yxqo41main commited on
Commit
d76efca
·
verified ·
1 Parent(s): d4a57ba

Upload 3 files

Browse files
Files changed (3) hide show
  1. Dockerfile +2 -2
  2. main.py +50 -26
  3. requirements.txt +1 -0
Dockerfile CHANGED
@@ -11,11 +11,11 @@ COPY . /app
11
  RUN pip install --no-cache-dir -r requirements.txt
12
 
13
  # Make port 8000 available to the world outside this container
14
- EXPOSE 7860
15
 
16
  # Define environment variables
17
  ENV NAME KalamalahQuranAPI
18
  ENV USE_HF_CDN true
19
 
20
  # Run uvicorn when the container launches
21
- CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
 
11
  RUN pip install --no-cache-dir -r requirements.txt
12
 
13
  # Make port 8000 available to the world outside this container
14
+ EXPOSE 8000
15
 
16
  # Define environment variables
17
  ENV NAME KalamalahQuranAPI
18
  ENV USE_HF_CDN true
19
 
20
  # Run uvicorn when the container launches
21
+ CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
main.py CHANGED
@@ -27,7 +27,10 @@ app.add_middleware(
27
 
28
  # Environment configuration
29
  USE_HF_CDN = os.getenv("USE_HF_CDN", "false").lower() == "true"
30
- HF_DATASET_URL = "https://huggingface.co/datasets/Kalamalah/cdn/raw/main"
 
 
 
31
 
32
  # Base paths
33
  BASE_DIR = Path(__file__).parent.parent
@@ -148,15 +151,20 @@ async def root():
148
  async def get_surahs():
149
  if USE_HF_CDN:
150
  try:
151
- hf_url = f"{HF_DATASET_URL}/api_data/surahs.json"
152
- response = requests.get(hf_url, timeout=10)
153
- response.raise_for_status()
154
- data = response.json()
 
 
 
 
155
  if data and data.get("code") == 200:
156
  return JSONResponse(content=data["data"])
157
  raise HTTPException(status_code=404, detail="Surahs data not found")
158
  except Exception as e:
159
- raise HTTPException(status_code=500, detail=str(e))
 
160
  else:
161
  if SURAHS_DATA and SURAHS_DATA.get("code") == 200:
162
  return JSONResponse(content=SURAHS_DATA["data"])
@@ -181,13 +189,16 @@ async def get_quran_text(language: str, surah_number: int, ayah_number: int = No
181
  "tafsir": "ar.muyassar.json"
182
  }
183
  file_name = edition_map.get(language, f"{language}.json")
184
- hf_url = f"{HF_DATASET_URL}/api_data/surah/{surah_number}/{file_name}"
185
- headers = {"Authorization": f"Bearer {HF_TOKEN}"} if HF_TOKEN else {}
186
 
187
  try:
188
- response = requests.get(hf_url, timeout=10)
189
- response.raise_for_status()
190
- data = response.json()
 
 
 
 
 
191
 
192
  if ayah_number:
193
  if data.get("code") == 200:
@@ -198,7 +209,8 @@ async def get_quran_text(language: str, surah_number: int, ayah_number: int = No
198
 
199
  return JSONResponse(content=data.get("data", data))
200
  except Exception as e:
201
- raise HTTPException(status_code=500, detail=str(e))
 
202
  else:
203
  surah_dir = API_DATA_DIR / "surah" / str(surah_number)
204
  if not surah_dir.exists():
@@ -239,8 +251,18 @@ async def get_quran_text(language: str, surah_number: int, ayah_number: int = No
239
  async def get_mushaf_page(mushaf_name: str, page_number: int):
240
  if USE_HF_CDN:
241
  for ext in [".jpg", ".jpeg", ".png"]:
242
- hf_url = f"{HF_DATASET_URL}/mushafs/{mushaf_name}/{page_number}{ext}"
243
- return RedirectResponse(url=hf_url)
 
 
 
 
 
 
 
 
 
 
244
  raise HTTPException(status_code=404, detail="Page not found")
245
  else:
246
  mushaf_dir = MUSHAFS_DIR / mushaf_name
@@ -298,25 +320,27 @@ async def get_reciter_audio(reciter_name: str, recitation_type: str, surah_numbe
298
  # If not found locally and USE_HF_CDN is true, try to fetch from HF CDN
299
  if USE_HF_CDN:
300
  print(f"[DEBUG] USE_HF_CDN is True. HF_TOKEN present: {bool(HF_TOKEN)}")
301
- hf_url = f"{HF_DATASET_URL}/reciters/audio/{reciter_name}/{recitation_type}/{surah_str_padded}.mp3"
302
- headers = {"Authorization": f"Bearer {HF_TOKEN}"} if HF_TOKEN else {}
303
- print(f"[DEBUG] Attempting to fetch from HF CDN: {hf_url} with headers: {bool(headers)}")
304
  try:
305
- # Use stream=True to avoid loading the entire file into memory
306
- response = requests.get(hf_url, stream=True, headers=headers, timeout=10)
307
- print(f"[DEBUG] Received response from HF CDN: {response.status_code}")
308
- response.raise_for_status() # Raise an exception for HTTP errors (4xx or 5xx)
309
-
310
- # Return a StreamingResponse
311
- return StreamingResponse(response.iter_content(chunk_size=8192),
312
- media_type=response.headers.get('Content-Type', 'audio/mpeg'),
313
- headers={"Content-Disposition": f"attachment; filename='{surah_str_padded}.mp3'"})
314
  except requests.exceptions.HTTPError as e:
315
  print(f"HTTP Error fetching from HF CDN: {e.response.status_code} - {e.response.text}")
316
  raise HTTPException(status_code=e.response.status_code, detail=f"Failed to fetch audio from CDN: {e.response.status_code}")
317
  except requests.exceptions.RequestException as e:
318
  print(f"Network Error fetching from HF CDN: {e}")
319
  raise HTTPException(status_code=500, detail=f"Network error fetching audio from CDN: {e}")
 
 
 
320
 
321
  raise HTTPException(status_code=404, detail="Audio file not found")
322
 
 
27
 
28
  # Environment configuration
29
  USE_HF_CDN = os.getenv("USE_HF_CDN", "false").lower() == "true"
30
+ HF_DATASET_URL = "Kalamalah/cdn" # This will be the repo_id
31
+ HF_TOKEN = os.getenv("HF_TOKEN")
32
+
33
+ api = HfApi(token=HF_TOKEN)
34
 
35
  # Base paths
36
  BASE_DIR = Path(__file__).parent.parent
 
151
  async def get_surahs():
152
  if USE_HF_CDN:
153
  try:
154
+ local_path = hf_hub_download(
155
+ repo_id=HF_DATASET_URL,
156
+ filename="api_data/surahs.json",
157
+ repo_type="dataset",
158
+ token=HF_TOKEN
159
+ )
160
+ with open(local_path, "r", encoding="utf-8") as f:
161
+ data = json.load(f)
162
  if data and data.get("code") == 200:
163
  return JSONResponse(content=data["data"])
164
  raise HTTPException(status_code=404, detail="Surahs data not found")
165
  except Exception as e:
166
+ print(f"Error fetching surahs from HF CDN: {e}")
167
+ raise HTTPException(status_code=500, detail=f"Failed to fetch surahs from CDN: {e}")
168
  else:
169
  if SURAHS_DATA and SURAHS_DATA.get("code") == 200:
170
  return JSONResponse(content=SURAHS_DATA["data"])
 
189
  "tafsir": "ar.muyassar.json"
190
  }
191
  file_name = edition_map.get(language, f"{language}.json")
 
 
192
 
193
  try:
194
+ local_path = hf_hub_download(
195
+ repo_id=HF_DATASET_URL,
196
+ filename=f"api_data/surah/{surah_number}/{file_name}",
197
+ repo_type="dataset",
198
+ token=HF_TOKEN
199
+ )
200
+ with open(local_path, "r", encoding="utf-8") as f:
201
+ data = json.load(f)
202
 
203
  if ayah_number:
204
  if data.get("code") == 200:
 
209
 
210
  return JSONResponse(content=data.get("data", data))
211
  except Exception as e:
212
+ print(f"Error fetching Quran text from HF CDN: {e}")
213
+ raise HTTPException(status_code=500, detail=f"Failed to fetch Quran text from CDN: {e}")
214
  else:
215
  surah_dir = API_DATA_DIR / "surah" / str(surah_number)
216
  if not surah_dir.exists():
 
251
  async def get_mushaf_page(mushaf_name: str, page_number: int):
252
  if USE_HF_CDN:
253
  for ext in [".jpg", ".jpeg", ".png"]:
254
+ filename = f"mushafs/{mushaf_name}/{page_number}{ext}"
255
+ try:
256
+ local_path = hf_hub_download(
257
+ repo_id=HF_DATASET_URL,
258
+ filename=filename,
259
+ repo_type="dataset",
260
+ token=HF_TOKEN
261
+ )
262
+ return FileResponse(local_path, media_type=f"image/{ext[1:]}")
263
+ except Exception as e:
264
+ print(f"Error fetching mushaf page from HF CDN: {e}")
265
+ continue # Try next extension
266
  raise HTTPException(status_code=404, detail="Page not found")
267
  else:
268
  mushaf_dir = MUSHAFS_DIR / mushaf_name
 
320
  # If not found locally and USE_HF_CDN is true, try to fetch from HF CDN
321
  if USE_HF_CDN:
322
  print(f"[DEBUG] USE_HF_CDN is True. HF_TOKEN present: {bool(HF_TOKEN)}")
323
+ surah_str_padded = str(surah_number).zfill(3)
324
+ filename = f"reciters/audio/{reciter_name}/{recitation_type}/{surah_str_padded}.mp3"
325
+ print(f"[DEBUG] Attempting to fetch from HF CDN: {filename}")
326
  try:
327
+ local_path = hf_hub_download(
328
+ repo_id=HF_DATASET_URL,
329
+ filename=filename,
330
+ repo_type="dataset",
331
+ token=HF_TOKEN
332
+ )
333
+ print(f"[DEBUG] Successfully downloaded {filename} to {local_path}")
334
+ return FileResponse(local_path, media_type="audio/mpeg")
 
335
  except requests.exceptions.HTTPError as e:
336
  print(f"HTTP Error fetching from HF CDN: {e.response.status_code} - {e.response.text}")
337
  raise HTTPException(status_code=e.response.status_code, detail=f"Failed to fetch audio from CDN: {e.response.status_code}")
338
  except requests.exceptions.RequestException as e:
339
  print(f"Network Error fetching from HF CDN: {e}")
340
  raise HTTPException(status_code=500, detail=f"Network error fetching audio from CDN: {e}")
341
+ except Exception as e:
342
+ print(f"Error fetching audio from HF CDN: {e}")
343
+ raise HTTPException(status_code=500, detail=f"Failed to fetch audio from CDN: {e}")
344
 
345
  raise HTTPException(status_code=404, detail="Audio file not found")
346
 
requirements.txt CHANGED
@@ -4,3 +4,4 @@ scalar-fastapi>=1.0.0
4
  python-multipart>=0.0.6
5
  typing-inspect>=0.9.0
6
  requests>=2.31.0
 
 
4
  python-multipart>=0.0.6
5
  typing-inspect>=0.9.0
6
  requests>=2.31.0
7
+ huggingface_hub>=0.20.0