Fixing broken images

gm/rebaseline_server/imagediffdb.py

 #!/usr/bin/python
 
 """
 Copyright 2013 Google Inc.
 
 Use of this source code is governed by a BSD-style license that can be
 found in the LICENSE file.
 
 Calulate differences between image pairs, and store them in a database.
 """
@@ skipping 32 matching lines @@
 
 RGBDIFFS_SUBDIR = 'diffs'
 WHITEDIFFS_SUBDIR = 'whitediffs'
 
 # Keys used within DiffRecord dictionary representations.
 # NOTE: Keep these in sync with static/constants.js
 KEY__DIFFERENCES__MAX_DIFF_PER_CHANNEL = 'maxDiffPerChannel'
 KEY__DIFFERENCES__NUM_DIFF_PIXELS = 'numDifferingPixels'
 KEY__DIFFERENCES__PERCENT_DIFF_PIXELS = 'percentDifferingPixels'
 KEY__DIFFERENCES__PERCEPTUAL_DIFF = 'perceptualDifference'
+KEY__DIFFERENCES__DIFF_URL = 'diffUrl'
+KEY__DIFFERENCES__WHITE_DIFF_URL = 'whiteDiffUrl'
 
 # Special values within ImageDiffDB._diff_dict
 _DIFFRECORD_FAILED = 'failed'
 _DIFFRECORD_PENDING = 'pending'
 
 # How often to report tasks_queue size
 QUEUE_LOGGING_GRANULARITY = 1000
 
 # Temporary variable to keep track of how many times we download
 # the same file in multiple threads.
@@ skipping 88 matching lines @@
 
       # Get information out of the skpdiff_summary_file.
       with contextlib.closing(open(skpdiff_summary_file)) as fp:
         data = json.load(fp)
 
       # For now, we can assume there is only one record in the output summary,
       # since we passed skpdiff only one pair of images.
       record = data['records'][0]
       self._width = record['width']
       self._height = record['height']
+      self._diffUrl = os.path.split(record['rgbDiffPath'])[1]
+      self._whiteDiffUrl = os.path.split(record['whiteDiffPath'])[1]
+
       # TODO: make max_diff_per_channel a tuple instead of a list, because the
       # structure is meaningful (first element is red, second is green, etc.)
       # See http://stackoverflow.com/a/626871
       self._max_diff_per_channel = [
           record['maxRedDiff'], record['maxGreenDiff'], record['maxBlueDiff']]
       per_differ_stats = record['diffs']
       for stats in per_differ_stats:
         differ_name = stats['differName']
         if differ_name == 'different_pixels':
           self._num_pixels_differing = stats['pointsOfInterest']
         elif differ_name == 'perceptual':
           perceptual_similarity = stats['result']
 
       # skpdiff returns the perceptual similarity; convert it to get the
       # perceptual difference percentage.
       # skpdiff outputs -1 if the images are different sizes. Treat any
       # output that does not lie in [0, 1] as having 0% perceptual
       # similarity.
       if not 0 <= perceptual_similarity <= 1:
         perceptual_similarity = 0
       self._perceptual_difference = 100 - (perceptual_similarity * 100)
+    except: 
+      print "expected:", expected_image_file
+      print "actual  :", actual_image_file
+      raise
     finally:
       shutil.rmtree(skpdiff_output_dir)
 
   # TODO(epoger): Use properties instead of getters throughout.
   # See http://stackoverflow.com/a/6618176
   def get_num_pixels_differing(self):
     """Returns the absolute number of pixels that differ."""
     return self._num_pixels_differing
 
   def get_percent_pixels_differing(self):
@@ skipping 13 matching lines @@
 
   def as_dict(self):
     """Returns a dictionary representation of this DiffRecord, as needed when
     constructing the JSON representation."""
     return {
         KEY__DIFFERENCES__NUM_DIFF_PIXELS: self._num_pixels_differing,
         KEY__DIFFERENCES__PERCENT_DIFF_PIXELS:
             self.get_percent_pixels_differing(),
         KEY__DIFFERENCES__MAX_DIFF_PER_CHANNEL: self._max_diff_per_channel,
         KEY__DIFFERENCES__PERCEPTUAL_DIFF: self._perceptual_difference,
+        KEY__DIFFERENCES__DIFF_URL: self._diffUrl,
+        KEY__DIFFERENCES__WHITE_DIFF_URL: self._whiteDiffUrl, 
     }
 
 
+
 class ImageDiffDB(object):
   """ Calculates differences between image pairs, maintaining a database of
   them for download."""
 
   def __init__(self, storage_root, gs=None,
                num_worker_threads=DEFAULT_NUM_WORKER_THREADS):
     """
     Args:
       storage_root: string; root path within the DB will store all of its stuff
       gs: instance of GSUtils object we can use to download images
@@ skipping 232 matching lines @@
 
   Args:
     locator: string, or something that can be represented as a string.
         If None or '', it is returned without modification, because empty
         locators have a particular meaning ("there is no image for this")
   """
   if locator:
     return DISALLOWED_FILEPATH_CHAR_REGEX.sub('_', str(locator))
   else:
     return locator