romfast/roa2web-service-auto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ocr): Fix store profile extraction patterns and module loading

Browse Source 
Major fixes to OCR store profiles for Romanian receipt extraction:

- Fix ProfileRegistry module path resolution (was loading 0 profiles)
- Add multiline TVA extraction for Brick, Electrobering, Gama Ink
- Add "CARTE CREDIT" payment detection for OMV/SOCAR gas stations
- Handle OCR artifacts: TVA→TUA, "-"→"4", I→L in CUI markers
- Add client CUI patterns for Brick receipts
- Add profile selection logging to ocr_extractor.py
- Create test script for all 29 PDFs (test_all_profiles.py)

Test results: 13/29 passing (improved from 9/29)
Remaining failures are primarily OCR quality issues.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Claude Agent
2026-01-07 09:40:58 +00:00
parent 099556213d
commit 28f259cd05
13 changed files with 1531 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
backend/modules/data_entry/services/ocr/profiles/electrobering.py
View File

@@ -2,11 +2,16 @@
ELECTROBERING S.R.L. store profile for OCR extraction.
Electronics and home supplies store.
Receipt structure:
- TVA format: "TOTAL TVA A - - 19%" with amount on next line
- "TOTAL TVA BON" with total TVA amount
- Client CUI: "CIF CLIENT: XXXXXXX"
"""
import re
from decimal import Decimal, InvalidOperation
from typing import List, Dict, Any
from typing import List, Dict, Any, Tuple, Optional
from .base import BaseStoreProfile
from . import ProfileRegistry
@@ -15,11 +20,11 @@ from . import ProfileRegistry
@ProfileRegistry.register
class ElectroberingProfile(BaseStoreProfile):
"""
ELECTROBERING S.R.L. - standard TVA profile.
ELECTROBERING S.R.L. - standard TVA profile with multiline support.
Key characteristics:
- Standard TVA format (single rate, any percentage)
- Electronics and home supplies
- TVA format with rate on one line, amount on next
- Double-dash separators common (OCR artifact)
- May have client CUI for B2B purchases
- CARD payment typical
"""
@@ -28,19 +33,28 @@ class ElectroberingProfile(BaseStoreProfile):
NAME_PATTERNS = ["ELECTROBERING", "ELECTR0BERING", "ELECTROBERING SRL"]
STORE_NAME = "ELECTROBERING S.R.L."
# Standard TVA patterns (flexible - accepts any rate)
# ELECTROBERING TVA patterns (handles double-dash and multiline)
TVA_PATTERNS = [
# "TVA A: XX% = YY,YY" or "TVA-A XX% YY,YY"
r'TVA\s*[-:]?\s*([A-D])\s*:?\s*(\d{1,2})\s*%\s*[=:]?\s*([\d.,]+)',
# "A - XX,XX% = YY,YY"
r'([A-D])\s*[-:]\s*(\d{1,2})[.,]?\d{0,2}\s*%\s*[=:]?\s*([\d.,]+)',
# "TVA XX% YY,YY" (simple format without code)
r'TVA\s+(\d{1,2})\s*%\s*([\d.,]+)',
# "TOTAL TVA A - - 19%" with amount on next line
r'TOTAL\s+TVA\s*([A-D])\s*[-\s]+(\d{1,2})\s*%',
# "TOTAL TVA A 19%" without separator
r'TOTAL\s+TVA\s+([A-D])\s+(\d{1,2})\s*%',
# Standard: "TVA A: XX% = YY,YY"
r'TVA\s*([A-D])\s*[-:]?\s*(\d{1,2})\s*%\s*[=:]?\s*([\d.,]+)',
]
# TOTAL TVA BON pattern (fallback)
TOTAL_TVA_BON_PATTERN = r'TOTAL\s+TVA\s+BON'
def extract_tva_entries(self, text: str) -> List[dict]:
"""
Extract TVA entries from receipt text.
Extract ELECTROBERING-specific TVA entries.
ELECTROBERING receipts show TVA in multi-line format:
"TOTAL TVA A - - 19%"
"5.59"
"TOTAL TVA BON"
"5.59"
Args:
text: Raw OCR text from receipt
@@ -49,45 +63,61 @@ class ElectroberingProfile(BaseStoreProfile):
List of TVA entries with code, percent, and amount
"""
entries = []
seen = set()
text_upper = text.upper()
lines = text_upper.split('\n')
# Try coded patterns first
for pattern in self.TVA_PATTERNS[:2]:
for match in re.finditer(pattern, text, re.IGNORECASE):
try:
code = match.group(1).upper()
percent = int(match.group(2))
amount = self._parse_decimal(match.group(3))
if amount and amount > 0:
entry_key = (code, percent)
if entry_key not in seen:
entries.append({
'code': code,
'percent': percent,
'amount': amount
})
seen.add(entry_key)
except (ValueError, InvalidOperation, IndexError):
continue
# Fallback to simple format
if not entries:
simple_pattern = self.TVA_PATTERNS[2]
for match in re.finditer(simple_pattern, text, re.IGNORECASE):
try:
percent = int(match.group(1))
amount = self._parse_decimal(match.group(2))
# Find TVA rate line and get amount from next line
for i, line in enumerate(lines):
# Match "TOTAL TVA A - - 19%" or "TOTAL TVA A 19%"
match = re.search(r'TOTAL\s+TVA\s*([A-D])\s*[-\s]+(\d{1,2})\s*%', line)
if match:
code = match.group(1)
percent = int(match.group(2))
# Amount should be on next line
if i + 1 < len(lines):
amount_str = lines[i + 1].strip()
amount = self._parse_decimal(amount_str)
if amount and amount > 0:
entries.append({
'code': 'A',
'code': code,
'percent': percent,
'amount': amount
})
break
return entries
# Fallback: Find TOTAL TVA BON and get amount
for i, line in enumerate(lines):
if re.search(self.TOTAL_TVA_BON_PATTERN, line):
# Amount should be on next line
if i + 1 < len(lines):
amount_str = lines[i + 1].strip()
amount = self._parse_decimal(amount_str)
if amount and amount > 0:
entries.append({
'code': 'A',
'percent': 19, # Default Romanian TVA rate
'amount': amount
})
return entries
# Last fallback: inline format "TVA A: XX% = YY,YY"
for pattern in [self.TVA_PATTERNS[2]]:
match = re.search(pattern, text_upper, re.IGNORECASE)
if match and len(match.groups()) >= 3:
try:
code = match.group(1)
percent = int(match.group(2))
amount = self._parse_decimal(match.group(3))
if amount and amount > 0:
entries.append({
'code': code,
'percent': percent,
'amount': amount
})
return entries
except (ValueError, InvalidOperation):
continue
pass
return entries
@@ -99,4 +129,5 @@ class ElectroberingProfile(BaseStoreProfile):
"has_client_cui": True, # May have client CUI for B2B
"has_efactura": False,
"is_non_vat_payer": False,
"tva_on_separate_line": True,
}