forked from 0xWheatyz/SPARC
Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| f33447eef8 | |||
| 55c131cb32 | |||
| fbb72fe2a5 | |||
| e484baaf5f | |||
| 069f1c343c | |||
| b000146585 |
@@ -9,7 +9,43 @@ on:
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Install system dependencies
|
||||
shell: sh
|
||||
run: |
|
||||
apk add --no-cache git python3 py3-pip gcc musl-dev libpq-dev python3-dev
|
||||
|
||||
- name: Checkout code
|
||||
shell: sh
|
||||
run: |
|
||||
git clone http://gitea.gitea.svc.cluster.local/${{ gitea.repository }}.git .
|
||||
git checkout ${{ gitea.sha }}
|
||||
|
||||
- name: Install Python dependencies
|
||||
shell: sh
|
||||
run: |
|
||||
pip3 install --break-system-packages -r requirements.txt ruff
|
||||
|
||||
- name: Run ruff linter
|
||||
shell: sh
|
||||
run: |
|
||||
ruff check SPARC/ tests/
|
||||
|
||||
- name: Run pytest
|
||||
shell: sh
|
||||
env:
|
||||
DATABASE_URL: "sqlite://"
|
||||
API_KEY: "test-key"
|
||||
OPENROUTER_API_KEY: "test-key"
|
||||
JWT_SECRET: "test-secret-for-ci"
|
||||
APP_ENV: "development"
|
||||
run: |
|
||||
python3 -m pytest tests/ -v --tb=short -x
|
||||
|
||||
build-api:
|
||||
needs: test
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Install dependencies
|
||||
@@ -81,6 +117,7 @@ jobs:
|
||||
echo "API image available at ${{ steps.tags.outputs.IMAGE_TAG }}"
|
||||
|
||||
build-frontend:
|
||||
needs: test
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Install dependencies
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
name: Test and Lint
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Install system dependencies
|
||||
shell: sh
|
||||
run: |
|
||||
apk add --no-cache git python3 py3-pip gcc musl-dev libpq-dev python3-dev
|
||||
|
||||
- name: Checkout code
|
||||
shell: sh
|
||||
run: |
|
||||
git clone http://gitea.gitea.svc.cluster.local/${{ gitea.repository }}.git .
|
||||
git checkout ${{ gitea.sha }}
|
||||
|
||||
- name: Install Python dependencies
|
||||
shell: sh
|
||||
run: |
|
||||
pip3 install --break-system-packages -r requirements.txt ruff
|
||||
|
||||
- name: Run ruff linter
|
||||
shell: sh
|
||||
run: |
|
||||
ruff check SPARC/ tests/
|
||||
|
||||
- name: Run pytest
|
||||
shell: sh
|
||||
env:
|
||||
DATABASE_URL: "sqlite://"
|
||||
API_KEY: "test-key"
|
||||
OPENROUTER_API_KEY: "test-key"
|
||||
JWT_SECRET: "test-secret-for-ci"
|
||||
APP_ENV: "development"
|
||||
run: |
|
||||
python3 -m pytest tests/ -v --tb=short -x
|
||||
+3
-2
@@ -1,3 +1,4 @@
|
||||
from .types import Patents, Patent
|
||||
from .types import Patent as Patent
|
||||
from .types import Patents as Patents
|
||||
|
||||
all = ["Patents", "Patent"]
|
||||
__all__ = ["Patents", "Patent"]
|
||||
|
||||
+23
-18
@@ -5,14 +5,17 @@ to provide company performance estimation based on patent portfolios.
|
||||
"""
|
||||
|
||||
import hashlib
|
||||
import logging
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from typing import Callable
|
||||
|
||||
from SPARC import config
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
from SPARC.database import DatabaseClient
|
||||
from SPARC.serp_api import SERP
|
||||
from SPARC.llm import LLMAnalyzer
|
||||
from SPARC.types import Patent, Patents, CompanyAnalysisResult, BatchAnalysisResult
|
||||
from SPARC.serp_api import SERP
|
||||
from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult, Patent, Patents
|
||||
|
||||
|
||||
class CompanyAnalyzer:
|
||||
@@ -52,13 +55,13 @@ class CompanyAnalyzer:
|
||||
query_hash = hashlib.sha256(company_name.lower().encode()).hexdigest()
|
||||
cached_ids = self.db.get_cached_serp_query(query_hash)
|
||||
if cached_ids is not None:
|
||||
print(f"Using cached SERP results for {company_name} ({len(cached_ids)} patents)")
|
||||
logger.info("Using cached SERP results for %s (%d patents)", company_name, len(cached_ids))
|
||||
patents = Patents(patents=[
|
||||
Patent(patent_id=pid, pdf_link="")
|
||||
for pid in cached_ids
|
||||
])
|
||||
else:
|
||||
print(f"Retrieving patents for {company_name}...")
|
||||
logger.info("Retrieving patents for %s...", company_name)
|
||||
patents = SERP.query(company_name)
|
||||
# Cache the SERP results
|
||||
if patents.patents:
|
||||
@@ -66,12 +69,13 @@ class CompanyAnalyzer:
|
||||
company_name=company_name,
|
||||
query_hash=query_hash,
|
||||
patent_ids=[p.patent_id for p in patents.patents],
|
||||
ttl_hours=config.serp_cache_ttl_hours,
|
||||
)
|
||||
|
||||
if not patents.patents:
|
||||
return f"No patents found for {company_name}"
|
||||
|
||||
print(f"Found {len(patents.patents)} patents. Processing...")
|
||||
logger.info("Found %d patents. Processing...", len(patents.patents))
|
||||
|
||||
# Download, parse, and minimize patents in parallel
|
||||
processed_patents = []
|
||||
@@ -87,12 +91,12 @@ class CompanyAnalyzer:
|
||||
if result:
|
||||
processed_patents.append(result)
|
||||
except Exception as e:
|
||||
print(f"Warning: Failed to process {patent.patent_id}: {e}")
|
||||
logger.warning("Failed to process %s: %s", patent.patent_id, e)
|
||||
|
||||
if not processed_patents:
|
||||
return f"Failed to process any patents for {company_name}"
|
||||
|
||||
print(f"Analyzing portfolio with LLM...")
|
||||
logger.info("Analyzing portfolio with LLM...")
|
||||
|
||||
# Analyze the full portfolio with LLM
|
||||
analysis = self.llm_analyzer.analyze_patent_portfolio(
|
||||
@@ -122,6 +126,7 @@ class CompanyAnalyzer:
|
||||
FileNotFoundError: If the patent PDF is not found at the expected path.
|
||||
"""
|
||||
import os
|
||||
logger.info("Analyzing patent %s for %s...", patent_id, company_name)
|
||||
|
||||
patent_path = f"patents/{patent_id}.pdf"
|
||||
|
||||
@@ -183,7 +188,7 @@ class CompanyAnalyzer:
|
||||
|
||||
return {"patent_id": patent.patent_id, "content": minimized_content}
|
||||
except Exception as e:
|
||||
print(f"Warning: Failed to process {patent.patent_id}: {e}")
|
||||
logger.warning("Failed to process %s: %s", patent.patent_id, e)
|
||||
return None
|
||||
|
||||
def _analyze_company_safe(self, company_name: str) -> CompanyAnalysisResult:
|
||||
@@ -254,7 +259,7 @@ class CompanyAnalyzer:
|
||||
results: list[CompanyAnalysisResult] = []
|
||||
total = len(companies)
|
||||
|
||||
print(f"Starting batch analysis of {total} companies...")
|
||||
logger.info("Starting batch analysis of %d companies...", total)
|
||||
|
||||
with ThreadPoolExecutor(max_workers=max_workers) as executor:
|
||||
future_to_company = {
|
||||
@@ -271,8 +276,8 @@ class CompanyAnalyzer:
|
||||
result = future.result()
|
||||
results.append(result)
|
||||
|
||||
status = "✓" if result.success else "✗"
|
||||
print(f"[{completed}/{total}] {status} {company}")
|
||||
status = "OK" if result.success else "FAIL"
|
||||
logger.info("[%d/%d] %s %s", completed, total, status, company)
|
||||
|
||||
if progress_callback:
|
||||
progress_callback(company, completed, total)
|
||||
@@ -287,12 +292,12 @@ class CompanyAnalyzer:
|
||||
error=str(e),
|
||||
)
|
||||
)
|
||||
print(f"[{completed}/{total}] ✗ {company}: {e}")
|
||||
logger.error("[%d/%d] FAIL %s: %s", completed, total, company, e)
|
||||
|
||||
successful = sum(1 for r in results if r.success)
|
||||
failed = total - successful
|
||||
|
||||
print(f"\nBatch complete: {successful} succeeded, {failed} failed")
|
||||
logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
|
||||
|
||||
return BatchAnalysisResult(
|
||||
results=results,
|
||||
@@ -318,20 +323,20 @@ class CompanyAnalyzer:
|
||||
results: list[CompanyAnalysisResult] = []
|
||||
total = len(companies)
|
||||
|
||||
print(f"Starting sequential analysis of {total} companies...")
|
||||
logger.info("Starting sequential analysis of %d companies...", total)
|
||||
|
||||
for idx, company in enumerate(companies, 1):
|
||||
print(f"\n[{idx}/{total}] Analyzing {company}...")
|
||||
logger.info("[%d/%d] Analyzing %s...", idx, total, company)
|
||||
result = self._analyze_company_safe(company)
|
||||
results.append(result)
|
||||
|
||||
status = "✓" if result.success else "✗"
|
||||
print(f"[{idx}/{total}] {status} {company}")
|
||||
status = "OK" if result.success else "FAIL"
|
||||
logger.info("[%d/%d] %s %s", idx, total, status, company)
|
||||
|
||||
successful = sum(1 for r in results if r.success)
|
||||
failed = total - successful
|
||||
|
||||
print(f"\nBatch complete: {successful} succeeded, {failed} failed")
|
||||
logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
|
||||
|
||||
return BatchAnalysisResult(
|
||||
results=results,
|
||||
|
||||
@@ -169,6 +169,9 @@ async def lifespan(app: FastAPI):
|
||||
import logging
|
||||
logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
|
||||
_db.close()
|
||||
# Start scheduled analysis if tracked companies are configured
|
||||
from SPARC.scheduler import start_scheduler
|
||||
start_scheduler()
|
||||
yield
|
||||
# Cleanup
|
||||
_analyzer = None
|
||||
@@ -369,6 +372,60 @@ async def delete_user(
|
||||
return {"message": "User deleted"}
|
||||
|
||||
|
||||
# ============== Tracked Companies Endpoints ==============
|
||||
|
||||
|
||||
class TrackCompanyRequest(BaseModel):
|
||||
"""Request to add a company to tracking."""
|
||||
|
||||
company_name: str = Field(..., min_length=1, max_length=255)
|
||||
|
||||
|
||||
@app.get("/admin/tracked", tags=["Admin"])
|
||||
async def list_tracked_companies(
|
||||
_: UserResponse = Depends(get_current_admin),
|
||||
):
|
||||
"""List all tracked companies (admin only)."""
|
||||
db = get_db_client()
|
||||
return db.list_tracked_companies()
|
||||
|
||||
|
||||
@app.post("/admin/tracked", tags=["Admin"])
|
||||
async def add_tracked_company(
|
||||
request: TrackCompanyRequest,
|
||||
_: UserResponse = Depends(get_current_admin),
|
||||
):
|
||||
"""Add a company to the tracked list (admin only)."""
|
||||
db = get_db_client()
|
||||
result = db.add_tracked_company(request.company_name)
|
||||
if not result:
|
||||
raise HTTPException(status_code=409, detail="Company already tracked")
|
||||
return result
|
||||
|
||||
|
||||
@app.delete("/admin/tracked/{company_name}", tags=["Admin"])
|
||||
async def remove_tracked_company(
|
||||
company_name: str,
|
||||
_: UserResponse = Depends(get_current_admin),
|
||||
):
|
||||
"""Remove a company from the tracked list (admin only)."""
|
||||
db = get_db_client()
|
||||
removed = db.remove_tracked_company(company_name)
|
||||
if not removed:
|
||||
raise HTTPException(status_code=404, detail="Company not found in tracking list")
|
||||
return {"message": f"Stopped tracking {company_name}"}
|
||||
|
||||
|
||||
@app.get("/admin/alerts", tags=["Admin"])
|
||||
async def list_alerts(
|
||||
limit: int = Query(default=50, ge=1, le=200),
|
||||
_: UserResponse = Depends(get_current_admin),
|
||||
):
|
||||
"""List recent alerts from scheduled analysis (admin only)."""
|
||||
db = get_db_client()
|
||||
return db.list_alerts(limit=limit)
|
||||
|
||||
|
||||
# ============== Analytics Endpoint ==============
|
||||
|
||||
|
||||
|
||||
+16
-1
@@ -2,11 +2,20 @@
|
||||
|
||||
Loads environment variables from .env file for API keys and other secrets.
|
||||
"""
|
||||
from dotenv import load_dotenv
|
||||
import logging
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_dotenv()
|
||||
|
||||
# Logging configuration
|
||||
log_level = os.getenv("LOG_LEVEL", "INFO").upper()
|
||||
logging.basicConfig(
|
||||
level=getattr(logging, log_level, logging.INFO),
|
||||
format="%(asctime)s %(levelname)s %(name)s %(message)s",
|
||||
)
|
||||
|
||||
# SerpAPI key for patent search
|
||||
api_key = os.getenv("API_KEY")
|
||||
|
||||
@@ -30,6 +39,12 @@ use_database = os.getenv("USE_DATABASE", "false").lower() in ("true", "1", "yes"
|
||||
patent_search_days = int(os.getenv("PATENT_SEARCH_DAYS", "90"))
|
||||
patent_thread_workers = int(os.getenv("PATENT_THREAD_WORKERS", "5"))
|
||||
|
||||
# LLM model to use via OpenRouter (e.g. "anthropic/claude-3.5-sonnet", "openai/gpt-4o")
|
||||
model = os.getenv("MODEL", "anthropic/claude-3.5-sonnet")
|
||||
|
||||
# SERP cache TTL in hours (how long cached search results are considered fresh)
|
||||
serp_cache_ttl_hours = int(os.getenv("SERP_CACHE_TTL_HOURS", "24"))
|
||||
|
||||
# Root path for running behind a reverse proxy (e.g., "/api" when served at /api/)
|
||||
# This ensures OpenAPI docs work correctly when accessed via the proxy
|
||||
root_path = os.getenv("ROOT_PATH", "")
|
||||
|
||||
+114
-6
@@ -1,14 +1,15 @@
|
||||
"""Database client for storing and retrieving LLM messages and user authentication."""
|
||||
|
||||
import contextlib
|
||||
import psycopg2
|
||||
from psycopg2.pool import ThreadedConnectionPool
|
||||
from psycopg2.extras import RealDictCursor
|
||||
from typing import Dict, List, Optional
|
||||
from datetime import datetime, timedelta
|
||||
import json
|
||||
import hashlib
|
||||
import json
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
import bcrypt
|
||||
import psycopg2
|
||||
from psycopg2.extras import RealDictCursor
|
||||
from psycopg2.pool import ThreadedConnectionPool
|
||||
|
||||
|
||||
class DatabaseClient:
|
||||
@@ -191,6 +192,35 @@ class DatabaseClient:
|
||||
ON jobs(status)
|
||||
""")
|
||||
|
||||
# Create tracked companies table for scheduled analysis
|
||||
cursor.execute("""
|
||||
CREATE TABLE IF NOT EXISTS tracked_companies (
|
||||
id SERIAL PRIMARY KEY,
|
||||
company_name VARCHAR(255) UNIQUE NOT NULL,
|
||||
last_patent_count INTEGER DEFAULT 0,
|
||||
last_analysis_at TIMESTAMP,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
""")
|
||||
|
||||
# Create alerts table for significant changes
|
||||
cursor.execute("""
|
||||
CREATE TABLE IF NOT EXISTS alerts (
|
||||
id SERIAL PRIMARY KEY,
|
||||
company_name VARCHAR(255) NOT NULL,
|
||||
alert_type VARCHAR(50) NOT NULL,
|
||||
message TEXT NOT NULL,
|
||||
old_value NUMERIC,
|
||||
new_value NUMERIC,
|
||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||
)
|
||||
""")
|
||||
|
||||
cursor.execute("""
|
||||
CREATE INDEX IF NOT EXISTS idx_alerts_company
|
||||
ON alerts(company_name)
|
||||
""")
|
||||
|
||||
self.conn.commit()
|
||||
|
||||
@staticmethod
|
||||
@@ -802,3 +832,81 @@ class DatabaseClient:
|
||||
with conn.cursor() as cursor:
|
||||
cursor.execute("SELECT COUNT(*) FROM users")
|
||||
return cursor.fetchone()[0]
|
||||
|
||||
# Tracked Companies Methods
|
||||
|
||||
def add_tracked_company(self, company_name: str) -> Optional[Dict]:
|
||||
"""Add a company to the tracking list."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||
try:
|
||||
cursor.execute(
|
||||
"INSERT INTO tracked_companies (company_name) VALUES (%s) RETURNING *",
|
||||
(company_name,),
|
||||
)
|
||||
row = cursor.fetchone()
|
||||
conn.commit()
|
||||
return dict(row) if row else None
|
||||
except Exception:
|
||||
conn.rollback()
|
||||
return None
|
||||
|
||||
def remove_tracked_company(self, company_name: str) -> bool:
|
||||
"""Remove a company from the tracking list."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor() as cursor:
|
||||
cursor.execute(
|
||||
"DELETE FROM tracked_companies WHERE LOWER(company_name) = LOWER(%s)",
|
||||
(company_name,),
|
||||
)
|
||||
conn.commit()
|
||||
return cursor.rowcount > 0
|
||||
|
||||
def list_tracked_companies(self) -> List[Dict]:
|
||||
"""List all tracked companies."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||
cursor.execute("SELECT * FROM tracked_companies ORDER BY company_name")
|
||||
return [dict(row) for row in cursor.fetchall()]
|
||||
|
||||
def update_tracked_company(
|
||||
self, company_name: str, patent_count: int
|
||||
) -> None:
|
||||
"""Update the last analysis stats for a tracked company."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor() as cursor:
|
||||
cursor.execute(
|
||||
"""UPDATE tracked_companies
|
||||
SET last_patent_count = %s, last_analysis_at = CURRENT_TIMESTAMP
|
||||
WHERE LOWER(company_name) = LOWER(%s)""",
|
||||
(patent_count, company_name),
|
||||
)
|
||||
conn.commit()
|
||||
|
||||
def store_alert(
|
||||
self,
|
||||
company_name: str,
|
||||
alert_type: str,
|
||||
message: str,
|
||||
old_value: float | None = None,
|
||||
new_value: float | None = None,
|
||||
) -> None:
|
||||
"""Record an alert for a significant change."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor() as cursor:
|
||||
cursor.execute(
|
||||
"""INSERT INTO alerts (company_name, alert_type, message, old_value, new_value)
|
||||
VALUES (%s, %s, %s, %s, %s)""",
|
||||
(company_name, alert_type, message, old_value, new_value),
|
||||
)
|
||||
conn.commit()
|
||||
|
||||
def list_alerts(self, limit: int = 50) -> List[Dict]:
|
||||
"""List recent alerts."""
|
||||
with self.get_conn() as conn:
|
||||
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||
cursor.execute(
|
||||
"SELECT * FROM alerts ORDER BY created_at DESC LIMIT %s",
|
||||
(limit,),
|
||||
)
|
||||
return [dict(row) for row in cursor.fetchall()]
|
||||
|
||||
+9
-8
@@ -1,9 +1,14 @@
|
||||
"""LLM integration for patent analysis using OpenRouter."""
|
||||
|
||||
import logging
|
||||
from typing import Dict
|
||||
|
||||
from openai import OpenAI
|
||||
|
||||
from SPARC import config
|
||||
from SPARC.database import DatabaseClient
|
||||
from typing import Dict
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class LLMAnalyzer:
|
||||
@@ -20,7 +25,7 @@ class LLMAnalyzer:
|
||||
"""
|
||||
self.test_mode = test_mode
|
||||
self.use_cache = use_cache if use_cache is not None else config.use_cache
|
||||
self.model = "anthropic/claude-3.5-sonnet"
|
||||
self.model = config.model
|
||||
|
||||
# Always initialize database client for storage and caching
|
||||
self.db_client = DatabaseClient(config.database_url)
|
||||
@@ -59,11 +64,7 @@ Patent Content:
|
||||
Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals about the company's technical direction and competitive advantage."""
|
||||
|
||||
if self.test_mode:
|
||||
print("=" * 80)
|
||||
print("TEST MODE - Prompt that would be sent to LLM:")
|
||||
print("=" * 80)
|
||||
print(prompt)
|
||||
print("=" * 80)
|
||||
logger.debug("TEST MODE - Prompt that would be sent to LLM:\n%s", prompt)
|
||||
return "[TEST MODE - No API call made]"
|
||||
|
||||
# Check cache first
|
||||
@@ -165,7 +166,7 @@ Patent Portfolio:
|
||||
Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the company's innovation strength and performance outlook."""
|
||||
|
||||
if self.test_mode:
|
||||
print(prompt)
|
||||
logger.debug("TEST MODE - Portfolio prompt:\n%s", prompt)
|
||||
return "[TEST MODE]"
|
||||
|
||||
metadata = {
|
||||
|
||||
@@ -0,0 +1,109 @@
|
||||
"""Scheduled patent analysis for tracked companies.
|
||||
|
||||
Uses APScheduler to periodically re-analyze tracked companies and
|
||||
detect significant changes in patent counts.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
|
||||
from SPARC import config
|
||||
from SPARC.analyzer import CompanyAnalyzer
|
||||
from SPARC.database import DatabaseClient
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Configurable via environment variable (in hours, default 24)
|
||||
SCHEDULE_INTERVAL_HOURS = int(os.getenv("SCHEDULE_INTERVAL_HOURS", "24"))
|
||||
|
||||
# Patent count change threshold (percentage) to trigger an alert
|
||||
CHANGE_THRESHOLD_PERCENT = int(os.getenv("CHANGE_THRESHOLD_PERCENT", "20"))
|
||||
|
||||
|
||||
def run_scheduled_analysis() -> None:
|
||||
"""Re-analyze all tracked companies and check for significant changes."""
|
||||
db = DatabaseClient(config.database_url)
|
||||
db.connect()
|
||||
db.initialize_schema()
|
||||
|
||||
tracked = db.list_tracked_companies()
|
||||
if not tracked:
|
||||
logger.info("No tracked companies configured; skipping scheduled analysis")
|
||||
return
|
||||
|
||||
logger.info("Running scheduled analysis for %d tracked companies", len(tracked))
|
||||
|
||||
analyzer = CompanyAnalyzer(db_client=db)
|
||||
|
||||
for company_row in tracked:
|
||||
name = company_row["company_name"]
|
||||
old_count = company_row.get("last_patent_count", 0) or 0
|
||||
|
||||
try:
|
||||
result = analyzer._analyze_company_safe(name)
|
||||
|
||||
if result.success:
|
||||
new_count = result.patent_count
|
||||
|
||||
# Update tracking record
|
||||
db.update_tracked_company(name, new_count)
|
||||
|
||||
# Check for significant change
|
||||
if old_count > 0:
|
||||
delta_pct = abs(new_count - old_count) / old_count * 100
|
||||
if delta_pct >= CHANGE_THRESHOLD_PERCENT:
|
||||
direction = "increased" if new_count > old_count else "decreased"
|
||||
message = (
|
||||
f"Patent count for {name} {direction} by {delta_pct:.0f}% "
|
||||
f"({old_count} -> {new_count})"
|
||||
)
|
||||
logger.warning("ALERT: %s", message)
|
||||
db.store_alert(
|
||||
company_name=name,
|
||||
alert_type="patent_count_change",
|
||||
message=message,
|
||||
old_value=old_count,
|
||||
new_value=new_count,
|
||||
)
|
||||
elif new_count > 0:
|
||||
# First analysis -- record baseline
|
||||
logger.info("Baseline for %s: %d patents", name, new_count)
|
||||
else:
|
||||
logger.warning("Scheduled analysis failed for %s: %s", name, result.error)
|
||||
|
||||
except Exception as e:
|
||||
logger.error("Error analyzing tracked company %s: %s", name, e)
|
||||
|
||||
db.close()
|
||||
logger.info("Scheduled analysis complete")
|
||||
|
||||
|
||||
def start_scheduler() -> None:
|
||||
"""Start the APScheduler background scheduler.
|
||||
|
||||
Safe to call at application startup. If apscheduler is not installed,
|
||||
the function logs a warning and returns without starting anything.
|
||||
"""
|
||||
try:
|
||||
from apscheduler.schedulers.background import BackgroundScheduler
|
||||
except ImportError:
|
||||
logger.warning(
|
||||
"apscheduler not installed; scheduled analysis disabled. "
|
||||
"Install with: pip install apscheduler"
|
||||
)
|
||||
return
|
||||
|
||||
scheduler = BackgroundScheduler()
|
||||
scheduler.add_job(
|
||||
run_scheduled_analysis,
|
||||
"interval",
|
||||
hours=SCHEDULE_INTERVAL_HOURS,
|
||||
id="scheduled_patent_analysis",
|
||||
replace_existing=True,
|
||||
)
|
||||
scheduler.start()
|
||||
logger.info(
|
||||
"Scheduled patent analysis started (every %d hours, threshold %d%%)",
|
||||
SCHEDULE_INTERVAL_HOURS,
|
||||
CHANGE_THRESHOLD_PERCENT,
|
||||
)
|
||||
+8
-5
@@ -1,12 +1,15 @@
|
||||
import os
|
||||
import serpapi
|
||||
from SPARC import config
|
||||
import re
|
||||
import pdfplumber # pip install pdfplumber
|
||||
import requests
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Dict
|
||||
from SPARC.types import Patents, Patent
|
||||
|
||||
import pdfplumber # pip install pdfplumber
|
||||
import requests
|
||||
import serpapi
|
||||
|
||||
from SPARC import config
|
||||
from SPARC.types import Patent, Patents
|
||||
|
||||
|
||||
class SERP:
|
||||
def query(company: str, days_back: int = None) -> Patents:
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ from datetime import datetime
|
||||
|
||||
@dataclass
|
||||
class Patent:
|
||||
patent_id: int
|
||||
patent_id: str
|
||||
pdf_link: str
|
||||
pdf_path: str | None = None
|
||||
summary: dict | None = None
|
||||
|
||||
@@ -15,3 +15,4 @@ pandas
|
||||
bcrypt
|
||||
PyJWT
|
||||
slowapi
|
||||
apscheduler
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
[lint]
|
||||
select = ["E", "F", "I"]
|
||||
ignore = [
|
||||
"E501", # line too long (handled by formatter)
|
||||
]
|
||||
|
||||
[lint.per-file-ignores]
|
||||
"tests/*" = ["E402", "F841"] # allow import not at top of file, unused vars (mocks) in tests
|
||||
@@ -1,9 +1,11 @@
|
||||
"""Tests for the high-level company analyzer orchestration."""
|
||||
|
||||
from unittest.mock import MagicMock, Mock
|
||||
|
||||
import pytest
|
||||
from unittest.mock import Mock, patch, call, MagicMock
|
||||
|
||||
from SPARC.analyzer import CompanyAnalyzer
|
||||
from SPARC.types import Patent, Patents, CompanyAnalysisResult, BatchAnalysisResult
|
||||
from SPARC.types import BatchAnalysisResult, Patent, Patents
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
@@ -24,7 +26,7 @@ class TestCompanyAnalyzer:
|
||||
"""Test analyzer initialization with API key."""
|
||||
mock_llm = mocker.patch("SPARC.analyzer.LLMAnalyzer")
|
||||
|
||||
analyzer = CompanyAnalyzer(openrouter_api_key="test-key")
|
||||
_analyzer = CompanyAnalyzer(openrouter_api_key="test-key") # noqa: F841
|
||||
|
||||
mock_llm.assert_called_once_with(api_key="test-key")
|
||||
|
||||
|
||||
+4
-3
@@ -1,12 +1,13 @@
|
||||
"""Tests for FastAPI web service endpoints."""
|
||||
|
||||
import pytest
|
||||
from datetime import datetime
|
||||
from unittest.mock import Mock, patch
|
||||
from unittest.mock import Mock
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
|
||||
from SPARC.api import app
|
||||
from SPARC.types import CompanyAnalysisResult, BatchAnalysisResult
|
||||
from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
||||
+3
-1
@@ -1,7 +1,9 @@
|
||||
"""Tests for LLM analysis functionality."""
|
||||
|
||||
from unittest.mock import Mock
|
||||
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch
|
||||
|
||||
from SPARC.llm import LLMAnalyzer
|
||||
|
||||
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
"""Tests for SERP API patent retrieval and parsing functionality."""
|
||||
|
||||
import os
|
||||
import pytest
|
||||
from unittest.mock import patch, Mock
|
||||
from datetime import datetime, timedelta
|
||||
from unittest.mock import Mock
|
||||
|
||||
from SPARC.serp_api import SERP
|
||||
from SPARC.types import Patent
|
||||
|
||||
|
||||
Reference in New Issue
Block a user