root/MarketingTool
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

replace default scoring with opportunity model
CI / compose (push) Successful in 13m53s
Details

Browse Source
This commit is contained in:
Marco0300
2026-09-03 23:21:35 +02:00
parent 00bd49a894
commit cb31f2dd04
4 changed files with 137 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/api/app/main.py
+10 -10
View File
@@ -7,12 +7,12 @@ from pathlib import Path
from urllib.parse import parse_qs, urlparse
if __package__ in (None, ""):
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from app.domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, score_business, normalize_domain, normalize_phone, match_businesses
from app.domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, normalize_domain, normalize_phone, match_businesses
from app.sources import adapter_for, contains_secret, available_adapters, normalize_record, circuit_is_open
from app.domain_intelligence import normalize_registrable_domain, resolve_domain, generate_candidate_domains
from app.website_scanner import scan_website, validate_url
from app.contact_extractor import extract_contacts, MAX_HTML_BYTES, MAX_RESULTS
from app.scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
from app.scoring import DEFAULT_RULES, signals_for_business, evaluate_score, score_business_opportunity, SCORE_VERSION
from app.ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
from app.discovery import discover as scoped_discover
from app.ai_research import provider_status as ai_research_provider_status, configure_db as configure_ai_research_db, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
@@ -20,12 +20,12 @@ if __package__ in (None, ""):
from app.config import load_config
from app.provider_config import validate_payload as validate_remote_provider, encrypt as encrypt_provider_secret, decrypt as decrypt_provider_secret, safe_status as remote_provider_status, test_connectivity as test_remote_connectivity
else:
from .domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, score_business, normalize_domain, normalize_phone, match_businesses
from .domain import deduplication_key, deduplicate_businesses, is_suppressed, normalize_business, normalize_domain, normalize_phone, match_businesses
from .sources import adapter_for, contains_secret, available_adapters, normalize_record, circuit_is_open
from .domain_intelligence import normalize_registrable_domain, resolve_domain, generate_candidate_domains
from .website_scanner import scan_website, validate_url
from .contact_extractor import extract_contacts, MAX_HTML_BYTES, MAX_RESULTS
from .scoring import DEFAULT_RULES, signals_for_business, evaluate_score, SCORE_VERSION
from .scoring import DEFAULT_RULES, signals_for_business, evaluate_score, score_business_opportunity, SCORE_VERSION
from .ai_assistance import generate as generate_ai, input_fingerprint, provider_status, MAX_INPUT_ITEMS, MAX_OUTPUT_CHARS
from .discovery import discover as scoped_discover
from .ai_research import provider_status as ai_research_provider_status, configure_db as configure_ai_research_db, validate_criteria as validate_ai_research_criteria, AIResearchConfigError
@@ -1180,7 +1180,7 @@ class ApiHandler(BaseHTTPRequestHandler):
if is_suppressed(b,suppressions):return self.send_json(409,{"error":"suppressed"})
fields=[(c,b[c]) for c in ("website_domain","email","phone") if b[c]]
if fields and db.execute("SELECT id FROM businesses WHERE organization_id=? AND ("+" OR ".join(f"{c}=?" for c,_ in fields)+")",[org]+[v for _,v in fields]).fetchone():return self.send_json(409,{"error":"duplicate"})
scored=score_business(b);cur=db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?)",(org,b["name"],b["website"],b["website_domain"],b["email"],b["phone"],str(b.get("description","")),b["province"],b["city"],b["suburb"],scored["score"],scored["score_version"],json.dumps(scored["factors"]),scored["website_class"])); self.audit(db,user,"business.created",str(cur.lastrowid));db.commit();return self.send_json(201,row_json(db.execute("SELECT * FROM businesses WHERE id=?",(cur.lastrowid,)).fetchone()))
scored=score_business_opportunity(b);cur=db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?)",(org,b["name"],b["website"],b["website_domain"],b["email"],b["phone"],str(b.get("description","")),b["province"],b["city"],b["suburb"],scored["score"],scored["score_version"],json.dumps(scored["explanations"]),scored["website_class"])); self.audit(db,user,"business.created",str(cur.lastrowid));db.commit();return self.send_json(201,row_json(db.execute("SELECT * FROM businesses WHERE id=?",(cur.lastrowid,)).fetchone()))
def create_suppression(self,payload,db,user):
kind,value=payload.get("kind"),str(payload.get("value","")).strip().lower()
if kind not in {"email","domain","phone"} or not value:return self.send_json(400,{"error":"invalid_suppression"})
@@ -1470,11 +1470,11 @@ def _run_scoped_discovery(db, job, handler):
existing = db.execute("SELECT id FROM businesses WHERE organization_id=? AND website_domain=?", (org, b["website_domain"])).fetchone()
if existing: bid = existing["id"]
else:
scored = score_business(b)
cur = db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?)", (org,b["name"],b["website"],b["website_domain"],b["email"],b["phone"],b.get("description", ""),b["province"],b["city"],b["suburb"],scored["score"],scored["score_version"],json.dumps(scored["factors"]),scored["website_class"]))
scored = score_business_opportunity(b, sources=["scoped_discovery"])
cur = db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?)", (org,b["name"],b["website"],b["website_domain"],b["email"],b["phone"],b.get("description", ""),b["province"],b["city"],b["suburb"],scored["score"],scored["score_version"],json.dumps(scored["explanations"]),scored["website_class"]))
bid = cur.lastrowid
priority = "high" if scored["score"] >= 70 else "medium" if scored["score"] >= 40 else "low"
db.execute("INSERT INTO score_history(organization_id,business_id,score,eligible,priority_band,score_version,explanations_json,signals_json) VALUES(?,?,?,?,?,?,?,?)", (org,bid,scored["score"],1,priority,scored["score_version"],json.dumps(scored["factors"]),json.dumps({"source": "scoped_discovery"}, sort_keys=True)))
db.execute("INSERT INTO score_history(organization_id,business_id,score,eligible,priority_band,score_version,explanations_json,signals_json) VALUES(?,?,?,?,?,?,?,?)", (org,bid,scored["score"],int(scored["eligible"]),scored["priority_band"],scored["score_version"],json.dumps(scored["explanations"]),json.dumps(scored["signals"], sort_keys=True)))
scan_ids = {}
for page in candidate.get("pages", []):
scan_key = hashlib.sha256((org + ":" + page["url"]).encode()).hexdigest()
@@ -1545,8 +1545,8 @@ def _run_source_discovery(db, job, handler):
existing=db.execute("SELECT * FROM businesses WHERE organization_id=? AND ((website_domain<>'' AND website_domain=?) OR (email<>'' AND email=?) OR (phone<>'' AND phone=?) OR (name=? AND city=?)) ORDER BY id LIMIT 1",(org,normalized["website_domain"],normalized["email"],normalized["phone"],normalized["name"],normalized["city"])).fetchone()
if existing: bid=existing["id"]; handler.add_job_event(db,job["id"],org,"business.matched",f"Matched business {bid}",50)
else:
scored=score_business(normalized); cur=db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class,review_status) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)",(org,normalized["name"],normalized["website"],normalized["website_domain"],normalized["email"],normalized["phone"],normalized.get("description",""),normalized["province"],normalized["city"],normalized["suburb"],scored["score"],scored["score_version"],json.dumps(scored["factors"]),scored["website_class"],"pending")); bid=cur.lastrowid
db.execute("INSERT INTO score_history(organization_id,business_id,score,eligible,priority_band,score_version,explanations_json,signals_json) VALUES(?,?,?,?,?,?,?,?)",(org,bid,scored["score"],1,"high" if scored["score"]>=70 else "medium" if scored["score"]>=40 else "low",scored["score_version"],json.dumps(scored["factors"]),json.dumps({"source":source["kind"]})))
scored=score_business_opportunity(normalized, sources=[source["kind"]]); cur=db.execute("INSERT INTO businesses(organization_id,name,website,website_domain,email,phone,description,province,city,suburb,score,score_version,score_factors,website_class,review_status) VALUES(?,?,?,?,?,?,?,?,?,?,?,?,?,?,?)",(org,normalized["name"],normalized["website"],normalized["website_domain"],normalized["email"],normalized["phone"],normalized.get("description",""),normalized["province"],normalized["city"],normalized["suburb"],scored["score"],scored["score_version"],json.dumps(scored["explanations"]),scored["website_class"],"pending")); bid=cur.lastrowid
db.execute("INSERT INTO score_history(organization_id,business_id,score,eligible,priority_band,score_version,explanations_json,signals_json) VALUES(?,?,?,?,?,?,?,?)",(org,bid,scored["score"],int(scored["eligible"]),scored["priority_band"],scored["score_version"],json.dumps(scored["explanations"]),json.dumps(scored["signals"],sort_keys=True)))
handler.add_job_event(db,job["id"],org,"business.created",f"Created business {bid}",60)
if normalized["website_domain"] and not db.execute("SELECT 1 FROM domains WHERE organization_id=? AND business_id=? AND domain=?",(org,bid,normalized["website_domain"])).fetchone(): db.execute("INSERT INTO domains(business_id,organization_id,domain,kind) VALUES(?,?,?,?)",(bid,org,normalized["website_domain"],"website"))
if normalized["website"] and not db.execute("SELECT 1 FROM websites WHERE organization_id=? AND business_id=? AND url=?",(org,bid,normalized["website"])).fetchone(): db.execute("INSERT INTO websites(business_id,organization_id,url,website_class) VALUES(?,?,?,?)",(bid,org,normalized["website"],"business_site"))