1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | Lib/test/test_gzip.py
"""Test script for the gzip module. """ import unittest from test import test_support import os import io import struct gzip = test_support.import_module('gzip') data1 = """ int length=DEFAULTALLOC, err = Z_OK; PyObject *RetVal; int flushmode = Z_FINISH; unsigned long start_total_out; """ data2 = """/* zlibmodule.c -- gzip-compatible data compression */ /* See http://www.gzip.org/zlib/ /* See http://www.winimage.com/zLibDll for Windows */ """ class TestGzip(unittest.TestCase): filename = test_support.TESTFN def setUp(self): test_support.unlink(self.filename) def tearDown(self): test_support.unlink(self.filename) def write_and_read_back(self, data, mode='b'): b_data = memoryview(data).tobytes() with gzip.GzipFile(self.filename, 'w'+mode) as f: l = f.write(data) self.assertEqual(l, len(b_data)) with gzip.GzipFile(self.filename, 'r'+mode) as f: self.assertEqual(f.read(), b_data) @test_support.requires_unicode def test_unicode_filename(self): unicode_filename = test_support.TESTFN_UNICODE try: unicode_filename.encode(test_support.TESTFN_ENCODING) except (UnicodeError, TypeError): self.skipTest("Requires unicode filenames support") self.filename = unicode_filename with gzip.GzipFile(unicode_filename, "wb") as f: f.write(data1 * 50) with gzip.GzipFile(unicode_filename, "rb") as f: self.assertEqual(f.read(), data1 * 50) # Sanity check that we are actually operating on the right file. with open(unicode_filename, 'rb') as fobj, \ gzip.GzipFile(fileobj=fobj, mode="rb") as f: self.assertEqual(f.read(), data1 * 50) def test_write(self): with gzip.GzipFile(self.filename, 'wb') as f: f.write(data1 * 50) # Try flush and fileno. f.flush() f.fileno() if hasattr(os, 'fsync'): os.fsync(f.fileno()) f.close() # Test multiple close() calls. f.close() # The following test_write_xy methods test that write accepts # the corresponding bytes-like object type as input # and that the data written equals bytes(xy) in all cases. def test_write_memoryview(self): self.write_and_read_back(memoryview(data1 * 50)) def test_write_incompatible_type(self): # Test that non-bytes-like types raise TypeError. # Issue #21560: attempts to write incompatible types # should not affect the state of the fileobject with gzip.GzipFile(self.filename, 'wb') as f: with self.assertRaises(UnicodeEncodeError): f.write(u'\xff') with self.assertRaises(TypeError): f.write([1]) f.write(data1) with gzip.GzipFile(self.filename, 'rb') as f: self.assertEqual(f.read(), data1) def test_read(self): self.test_write() # Try reading. with gzip.GzipFile(self.filename, 'r') as f: d = f.read() self.assertEqual(d, data1*50) def test_read_universal_newlines(self): # Issue #5148: Reading breaks when mode contains 'U'. self.test_write() with gzip.GzipFile(self.filename, 'rU') as f: d = f.read() self.assertEqual(d, data1*50) def test_io_on_closed_object(self): # Test that I/O operations on closed GzipFile objects raise a # ValueError, just like the corresponding functions on file objects. # Write to a file, open it for reading, then close it. self.test_write() f = gzip.GzipFile(self.filename, 'r') f.close() with self.assertRaises(ValueError): f.read(1) with self.assertRaises(ValueError): f.seek(0) with self.assertRaises(ValueError): f.tell() # Open the file for writing, then close it. f = gzip.GzipFile(self.filename, 'w') f.close() with self.assertRaises(ValueError): f.write('') with self.assertRaises(ValueError): f.flush() def test_append(self): self.test_write() # Append to the previous file with gzip.GzipFile(self.filename, 'ab') as f: f.write(data2 * 15) with gzip.GzipFile(self.filename, 'rb') as f: d = f.read() self.assertEqual(d, (data1*50) + (data2*15)) def test_many_append(self): # Bug #1074261 was triggered when reading a file that contained # many, many members. Create such a file and verify that reading it # works. with gzip.open(self.filename, 'wb', 9) as f: f.write('a') for i in range(0, 200): with gzip.open(self.filename, "ab", 9) as f: # append f.write('a') # Try reading the file with gzip.open(self.filename, "rb") as zgfile: contents = "" while 1: ztxt = zgfile.read(8192) contents += ztxt if not ztxt: break self.assertEqual(contents, 'a'*201) def test_buffered_reader(self): # Issue #7471: a GzipFile can be wrapped in a BufferedReader for # performance. self.test_write() with gzip.GzipFile(self.filename, 'rb') as f: with io.BufferedReader(f) as r: lines = [line for line in r] self.assertEqual(lines, 50 * data1.splitlines(True)) def test_readline(self): self.test_write() # Try .readline() with varying line lengths with gzip.GzipFile(self.filename, 'rb') as f: line_length = 0 while 1: L = f.readline(line_length) if not L and line_length != 0: break self.assertTrue(len(L) <= line_length) line_length = (line_length + 1) % 50 def test_readlines(self): self.test_write() # Try .readlines() with gzip.GzipFile(self.filename, 'rb') as f: L = f.readlines() with gzip.GzipFile(self.filename, 'rb') as f: while 1: L = f.readlines(150) if L == []: break def test_seek_read(self): self.test_write() # Try seek, read test with gzip.GzipFile(self.filename) as f: while 1: oldpos = f.tell() line1 = f.readline() if not line1: break newpos = f.tell() f.seek(oldpos) # negative seek if len(line1)>10: amount = 10 else: amount = len(line1) line2 = f.read(amount) self.assertEqual(line1[:amount], line2) f.seek(newpos) # positive seek def test_seek_whence(self): self.test_write() # Try seek(whence=1), read test with gzip.GzipFile(self.filename) as f: f.read(10) f.seek(10, whence=1) y = f.read(10) self.assertEqual(y, data1[20:30]) def test_seek_write(self): # Try seek, write test with gzip.GzipFile(self.filename, 'w') as f: for pos in range(0, 256, 16): f.seek(pos) f.write('GZ\n') def test_mode(self): self.test_write() with gzip.GzipFile(self.filename, 'r') as f: self.assertEqual(f.myfileobj.mode, 'rb') def test_1647484(self): for mode in ('wb', 'rb'): with gzip.GzipFile(self.filename, mode) as f: self.assertTrue(hasattr(f, "name")) self.assertEqual(f.name, self.filename) def test_mtime(self): mtime = 123456789 with gzip.GzipFile(self.filename, 'w', mtime = mtime) as fWrite: fWrite.write(data1) with gzip.GzipFile(self.filename) as fRead: dataRead = fRead.read() self.assertEqual(dataRead, data1) self.assertTrue(hasattr(fRead, 'mtime')) self.assertEqual(fRead.mtime, mtime) def test_metadata(self): mtime = 123456789 with gzip.GzipFile(self.filename, 'w', mtime = mtime) as fWrite: fWrite.write(data1) with open(self.filename, 'rb') as fRead: # see RFC 1952: http://www.faqs.org/rfcs/rfc1952.html idBytes = fRead.read(2) self.assertEqual(idBytes, '\x1f\x8b') # gzip ID cmByte = fRead.read(1) self.assertEqual(cmByte, '\x08') # deflate flagsByte = fRead.read(1) self.assertEqual(flagsByte, '\x08') # only the FNAME flag is set mtimeBytes = fRead.read(4) self.assertEqual(mtimeBytes, struct.pack('<i', mtime)) # little-endian xflByte = fRead.read(1) self.assertEqual(xflByte, '\x02') # maximum compression osByte = fRead.read(1) self.assertEqual(osByte, '\xff') # OS "unknown" (OS-independent) # Since the FNAME flag is set, the zero-terminated filename follows. # RFC 1952 specifies that this is the name of the input file, if any. # However, the gzip module defaults to storing the name of the output # file in this field. expected = self.filename.encode('Latin-1') + '\x00' nameBytes = fRead.read(len(expected)) self.assertEqual(nameBytes, expected) # Since no other flags were set, the header ends here. # Rather than process the compressed data, let's seek to the trailer. fRead.seek(os.stat(self.filename).st_size - 8) crc32Bytes = fRead.read(4) # CRC32 of uncompressed data [data1] self.assertEqual(crc32Bytes, '\xaf\xd7d\x83') isizeBytes = fRead.read(4) self.assertEqual(isizeBytes, struct.pack('<i', len(data1))) def test_with_open(self): # GzipFile supports the context management protocol with gzip.GzipFile(self.filename, "wb") as f: f.write(b"xxx") f = gzip.GzipFile(self.filename, "rb") f.close() try: with f: pass except ValueError: pass else: self.fail("__enter__ on a closed file didn't raise an exception") try: with gzip.GzipFile(self.filename, "wb") as f: 1 // 0 except ZeroDivisionError: pass else: self.fail("1 // 0 didn't raise an exception") def test_zero_padded_file(self): with gzip.GzipFile(self.filename, "wb") as f: f.write(data1 * 50) # Pad the file with zeroes with open(self.filename, "ab") as f: f.write("\x00" * 50) with gzip.GzipFile(self.filename, "rb") as f: d = f.read() self.assertEqual(d, data1 * 50, "Incorrect data in file") def test_fileobj_from_fdopen(self): # Issue #13781: Creating a GzipFile using a fileobj from os.fdopen() # should not embed the fake filename "<fdopen>" in the output file. fd = os.open(self.filename, os.O_WRONLY | os.O_CREAT) with os.fdopen(fd, "wb") as f: with gzip.GzipFile(fileobj=f, mode="w") as g: self.assertEqual(g.name, "") def test_read_with_extra(self): # Gzip data with an extra field gzdata = (b'\x1f\x8b\x08\x04\xb2\x17cQ\x02\xff' b'\x05\x00Extra' b'\x0bI-.\x01\x002\xd1Mx\x04\x00\x00\x00') with gzip.GzipFile(fileobj=io.BytesIO(gzdata)) as f: self.assertEqual(f.read(), b'Test') def test_main(verbose=None): test_support.run_unittest(TestGzip) if __name__ == "__main__": test_main(verbose=True) |