sam/ai-resume
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ingestion: group oversize and binary rejections in the report

Browse Source
This commit is contained in:
Paperclip Builder
2026-10-26 22:36:34 +11:00
parent 720feddfcc
commit 0b910d216e
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
corpus/sources/estate.py
View File

@@ -54,7 +54,14 @@ class Harvest:
def rejection_summary(self) -> dict: def rejection_summary(self) -> dict:
counts = {} counts = {}
for row in self.rejections: for row in self.rejections:
key = f"{row.get('platform')}/{row.get('reason')}" reason = str(row.get("reason") or "unknown")
# Keep the summary readable: 200 distinct oversize byte counts are
# one finding, not two hundred.
if reason.startswith("oversize"):
reason = "oversize"
elif reason.startswith("binary"):
reason = "binary"
key = f"{row.get('platform')}/{reason}"
counts[key] = counts.get(key, 0) + 1 counts[key] = counts.get(key, 0) + 1
return dict(sorted(counts.items())) return dict(sorted(counts.items()))