From 80a9fd77a0d63eed2f5d40e60437b5a465b7c1a5 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Tue, 15 Jan 2013 00:29:51 +0200
Subject: [PATCH] Issue #9720: zipfile now writes correct local headers for
 files larger than 4 GiB.

---
 Lib/zipfile.py | 47 ++++++++++++++++++++++++++++++++---------------
 Misc/NEWS      |  3 +++
 2 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/Lib/zipfile.py b/Lib/zipfile.py
index 6e776882539..f340aa65758 100644
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -316,7 +316,7 @@ class ZipInfo (object):
         # compress_size         Size of the compressed file
         # file_size             Size of the uncompressed file
 
-    def FileHeader(self):
+    def FileHeader(self, zip64=None):
         """Return the per-file header as a string."""
         dt = self.date_time
         dosdate = (dt[0] - 1980) << 9 | dt[1] << 5 | dt[2]
@@ -331,12 +331,17 @@ class ZipInfo (object):
 
         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
+        if zip64 is None:
+            zip64 = file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT
+        if zip64:
             fmt = '<HHQQ'
             extra = extra + struct.pack(fmt,
                     1, struct.calcsize(fmt)-4, file_size, compress_size)
+        if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
+            if not zip64:
+                raise LargeZipFile("Filesize would require ZIP64 extensions")
+            # File is larger than what fits into a 4 byte integer,
+            # fall back to the ZIP64 extension
             file_size = 0xffffffff
             compress_size = 0xffffffff
             self.extract_version = max(45, self.extract_version)
@@ -1113,20 +1118,23 @@ class ZipFile(object):
             zinfo.CRC = 0
             self.filelist.append(zinfo)
             self.NameToInfo[zinfo.filename] = zinfo
-            self.fp.write(zinfo.FileHeader())
+            self.fp.write(zinfo.FileHeader(False))
             return
 
         with open(filename, "rb") as fp:
             # Must overwrite CRC and sizes with correct data later
             zinfo.CRC = CRC = 0
             zinfo.compress_size = compress_size = 0
-            zinfo.file_size = file_size = 0
-            self.fp.write(zinfo.FileHeader())
+            # Compressed size can be larger than uncompressed size
+            zip64 = self._allowZip64 and \
+                    zinfo.file_size * 1.05 > ZIP64_LIMIT
+            self.fp.write(zinfo.FileHeader(zip64))
             if zinfo.compress_type == ZIP_DEFLATED:
                 cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
                      zlib.DEFLATED, -15)
             else:
                 cmpr = None
+            file_size = 0
             while 1:
                 buf = fp.read(1024 * 8)
                 if not buf:
@@ -1146,11 +1154,16 @@ class ZipFile(object):
             zinfo.compress_size = file_size
         zinfo.CRC = CRC
         zinfo.file_size = file_size
-        # Seek backwards and write CRC and file sizes
+        if not zip64 and self._allowZip64:
+            if file_size > ZIP64_LIMIT:
+                raise RuntimeError('File size has increased during compressing')
+            if compress_size > ZIP64_LIMIT:
+                raise RuntimeError('Compressed size larger than uncompressed size')
+        # Seek backwards and write file header (which will now include
+        # correct CRC and file sizes)
         position = self.fp.tell()       # Preserve current position in file
-        self.fp.seek(zinfo.header_offset + 14, 0)
-        self.fp.write(struct.pack("<LLL", zinfo.CRC, zinfo.compress_size,
-              zinfo.file_size))
+        self.fp.seek(zinfo.header_offset, 0)
+        self.fp.write(zinfo.FileHeader(zip64))
         self.fp.seek(position, 0)
         self.filelist.append(zinfo)
         self.NameToInfo[zinfo.filename] = zinfo
@@ -1187,14 +1200,18 @@ class ZipFile(object):
             zinfo.compress_size = len(bytes)    # Compressed size
         else:
             zinfo.compress_size = zinfo.file_size
-        zinfo.header_offset = self.fp.tell()    # Start of header bytes
-        self.fp.write(zinfo.FileHeader())
+        zip64 = zinfo.file_size > ZIP64_LIMIT or \
+                zinfo.compress_size > ZIP64_LIMIT
+        if zip64 and not self._allowZip64:
+            raise LargeZipFile("Filesize would require ZIP64 extensions")
+        self.fp.write(zinfo.FileHeader(zip64))
         self.fp.write(bytes)
-        self.fp.flush()
         if zinfo.flag_bits & 0x08:
             # Write CRC and file sizes after the file data
-            self.fp.write(struct.pack("<LLL", zinfo.CRC, zinfo.compress_size,
+            fmt = '<LQQ' if zip64 else '<LLL'
+            self.fp.write(struct.pack(fmt, zinfo.CRC, zinfo.compress_size,
                   zinfo.file_size))
+        self.fp.flush()
         self.filelist.append(zinfo)
         self.NameToInfo[zinfo.filename] = zinfo
 
diff --git a/Misc/NEWS b/Misc/NEWS
index b69e70c492e..ab219aeaa5a 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -186,6 +186,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #9720: zipfile now writes correct local headers for files larger than
+  4 GiB.
+
 - Issue #16829: IDLE printing no longer fails if there are spaces or other
   special characters in the file path.