cropping summaries

This commit is contained in:
2026-09-10 20:03:23 +02:00
parent dfce79f240
commit 060859ddef
4 changed files with 120 additions and 4 deletions
+26 -1
View File
@@ -83,6 +83,26 @@ def process_copies(files: list[Path], staging: Path, workers: int) -> list[dict]
key=lambda row: (order[row["file"]], row["page"]))
def crop_statistics(records: list[dict]) -> tuple[int, float, int]:
"""Return cropped page count, their mean removed percentage, and >30% count."""
percentages: list[float] = []
for record in records:
removed_mm = record["top_removed_mm"] + record["bottom_removed_mm"]
if removed_mm <= 0:
continue
x0, y0, x1, y1 = record["original_cropbox"]
original_height_points = (
x1 - x0 if record.get("rotation", 0) % 180 else y1 - y0
)
if original_height_points <= 0:
continue
original_height_mm = original_height_points * 25.4 / 72
percentages.append(min(100.0, removed_mm / original_height_mm * 100))
mean_percentage = sum(percentages) / len(percentages) if percentages else 0.0
over_thirty = sum(percentage > 30 for percentage in percentages)
return len(percentages), mean_percentage, over_thirty
def run(workspace: EvaluationWorkspace, target: Path, *, workers: int = 5) -> ExitCode:
if workers < 1:
raise CliError("Le nombre de traitements parallèles doit être positif.",
@@ -109,9 +129,14 @@ def run(workspace: EvaluationWorkspace, target: Path, *, workers: int = 5) -> Ex
(backup/"report.json").write_text(json.dumps(records, ensure_ascii=False, indent=2),
encoding="utf-8")
print(f"Sauvegarde des PDF non rognés : {originals}", flush=True)
cropped = sum(row["top_removed_mm"]+row["bottom_removed_mm"] > 0 for row in records)
cropped, mean_percentage, over_thirty = crop_statistics(records)
print(f"Terminé : {cropped}/{len(records)} pages rognées ; "
f"{len(files)} PDF remplacés dans Copies.", flush=True)
print(
f"Rognage moyen des pages modifiées : {mean_percentage:.1f} % ; "
f"{over_thirty} page(s) rognée(s) de plus de 30 %.",
flush=True,
)
return ExitCode.SUCCESS