#!/usr/bin/env python3 """ Recovery script to parse XLSX and DOCX files that segfaulted on Windows. Runs via WSL2 Ubuntu where libraries work correctly. Outputs JSON results that the main script can merge. """ import os import re import sys import json from pathlib import Path from collections import defaultdict import openpyxl from docx import Document as DocxDocument BASE = "/mnt/c/Users/Squir/Desktop/HAITI/DUMP" # Files that failed on Windows (exit code 3221225477) FAILED_FILES = [ # XLSX files (Douane) "DOUANE-GOUV/downloads/Liste-de-localisation-des-marchandises.xlsx", "DOUANE-GOUV/downloads/Liste-des-candidats-retenus-no_phone.xlsx", "DOUANE-GOUV/downloads/Liste-des-candidats-retenus.xlsx", "DOUANE-GOUV/downloads/Liste-des-conteneurs.xlsx", "DOUANE-GOUV/downloads/Liste-des-emballages-sydonia.xlsx", "DOUANE-GOUV/downloads/Liste-des-ports-internationaux-.xlsx", # DOCX files (DINEPA) "DINEPA-GOUV/downloads/RPF-EPARD-II-Fevrier-2023.docx", # DOCX files (MICT root) "MICT-GOUV/DG-Avis-de-recrutement-internes.docx", "MICT-GOUV/DOSSIER-PREQUALIFICATION-INTERIEUR.docx", "MICT-GOUV/Publication-Recrutement-avis.docx", # DOCX files (MICT documents) "MICT-GOUV/documents/Ouverture-Saison-Cyclonique-2020-Ministre-Interieur.docx", "MICT-GOUV/documents/PGES_Ravines-Belle-hotesse-et-Zetrier-MDUR-Revis-Dec-2018.docx", "MICT-GOUV/documents/Rapport_final_du_CPR_du_PGRAC_-_10____janvier_2019.docx", "MICT-GOUV/documents/REVISED-PAR-Ravines-Belle-Hotesse-et-Zetriye-Dec-13-FINAL-Approved.docx", # DOCX files (MICT uploads - duplicates of documents/) "MICT-GOUV/uploads/2019/01/Rapport_final_du_CPR_du_PGRAC_-_10____janvier_2019.docx", "MICT-GOUV/uploads/2019/02/PGES_Ravines-Belle-hotesse-et-Zetrier-MDUR-Revis-Dec-2018.docx", "MICT-GOUV/uploads/2019/02/REVISED-PAR-Ravines-Belle-Hotesse-et-Zetriye-Dec-13-FINAL-Approved.docx", "MICT-GOUV/uploads/2020/06/Ouverture-Saison-Cyclonique-2020-Ministre-Interieur.docx", "MICT-GOUV/uploads/2025/01/DG-Avis-de-recrutement-internes.docx", "MICT-GOUV/uploads/2025/01/Publication-Recrutement-avis.docx", "MICT-GOUV/uploads/2025/09/DOSSIER-PREQUALIFICATION-INTERIEUR.docx", ] # Regex patterns PATTERNS = { "email": (r'[a-zA-Z0-9._%+\-]+@[a-zA-Z0-9.\-]+\.[a-zA-Z]{2,}', 0), "phone_haiti": (r'(?:\+509|509)[\s.\-]?\d{4}[\s.\-]?\d{4}', 0), "phone_general": (r'(?:\+\d{1,3}[\s.\-])?\(?\d{2,4}\)?[\s.\-]?\d{3,4}[\s.\-]?\d{3,4}', 0), "nif_tax": (r'\d{3}-\d{3}-\d{3}-\d{1}', 0), "cin_id": (r'(?:CIN|NIF|NIN)[:\s]*[\d\-]+', 0), "address": (r'(?:Rue|Avenue|Route|Boulevard|Blvd|Impasse|Ruelle)\s+[A-Z\u00C0-\u00DC][a-z\u00E0-\u00FC\s,.\-]+(?:Port-au-Prince|P[eé]tion-Ville|Delmas|Carrefour|Cap-Ha[iï]tien)?', 0), "named_person": (r'(?:Monsieur|Madame|M\.|Mme|Dr\.?|Ing\.?|Prof\.?)\s+[A-Z\u00C0-\u00DC][a-z\u00E0-\u00FC]+\s+[A-Z\u00C0-\u00DC][A-Z\u00C0-\u00DCa-z\u00E0-\u00FC]+', 0), "url": (r'https?://[^\s<>"\']+', 0), "credential": (r'(?:password|passwd|pwd|mot de passe|secret|token|api.?key)[:\s=]+\S+', re.IGNORECASE), "db_string": (r'(?:mysql|postgres|mongodb|redis)://[^\s<>"\']+', re.IGNORECASE), "ip_address": (r'\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b', 0), } EMAIL_JUNK = re.compile(r'(?:\.png|\.jpg|\.gif|\.svg|\.css|\.js|\.woff|\.ttf|\.pdf|\.docx|\.xlsx|\.php|\.html)$', re.IGNORECASE) PHONE_JUNK = re.compile(r'^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$') all_findings = defaultdict(list) all_emails = set() all_phones = set() errors = [] raw_data = {} # Store raw extracted text for interesting files def scan_text(text, source_file, location): if not text or not text.strip(): return for name, (pattern_str, flags) in PATTERNS.items(): pat = re.compile(pattern_str, flags) for m in pat.finditer(text): val = m.group(0).strip() if name == "email" and (EMAIL_JUNK.search(val) or len(val) < 6): continue if name in ("phone_haiti", "phone_general") and (PHONE_JUNK.match(val) or len(val) < 7): continue all_findings[name].append((source_file, location, val)) if name == "email": all_emails.add(val) if name in ("phone_haiti", "phone_general"): all_phones.add(val) def process_xlsx(filepath, relname): print(f" [XLSX] {relname}", flush=True) try: wb = openpyxl.load_workbook(filepath, read_only=True, data_only=True) for sheet_name in wb.sheetnames: ws = wb[sheet_name] row_count = 0 sample_rows = [] for row_idx, row in enumerate(ws.iter_rows(values_only=True), 1): row_count += 1 if row: row_text = " | ".join(str(c) if c is not None else "" for c in row) scan_text(row_text, relname, f"sheet '{sheet_name}' row {row_idx}") if row_idx <= 5: sample_rows.append(row_text) print(f" Sheet '{sheet_name}': {row_count} rows") if sample_rows: raw_data[f"{relname} - {sheet_name}"] = sample_rows wb.close() return True except Exception as e: errors.append((relname, str(e))) print(f" ERROR: {e}") return False def process_docx(filepath, relname): print(f" [DOCX] {relname}", flush=True) try: doc = DocxDocument(filepath) parts = [] for para in doc.paragraphs: if para.text.strip(): parts.append(para.text) for table in doc.tables: for row in table.rows: row_text = " | ".join(cell.text for cell in row.cells) parts.append(row_text) if parts: combined = "\n".join(parts) scan_text(combined, relname, "full document") # Store first 10 lines as sample raw_data[relname] = parts[:10] print(f" Extracted {len(parts)} text blocks") return True except Exception as e: errors.append((relname, str(e))) print(f" ERROR: {e}") return False def main(): print("=" * 60) print("RECOVERY PARSER — Failed XLSX/DOCX via WSL2") print("=" * 60) processed = 0 for relname in FAILED_FILES: filepath = os.path.join(BASE, relname) if not os.path.exists(filepath): print(f" [SKIP] {relname} — file not found") continue ext = os.path.splitext(filepath)[1].lower() if ext == ".xlsx": if process_xlsx(filepath, relname): processed += 1 elif ext == ".docx": if process_docx(filepath, relname): processed += 1 # Output JSON results for merging output = { "processed": processed, "errors": errors, "findings": {k: v for k, v in all_findings.items()}, "emails": sorted(all_emails), "phones": sorted(all_phones), "raw_data": raw_data, } output_path = os.path.join(BASE, "recovery_results.json") with open(output_path, "w", encoding="utf-8") as f: json.dump(output, f, indent=2, ensure_ascii=False) print(f"\n{'='*60}") print(f"RECOVERY RESULTS") print(f"{'='*60}") print(f"Files processed: {processed}") print(f"Errors: {len(errors)}") for name in sorted(all_findings.keys()): unique = set(v[2] for v in all_findings[name]) print(f" {name:35s} {len(all_findings[name]):5d} matches ({len(unique)} unique)") print(f"\n Emails: {len(all_emails)}") print(f" Phones: {len(all_phones)}") # Also print raw sample data for key files print(f"\n{'='*60}") print("SAMPLE DATA FROM KEY FILES") print(f"{'='*60}") for fname, rows in raw_data.items(): print(f"\n--- {fname} ---") for row in rows: print(f" {row[:200]}") print(f"\nResults saved to: {output_path}") if __name__ == "__main__": main()