Spaces:
Sleeping
Sleeping
Upload 2 files
Browse files- script/create_sqlite_db.py +20 -3
- script/test_api.py +35 -0
script/create_sqlite_db.py
CHANGED
|
@@ -1,21 +1,27 @@
|
|
| 1 |
import sqlite3
|
| 2 |
import pandas as pd
|
|
|
|
| 3 |
import itertools
|
| 4 |
import ast
|
| 5 |
import uuid
|
|
|
|
| 6 |
from pathlib import Path
|
| 7 |
|
| 8 |
# Initialisations
|
| 9 |
print("Initialisations ...")
|
|
|
|
| 10 |
DATA_DIR = Path("../data") # dossier parent du script
|
| 11 |
-
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
| 13 |
# Créer le dossier data s'il n'existe pas
|
| 14 |
DATA_DIR.mkdir(exist_ok=True)
|
| 15 |
|
| 16 |
# Chargement des données
|
| 17 |
print("Chargement des données ...")
|
| 18 |
-
df = pd.read_parquet(
|
| 19 |
|
| 20 |
# Initialisations de la base SQLite
|
| 21 |
print("Initialisations de la base SQLite ...")
|
|
@@ -96,4 +102,15 @@ for _, row in df.iterrows():
|
|
| 96 |
|
| 97 |
conn.commit()
|
| 98 |
conn.close()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
print("Traitement terminé.")
|
|
|
|
| 1 |
import sqlite3
|
| 2 |
import pandas as pd
|
| 3 |
+
import os
|
| 4 |
import itertools
|
| 5 |
import ast
|
| 6 |
import uuid
|
| 7 |
+
from huggingface_hub import hf_hub_download, upload_file
|
| 8 |
from pathlib import Path
|
| 9 |
|
| 10 |
# Initialisations
|
| 11 |
print("Initialisations ...")
|
| 12 |
+
hf_token = os.environ["API_HF_TOKEN"]
|
| 13 |
DATA_DIR = Path("../data") # dossier parent du script
|
| 14 |
+
parquet_path = hf_hub_download(repo_id="Loren/articles_data",
|
| 15 |
+
filename="mon_fichier.parquet")
|
| 16 |
+
REPO_ID = "Loren/articles_db" # dataset HF
|
| 17 |
+
DB_NAME = 'articles.db'
|
| 18 |
+
SQLITE_FILE = DATA_DIR / DB_NAME
|
| 19 |
# Créer le dossier data s'il n'existe pas
|
| 20 |
DATA_DIR.mkdir(exist_ok=True)
|
| 21 |
|
| 22 |
# Chargement des données
|
| 23 |
print("Chargement des données ...")
|
| 24 |
+
df = pd.read_parquet(parquet_path)
|
| 25 |
|
| 26 |
# Initialisations de la base SQLite
|
| 27 |
print("Initialisations de la base SQLite ...")
|
|
|
|
| 102 |
|
| 103 |
conn.commit()
|
| 104 |
conn.close()
|
| 105 |
+
|
| 106 |
+
# Upload dans le dataset hugging face
|
| 107 |
+
print("Upload dans le dataset hugging face ...")
|
| 108 |
+
upload_file(
|
| 109 |
+
path_or_fileobj=SQLITE_FILE,
|
| 110 |
+
path_in_repo=DB_NAME,
|
| 111 |
+
repo_id=REPO_ID,
|
| 112 |
+
repo_type="dataset",
|
| 113 |
+
token=hf_token
|
| 114 |
+
)
|
| 115 |
+
|
| 116 |
print("Traitement terminé.")
|
script/test_api.py
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import requests
|
| 2 |
+
|
| 3 |
+
BASE_URL = "http://localhost:8000" # ⚠️ changer en URL HF Space si déployé
|
| 4 |
+
|
| 5 |
+
def test_get_tags():
|
| 6 |
+
print("🔍 Test: /get_tags")
|
| 7 |
+
resp = requests.get(f"{BASE_URL}/get_tags")
|
| 8 |
+
if resp.status_code != 200:
|
| 9 |
+
print("❌ Erreur", resp.status_code, resp.text)
|
| 10 |
+
return
|
| 11 |
+
tags = resp.json().get("tags", [])
|
| 12 |
+
print(f"✅ {len(tags)} tags récupérés : {tags[:10]}...") # affiche 10 premiers
|
| 13 |
+
|
| 14 |
+
return tags
|
| 15 |
+
|
| 16 |
+
def test_get_articles_with_tags(tags):
|
| 17 |
+
if not tags:
|
| 18 |
+
print("⚠️ Aucun tag trouvé, test sauté")
|
| 19 |
+
return
|
| 20 |
+
|
| 21 |
+
print("\n🔍 Test: /get_articles_with_tags")
|
| 22 |
+
params = {"tags": tags}
|
| 23 |
+
resp = requests.get(f"{BASE_URL}/get_articles_with_tags", params=params)
|
| 24 |
+
if resp.status_code != 200:
|
| 25 |
+
print("❌ Erreur", resp.status_code, resp.text)
|
| 26 |
+
return
|
| 27 |
+
data = resp.json()
|
| 28 |
+
print(f"✅ Articles trouvés: {len(data['articles'])}")
|
| 29 |
+
|
| 30 |
+
def main():
|
| 31 |
+
tags = test_get_tags()
|
| 32 |
+
test_get_articles_with_tags(tags)
|
| 33 |
+
|
| 34 |
+
if __name__ == "__main__":
|
| 35 |
+
main()
|