We and our partners use cookies and other tracking technologies to improve your online experience, help prevent fraud, deliver targeted ads, and support other business purposes. By visiting our site, you're agreeing to our Privacy Policy.
def parse_token(s): s = s.strip() parts = s.split() flag = None if parts and parts[-1].lower() in KNOWN_FLAGS: flag = parts.pop(-1).lower() core = "".join(parts) tokens = [] for m in re.finditer(r"[A-Za-z]+|\d+", core): tok = m.group(0) if tok.isalpha(): tokens.append("type":"alpha","raw":tok,"normalized":tok.lower()) else: norm = tok.zfill(3) if len(tok) < 3 else tok tokens.append("type":"num","raw":tok,"normalized":norm) if flag: tokens.append("type":"flag","raw":flag,"normalized":flag) errors = [] # basic validation if not tokens: errors.append("empty input") summary = "has_flag": bool(flag), "flag": flag, "validity": not errors, "errors": errors normalized_string = "-".join(t["normalized"] for t in tokens) return "tokens": tokens, "summary": summary, "normalized_string": normalized_string
KNOWN_FLAGS = "upd","new","rev"