"""Schémas et règles structurelles communs aux scripts de fiches."""

import re

SECTION_ALIASES = {
    "article": "articles",
    "articles": "articles",
    "grammaire": "grammaire",
    "signe": "signes",
    "signes": "signes",
    "texte": "textes",
    "textes": "textes",
    "vocabulaire": "vocabulaire",
}

VOCABULARY_FIELDS = {
    "nom": ("meaning", "logograms", "gender", "bound", "plural"),
    "adjectif": (
        "meaning",
        "logograms",
        "bound",
        "feminine",
        "masculine_plural",
        "feminine_plural",
        "predicative",
    ),
    "verbe": (
        "meaning",
        "logograms",
        "root",
        "stem",
        "verb_class",
        "vowel_class",
        "preterite",
        "durative",
        "perfect",
        "imperative",
        "participle",
        "verbal_adjective",
    ),
    "pronom": (
        "meaning",
        "logograms",
        "pronoun_type",
        "person",
        "gender",
        "number",
    ),
    "préposition": ("meaning", "logograms", "governs"),
    "adverbe": ("meaning", "logograms", "function"),
    "conjonction": ("meaning", "logograms", "function"),
    "particule": ("meaning", "logograms", "function"),
    "numéral": (
        "meaning",
        "logograms",
        "numeral_type",
        "value",
        "gender",
        "feminine",
    ),
}

SECTION_FIELDS = {
    "articles": {"extra": ("banner", "banner_alt", "banner_credit")},
    "grammaire": {"taxonomies": ("themes",)},
    "signes": {
        "extra": ("sign", "mzl"),
        "taxonomies": ("lectures",),
    },
    "textes": {"taxonomies": ("genres",)},
}

LIST_FIELDS = frozenset({"logograms", "lectures", "themes", "genres"})
URL_TERM_FIELDS = frozenset({"themes", "genres"})

CONTENT_SECTIONS = frozenset(SECTION_FIELDS) | {"vocabulaire"}
UPDATED_LINE_RE = re.compile(r"(?m)^(?:#\s*)?updated\s*=.*?(?=\r?$)")