66 lines
1.7 KiB
Python
66 lines
1.7 KiB
Python
|
import json
|
||
|
|
from argparse import ArgumentParser
|
||
|
|
from time import time
|
||
|
|
|
||
|
|
import numpy as np
|
||
|
|
|
||
|
|
from archive_item import cache_item, fetch_item
|
||
|
|
from engine import analyze_doc
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
parser = ArgumentParser()
|
||
|
|
parser.add_argument("--item-id")
|
||
|
|
parser.add_argument("--cpus", type=int, default=4)
|
||
|
|
args = parser.parse_args()
|
||
|
|
|
||
|
|
cache_item(
|
||
|
|
args.item_id,
|
||
|
|
# Will not refetch if value is already cached.
|
||
|
|
overwrite=False,
|
||
|
|
)
|
||
|
|
item = fetch_item(args.item_id, use_cache=True)
|
||
|
|
|
||
|
|
t_start = time()
|
||
|
|
|
||
|
|
minimal_docs = (
|
||
|
|
[doc for doc in item.docs if doc.name != ""]
|
||
|
|
if len(item.docs) > 1
|
||
|
|
else item.docs
|
||
|
|
)
|
||
|
|
analyses = [
|
||
|
|
analyze_doc(doc, parallel=args.cpus, use_cache=True) for doc in minimal_docs
|
||
|
|
]
|
||
|
|
|
||
|
|
t_end = time()
|
||
|
|
|
||
|
|
print(
|
||
|
|
json.dumps(
|
||
|
|
{
|
||
|
|
"analyses": analyses,
|
||
|
|
"duration_secs": t_end - t_start,
|
||
|
|
"disoriented_pages": [
|
||
|
|
[
|
||
|
|
i
|
||
|
|
for i, page in enumerate(doc["pages"])
|
||
|
|
if not page["ocr_orientation_match"]
|
||
|
|
]
|
||
|
|
for doc in analyses
|
||
|
|
],
|
||
|
|
"sharpness_max": max(
|
||
|
|
*[page["sharpness"] for doc in analyses for page in doc["pages"]]
|
||
|
|
),
|
||
|
|
"sharpness_median": np.median(
|
||
|
|
[page["sharpness"] for doc in analyses for page in doc["pages"]]
|
||
|
|
).tolist(),
|
||
|
|
"sharpness_min": min(
|
||
|
|
*[page["sharpness"] for doc in analyses for page in doc["pages"]]
|
||
|
|
),
|
||
|
|
}
|
||
|
|
)
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|