ci: add spell checking (#4148)

Adds [typos](https://github.com/crate-ci/typos) as a CI check and
pre-commit hook, the same way Lance does it, so misspellings like the
ones fixed in #4146 get caught automatically going forward.

This also fixes the misspellings `typos` found across the repo (Rust,
Python, TypeScript source, comments, and generated docs), and adds a
small `.typos.toml` with `extend-words` entries for terms that are
correct but look like typos: `AKS` (Azure Kubernetes Service), `RabitQ`
(a real quantization algorithm name), `mmaped` (the actual name of a
`candle-core` API we call), and `Writeable` (from Python's
`_typeshed.WriteableBuffer`). Third-party license files are excluded.

Fixes #4147

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>

python/python/lancedb/embeddings/instructor.py

@@ -60,7 +60,7 @@ class InstructorEmbeddingFunction(TextEmbeddingFunction):
 
     import lancedb
     from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import get_registry, InstuctorEmbeddingFunction
+    from lancedb.embeddings import get_registry, InstructorEmbeddingFunction
 
     instructor = get_registry().get("instructor").create(
         source_instruction="represent the document for retrieval",

python/python/lancedb/table.py

@@ -5638,7 +5638,7 @@ class AsyncTable:
         if fill_value is None:
             fill_value = 0.0
 
-        # _santitize_data is an old code path, but we will use it until the
+        # _sanitize_data is an old code path, but we will use it until the
         # new code path is ready.
         if mode == "overwrite":
             # For overwrite, apply the same preprocessing as create_table

python/python/tests/test_embeddings.py

@@ -327,8 +327,8 @@ def test_embedding_function_with_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registery = get_registry()
-    func = registery.get("mock-embedding").create()
+    registry = get_registry()
+    func = registry.get("mock-embedding").create()
 
     class TestSchema(LanceModel):
         text: str = func.SourceField()
@@ -394,9 +394,9 @@ def test_multiple_embeddings_for_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registery = get_registry()
-    func1 = registery.get("mock-embedding").create()
-    func2 = registery.get("mock-embedding2").create()
+    registry = get_registry()
+    func1 = registry.get("mock-embedding").create()
+    func2 = registry.get("mock-embedding2").create()
 
     class TestSchema(LanceModel):
         text: str = func1.SourceField()

python/python/tests/test_fts.py

@@ -1011,8 +1011,13 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search("nce", query_type="fts").limit(10).to_list()
-    )  # spellchecker:disable-line
+        table.search(
+            "nce",  # spellchecker:disable-line
+            query_type="fts",
+        )
+        .limit(10)
+        .to_list()
+    )
     assert len(results) == 2
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
@@ -1034,8 +1039,13 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search("nce", query_type="fts").limit(10).to_list()
-    )  # spellchecker:disable-line
+        table.search(
+            "nce",  # spellchecker:disable-line
+            query_type="fts",
+        )
+        .limit(10)
+        .to_list()
+    )
     assert len(results) == 0
 
     results = table.search("la", query_type="fts").limit(10).to_list()

python/python/tests/test_rerankers.py

@@ -81,7 +81,7 @@ def get_test_table(tmp_path):
         "but his son was mortal",
         "there hasn't been a good battlefield game since 2142",
         "I wish they would make another one",
-        "campains are not as good as they used to be",
+        "campaigns are not as good as they used to be",
         "Multiplayer and open world games have destroyed the single player experience",
         "Maybe the future is console games",
         "I don't know",

python/python/tests/test_table.py

@@ -3354,7 +3354,7 @@ def test_empty_query(mem_db: DBConnection):
     # None is the same as default
     df = table.search().select(["id"]).limit(None).to_arrow()
     assert df.num_rows == 100
-    # invalid limist is the same as None, wihch is the same as default
+    # invalid limist is the same as None, which is the same as default
     df = table.search().select(["id"]).limit(-1).to_arrow()
     assert df.num_rows == 100
     # valid limit should work

python/src/query.rs

@@ -334,7 +334,7 @@ pub struct PyQueryRequest {
     pub column: Option<String>,
     pub query_vector: Option<PyQueryVectors>,
     pub minimum_nprobes: Option<usize>,
-    // None means user did not set it and default shoud be used (currenty 20)
+    // None means user did not set it and default should be used (currently 20)
     // Some(0) means user set it to None and there is no limit
     pub maximum_nprobes: Option<usize>,
     pub lower_bound: Option<f32>,