|
1 """ |
|
2 Read and write ZIP files. |
|
3 """ |
|
4 import struct, os, time, sys |
|
5 import binascii, cStringIO |
|
6 |
|
7 try: |
|
8 import zlib # We may need its compression method |
|
9 except ImportError: |
|
10 zlib = None |
|
11 |
|
12 __all__ = ["BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "is_zipfile", |
|
13 "ZipInfo", "ZipFile", "PyZipFile", "LargeZipFile" ] |
|
14 |
|
15 class BadZipfile(Exception): |
|
16 pass |
|
17 |
|
18 |
|
19 class LargeZipFile(Exception): |
|
20 """ |
|
21 Raised when writing a zipfile, the zipfile requires ZIP64 extensions |
|
22 and those extensions are disabled. |
|
23 """ |
|
24 |
|
25 error = BadZipfile # The exception raised by this module |
|
26 |
|
27 ZIP64_LIMIT= (1 << 31) - 1 |
|
28 |
|
29 # constants for Zip file compression methods |
|
30 ZIP_STORED = 0 |
|
31 ZIP_DEFLATED = 8 |
|
32 # Other ZIP compression methods not supported |
|
33 |
|
34 # Here are some struct module formats for reading headers |
|
35 structEndArchive = "<4s4H2LH" # 9 items, end of archive, 22 bytes |
|
36 stringEndArchive = "PK\005\006" # magic number for end of archive record |
|
37 structCentralDir = "<4s4B4HlLL5HLL"# 19 items, central directory, 46 bytes |
|
38 stringCentralDir = "PK\001\002" # magic number for central directory |
|
39 structFileHeader = "<4s2B4HlLL2H" # 12 items, file header record, 30 bytes |
|
40 stringFileHeader = "PK\003\004" # magic number for file header |
|
41 structEndArchive64Locator = "<4slql" # 4 items, locate Zip64 header, 20 bytes |
|
42 stringEndArchive64Locator = "PK\x06\x07" # magic token for locator header |
|
43 structEndArchive64 = "<4sqhhllqqqq" # 10 items, end of archive (Zip64), 56 bytes |
|
44 stringEndArchive64 = "PK\x06\x06" # magic token for Zip64 header |
|
45 |
|
46 |
|
47 # indexes of entries in the central directory structure |
|
48 _CD_SIGNATURE = 0 |
|
49 _CD_CREATE_VERSION = 1 |
|
50 _CD_CREATE_SYSTEM = 2 |
|
51 _CD_EXTRACT_VERSION = 3 |
|
52 _CD_EXTRACT_SYSTEM = 4 # is this meaningful? |
|
53 _CD_FLAG_BITS = 5 |
|
54 _CD_COMPRESS_TYPE = 6 |
|
55 _CD_TIME = 7 |
|
56 _CD_DATE = 8 |
|
57 _CD_CRC = 9 |
|
58 _CD_COMPRESSED_SIZE = 10 |
|
59 _CD_UNCOMPRESSED_SIZE = 11 |
|
60 _CD_FILENAME_LENGTH = 12 |
|
61 _CD_EXTRA_FIELD_LENGTH = 13 |
|
62 _CD_COMMENT_LENGTH = 14 |
|
63 _CD_DISK_NUMBER_START = 15 |
|
64 _CD_INTERNAL_FILE_ATTRIBUTES = 16 |
|
65 _CD_EXTERNAL_FILE_ATTRIBUTES = 17 |
|
66 _CD_LOCAL_HEADER_OFFSET = 18 |
|
67 |
|
68 # indexes of entries in the local file header structure |
|
69 _FH_SIGNATURE = 0 |
|
70 _FH_EXTRACT_VERSION = 1 |
|
71 _FH_EXTRACT_SYSTEM = 2 # is this meaningful? |
|
72 _FH_GENERAL_PURPOSE_FLAG_BITS = 3 |
|
73 _FH_COMPRESSION_METHOD = 4 |
|
74 _FH_LAST_MOD_TIME = 5 |
|
75 _FH_LAST_MOD_DATE = 6 |
|
76 _FH_CRC = 7 |
|
77 _FH_COMPRESSED_SIZE = 8 |
|
78 _FH_UNCOMPRESSED_SIZE = 9 |
|
79 _FH_FILENAME_LENGTH = 10 |
|
80 _FH_EXTRA_FIELD_LENGTH = 11 |
|
81 |
|
82 def is_zipfile(filename): |
|
83 """Quickly see if file is a ZIP file by checking the magic number.""" |
|
84 try: |
|
85 fpin = open(filename, "rb") |
|
86 endrec = _EndRecData(fpin) |
|
87 fpin.close() |
|
88 if endrec: |
|
89 return True # file has correct magic number |
|
90 except IOError: |
|
91 pass |
|
92 return False |
|
93 |
|
94 def _EndRecData64(fpin, offset, endrec): |
|
95 """ |
|
96 Read the ZIP64 end-of-archive records and use that to update endrec |
|
97 """ |
|
98 locatorSize = struct.calcsize(structEndArchive64Locator) |
|
99 fpin.seek(offset - locatorSize, 2) |
|
100 data = fpin.read(locatorSize) |
|
101 sig, diskno, reloff, disks = struct.unpack(structEndArchive64Locator, data) |
|
102 if sig != stringEndArchive64Locator: |
|
103 return endrec |
|
104 |
|
105 if diskno != 0 or disks != 1: |
|
106 raise BadZipfile("zipfiles that span multiple disks are not supported") |
|
107 |
|
108 # Assume no 'zip64 extensible data' |
|
109 endArchiveSize = struct.calcsize(structEndArchive64) |
|
110 fpin.seek(offset - locatorSize - endArchiveSize, 2) |
|
111 data = fpin.read(endArchiveSize) |
|
112 sig, sz, create_version, read_version, disk_num, disk_dir, \ |
|
113 dircount, dircount2, dirsize, diroffset = \ |
|
114 struct.unpack(structEndArchive64, data) |
|
115 if sig != stringEndArchive64: |
|
116 return endrec |
|
117 |
|
118 # Update the original endrec using data from the ZIP64 record |
|
119 endrec[1] = disk_num |
|
120 endrec[2] = disk_dir |
|
121 endrec[3] = dircount |
|
122 endrec[4] = dircount2 |
|
123 endrec[5] = dirsize |
|
124 endrec[6] = diroffset |
|
125 return endrec |
|
126 |
|
127 |
|
128 def _EndRecData(fpin): |
|
129 """Return data from the "End of Central Directory" record, or None. |
|
130 |
|
131 The data is a list of the nine items in the ZIP "End of central dir" |
|
132 record followed by a tenth item, the file seek offset of this record.""" |
|
133 fpin.seek(-22, 2) # Assume no archive comment. |
|
134 filesize = fpin.tell() + 22 # Get file size |
|
135 data = fpin.read() |
|
136 if data[0:4] == stringEndArchive and data[-2:] == "\000\000": |
|
137 endrec = struct.unpack(structEndArchive, data) |
|
138 endrec = list(endrec) |
|
139 endrec.append("") # Append the archive comment |
|
140 endrec.append(filesize - 22) # Append the record start offset |
|
141 if endrec[-4] == -1 or endrec[-4] == 0xffffffff: |
|
142 return _EndRecData64(fpin, -22, endrec) |
|
143 return endrec |
|
144 # Search the last END_BLOCK bytes of the file for the record signature. |
|
145 # The comment is appended to the ZIP file and has a 16 bit length. |
|
146 # So the comment may be up to 64K long. We limit the search for the |
|
147 # signature to a few Kbytes at the end of the file for efficiency. |
|
148 # also, the signature must not appear in the comment. |
|
149 END_BLOCK = min(filesize, 1024 * 4) |
|
150 fpin.seek(filesize - END_BLOCK, 0) |
|
151 data = fpin.read() |
|
152 start = data.rfind(stringEndArchive) |
|
153 if start >= 0: # Correct signature string was found |
|
154 endrec = struct.unpack(structEndArchive, data[start:start+22]) |
|
155 endrec = list(endrec) |
|
156 comment = data[start+22:] |
|
157 if endrec[7] == len(comment): # Comment length checks out |
|
158 # Append the archive comment and start offset |
|
159 endrec.append(comment) |
|
160 endrec.append(filesize - END_BLOCK + start) |
|
161 if endrec[-4] == -1 or endrec[-4] == 0xffffffff: |
|
162 return _EndRecData64(fpin, - END_BLOCK + start, endrec) |
|
163 return endrec |
|
164 return # Error, return None |
|
165 |
|
166 |
|
167 class ZipInfo (object): |
|
168 """Class with attributes describing each file in the ZIP archive.""" |
|
169 |
|
170 __slots__ = ( |
|
171 'orig_filename', |
|
172 'filename', |
|
173 'date_time', |
|
174 'compress_type', |
|
175 'comment', |
|
176 'extra', |
|
177 'create_system', |
|
178 'create_version', |
|
179 'extract_version', |
|
180 'reserved', |
|
181 'flag_bits', |
|
182 'volume', |
|
183 'internal_attr', |
|
184 'external_attr', |
|
185 'header_offset', |
|
186 'CRC', |
|
187 'compress_size', |
|
188 'file_size', |
|
189 ) |
|
190 |
|
191 def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)): |
|
192 self.orig_filename = filename # Original file name in archive |
|
193 |
|
194 # Terminate the file name at the first null byte. Null bytes in file |
|
195 # names are used as tricks by viruses in archives. |
|
196 null_byte = filename.find(chr(0)) |
|
197 if null_byte >= 0: |
|
198 filename = filename[0:null_byte] |
|
199 # This is used to ensure paths in generated ZIP files always use |
|
200 # forward slashes as the directory separator, as required by the |
|
201 # ZIP format specification. |
|
202 if os.sep != "/" and os.sep in filename: |
|
203 filename = filename.replace(os.sep, "/") |
|
204 |
|
205 self.filename = filename # Normalized file name |
|
206 self.date_time = date_time # year, month, day, hour, min, sec |
|
207 # Standard values: |
|
208 self.compress_type = ZIP_STORED # Type of compression for the file |
|
209 self.comment = "" # Comment for each file |
|
210 self.extra = "" # ZIP extra data |
|
211 if sys.platform == 'win32': |
|
212 self.create_system = 0 # System which created ZIP archive |
|
213 else: |
|
214 # Assume everything else is unix-y |
|
215 self.create_system = 3 # System which created ZIP archive |
|
216 self.create_version = 20 # Version which created ZIP archive |
|
217 self.extract_version = 20 # Version needed to extract archive |
|
218 self.reserved = 0 # Must be zero |
|
219 self.flag_bits = 0 # ZIP flag bits |
|
220 self.volume = 0 # Volume number of file header |
|
221 self.internal_attr = 0 # Internal attributes |
|
222 self.external_attr = 0 # External file attributes |
|
223 # Other attributes are set by class ZipFile: |
|
224 # header_offset Byte offset to the file header |
|
225 # CRC CRC-32 of the uncompressed file |
|
226 # compress_size Size of the compressed file |
|
227 # file_size Size of the uncompressed file |
|
228 |
|
229 def FileHeader(self): |
|
230 """Return the per-file header as a string.""" |
|
231 dt = self.date_time |
|
232 dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2] |
|
233 dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2) |
|
234 if self.flag_bits & 0x08: |
|
235 # Set these to zero because we write them after the file data |
|
236 CRC = compress_size = file_size = 0 |
|
237 else: |
|
238 CRC = self.CRC |
|
239 compress_size = self.compress_size |
|
240 file_size = self.file_size |
|
241 |
|
242 extra = self.extra |
|
243 |
|
244 if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT: |
|
245 # File is larger than what fits into a 4 byte integer, |
|
246 # fall back to the ZIP64 extension |
|
247 fmt = '<hhqq' |
|
248 extra = extra + struct.pack(fmt, |
|
249 1, struct.calcsize(fmt)-4, file_size, compress_size) |
|
250 file_size = 0xffffffff # -1 |
|
251 compress_size = 0xffffffff # -1 |
|
252 self.extract_version = max(45, self.extract_version) |
|
253 self.create_version = max(45, self.extract_version) |
|
254 |
|
255 header = struct.pack(structFileHeader, stringFileHeader, |
|
256 self.extract_version, self.reserved, self.flag_bits, |
|
257 self.compress_type, dostime, dosdate, CRC, |
|
258 compress_size, file_size, |
|
259 len(self.filename), len(extra)) |
|
260 return header + self.filename + extra |
|
261 |
|
262 def _decodeExtra(self): |
|
263 # Try to decode the extra field. |
|
264 extra = self.extra |
|
265 unpack = struct.unpack |
|
266 while extra: |
|
267 tp, ln = unpack('<hh', extra[:4]) |
|
268 if tp == 1: |
|
269 if ln >= 24: |
|
270 counts = unpack('<qqq', extra[4:28]) |
|
271 elif ln == 16: |
|
272 counts = unpack('<qq', extra[4:20]) |
|
273 elif ln == 8: |
|
274 counts = unpack('<q', extra[4:12]) |
|
275 elif ln == 0: |
|
276 counts = () |
|
277 else: |
|
278 raise RuntimeError, "Corrupt extra field %s"%(ln,) |
|
279 |
|
280 idx = 0 |
|
281 |
|
282 # ZIP64 extension (large files and/or large archives) |
|
283 if self.file_size == -1 or self.file_size == 0xFFFFFFFFL: |
|
284 self.file_size = counts[idx] |
|
285 idx += 1 |
|
286 |
|
287 if self.compress_size == -1 or self.compress_size == 0xFFFFFFFFL: |
|
288 self.compress_size = counts[idx] |
|
289 idx += 1 |
|
290 |
|
291 if self.header_offset == -1 or self.header_offset == 0xffffffffL: |
|
292 old = self.header_offset |
|
293 self.header_offset = counts[idx] |
|
294 idx+=1 |
|
295 |
|
296 extra = extra[ln+4:] |
|
297 |
|
298 |
|
299 class ZipFile: |
|
300 """ Class with methods to open, read, write, close, list zip files. |
|
301 |
|
302 z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=True) |
|
303 |
|
304 file: Either the path to the file, or a file-like object. |
|
305 If it is a path, the file will be opened and closed by ZipFile. |
|
306 mode: The mode can be either read "r", write "w" or append "a". |
|
307 compression: ZIP_STORED (no compression) or ZIP_DEFLATED (requires zlib). |
|
308 allowZip64: if True ZipFile will create files with ZIP64 extensions when |
|
309 needed, otherwise it will raise an exception when this would |
|
310 be necessary. |
|
311 |
|
312 """ |
|
313 |
|
314 fp = None # Set here since __del__ checks it |
|
315 |
|
316 def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=False): |
|
317 """Open the ZIP file with mode read "r", write "w" or append "a".""" |
|
318 self._allowZip64 = allowZip64 |
|
319 self._didModify = False |
|
320 if compression == ZIP_STORED: |
|
321 pass |
|
322 elif compression == ZIP_DEFLATED: |
|
323 if not zlib: |
|
324 raise RuntimeError,\ |
|
325 "Compression requires the (missing) zlib module" |
|
326 else: |
|
327 raise RuntimeError, "That compression method is not supported" |
|
328 self.debug = 0 # Level of printing: 0 through 3 |
|
329 self.NameToInfo = {} # Find file info given name |
|
330 self.filelist = [] # List of ZipInfo instances for archive |
|
331 self.compression = compression # Method of compression |
|
332 self.mode = key = mode.replace('b', '')[0] |
|
333 |
|
334 # Check if we were passed a file-like object |
|
335 if isinstance(file, basestring): |
|
336 self._filePassed = 0 |
|
337 self.filename = file |
|
338 modeDict = {'r' : 'rb', 'w': 'wb', 'a' : 'r+b'} |
|
339 self.fp = open(file, modeDict[mode]) |
|
340 else: |
|
341 self._filePassed = 1 |
|
342 self.fp = file |
|
343 self.filename = getattr(file, 'name', None) |
|
344 |
|
345 if key == 'r': |
|
346 self._GetContents() |
|
347 elif key == 'w': |
|
348 pass |
|
349 elif key == 'a': |
|
350 try: # See if file is a zip file |
|
351 self._RealGetContents() |
|
352 # seek to start of directory and overwrite |
|
353 self.fp.seek(self.start_dir, 0) |
|
354 except BadZipfile: # file is not a zip file, just append |
|
355 self.fp.seek(0, 2) |
|
356 else: |
|
357 if not self._filePassed: |
|
358 self.fp.close() |
|
359 self.fp = None |
|
360 raise RuntimeError, 'Mode must be "r", "w" or "a"' |
|
361 |
|
362 def _GetContents(self): |
|
363 """Read the directory, making sure we close the file if the format |
|
364 is bad.""" |
|
365 try: |
|
366 self._RealGetContents() |
|
367 except BadZipfile: |
|
368 if not self._filePassed: |
|
369 self.fp.close() |
|
370 self.fp = None |
|
371 raise |
|
372 |
|
373 def _RealGetContents(self): |
|
374 """Read in the table of contents for the ZIP file.""" |
|
375 fp = self.fp |
|
376 endrec = _EndRecData(fp) |
|
377 if not endrec: |
|
378 raise BadZipfile, "File is not a zip file" |
|
379 if self.debug > 1: |
|
380 print endrec |
|
381 size_cd = endrec[5] # bytes in central directory |
|
382 offset_cd = endrec[6] # offset of central directory |
|
383 self.comment = endrec[8] # archive comment |
|
384 # endrec[9] is the offset of the "End of Central Dir" record |
|
385 if endrec[9] > ZIP64_LIMIT: |
|
386 x = endrec[9] - size_cd - 56 - 20 |
|
387 else: |
|
388 x = endrec[9] - size_cd |
|
389 # "concat" is zero, unless zip was concatenated to another file |
|
390 concat = x - offset_cd |
|
391 if self.debug > 2: |
|
392 print "given, inferred, offset", offset_cd, x, concat |
|
393 # self.start_dir: Position of start of central directory |
|
394 self.start_dir = offset_cd + concat |
|
395 fp.seek(self.start_dir, 0) |
|
396 data = fp.read(size_cd) |
|
397 fp = cStringIO.StringIO(data) |
|
398 total = 0 |
|
399 while total < size_cd: |
|
400 centdir = fp.read(46) |
|
401 total = total + 46 |
|
402 if centdir[0:4] != stringCentralDir: |
|
403 raise BadZipfile, "Bad magic number for central directory" |
|
404 centdir = struct.unpack(structCentralDir, centdir) |
|
405 if self.debug > 2: |
|
406 print centdir |
|
407 filename = fp.read(centdir[_CD_FILENAME_LENGTH]) |
|
408 # Create ZipInfo instance to store file information |
|
409 x = ZipInfo(filename) |
|
410 x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH]) |
|
411 x.comment = fp.read(centdir[_CD_COMMENT_LENGTH]) |
|
412 total = (total + centdir[_CD_FILENAME_LENGTH] |
|
413 + centdir[_CD_EXTRA_FIELD_LENGTH] |
|
414 + centdir[_CD_COMMENT_LENGTH]) |
|
415 x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET] |
|
416 (x.create_version, x.create_system, x.extract_version, x.reserved, |
|
417 x.flag_bits, x.compress_type, t, d, |
|
418 x.CRC, x.compress_size, x.file_size) = centdir[1:12] |
|
419 x.volume, x.internal_attr, x.external_attr = centdir[15:18] |
|
420 # Convert date/time code to (year, month, day, hour, min, sec) |
|
421 x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F, |
|
422 t>>11, (t>>5)&0x3F, (t&0x1F) * 2 ) |
|
423 |
|
424 x._decodeExtra() |
|
425 x.header_offset = x.header_offset + concat |
|
426 self.filelist.append(x) |
|
427 self.NameToInfo[x.filename] = x |
|
428 if self.debug > 2: |
|
429 print "total", total |
|
430 |
|
431 |
|
432 def namelist(self): |
|
433 """Return a list of file names in the archive.""" |
|
434 l = [] |
|
435 for data in self.filelist: |
|
436 l.append(data.filename) |
|
437 return l |
|
438 |
|
439 def infolist(self): |
|
440 """Return a list of class ZipInfo instances for files in the |
|
441 archive.""" |
|
442 return self.filelist |
|
443 |
|
444 def printdir(self): |
|
445 """Print a table of contents for the zip file.""" |
|
446 print "%-46s %19s %12s" % ("File Name", "Modified ", "Size") |
|
447 for zinfo in self.filelist: |
|
448 date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time[:6] |
|
449 print "%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size) |
|
450 |
|
451 def testzip(self): |
|
452 """Read all the files and check the CRC.""" |
|
453 for zinfo in self.filelist: |
|
454 try: |
|
455 self.read(zinfo.filename) # Check CRC-32 |
|
456 except BadZipfile: |
|
457 return zinfo.filename |
|
458 |
|
459 |
|
460 def getinfo(self, name): |
|
461 """Return the instance of ZipInfo given 'name'.""" |
|
462 return self.NameToInfo[name] |
|
463 |
|
464 def read(self, name): |
|
465 """Return file bytes (as a string) for name.""" |
|
466 if self.mode not in ("r", "a"): |
|
467 raise RuntimeError, 'read() requires mode "r" or "a"' |
|
468 if not self.fp: |
|
469 raise RuntimeError, \ |
|
470 "Attempt to read ZIP archive that was already closed" |
|
471 zinfo = self.getinfo(name) |
|
472 filepos = self.fp.tell() |
|
473 |
|
474 self.fp.seek(zinfo.header_offset, 0) |
|
475 |
|
476 # Skip the file header: |
|
477 fheader = self.fp.read(30) |
|
478 if fheader[0:4] != stringFileHeader: |
|
479 raise BadZipfile, "Bad magic number for file header" |
|
480 |
|
481 fheader = struct.unpack(structFileHeader, fheader) |
|
482 fname = self.fp.read(fheader[_FH_FILENAME_LENGTH]) |
|
483 if fheader[_FH_EXTRA_FIELD_LENGTH]: |
|
484 self.fp.read(fheader[_FH_EXTRA_FIELD_LENGTH]) |
|
485 |
|
486 if fname != zinfo.orig_filename: |
|
487 raise BadZipfile, \ |
|
488 'File name in directory "%s" and header "%s" differ.' % ( |
|
489 zinfo.orig_filename, fname) |
|
490 |
|
491 bytes = self.fp.read(zinfo.compress_size) |
|
492 self.fp.seek(filepos, 0) |
|
493 if zinfo.compress_type == ZIP_STORED: |
|
494 pass |
|
495 elif zinfo.compress_type == ZIP_DEFLATED: |
|
496 if not zlib: |
|
497 raise RuntimeError, \ |
|
498 "De-compression requires the (missing) zlib module" |
|
499 # zlib compress/decompress code by Jeremy Hylton of CNRI |
|
500 dc = zlib.decompressobj(-15) |
|
501 bytes = dc.decompress(bytes) |
|
502 # need to feed in unused pad byte so that zlib won't choke |
|
503 ex = dc.decompress('Z') + dc.flush() |
|
504 if ex: |
|
505 bytes = bytes + ex |
|
506 else: |
|
507 raise BadZipfile, \ |
|
508 "Unsupported compression method %d for file %s" % \ |
|
509 (zinfo.compress_type, name) |
|
510 crc = binascii.crc32(bytes) |
|
511 if crc != zinfo.CRC: |
|
512 raise BadZipfile, "Bad CRC-32 for file %s" % name |
|
513 return bytes |
|
514 |
|
515 def _writecheck(self, zinfo): |
|
516 """Check for errors before writing a file to the archive.""" |
|
517 if zinfo.filename in self.NameToInfo: |
|
518 if self.debug: # Warning for duplicate names |
|
519 print "Duplicate name:", zinfo.filename |
|
520 if self.mode not in ("w", "a"): |
|
521 raise RuntimeError, 'write() requires mode "w" or "a"' |
|
522 if not self.fp: |
|
523 raise RuntimeError, \ |
|
524 "Attempt to write ZIP archive that was already closed" |
|
525 if zinfo.compress_type == ZIP_DEFLATED and not zlib: |
|
526 raise RuntimeError, \ |
|
527 "Compression requires the (missing) zlib module" |
|
528 if zinfo.compress_type not in (ZIP_STORED, ZIP_DEFLATED): |
|
529 raise RuntimeError, \ |
|
530 "That compression method is not supported" |
|
531 if zinfo.file_size > ZIP64_LIMIT: |
|
532 if not self._allowZip64: |
|
533 raise LargeZipFile("Filesize would require ZIP64 extensions") |
|
534 if zinfo.header_offset > ZIP64_LIMIT: |
|
535 if not self._allowZip64: |
|
536 raise LargeZipFile("Zipfile size would require ZIP64 extensions") |
|
537 |
|
538 def write(self, filename, arcname=None, compress_type=None): |
|
539 """Put the bytes from filename into the archive under the name |
|
540 arcname.""" |
|
541 st = os.stat(filename) |
|
542 mtime = time.localtime(st.st_mtime) |
|
543 date_time = mtime[0:6] |
|
544 # Create ZipInfo instance to store file information |
|
545 if arcname is None: |
|
546 arcname = filename |
|
547 arcname = os.path.normpath(os.path.splitdrive(arcname)[1]) |
|
548 while arcname[0] in (os.sep, os.altsep): |
|
549 arcname = arcname[1:] |
|
550 zinfo = ZipInfo(arcname, date_time) |
|
551 zinfo.external_attr = (st[0] & 0xFFFF) << 16L # Unix attributes |
|
552 if compress_type is None: |
|
553 zinfo.compress_type = self.compression |
|
554 else: |
|
555 zinfo.compress_type = compress_type |
|
556 |
|
557 zinfo.file_size = st.st_size |
|
558 zinfo.flag_bits = 0x00 |
|
559 zinfo.header_offset = self.fp.tell() # Start of header bytes |
|
560 |
|
561 self._writecheck(zinfo) |
|
562 self._didModify = True |
|
563 fp = open(filename, "rb") |
|
564 # Must overwrite CRC and sizes with correct data later |
|
565 zinfo.CRC = CRC = 0 |
|
566 zinfo.compress_size = compress_size = 0 |
|
567 zinfo.file_size = file_size = 0 |
|
568 self.fp.write(zinfo.FileHeader()) |
|
569 if zinfo.compress_type == ZIP_DEFLATED: |
|
570 cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION, |
|
571 zlib.DEFLATED, -15) |
|
572 else: |
|
573 cmpr = None |
|
574 while 1: |
|
575 buf = fp.read(1024 * 8) |
|
576 if not buf: |
|
577 break |
|
578 file_size = file_size + len(buf) |
|
579 CRC = binascii.crc32(buf, CRC) |
|
580 if cmpr: |
|
581 buf = cmpr.compress(buf) |
|
582 compress_size = compress_size + len(buf) |
|
583 self.fp.write(buf) |
|
584 fp.close() |
|
585 if cmpr: |
|
586 buf = cmpr.flush() |
|
587 compress_size = compress_size + len(buf) |
|
588 self.fp.write(buf) |
|
589 zinfo.compress_size = compress_size |
|
590 else: |
|
591 zinfo.compress_size = file_size |
|
592 zinfo.CRC = CRC |
|
593 zinfo.file_size = file_size |
|
594 # Seek backwards and write CRC and file sizes |
|
595 position = self.fp.tell() # Preserve current position in file |
|
596 self.fp.seek(zinfo.header_offset + 14, 0) |
|
597 self.fp.write(struct.pack("<lLL", zinfo.CRC, zinfo.compress_size, |
|
598 zinfo.file_size)) |
|
599 self.fp.seek(position, 0) |
|
600 self.filelist.append(zinfo) |
|
601 self.NameToInfo[zinfo.filename] = zinfo |
|
602 |
|
603 def writestr(self, zinfo_or_arcname, bytes): |
|
604 """Write a file into the archive. The contents is the string |
|
605 'bytes'. 'zinfo_or_arcname' is either a ZipInfo instance or |
|
606 the name of the file in the archive.""" |
|
607 if not isinstance(zinfo_or_arcname, ZipInfo): |
|
608 zinfo = ZipInfo(filename=zinfo_or_arcname, |
|
609 date_time=time.localtime(time.time())[:6]) |
|
610 zinfo.compress_type = self.compression |
|
611 else: |
|
612 zinfo = zinfo_or_arcname |
|
613 zinfo.file_size = len(bytes) # Uncompressed size |
|
614 zinfo.header_offset = self.fp.tell() # Start of header bytes |
|
615 self._writecheck(zinfo) |
|
616 self._didModify = True |
|
617 zinfo.CRC = binascii.crc32(bytes) # CRC-32 checksum |
|
618 if zinfo.compress_type == ZIP_DEFLATED: |
|
619 co = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION, |
|
620 zlib.DEFLATED, -15) |
|
621 bytes = co.compress(bytes) + co.flush() |
|
622 zinfo.compress_size = len(bytes) # Compressed size |
|
623 else: |
|
624 zinfo.compress_size = zinfo.file_size |
|
625 zinfo.header_offset = self.fp.tell() # Start of header bytes |
|
626 self.fp.write(zinfo.FileHeader()) |
|
627 self.fp.write(bytes) |
|
628 self.fp.flush() |
|
629 if zinfo.flag_bits & 0x08: |
|
630 # Write CRC and file sizes after the file data |
|
631 self.fp.write(struct.pack("<lLL", zinfo.CRC, zinfo.compress_size, |
|
632 zinfo.file_size)) |
|
633 self.filelist.append(zinfo) |
|
634 self.NameToInfo[zinfo.filename] = zinfo |
|
635 |
|
636 def __del__(self): |
|
637 """Call the "close()" method in case the user forgot.""" |
|
638 self.close() |
|
639 |
|
640 def close(self): |
|
641 """Close the file, and for mode "w" and "a" write the ending |
|
642 records.""" |
|
643 if self.fp is None: |
|
644 return |
|
645 |
|
646 if self.mode in ("w", "a") and self._didModify: # write ending records |
|
647 count = 0 |
|
648 pos1 = self.fp.tell() |
|
649 for zinfo in self.filelist: # write central directory |
|
650 count = count + 1 |
|
651 dt = zinfo.date_time |
|
652 dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2] |
|
653 dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2) |
|
654 extra = [] |
|
655 if zinfo.file_size > ZIP64_LIMIT \ |
|
656 or zinfo.compress_size > ZIP64_LIMIT: |
|
657 extra.append(zinfo.file_size) |
|
658 extra.append(zinfo.compress_size) |
|
659 file_size = 0xffffffff #-1 |
|
660 compress_size = 0xffffffff #-1 |
|
661 else: |
|
662 file_size = zinfo.file_size |
|
663 compress_size = zinfo.compress_size |
|
664 |
|
665 if zinfo.header_offset > ZIP64_LIMIT: |
|
666 extra.append(zinfo.header_offset) |
|
667 header_offset = -1 # struct "l" format: 32 one bits |
|
668 else: |
|
669 header_offset = zinfo.header_offset |
|
670 |
|
671 extra_data = zinfo.extra |
|
672 if extra: |
|
673 # Append a ZIP64 field to the extra's |
|
674 extra_data = struct.pack( |
|
675 '<hh' + 'q'*len(extra), |
|
676 1, 8*len(extra), *extra) + extra_data |
|
677 |
|
678 extract_version = max(45, zinfo.extract_version) |
|
679 create_version = max(45, zinfo.create_version) |
|
680 else: |
|
681 extract_version = zinfo.extract_version |
|
682 create_version = zinfo.create_version |
|
683 |
|
684 centdir = struct.pack(structCentralDir, |
|
685 stringCentralDir, create_version, |
|
686 zinfo.create_system, extract_version, zinfo.reserved, |
|
687 zinfo.flag_bits, zinfo.compress_type, dostime, dosdate, |
|
688 zinfo.CRC, compress_size, file_size, |
|
689 len(zinfo.filename), len(extra_data), len(zinfo.comment), |
|
690 0, zinfo.internal_attr, zinfo.external_attr, |
|
691 header_offset) |
|
692 self.fp.write(centdir) |
|
693 self.fp.write(zinfo.filename) |
|
694 self.fp.write(extra_data) |
|
695 self.fp.write(zinfo.comment) |
|
696 |
|
697 pos2 = self.fp.tell() |
|
698 # Write end-of-zip-archive record |
|
699 if pos1 > ZIP64_LIMIT: |
|
700 # Need to write the ZIP64 end-of-archive records |
|
701 zip64endrec = struct.pack( |
|
702 structEndArchive64, stringEndArchive64, |
|
703 44, 45, 45, 0, 0, count, count, pos2 - pos1, pos1) |
|
704 self.fp.write(zip64endrec) |
|
705 |
|
706 zip64locrec = struct.pack( |
|
707 structEndArchive64Locator, |
|
708 stringEndArchive64Locator, 0, pos2, 1) |
|
709 self.fp.write(zip64locrec) |
|
710 |
|
711 # XXX Why is `pos3` computed next? It's never referenced. |
|
712 pos3 = self.fp.tell() |
|
713 endrec = struct.pack(structEndArchive, stringEndArchive, |
|
714 0, 0, count, count, pos2 - pos1, -1, 0) |
|
715 self.fp.write(endrec) |
|
716 |
|
717 else: |
|
718 endrec = struct.pack(structEndArchive, stringEndArchive, |
|
719 0, 0, count, count, pos2 - pos1, pos1, 0) |
|
720 self.fp.write(endrec) |
|
721 self.fp.flush() |
|
722 if not self._filePassed: |
|
723 self.fp.close() |
|
724 self.fp = None |
|
725 |
|
726 |
|
727 class PyZipFile(ZipFile): |
|
728 """Class to create ZIP archives with Python library files and packages.""" |
|
729 |
|
730 def writepy(self, pathname, basename = ""): |
|
731 """Add all files from "pathname" to the ZIP archive. |
|
732 |
|
733 If pathname is a package directory, search the directory and |
|
734 all package subdirectories recursively for all *.py and enter |
|
735 the modules into the archive. If pathname is a plain |
|
736 directory, listdir *.py and enter all modules. Else, pathname |
|
737 must be a Python *.py file and the module will be put into the |
|
738 archive. Added modules are always module.pyo or module.pyc. |
|
739 This method will compile the module.py into module.pyc if |
|
740 necessary. |
|
741 """ |
|
742 dir, name = os.path.split(pathname) |
|
743 if os.path.isdir(pathname): |
|
744 initname = os.path.join(pathname, "__init__.py") |
|
745 if os.path.isfile(initname): |
|
746 # This is a package directory, add it |
|
747 if basename: |
|
748 basename = "%s/%s" % (basename, name) |
|
749 else: |
|
750 basename = name |
|
751 if self.debug: |
|
752 print "Adding package in", pathname, "as", basename |
|
753 fname, arcname = self._get_codename(initname[0:-3], basename) |
|
754 if self.debug: |
|
755 print "Adding", arcname |
|
756 self.write(fname, arcname) |
|
757 dirlist = os.listdir(pathname) |
|
758 dirlist.remove("__init__.py") |
|
759 # Add all *.py files and package subdirectories |
|
760 for filename in dirlist: |
|
761 path = os.path.join(pathname, filename) |
|
762 root, ext = os.path.splitext(filename) |
|
763 if os.path.isdir(path): |
|
764 if os.path.isfile(os.path.join(path, "__init__.py")): |
|
765 # This is a package directory, add it |
|
766 self.writepy(path, basename) # Recursive call |
|
767 elif ext == ".py": |
|
768 fname, arcname = self._get_codename(path[0:-3], |
|
769 basename) |
|
770 if self.debug: |
|
771 print "Adding", arcname |
|
772 self.write(fname, arcname) |
|
773 else: |
|
774 # This is NOT a package directory, add its files at top level |
|
775 if self.debug: |
|
776 print "Adding files from directory", pathname |
|
777 for filename in os.listdir(pathname): |
|
778 path = os.path.join(pathname, filename) |
|
779 root, ext = os.path.splitext(filename) |
|
780 if ext == ".py": |
|
781 fname, arcname = self._get_codename(path[0:-3], |
|
782 basename) |
|
783 if self.debug: |
|
784 print "Adding", arcname |
|
785 self.write(fname, arcname) |
|
786 else: |
|
787 if pathname[-3:] != ".py": |
|
788 raise RuntimeError, \ |
|
789 'Files added with writepy() must end with ".py"' |
|
790 fname, arcname = self._get_codename(pathname[0:-3], basename) |
|
791 if self.debug: |
|
792 print "Adding file", arcname |
|
793 self.write(fname, arcname) |
|
794 |
|
795 def _get_codename(self, pathname, basename): |
|
796 """Return (filename, archivename) for the path. |
|
797 |
|
798 Given a module name path, return the correct file path and |
|
799 archive name, compiling if necessary. For example, given |
|
800 /python/lib/string, return (/python/lib/string.pyc, string). |
|
801 """ |
|
802 file_py = pathname + ".py" |
|
803 file_pyc = pathname + ".pyc" |
|
804 file_pyo = pathname + ".pyo" |
|
805 if os.path.isfile(file_pyo) and \ |
|
806 os.stat(file_pyo).st_mtime >= os.stat(file_py).st_mtime: |
|
807 fname = file_pyo # Use .pyo file |
|
808 elif not os.path.isfile(file_pyc) or \ |
|
809 os.stat(file_pyc).st_mtime < os.stat(file_py).st_mtime: |
|
810 import py_compile |
|
811 if self.debug: |
|
812 print "Compiling", file_py |
|
813 try: |
|
814 py_compile.compile(file_py, file_pyc, None, True) |
|
815 except py_compile.PyCompileError,err: |
|
816 print err.msg |
|
817 fname = file_pyc |
|
818 else: |
|
819 fname = file_pyc |
|
820 archivename = os.path.split(fname)[1] |
|
821 if basename: |
|
822 archivename = "%s/%s" % (basename, archivename) |
|
823 return (fname, archivename) |
|
824 |
|
825 |
|
826 def main(args = None): |
|
827 import textwrap |
|
828 USAGE=textwrap.dedent("""\ |
|
829 Usage: |
|
830 zipfile.py -l zipfile.zip # Show listing of a zipfile |
|
831 zipfile.py -t zipfile.zip # Test if a zipfile is valid |
|
832 zipfile.py -e zipfile.zip target # Extract zipfile into target dir |
|
833 zipfile.py -c zipfile.zip src ... # Create zipfile from sources |
|
834 """) |
|
835 if args is None: |
|
836 args = sys.argv[1:] |
|
837 |
|
838 if not args or args[0] not in ('-l', '-c', '-e', '-t'): |
|
839 print USAGE |
|
840 sys.exit(1) |
|
841 |
|
842 if args[0] == '-l': |
|
843 if len(args) != 2: |
|
844 print USAGE |
|
845 sys.exit(1) |
|
846 zf = ZipFile(args[1], 'r') |
|
847 zf.printdir() |
|
848 zf.close() |
|
849 |
|
850 elif args[0] == '-t': |
|
851 if len(args) != 2: |
|
852 print USAGE |
|
853 sys.exit(1) |
|
854 zf = ZipFile(args[1], 'r') |
|
855 zf.testzip() |
|
856 print "Done testing" |
|
857 |
|
858 elif args[0] == '-e': |
|
859 if len(args) != 3: |
|
860 print USAGE |
|
861 sys.exit(1) |
|
862 |
|
863 zf = ZipFile(args[1], 'r') |
|
864 out = args[2] |
|
865 for path in zf.namelist(): |
|
866 if path.startswith('./'): |
|
867 tgt = os.path.join(out, path[2:]) |
|
868 else: |
|
869 tgt = os.path.join(out, path) |
|
870 |
|
871 tgtdir = os.path.dirname(tgt) |
|
872 if not os.path.exists(tgtdir): |
|
873 os.makedirs(tgtdir) |
|
874 fp = open(tgt, 'wb') |
|
875 fp.write(zf.read(path)) |
|
876 fp.close() |
|
877 zf.close() |
|
878 |
|
879 elif args[0] == '-c': |
|
880 if len(args) < 3: |
|
881 print USAGE |
|
882 sys.exit(1) |
|
883 |
|
884 def addToZip(zf, path, zippath): |
|
885 if os.path.isfile(path): |
|
886 zf.write(path, zippath, ZIP_DEFLATED) |
|
887 elif os.path.isdir(path): |
|
888 for nm in os.listdir(path): |
|
889 addToZip(zf, |
|
890 os.path.join(path, nm), os.path.join(zippath, nm)) |
|
891 # else: ignore |
|
892 |
|
893 zf = ZipFile(args[1], 'w', allowZip64=True) |
|
894 for src in args[2:]: |
|
895 addToZip(zf, src, os.path.basename(src)) |
|
896 |
|
897 zf.close() |
|
898 |
|
899 if __name__ == "__main__": |
|
900 main() |