Skip to content
Open
Show file tree
Hide file tree
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
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
pre-commit hook to remove cell output of .ipynb notebook and some metadata for better security.
pre-commit hook to remove cell output of .ipynb notebook and some metadata for better security/easier git versioning.

Sample config:
```
Expand All @@ -9,6 +9,7 @@ repos:
- id: jupyter-notebook-cleanup
args:
# - --remove-kernel-metadata
# - --remove-widget-state
- --pin-patterns
- "[pin];[donotremove]"
```
Expand Down
14 changes: 10 additions & 4 deletions jupyter_notebook_cleanup/cli.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ def parse_args():
psr.add_argument("files", nargs="*", help="ipynb files")
psr.add_argument("--dry-run", action="store_true", default=False)
psr.add_argument("--remove-kernel-metadata", action="store_true", default=False)
psr.add_argument("--remove-widget-state", action="store_true", default=False)
psr.add_argument(
"-p", "--pin-patterns", default="[pin]", help="semicolon-separated patterns (wildcards are not supported)"
)
Expand All @@ -25,7 +26,8 @@ def main():
patterns = args.pin_patterns.split(";")
for path in args.files:
remove_output_file(
path, patterns=patterns, remove_kernel_metadata=args.remove_kernel_metadata, preview=args.dry_run
path, patterns=patterns, remove_kernel_metadata=args.remove_kernel_metadata,
preview=args.dry_run, remove_widget_state=args.remove_widget_state
)


Expand All @@ -38,7 +40,8 @@ def check_if_unremovable(source, patterns):
return False


def remove_output_file(path, patterns, remove_kernel_metadata, preview):
def remove_output_file(path, patterns, remove_kernel_metadata, preview,
remove_widget_state):
"""If preview=True, Do not overwrite a path, only display an diffs"""
dump_args = {"ensure_ascii": False, "separators": (",", ": "), "indent": 1}
# to preserve timestamps, making temporal copy
Expand All @@ -47,7 +50,8 @@ def remove_output_file(path, patterns, remove_kernel_metadata, preview):
shutil.copy2(path, tpath)
with open(path, "rt", encoding="utf-8") as f:
data = json.load(f, object_pairs_hook=OrderedDict)
new_data = remove_output_object(data, patterns, remove_kernel_metadata)
new_data = remove_output_object(data, patterns, remove_kernel_metadata,
remove_widget_state)
before_j = json.dumps(data, **dump_args)
after_j = json.dumps(new_data, **dump_args)
# ensure eof newlines
Expand All @@ -63,14 +67,16 @@ def remove_output_file(path, patterns, remove_kernel_metadata, preview):
shutil.copystat(tpath, path) # copy original timestamps


def remove_output_object(data, patterns, remove_kernel_metadata):
def remove_output_object(data, patterns, remove_kernel_metadata, remove_widget_state):
new_data = copy.deepcopy(data)
if remove_kernel_metadata:
kernelspec = new_data.get("metadata", {}).get("kernelspec", {})
if "display_name" in kernelspec:
kernelspec["display_name"] = ""
if "name" in kernelspec:
kernelspec["name"] = ""
if remove_widget_state:
new_data.get("metadata", {}).pop("widgets", None)
for cell in new_data["cells"]:
if "execution_count" in cell:
cell["execution_count"] = None
Expand Down