def normalize_blob(blob, conversion, binary_detection):
""" Takes a blob as input returns either the original blob if
binary_detection is True and the blob content looks like binary, else
return a new blob with converted data
"""
# Read the original blob
data = blob.data
# If we need to detect if a file is binary and the file is detected as
# binary, do not apply the conversion function and return the original
# chunked text
if binary_detection is True:
if is_binary(data):
return blob
# Now apply the conversion
converted_data = conversion(data)
new_blob = Blob()
new_blob.data = converted_data
return new_blob
def normalize_blob(blob, conversion, binary_detection):
""" Takes a blob as input returns either the original blob if
binary_detection is True and the blob content looks like binary, else
return a new blob with converted data
"""
# Read the original blob
data = blob.data
# If we need to detect if a file is binary and the file is detected as
# binary, do not apply the conversion function and return the original
# chunked text
if binary_detection is True:
if is_binary(data):
return blob
# Now apply the conversion
converted_data = conversion(data)
new_blob = Blob()
new_blob.data = converted_data
return new_blob
def fn(info):
path, mode, sha = info
return path is None or (type(store[sha]) is Blob
and not is_binary(store[sha].data))
def fn(info):
path, mode, sha = info
return path is None or (type(store[sha]) is Blob and not is_binary(store[sha].data))
def difflist(self, old_rev, new_rev):
r = self.repo
store = r.object_store
try:
old_tree = r[old_rev].tree
except KeyError:
old_tree = self.head()
new_tree = r[new_rev].tree
changes = store.tree_changes(old_tree, new_tree)
def shortid(hexsha):
if hexsha is None:
return '0' * 7
return hexsha[:7]
def content(mode, hexsha):
if hexsha is None:
return ''
elif S_ISGITLINK(mode):
return 'Submodule commit {}\n'.format(hexsha)
else:
return store[hexsha].data
def lines(content):
if not content:
return []
else:
return content.splitlines(True)
tree = {'stats': {'files_added': 0,
'files_deleted': 0,
'lines_added': 0,
'lines_deleted': 0,
'lines_added_ratio': 0,
'lines_deleted_ratio': 0},
'changes': []}
for path, mode, sha in changes:
old_path, old_mode, old_sha = path[1], mode[1], sha[1]
new_path, new_mode, new_sha = path[0], mode[0], sha[0]
file_added = False
file_deleted = False
if not old_path:
old_path = new_path
file_added = True
if not new_path:
new_path = old_path
file_deleted = True
# Construct our object entry
entry = {'old_path': old_path,
'new_path': new_path,
'old_mode': old_mode,
'new_mode': new_mode,
'file_added': file_added,
'file_deleted': file_deleted,
'lines_added': 0,
'lines_deleted': 0,
'diff': []}
# Fetch all of the content
old_content = content(old_mode, old_sha)
new_content = content(new_mode, new_sha)
if is_binary(old_content) or is_binary(new_content):
msg = 'Binary files {} and {} are different'
entry['diff'] = msg.format(old_path, new_path)
entry['lines_added'] = 0
entry['lines_deleted'] = 0
entry['lines_added_ratio'] = 0
entry['lines_deleted_ratio'] = 0
else:
# Diff the file for changes
new_lines = lines(new_content)
old_lines = lines(old_content)
diff, added, deleted = unified_diff(old_lines, new_lines)
entry['diff'] = diff
entry['lines_added'] += added
entry['lines_deleted'] += deleted
total = float(entry['lines_added'] + entry['lines_deleted'])
if total > 0:
lines_added = entry['lines_added'] * 100.0
lines_deleted = entry['lines_deleted'] * 100.0
entry['lines_added_ratio'] = lines_added / total
entry['lines_deleted_ratio'] = lines_deleted / total
# Aggregate statistics
tree['stats']['lines_added'] += entry['lines_added']
tree['stats']['lines_deleted'] += entry['lines_deleted']
tree['changes'].append(entry)
return tree
