Delete old bot versions in src/old

The bot, tests and .exe build use none of them. They stay in Git history (902ff93) if the old logic is ever needed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-21 17:31:33 +05:30
1 parent 230da1af36
commit 48781f35eb
@@ -1,22 +0,0 @@
-python -m PyInstaller ^
-  --onefile ^
-  --console ^
-  --name ClaimStatusBot ^
-  --add-data "..\Config;Config" ^
-  main.py
-
-python -m PyInstaller --onefile ^
--add-data "..\Input;Input" ^
--add-data "..\Screenshots;Screenshots" ^
--hidden-import=pyotp ^
--hidden-import=pandas ^
--hidden-import=openpyxl ^
-main.py
-
-
-python -m PyInstaller --onefile ^
--add-data "..\Input;Input" ^
--add-data "..\Screenshots;Screenshots" ^
--hidden-import=pandas ^
--hidden-import=openpyxl ^
-AR_Workable
@@ -1,38 +0,0 @@
-# -*- mode: python ; coding: utf-8 -*-
-
-
-a = Analysis(
-    ['main.py'],
-    pathex=[],
-    binaries=[],
-    datas=[('..\\Input', 'Input'), ('..\\Screenshots', 'Screenshots')],
-    hiddenimports=['pyotp', 'pandas', 'openpyxl'],
-    hookspath=[],
-    hooksconfig={},
-    runtime_hooks=[],
-    excludes=[],
-    noarchive=False,
-    optimize=0,
-)
-pyz = PYZ(a.pure)
-
-exe = EXE(
-    pyz,
-    a.scripts,
-    a.binaries,
-    a.datas,
-    [],
-    name='main',
-    debug=False,
-    bootloader_ignore_signals=False,
-    strip=False,
-    upx=True,
-    upx_exclude=[],
-    runtime_tmpdir=None,
-    console=True,
-    disable_windowed_traceback=False,
-    argv_emulation=False,
-    target_arch=None,
-    codesign_identity=None,
-    entitlements_file=None,
-)
@@ -1,38 +0,0 @@
-# -*- mode: python ; coding: utf-8 -*-
-
-
-a = Analysis(
-    ['main_v1.py'],
-    pathex=[],
-    binaries=[],
-    datas=[],
-    hiddenimports=[],
-    hookspath=[],
-    hooksconfig={},
-    runtime_hooks=[],
-    excludes=[],
-    noarchive=False,
-    optimize=0,
-)
-pyz = PYZ(a.pure)
-
-exe = EXE(
-    pyz,
-    a.scripts,
-    a.binaries,
-    a.datas,
-    [],
-    name='main_v1',
-    debug=False,
-    bootloader_ignore_signals=False,
-    strip=False,
-    upx=True,
-    upx_exclude=[],
-    runtime_tmpdir=None,
-    console=True,
-    disable_windowed_traceback=False,
-    argv_emulation=False,
-    target_arch=None,
-    codesign_identity=None,
-    entitlements_file=None,
-)
@@ -1,491 +0,0 @@
-import re
-import pdfplumber
-
-# ===========================================================================
-# CMS-1500 PDF EXTRACTOR  —  Production-Ready  v3.0
-# ===========================================================================
-# Fixes vs prior versions:
-#   • CPT  : strict 5-digit match guarded by known CPT range (10000-99999),
-#             zip-codes / account-numbers / tax-ids filtered out
-#   • POS  : extracted per service-line row; count always matches CPT count
-#   • Modifier: column-position aware extraction (not regex on full row text)
-#   • Diagnosis codes: dual-pass — word-level near field-21 + full-text regex
-#   • Date of Service: handles split cells (MM | DD | YY) and slash formats
-#   • Units: column-position aware (column G on CMS-1500)
-#   • Rendering Provider #: 10-digit NPI per row, column J
-#   • All multi-value fields formatted as "Field 1: val; Field 2: val …"
-# ===========================================================================
-
-
-# ---------------------------------------------------------------------------
-# Helper: is this token a valid CPT code?
-# ---------------------------------------------------------------------------
-def _is_cpt(token: str) -> bool:
-    """Return True only for 5-digit numbers in the plausible CPT range."""
-    if not re.fullmatch(r"\d{5}", token):
-        return False
-    val = int(token)
-    return 10000 <= val <= 99999
-
-
-# ---------------------------------------------------------------------------
-# Helper: is this token a valid ICD-10 diagnosis code?
-# ---------------------------------------------------------------------------
-def _is_icd10(token: str) -> bool:
-    return bool(re.fullmatch(r"[A-Z]\d{2,3}(?:\.\d{1,4})?", token))
-
-
-# ---------------------------------------------------------------------------
-# Helper: clean / normalise a cell value
-# ---------------------------------------------------------------------------
-def _cell(c) -> str:
-    return str(c).strip() if c else ""
-
-
-# ---------------------------------------------------------------------------
-# Helper: join multi-value list into labelled string
-# ---------------------------------------------------------------------------
-def _format_list(values: list, label: str) -> str:
-    clean = [v for v in values if v]
-    if not clean:
-        return ""
-    if len(clean) == 1:
-        return clean[0]
-    return "; ".join(f"{label} {i+1}: {v}" for i, v in enumerate(clean))
-
-
-# ---------------------------------------------------------------------------
-# Known modifier codes (GP, GN, GO …) + numeric modifiers (25, 26, 51, 59 …)
-# CMS-1500 column E holds up to 4 modifier slots.
-# ---------------------------------------------------------------------------
-_ALPHA_MODIFIERS = {
-    "GP", "GN", "GO", "GQ", "GX", "GY", "GZ",
-    "CQ", "TC", "26", "LT", "RT", "NU", "RR", "UE",
-    "KX", "KU", "KV", "KW", "KX",
-    "JW", "JZ",
-    "AA", "AB", "AD", "AE", "AF", "AG", "AH", "AI", "AJ", "AK",
-    "AM", "AO", "AP", "AQ", "AR", "AS", "AT",
-    "CA", "CB", "CC", "CD", "CE", "CF", "CH", "CI", "CJ", "CK", "CL",
-    "CM", "CN", "CO", "CP", "CR", "CS",
-    "DA",
-    "E1","E2","E3","E4",
-    "FA","F1","F2","F3","F4","F5","F6","F7","F8","F9",
-    "FX",
-    "GA","GB","GC","GD","GE","GF","GH","GJ","GK","GL","GM",
-    "HA","HB","HC","HD","HE","HF","HG","HH","HI","HJ","HK",
-    "HL","HM","HN","HO","HP","HQ","HR","HS","HT","HU","HV","HW",
-    "HX","HY","HZ",
-    "JA","JB","JC","JD","JE",
-    "LA","LC","LD","LE","LF","LG","LH","LI","LJ","LK","LL","LM",
-    "LN","LO","LP","LQ","LR","LS","LT","LU","LV","LW","LX","LY","LZ",
-    "P1","P2","P3","P4","P5","P6",
-    "Q0","Q1","Q2","Q3","Q4","Q5","Q6","Q7","Q8","Q9",
-    "QA","QB","QC","QD","QE","QF","QG","QH","QJ","QK","QL","QM","QN",
-    "QP","QQ","QR","QS","QT","QU","QV","QW","QX","QY","QZ",
-    "RA","RB","RC","RD","RE","RF","RG","RH","RI","RJ","RK","RL","RM",
-    "RN","RO","RP","RQ","RR","RS","RT","RU","RV","RW","RX","RY","RZ",
-    "SA","SB","SC","SD","SE","SF","SG","SH","SI","SJ","SK","SL","SM",
-    "SN","SO","SP","SQ","SR","SS","ST","SU","SV","SW","SX","SY",
-    "TA","TB","TC","TD","TE","TF","TG","TH","TI","TJ","TK","TL","TM",
-    "TN","TP","TQ","TR","TS","TT","TU","TV","TW","TX","TY","TZ",
-    "U1","U2","U3","U4","U5","U6","U7","U8","U9",
-    "UA","UB","UC","UD","UE","UF","UG","UH","UJ","UK","UL","UM","UN",
-    "UP","UQ","UR","US",
-    "V5","V6","V7","V8","V9",
-    "XE","XP","XS","XU",
-}
-
-_NUMERIC_MODIFIERS = {str(n) for n in range(22, 100)}  # 22-99
-
-_ALL_MODIFIERS = _ALPHA_MODIFIERS | _NUMERIC_MODIFIERS
-
-# Tokens that look like 2-letter codes but are NOT modifiers
-_NOT_MODIFIERS = {
-    "MM","DD","YY","TO","OF","OR","IN","IS","NO","BY","AT","BE",
-    "DO","GO","HE","HI","IF","ME","MY","OK","ON","SO","UP","US","WE",
-    "NPI","ABC","ICD","CPT","POS","DOS","EMG","REF","QTY",
-    "MM","DD","YY",
-}
-
-
-def _extract_modifiers_from_tokens(tokens: list[str]) -> str:
-    """
-    Given the token list of a service-line row, return only legitimate
-    modifier codes.  Tokens are scanned left-to-right; we stop after 4
-    modifiers (CMS-1500 allows max 4 per line).
-    """
-    found = []
-    for t in tokens:
-        t_up = t.upper()
-        if t_up in _NOT_MODIFIERS:
-            continue
-        if t_up in _ALL_MODIFIERS and t_up not in found:
-            found.append(t_up)
-            if len(found) == 4:
-                break
-    return " ".join(found)
-
-
-# ---------------------------------------------------------------------------
-# CMS-1500 service-line table parser
-# ---------------------------------------------------------------------------
-def _parse_service_lines(tables: list) -> dict:
-    """
-    Walk every table extracted by pdfplumber and collect per-row data for
-    columns A-J of CMS-1500 section 24:
-      A  Date(s) of Service (From / To)
-      B  Place of Service
-      C  EMG
-      D  CPT / HCPCS + Modifier(s)
-      E  Diagnosis Pointer
-      F  $ Charges
-      G  Days or Units
-      H  EPSDT
-      I  ID Qual
-      J  Rendering Provider ID
-    """
-    cpts, pos_list, dos_list, mod_list, units_list, rp_list = [], [], [], [], [], []
-
-    for table in tables:
-        for row in table:
-            if not row:
-                continue
-
-            cells = [_cell(c) for c in row]
-            row_text = " ".join(cells)
-
-            # ---- Quick pre-filter: row must contain a valid CPT code --------
-            candidate_cpts = re.findall(r"\b(\d{5})\b", row_text)
-            valid_cpts_in_row = [c for c in candidate_cpts if _is_cpt(c)]
-            if not valid_cpts_in_row:
-                continue
-
-            # ---- Guard: skip header / label rows ----------------------------
-            # If the row text contains many uppercase words it's likely a label
-            upper_words = re.findall(r"\b[A-Z]{3,}\b", row_text)
-            if len(upper_words) > 4:
-                continue
-
-            # ---- CPT: first valid CPT per row (CMS-1500 = 1 CPT per line) ---
-            cpt_val = valid_cpts_in_row[0]
-            cpts.append(cpt_val)
-
-            # ---- Date of Service -------------------------------------------
-            # Format variants: "03 26 26", "03/26/26", "03-26-26"
-            date_match = re.search(
-                r"\b(\d{2})[\/\s\-]+(\d{2})[\/\s\-]+(\d{2,4})\b", row_text
-            )
-            if date_match:
-                mm, dd, yy = date_match.group(1), date_match.group(2), date_match.group(3)
-                yy = yy if len(yy) == 4 else ("20" + yy if int(yy) < 50 else "19" + yy)
-                dos_list.append(f"{mm}/{dd}/{yy}")
-            else:
-                dos_list.append("")
-
-            # ---- POS (Place of Service) — 2-digit code, column B -----------
-            # Strategy: find the 2-digit token that appears BEFORE the CPT code
-            # in the row text.  Common POS values: 11,12,21,22,23,24,31,32,33,
-            # 41,42,49,50,51,52,53,54,55,56,57,61,62,65,71,72,81,99
-            pos_val = ""
-            row_before_cpt = row_text[: row_text.index(cpt_val)]
-            pos_candidates = re.findall(r"\b(\d{2})\b", row_before_cpt)
-            # Take the LAST 2-digit number before CPT (closest to CPT = POS)
-            # but exclude date fragments (must not be 01-31 preceded by another)
-            valid_pos_codes = {
-                "11","12","13","14","15","16","17","18","19","20",
-                "21","22","23","24","25","31","32","33","34","41",
-                "42","49","50","51","52","53","54","55","56","57",
-                "60","61","62","65","71","72","81","99",
-            }
-            for p in reversed(pos_candidates):
-                if p in valid_pos_codes:
-                    pos_val = p
-                    break
-            pos_list.append(pos_val)
-
-            # ---- Modifiers — tokens AFTER CPT code, before $-amount --------
-            # Isolate the segment after CPT to reduce noise
-            cpt_idx = row_text.index(cpt_val)
-            segment_after_cpt = row_text[cpt_idx + len(cpt_val):]
-            tokens_after = segment_after_cpt.split()
-            mod_val = _extract_modifiers_from_tokens(tokens_after)
-            mod_list.append(mod_val)
-
-            # ---- Units (Days/Units) — column G on CMS-1500 -----------------
-            # Units is almost always a small integer (1-99).
-            # We look for a standalone 1-2 digit number that appears AFTER
-            # any dollar amount (charges column F).
-            units_val = ""
-            # Remove currency-looking tokens to isolate units
-            seg_no_dollars = re.sub(r"\d{1,3}(?:,\d{3})*(?:\.\d{2})?", " MONEY ", segment_after_cpt)
-            unit_candidates = re.findall(r"\b([1-9]\d?)\b", seg_no_dollars)
-            # The first small integer after modifiers is usually units
-            for uc in unit_candidates:
-                if 1 <= int(uc) <= 99:
-                    units_val = uc
-                    break
-            units_list.append(units_val)
-
-            # ---- Rendering Provider / NPI — 10-digit number, column J ------
-            npi_candidates = re.findall(r"\b(\d{10})\b", row_text)
-            rp_list.append(npi_candidates[-1] if npi_candidates else "")
-
-    return {
-        "cpts": cpts,
-        "pos_list": pos_list,
-        "dos_list": dos_list,
-        "mod_list": mod_list,
-        "units_list": units_list,
-        "rp_list": rp_list,
-    }
-
-
-# ---------------------------------------------------------------------------
-# Diagnosis code extraction (field 21 of CMS-1500)
-# ---------------------------------------------------------------------------
-def _extract_diagnosis_codes(text: str, words: list) -> list:
-    """Return a deduplicated, ordered list of ICD-10 codes from field 21."""
-    codes = []
-
-    # --- Pass 1: word-coordinate scan near field "21" label -----------------
-    for i, w in enumerate(words):
-        if w["text"] in ("21", "21.", "21:"):
-            base_y = w["top"]
-            # Field 21 spans ~80px vertically and the full page width after label
-            region = [
-                nxt for nxt in words
-                if (base_y - 5) <= nxt["top"] <= (base_y + 90)
-                and nxt["x0"] >= w["x0"] - 5
-            ]
-            for word in region:
-                if _is_icd10(word["text"]):
-                    codes.append(word["text"])
-            if codes:
-                break
-
-    # --- Pass 2: regex scan on full extracted text --------------------------
-    if not codes:
-        # Try to isolate the diagnosis section (between field 21 and 22/23/24)
-        diag_section_match = re.search(
-            r"(?:21|DIAGNOSIS)[^\n]*\n([\s\S]{0,400})(?:22\.|23\.|24\.|ICD)",
-            text, re.IGNORECASE
-        )
-        target = diag_section_match.group(1) if diag_section_match else text
-        raw = re.findall(r"\b([A-Z]\d{2,3}(?:\.\d{1,4})?)\b", target)
-        codes.extend(raw)
-
-    # --- Pass 3: broad scan if still empty ----------------------------------
-    if not codes:
-        raw = re.findall(r"\b([A-Z]\d{2,3}(?:\.\d{1,4})?)\b", text)
-        # Filter obvious non-ICD tokens
-        codes = [c for c in raw if not c.startswith("NP")]
-
-    # Deduplicate preserving order
-    seen = set()
-    unique = []
-    for c in codes:
-        if c not in seen:
-            seen.add(c)
-            unique.append(c)
-    return unique
-
-
-# ===========================================================================
-# MAIN FUNCTION
-# ===========================================================================
-def extract_pdf_data_fast(
-    pdf_path: str,
-    claim_id: str = "",
-    patient_account: str = "",
-    insurance: str = "",
-    patient_name: str = "",
-    total_charges: str = "",
-    signature_physician: str = "",
-) -> dict | None:
-    """
-    Extract all relevant fields from a CMS-1500 PDF.
-
-    Parameters
-    ----------
-    pdf_path            : Path to the PDF file.
-    claim_id            : Pre-populated from upstream data (e.g. spreadsheet).
-    patient_account     : Pre-populated patient account number.
-    insurance           : Pre-populated insurance name.
-    patient_name        : Pre-populated patient name.
-    total_charges       : Pre-populated total charges.
-    signature_physician : Pre-populated physician signature.
-
-    Returns
-    -------
-    dict with all extracted fields, or None on critical failure.
-    """
-
-    data = {
-        "Claim ID": claim_id,
-        "Rendering Provider #": "",
-        "Signature of Physician": signature_physician,
-        "Patient's Account No": patient_account,
-        "Date of Birth": "",
-        "Insurance Name": insurance,
-        "Insured ID Number": "",
-        "Patient's Name": patient_name,
-        "Date of Service": "",
-        "Diagnosis Codes": "",
-        "CPT": "",
-        "POS": "",
-        "Modifier": "",
-        "Units": "",
-        "Charges": total_charges,
-    }
-
-    try:
-        # ------------------------------------------------------------------ #
-        # Open once, grab text + words + tables                               #
-        # ------------------------------------------------------------------ #
-        with pdfplumber.open(pdf_path) as pdf:
-            page = pdf.pages[0]
-            text  = page.extract_text(x_tolerance=2, y_tolerance=2) or ""
-            words = page.extract_words()
-            tables = page.extract_tables()
-
-        print(f"[DEBUG] Opened PDF: {pdf_path}")
-        print(f"[DEBUG] Tables found: {len(tables)}")
-
-        # ================================================================== #
-        # 1. DATE OF BIRTH  (field 3 — format MM DD YYYY)                    #
-        # ================================================================== #
-        dob_match = re.search(r"\b(\d{2})\s+(\d{2})\s+(\d{4})\b", text)
-        if dob_match:
-            data["Date of Birth"] = (
-                f"{dob_match.group(1)}/{dob_match.group(2)}/{dob_match.group(3)}"
-            )
-
-        # ================================================================== #
-        # 2. INSURED'S I.D. NUMBER  (field 1a)                               #
-        # ================================================================== #
-        insured_id = ""
-
-        # Method A: word following "1a." label
-        for i, w in enumerate(words):
-            if w["text"].lower().rstrip(".") in ("1a",):
-                for nxt in words[i + 1 : i + 6]:
-                    t = nxt["text"]
-                    # Must be alphanumeric, ≥8 chars, contain both letters & digits
-                    if (
-                        re.match(r"^[A-Z0-9]{8,20}$", t)
-                        and re.search(r"[A-Z]", t)
-                        and re.search(r"\d", t)
-                    ):
-                        insured_id = t
-                        break
-                if insured_id:
-                    break
-
-        # Method B: proximity to "INSURED'S I.D. NUMBER" label
-        if not insured_id:
-            for i, w in enumerate(words):
-                if "INSURED" in w["text"].upper():
-                    nearby = words[i : min(i + 6, len(words))]
-                    if any("NUMBER" in nxt["text"].upper() for nxt in nearby):
-                        base_y = w["top"]
-                        candidates = [
-                            nxt for nxt in words
-                            if abs(nxt["top"] - base_y) < 15 and nxt["x0"] > w["x0"]
-                        ]
-                        for c in reversed(candidates):
-                            t = c["text"]
-                            if (
-                                re.match(r"^[A-Z0-9]{8,20}$", t)
-                                and re.search(r"[A-Z]", t)
-                                and re.search(r"\d", t)
-                            ):
-                                insured_id = t
-                                break
-                        if insured_id:
-                            break
-
-        # Method C: top-right quadrant scan
-        if not insured_id:
-            _skip = {"MEDICARE", "MEDICAID", "CHAMPVA", "TRICARE", "CHAMPUS"}
-            for w in words:
-                if w["x0"] > 400 and w["top"] < 200:
-                    t = w["text"]
-                    if (
-                        re.match(r"^[A-Z0-9]{8,20}$", t)
-                        and re.search(r"[A-Z]", t)
-                        and re.search(r"\d", t)
-                        and t not in _skip
-                    ):
-                        insured_id = t
-                        break
-
-        data["Insured ID Number"] = insured_id
-        print(f"[DEBUG] Insured ID: {insured_id}")
-
-        # ================================================================== #
-        # 3. DIAGNOSIS CODES  (field 21)                                     #
-        # ================================================================== #
-        dx_codes = _extract_diagnosis_codes(text, words)
-        if dx_codes:
-            codes_str  = ", ".join(dx_codes)
-            data["Diagnosis Codes"] = f"{codes_str} (Total: {len(dx_codes)})"
-        print(f"[DEBUG] Diagnosis codes ({len(dx_codes)}): {dx_codes}")
-
-        # ================================================================== #
-        # 4. SERVICE LINES  (section 24 — columns A-J)                       #
-        # ================================================================== #
-        svc = _parse_service_lines(tables)
-        cpts      = svc["cpts"]
-        pos_list  = svc["pos_list"]
-        dos_list  = svc["dos_list"]
-        mod_list  = svc["mod_list"]
-        units_list= svc["units_list"]
-        rp_list   = svc["rp_list"]
-
-        print(f"[DEBUG] Service lines found: {len(cpts)}")
-        print(f"[DEBUG] CPTs      : {cpts}")
-        print(f"[DEBUG] POS       : {pos_list}")
-        print(f"[DEBUG] DOS       : {dos_list}")
-        print(f"[DEBUG] Modifiers : {mod_list}")
-        print(f"[DEBUG] Units     : {units_list}")
-        print(f"[DEBUG] Providers : {rp_list}")
-
-        # Counts must match CPT count — pad with "" if somehow shorter
-        n = len(cpts)
-        def _pad(lst): return lst + [""] * max(0, n - len(lst))
-
-        pos_list   = _pad(pos_list)
-        dos_list   = _pad(dos_list)
-        mod_list   = _pad(mod_list)
-        units_list = _pad(units_list)
-        rp_list    = _pad(rp_list)
-
-        data["CPT"]                = _format_list(cpts,       "CPT")
-        data["POS"]                = _format_list(pos_list,   "POS")
-        data["Date of Service"]    = _format_list(dos_list,   "DOS")
-        data["Modifier"]           = _format_list(mod_list,   "Modifier")
-        data["Units"]              = _format_list(units_list, "Units")
-        data["Rendering Provider #"] = _format_list(rp_list,  "RP #")
-
-        return data
-
-    except Exception as exc:
-        import traceback
-        print(f"[ERROR] PDF parsing failed → {pdf_path} → {exc}")
-        traceback.print_exc()
-        return None
-
-
-# ===========================================================================
-# Quick smoke-test  (remove / guard with __main__ in production)
-# ===========================================================================
-if __name__ == "__main__":
-    import sys, json
-
-    if len(sys.argv) < 2:
-        print("Usage: python extract_pdf_data_v3.py <path_to_cms1500.pdf>")
-        sys.exit(1)
-
-    result = extract_pdf_data_fast(sys.argv[1])
-    print("\n===== EXTRACTED DATA =====")
-    print(json.dumps(result, indent=2))
@@ -1,31 +0,0 @@
-from google.cloud import documentai_v1 as documentai
-from google.oauth2 import service_account
-
-DOCAI_CREDENTIALS_PATH = r"C:\Potential Project G2\.env\pdf-extraction-492807-41531f078f92.json"
-DOCAI_PROJECT_ID       = "580776411227"
-DOCAI_LOCATION         = "us"
-DOCAI_PROCESSOR_ID     = "894f921d904bc9bd"
-
-def test_connection():
-    try:
-        credentials = service_account.Credentials.from_service_account_file(
-            DOCAI_CREDENTIALS_PATH,
-            scopes=["https://www.googleapis.com/auth/cloud-platform"]
-        )
-        client_options = {"api_endpoint": "us-documentai.googleapis.com"}
-        client = documentai.DocumentProcessorServiceClient(
-            credentials=credentials,
-            client_options=client_options
-        )
-        processor_name = (
-            f"projects/{DOCAI_PROJECT_ID}/locations/{DOCAI_LOCATION}"
-            f"/processors/{DOCAI_PROCESSOR_ID}"
-        )
-        processor = client.get_processor(name=processor_name)
-        print(f"✅ Connection successful!")
-        print(f"   Processor: {processor.display_name}")
-        print(f"   State:     {processor.state.name}")
-    except Exception as e:
-        print(f"❌ Connection failed: {e}")
-
-test_connection()
@@ -1,60 +0,0 @@
-from google.cloud import documentai_v1 as documentai
-from google.oauth2 import service_account
-
-DOCAI_CREDENTIALS_PATH = r"C:\Potential Project G2\.env\pdf-extraction-492807-41531f078f92.json"
-DOCAI_PROJECT_ID       = "1065395041789"
-DOCAI_LOCATION         = "us"
-DOCAI_PROCESSOR_ID     = "2d4c7121ce241b13"
-
-# ← Put path to any CMS-1500 PDF you have
-TEST_PDF_PATH = r"C:\Potential Project G2\Output\04-07-2026\PDF Folder\Dynamic Mobile Rehab (238268)\10882239127.pdf"
-
-def test_pdf():
-    credentials = service_account.Credentials.from_service_account_file(
-        DOCAI_CREDENTIALS_PATH,
-        scopes=["https://www.googleapis.com/auth/cloud-platform"]
-    )
-    client_options = {"api_endpoint": "us-documentai.googleapis.com"}
-    client = documentai.DocumentProcessorServiceClient(
-        credentials=credentials,
-        client_options=client_options
-    )
-
-    with open(TEST_PDF_PATH, "rb") as f:
-        pdf_bytes = f.read()
-
-    processor_name = (
-        f"projects/{DOCAI_PROJECT_ID}/locations/{DOCAI_LOCATION}"
-        f"/processors/{DOCAI_PROCESSOR_ID}"
-    )
-
-    request = documentai.ProcessRequest(
-        name=processor_name,
-        raw_document=documentai.RawDocument(
-            content=pdf_bytes,
-            mime_type="application/pdf"
-        )
-    )
-
-    result = client.process_document(request=request)
-    document = result.document
-
-    print(f"\n✅ PDF processed successfully!")
-    print(f"   Pages: {len(document.pages)}")
-    print(f"\n--- RAW TEXT (first 500 chars) ---")
-    print(document.text[:500])
-    print(f"\n--- FORM FIELDS DETECTED ---")
-    for page in document.pages:
-        for field in page.form_fields:
-            key = "".join(
-                document.text[s.start_index:s.end_index]
-                for s in field.field_name.text_anchor.text_segments
-            ).strip()
-            val = "".join(
-                document.text[s.start_index:s.end_index]
-                for s in field.field_value.text_anchor.text_segments
-            ).strip()
-            if key and val:
-                print(f"   {key:30s} → {val}")
-
-test_pdf()