Index: zipfile.py
===================================================================
--- zipfile.py	(revision 42911)
+++ zipfile.py	(working copy)
@@ -15,6 +15,8 @@
     pass
 error = BadZipfile      # The exception raised by this module
 
+ZIP64_LIMIT= 1 << 30
+
 # constants for Zip file compression methods
 ZIP_STORED = 0
 ZIP_DEFLATED = 8
@@ -27,7 +29,12 @@
 stringCentralDir = "PK\001\002"   # magic number for central directory
 structFileHeader = "<4s2B4HlLL2H"  # 12 items, file header record, 30 bytes
 stringFileHeader = "PK\003\004"   # magic number for file header
+structEndArchive64Locator = "<4slql" # 4 items, locate Zip64 header, 20 bytes
+stringEndArchive64Locator = "PK\x06\x07" # magic token for locator header
+structEndArchive64 = "<4sqhhllqqqq" # 10 items, end of archive (Zip64), 56 bytes
+stringEndArchive64 = "PK\x06\x06" # magic token for Zip64 header
 
+
 # indexes of entries in the central directory structure
 _CD_SIGNATURE = 0
 _CD_CREATE_VERSION = 1
@@ -75,6 +82,40 @@
         pass
     return False
 
+def _EndRecData64(fpin, offset, endrec):
+    """
+    Read the ZIP64 end-of-archive records and use that to update endrec
+    """
+    locatorSize = struct.calcsize(structEndArchive64Locator)
+    fpin.seek(offset - locatorSize, 2)
+    data = fpin.read(locatorSize)
+    sig, diskno, reloff, disks = struct.unpack(structEndArchive64Locator, data)
+    if sig != stringEndArchive64Locator: 
+        return endrec
+
+    assert diskno == 0
+    assert disks  == 1
+
+    # Assume no 'zip64 extensible data' 
+    endArchiveSize = struct.calcsize(structEndArchive64)
+    fpin.seek(offset - locatorSize - endArchiveSize, 2)
+    data = fpin.read(endArchiveSize)
+    sig, sz, create_version, read_version, disk_num, disk_dir, \
+            dircount, dircount2, dirsize, diroffset = \
+            struct.unpack(structEndArchive64, data)
+    if sig != stringEndArchive64: 
+        return endrec
+
+    # Update the original endrec using data from the ZIP64 record
+    endrec[1] = disk_num
+    endrec[2] = disk_dir
+    endrec[3] = dircount
+    endrec[4] = dircount2
+    endrec[5] = dirsize
+    endrec[6] = diroffset
+    return endrec
+
+
 def _EndRecData(fpin):
     """Return data from the "End of Central Directory" record, or None.
 
@@ -88,6 +129,8 @@
         endrec = list(endrec)
         endrec.append("")               # Append the archive comment
         endrec.append(filesize - 22)    # Append the record start offset
+        if endrec[-4] == -1:
+            return _EndRecData64(fpin, -22, endrec)
         return endrec
     # Search the last END_BLOCK bytes of the file for the record signature.
     # The comment is appended to the ZIP file and has a 16 bit length.
@@ -106,6 +149,8 @@
             # Append the archive comment and start offset
             endrec.append(comment)
             endrec.append(filesize - END_BLOCK + start)
+            if endrec[-4] == -1:
+                return _EndRecData64(fpin, - END_BLOCK + start, endrec)
             return endrec
     return      # Error, return None
 
@@ -162,14 +207,51 @@
             CRC = self.CRC
             compress_size = self.compress_size
             file_size = self.file_size
+
+        extra = self.extra
+
+        if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
+            # File is larger than what fits into a 4 byte integer,
+            # fall back to the ZIP64 extension
+            fmt = '<hhqq'
+            extra = extra + struct.pack(fmt,
+                    1, struct.calcsize(fmt)-4, file_size, compress_size)
+            file_size = -1
+            compress_size = -1
+            self.extract_version = max(45, self.extract_version)
+            self.create_version = max(45, self.extract_version)
+
         header = struct.pack(structFileHeader, stringFileHeader,
                  self.extract_version, self.reserved, self.flag_bits,
                  self.compress_type, dostime, dosdate, CRC,
                  compress_size, file_size,
-                 len(self.filename), len(self.extra))
-        return header + self.filename + self.extra
+                 len(self.filename), len(extra))
+        return header + self.filename + extra
 
+    def _decodeExtra(self):
+        # Try to decode the extra field.
+        extra = self.extra
+        while extra:
+            tp, ln = struct.unpack('<hh', extra[:4])
+            rest = extra[4:ln+4]
+            extra = extra[ln+4:]
+            if tp == 1:
+                # ZIP64 extension (large files and/or large archives)
+                if self.file_size == -1 or self.file_size == 0xFFFFFFFFL:
+                    self.file_size = struct.unpack('<q', rest[:8])[0]
+                    rest = rest[8:]
 
+                if self.file_size == -1 or self.compress_size == 0xFFFFFFFFL:
+                    self.file_size = struct.unpack('<q', rest[:8])[0]
+                    self.compress_size = struct.unpack('<q', rest[:8])[0]
+                    rest = rest[8:]
+
+                if self.header_offset == -1:
+                    old = self.header_offset
+                    self.header_offset = struct.unpack('<q', rest[:8])[0]
+                    rest = rest[8:]
+               
+
 class ZipFile:
     """ Class with methods to open, read, write, close, list zip files.
 
@@ -250,7 +332,10 @@
         offset_cd = endrec[6]   # offset of central directory
         self.comment = endrec[8]        # archive comment
         # endrec[9] is the offset of the "End of Central Dir" record
-        x = endrec[9] - size_cd
+        if endrec[9] > ZIP64_LIMIT:
+            x = endrec[9] - size_cd - 56 - 20
+        else:
+            x = endrec[9] - size_cd
         # "concat" is zero, unless zip was concatenated to another file
         concat = x - offset_cd
         if self.debug > 2:
@@ -275,7 +360,7 @@
             total = (total + centdir[_CD_FILENAME_LENGTH]
                      + centdir[_CD_EXTRA_FIELD_LENGTH]
                      + centdir[_CD_COMMENT_LENGTH])
-            x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET] + concat
+            x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET]
             # file_offset must be computed below...
             (x.create_version, x.create_system, x.extract_version, x.reserved,
                 x.flag_bits, x.compress_type, t, d,
@@ -284,6 +369,10 @@
             # Convert date/time code to (year, month, day, hour, min, sec)
             x.date_time = ( (d>>9)+1980, (d>>5)&0xF, d&0x1F,
                                      t>>11, (t>>5)&0x3F, (t&0x1F) * 2 )
+
+            x._decodeExtra()
+            x.header_offset = x.header_offset + concat
+
             self.filelist.append(x)
             self.NameToInfo[x.filename] = x
             if self.debug > 2:
@@ -491,6 +580,7 @@
         records."""
         if self.fp is None:
             return
+        
         if self.mode in ("w", "a"):             # write ending records
             count = 0
             pos1 = self.fp.tell()
@@ -499,23 +589,72 @@
                 dt = zinfo.date_time
                 dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
                 dostime = dt[3] << 11 | dt[4] << 5 | (dt[5] // 2)
+                extra = []
+                if zinfo.file_size > ZIP64_LIMIT \
+                        or zinfo.compress_size > ZIP64_LIMIT:
+                    extra.append(zinfo.file_size)
+                    extra.append(zinfo.compress_size)
+                    file_size = -1
+                    compress_size = -1
+                else:
+                    file_size = zinfo.file_size
+                    compress_size = zinfo.file_size
+
+                if zinfo.header_offset > ZIP64_LIMIT:
+                    extra.append(zinfo.header_offset)
+                    header_offset = -1
+                else:
+                    header_offset = zinfo.header_offset
+
+                extra_data = zinfo.extra
+                if extra:
+                    # Append a ZIP64 field to the extra's
+                    extra_data = struct.pack(
+                            '<hh' + 'q'*len(extra),
+                            1, 8*len(extra), *extra) + extra_data
+                    
+                    extract_version = max(45, zinfo.extract_version)
+                    create_version = max(45, zinfo.create_version)
+                else:
+                    extract_version = zinfo.extract_version
+                    create_version = zinfo.create_version
+
                 centdir = struct.pack(structCentralDir,
-                  stringCentralDir, zinfo.create_version,
-                  zinfo.create_system, zinfo.extract_version, zinfo.reserved,
+                  stringCentralDir, create_version,
+                  zinfo.create_system, extract_version, zinfo.reserved,
                   zinfo.flag_bits, zinfo.compress_type, dostime, dosdate,
-                  zinfo.CRC, zinfo.compress_size, zinfo.file_size,
-                  len(zinfo.filename), len(zinfo.extra), len(zinfo.comment),
+                  zinfo.CRC, compress_size, file_size,
+                  len(zinfo.filename), len(extra_data), len(zinfo.comment),
                   0, zinfo.internal_attr, zinfo.external_attr,
-                  zinfo.header_offset)
+                  header_offset)
                 self.fp.write(centdir)
                 self.fp.write(zinfo.filename)
-                self.fp.write(zinfo.extra)
+                self.fp.write(extra_data)
                 self.fp.write(zinfo.comment)
+
             pos2 = self.fp.tell()
             # Write end-of-zip-archive record
-            endrec = struct.pack(structEndArchive, stringEndArchive,
-                     0, 0, count, count, pos2 - pos1, pos1, 0)
-            self.fp.write(endrec)
+            if pos1 > ZIP64_LIMIT:
+                # Need to write the ZIP64 end-of-archive records
+                zip64endrec = struct.pack(
+                        structEndArchive64, stringEndArchive64,
+                        44, 45, 45, 0, 0, count, count, pos2 - pos1, pos1)
+                self.fp.write(zip64endrec)
+
+                zip64locrec = struct.pack(
+                        structEndArchive64Locator, 
+                        stringEndArchive64Locator, 0, pos2, 1)
+                self.fp.write(zip64locrec)
+
+                pos3 = self.fp.tell()
+                endrec = struct.pack(structEndArchive, stringEndArchive,
+                         0, 0, count, count, pos2 - pos1, -1, 0)
+                self.fp.write(endrec)
+
+            else:
+                endrec = struct.pack(structEndArchive, stringEndArchive,
+                         0, 0, count, count, pos2 - pos1, pos1, 0)
+                self.fp.write(endrec)
             self.fp.flush()
         if not self._filePassed:
             self.fp.close()