"""Titel-normalisatie om hoofdstukken van één reeks te groeperen.""" from __future__ import annotations import re import unicodedata # Tags die auteurs vaak in de titel zetten en die niet tot de reeksnaam horen. _TAG = re.compile( r"\[\s*(?:oc|pi|hfy|ff|fic|meta|chapter|ch|part|pt|oneshot|one[-\s]?shot)" r"(?:[^\]]*)\]", re.IGNORECASE, ) _PREFIX_TAG = re.compile(r"^\s*(?:oc|pi|hfy|ff)\s*[:|\-–—]\s*", re.IGNORECASE) # "Part 12", "Chapter 3/40", "Ch. 7", "Ep 2", "#14" _PART = re.compile( r""" (?:^|[\s,;:\-–—|\[\(]) (?: (?:part|chapter|chapters|ch|pt|episode|ep|update|book|vol|volume)\.? \s* (?:[0-9]+(?:\s*[./]\s*[0-9]+)?) | \#\s*[0-9]+ ) [\]\)]? """, re.IGNORECASE | re.VERBOSE, ) # "Title (194/?)", "Title (194/200)", "Title (194)" _PAREN_NUM = re.compile( r"[\s:\-–—|]*\(\s*[0-9]{1,4}\s*(?:/\s*(?:[0-9]{1,4}|\?)\s*)?\)", re.IGNORECASE, ) # "194/?" of "194/200" zonder haakjes _SLASH_NUM = re.compile(r"[\s:\-–—|]*[0-9]{1,4}\s*/\s*(?:[0-9]{1,4}|\?)\s*$") # "Chapter twenty-two", "Part IV" (Romeins tot 40 is overkill; we doen 1-39 en i-xxxix) _WORD_NUM = ( r"(?:twenty[-\s](?:first|second|third|fourth|fifth|sixth|seventh|eighth|ninth|one|two|three|four|five|six|seven|eight|nine)|" r"thirty[-\s](?:first|second|third|fourth|fifth|sixth|seventh|eighth|ninth|one|two|three|four|five|six|seven|eight|nine)|" r"eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen|eighteen|nineteen|" r"twenty|thirty|one|two|three|four|five|six|seven|eight|nine|ten|" r"xxxix|xxxviii|xxxvii|xxxvi|xxxv|xxxiv|xxxiii|xxxii|xxxi|xxx|" r"xxix|xxviii|xxvii|xxvi|xxv|xxiv|xxiii|xxii|xxi|xx|" r"xix|xviii|xvii|xvi|xv|xiv|xiii|xii|xi|x|ix|viii|vii|vi|v|iv|iii|ii|i)" ) _PART_WORD = re.compile( rf"(?:^|[\s,;:\-–—|\[\(])(?:part|chapter|ch|pt|episode|ep)\.?\s*{_WORD_NUM}\b[\]\)]?", re.IGNORECASE, ) # Afsluitend kaal nummer ("Title - 12", "Title 12") ná andere opschoning. _TRAILING_NUM = re.compile(r"[\s:\-–—|]+(?:[0-9]{1,4})(?:\s*[./]\s*[0-9]{1,4})?\s*$") # Scheidingsteken plus een kort suffix ("Title - Puppeteer") laten we staan: # dat kan een ondertitel zijn. Alleen nummer-achtige suffixes gaan eraf. _SPACE = re.compile(r"\s+") _PUNCT = re.compile(r"[\"“”‘’`]+") def strip_diacritics(text: str) -> str: nfkd = unicodedata.normalize("NFKD", text) return "".join(ch for ch in nfkd if not unicodedata.combining(ch)) def normalize_title(title: str) -> str: """Geef een groepsleutel terug: lowercase, zonder part-nummers en tags.""" if not title: return "" text = strip_diacritics(title) text = _TAG.sub(" ", text) text = _PREFIX_TAG.sub(" ", text) text = _PART.sub(" ", text) text = _PAREN_NUM.sub(" ", text) text = _PART_WORD.sub(" ", text) text = _SLASH_NUM.sub(" ", text) text = _PUNCT.sub("", text) text = text.replace("—", "-").replace("–", "-") text = _TRAILING_NUM.sub("", text) text = re.sub(r"[\s:\-_|/]+$", "", text) text = re.sub(r"^[\s:\-_|/]+", "", text) text = _SPACE.sub(" ", text).strip().lower() return text def display_series_title(titles: list[str]) -> str: """Kies een leesbare reeksnaam uit de hoofdstuktitels.""" if not titles: return "Untitled" # De genormaliseerde vorm van de eerste titel, netjes gekapitaliseerd, # tenzij die leeg is; dan de ruwe eerste titel zonder tags. key = normalize_title(titles[0]) if key: return key.title() cleaned = _TAG.sub("", titles[0]).strip() return cleaned or titles[0] def slug(text: str, max_len: int = 48) -> str: text = normalize_title(text) or "untitled" text = re.sub(r"[^a-z0-9]+", "-", text).strip("-") return text[:max_len].strip("-") or "untitled" # Flares die (bijna) altijd verhalen zijn. STORY_FLAIRS = { "oc-series", "oc-oneshot", "oc-firstofseries", "oc", "pi/ff-series", "pi/ff-oneshot", "pi/ff-firstofseries", "pi-series", "pi-oneshot", "pi", "fanfic-series", "fanfic-oneshot", } # Flares die we overslaan (geen verhaal). SKIP_FLAIRS = { "meta", "mod", "media", "art", "video", "misc", } def is_story_post(flair: str | None, is_self: bool, title: str = "") -> bool: if not is_self: return False key = (flair or "").strip().lower().replace(" ", "") if key in SKIP_FLAIRS: return False if key in STORY_FLAIRS: return True # Oudere posts zonder het huidige flairsysteem: wel tekst, geen meta-achtige titel. lowered = title.lower() if lowered.startswith("[meta]") or lowered.startswith("[mod]"): return False # Zonder flair of met een onbekende flair nemen we self-posts mee, # behalve als de titel duidelijk geen verhaal is. if key in {"", "none"}: return True return True def is_oneshot(flair: str | None, chapter_count: int) -> bool: key = (flair or "").strip().lower().replace(" ", "") if "oneshot" in key or "one-shot" in key: return True return chapter_count <= 1 def is_series_start(flair: str | None) -> bool: key = (flair or "").strip().lower().replace(" ", "") return "firstofseries" in key