failing to print not matched lines from second file

[deanhystad]

Why were you confused by square brackets? You use them in your original post.

[menator01]

Outside square brackets is list comprehension and the [3] is string slicing.
Someone correct me if I am wrong please.

[DeaD_EyE]

Hm, I do not understand why you split the line, if you compare whole lines.

Things to pay attention for:

• what is compared? Lines or some columns in the liens?
  
• What should happen with empty lines?
  
• What should happen if one line has leading white spaces and the references not?
  
• What should happen if one line has tailing white spaces and the references not?
  
• Do the reference have empty lines and leading white spaces?
  

If you just want to compare whole not empty lines and stripping whitespaces:

from io import StringIO


test1 = """

03/28/2021,P,6,LINE2
03/28/2021,P,9,LINE4

"""


test2 = """

03/28/2021,P,16,LINE1
03/28/2021,P,6,LINE2
03/28/2021,P,9,LINE3
03/28/2021,P,9,LINE4
03/28/2021,P,8,LINE5
03/28/2021,S,95,LINE6
03/28/2021,S,1,LINE7
03/28/2021,P,46,LINE8

"""

file1 = StringIO(test1)
file2 = StringIO(test2)
# using StringIO to simulate an open file


# file1 and file2 can also come from open()
# TextIOWrapper, StringIO, BytesIO, ... supports
# line iteration


def get_references(text):
    references = set()
    # we want to look up fast
    # preserving the order is not required for
    # the references
    # a set contains only unique elements

    # this removes leading and tailing white spaces
    for line in map(str.strip, text):
        if not line:
            # skip empty lines
            # because of str.strip
            # the line does not contain white spaces
            # bool(empty_string) -> False
            continue
        # set has no append.
        # instead you add objects to the set
        references.add(line)
    return references


def show_not_matching(text, references):
    line_iter = map(str.strip, text)
    # to get line numbers, enumerate is used
    # it just iterates over the iterable and
    # yields (number, elemten_of_iterable)
    lines = enumerate(line_iter, start=1)
    for line_number, line in lines:
        if not line:
            continue
        if line not in references:
            # string formatting
            print(f"[{line_number:>5}] Not matching -> {line}")


if __name__ == "__main__":
    # with test data in source code
    ref = get_references(file1)
    show_not_matching(file2, ref)

    # later with real files
    # with open("file1.txt") as fd_ref:
    #     refs = get_references(fd_ref)
    #
    # with open("file2.txt") as fd:
    #     show_not_matching(fd, refs)

And if you not want to compare the date:

from io import StringIO


test1 = """

03/28/2021,P,6,LINE2
03/28/2021,P,9,LINE4

"""


test2 = """

03/28/2021,P,16,LINE1
03/28/2021,P,6,LINE2
03/28/2021,P,9,LINE3
03/28/2021,P,9,LINE4
03/28/2021,P,8,LINE5
03/28/2021,S,95,LINE6
03/28/2021,S,1,LINE7
03/28/2021,P,46,LINE8

"""

file1 = StringIO(test1)
file2 = StringIO(test2)
# using StringIO to simulate an open file


# file1 and file2 can also come from open()
# TextIOWrapper, StringIO, BytesIO, ... supports
# line iteration


def get_references(text):
    references = set()
    # we want to look up fast
    # preserving the order is not required for
    # the references
    # a set contains only unique elements

    # this removes leading and tailing white spaces
    for line in map(str.strip, text):
        if not line:
            # skip empty lines
            # because of str.strip
            # the line does not contain white spaces
            # bool(empty_string) -> False
            continue
        # set has no append.
        # instead you add objects to the set

        # just removing the date from line
        # _ is a throw away name
        _, line = line.split(",", maxsplit=1)
        references.add(line)
    print("References:", references)
    return references


def show_not_matching(text, references):
    line_iter = map(str.strip, text)
    # to get line numbers, enumerate is used
    # it just iterates over the iterable and
    # yields (number, elemten_of_iterable)
    lines = enumerate(line_iter, start=1)
    for line_number, line in lines:
        if not line:
            continue
        # here the same
        # we want to remove the date from the
        # line we want to compare with the references
        # where the date was also removed
        # but we keep the original line, for
        # printing it
        _, line_to_compare = line.split(",", maxsplit=1)
        # now use the modified line to look it up in references
        if line_to_compare not in references:
            # string formatting
            print(f"[{line_number:>5}] Not matching -> {line}")


if __name__ == "__main__":
    # with test data in source code
    ref = get_references(file1)
    show_not_matching(file2, ref)

    # later with real files
    # with open("file1.txt") as fd_ref:
    #     refs = get_references(fd_ref)
    #
    # with open("file2.txt") as fd:
    #     show_not_matching(fd, refs)

This time without comments, but with real files:

def get_references(text):
    references = set()
    for line in map(str.strip, text):
        if not line:
            continue
        _, line = line.split(",", maxsplit=1)
        references.add(line)
    return references


def show_not_matching(text, references):
    line_iter = map(str.strip, text)
    lines = enumerate(line_iter, start=1)
    for line_number, line in lines:
        if not line:
            continue
        _, line_to_compare = line.split(",", maxsplit=1)
        if line_to_compare not in references:
            print(f"[{line_number:>5}] Not matching -> {line}")


if __name__ == "__main__":
    with open("file1.txt") as fd_ref:
        refs = get_references(fd_ref)

    with open("file2.txt") as fd:
        show_not_matching(fd, refs)

Read the Python documentation, if you see functions you don't know.
enumerate, map, str.split, set, in operator.

Also important for later use: str.strip(both_sides), str.lstrip(left_side), str.rstrip(right_side).
To remove only tailing white spaces, use str.lstrip.

[DeaD_EyE]

By the way, you can use the csv Module.
This is also in the standard library.

[codinglearner]

Build a set of strings then read the second file - this will fix the problem that you are facing.

with open(DIR/'lines_to_look_for.txt', 'r') as file:
    lines = set([line.strip().split(',')[3] for line in file])
 
with open(DIR/'check_for_lines.txt', 'r') as file:
    for line in file:
        line = line.strip()
        if line.split(',')[3] in lines:
            print(f'{line} MATCH')
        else:
            print(f'{line} NO MATCH')

Square Brackets is list comprehension and the [3] is string slicing. menator01 said right only.