diff --git a/pristine_zip/delta_to_zipball.py b/pristine_zip/delta_to_zipball.py index 10ad728..9d0276a 100644 --- a/pristine_zip/delta_to_zipball.py +++ b/pristine_zip/delta_to_zipball.py @@ -1,62 +1,62 @@ # 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 compress +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 - compress.compress(checkout_dir, reference_zipball_path) + 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): 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 a80e9cc..dd7533d 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 compress +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)) 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)) 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)) 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(exists=False, writable=True)) +@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() - compress.compress( + reference.compress( checkout_dir, reference_zipball, ) def main(): return cli() diff --git a/pristine_zip/compress.py b/pristine_zip/reference.py similarity index 100% rename from pristine_zip/compress.py rename to pristine_zip/reference.py diff --git a/pristine_zip/zipball_to_delta.py b/pristine_zip/zipball_to_delta.py index 0104929..ba0d34a 100644 --- a/pristine_zip/zipball_to_delta.py +++ b/pristine_zip/zipball_to_delta.py @@ -1,97 +1,97 @@ # 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 compress +from . import reference def gendelta(zipball_path: str, delta_path: str): with tempfile.TemporaryDirectory(prefix="pristine-zip-gendelta") as work_dir: reference_zipball_path = os.path.join(work_dir, "reference.zip") generate_reference_zipball_from_zipball( zipball_path, reference_zipball_path, work_dir ) _generate_delta(zipball_path, reference_zipball_path, work_dir, delta_path) def _generate_delta( upstream_zipball_path: str, reference_zipball_path: str, work_dir: str, delta_path: str, ): _generate_xdelta3( upstream_zipball_path, reference_zipball_path, os.path.join(work_dir, "delta") ) with open(os.path.join(work_dir, "type"), "wb") as fd: fd.write(b"zip\n") proc = subprocess.run(["md5sum", reference_zipball_path], capture_output=True) proc.check_returncode() md5sum = proc.stdout.split(b" ", 1)[0] with open(os.path.join(work_dir, "reference_md5sum"), "wb") as fd: fd.write(md5sum + b"\n") files = ["delta", "reference_md5sum", "type"] # Make the timestamps in the delta tarball deterministic for file in files: os.utime(os.path.join(work_dir, file), times=(0, 0)) proc = subprocess.run( [ "tar", # make entries in the delta tarball deterministic: "--owner", "0", "--group", "0", "--numeric-owner", "--mode", "644", # generic options: "--create", "--compress", "-f", delta_path, *files, ], cwd=work_dir, ) proc.check_returncode() def _generate_xdelta3( upstream_zipball_path: str, reference_zipball_path: str, delta_path: str ): """Generates the xdelta3 difference between a reference zipball and the original one.""" proc = subprocess.run( [ "xdelta3", "-e", "-s", reference_zipball_path, upstream_zipball_path, delta_path, ] ) proc.check_returncode() def generate_reference_zipball_from_zipball( upstream_zipball_path: str, reference_zipball_path: str, work_dir: str ): """Unzips an upstream zipball and rezips it in a reference zipball.""" checkout_dir = os.path.join(work_dir, "checkout") os.mkdir(checkout_dir) proc = subprocess.run(["unzip", upstream_zipball_path], cwd=checkout_dir) proc.check_returncode() - compress.compress(checkout_dir, reference_zipball_path) + reference.compress(checkout_dir, reference_zipball_path)