add a bunch of things for hierarchysearch

anansyTypes/__init__.py

@@ -26,6 +26,19 @@ __all__ = [
     "SearchSymbolsRequest",
     "GetSymbolsResponse",
     "ReplaceFinishedRequest",
+    "SymbolLeaf",
+    "SentenceWord",
+    "WordsPreprocessResponse",
+    "DictionaryMatch",
+    "WordLookup",
+    "LookupRequest",
+    "LookupResponse",
+    "JevQuestion",
+    "JevRequest",
+    "JevOption",
+    "JevAnswer",
+    "JevResponse",
+    "GetLeafSymbolsRequest",
     "UsageStatusResponse",
     "ModelType",
     "PreprocessorType",

anansyTypes/schemas.py

@@ -100,6 +100,71 @@ class ReplaceFinishedRequest(ModifiedBaseModel):
     replacement: Symbol
     language: str
     
+#### Symbol hierarchy (jev translator) ####
+
+class SymbolLeaf(ModifiedBaseModel):
+    """One leaf of the symbol hierarchy. A label with several parts ("bat|club") gives one leaf per part."""
+    model_config = ConfigDict(frozen=True)
+    group_id: str
+    part: int = 0
+
+class SentenceWord(ModifiedBaseModel):
+    """A word, or a phrase kept together ("thank you", "Kari Nordmann"), from a wordlist preprocessor."""
+    text: str
+    lemmas: List[str] = []          # base forms, most likely first
+    name: bool = False              # a person's name: gets a generic person symbol
+    gender: Optional[str] = None    # "fem" or "mask" for a name, if known
+    grammar: bool = False           # a common grammar word ("the", "og"): skipped if the dictionary has no match
+
+class WordsPreprocessResponse(ModifiedBaseModel):
+    words: List[SentenceWord]
+
+class DictionaryMatch(ModifiedBaseModel):
+    leaf: SymbolLeaf
+    kind: Literal["label", "synonym", "related"]
+
+class WordLookup(ModifiedBaseModel):
+    matches: List[DictionaryMatch]  # labels first
+    matched: Optional[str] = None   # the base form that found the matches, if exactly one did
+
+class LookupRequest(ModifiedBaseModel):
+    words: List[SentenceWord]
+
+class LookupResponse(ModifiedBaseModel):
+    words: List[WordLookup]         # one per requested word
+    people: List[SymbolLeaf]        # the generic person symbols offered for names
+
+class JevQuestion(ModifiedBaseModel):
+    """choose: which of `leaves` matches the word. search: which child of `category_id` (None: the top) does."""
+    name: str
+    kind: Literal["choose", "search"]
+    word: str                       # the form asked about
+    is_name: bool = False
+    gender: Optional[str] = None
+    leaves: List[SymbolLeaf] = []
+    category_id: Optional[str] = None
+
+class JevRequest(ModifiedBaseModel):
+    sentence: str
+    questions: List[JevQuestion]
+
+class JevOption(ModifiedBaseModel):
+    """A symbol or a category the model gave probability p."""
+    p: float
+    leaf: Optional[SymbolLeaf] = None
+    category_id: Optional[str] = None
+
+class JevAnswer(ModifiedBaseModel):
+    options: List[JevOption] = []
+    p_none: float = 0.0             # probability that none of the options matches
+
+class JevResponse(ModifiedBaseModel):
+    answers: Dict[str, JevAnswer]   # question name -> answer
+
+class GetLeafSymbolsRequest(ModifiedBaseModel):
+    leaves: List[SymbolLeaf]
+
+
 class UsageStatusResponse(ModifiedBaseModel):
     """Read-only snapshot of a caller's rate-limit window."""
     limit: int