Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Do not perform domain substitutions within comments #1026

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 38 additions & 0 deletions utils/domain_substitution.py
Original file line number Diff line number Diff line change
Expand Up @@ -102,11 +102,36 @@ def _substitute_path(path, regex_iter):
continue
if not content:
raise UnicodeDecodeError('Unable to decode with any encoding: %s' % path)

# list that will contain the comments
comments = []
replace_comments = (path.suffix == '.java' or path.suffix == '.cc' or path.suffix == '.h'
or path.suffix == '.js' or path.suffix == '.cpp' or path.suffix == '.c')
if replace_comments:
content = re.sub(
r'(\/\*.*?\*/\n|\s\/\/[^\n]+)',
lambda match: _replace_comments(comments, match.group(0)),
content,
flags=re.DOTALL)
if path.suffix == '.py' or path.suffix == '.gn':
content = re.sub(
# docstrings not supported
r'\s\#[^\n]+',
lambda match: _replace_comments(comments, match.group(0)),
content,
flags=re.DOTALL)
replace_comments = True

file_subs = 0
for regex_pair in regex_iter:
content, sub_count = regex_pair.pattern.subn(regex_pair.replacement, content)
file_subs += sub_count
if file_subs > 0:
if replace_comments:
# restore comments
content = re.sub(PLACE_HOLDER + r'(\d+):',
lambda match: _restore_comments(comments, match.group(1)), content)

substituted_content = content.encode(encoding)
input_file.seek(0)
input_file.write(content.encode(encoding))
Expand All @@ -115,6 +140,19 @@ def _substitute_path(path, regex_iter):
return (None, None)


# use a randomized placeholder for comment replacements
PLACE_HOLDER = ':C7yae7ozv:'


def _replace_comments(comments, comment):
comments.append(comment)
return PLACE_HOLDER + str(len(comments)) + ':'


def _restore_comments(comments, index):
return comments[int(index) - 1]


def _validate_file_index(index_file, resolved_tree, cache_index_files):
"""
Validation of file index and hashes against the source tree.
Expand Down