import contextlib import importlib.util import io import itertools import os import pathlib import posixpath import string import struct import subprocess import sys import time import unittest import unittest.mock as mock import zipfile import functools from tempfile import TemporaryFile from random import randint, random, randbytes from test.support import script_helper from test.support import (findfile, requires_zlib, requires_bz2, requires_lzma, captured_stdout) from test.support.os_helper import TESTFN, unlink, rmtree, temp_dir, temp_cwd TESTFN2 = TESTFN + "2" TESTFNDIR = TESTFN + "d" FIXEDTEST_SIZE = 1000 DATAFILES_DIR = 'zipfile_datafiles' SMALL_TEST_DATA = [('_ziptest1', '1q2w3e4r5t'), ('ziptest2dir/_ziptest2', 'qawsedrftg'), ('ziptest2dir/ziptest3dir/_ziptest3', 'azsxdcfvgb'), ('ziptest2dir/ziptest3dir/ziptest4dir/_ziptest3', '6y7u8i9o0p')] def get_files(test): yield TESTFN2 with TemporaryFile() as f: yield f test.assertFalse(f.closed) with io.BytesIO() as f: yield f test.assertFalse(f.closed) class AbstractTestsWithSourceFile: @classmethod def setUpClass(cls): cls.line_gen = [bytes("Zipfile test line %d. random float: %f\n" % (i, random()), "ascii") for i in range(FIXEDTEST_SIZE)] cls.data = b''.join(cls.line_gen) def setUp(self): # Make a source file with some lines with open(TESTFN, "wb") as fp: fp.write(self.data) def make_test_archive(self, f, compression, compresslevel=None): kwargs = {'compression': compression, 'compresslevel': compresslevel} # Create the ZIP archive with zipfile.ZipFile(f, "w", **kwargs) as zipfp: zipfp.write(TESTFN, "another.name") zipfp.write(TESTFN, TESTFN) zipfp.writestr("strfile", self.data) with zipfp.open('written-open-w', mode='w') as f: for line in self.line_gen: f.write(line) def zip_test(self, f, compression, compresslevel=None): self.make_test_archive(f, compression, compresslevel) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read("another.name"), self.data) self.assertEqual(zipfp.read("strfile"), self.data) # Print the ZIP directory fp = io.StringIO() zipfp.printdir(file=fp) directory = fp.getvalue() lines = directory.splitlines() self.assertEqual(len(lines), 5) # Number of files + header self.assertIn('File Name', lines[0]) self.assertIn('Modified', lines[0]) self.assertIn('Size', lines[0]) fn, date, time_, size = lines[1].split() self.assertEqual(fn, 'another.name') self.assertTrue(time.strptime(date, '%Y-%m-%d')) self.assertTrue(time.strptime(time_, '%H:%M:%S')) self.assertEqual(size, str(len(self.data))) # Check the namelist names = zipfp.namelist() self.assertEqual(len(names), 4) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) self.assertIn("written-open-w", names) # Check infolist infos = zipfp.infolist() names = [i.filename for i in infos] self.assertEqual(len(names), 4) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) self.assertIn("written-open-w", names) for i in infos: self.assertEqual(i.file_size, len(self.data)) # check getinfo for nm in (TESTFN, "another.name", "strfile", "written-open-w"): info = zipfp.getinfo(nm) self.assertEqual(info.filename, nm) self.assertEqual(info.file_size, len(self.data)) # Check that testzip doesn't raise an exception zipfp.testzip() def test_basic(self): for f in get_files(self): self.zip_test(f, self.compression) def zip_open_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: zipdata1 = [] with zipfp.open(TESTFN) as zipopen1: while True: read_data = zipopen1.read(256) if not read_data: break zipdata1.append(read_data) zipdata2 = [] with zipfp.open("another.name") as zipopen2: while True: read_data = zipopen2.read(256) if not read_data: break zipdata2.append(read_data) self.assertEqual(b''.join(zipdata1), self.data) self.assertEqual(b''.join(zipdata2), self.data) def test_open(self): for f in get_files(self): self.zip_open_test(f, self.compression) def test_open_with_pathlike(self): path = pathlib.Path(TESTFN2) self.zip_open_test(path, self.compression) with zipfile.ZipFile(path, "r", self.compression) as zipfp: self.assertIsInstance(zipfp.filename, str) def zip_random_open_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: zipdata1 = [] with zipfp.open(TESTFN) as zipopen1: while True: read_data = zipopen1.read(randint(1, 1024)) if not read_data: break zipdata1.append(read_data) self.assertEqual(b''.join(zipdata1), self.data) def test_random_open(self): for f in get_files(self): self.zip_random_open_test(f, self.compression) def zip_read1_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: zipdata = [] while True: read_data = zipopen.read1(-1) if not read_data: break zipdata.append(read_data) self.assertEqual(b''.join(zipdata), self.data) def test_read1(self): for f in get_files(self): self.zip_read1_test(f, self.compression) def zip_read1_10_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: zipdata = [] while True: read_data = zipopen.read1(10) self.assertLessEqual(len(read_data), 10) if not read_data: break zipdata.append(read_data) self.assertEqual(b''.join(zipdata), self.data) def test_read1_10(self): for f in get_files(self): self.zip_read1_10_test(f, self.compression) def zip_readline_read_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: data = b'' while True: read = zipopen.readline() if not read: break data += read read = zipopen.read(100) if not read: break data += read self.assertEqual(data, self.data) def test_readline_read(self): # Issue #7610: calls to readline() interleaved with calls to read(). for f in get_files(self): self.zip_readline_read_test(f, self.compression) def zip_readline_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: for line in self.line_gen: linedata = zipopen.readline() self.assertEqual(linedata, line) def test_readline(self): for f in get_files(self): self.zip_readline_test(f, self.compression) def zip_readlines_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: ziplines = zipopen.readlines() for line, zipline in zip(self.line_gen, ziplines): self.assertEqual(zipline, line) def test_readlines(self): for f in get_files(self): self.zip_readlines_test(f, self.compression) def zip_iterlines_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: for line, zipline in zip(self.line_gen, zipopen): self.assertEqual(zipline, line) def test_iterlines(self): for f in get_files(self): self.zip_iterlines_test(f, self.compression) def test_low_compression(self): """Check for cases where compressed data is larger than original.""" # Create the ZIP archive with zipfile.ZipFile(TESTFN2, "w", self.compression) as zipfp: zipfp.writestr("strfile", '12') # Get an open object for strfile with zipfile.ZipFile(TESTFN2, "r", self.compression) as zipfp: with zipfp.open("strfile") as openobj: self.assertEqual(openobj.read(1), b'1') self.assertEqual(openobj.read(1), b'2') def test_writestr_compression(self): zipfp = zipfile.ZipFile(TESTFN2, "w") zipfp.writestr("b.txt", "hello world", compress_type=self.compression) info = zipfp.getinfo('b.txt') self.assertEqual(info.compress_type, self.compression) def test_writestr_compresslevel(self): zipfp = zipfile.ZipFile(TESTFN2, "w", compresslevel=1) zipfp.writestr("a.txt", "hello world", compress_type=self.compression) zipfp.writestr("b.txt", "hello world", compress_type=self.compression, compresslevel=2) # Compression level follows the constructor. a_info = zipfp.getinfo('a.txt') self.assertEqual(a_info.compress_type, self.compression) self.assertEqual(a_info._compresslevel, 1) # Compression level is overridden. b_info = zipfp.getinfo('b.txt') self.assertEqual(b_info.compress_type, self.compression) self.assertEqual(b_info._compresslevel, 2) def test_read_return_size(self): # Issue #9837: ZipExtFile.read() shouldn't return more bytes # than requested. for test_size in (1, 4095, 4096, 4097, 16384): file_size = test_size + 1 junk = randbytes(file_size) with zipfile.ZipFile(io.BytesIO(), "w", self.compression) as zipf: zipf.writestr('foo', junk) with zipf.open('foo', 'r') as fp: buf = fp.read(test_size) self.assertEqual(len(buf), test_size) def test_truncated_zipfile(self): fp = io.BytesIO() with zipfile.ZipFile(fp, mode='w') as zipf: zipf.writestr('strfile', self.data, compress_type=self.compression) end_offset = fp.tell() zipfiledata = fp.getvalue() fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): zipopen.read() fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): while zipopen.read(100): pass fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): while zipopen.read1(100): pass def test_repr(self): fname = 'file.name' for f in get_files(self): with zipfile.ZipFile(f, 'w', self.compression) as zipfp: zipfp.write(TESTFN, fname) r = repr(zipfp) self.assertIn("mode='w'", r) with zipfile.ZipFile(f, 'r') as zipfp: r = repr(zipfp) if isinstance(f, str): self.assertIn('filename=%r' % f, r) else: self.assertIn('file=%r' % f, r) self.assertIn("mode='r'", r) r = repr(zipfp.getinfo(fname)) self.assertIn('filename=%r' % fname, r) self.assertIn('filemode=', r) self.assertIn('file_size=', r) if self.compression != zipfile.ZIP_STORED: self.assertIn('compress_type=', r) self.assertIn('compress_size=', r) with zipfp.open(fname) as zipopen: r = repr(zipopen) self.assertIn('name=%r' % fname, r) self.assertIn("mode='r'", r) if self.compression != zipfile.ZIP_STORED: self.assertIn('compress_type=', r) self.assertIn('[closed]', repr(zipopen)) self.assertIn('[closed]', repr(zipfp)) def test_compresslevel_basic(self): for f in get_files(self): self.zip_test(f, self.compression, compresslevel=9) def test_per_file_compresslevel(self): """Check that files within a Zip archive can have different compression levels.""" with zipfile.ZipFile(TESTFN2, "w", compresslevel=1) as zipfp: zipfp.write(TESTFN, 'compress_1') zipfp.write(TESTFN, 'compress_9', compresslevel=9) one_info = zipfp.getinfo('compress_1') nine_info = zipfp.getinfo('compress_9') self.assertEqual(one_info._compresslevel, 1) self.assertEqual(nine_info._compresslevel, 9) def test_writing_errors(self): class BrokenFile(io.BytesIO): def write(self, data): nonlocal count if count is not None: if count == stop: raise OSError count += 1 super().write(data) stop = 0 while True: testfile = BrokenFile() count = None with zipfile.ZipFile(testfile, 'w', self.compression) as zipfp: with zipfp.open('file1', 'w') as f: f.write(b'data1') count = 0 try: with zipfp.open('file2', 'w') as f: f.write(b'data2') except OSError: stop += 1 else: break finally: count = None with zipfile.ZipFile(io.BytesIO(testfile.getvalue())) as zipfp: self.assertEqual(zipfp.namelist(), ['file1']) self.assertEqual(zipfp.read('file1'), b'data1') with zipfile.ZipFile(io.BytesIO(testfile.getvalue())) as zipfp: self.assertEqual(zipfp.namelist(), ['file1', 'file2']) self.assertEqual(zipfp.read('file1'), b'data1') self.assertEqual(zipfp.read('file2'), b'data2') def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class StoredTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_STORED test_low_compression = None def zip_test_writestr_permissions(self, f, compression): # Make sure that writestr and open(... mode='w') create files with # mode 0600, when they are passed a name rather than a ZipInfo # instance. self.make_test_archive(f, compression) with zipfile.ZipFile(f, "r") as zipfp: zinfo = zipfp.getinfo('strfile') self.assertEqual(zinfo.external_attr, 0o600 << 16) zinfo2 = zipfp.getinfo('written-open-w') self.assertEqual(zinfo2.external_attr, 0o600 << 16) def test_writestr_permissions(self): for f in get_files(self): self.zip_test_writestr_permissions(f, zipfile.ZIP_STORED) def test_absolute_arcnames(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, "/absolute") with zipfile.ZipFile(TESTFN2, "r", zipfile.ZIP_STORED) as zipfp: self.assertEqual(zipfp.namelist(), ["absolute"]) def test_append_to_zip_file(self): """Test appending to an existing zipfile.""" with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with zipfile.ZipFile(TESTFN2, "a", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("strfile", self.data) self.assertEqual(zipfp.namelist(), [TESTFN, "strfile"]) def test_append_to_non_zip_file(self): """Test appending to an existing file that is not a zipfile.""" # NOTE: this test fails if len(d) < 22 because of the first # line "fpin.seek(-22, 2)" in _EndRecData data = b'I am not a ZipFile!'*10 with open(TESTFN2, 'wb') as f: f.write(data) with zipfile.ZipFile(TESTFN2, "a", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'rb') as f: f.seek(len(data)) with zipfile.ZipFile(f, "r") as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) with open(TESTFN2, 'rb') as f: self.assertEqual(f.read(len(data)), data) zipfiledata = f.read() with io.BytesIO(zipfiledata) as bio, zipfile.ZipFile(bio) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) def test_read_concatenated_zip_file(self): with io.BytesIO() as bio: with zipfile.ZipFile(bio, 'w', zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) zipfiledata = bio.getvalue() data = b'I am not a ZipFile!'*10 with open(TESTFN2, 'wb') as f: f.write(data) f.write(zipfiledata) with zipfile.ZipFile(TESTFN2) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) def test_append_to_concatenated_zip_file(self): with io.BytesIO() as bio: with zipfile.ZipFile(bio, 'w', zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) zipfiledata = bio.getvalue() data = b'I am not a ZipFile!'*1000000 with open(TESTFN2, 'wb') as f: f.write(data) f.write(zipfiledata) with zipfile.ZipFile(TESTFN2, 'a') as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) zipfp.writestr('strfile', self.data) with open(TESTFN2, 'rb') as f: self.assertEqual(f.read(len(data)), data) zipfiledata = f.read() with io.BytesIO(zipfiledata) as bio, zipfile.ZipFile(bio) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN, 'strfile']) self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read('strfile'), self.data) def test_ignores_newline_at_end(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'a', encoding='utf-8') as f: f.write("\r\n\00\00\00") with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsInstance(zipfp, zipfile.ZipFile) def test_ignores_stuff_appended_past_comments(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.comment = b"this is a comment" zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'a', encoding='utf-8') as f: f.write("abcdef\r\n") with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsInstance(zipfp, zipfile.ZipFile) self.assertEqual(zipfp.comment, b"this is a comment") def test_write_default_name(self): """Check that calling ZipFile.write without arcname specified produces the expected result.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: zipfp.write(TESTFN) with open(TESTFN, "rb") as f: self.assertEqual(zipfp.read(TESTFN), f.read()) def test_io_on_closed_zipextfile(self): fname = "somefile.txt" with zipfile.ZipFile(TESTFN2, mode="w") as zipfp: zipfp.writestr(fname, "bogus") with zipfile.ZipFile(TESTFN2, mode="r") as zipfp: with zipfp.open(fname) as fid: fid.close() self.assertRaises(ValueError, fid.read) self.assertRaises(ValueError, fid.seek, 0) self.assertRaises(ValueError, fid.tell) self.assertRaises(ValueError, fid.readable) self.assertRaises(ValueError, fid.seekable) def test_write_to_readonly(self): """Check that trying to call write() on a readonly ZipFile object raises a ValueError.""" with zipfile.ZipFile(TESTFN2, mode="w") as zipfp: zipfp.writestr("somefile.txt", "bogus") with zipfile.ZipFile(TESTFN2, mode="r") as zipfp: self.assertRaises(ValueError, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, mode="r") as zipfp: with self.assertRaises(ValueError): zipfp.open(TESTFN, mode='w') def test_add_file_before_1980(self): # Set atime and mtime to 1970-01-01 os.utime(TESTFN, (0, 0)) with zipfile.ZipFile(TESTFN2, "w") as zipfp: self.assertRaises(ValueError, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, "w", strict_timestamps=False) as zipfp: zipfp.write(TESTFN) zinfo = zipfp.getinfo(TESTFN) self.assertEqual(zinfo.date_time, (1980, 1, 1, 0, 0, 0)) def test_add_file_after_2107(self): # Set atime and mtime to 2108-12-30 ts = 4386268800 try: time.localtime(ts) except OverflowError: self.skipTest(f'time.localtime({ts}) raises OverflowError') try: os.utime(TESTFN, (ts, ts)) except OverflowError: self.skipTest('Host fs cannot set timestamp to required value.') mtime_ns = os.stat(TESTFN).st_mtime_ns if mtime_ns != (4386268800 * 10**9): # XFS filesystem is limited to 32-bit timestamp, but the syscall # didn't fail. Moreover, there is a VFS bug which returns # a cached timestamp which is different than the value on disk. # # Test st_mtime_ns rather than st_mtime to avoid rounding issues. # # https://bugzilla.redhat.com/show_bug.cgi?id=1795576 # https://bugs.python.org/issue39460#msg360952 self.skipTest(f"Linux VFS/XFS kernel bug detected: {mtime_ns=}") with zipfile.ZipFile(TESTFN2, "w") as zipfp: self.assertRaises(struct.error, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, "w", strict_timestamps=False) as zipfp: zipfp.write(TESTFN) zinfo = zipfp.getinfo(TESTFN) self.assertEqual(zinfo.date_time, (2107, 12, 31, 23, 59, 59)) @requires_zlib() class DeflateTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_DEFLATED def test_per_file_compression(self): """Check that files within a Zip archive can have different compression options.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: zipfp.write(TESTFN, 'storeme', zipfile.ZIP_STORED) zipfp.write(TESTFN, 'deflateme', zipfile.ZIP_DEFLATED) sinfo = zipfp.getinfo('storeme') dinfo = zipfp.getinfo('deflateme') self.assertEqual(sinfo.compress_type, zipfile.ZIP_STORED) self.assertEqual(dinfo.compress_type, zipfile.ZIP_DEFLATED) @requires_bz2() class Bzip2TestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_BZIP2 @requires_lzma() class LzmaTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_LZMA class AbstractTestZip64InSmallFiles: # These tests test the ZIP64 functionality without using large files, # see test_zipfile64 for proper tests. @classmethod def setUpClass(cls): line_gen = (bytes("Test of zipfile line %d." % i, "ascii") for i in range(0, FIXEDTEST_SIZE)) cls.data = b'\n'.join(line_gen) def setUp(self): self._limit = zipfile.ZIP64_LIMIT self._filecount_limit = zipfile.ZIP_FILECOUNT_LIMIT zipfile.ZIP64_LIMIT = 1000 zipfile.ZIP_FILECOUNT_LIMIT = 9 # Make a source file with some lines with open(TESTFN, "wb") as fp: fp.write(self.data) def zip_test(self, f, compression): # Create the ZIP archive with zipfile.ZipFile(f, "w", compression, allowZip64=True) as zipfp: zipfp.write(TESTFN, "another.name") zipfp.write(TESTFN, TESTFN) zipfp.writestr("strfile", self.data) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read("another.name"), self.data) self.assertEqual(zipfp.read("strfile"), self.data) # Print the ZIP directory fp = io.StringIO() zipfp.printdir(fp) directory = fp.getvalue() lines = directory.splitlines() self.assertEqual(len(lines), 4) # Number of files + header self.assertIn('File Name', lines[0]) self.assertIn('Modified', lines[0]) self.assertIn('Size', lines[0]) fn, date, time_, size = lines[1].split() self.assertEqual(fn, 'another.name') self.assertTrue(time.strptime(date, '%Y-%m-%d')) self.assertTrue(time.strptime(time_, '%H:%M:%S')) self.assertEqual(size, str(len(self.data))) # Check the namelist names = zipfp.namelist() self.assertEqual(len(names), 3) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) # Check infolist infos = zipfp.infolist() names = [i.filename for i in infos] self.assertEqual(len(names), 3) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) for i in infos: self.assertEqual(i.file_size, len(self.data)) # check getinfo for nm in (TESTFN, "another.name", "strfile"): info = zipfp.getinfo(nm) self.assertEqual(info.filename, nm) self.assertEqual(info.file_size, len(self.data)) # Check that testzip doesn't raise an exception zipfp.testzip() def test_basic(self): for f in get_files(self): self.zip_test(f, self.compression) def test_too_many_files(self): # This test checks that more than 64k files can be added to an archive, # and that the resulting archive can be read properly by ZipFile zipf = zipfile.ZipFile(TESTFN, "w", self.compression, allowZip64=True) zipf.debug = 100 numfiles = 15 for i in range(numfiles): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf2 = zipfile.ZipFile(TESTFN, "r", self.compression) self.assertEqual(len(zipf2.namelist()), numfiles) for i in range(numfiles): content = zipf2.read("foo%08d" % i).decode('ascii') self.assertEqual(content, "%d" % (i**3 % 57)) zipf2.close() def test_too_many_files_append(self): zipf = zipfile.ZipFile(TESTFN, "w", self.compression, allowZip64=False) zipf.debug = 100 numfiles = 9 for i in range(numfiles): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles) with self.assertRaises(zipfile.LargeZipFile): zipf.writestr("foo%08d" % numfiles, b'') self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf = zipfile.ZipFile(TESTFN, "a", self.compression, allowZip64=False) zipf.debug = 100 self.assertEqual(len(zipf.namelist()), numfiles) with self.assertRaises(zipfile.LargeZipFile): zipf.writestr("foo%08d" % numfiles, b'') self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf = zipfile.ZipFile(TESTFN, "a", self.compression, allowZip64=True) zipf.debug = 100 self.assertEqual(len(zipf.namelist()), numfiles) numfiles2 = 15 for i in range(numfiles, numfiles2): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles2) zipf.close() zipf2 = zipfile.ZipFile(TESTFN, "r", self.compression) self.assertEqual(len(zipf2.namelist()), numfiles2) for i in range(numfiles2): content = zipf2.read("foo%08d" % i).decode('ascii') self.assertEqual(content, "%d" % (i**3 % 57)) zipf2.close() def tearDown(self): zipfile.ZIP64_LIMIT = self._limit zipfile.ZIP_FILECOUNT_LIMIT = self._filecount_limit unlink(TESTFN) unlink(TESTFN2) class StoredTestZip64InSmallFiles(AbstractTestZip64InSmallFiles, unittest.TestCase): compression = zipfile.ZIP_STORED def large_file_exception_test(self, f, compression): with zipfile.ZipFile(f, "w", compression, allowZip64=False) as zipfp: self.assertRaises(zipfile.LargeZipFile, zipfp.write, TESTFN, "another.name") def large_file_exception_test2(self, f, compression): with zipfile.ZipFile(f, "w", compression, allowZip64=False) as zipfp: self.assertRaises(zipfile.LargeZipFile, zipfp.writestr, "another.name", self.data) def test_large_file_exception(self): for f in get_files(self): self.large_file_exception_test(f, zipfile.ZIP_STORED) self.large_file_exception_test2(f, zipfile.ZIP_STORED) def test_absolute_arcnames(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED, allowZip64=True) as zipfp: zipfp.write(TESTFN, "/absolute") with zipfile.ZipFile(TESTFN2, "r", zipfile.ZIP_STORED) as zipfp: self.assertEqual(zipfp.namelist(), ["absolute"]) def test_append(self): # Test that appending to the Zip64 archive doesn't change # extra fields of existing entries. with zipfile.ZipFile(TESTFN2, "w", allowZip64=True) as zipfp: zipfp.writestr("strfile", self.data) with zipfile.ZipFile(TESTFN2, "r", allowZip64=True) as zipfp: zinfo = zipfp.getinfo("strfile") extra = zinfo.extra with zipfile.ZipFile(TESTFN2, "a", allowZip64=True) as zipfp: zipfp.writestr("strfile2", self.data) with zipfile.ZipFile(TESTFN2, "r", allowZip64=True) as zipfp: zinfo = zipfp.getinfo("strfile") self.assertEqual(zinfo.extra, extra) def make_zip64_file( self, file_size_64_set=False, file_size_extra=False, compress_size_64_set=False, compress_size_extra=False, header_offset_64_set=False, header_offset_extra=False, ): """Generate bytes sequence for a zip with (incomplete) zip64 data. The actual values (not the zip 64 0xffffffff values) stored in the file are: file_size: 8 compress_size: 8 header_offset: 0 """ actual_size = 8 actual_header_offset = 0 local_zip64_fields = [] central_zip64_fields = [] file_size = actual_size if file_size_64_set: file_size = 0xffffffff if file_size_extra: local_zip64_fields.append(actual_size) central_zip64_fields.append(actual_size) file_size = struct.pack("e|f"g?h*i', ','), r'a\b,c_d_e_f_g_h_i') self.assertEqual(san('../../foo../../ba..r', '/'), r'foo/ba..r') def test_extract_hackers_arcnames_common_cases(self): common_hacknames = [ ('../foo/bar', 'foo/bar'), ('foo/../bar', 'foo/bar'), ('foo/../../bar', 'foo/bar'), ('foo/bar/..', 'foo/bar'), ('./../foo/bar', 'foo/bar'), ('/foo/bar', 'foo/bar'), ('/foo/../bar', 'foo/bar'), ('/foo/../../bar', 'foo/bar'), ] self._test_extract_hackers_arcnames(common_hacknames) @unittest.skipIf(os.path.sep != '\\', 'Requires \\ as path separator.') def test_extract_hackers_arcnames_windows_only(self): """Test combination of path fixing and windows name sanitization.""" windows_hacknames = [ (r'..\foo\bar', 'foo/bar'), (r'..\/foo\/bar', 'foo/bar'), (r'foo/\..\/bar', 'foo/bar'), (r'foo\/../\bar', 'foo/bar'), (r'C:foo/bar', 'foo/bar'), (r'C:/foo/bar', 'foo/bar'), (r'C://foo/bar', 'foo/bar'), (r'C:\foo\bar', 'foo/bar'), (r'//conky/mountpoint/foo/bar', 'foo/bar'), (r'\\conky\mountpoint\foo\bar', 'foo/bar'), (r'///conky/mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\\conky\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//conky//mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\conky\\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//?/C:/foo/bar', 'foo/bar'), (r'\\?\C:\foo\bar', 'foo/bar'), (r'C:/../C:/foo/bar', 'C_/foo/bar'), (r'a:b\ce|f"g?h*i', 'b/c_d_e_f_g_h_i'), ('../../foo../../ba..r', 'foo/ba..r'), ] self._test_extract_hackers_arcnames(windows_hacknames) @unittest.skipIf(os.path.sep != '/', r'Requires / as path separator.') def test_extract_hackers_arcnames_posix_only(self): posix_hacknames = [ ('//foo/bar', 'foo/bar'), ('../../foo../../ba..r', 'foo../ba..r'), (r'foo/..\bar', r'foo/..\bar'), ] self._test_extract_hackers_arcnames(posix_hacknames) def _test_extract_hackers_arcnames(self, hacknames): for arcname, fixedname in hacknames: content = b'foobar' + arcname.encode() with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipfp: zinfo = zipfile.ZipInfo() # preserve backslashes zinfo.filename = arcname zinfo.external_attr = 0o600 << 16 zipfp.writestr(zinfo, content) arcname = arcname.replace(os.sep, "/") targetpath = os.path.join('target', 'subdir', 'subsub') correctfile = os.path.join(targetpath, *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname, targetpath) self.assertEqual(writtenfile, correctfile, msg='extract %r: %r != %r' % (arcname, writtenfile, correctfile)) self.check_file(correctfile, content) rmtree('target') with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall(targetpath) self.check_file(correctfile, content) rmtree('target') correctfile = os.path.join(os.getcwd(), *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname) self.assertEqual(writtenfile, correctfile, msg="extract %r" % arcname) self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall() self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) unlink(TESTFN2) class OtherTests(unittest.TestCase): def test_open_via_zip_info(self): # Create the ZIP archive with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("name", "foo") with self.assertWarns(UserWarning): zipfp.writestr("name", "bar") self.assertEqual(zipfp.namelist(), ["name"] * 2) with zipfile.ZipFile(TESTFN2, "r") as zipfp: infos = zipfp.infolist() data = b"" for info in infos: with zipfp.open(info) as zipopen: data += zipopen.read() self.assertIn(data, {b"foobar", b"barfoo"}) data = b"" for info in infos: data += zipfp.read(info) self.assertIn(data, {b"foobar", b"barfoo"}) def test_writestr_extended_local_header_issue1202(self): with zipfile.ZipFile(TESTFN2, 'w') as orig_zip: for data in 'abcdefghijklmnop': zinfo = zipfile.ZipInfo(data) zinfo.flag_bits |= zipfile._MASK_USE_DATA_DESCRIPTOR # Include an extended local header. orig_zip.writestr(zinfo, data) def test_close(self): """Check that the zipfile is closed after the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') def test_close_on_exception(self): """Check that the zipfile is closed if an exception is raised in the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) try: with zipfile.ZipFile(TESTFN2, "r") as zipfp2: raise zipfile.BadZipFile() except zipfile.BadZipFile: self.assertIsNone(zipfp2.fp, 'zipfp is not closed') def test_unsupported_version(self): # File has an extract_version of 120 data = (b'PK\x03\x04x\x00\x00\x00\x00\x00!p\xa1@\x00\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00xPK\x01\x02x\x03x\x00\x00\x00\x00' b'\x00!p\xa1@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00\x00xPK\x05\x06' b'\x00\x00\x00\x00\x01\x00\x01\x00/\x00\x00\x00\x1f\x00\x00\x00\x00\x00') self.assertRaises(NotImplementedError, zipfile.ZipFile, io.BytesIO(data), 'r') @requires_zlib() def test_read_unicode_filenames(self): # bug #10801 fname = findfile('zip_cp437_header.zip') with zipfile.ZipFile(fname) as zipfp: for name in zipfp.namelist(): zipfp.open(name).close() def test_write_unicode_filenames(self): with zipfile.ZipFile(TESTFN, "w") as zf: zf.writestr("foo.txt", "Test for unicode filename") zf.writestr("\xf6.txt", "Test for unicode filename") self.assertIsInstance(zf.infolist()[0].filename, str) with zipfile.ZipFile(TESTFN, "r") as zf: self.assertEqual(zf.filelist[0].filename, "foo.txt") self.assertEqual(zf.filelist[1].filename, "\xf6.txt") def test_read_after_write_unicode_filenames(self): with zipfile.ZipFile(TESTFN2, 'w') as zipfp: zipfp.writestr('приклад', b'sample') self.assertEqual(zipfp.read('приклад'), b'sample') def test_exclusive_create_zip_file(self): """Test exclusive creating a new zipfile.""" unlink(TESTFN2) filename = 'testfile.txt' content = b'hello, world. this is some content.' with zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) as zipfp: zipfp.writestr(filename, content) with self.assertRaises(FileExistsError): zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertEqual(zipfp.namelist(), [filename]) self.assertEqual(zipfp.read(filename), content) def test_create_non_existent_file_for_append(self): if os.path.exists(TESTFN): os.unlink(TESTFN) filename = 'testfile.txt' content = b'hello, world. this is some content.' try: with zipfile.ZipFile(TESTFN, 'a') as zf: zf.writestr(filename, content) except OSError: self.fail('Could not append data to a non-existent zip file.') self.assertTrue(os.path.exists(TESTFN)) with zipfile.ZipFile(TESTFN, 'r') as zf: self.assertEqual(zf.read(filename), content) def test_close_erroneous_file(self): # This test checks that the ZipFile constructor closes the file object # it opens if there's an error in the file. If it doesn't, the # traceback holds a reference to the ZipFile object and, indirectly, # the file object. # On Windows, this causes the os.unlink() call to fail because the # underlying file is still open. This is SF bug #412214. # with open(TESTFN, "w", encoding="utf-8") as fp: fp.write("this is not a legal zip file\n") try: zf = zipfile.ZipFile(TESTFN) except zipfile.BadZipFile: pass def test_is_zip_erroneous_file(self): """Check that is_zipfile() correctly identifies non-zip files.""" # - passing a filename with open(TESTFN, "w", encoding='utf-8') as fp: fp.write("this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(TESTFN)) # - passing a path-like object self.assertFalse(zipfile.is_zipfile(pathlib.Path(TESTFN))) # - passing a file object with open(TESTFN, "rb") as fp: self.assertFalse(zipfile.is_zipfile(fp)) # - passing a file-like object fp = io.BytesIO() fp.write(b"this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertFalse(zipfile.is_zipfile(fp)) def test_damaged_zipfile(self): """Check that zipfiles with missing bytes at the end raise BadZipFile.""" # - Create a valid zip file fp = io.BytesIO() with zipfile.ZipFile(fp, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") zipfiledata = fp.getvalue() # - Now create copies of it missing the last N bytes and make sure # a BadZipFile exception is raised when we try to open it for N in range(len(zipfiledata)): fp = io.BytesIO(zipfiledata[:N]) self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, fp) def test_is_zip_valid_file(self): """Check that is_zipfile() correctly identifies zip files.""" # - passing a filename with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") self.assertTrue(zipfile.is_zipfile(TESTFN)) # - passing a file object with open(TESTFN, "rb") as fp: self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) zip_contents = fp.read() # - passing a file-like object fp = io.BytesIO() fp.write(zip_contents) self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertTrue(zipfile.is_zipfile(fp)) def test_non_existent_file_raises_OSError(self): # make sure we don't raise an AttributeError when a partially-constructed # ZipFile instance is finalized; this tests for regression on SF tracker # bug #403871. # The bug we're testing for caused an AttributeError to be raised # when a ZipFile instance was created for a file that did not # exist; the .fp member was not initialized but was needed by the # __del__() method. Since the AttributeError is in the __del__(), # it is ignored, but the user should be sufficiently annoyed by # the message on the output that regression will be noticed # quickly. self.assertRaises(OSError, zipfile.ZipFile, TESTFN) def test_empty_file_raises_BadZipFile(self): f = open(TESTFN, 'w', encoding='utf-8') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) with open(TESTFN, 'w', encoding='utf-8') as fp: fp.write("short file") self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) def test_closed_zip_raises_ValueError(self): """Verify that testzip() doesn't swallow inappropriate exceptions.""" data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # This is correct; calling .read on a closed ZipFile should raise # a ValueError, and so should calling .testzip. An earlier # version of .testzip would swallow this exception (and any other) # and report that the first file in the archive was corrupt. self.assertRaises(ValueError, zipf.read, "foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt") self.assertRaises(ValueError, zipf.testzip) self.assertRaises(ValueError, zipf.writestr, "bogus.txt", "bogus") with open(TESTFN, 'w', encoding='utf-8') as f: f.write('zipfile test data') self.assertRaises(ValueError, zipf.write, TESTFN) def test_bad_constructor_mode(self): """Check that bad modes passed to ZipFile constructor are caught.""" self.assertRaises(ValueError, zipfile.ZipFile, TESTFN, "q") def test_bad_open_mode(self): """Check that bad modes passed to ZipFile.open are caught.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipf: # read the data to make sure the file is there zipf.read("foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt", "q") # universal newlines support is removed self.assertRaises(ValueError, zipf.open, "foo.txt", "U") self.assertRaises(ValueError, zipf.open, "foo.txt", "rU") def test_read0(self): """Check that calling read(0) on a ZipExtFile object returns an empty string and doesn't advance file pointer.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # read the data to make sure the file is there with zipf.open("foo.txt") as f: for i in range(FIXEDTEST_SIZE): self.assertEqual(f.read(0), b'') self.assertEqual(f.read(), b"O, for a Muse of Fire!") def test_open_non_existent_item(self): """Check that attempting to call open() for an item that doesn't exist in the archive raises a RuntimeError.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertRaises(KeyError, zipf.open, "foo.txt", "r") def test_bad_compression_mode(self): """Check that bad compression methods passed to ZipFile.open are caught.""" self.assertRaises(NotImplementedError, zipfile.ZipFile, TESTFN, "w", -1) def test_unsupported_compression(self): # data is declared as shrunk, but actually deflated data = (b'PK\x03\x04.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00' b'\x00\x02\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00x\x03\x00PK\x01' b'\x02.\x03.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00\x00\x02\x00\x00' b'\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00' b'\x80\x01\x00\x00\x00\x00xPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x00' b'/\x00\x00\x00!\x00\x00\x00\x00\x00') with zipfile.ZipFile(io.BytesIO(data), 'r') as zipf: self.assertRaises(NotImplementedError, zipf.open, 'x') def test_null_byte_in_filename(self): """Check that a filename containing a null byte is properly terminated.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt\x00qqq", b"O, for a Muse of Fire!") self.assertEqual(zipf.namelist(), ['foo.txt']) def test_struct_sizes(self): """Check that ZIP internal structure sizes are calculated correctly.""" self.assertEqual(zipfile.sizeEndCentDir, 22) self.assertEqual(zipfile.sizeCentralDir, 46) self.assertEqual(zipfile.sizeEndCentDir64, 56) self.assertEqual(zipfile.sizeEndCentDir64Locator, 20) def test_comments(self): """Check that comments on the archive are handled properly.""" # check default comment is empty with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertEqual(zipf.comment, b'') zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, b'') # check a simple short comment comment = b'Bravely taking to his feet, he beat a very brave retreat.' with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipf.comment, comment) # check a comment of max length comment2 = ''.join(['%d' % (i**3 % 10) for i in range((1 << 16)-1)]) comment2 = comment2.encode("ascii") with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment2 zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check a comment that is too long is truncated with zipfile.ZipFile(TESTFN, mode="w") as zipf: with self.assertWarns(UserWarning): zipf.comment = comment2 + b'oops' zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check that comments are correctly modified in append mode with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"an updated comment" with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"an updated comment") # check that comments are correctly shortened in append mode # and the file is indeed truncated with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment that's longer" zipf.writestr("foo.txt", "O, for a Muse of Fire!") original_zip_size = os.path.getsize(TESTFN) with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"shorter comment" self.assertTrue(original_zip_size > os.path.getsize(TESTFN)) with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"shorter comment") def test_unicode_comment(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with self.assertRaises(TypeError): zipf.comment = "this is an error" def test_change_comment_in_empty_archive(self): with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertFalse(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_change_comment_in_nonempty_archive(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertTrue(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_empty_zipfile(self): # Check that creating a file in 'w' or 'a' mode and closing without # adding any files to the archives creates a valid empty ZIP file zipf = zipfile.ZipFile(TESTFN, mode="w") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except zipfile.BadZipFile: self.fail("Unable to create empty ZIP file in 'w' mode") zipf = zipfile.ZipFile(TESTFN, mode="a") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except: self.fail("Unable to create empty ZIP file in 'a' mode") def test_open_empty_file(self): # Issue 1710703: Check that opening a file with less than 22 bytes # raises a BadZipFile exception (rather than the previously unhelpful # OSError) f = open(TESTFN, 'w', encoding='utf-8') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN, 'r') def test_create_zipinfo_before_1980(self): self.assertRaises(ValueError, zipfile.ZipInfo, 'seventies', (1979, 1, 1, 0, 0, 0)) def test_create_empty_zipinfo_repr(self): """Before bpo-26185, repr() on empty ZipInfo object was failing.""" zi = zipfile.ZipInfo(filename="empty") self.assertEqual(repr(zi), "") def test_create_empty_zipinfo_default_attributes(self): """Ensure all required attributes are set.""" zi = zipfile.ZipInfo() self.assertEqual(zi.orig_filename, "NoName") self.assertEqual(zi.filename, "NoName") self.assertEqual(zi.date_time, (1980, 1, 1, 0, 0, 0)) self.assertEqual(zi.compress_type, zipfile.ZIP_STORED) self.assertEqual(zi.comment, b"") self.assertEqual(zi.extra, b"") self.assertIn(zi.create_system, (0, 3)) self.assertEqual(zi.create_version, zipfile.DEFAULT_VERSION) self.assertEqual(zi.extract_version, zipfile.DEFAULT_VERSION) self.assertEqual(zi.reserved, 0) self.assertEqual(zi.flag_bits, 0) self.assertEqual(zi.volume, 0) self.assertEqual(zi.internal_attr, 0) self.assertEqual(zi.external_attr, 0) # Before bpo-26185, both were missing self.assertEqual(zi.file_size, 0) self.assertEqual(zi.compress_size, 0) def test_zipfile_with_short_extra_field(self): """If an extra field in the header is less than 4 bytes, skip it.""" zipdata = ( b'PK\x03\x04\x14\x00\x00\x00\x00\x00\x93\x9b\xad@\x8b\x9e' b'\xd9\xd3\x01\x00\x00\x00\x01\x00\x00\x00\x03\x00\x03\x00ab' b'c\x00\x00\x00APK\x01\x02\x14\x03\x14\x00\x00\x00\x00' b'\x00\x93\x9b\xad@\x8b\x9e\xd9\xd3\x01\x00\x00\x00\x01\x00\x00' b'\x00\x03\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x81\x00' b'\x00\x00\x00abc\x00\x00PK\x05\x06\x00\x00\x00\x00' b'\x01\x00\x01\x003\x00\x00\x00%\x00\x00\x00\x00\x00' ) with zipfile.ZipFile(io.BytesIO(zipdata), 'r') as zipf: # testzip returns the name of the first corrupt file, or None self.assertIsNone(zipf.testzip()) def test_open_conflicting_handles(self): # It's only possible to open one writable file handle at a time msg1 = b"It's fun to charter an accountant!" msg2 = b"And sail the wide accountant sea" msg3 = b"To find, explore the funds offshore" with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipf: with zipf.open('foo', mode='w') as w2: w2.write(msg1) with zipf.open('bar', mode='w') as w1: with self.assertRaises(ValueError): zipf.open('handle', mode='w') with self.assertRaises(ValueError): zipf.open('foo', mode='r') with self.assertRaises(ValueError): zipf.writestr('str', 'abcde') with self.assertRaises(ValueError): zipf.write(__file__, 'file') with self.assertRaises(ValueError): zipf.close() w1.write(msg2) with zipf.open('baz', mode='w') as w2: w2.write(msg3) with zipfile.ZipFile(TESTFN2, 'r') as zipf: self.assertEqual(zipf.read('foo'), msg1) self.assertEqual(zipf.read('bar'), msg2) self.assertEqual(zipf.read('baz'), msg3) self.assertEqual(zipf.namelist(), ['foo', 'bar', 'baz']) def test_seek_tell(self): # Test seek functionality txt = b"Where's Bruce?" bloc = txt.find(b"Bruce") # Check seek on a file with zipfile.ZipFile(TESTFN, "w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(TESTFN, "r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Check seek on memory file data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(data, mode="r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) @requires_bz2() def test_decompress_without_3rd_party_library(self): data = b'PK\x05\x06\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00' zip_file = io.BytesIO(data) with zipfile.ZipFile(zip_file, 'w', compression=zipfile.ZIP_BZIP2) as zf: zf.writestr('a.txt', b'a') with mock.patch('zipfile.bz2', None): with zipfile.ZipFile(zip_file) as zf: self.assertRaises(RuntimeError, zf.extract, 'a.txt') def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class AbstractBadCrcTests: def test_testzip_with_bad_crc(self): """Tests that files with bad CRCs return their name from testzip.""" zipdata = self.zip_with_bad_crc with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: # testzip returns the name of the first corrupt file, or None self.assertEqual('afile', zipf.testzip()) def test_read_with_bad_crc(self): """Tests that files with bad CRCs raise a BadZipFile exception when read.""" zipdata = self.zip_with_bad_crc # Using ZipFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: self.assertRaises(zipfile.BadZipFile, zipf.read, 'afile') # Using ZipExtFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: self.assertRaises(zipfile.BadZipFile, corrupt_file.read) # Same with small reads (in order to exercise the buffering logic) with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: corrupt_file.MIN_READ_SIZE = 2 with self.assertRaises(zipfile.BadZipFile): while corrupt_file.read(2): pass class StoredBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_STORED zip_with_bad_crc = ( b'PK\003\004\024\0\0\0\0\0 \213\212;:r' b'\253\377\f\0\0\0\f\0\0\0\005\0\0\000af' b'ilehello,AworldP' b'K\001\002\024\003\024\0\0\0\0\0 \213\212;:' b'r\253\377\f\0\0\0\f\0\0\0\005\0\0\0\0' b'\0\0\0\0\0\0\0\200\001\0\0\0\000afi' b'lePK\005\006\0\0\0\0\001\0\001\0003\000' b'\0\0/\0\0\0\0\0') @requires_zlib() class DeflateBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_DEFLATED zip_with_bad_crc = ( b'PK\x03\x04\x14\x00\x00\x00\x08\x00n}\x0c=FA' b'KE\x10\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\xc9\xa0' b'=\x13\x00PK\x01\x02\x14\x03\x14\x00\x00\x00\x08\x00n' b'}\x0c=FAKE\x10\x00\x00\x00n\x00\x00\x00\x05' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00' b'\x00afilePK\x05\x06\x00\x00\x00\x00\x01\x00' b'\x01\x003\x00\x00\x003\x00\x00\x00\x00\x00') @requires_bz2() class Bzip2BadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_BZIP2 zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0c\x00nu\x0c=FA' b'KE8\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ileBZh91AY&SY\xd4\xa8\xca' b'\x7f\x00\x00\x0f\x11\x80@\x00\x06D\x90\x80 \x00 \xa5' b'P\xd9!\x03\x03\x13\x13\x13\x89\xa9\xa9\xc2u5:\x9f' b'\x8b\xb9"\x9c(HjTe?\x80PK\x01\x02\x14' b'\x03\x14\x03\x00\x00\x0c\x00nu\x0c=FAKE8' b'\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00' b'\x00 \x80\x80\x81\x00\x00\x00\x00afilePK' b'\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00\x00[\x00' b'\x00\x00\x00\x00') @requires_lzma() class LzmaBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_LZMA zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\t\x04\x05\x00]\x00\x00\x00\x04\x004\x19I' b'\xee\x8d\xe9\x17\x89:3`\tq!.8\x00PK' b'\x01\x02\x14\x03\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00 \x80\x80\x81\x00\x00\x00\x00afil' b'ePK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00' b'\x00>\x00\x00\x00\x00\x00') class DecryptionTests(unittest.TestCase): """Check that ZIP decryption works. Since the library does not support encryption at the moment, we use a pre-generated encrypted ZIP file.""" data = ( b'PK\x03\x04\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00\x1a\x00' b'\x00\x00\x08\x00\x00\x00test.txt\xfa\x10\xa0gly|\xfa-\xc5\xc0=\xf9y' b'\x18\xe0\xa8r\xb3Z}Lg\xbc\xae\xf9|\x9b\x19\xe4\x8b\xba\xbb)\x8c\xb0\xdbl' b'PK\x01\x02\x14\x00\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00' b'\x1a\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x01\x00 \x00\xb6\x81' b'\x00\x00\x00\x00test.txtPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x006\x00' b'\x00\x00L\x00\x00\x00\x00\x00' ) data2 = ( b'PK\x03\x04\x14\x00\t\x00\x08\x00\xcf}38xu\xaa\xb2\x14\x00\x00\x00\x00\x02' b'\x00\x00\x04\x00\x15\x00zeroUT\t\x00\x03\xd6\x8b\x92G\xda\x8b\x92GUx\x04' b'\x00\xe8\x03\xe8\x03\xc7