Created
January 31, 2022 10:09
-
-
Save Cryolite/d3814188079c975f5d6d6c840a5abc74 to your computer and use it in GitHub Desktop.
Merges two or more shuffled files into one shuffled stream as a whole
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import random | |
from pathlib import Path | |
import gzip | |
import sys | |
def main() -> None: | |
if len(sys.argv) <= 2: | |
raise RuntimeError('Too few arguments.') | |
paths = [Path(p) for p in sys.argv[1:]] | |
for path in paths: | |
if not path.exists(): | |
raise RuntimeError(f'{path}: Does not exist.') | |
if not path.is_file(): | |
raise RuntimeError(f'{path}: Not a file.') | |
n = len(paths) | |
files = [gzip.open(p, 'rt', encoding='UTF-8') for p in paths] | |
num_lines = [0] * n | |
for i in range(n): | |
path = paths[i] | |
f = files[i] | |
for line in f: | |
num_lines[i] += 1 | |
print(f'{path}: {num_lines[i]}', file=sys.stderr) | |
f.close() | |
files = [gzip.open(p, 'rt', encoding='UTF-8') for p in paths] | |
while num_lines != [0] * n: | |
i = random.choices(range(n), weights=num_lines) | |
assert(len(i) == 1) | |
i = i[0] | |
f = files[i] | |
line = next(f) | |
print(line, end='') | |
num_lines[i] -= 1 | |
for path, f in zip(paths, files): | |
try: | |
next(f) | |
raise AssertionError(f'{path}: Has not been fully consumed.') | |
except StopIteration: | |
pass | |
f.close() | |
if __name__ == '__main__': | |
main() | |
sys.exit(0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment