import os import re import csv import hashlib import tkinter as tk from pathlib import Path # ============================================================ # GUI # ============================================================ def select_folder(): return input("Enter folder path: ").strip().strip("'\"") # ============================================================ # Helper Functions # ============================================================ def normalize_nc_content(text): output = [] for line in text.splitlines(): line = line.upper() # Remove comments line = re.sub(r"\(.*?\)", "", line) line = re.sub(r";.*", "", line) # Remove tool numbers line = re.sub(r"\bT\d+\b", "", line) # Remove spindle speeds line = re.sub(r"\bS[-+]?\d*\.?\d+\b", "", line) line = line.strip() if line: output.append(line) return "\n".join(output) def calculate_file_hash(file_path): sha = hashlib.sha256() with open(file_path, "rb") as f: while True: chunk = f.read(8192) if not chunk: break sha.update(chunk) return sha.hexdigest() # ============================================================ # Geometry Comparison # ============================================================ AXIS_PATTERN = re.compile(r"([XYZIJKR])([-+]?\d*\.?\d+)") COMMAND_PATTERN = re.compile(r"\b(G\d+|M\d+)\b") def extract_toolpath(file_path): motions = [] with open(file_path, "r", encoding="utf-8", errors="ignore") as f: for raw_line in f: line = normalize_nc_content(raw_line) if not line: continue commands = COMMAND_PATTERN.findall(line) axes = { axis: float(value) for axis, value in AXIS_PATTERN.findall(line) } if commands or axes: motions.append({ "commands": tuple(commands), "axes": axes }) return motions def compare_program_structure(file1, file2, tolerance=0.005): path1 = extract_toolpath(file1) path2 = extract_toolpath(file2) if len(path1) != len(path2): return False, None max_diff = 0 for move1, move2 in zip(path1, path2): if move1["commands"] != move2["commands"]: return False, None axes = set(move1["axes"]) | set(move2["axes"]) for axis in axes: if axis not in move1["axes"]: return False, None if axis not in move2["axes"]: return False, None diff = abs( move1["axes"][axis] - move2["axes"][axis] ) max_diff = max(max_diff, diff) if diff > tolerance: return False, max_diff return True, max_diff # ============================================================ # Extension Normalization # ============================================================ def normalize_extensions(root_folder): root_path = Path(root_folder) if not root_path.exists(): raise FileNotFoundError(root_folder) for file in root_path.rglob("*"): if not file.is_file(): continue suffix = file.suffix.lower() if suffix == "": new_file = file.with_name( file.name + ".txt" ) elif suffix == ".nc": new_file = file.with_suffix(".txt") elif suffix == ".txt": if file.suffix == ".txt": continue new_file = file.with_suffix(".txt") else: continue try: file.rename(new_file) except Exception as e: print(f"Failed: {file}") print(e) print("Extension normalization complete.") # ============================================================ # Program Splitting # ============================================================ def split_file_by_key(input_file, output_dir): os.makedirs(output_dir, exist_ok=True) current_output = None with open(input_file, "r", encoding="utf-8", errors="ignore") as infile: for line in infile: if line.startswith("O"): if current_output: current_output.write("%\n") current_output.close() filename = line[:6].strip() output_path = os.path.join(output_dir, f"{filename}.txt") current_output = open(output_path, "w", encoding="utf-8") current_output.write("%\n") if current_output: current_output.write(line) if current_output: current_output.write("%\n") current_output.close() print(f"Finished: {input_file}") # ============================================================ # Exact Duplicate Removal # ============================================================ def remove_exact_duplicates(root_dir): known_hashes = {} deleted = [] for file in Path(root_dir).rglob("*.txt"): file_hash = calculate_file_hash(file) if file_hash in known_hashes: print(f"Removing exact duplicate: {file}") file.unlink() deleted.append(file) else: known_hashes[file_hash] = file print( f"Removed {len(deleted)} exact duplicates." ) # ============================================================ # Geometry Duplicate Removal # ============================================================ def remove_geometry_duplicates(root_dir, tolerance=0.005): files = list(Path(root_dir).rglob("*.txt")) removed = set() for i in range(len(files)): if files[i] in removed: continue for j in range(i + 1, len(files)): if files[j] in removed: continue duplicate, max_diff = compare_program_structure(files[i], files[j], tolerance) if duplicate: print( f"Removing geometric duplicate:\n" f" Keep: {files[i].name}\n" f" Delete: {files[j].name}\n" f" Max Delta: {max_diff:.5f}" ) files[j].unlink() removed.add(files[j]) print( f"Removed {len(removed)} geometry duplicates." ) # ============================================================ # Similarity Report # ============================================================ def generate_similarity_report( root_dir, tolerance=0.005, output_csv="similarity_report.csv" ): files = list(Path(root_dir).rglob("*.txt")) with open(output_csv, "w", newline="", encoding="utf-8") as csvfile: writer = csv.writer(csvfile) writer.writerow([ "File1", "File2", "Duplicate", "MaxCoordinateDelta" ]) for i in range(len(files)): for j in range(i + 1, len(files)): duplicate, delta = compare_program_structure(files[i], files[j], tolerance) writer.writerow([ files[i].name, files[j].name, duplicate, delta ]) print( f"Similarity report written to {output_csv}" ) # ============================================================ # Main # ============================================================ if __name__ == "__main__": input_dir = select_folder() if not os.path.isdir(input_dir): print("Invalid folder.") raise SystemExit(1) normalize_extensions(input_dir) master_output_dir = os.path.join(input_dir, "Split_Output") os.makedirs(master_output_dir, exist_ok=True) for root, dirs, files in os.walk(input_dir): if os.path.abspath(root).startswith(os.path.abspath(master_output_dir)): continue for filename in files: if not filename.lower().endswith(".pgm"): continue input_file = os.path.join(root, filename) program_output_dir = os.path.join(master_output_dir, os.path.splitext(filename)[0]) split_file_by_key(input_file, program_output_dir) remove_exact_duplicates(master_output_dir) remove_geometry_duplicates(master_output_dir, tolerance=0.005) generate_similarity_report(master_output_dir, tolerance=0.005) print("All files processed.")