Parsing CSV in Python

Question

I want to analyze a csv file, which is in the following format:

Test Environment INFO for 1 line.
Test,TestName1,
TestAttribute1-1,TestAttribute1-2,TestAttribute1-3
TestAttributeValue1-1,TestAttributeValue1-2,TestAttributeValue1-3

Test,TestName2,
TestAttribute2-1,TestAttribute2-2,TestAttribute2-3
TestAttributeValue2-1,TestAttributeValue2-2,TestAttributeValue2-3

Test,TestName3,
TestAttribute3-1,TestAttribute3-2,TestAttribute3-3
TestAttributeValue3-1,TestAttributeValue3-2,TestAttributeValue3-3

Test,TestName4,
TestAttribute4-1,TestAttribute4-2,TestAttribute4-3
TestAttributeValue4-1-1,TestAttributeValue4-1-2,TestAttributeValue4-1-3
TestAttributeValue4-2-1,TestAttributeValue4-2-2,TestAttributeValue4-2-3
TestAttributeValue4-3-1,TestAttributeValue4-3-2,TestAttributeValue4-3-3

and would like to turn this into a tab-split format, as shown below:

TestName1
TestAttribute1-1 TestAttributeValue1-1
TestAttribute1-2 TestAttributeValue1-2
TestAttribute1-3 TestAttributeValue1-3

TestName2
TestAttribute2-1 TestAttributeValue2-1
TestAttribute2-2 TestAttributeValue2-2
TestAttribute2-3 TestAttributeValue2-3


TestName3
TestAttribute3-1 TestAttributeValue3-1
TestAttribute3-2 TestAttributeValue3-2
TestAttribute3-3 TestAttributeValue3-3

TestName4
TestAttribute4-1 TestAttributeValue4-1-1 TestAttributeValue4-2-1 TestAttributeValue4-3-1
TestAttribute4-2 TestAttributeValue4-1-2 TestAttributeValue4-2-2 TestAttributeValue4-3-2
TestAttribute4-3 TestAttributeValue4-1-3 TestAttributeValue4-2-3 TestAttributeValue4-3-3

The number of test attributes varies from test to test. For some tests, there are only 3 values, for some others 7, etc. Also, as in the TestName4 example, some tests are executed more than once, and therefore, each execution has its own TestAttributeValue line. (in the example testname4 is executed 3 times, therefore, we have 3 lines of values)

python , csv python. csv python , , ? ?

Answer 1

, itertools.groupby csv. , itertools - , !

, , :

import csv
from itertools import groupby

with open('my_data.csv') as ifile, open('my_out_data.csv', 'wb') as ofile:
    # Use the csv module to handle reading and writing of delimited files.
    reader = csv.reader(ifile)
    writer = csv.writer(ofile, delimiter='\t')
    # Skip info line
    next(reader)
    # Group datasets by the condition if len(row) > 0 or not, then filter
    # out all empty lines
    for group in (v for k, v in groupby(reader, lambda x: bool(len(x))) if k):
        test_data = list(group)
        # Write header
        writer.writerow([test_data[0][1]])
        # Write transposed data
        writer.writerows(zip(*test_data[1:]))
        # Write blank line
        writer.writerow([])

, my_data.csv:

TestName1
TestAttribute1-1    TestAttributeValue1-1
TestAttribute1-2    TestAttributeValue1-2
TestAttribute1-3    TestAttributeValue1-3

TestName2
TestAttribute2-1    TestAttributeValue2-1
TestAttribute2-2    TestAttributeValue2-2
TestAttribute2-3    TestAttributeValue2-3

TestName3
TestAttribute3-1    TestAttributeValue3-1
TestAttribute3-2    TestAttributeValue3-2
TestAttribute3-3    TestAttributeValue3-3

TestName4
TestAttribute4-1    TestAttributeValue4-1-1 TestAttributeValue4-2-1 TestAttributeValue4-3-1
TestAttribute4-2    TestAttributeValue4-1-2 TestAttributeValue4-2-2 TestAttributeValue4-3-2
TestAttribute4-3    TestAttributeValue4-1-3 TestAttributeValue4-2-3 TestAttributeValue4-3-3

Answer 2

, , ( ). in_path out_path :

import csv
def print_section(section, f_out):
    if len(section) > 0:
        # find maximum column length
        max_len = max([len(col) for col in section])
        # build and print each row
        for i in xrange(max_len):
            f_out.write('\t'.join([col[i] if len(col) > i else '' for col in section]) + '\n')
        f_out.write('\n')

with csv.reader(open(in_path, 'r')) as f_in, open(out_path, 'w') as f_out:
    line = f_in.next()
    section = []
    for line in f_in:
        # test for new "Test" section
        if len(line) == 3 and line[0] == 'Test' and line[2] == '':
            # write previous section data
            print_section(section, f_out)
            # reset section
            section = []
            # write new section header
            f_out.write(line[1] + '\n')
        else:
            # add line to section
            section.append(line)
    # print the last section
    print_section(section, f_out)

, 'Test' line[0] == 'Test' .

, , , ( , ).