diff --git a/corpus/sources/estate.py b/corpus/sources/estate.py index 09da499..09e095b 100644 --- a/corpus/sources/estate.py +++ b/corpus/sources/estate.py @@ -271,6 +271,9 @@ def _file_document(result, client, guide, repo, branch, area, updated, created, result.add_rejection(exclusions.Rejection(path, "gitea", "binary content", full_name)) return None text = raw.decode("utf-8", "replace") + if not text.strip(): + result.add_rejection(exclusions.Rejection(path, "gitea", "empty file", full_name)) + return None hits = exclusions.scan_text(text) if hits: kinds = sorted({hit[0] for hit in hits}) @@ -506,6 +509,9 @@ def _harvest_obsidian(result, client, guide, repos, vault_repo, tree, cfg, base_ result.add_rejection(exclusions.Rejection(path, "obsidian", "binary content")) continue text = raw.decode("utf-8", "replace") + if not text.strip(): + result.add_rejection(exclusions.Rejection(path, "obsidian", "empty file")) + continue hits = exclusions.scan_text(text) if hits: result.add_rejection( @@ -517,6 +523,9 @@ def _harvest_obsidian(result, client, guide, repos, vault_repo, tree, cfg, base_ continue fields, body = _split_note(text, validator) + if not body.strip(): + result.add_rejection(exclusions.Rejection(path, "obsidian", "empty note")) + continue title = str(fields.get("title") or _heading(body) or os.path.splitext(os.path.basename(path))[0]) tag_values = fields.get("tags") or [] if isinstance(tag_values, str):