Add core encounter processing pipeline

Filter by game version, parse levels and rate variants across all
generations, aggregate encounters by pokemon+method, and build
parent/child route hierarchy. Also completes encounter method coverage
(73/73) and pokemon form mapping (1180/1181) with manual overrides.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

tools/import-pokedb/import_pokedb/mappings.py

@@ -89,15 +89,42 @@ ENCOUNTER_METHOD_MAP: dict[str, str] = {
     "ambush": "walk",
     # Seaweed / diving
     "diving": "surf",
+    "diving-seaweed": "surf",
     "seaweed": "surf",
     # Raids
     "max-raid": "raid",
+    "max-raid-battle": "raid",
     "dynamax-adventure": "raid",
     "tera-raid": "raid",
+    "tera-raid-battle": "raid",
+    "fixed-tera-encounter": "static",
     # Misc
     "roaming": "roaming",
     "safari-zone": "walk",
     "bug-contest": "walk",
+    "dust-cloud": "walk",
+    "hidden-grotto": "static",
+    "hidden-encounter": "walk",
+    "horde-encounter": "walk",
+    "shaking-trees": "walk",
+    "shaking-ore-deposits": "walk",
+    "island-scan": "static",
+    "mass-outbreak": "swarm",
+    "npc-buy": "gift",
+    "special-encounter": "static",
+    "sea-skim": "surf",
+    "midair": "walk",
+    "mr-backlot": "walk",
+    "hoenn-sound": "walk",
+    "sinnoh-sound": "walk",
+    "curry": "gift",
+    "boxes": "gift",
+    "berry-tree": "walk",
+    "zygarde-cube-assemble": "static",
+    "contact-flock": "walk",
+    "contact-space-time-distortion": "walk",
+    "contact-unown-reasearch-notes": "static",
+    "flying-pokemon-shadow": "walk",
 }
 
 # Prefix-based fallbacks for methods not explicitly listed above.
@@ -107,6 +134,8 @@ _METHOD_PREFIX_MAP: list[tuple[str, str]] = [
     ("fishing-", "fishing"),
     ("headbutt-", "headbutt"),
     ("flying-", "walk"),
+    ("ambush-", "walk"),
+    ("contact-", "walk"),
 ]
 
 
@@ -180,14 +209,119 @@ def build_version_map(
 # Pokemon form mapping
 # ---------------------------------------------------------------------------
 
+
+# PokeDB uses adjectival region forms ("alolan") while PokeAPI/our data uses
+# region names ("alola"). This maps PokeDB suffixes → our suffixes.
+_FORM_SUFFIX_MAP: dict[str, str] = {
+    "alolan": "alola",
+    "galarian": "galar",
+    "hisuian": "hisui",
+    "paldean": "paldea",
+    # Totem forms
+    "alolan-totem": "totem-alola",
+    # Basculin stripes
+    "blue-stripe": "blue-striped",
+    "red-stripe": "red-striped",
+    "white-stripe": "white-striped",
+    # Sea forms
+    "west-sea": "west",
+    "east-sea": "east",
+    # Cloak forms
+    "plant-cloak": "plant",
+    "sandy-cloak": "sandy",
+    "trash-cloak": "trash",
+    # Eiscue
+    "ice-face": "ice",
+    # Misc forms
+    "pompom": "pom-pom",
+    "10p": "10",
+    "50p": "50",
+    "owntempo": "own-tempo",
+    "two": "two-segment",
+    "chest": "chest-form",
+    "ice-rider": "ice",
+    "shadow-rider": "shadow",
+    "apex": "apex-build",
+    "ultimate": "ultimate-mode",
+    "black-activated": "black",
+    "white-activated": "white",
+    "hero": "hero",
+    "sword": "crowned",
+    "shield": "crowned",
+    # Gigantamax
+    "gigantamax": "gmax",
+    # Partner forms
+    "partner": "partner-cap",
+    # Flabébé / Floette / Florges color forms — these don't have form suffixes in our data
+    # since each color is just the base form. Map to base.
+    "blue": "blue",
+    "orange": "orange",
+    "red": "red",
+    "white": "white",
+    "yellow": "yellow",
+    # Gender forms
+    "female": "female",
+    "male": "male",
+    # Furfrou
+    "natural": "natural",
+    # Cherrim
+    "overcast": "overcast",
+    # Sinistea / Polteageist
+    "antique": "antique",
+    "phony": "phony",
+    # Poltchageist / Sinistcha
+    "artisan": "artisan",
+    "counterfeit": "counterfeit",
+    "masterpiece": "masterpiece",
+    "unremarkable": "unremarkable",
+    # Minior cores
+    "blue-core": "blue",
+    "green-core": "green",
+    "indigo-core": "indigo",
+    "orange-core": "orange",
+    "red-core": "red",
+    "violet-core": "violet",
+    "yellow-core": "yellow",
+    # Vivillon
+    "fancy": "fancy",
+    # Squawkabilly
+    # these use same name
+    # Xerneas
+    "neutral": "neutral",
+    # Deerling / Sawsbuck
+    "spring": "spring",
+    "summer": "summer",
+    "autumn": "autumn",
+    "winter": "winter",
+    # Spiky-ears Pichu
+    "spiky-ears": "spiky-eared",
+    # Paldean breeds
+    "paldean-combat-breed": "paldea-combat-breed",
+    "paldean-blaze-breed": "paldea-blaze-breed",
+    "paldean-aqua-breed": "paldea-aqua-breed",
+}
+
+
 def _normalize_slug(identifier: str) -> str:
     """Normalize a PokeDB pokemon_form_identifier to a PokeAPI-style slug.
 
     PokeDB uses "pidgey-default" for base forms — strip the "-default" suffix.
-    Non-default forms like "rattata-alola" are already PokeAPI-style slugs.
+    For alternate forms, translate PokeDB naming conventions to ours.
     """
     if identifier.endswith("-default"):
         return identifier[: -len("-default")]
+
+    # Try suffix-based mapping: split into species + form suffix
+    # e.g. "rattata-alolan" → species="rattata", suffix="alolan"
+    # e.g. "mr-mime-galarian" → need to find the right split point
+    # Strategy: try longest suffix first
+    for pokedb_suffix, our_suffix in sorted(
+        _FORM_SUFFIX_MAP.items(), key=lambda x: -len(x[0])
+    ):
+        if identifier.endswith("-" + pokedb_suffix):
+            species = identifier[: -(len(pokedb_suffix) + 1)]
+            return f"{species}-{our_suffix}"
+
     return identifier
 
 
@@ -234,6 +368,21 @@ def _name_to_form_slug(name: str) -> str | None:
     return None
 
 
+# Manual overrides for PokeDB identifiers that can't be resolved generically.
+# These are cases where our pokemon.json uses non-standard base form names
+# (e.g. "Deoxys Normal" instead of "Deoxys").
+_FORM_OVERRIDES: dict[str, tuple[int, str]] = {
+    "deoxys-default": (386, "Deoxys Normal"),
+    "darmanitan-galarian": (10177, "Darmanitan (Galar Standard)"),
+    "mimikyu-totem": (10144, "Mimikyu (Totem Disguised)"),
+    "squawkabilly-green": (931, "Squawkabilly Green Plumage"),
+    "squawkabilly-blue": (10260, "Squawkabilly (Blue Plumage)"),
+    "squawkabilly-white": (10262, "Squawkabilly (White Plumage)"),
+    "squawkabilly-yellow": (10261, "Squawkabilly (Yellow Plumage)"),
+    "toxtricity-gigantamax": (849, "Toxtricity Amped"),
+}
+
+
 class PokemonMapper:
     """Maps PokeDB pokemon_form_identifier → (pokeapi_id, display_name)."""
 
@@ -277,6 +426,10 @@ class PokemonMapper:
         if not pokemon_form_identifier:
             return None
 
+        # Check manual overrides first
+        if pokemon_form_identifier in _FORM_OVERRIDES:
+            return _FORM_OVERRIDES[pokemon_form_identifier]
+
         slug = _normalize_slug(pokemon_form_identifier)
 
         # Direct slug match
@@ -292,6 +445,19 @@ class PokemonMapper:
             self._slug_to_info[slug] = (pokemon_id, name)
             return (pokemon_id, name)
 
+        # Fallback: strip form suffix to find base species.
+        # Many cosmetic forms (colors, genders, seasons) don't have separate
+        # entries in our pokemon.json — they use the base species entry.
+        # Try progressively shorter slugs: "flabebe-blue" → "flabebe"
+        parts = slug.split("-")
+        for i in range(len(parts) - 1, 0, -1):
+            base = "-".join(parts[:i])
+            if base in self._slug_to_info:
+                result = self._slug_to_info[base]
+                # Cache for future lookups
+                self._slug_to_info[slug] = result
+                return result
+
         # Track unmapped
         if pokemon_form_identifier not in self._unmapped:
             self._unmapped.add(pokemon_form_identifier)