Spaces:
Sleeping
Sleeping
Commit
·
eb2e1af
1
Parent(s):
7626f3a
Upd debug logs
Browse files- .DS_Store +0 -0
- app/.DS_Store +0 -0
- app/main.py +12 -0
- app/routers/import_doc.py +33 -13
- app/services/google_books.py +6 -1
.DS_Store
CHANGED
|
Binary files a/.DS_Store and b/.DS_Store differ
|
|
|
app/.DS_Store
CHANGED
|
Binary files a/app/.DS_Store and b/app/.DS_Store differ
|
|
|
app/main.py
CHANGED
|
@@ -18,6 +18,18 @@
|
|
| 18 |
from fastapi import FastAPI, WebSocket
|
| 19 |
from app.routers import search, import_doc
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
app = FastAPI()
|
| 22 |
|
| 23 |
app.include_router(search.router, prefix="/search")
|
|
|
|
| 18 |
from fastapi import FastAPI, WebSocket
|
| 19 |
from app.routers import search, import_doc
|
| 20 |
|
| 21 |
+
# Debugger
|
| 22 |
+
import logging
|
| 23 |
+
logging.basicConfig(
|
| 24 |
+
level=logging.DEBUG,
|
| 25 |
+
format="%(asctime)s — %(name)s — %(levelname)s — %(message)s",
|
| 26 |
+
force=True
|
| 27 |
+
)
|
| 28 |
+
logger = logging.getLogger("book-query")
|
| 29 |
+
logger.setLevel(logging.DEBUG)
|
| 30 |
+
logger.info("🚀 Starting Tutor Book Querier...")
|
| 31 |
+
|
| 32 |
+
|
| 33 |
app = FastAPI()
|
| 34 |
|
| 35 |
app.include_router(search.router, prefix="/search")
|
app/routers/import_doc.py
CHANGED
|
@@ -8,6 +8,9 @@ import aiofiles, uuid, os
|
|
| 8 |
import asyncio
|
| 9 |
import httpx
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
router = APIRouter()
|
| 12 |
|
| 13 |
class ImportRequest(BaseModel):
|
|
@@ -18,45 +21,62 @@ class ImportRequest(BaseModel):
|
|
| 18 |
|
| 19 |
@router.post("")
|
| 20 |
async def import_book(req: ImportRequest):
|
|
|
|
| 21 |
source_lookup = {
|
| 22 |
"google": google_books.fetch,
|
| 23 |
"openlibrary": open_library.fetch,
|
| 24 |
"ia": internet_archive.fetch
|
| 25 |
}
|
| 26 |
if req.source not in source_lookup:
|
|
|
|
| 27 |
raise HTTPException(400, "Invalid source")
|
| 28 |
|
| 29 |
result = await source_lookup[req.source](req.ref)
|
| 30 |
-
|
| 31 |
|
| 32 |
# Debugs
|
| 33 |
if not result:
|
| 34 |
-
|
| 35 |
raise HTTPException(403, "Download not permitted")
|
| 36 |
if not result.get("download_url"):
|
| 37 |
-
|
| 38 |
raise HTTPException(403, "Download not permitted")
|
| 39 |
|
| 40 |
# Write temp file and save as Pdf from downloadable link
|
| 41 |
download_url = result["download_url"]
|
| 42 |
file_path = f"/tmp/{req.candidate_id}.pdf"
|
|
|
|
| 43 |
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
doc = {
|
| 54 |
"_id": req.candidate_id,
|
| 55 |
"title": req.title,
|
| 56 |
"status": "queued",
|
| 57 |
"metadata": result
|
| 58 |
}
|
|
|
|
| 59 |
asyncio.create_task(parse_and_index(req.candidate_id))
|
| 60 |
-
|
| 61 |
return {"document_id": req.candidate_id, "status": "queued"}
|
| 62 |
|
|
|
|
| 8 |
import asyncio
|
| 9 |
import httpx
|
| 10 |
|
| 11 |
+
import logging
|
| 12 |
+
logger = logging.getLogger("book-query")
|
| 13 |
+
|
| 14 |
router = APIRouter()
|
| 15 |
|
| 16 |
class ImportRequest(BaseModel):
|
|
|
|
| 21 |
|
| 22 |
@router.post("")
|
| 23 |
async def import_book(req: ImportRequest):
|
| 24 |
+
logger.info(f"📥 Received import request: {req.dict()}")
|
| 25 |
source_lookup = {
|
| 26 |
"google": google_books.fetch,
|
| 27 |
"openlibrary": open_library.fetch,
|
| 28 |
"ia": internet_archive.fetch
|
| 29 |
}
|
| 30 |
if req.source not in source_lookup:
|
| 31 |
+
logger.warning(f"❌ Invalid source: {req.source}")
|
| 32 |
raise HTTPException(400, "Invalid source")
|
| 33 |
|
| 34 |
result = await source_lookup[req.source](req.ref)
|
| 35 |
+
logger.debug(f"🔎 Fetch result for ref {req.ref}: {result}")
|
| 36 |
|
| 37 |
# Debugs
|
| 38 |
if not result:
|
| 39 |
+
logger.warning(f"⛔️ No fetch result for {req.source} with ref {req.ref}")
|
| 40 |
raise HTTPException(403, "Download not permitted")
|
| 41 |
if not result.get("download_url"):
|
| 42 |
+
logger.warning(f"📄 No download URL from {req.source}. Viewability: {result.get('viewability', 'unknown')}")
|
| 43 |
raise HTTPException(403, "Download not permitted")
|
| 44 |
|
| 45 |
# Write temp file and save as Pdf from downloadable link
|
| 46 |
download_url = result["download_url"]
|
| 47 |
file_path = f"/tmp/{req.candidate_id}.pdf"
|
| 48 |
+
logger.info(f"⬇️ Downloading from: {download_url}")
|
| 49 |
|
| 50 |
+
# Read and write file
|
| 51 |
+
try:
|
| 52 |
+
async with aiofiles.open(file_path, mode='wb') as f:
|
| 53 |
+
async with httpx.AsyncClient() as client:
|
| 54 |
+
r = await client.get(download_url)
|
| 55 |
+
r.raise_for_status()
|
| 56 |
+
await f.write(r.content)
|
| 57 |
+
logger.info(f"✅ PDF saved to {file_path}")
|
| 58 |
+
except Exception as e:
|
| 59 |
+
logger.error(f"🚨 Failed to download or write PDF: {e}")
|
| 60 |
+
raise HTTPException(500, "Failed to download PDF")
|
| 61 |
+
|
| 62 |
+
# Save to bucket
|
| 63 |
+
try:
|
| 64 |
+
with open(file_path, "rb") as f:
|
| 65 |
+
await grid_fs_bucket.upload_from_stream(f"{req.candidate_id}.pdf", f)
|
| 66 |
+
os.remove(file_path)
|
| 67 |
+
except Exception as e:
|
| 68 |
+
logger.error(f"💥 Failed to upload to GridFS: {e}")
|
| 69 |
+
raise HTTPException(500, "Storage failed")
|
| 70 |
+
|
| 71 |
+
# Doc tags
|
| 72 |
doc = {
|
| 73 |
"_id": req.candidate_id,
|
| 74 |
"title": req.title,
|
| 75 |
"status": "queued",
|
| 76 |
"metadata": result
|
| 77 |
}
|
| 78 |
+
await db.documents.insert_one(doc)
|
| 79 |
asyncio.create_task(parse_and_index(req.candidate_id))
|
| 80 |
+
logger.info(f"📚 Document {req.candidate_id} queued for indexing")
|
| 81 |
return {"document_id": req.candidate_id, "status": "queued"}
|
| 82 |
|
app/services/google_books.py
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
# app/services/google_books.py
|
| 2 |
import httpx, os
|
| 3 |
from tenacity import retry, stop_after_attempt, wait_fixed
|
|
|
|
|
|
|
| 4 |
|
| 5 |
@retry(stop=stop_after_attempt(3), wait=wait_fixed(1))
|
| 6 |
async def search(q):
|
|
@@ -25,4 +27,7 @@ async def search(q):
|
|
| 25 |
]
|
| 26 |
|
| 27 |
async def fetch(ref):
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# app/services/google_books.py
|
| 2 |
import httpx, os
|
| 3 |
from tenacity import retry, stop_after_attempt, wait_fixed
|
| 4 |
+
import logging
|
| 5 |
+
logger = logging.getLogger("book-query")
|
| 6 |
|
| 7 |
@retry(stop=stop_after_attempt(3), wait=wait_fixed(1))
|
| 8 |
async def search(q):
|
|
|
|
| 27 |
]
|
| 28 |
|
| 29 |
async def fetch(ref):
|
| 30 |
+
logger = logging.getLogger("book-query")
|
| 31 |
+
logger.debug(f"[Google] fetch() called with ref={ref}")
|
| 32 |
+
return None # Always returns None, so import will 403
|
| 33 |
+
|