glitchlings 0.4.1__cp312-cp312-win_amd64.whl → 0.4.3__cp312-cp312-win_amd64.whl

glitchlings/lexicon/graph.py

@@ -1,290 +0,0 @@
-"""Graph-based lexicon backed by ConceptNet/Numberbatch embeddings."""
-
-from __future__ import annotations
-
-import re
-from pathlib import Path
-from typing import Iterable, Mapping, MutableMapping, Sequence
-
-from . import LexiconBackend
-from ._cache import CacheSnapshot, load_cache as _load_cache_file, write_cache as _write_cache_file
-from .vector import VectorLexicon
-
-
-_CONCEPT_RE = re.compile(r"^/c/(?P<lang>[a-z]{2})/(?P<term>[^/]+)")
-_PUNCTUATION_RE = re.compile(r"[^\w\s-]+", re.UNICODE)
-
-
-def _lemmatize_token(token: str) -> str:
-    """Return a lightweight lemma for ``token`` using heuristic rules."""
-
-    irregular = {
-        "children": "child",
-        "mice": "mouse",
-        "geese": "goose",
-        "feet": "foot",
-        "teeth": "tooth",
-        "men": "man",
-        "women": "woman",
-        "better": "good",
-        "worse": "bad",
-    }
-    lowered = token.lower()
-    if lowered in irregular:
-        return irregular[lowered]
-
-    if lowered.endswith("ies") and len(lowered) > 3:
-        return lowered[:-3] + "y"
-    if lowered.endswith("ves") and len(lowered) > 3:
-        return lowered[:-3] + "f"
-    if lowered.endswith("men") and len(lowered) > 3:
-        return lowered[:-3] + "man"
-    if lowered.endswith("ses") and len(lowered) > 3:
-        return lowered[:-2]
-    if lowered.endswith("es") and len(lowered) > 3:
-        return lowered[:-2]
-    if lowered.endswith("s") and len(lowered) > 2 and not lowered.endswith("ss"):
-        return lowered[:-1]
-    if lowered.endswith("ing") and len(lowered) > 4:
-        stem = lowered[:-3]
-        if len(stem) > 2 and stem[-1] == stem[-2]:
-            stem = stem[:-1]
-        return stem
-    if lowered.endswith("ed") and len(lowered) > 3:
-        stem = lowered[:-2]
-        if len(stem) > 2 and stem[-1] == stem[-2]:
-            stem = stem[:-1]
-        return stem
-    return lowered
-
-
-def _normalize_phrase(phrase: str) -> str:
-    """Normalise ``phrase`` for ConceptNet lookups."""
-
-    stripped = _PUNCTUATION_RE.sub(" ", phrase.lower())
-    tokens = [token for token in stripped.split() if token]
-    if not tokens:
-        return ""
-    lemmatised = [_lemmatize_token(token) for token in tokens]
-    return " ".join(lemmatised)
-
-
-def _concept_terms(normalized: str) -> list[str]:
-    """Return ConceptNet term variants for ``normalized``."""
-
-    collapsed = normalized.replace(" ", "_")
-    if not collapsed:
-        return []
-    variants = {collapsed}
-    variants.add(collapsed.replace("_", "-"))
-    variants.add(collapsed.replace("-", "_"))
-    return list(variants)
-
-
-def _surface_from_concept(concept: str) -> str | None:
-    """Return a human-readable surface form for ``concept``."""
-
-    match = _CONCEPT_RE.match(concept)
-    if match is None:
-        return None
-    term = match.group("term")
-    surface = term.replace("_", " ")
-    surface = surface.replace("-", " ")
-    return " ".join(surface.split())
-
-
-def _language_from_concept(concept: str) -> str | None:
-    match = _CONCEPT_RE.match(concept)
-    if match is None:
-        return None
-    return match.group("lang")
-
-
-def _load_numberbatch(path: Path, *, languages: set[str]) -> Mapping[str, list[float]]:
-    """Load ConceptNet Numberbatch embeddings from ``path``."""
-
-    if not path.exists():
-        return {}
-
-    if path.suffix == ".gz":
-        import gzip
-
-        handle = gzip.open(path, "rt", encoding="utf8")
-    else:
-        handle = path.open("r", encoding="utf8")
-
-    with handle as stream:
-        header = stream.readline()
-        try:
-            parts = header.strip().split()
-            if len(parts) >= 2:
-                int(parts[0])
-                int(parts[1])
-        except ValueError:
-            stream.seek(0)
-
-        embeddings: dict[str, list[float]] = {}
-        for line in stream:
-            tokens = line.strip().split()
-            if len(tokens) <= 2:
-                continue
-            concept = tokens[0]
-            lang = _language_from_concept(concept)
-            if lang is None or lang not in languages:
-                continue
-            try:
-                vector = [float(value) for value in tokens[1:]]
-            except ValueError:
-                continue
-            embeddings[concept] = vector
-    return embeddings
-
-
-class GraphLexicon(LexiconBackend):
-    """Lexicon backed by ConceptNet/Numberbatch embeddings."""
-
-    def __init__(
-        self,
-        *,
-        source: Mapping[str, Sequence[float]] | str | Path | None = None,
-        cache: Mapping[str, Sequence[str]] | None = None,
-        cache_path: str | Path | None = None,
-        languages: Iterable[str] = ("en",),
-        max_neighbors: int = 50,
-        min_similarity: float = 0.0,
-        seed: int | None = None,
-    ) -> None:
-        super().__init__(seed=seed)
-        self._languages = {language.lower() for language in languages}
-        if not self._languages:
-            self._languages = {"en"}
-        self._max_neighbors = max(1, max_neighbors)
-        self._min_similarity = min_similarity
-        self._cache: MutableMapping[str, list[str]] = {}
-        self._cache_path: Path | None = Path(cache_path) if cache_path is not None else None
-        self._cache_checksum: str | None = None
-        if self._cache_path is not None:
-            snapshot = _load_cache_file(self._cache_path)
-            self._cache.update(snapshot.entries)
-            self._cache_checksum = snapshot.checksum
-        if cache is not None:
-            for key, values in cache.items():
-                self._cache[str(key)] = [str(value) for value in values]
-        self._cache_dirty = False
-
-        prepared_source = self._prepare_source(source)
-        self._backend = VectorLexicon(
-            source=prepared_source if prepared_source else None,
-            max_neighbors=self._max_neighbors,
-            min_similarity=self._min_similarity,
-            case_sensitive=True,
-            seed=seed,
-        )
-
-    def _prepare_source(
-        self, source: Mapping[str, Sequence[float]] | str | Path | None
-    ) -> Mapping[str, Sequence[float]]:
-        if source is None:
-            return {}
-        if isinstance(source, Mapping):
-            prepared: dict[str, list[float]] = {}
-            for key, vector in source.items():
-                lang = _language_from_concept(key)
-                if lang is None or lang not in self._languages:
-                    continue
-                prepared[key] = [float(value) for value in vector]
-            return prepared
-        path = Path(source)
-        embeddings = _load_numberbatch(path, languages=self._languages)
-        return embeddings
-
-    def reseed(self, seed: int | None) -> None:
-        super().reseed(seed)
-        self._backend.reseed(seed)
-
-    def _concept_candidates(self, normalized: str) -> list[str]:
-        terms = _concept_terms(normalized)
-        concepts = []
-        for language in sorted(self._languages):
-            for term in terms:
-                concepts.append(f"/c/{language}/{term}")
-        return concepts
-
-    def _collect_synonyms(self, normalized: str) -> list[str]:
-        candidates: list[str] = []
-        seen: set[str] = set()
-        for concept in self._concept_candidates(normalized):
-            neighbors = self._backend.precompute(concept, limit=self._max_neighbors)
-            for neighbor in neighbors:
-                lang = _language_from_concept(neighbor)
-                if lang is None or lang not in self._languages:
-                    continue
-                surface = _surface_from_concept(neighbor)
-                if surface is None:
-                    continue
-                surface_norm = _normalize_phrase(surface)
-                if not surface_norm or surface_norm == normalized:
-                    continue
-                if surface_norm in seen:
-                    continue
-                seen.add(surface_norm)
-                candidates.append(surface)
-        return candidates
-
-    def _ensure_cached(self, normalized: str) -> list[str]:
-        if normalized in self._cache:
-            return self._cache[normalized]
-        synonyms = self._collect_synonyms(normalized)
-        self._cache[normalized] = synonyms
-        if self._cache_path is not None:
-            self._cache_dirty = True
-        return synonyms
-
-    def get_synonyms(
-        self, word: str, pos: str | None = None, n: int = 5
-    ) -> list[str]:
-        normalized = _normalize_phrase(word)
-        if not normalized:
-            return []
-        synonyms = self._ensure_cached(normalized)
-        return self._deterministic_sample(synonyms, limit=n, word=word, pos=pos)
-
-    def precompute(self, word: str) -> list[str]:
-        normalized = _normalize_phrase(word)
-        if not normalized:
-            return []
-        return list(self._ensure_cached(normalized))
-
-    def export_cache(self) -> dict[str, list[str]]:
-        return {key: list(values) for key, values in self._cache.items()}
-
-    @classmethod
-    def load_cache(cls, path: str | Path) -> CacheSnapshot:
-        """Load and validate a persisted ConceptNet cache file."""
-
-        return _load_cache_file(Path(path))
-
-    def save_cache(self, path: str | Path | None = None) -> Path:
-        if path is None:
-            if self._cache_path is None:
-                raise RuntimeError("No cache path supplied to GraphLexicon.")
-            target = self._cache_path
-        else:
-            target = Path(path)
-            self._cache_path = target
-        snapshot = _write_cache_file(target, self._cache)
-        self._cache_checksum = snapshot.checksum
-        self._cache_dirty = False
-        return target
-
-    def supports_pos(self, pos: str | None) -> bool:
-        return True
-
-    def __repr__(self) -> str:  # pragma: no cover - debug helper
-        adapter = getattr(self._backend, "_adapter", None)
-        state = "loaded" if adapter else "empty"
-        return (
-            f"GraphLexicon(languages={sorted(self._languages)!r}, "
-            f"max_neighbors={self._max_neighbors}, seed={self.seed!r}, state={state})"
-        )
-

glitchlings-0.4.1.dist-info/RECORD

@@ -1,39 +0,0 @@
-glitchlings/__init__.py,sha256=onTBFM_ih4O1E1ntZaNaFxiMcD5NtCGc4TaX276sgNk,867
-glitchlings/__main__.py,sha256=pqNe1C9hMf8pap4oh6x6yo2h4Nsa2RFSaMWHfGtNXj0,130
-glitchlings/_zoo_rust.cp312-win_amd64.pyd,sha256=EMWrDQpRnkzHPhEiK2X7H1qcMPnNN_eIAx_SbAsKlas,2103808
-glitchlings/config.py,sha256=P6qMJdHrvZYAIUj7NXxrpEKcv6lDy8Eo4toWu3ctsHs,8043
-glitchlings/config.toml,sha256=EOEqKUwPygOv7MuEuExil5ZQfwKV1H2hU-Z5aBKQ440,111
-glitchlings/main.py,sha256=sKdUk4trBS-yNbEAOwdTXldg87TSPwnSAr_inecj4bE,10442
-glitchlings/dlc/__init__.py,sha256=IHD-GGhVFb7SVzErvf2YCJkOR4wGo0nFHXkn_daMvS8,146
-glitchlings/dlc/huggingface.py,sha256=PIesnDIEvyJxj1IuLw2P9nVPTr4Nv81XM7w2axfyhkA,3029
-glitchlings/dlc/prime.py,sha256=b5CE1qDl5MxZjTudlKrqMsmSGxXNKZ16krqPyrr2nK8,9569
-glitchlings/lexicon/__init__.py,sha256=WTX3vZhbhjd-WsRs63RT9Lw6KSfPW7SfzP2R3L_MFx0,6438
-glitchlings/lexicon/_cache.py,sha256=3hiGngtRlMfqKK4vIOnvjxb0tvCfF5u7DZP3wbn2Zlc,4066
-glitchlings/lexicon/graph.py,sha256=-AEh3eybkuUbVYg4GtOSvZhSqvik2QYY49A-lcNSi1I,10331
-glitchlings/lexicon/metrics.py,sha256=zwd3vm9-pUQbSywORXgHyHCfAjIJs8S5rPNQ70UYgUo,4768
-glitchlings/lexicon/vector.py,sha256=rEAKk8o8l8DfiV_-9D-9asLKg1dYc9MzHA5_oRmNIVM,20304
-glitchlings/lexicon/wordnet.py,sha256=EeZ1bZx9y-snjEsgItpJTysR1pDNpyO8CxcUztjloj4,6226
-glitchlings/lexicon/data/default_vector_cache.json,sha256=fLT-v1sgF0lv88aPwOP23br9azrjeAkJ1ft6OgPlMeM,741
-glitchlings/util/__init__.py,sha256=GoyQuHTfGRkHzuZwJji6QWSiGd_LHa9QiyjjEpBFW7E,4679
-glitchlings/zoo/__init__.py,sha256=AQu2Z0ECuzQDXwM_DbGaNzkcjLu8WptJS17sh6WTyyA,4975
-glitchlings/zoo/_ocr_confusions.py,sha256=W59Aa5MBDwRF65f8GV-6XwGAmlR5Uk7pa5qvHvhIYdY,1252
-glitchlings/zoo/_rate.py,sha256=EYUWXYyR2IK0zYBWyBOlnUjDxU32JE9mZTZeodVx5CA,548
-glitchlings/zoo/_sampling.py,sha256=UK-XmEERjtY7nLaWDp81yktuZ_K80Un-9tvj4MjsHcg,1642
-glitchlings/zoo/_text_utils.py,sha256=YxV069L8c0YSn5iCp72Dv8XCdfhbcFeBrbMoBeKIDns,2862
-glitchlings/zoo/adjax.py,sha256=G2diAEsQ8T4mjFCcTeiGzLF0261n7LjLyW5HyVCy3R4,3661
-glitchlings/zoo/core.py,sha256=zptaRvSL4wFdiUkmy_x4tD4CUD0la_egDQVMZ1n3xj0,17708
-glitchlings/zoo/jargoyle.py,sha256=yRSVRKHdnaUfZMDJ6miBhRQpPHfYK9iD2DCYMp-7Dec,11807
-glitchlings/zoo/mim1c.py,sha256=3ddNOzWgLABuEOh5T98Xk439ejx-YHGI7ErXET03Crc,3537
-glitchlings/zoo/ocr_confusions.tsv,sha256=S-IJEYCIXYKT1Uu7Id8Lnvg5pw528yNigTtWUdnMv9k,213
-glitchlings/zoo/redactyl.py,sha256=P2YYo1V_u62WIj8zqgDpbzDsreGx2I77BJ0RkdCKhXU,5651
-glitchlings/zoo/reduple.py,sha256=w90xQWQKwkY3tItk8S20emDQy4FLDbee9rrPyh_ffpg,4363
-glitchlings/zoo/rushmore.py,sha256=amAk44TIQBN4rU1c-W1g7I6WForGJMGxNb8uaa8Zfaw,4495
-glitchlings/zoo/scannequin.py,sha256=TJyNYTTIB7rxZH3XKIETy0YVf4EjsMgGWYmYaxH9jxU,5030
-glitchlings/zoo/typogre.py,sha256=j7LuAyYLrP6LjmCm8Jwi_wPxhTAP_TmWbt5pQrOvFZk,6901
-glitchlings/zoo/zeedub.py,sha256=J8F1XZeCMQVVtzWwNiFhOeogjBt1BsOtqrnDjlwUcl8,4984
-glitchlings-0.4.1.dist-info/licenses/LICENSE,sha256=EFEP1evBfHaxsMTBjxm0sZVRp2wct8QLvHE1saII5FI,11538
-glitchlings-0.4.1.dist-info/METADATA,sha256=5cwuNjNuQCoGUBsM_xipGSoDmC1DBb8AJGhrAeRFnDI,28787
-glitchlings-0.4.1.dist-info/WHEEL,sha256=8UP9x9puWI0P1V_d7K2oMTBqfeLNm21CTzZ_Ptr0NXU,101
-glitchlings-0.4.1.dist-info/entry_points.txt,sha256=kGOwuAsjFDLtztLisaXtOouq9wFVMOJg5FzaAkg-Hto,54
-glitchlings-0.4.1.dist-info/top_level.txt,sha256=VHFNBrLjtDwPCYXbGKi6o17Eueedi81eNbR3hBOoST0,12
-glitchlings-0.4.1.dist-info/RECORD,,