This commit is contained in:
Nyako
2026-06-06 13:30:10 +03:00
parent d1bc3fe836
commit 36a044c8da
2 changed files with 61 additions and 27 deletions
+2 -1
View File
@@ -16,6 +16,7 @@
"file":{
"repos":["data/files"],
"dw":"data/files",
"thumb":"data/thumb"
"thumb":"data/thumb",
"data":"data"
}
}
+59 -26
View File
@@ -1,4 +1,5 @@
import os
import json
from pathlib import Path
def find_file(filename, file_folders):
@@ -17,7 +18,7 @@ def get_size_format(b, factor=1024, suffix="B"):
b /= factor
return f"{b:.2f} P{suffix}"
def get_dir_size(path):
def get_dir_size(path: str):
total = 0
if os.path.exists(path):
for f in os.listdir(path):
@@ -33,6 +34,12 @@ def get_file_list_size(file_list: list[str]):
total += os.path.getsize(fp)
return total
def get_size_edge(type_searсh: bool, file_list: list[str]):
if type_searсh:
return min(file_list, key=os.path.getsize)
else:
return max(file_list, key=os.path.getsize)
def calculate_analytic(database, config):
all_db = database.get_all()
explicit_db = database.get_search(["e"], [])
@@ -40,48 +47,72 @@ def calculate_analytic(database, config):
questionable_db = database.get_search(["q"], [])
general_db = database.get_search(["g"], [])
rating_list_file_path = {"explicit":[], "sensitive":[], "questionable":[], "general":[]}
type_list_file_path = {"images":[], "videos":[], "gifs":[]}
files_not_found = 0
for one_post in all_db:
file_path = find_file(one_post["local_filename"], config["file"]["repos"])
if file_path != None:
rating_list_file_path[one_post["rating"]].append(file_path)
if one_post["is_gif"] == 1:
type_list_file_path["gifs"].append(file_path)
elif one_post["is_video"] == 1:
type_list_file_path["videos"].append(file_path)
else:
type_list_file_path["images"].append(file_path)
else:
files_not_found += 1
file_size_dict = {"explicit":get_file_list_size(rating_list_file_path["explicit"]),
"sensitive":get_file_list_size(rating_list_file_path["sensitive"]),
"questionable":get_file_list_size(rating_list_file_path["questionable"]),
"general":get_file_list_size(rating_list_file_path["general"])
}
type_size_dict = {"images":get_file_list_size(type_list_file_path["images"]),
"videos":get_file_list_size(type_list_file_path["videos"]),
"gifs":get_file_list_size(type_list_file_path["gifs"])}
ratings_stats = {
"explicit": {
"count": len(explicit_db),
"size_formatted": get_size_format(get_file_list_size(rating_list_file_path["explicit"]))
"size_formatted": get_size_format(file_size_dict["explicit"])
},
"sensitive": {
"count": len(sensitive_db),
"size_formatted": get_size_format(get_file_list_size(rating_list_file_path["sensitive"]))
"size_formatted": get_size_format(file_size_dict["sensitive"])
},
"questionable": {
"count": len(questionable_db),
"size_formatted": get_size_format(get_file_list_size(rating_list_file_path["questionable"]))
"size_formatted": get_size_format(file_size_dict["questionable"])
},
"general": {
"count": len(general_db),
"size_formatted": get_size_format(get_file_list_size(rating_list_file_path["general"]))
"size_formatted": get_size_format(file_size_dict["general"])
}
},
}
total_file_data_size = file_size_dict["general"]+file_size_dict["questionable"]+file_size_dict["sensitive"]+file_size_dict["explicit"]
total_thumb_size = get_dir_size(config[["file"]["thumb"]])
total_log_size = get_file_list_size(["logs.log"])
total_db_size = get_file_list_size([os.path.join("data", "db.sqlite")])
weight_stats_smallest = get_size_edge(True, type_list_file_path["gifs"]+type_list_file_path["images"]+type_list_file_path["videos"])
weight_stats_largest = get_size_edge(False, type_list_file_path["gifs"]+type_list_file_path["images"]+type_list_file_path["videos"])
result = {
"total_images_analyzed": len(all_db),
"files_not_found":files_not_found,
"average_weight": {
"bytes": round(avg_size_bytes, 2),
"formatted": get_size_format(avg_size_bytes)
"bytes": round(total_file_data_size/(len(rating_list_file_path["explicit"])+len(rating_list_file_path["sensitive"])+len(rating_list_file_path["questionable"])+len(rating_list_file_path["general"])), 2),
"formatted": get_size_format(round(total_file_data_size/(len(rating_list_file_path["explicit"])+len(rating_list_file_path["sensitive"])+len(rating_list_file_path["questionable"])+len(rating_list_file_path["general"])), 2))
},
"storage_stats": {
"folders": {
"img": get_size_format(size_img),
"json_db": get_size_format(size_json),
"thumb": get_size_format(size_thumb),
"logs": get_size_format(size_logs)
"data": get_size_format(total_file_data_size),
"db": get_size_format(total_db_size),
"thumb": get_size_format(total_thumb_size),
"logs": get_size_format(total_log_size)
},
"types_in_img": {
"images": get_size_format(type_sizes["IMG"]),
"videos": get_size_format(type_sizes["VID"]),
"gifs": get_size_format(type_sizes["GIF"]),
"logs": get_size_format(type_sizes["LOGS"])
"types": {
"images": get_size_format(type_size_dict["images"]),
"videos": get_size_format(type_size_dict["videos"]),
"gifs": get_size_format(type_size_dict["gifs"])
},
"grand_total": get_size_format(grand_total)
"grand_total": get_size_format(total_file_data_size+total_thumb_size+total_log_size+total_db_size)
},
"ratings_stats": ratings_stats,
"resolution_stats": {
@@ -92,21 +123,23 @@ def calculate_analytic(database, config):
},
"smallest": {
"filename": min_res["filename"],
"md5": min_res["md5"] if min_res["area"] != float('inf') else "",
"resolution": f'{min_res["width"]}x{min_res["height"]}' if min_res["area"] != float('inf') else "N/A"
"md5": min_res["md5"],
"resolution": f'{min_res["width"]}x{min_res["height"]}'
}
},
"weight_stats": {
"largest": {
"filename": max_weight["filename"],
"filename": weight_stats_largest,
"md5": max_weight["md5"],
"size_formatted": get_size_format(max_weight["size"])
},
"smallest": {
"filename": min_weight["filename"],
"md5": min_weight["md5"] if min_weight["size"] != float('inf') else "",
"size_formatted": get_size_format(min_weight["size"]) if min_weight["size"] != float('inf') else "N/A"
"filename": weight_stats_smallest,
"md5": min_weight["md5"],
"size_formatted": get_size_format(min_weight["size"])
}
},
"tag_top":database.get_top_tag("")
}
"top_tag":database.get_top_tag("")
}
with open(os.path.join(config["file"]["data"], "analytic.json"), 'w', encoding='utf-8') as out_f:
json.dump(result, out_f, indent=4, ensure_ascii=False)