romfast/gomag-vending
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(address): extract scara/etaj/apartament from comma-less addresses

Browse Source 
Oracle parser failed to extract sc/ap/et when GoMag addresses had no
commas. Added REGEXP_REPLACE to insert commas before address keywords
in v_strada before the comma-split, ensuring the token parser always
fires. Also added 5 Oracle integration tests calling
parseaza_adresa_semicolon directly, and improved diacritics handling
in addr_match (Python + JS).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude Agent
2026-04-08 22:00:17 +00:00
parent f049b0bf12
commit f48c2d62c6
5 changed files with 122 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/app/services/sync_service.py
View File

@@ -2,7 +2,6 @@ import asyncio
import json
import logging
import re
import unicodedata
import uuid
from datetime import datetime, timedelta
from zoneinfo import ZoneInfo
@@ -36,8 +35,7 @@ def _addr_match(gomag_json, roa_json):
r'ET|ETAJ|COM|COMUNA|SAT|MUN|MUNICIPIUL|JUD|JUDETUL|CARTIER|PARTER|SECTOR|SECTORUL|ORAS)(?:\b|(?=\d))'
)
def norm(s):
s = unicodedata.normalize('NFD', s or '')
s = re.sub(r'[\u0300-\u036f]', '', s).upper()
s = (s or '').translate(import_service._DIACRITICS).upper()
s = _ADDR_WORDS.sub('', s)
return re.sub(r'[^A-Z0-9]', '', s)
g_street = norm(g.get('address') or g.get('strada') or '')

7
api/app/static/js/shared.js
View File

@@ -822,8 +822,13 @@ function fmtAddr(a) {
function addrMatch(gomag, roa) {
if (!gomag || !roa) return true; // can't compare
const _DIAC = {
'\u0103':'a','\u00e2':'a','\u00ee':'i','\u0219':'s','\u021b':'t',
'\u0102':'A','\u00c2':'A','\u00ce':'I','\u0218':'S','\u021a':'T',
'\u015f':'s','\u0163':'t','\u015e':'S','\u0162':'T'
};
function norm(s) {
return (s || '').normalize('NFD').replace(/[\u0300-\u036f]/g, '')
return (s || '').replace(/[\u0103\u00e2\u00ee\u0219\u021b\u0102\u00c2\u00ce\u0218\u021a\u015f\u0163\u015e\u0162]/g, c => _DIAC[c] || c)
.toUpperCase()
.replace(/\b(STR|STRADA|NR|NUMAR|NUMARUL|BL|BLOC|SC|SCARA|AP|APART|APARTAMENT|ET|ETAJ|COM|COMUNA|SAT|MUN|MUNICIPIUL|JUD|JUDETUL|CARTIER|PARTER|SECTOR|SECTORUL|ORAS)(?:\b|(?=\d))/g, '')
.replace(/[^A-Z0-9]/g, '');

9
api/database-scripts/05_pack_import_parteneri.pck
View File

@@ -12,6 +12,7 @@ CREATE OR REPLACE PACKAGE PACK_IMPORT_PARTENERI AS
-- 07.04.2026 - fix parser adrese: inserare virgule inaintea keywords, tokeni lipiti (Ap78), strip localitate din strada
-- 07.04.2026 - fix duplicate: normalize localitate + resolve id_localitate inainte de TIER 1 (match pe id_loc)
-- 07.04.2026 - fix localitate necunoscuta: SOUNDEX fuzzy match (TIER L2) + pastreaza judetul in L3
-- 08.04.2026 - fix parser: inserare virgule in strada inainte de comma-split (sc/ap/et nu se extrageau fara virgula)
-- ====================================================================
-- CONSTANTS
@@ -441,6 +442,7 @@ CREATE OR REPLACE PACKAGE BODY PACK_IMPORT_PARTENERI AS
END separa_nume_prenume;
-- 31.03.2026 - parser inteligent: split numar in bloc/scara/apart/etaj (fix ORA-12899 pe NUMAR max 10 chars)
-- 08.04.2026 - fix: inserare virgule in strada inainte de comma-split (sc/ap/et nu se extrageau fara virgula)
PROCEDURE parseaza_adresa_semicolon(p_adresa_text IN VARCHAR2,
p_judet OUT VARCHAR2,
p_localitate OUT VARCHAR2,
@@ -518,6 +520,13 @@ CREATE OR REPLACE PACKAGE BODY PACK_IMPORT_PARTENERI AS
p_strada := SUBSTR(v_componente(3), 1, 100);
v_strada := p_strada;
-- 08.04.2026 - insert commas before address keywords so comma-split always fires
-- Reuses same regex as v_raw_numar comma insertion (lines below)
-- Ex: "Str X nr 26 bl 6 sc 2 ap 36" → "Str X,nr 26,bl 6,sc 2,ap 36"
v_strada := REGEXP_REPLACE(v_strada,
'(\s)(BLOC|BL|SCARA|SC|APARTAMENT|APART|AP|ETAJ|ET|NUMARUL|NUMAR|NR)(\s|\.|\d)',
',\2\3', 1, 0, 'i');
-- Separa strada de tot ce e dupa prima virgula
v_pozitie := INSTR(v_strada, ',');
IF v_pozitie > 0 THEN

94
api/tests/test_address_rules_oracle.py
View File

@@ -93,7 +93,8 @@ def app_settings(client):
resp = client.get("/api/sync/schedule")
assert resp.status_code == 200
import sqlite3
db_path = os.environ.get("SQLITE_DB_PATH", os.path.join(_script_dir, "orders.db"))
from app.config import settings as _s
db_path = _s.SQLITE_DB_PATH if os.path.isabs(_s.SQLITE_DB_PATH) else os.path.join(_script_dir, _s.SQLITE_DB_PATH)
conn = sqlite3.connect(db_path)
conn.row_factory = sqlite3.Row
rows = conn.execute("SELECT key, value FROM app_settings").fetchall()
@@ -273,6 +274,97 @@ class TestAddressRulesE2E:
)
# ---------------------------------------------------------------------------
# Test: parsare componente adresă (strada, numar, bloc, scara, apart, etaj)
# Apelează direct parseaza_adresa_semicolon din Oracle — fără import comandă.
# ---------------------------------------------------------------------------
class TestAddressComponentParsing:
"""Verifică extragerea componentelor adresei direct prin parseaza_adresa_semicolon."""
def _parse_address(self, oracle_pool, address, city="Bucuresti", region="Bucuresti"):
"""Call Oracle parseaza_adresa_semicolon and return parsed components."""
from app.services.import_service import format_address_for_oracle
formatted = format_address_for_oracle(address, city, region)
conn = oracle_pool.acquire()
try:
with conn.cursor() as cur:
p_judet = cur.var(str, 200)
p_localitate = cur.var(str, 200)
p_strada = cur.var(str, 100)
p_numar = cur.var(str, 100)
p_sector = cur.var(str, 100)
p_bloc = cur.var(str, 30)
p_scara = cur.var(str, 10)
p_apart = cur.var(str, 10)
p_etaj = cur.var(str, 20)
cur.callproc("PACK_IMPORT_PARTENERI.parseaza_adresa_semicolon", [
formatted, p_judet, p_localitate, p_strada, p_numar,
p_sector, p_bloc, p_scara, p_apart, p_etaj
])
return {
"strada": p_strada.getvalue(),
"numar": p_numar.getvalue(),
"bloc": p_bloc.getvalue(),
"scara": p_scara.getvalue(),
"apart": p_apart.getvalue(),
"etaj": p_etaj.getvalue(),
"localitate": p_localitate.getvalue(),
"judet": p_judet.getvalue(),
}
finally:
oracle_pool.release(conn)
def test_full_address_all_components(self, oracle_pool):
"""Adresa completă cu nr, bl, sc, ap — toate componentele se extrag din strada."""
addr = self._parse_address(oracle_pool,
"Bd. 1 Decembrie 1918 nr. 26 bl. 6 sc. 2 ap. 36")
assert addr["numar"] == "26", f"numar={addr['numar']}"
assert addr["bloc"] == "6", f"bloc={addr['bloc']}"
assert addr["scara"] == "2", f"scara={addr['scara']}"
assert addr["apart"] == "36", f"apart={addr['apart']}"
assert "SC" not in (addr["strada"] or ""), f"SC ramas in strada: {addr['strada']}"
assert "AP" not in (addr["strada"] or ""), f"AP ramas in strada: {addr['strada']}"
def test_alphanumeric_bloc_and_letter_scara(self, oracle_pool):
"""Bloc alfanumeric (VN9) și scara literă (A) + etaj."""
addr = self._parse_address(oracle_pool,
"Strada Becatei nr 29 bl. VN9 sc. A et. 10 ap. 42")
assert addr["numar"] == "29", f"numar={addr['numar']}"
assert addr["bloc"] == "VN9", f"bloc={addr['bloc']}"
assert addr["scara"] == "A", f"scara={addr['scara']}"
assert addr["etaj"] == "10", f"etaj={addr['etaj']}"
assert addr["apart"] == "42", f"apart={addr['apart']}"
def test_address_without_commas_uppercase(self, oracle_pool):
"""Adresa uppercase fără virgule — keywords spațiu-separate."""
addr = self._parse_address(oracle_pool,
"STR DACIA NR 15 BLOC Z2 SC 1 AP 7 ET 3")
assert addr["numar"] == "15", f"numar={addr['numar']}"
assert addr["bloc"] == "Z2", f"bloc={addr['bloc']}"
assert addr["scara"] == "1", f"scara={addr['scara']}"
assert addr["apart"] == "7", f"apart={addr['apart']}"
assert addr["etaj"] == "3", f"etaj={addr['etaj']}"
def test_address_with_existing_commas(self, oracle_pool):
"""Adresa care deja are virgule — nu se strică parsarea."""
addr = self._parse_address(oracle_pool,
"Str Victoriei, nr. 10, bl. A1, sc. B, et. 2, ap. 15")
assert addr["numar"] == "10", f"numar={addr['numar']}"
assert addr["bloc"] == "A1", f"bloc={addr['bloc']}"
assert addr["scara"] == "B", f"scara={addr['scara']}"
assert addr["etaj"] == "2", f"etaj={addr['etaj']}"
assert addr["apart"] == "15", f"apart={addr['apart']}"
def test_no_keywords_street_unchanged(self, oracle_pool):
"""Adresa simplă fără keywords — strada rămâne intactă."""
addr = self._parse_address(oracle_pool, "Strada Victoriei 10")
assert "VICTORIEI" in (addr["strada"] or ""), f"strada={addr['strada']}"
# ---------------------------------------------------------------------------
# Test regresie: comenzi existente în SQLite
# ---------------------------------------------------------------------------

13
api/tests/test_business_rules.py
View File

@@ -615,6 +615,19 @@ class TestAddrMatch:
r = json.dumps({"strada": "BLD DECEBAL", "numar": "24", "bloc": "S2B", "scara": "1", "apart": "94", "etaj": "7", "localitate": "BUCURESTI", "judet": "BUCURESTI"})
assert _addr_match(g, r) is True
def test_addr_match_diacritics(self):
"""Romanian diacritics (â, ș, ț, î) are normalized same as Oracle storage."""
from app.services.sync_service import _addr_match
import json
# â→a, î→i in city name
g = json.dumps({"address": "Str. Morii 208", "city": "Sf\u00e2ntu Ilie", "region": "Suceava"})
r = json.dumps({"strada": "MORII", "numar": "208", "localitate": "SFANTU ILIE", "judet": "SUCEAVA"})
assert _addr_match(g, r) is True
# ș→s, ț→t in street
g2 = json.dumps({"address": "Str. \u0218oseaua \u021a\u0103rii 5", "city": "Bucure\u0219ti", "region": "Bucure\u0219ti"})
r2 = json.dumps({"strada": "SOSEAUA TARII", "numar": "5", "localitate": "BUCURESTI", "judet": "BUCURESTI"})
assert _addr_match(g2, r2) is True
def test_billing_equals_shipping_short_circuit(self):
"""Short-circuit condition: billing == shipping → reuse addr_livr_id."""
from app.services.import_service import format_address_for_oracle