Using git diff, how can I get added and modified lines numbers?

Question

Assuming I have a text file

alex
bob
matrix
will be removed
git repo

and I have updated it to be

alex
new line here
another         


        

Answer 1

Here's some Python copypasta to get the line numbers for modified / removed lines, in case you came across this question looking for that.

It should be fairly easy to modify it into something that gets the modified and added line numbers as well.

I've only tested on Windows, but it should be cross platform as well.

import re
import subprocess

def main(file1: str, file2: str):
    diff = get_git_diff(file1, file2)
    print(edited_lines(diff))

def edited_lines(git_diff: str):
    ans = []
    diff_lines = git_diff.split("\n")
    found_first = False
    # adjust for added lines
    adjust = 0
    # how many lines since the start
    count = 0
    for line in diff_lines:
        if found_first:
            count += 1
            if line.startswith('-'):
                # minus one because count is 1 when we're looking at the start line
                ans.append(start + count - adjust - 1)
                continue

            if line.startswith('+'):
                adjust += 1
                continue

        # get the start line
        match = re.fullmatch(r'@@ \-(\d+),\d+ \+\d+,\d+ @@', line)
        if match:
            start = int(match.group(1))
            count = 0
            adjust = 0
            found_first = True

    return ans


def get_git_diff(file1: str, file2: str):
    try:
        diff_process: subprocess.CompletedProcess = subprocess.run(['git', 'diff', '--no-index', '-u', file1, file2], shell=True, check=True, stdout=subprocess.PIPE)
        ans = diff_process.stdout
    # git may exit with 1 even though it worked
    except subprocess.CalledProcessError as e:
        if e.stdout and e.stderr is None:
            ans = e.stdout
        else:
            raise

    # remove carriage at the end of lines from Windows
    ans = ans.decode()
    ans.replace('\r', '')
    return ans


if __name__ == "__main__":
    main("file1.txt", "file2.txt")