From 082f334c22f2a84aaa38de67f5e88473f8e664a6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jukka=20Jyl=C3=A4nki?= <jujjyl@gmail.com>
Date: Tue, 19 Nov 2013 15:26:45 +0200
Subject: [PATCH] If URL download fails, delete the partially downloaded file
 (if it exists). If unzipping fails, print an error, and if the zip was
 corrupted, delete the corrupted file. Fixes
 https://github.com/kripken/emscripten/issues/1687.

---
 emsdk | 122 +++++++++++++++++++++++++++++++---------------------------
 1 file changed, 65 insertions(+), 57 deletions(-)

diff --git a/emsdk b/emsdk
index 47a7fb0..c6757dc 100644
--- a/emsdk
+++ b/emsdk
@@ -110,49 +110,54 @@ def unzip(source_filename, dest_dir, unpack_even_if_exists=False):
   print "Unpacking '" + source_filename + "' to '" + dest_dir + "'"
   mkdir_p(dest_dir)
   common_subdir = None
-  with zipfile.ZipFile(source_filename) as zf:
-    # Implement '--strip 1' behavior to unzipping by testing if all the files in the zip reside in a common subdirectory, and if so,
-    # we move the output tree at the end of uncompression step.
-    for member in zf.infolist():
-      words = member.filename.split('/')
-      if common_subdir == None:
-        common_subdir = words[0]
-      elif common_subdir != words[0]:
-        common_subdir = ''
-        break
+  try:
+    with zipfile.ZipFile(source_filename) as zf:
+      # Implement '--strip 1' behavior to unzipping by testing if all the files in the zip reside in a common subdirectory, and if so,
+      # we move the output tree at the end of uncompression step.
+      for member in zf.infolist():
+        words = member.filename.split('/')
+        if len(words) > 1: # If there is a directory component?
+          if common_subdir == None:
+            common_subdir = words[0]
+          elif common_subdir != words[0]:
+            common_subdir = ''
+            break
 
-    unzip_to_dir = dest_dir
-    if common_subdir:
-      unzip_to_dir = os.path.join('/'.join(dest_dir.split('/')[:-1]), 'unzip_temp')
+      unzip_to_dir = dest_dir
+      if common_subdir:
+        unzip_to_dir = os.path.join('/'.join(dest_dir.split('/')[:-1]), 'unzip_temp')
 
-    # Now do the actual decompress.
-    for member in zf.infolist():
-      # Path traversal defense copied from
-      # http://hg.python.org/cpython/file/tip/Lib/http/server.py#l789
-      words = member.filename.split('/')
-#      print "words: " + str(words)
-      path = unzip_to_dir
-      for word in words[:-1]:
-        drive, word = os.path.splitdrive(word)
-        head, word = os.path.split(word)
-        if word in (os.curdir, os.pardir, ''): continue
-        path = os.path.join(path, word)
-#      print "Extracting " + member.filename + " to " + path
-#      zf.extract(member, path)
-#      print "Extracting " + member.filename + " to " + unzip_to_dir
-      zf.extract(member, unzip_to_dir)
+      # Now do the actual decompress.
+      for member in zf.infolist():
+        # Path traversal defense copied from
+        # http://hg.python.org/cpython/file/tip/Lib/http/server.py#l789
+        words = member.filename.split('/')
+        path = unzip_to_dir
+        for word in words[:-1]:
+          drive, word = os.path.splitdrive(word)
+          head, word = os.path.split(word)
+          if word in (os.curdir, os.pardir, ''): continue
+          path = os.path.join(path, word)
+        zf.extract(member, unzip_to_dir)
 
-    if common_subdir:
-      try:
-        if os.path.exists(dest_dir):
-          shutil.rmtree(dest_dir)
-      except:
-        pass
-      shutil.copytree(os.path.join(unzip_to_dir, common_subdir), dest_dir)
-      try:
-        shutil.rmtree(unzip_to_dir)
-      except:
-        pass
+      if common_subdir:
+        try:
+          if os.path.exists(dest_dir):
+            shutil.rmtree(dest_dir)
+        except:
+          pass
+        shutil.copytree(os.path.join(unzip_to_dir, common_subdir), dest_dir)
+        try:
+          shutil.rmtree(unzip_to_dir)
+        except:
+          pass
+  except zipfile.BadZipfile, e:
+    print "Unzipping file '" + source_filename + "' failed due to reason: " + str(e) + "! Removing the corrupted zip file."
+    rmfile(source_filename)
+    return False
+  except Exception, e:
+    print "Unzipping file '" + source_filename + "' failed due to reason: " + str(e)
+    return False
 
   return True
 
@@ -190,27 +195,30 @@ def download_file(url, dstpath, download_even_if_exists=False):
   try:
     u = urllib2.urlopen(url)
     mkdir_p(os.path.dirname(file_name))
-    f = open(file_name, 'wb')
-    meta = u.info()
-    file_size = int(meta.getheaders("Content-Length")[0])
-    print "Downloading: %s from %s Bytes: %s" % (file_name, url, file_size)
+    with open(file_name, 'wb') as f: 
+      meta = u.info()
+      file_size = int(meta.getheaders("Content-Length")[0])
+      print "Downloading: %s from %s Bytes: %s" % (file_name, url, file_size)
 
-    file_size_dl = 0
-    block_sz = 8192
-    while True:
-        buffer = u.read(block_sz)
-        if not buffer:
-            break
+      file_size_dl = 0
+      block_sz = 8192
+      while True:
+          buffer = u.read(block_sz)
+          if not buffer:
+              break
 
-        file_size_dl += len(buffer)
-        f.write(buffer)
-        status = r"%10d  [%3.2f%%]" % (file_size_dl, file_size_dl * 100. / file_size)
-        status = status + chr(8)*(len(status)+1)
-        print status,
-
-    f.close()
+          file_size_dl += len(buffer)
+          f.write(buffer)
+          status = r"%10d  [%3.2f%%]" % (file_size_dl, file_size_dl * 100. / file_size)
+          status = status + chr(8)*(len(status)+1)
+          print status,
   except urllib2.HTTPError, e:
     print "HTTP error with URL '" + url + "': " + str(e)
+    rmfile(file_name)
+    return None
+  except:
+    print "Error downloading URL '" + url + "'!"
+    rmfile(file_name)
     return None
   return file_name