating table")
if len(rows) == 0:
if options.allow_empty:
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id: csv2xls.py 2782 2009-09-10 11:40:29Z andreas $")
parser.add_option("-o", "--outfile=", dest="output_filename", type="string",
help="write to output filename.")
parser.set_defaults(
output_filename=None,
)
(options, args) = E.Start(parser, add_csv_options=True)
if not options.output_filename:
raise ValueError("please specify an output filename.")
w = openpyxl.Workbook(optimized_write=True)
# create styles
header_style = GetHeaderStyle()
data_style = GetDataStyle()
for filename in args:
lines = filter(lambda x: x[0] != "#", open(filename, "r").readlines())
if len(lines) == 0:
continue
if options.loglevel >= 2:
print "# read %i rows" % len(lines)
sys.stdout.flush()
headers = lines[0][:-1].split("\t")
ws = w.add_sheet(os.path.basename(filename))
cur_row = 0
ws.append(headers)
cur_row += 1
reader = csv.DictReader(lines, dialect=options.csv_dialect)
for row in reader:
row = CSV.ConvertDictionary(row)
data = [row.get(headers[x], "") for x in range(len(headers))]
ws.append(data)
cur_row += 1
w.save(options.output_filename)
E.Stop()
