pfm-ocr/backend/config/date_extract.py

# Expiry-date extraction cascade, split out of classify_ocr_server.py so it
# can be imported (and offline-tested against captured OCR lines) without
# loading any models. Pure regex/string logic - no torch/paddle imports.
import re

EXP_KEYWORD_RE = re.compile(
    r'(?:exp(?:\.|ired)?|tgl(?:\s*exp)?|expiry|bbd|best\s*before|before|best|baik\s*digunakan|\bbb\b)',
    re.IGNORECASE,
)
DD_MM_YYYY_RE = re.compile(
    r'(?<!\d)(0[1-9]|[12]\d|3[01]).*?(0[1-9]|1[0-2]).*?(20\d{2})(?!\d)'
)
DDMMYYYY_RE = re.compile(
    r'(?<!\d)(0[1-9]|[12]\d|3[01])(0[1-9]|1[0-2])(20\d{2})(?!\d)'
)
BB_ATTACHED_DATE_RE = re.compile(
    r'\b(?:bb|bestbefore)\s*[:.-]?\s*(0[1-9]|[12]\d|3[01])(0[1-9]|1[0-2])(20\d{2})(?!\d)',
    re.IGNORECASE,
)
KEYWORD_DIGITS_RE = re.compile(
    r'(?:exp|expired|tgl|expiry|bbd|before|best|bb|baik|digunakan)\s*[:.-]?\s*(\d{6,8})\b',
    re.IGNORECASE,
)
LENIENT_DATE_RE = re.compile(
    r'(?<!\d)(\d{1,2}).*?(\d{1,2}).*?((?:20)?\d{2})(?!\d)'
)
# Store price-tag / label-printer lines ("Printed:04/05/2026 19:53",
# "Rp.6,800/PC"). The date on these is the moment the shelf label was
# printed, never the product's expiry - excluded from the keyword-less
# stages so it can't shadow the real date elsewhere on the package.
PRICE_TAG_RE = re.compile(r'(?i)printed\s*[:.]?|rp\s*[.,]?\s*\d')

def is_valid_ddmmyyyy_digits(val: str) -> bool:
    if len(val) != 8 or not val.isdigit():
        return False
    day, month, year = int(val[0:2]), int(val[2:4]), int(val[4:8])
    return 1 <= day <= 31 and 1 <= month <= 12 and 2000 <= year <= 2099

def is_plausible_date_parts(day: str, month: str, year: str) -> bool:
    # Sanity gate for the lenient stage: it happily assembles junk like
    # "00/22/26" or "1/3/06" out of garbled digit runs. A frozen-food
    # expiry is always a real calendar day within a few years of today.
    if not (day.isdigit() and month.isdigit() and year.isdigit()):
        return False
    d, m = int(day), int(month)
    y = int(year) if len(year) == 4 else 2000 + int(year)
    return 1 <= d <= 31 and 1 <= m <= 12 and 2020 <= y <= 2039

def format_ddmmyyyy(val: str) -> str:
    if is_valid_ddmmyyyy_digits(val):
        return f"{val[0:2]}/{val[2:4]}/{val[4:8]}"
    return val.upper()

def format_ddmmyy(val: str) -> str:
    if len(val) == 6 and val.isdigit():
        day, month = int(val[0:2]), int(val[2:4])
        if 1 <= day <= 31 and 1 <= month <= 12:
            return f"{val[0:2]}/{val[2:4]}/{val[4:6]}"
    return val.upper()

def line_has_exp_keyword(line: str) -> bool:
    if EXP_KEYWORD_RE.search(line):
        return True
    # BB05032027 — keyword directly followed by digits
    return bool(re.search(r'(?i)\b(?:bb|bestbefore)(?:\s*[:.-]?\s*)?\d', line))

def clean_date_line(line: str) -> str:
    # 1) Replace "1)" with "0"
    cleaned = line.replace("1)", "0")

    # 2) Replace "()" with "0"
    cleaned = cleaned.replace("()", "0")

    # Clean BB misrecognitions (convert B8, 8B, 88 to BB when followed by digits)
    cleaned = re.sub(r'\b(?:B8|8B|88)(?=\d)', 'BB', cleaned)
    cleaned = re.sub(r'^(?:B8|8B|88)(?=\d)', 'BB', cleaned)

    # Clean 012/112 month misrecognitions (e.g. 020122027 -> 02022027) —
    # but only when the line does NOT already hold a valid date: a real
    # "01122026" (= 01/12/2026) also matches the 112 pattern (0+112+2026)
    # and would be mangled into 7-digit junk.
    if not (DDMMYYYY_RE.search(cleaned) or DD_MM_YYYY_RE.search(cleaned)):
        cleaned = re.sub(r'(?<!\d)(\d{1,2})012(20\d{2})(?!\d)', r'\g<1>02\g<2>', cleaned)
        cleaned = re.sub(r'(?<!\d)(\d{1,2})([-./\s]+)012([-./\s]+)(20\d{2})(?!\d)', r'\g<1>\g<2>02\g<3>\g<4>', cleaned)
        cleaned = re.sub(r'(?<!\d)(\d{1,2})112(20\d{2})(?!\d)', r'\g<1>02\g<2>', cleaned)
        cleaned = re.sub(r'(?<!\d)(\d{1,2})([-./\s]+)112([-./\s]+)(20\d{2})(?!\d)', r'\g<1>\g<2>02\g<3>\g<4>', cleaned)

    # Run contextual replacements
    for _ in range(3):
        # letter o/O flanked by digits or boundary -> 0
        cleaned = re.compile(r'(\d)[oO](\d|\b)').sub(r'\g<1>0\g<2>', cleaned)
        cleaned = re.compile(r'(\b|\d)[oO](\d)').sub(r'\g<1>0\g<2>', cleaned)

        # letter I/i/l/| flanked by digits -> 1
        cleaned = re.compile(r'(\d)[Ii|l](\d|\b)').sub(r'\g<1>1\g<2>', cleaned)
        cleaned = re.compile(r'(\b|\d)[Ii|l](\d)').sub(r'\g<1>1\g<2>', cleaned)

        # letter S/s flanked by digits -> 5
        cleaned = re.compile(r'(\d)[Ss](\d|\b)').sub(r'\g<1>5\g<2>', cleaned)
        cleaned = re.compile(r'(\b|\d)[Ss](\d)').sub(r'\g<1>5\g<2>', cleaned)

        # letter Z/z flanked by digits -> 2
        cleaned = re.compile(r'(\d)[Zz](\d|\b)').sub(r'\g<1>2\g<2>', cleaned)
        cleaned = re.compile(r'(\b|\d)[Zz](\d)').sub(r'\g<1>2\g<2>', cleaned)

        # letter B flanked by digits -> 8
        cleaned = re.compile(r'(\d)B(\d|\b)').sub(r'\g<1>8\g<2>', cleaned)
        cleaned = re.compile(r'(\b|\d)B(\d)').sub(r'\g<1>8\g<2>', cleaned)

    return cleaned

def extract_expired_date(text_lines):
    """Return (formatted_date, line_index, source_line). Prioritises BB/EXP + DDMMYYYY or DD MM YYYY."""
    if not text_lines:
        return None, None, None

    cleaned_lines = [clean_date_line(line) for line in text_lines]

    def pick(match, idx, cleaned_line, formatter=None):
        raw = match.group(0)
        original_line = text_lines[idx].strip()
        if match.lastindex and match.lastindex >= 3:
            formatted = f"{match.group(1)}/{match.group(2)}/{match.group(3)}"
        elif match.lastindex and match.lastindex >= 1 and match.group(1).isdigit():
            digits = match.group(1)
            if len(digits) == 8:
                formatted = format_ddmmyyyy(digits)
            elif len(digits) == 6:
                formatted = format_ddmmyy(digits)
            else:
                formatted = digits
        elif formatter:
            formatted = formatter(raw)
        else:
            formatted = raw.strip().upper()
        return formatted, idx, original_line

    # 1) BB/EXP keyword lines — compact DDMMYYYY (e.g. BB05032027, EXP 05032027)
    for idx, line in enumerate(cleaned_lines):
        if not line_has_exp_keyword(line):
            continue
        match = BB_ATTACHED_DATE_RE.search(line) or DDMMYYYY_RE.search(line)
        if match:
            return pick(match, idx, line)

    # 2) BB/EXP keyword lines — spaced DD MM YYYY (e.g. BB 05 03 2027)
    for idx, line in enumerate(cleaned_lines):
        if not line_has_exp_keyword(line):
            continue
        match = DD_MM_YYYY_RE.search(line)
        if match:
            return pick(match, idx, line)

    # 3) Keyword + 6–8 digit run (BB05032027 via keyword_digits)
    for idx, line in enumerate(cleaned_lines):
        match = KEYWORD_DIGITS_RE.search(line)
        if match:
            digits = match.group(1)
            if len(digits) == 8 and is_valid_ddmmyyyy_digits(digits):
                return format_ddmmyyyy(digits), idx, text_lines[idx].strip()
            if len(digits) == 6:
                return format_ddmmyy(digits), idx, text_lines[idx].strip()

    # 3.5) BB/EXP keyword lines — lenient check for unclear/noisy date formats (e.g. BB 02J 132027)
    for idx, line in enumerate(cleaned_lines):
        if not line_has_exp_keyword(line):
            continue
        match = LENIENT_DATE_RE.search(line)
        if match and is_plausible_date_parts(match.group(1), match.group(2), match.group(3)):
            return pick(match, idx, line)

    # 3.6) Keyword line + date split onto an adjacent line (PaddleOCR sometimes
    # detects "BB"/"Baik digunakan" as its own box, separate from the date
    # digits in a neighboring box, e.g. "BB" / "05032027" as two lines).
    for idx, line in enumerate(cleaned_lines):
        if not line_has_exp_keyword(line):
            continue
        for j in (idx + 1, idx - 1, idx + 2):
            if j < 0 or j >= len(cleaned_lines) or j == idx:
                continue
            neighbor = cleaned_lines[j]
            combined = f"{line} {neighbor}" if j > idx else f"{neighbor} {line}"
            match = (BB_ATTACHED_DATE_RE.search(combined)
                     or DDMMYYYY_RE.search(combined)
                     or DD_MM_YYYY_RE.search(combined))
            if match:
                report_idx = j if sum(c.isdigit() for c in neighbor) > sum(c.isdigit() for c in line) else idx
                return pick(match, report_idx, combined)

    # 4) Any line — spaced DD MM YYYY (excluding store price-tag lines)
    for idx, line in enumerate(cleaned_lines):
        if PRICE_TAG_RE.search(line):
            continue
        match = DD_MM_YYYY_RE.search(line)
        if match:
            return pick(match, idx, line)

    # 5) Any line — compact DDMMYYYY (skip likely SKU: same line has 8-digit product code context)
    for idx, line in enumerate(cleaned_lines):
        if PRICE_TAG_RE.search(line):
            continue
        for match in DDMMYYYY_RE.finditer(line):
            digits = f"{match.group(1)}{match.group(2)}{match.group(3)}"
            if is_valid_ddmmyyyy_digits(digits):
                # Skip if this 8-digit block is the only digits and looks like SKU on label top
                if re.search(r'\b\d{8}\b', line) and not line_has_exp_keyword(line):
                    if re.search(r'(?:nugget|chicken|fiesta|champ|okey|akumo|frozen|gr)', line, re.I):
                        continue
                return format_ddmmyyyy(digits), idx, text_lines[idx].strip()

    # 6) Legacy patterns (slashes, month names, etc.)
    date_patterns = [
        r'\b\d{2}[-./]\d{2}[-./]\d{2,4}\b',
        r'\b\d{4}[-./]\d{2}[-./]\d{2}\b',
        r'\b\d{2}\s+(?:JAN|FEB|MAR|APR|MAY|JUN|JUL|AUG|SEP|OCT|NOV|DEC)[a-zA-Z]*\s+\d{2,4}\b',
    ]
    for idx, line in enumerate(cleaned_lines):
        if not line_has_exp_keyword(line):
            continue
        for pat in date_patterns:
            match = re.search(pat, line, re.IGNORECASE)
            if match:
                return match.group(0).upper(), idx, text_lines[idx].strip()

    return None, None, None

def line_contains_expired_date(line: str, expired_date: str) -> bool:
    if not line or not expired_date:
        return False
    digits_only = re.sub(r"\D", "", expired_date)
    line_digits = re.sub(r"\D", "", line)
    if len(digits_only) >= 6 and digits_only in line_digits:
        return True
    compact = expired_date.replace("/", "")
    return compact in line.replace(" ", "") or expired_date in line

def find_expired_crop_index(text_lines, expired_idx, expired_date, polys_len):
    """Pick OCR box index for cropping; prefer the line that actually contains the date."""
    if not expired_date or polys_len <= 0:
        return None

    if (
        expired_idx is not None
        and expired_idx < polys_len
        and expired_idx < len(text_lines)
        and line_contains_expired_date(text_lines[expired_idx], expired_date)
    ):
        return expired_idx

    keyword_match = None
    for idx, line in enumerate(text_lines):
        if idx >= polys_len:
            break
        if not line_contains_expired_date(line, expired_date):
            continue
        if line_has_exp_keyword(line):
            return idx
        if keyword_match is None:
            keyword_match = idx

    if keyword_match is not None:
        return keyword_match

    if expired_idx is not None and expired_idx < polys_len:
        return expired_idx
    return None