[Android] Fix checksum handling when md5sum generates unexpected output.

build/android/pylib/utils/md5sum.py

Index: build/android/pylib/utils/md5sum.py
diff --git a/build/android/pylib/utils/md5sum.py b/build/android/pylib/utils/md5sum.py
index da3cd15c785b0da5a2382816078d6817f63fc7aa..9bbd8bc8d5e568eb620be4951e326acb3cab9c8d 100644
--- a/build/android/pylib/utils/md5sum.py
+++ b/build/android/pylib/utils/md5sum.py
@@ -5,6 +5,7 @@
 import collections
 import logging
 import os
+import re
 import tempfile
 import types
 
@@ -21,6 +22,8 @@ MD5SUM_DEVICE_SCRIPT_FORMAT = (
     'test -f {path} -o -d {path} '
     '&& LD_LIBRARY_PATH={md5sum_lib} {device_pie_wrapper} {md5sum_bin} {path}')
 
+_STARTS_WITH_CHECKSUM_RE = re.compile(r'^\s*[0-9a-fA-f]{32}\s+')
+
 
 def CalculateHostMd5Sums(paths):
   """Calculates the MD5 sum value for all items in |paths|.
@@ -28,7 +31,7 @@ def CalculateHostMd5Sums(paths):
   Args:
     paths: A list of host paths to md5sum.
   Returns:
-    A list of named tuples with 'hash' and 'path' attributes.
+    A dict mapping paths to their respective md5sum checksums.
   """
   if isinstance(paths, basestring):
     paths = [paths]
@@ -36,7 +39,8 @@ def CalculateHostMd5Sums(paths):
   out = cmd_helper.GetCmdOutput(
       [os.path.join(constants.GetOutDirectory(), 'md5sum_bin_host')] +
           [p for p in paths])
-  return [HashAndPath(*l.split(None, 1)) for l in out.splitlines()]
+
+  return _ParseMd5SumOutput(out.splitlines())
 
 
 def CalculateDeviceMd5Sums(paths, device):
@@ -45,7 +49,7 @@ def CalculateDeviceMd5Sums(paths, device):
   Args:
     paths: A list of device paths to md5sum.
   Returns:
-    A list of named tuples with 'hash' and 'path' attributes.
+    A dict mapping paths to their respective md5sum checksums.
   """
   if isinstance(paths, basestring):
     paths = [paths]
@@ -72,5 +76,11 @@ def CalculateDeviceMd5Sums(paths, device):
       device.adb.Push(md5sum_script_file.name, md5sum_device_script_file.name)
       out = device.RunShellCommand(['sh', md5sum_device_script_file.name])
 
-  return [HashAndPath(*l.split(None, 1)) for l in out if l]
+  return _ParseMd5SumOutput(out)
+
+
+def _ParseMd5SumOutput(out):
+  hash_and_path = (l.split(None, 1) for l in out
+                   if l and _STARTS_WITH_CHECKSUM_RE.match(l))
+  return dict((p, h) for h, p in hash_and_path)

[perezju, 2015/04/24 08:06:32]

nit: can be written as:

  return {p: h for h, p in hash_and_path}

[jbudorick, 2015/04/24 13:56:36]

We have generally avoided dictionary comprehensions for reasons I don't
remember.

[perezju, 2015/04/24 14:13:25]

hmmm, strange, but ok.