#!/usr/bin/env python3 """ thorlabs_to_yml.py generated by claude May 10 2026 Scans a folder for Thorlabs Beam M² .txt files and writes a YAML file containing 10 fields per file: From filename parsing (format: ZM4_V__ZM5_V_.txt): ZM4 V PZT – integer voltage after "ZM4_" ZM4 V sg – signal value after first "V_" (n→-, p→.) ZM5 V PZT – integer voltage after "_ZM5_" ZM5 V sg – signal value after second "V_" (n→-, p→.) From "Original Waist Measurement Results" section of each file: M2 x – M² X' M2 y – M² Y' Rayleigh Length X Rayleigh Length Y Beam Waist Position X Beam Waist Position Y Usage: python thorlabs_to_yml.py [output.yml] """ import os import sys import re from datetime import datetime, timezone # --------------------------------------------------------------------------- # Filename parsing # --------------------------------------------------------------------------- def parse_sg_value(token: str) -> str: """ Convert a signal-value token like '6p2', 'np4', '10', 'n3p5' into a numeric string: - Leading 'n' → '-' - 'p' → '.' Examples: '6p2' → '6.2' 'np4' → '-0.4' (n with nothing before p → -0.) 'n4' → '-4' '10' → '10' 'n3p5' → '-3.5' """ s = token negative = s.startswith('n') if negative: s = s[1:] # strip leading 'n' s = s.replace('p', '.') if negative: # if there was nothing between 'n' and 'p', s starts with '.' s = '-' + s if s else '-0' return float(s) def parse_filename(stem: str) -> dict: """ Parse a filename stem of the form: ZM4_V__ZM5_V_ Returns a dict with the four fields, or empty strings on failure. """ pattern = re.compile( r'^ZM4_(?P\d+)V_(?P[A-Za-z0-9]+)_ZM5_(?P\d+)V_(?P[A-Za-z0-9]+)$', re.IGNORECASE ) m = pattern.match(stem) if not m: return { 'ZM4 V PZT': '', 'ZM4 V sg': '', 'ZM5 V PZT': '', 'ZM5 V sg': '', } return { 'ZM4 V PZT': int(m.group('pzt4')), 'ZM4 V sg': parse_sg_value(m.group('sg4')), 'ZM5 V PZT': int(m.group('pzt5')), 'ZM5 V sg': parse_sg_value(m.group('sg5')), } # --------------------------------------------------------------------------- # File content parsing # --------------------------------------------------------------------------- # Map the exact label text in the file to our YAML key names. WAIST_FIELDS = { "M\u00b2x'": 'M2 x', # M²x' "M\u00b2y'": 'M2 y', # M²y' "Rayleigh Length X'": 'Rayleigh Length X', "Rayleigh Length Y'": 'Rayleigh Length Y', "Beam Waist Position X'": 'Beam Waist Position X', "Beam Waist Position Y'": 'Beam Waist Position Y', } def parse_waist_results(content: str) -> dict: """ Extract the 6 values from the 'Original Waist Measurement Results' section. The file structure around this section is: * * * * * * * * * * Original Waist Measurement Results * * * * * * * * * * ← closing stars on the SAME block Parameter;Unit;Result; M²x'; ;1.44; ... (blank line or next * * * block starts a new section) So we locate the heading line, skip the very next '* * *' line, then collect data lines until we hit another '* * *' line or end of file. """ results = {v: '' for v in WAIST_FIELDS.values()} lines = content.splitlines() in_section = False skip_next_stars = False for line in lines: stripped = line.strip() if not in_section: if re.search(r'Original Waist Measurement Results', stripped, re.IGNORECASE): in_section = True skip_next_stars = True # the very next * * * line closes the heading continue # We are inside the section if stripped.startswith('* * *'): if skip_next_stars: skip_next_stars = False # consume the closing header stars continue else: break # a new section starts — stop skip_next_stars = False # clear flag once we've passed the stars line parts = [p.strip() for p in stripped.split(';')] if len(parts) < 3: continue label = parts[0] value = parts[2] if label in WAIST_FIELDS: try: results[WAIST_FIELDS[label]] = float(value) except ValueError: results[WAIST_FIELDS[label]] = value return results def analyze_file(filepath: str, stem: str) -> dict: """Combine filename fields and waist-results fields into one ordered dict.""" with open(filepath, 'r', encoding='latin-1') as f: content = f.read() entry = {} entry.update(parse_filename(stem)) entry.update(parse_waist_results(content)) return entry # --------------------------------------------------------------------------- # YAML writer (stdlib only) # --------------------------------------------------------------------------- def yaml_scalar(v) -> str: """Format a scalar value for YAML output.""" if isinstance(v, (int, float)): return str(v) s = str(v) if not s: return "''" # Quote if the string contains YAML-special characters or looks numeric-ish needs_quote = any(c in s for c in (':', '#', '[', ']', '{', '}', ',', '&', '*', '?', '|', '-', '<', '>', '=', '!', '%', '@', '`', "'", '"', '\n')) if needs_quote: escaped = s.replace('"', '\\"') return f'"{escaped}"' return s def write_yaml(data: dict, output_path: str) -> None: with open(output_path, 'w', encoding='utf-8') as f: f.write('# Generated by thorlabs_to_yml.py\n') f.write(f'# Created: {datetime.now(tz=timezone.utc).isoformat()}\n\n') f.write('files:\n') for filename, fields in data.items(): f.write(f' {filename}:\n') for key, value in fields.items(): f.write(f' {key}: {yaml_scalar(value)}\n') f.write('\n') # --------------------------------------------------------------------------- # Main # --------------------------------------------------------------------------- def main(): if len(sys.argv) < 2: print(__doc__) sys.exit(1) folder = sys.argv[1] output_file = sys.argv[2] if len(sys.argv) >= 3 else 'output.yml' if not os.path.isdir(folder): print(f"Error: '{folder}' is not a valid directory.") sys.exit(1) txt_files = sorted( f for f in os.listdir(folder) if f.lower().endswith('.txt') ) if not txt_files: print(f"No .txt files found in '{folder}'.") sys.exit(0) print(f"Found {len(txt_files)} .txt file(s). Parsing...") results = {} for filename in txt_files: filepath = os.path.join(folder, filename) stem = os.path.splitext(filename)[0] print(f" → {filename}") results[filename] = analyze_file(filepath, stem) write_yaml(results, output_file) print(f"\nDone! YAML written to: {output_file}") if __name__ == '__main__': main()