diff --git a/pristine_zip/delta_to_zipball.py b/pristine_zip/delta_to_zipball.py index 9d0276a..ca8f6fd 100644 --- a/pristine_zip/delta_to_zipball.py +++ b/pristine_zip/delta_to_zipball.py @@ -1,62 +1,66 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import os import subprocess import tempfile from . import reference def genzip(checkout_dir: str, delta_path: str, zipball_path: str): with tempfile.TemporaryDirectory(prefix="pristine-zip-genzip") as work_dir: reference_zipball_path = os.path.join(work_dir, "reference.zip") # generate reference zipball reference.compress(checkout_dir, reference_zipball_path) _apply_delta(reference_zipball_path, zipball_path, work_dir, delta_path) def _apply_delta( reference_zipball_path: str, zipball_path: str, work_dir: str, delta_path: str, ): proc = subprocess.run(["tar", "--extract", "-f", delta_path,], cwd=work_dir) proc.check_returncode() with open(os.path.join(work_dir, "type"), "rb") as fd: type_ = fd.read().decode().strip() assert type_ == "zip", ( f"Unknown zipball type {type}. Are you" f"extracting a delta from pristine-tar instead of pristine-zip?" ) with open(os.path.join(work_dir, "reference_md5sum"), "rb") as fd: expected_md5sum = fd.read().decode().strip() proc = subprocess.run(["md5sum", reference_zipball_path], capture_output=True) proc.check_returncode() actual_md5sum = proc.stdout.decode().split(" ", 1)[0].strip() if actual_md5sum != expected_md5sum: print( f"md5sum mismatch between reference zipballs " f"(expected '{expected_md5sum}', got '{actual_md5sum}').\n" f"This is a bug, please report it along with the original zipball " f"and the version number of pristine-zip." ) exit(1) xdelta3_path = os.path.join(work_dir, "delta") assert os.path.isfile(xdelta3_path), "Missing 'delta' file in delta archive." _apply_xdelta3(reference_zipball_path, zipball_path, xdelta3_path) def _apply_xdelta3(reference_zipball_path: str, zipball_path: str, xdelta3_path: str): + try: + os.remove(zipball_path) + except FileNotFoundError: + pass proc = subprocess.run( ["xdelta3", "-d", "-s", reference_zipball_path, xdelta3_path, zipball_path] ) proc.check_returncode() diff --git a/pristine_zip/main.py b/pristine_zip/main.py index dd7533d..47c2677 100644 --- a/pristine_zip/main.py +++ b/pristine_zip/main.py @@ -1,67 +1,67 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import os.path import tempfile import click from . import reference from . import delta_to_zipball from . import zipball_to_delta @click.group() def cli(): pass @cli.command() @click.argument("zipball", type=click.Path(exists=True, readable=True)) -@click.argument("delta", type=click.Path(exists=False, writable=True)) +@click.argument("delta", type=click.Path()) def gendelta(zipball: str, delta: str): """Takes an upstream zipball and generates a small binary delta that can be used to re-generate the zipball.""" zipball_to_delta.gendelta(os.path.abspath(zipball), os.path.abspath(delta)) @cli.command() @click.argument("delta", type=click.Path(exists=True, readable=True)) -@click.argument("zipball", type=click.Path(exists=False, writable=True)) +@click.argument("zipball", type=click.Path()) def genzip(delta: str, zipball: str): """Takes a delta generated by 'pristine-zip gendelta' and reads files from the CWD to generate the exact same zipball as was given to 'gendelta'.""" checkout_dir = os.getcwd() delta_to_zipball.genzip( checkout_dir, os.path.abspath(delta), os.path.abspath(zipball) ) @cli.command() @click.argument("source_zipball", type=click.Path(exists=True, readable=True)) -@click.argument("reference_zipball", type=click.Path(exists=False, writable=True)) +@click.argument("reference_zipball", type=click.Path()) def regenzip(source_zipball: str, reference_zipball: str): """Takes a zipball and generates a reference zipball from it.""" with tempfile.TemporaryDirectory() as work_dir: zipball_to_delta.generate_reference_zipball_from_zipball( os.path.abspath(source_zipball), os.path.abspath(reference_zipball), work_dir, ) @cli.command() @click.argument("reference_zipball", type=click.Path()) def cwdgenzip(reference_zipball: str): """Reads the CWD and generates a reference zipball from it.""" checkout_dir = os.getcwd() reference.compress( checkout_dir, reference_zipball, ) def main(): return cli() diff --git a/pristine_zip/reference.py b/pristine_zip/reference.py index 0acd1a0..5060c71 100644 --- a/pristine_zip/reference.py +++ b/pristine_zip/reference.py @@ -1,41 +1,44 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """Creates a ZIP file deterministically. This can be used a base reference for delta files.""" import os import subprocess def walk(checkout_dir): entries = [] for (dirpath, dirnames, filenames) in os.walk(checkout_dir): assert dirpath.startswith(checkout_dir) dirpath = dirpath[len(checkout_dir) :].lstrip("/") entries.append(dirpath) entries.extend(os.path.join(dirpath, filename) for filename in filenames) return entries def compress(checkout_dir: str, target: str): """Generates a reference zipball for the given checked out directory.""" - assert not os.path.isfile(target), target + try: + os.remove(target) + except FileNotFoundError: + pass assert os.path.isdir(checkout_dir), checkout_dir # Encode *before* sorting; sorting on unicode changes across configurations. entries = [entry.encode() for entry in walk(checkout_dir)] # Sort entries ourselves; InfoZIP's zip does not guarantee order entries.sort() # -X = --no-extra, which prevents inclusion of extra non-deterministic # and implementation-dependant data proc = subprocess.run( ["zip", "-X", target, "--names-stdin"], cwd=checkout_dir, input=b"\n".join(entries), ) proc.check_returncode()