add type fields for rs

python/src/build.rs

@@ -59,8 +59,19 @@ fn create_file(p: &Path) -> std::io::Result<File> {
 }
 
 /// Build system dictionary from matrix and lexicons.
+///
+/// :param matrix: Path to the matrix file.
+/// :param lex: List of paths to lexicon files.
+/// :param output: Path to output built dictionray.
+/// :param description: A description text to embed in the dictionary.
+/// :return: A build report, list of (part, size, time).
+/// 
+/// :type matrix: pathlib.Path | str | bytes
+/// :type lex: list[pathlib.Path | str | bytes]
+/// :type output: pathlib.Path | str
+/// :type description: str
 #[pyfunction]
-#[pyo3(text_signature="(matrix, lex, output, description=None) -> list[tuple[str, int, float]]")]
+#[pyo3(text_signature = "(matrix, lex, output, description=None) -> list[tuple[str, int, float]]")]
 fn build_system_dic<'p>(
     py: Python<'p>,
     matrix: &'p PyAny,
@@ -89,8 +100,19 @@ fn build_system_dic<'p>(
 }
 
 /// Build user dictionary from lexicons based on the given system dictionary.
+///
+/// :param system: Path to the system dictionary.
+/// :param lex: List of paths to lexicon files.
+/// :param output: Path to output built dictionray.
+/// :param description: A description text to embed in the dictionary.
+/// :return: A build report, list of (part, size, time).
+/// 
+/// :type system: pathlib.Path | str
+/// :type lex: list[pathlib.Path | str | bytes]
+/// :type output: pathlib.Path | str
+/// :type description: str
 #[pyfunction]
-#[pyo3(text_signature="(system, lex, output, description=None) -> list[tuple[str, int, float]]")]
+#[pyo3(text_signature = "(system, lex, output, description=None) -> list[tuple[str, int, float]]")]
 fn build_user_dic<'p>(
     py: Python<'p>,
     system: &'p PyAny,

python/src/dictionary.rs

@@ -90,6 +90,12 @@ impl PyDicData {
 /// :param dict: type of pre-packaged dictionary, referring to sudachidict_<dict_type> packages on PyPI: https://pypi.org/search/?q=sudachidict.
 ///     Also, can be an _absolute_ path to a compiled dictionary file.
 /// :param dict_type: deprecated alias to dict.
+///
+/// :type config_path: Config | pathlib.Path | str | None
+/// :type config: Config | pathlib.Path | str | None
+/// :type resource_dir: pathlib.Path | str | None
+/// :type dict: pathlib.Path | str | None
+/// :type dict_type: pathlib.Path | str | None
 #[pyclass(module = "sudachipy.dictionary", name = "Dictionary")]
 #[derive(Clone)]
 pub struct PyDictionary {
@@ -111,6 +117,12 @@ impl PyDictionary {
     /// :param dict: type of pre-packaged dictionary, referring to sudachidict_<dict_type> packages on PyPI: https://pypi.org/search/?q=sudachidict.
     ///     Also, can be an _absolute_ path to a compiled dictionary file.
     /// :param dict_type: deprecated alias to dict.
+    ///
+    /// :type config_path: Config | pathlib.Path | str | None
+    /// :type config: Config | pathlib.Path | str | None
+    /// :type resource_dir: pathlib.Path | str | None
+    /// :type dict: pathlib.Path | str | None
+    /// :type dict_type: pathlib.Path | str | None
     #[new]
     #[pyo3(
         text_signature="(config_path=None, resource_dir=None, dict=None, dict_type=None, *, config=None) -> Dictionary",
@@ -235,6 +247,10 @@ impl PyDictionary {
     /// :param fields: load only a subset of fields.
     ///     See https://worksapplications.github.io/sudachi.rs/python/topics/subsetting.html.
     /// :param projection: Projection override for created Tokenizer. See Config.projection for values.
+    ///
+    /// :type mode: SplitMode | str | None
+    /// :type fields: set[str] | None
+    /// :type projection: str | None
     #[pyo3(
         text_signature="(self, /, mode=SplitMode.C, fields=None, *, projection=None) -> Tokenizer",
         signature=(mode=None, fields=None, *, projection=None)
@@ -277,7 +293,9 @@ impl PyDictionary {
     /// (None, None, None, None, None, '終止形‐一般') will match any word in 終止形‐一般 conjugation form.
     ///
     /// :param target: can be either a list of POS partial tuples or a callable which maps POS to bool.
-    #[pyo3(text_signature="(self, /, target) -> PosMatcher")]
+    ///
+    /// :type target: Iterable[PartialPOS] | Callable[[POS], bool]
+    #[pyo3(text_signature = "(self, /, target) -> PosMatcher")]
     fn pos_matcher<'py>(&'py self, py: Python<'py>, target: &PyAny) -> PyResult<PyPosMatcher> {
         PyPosMatcher::create(py, self.dictionary.as_ref().unwrap(), target)
     }
@@ -293,8 +311,10 @@ impl PyDictionary {
     ///     See https://github.com/huggingface/tokenizers/blob/master/bindings/python/examples/custom_components.py.
     /// :param projection: Projection override for created Tokenizer. See Config.projection for values.
     ///
-    /// :type mode: SplitMode
-    /// :type fields: Set[str]
+    /// :type mode: SplitMode | str | None
+    /// :type fields: set[str] | None
+    /// :type handler: Callable[[int, NormalizedString, MorphemeList], list[NormalizedString]] | None
+    /// :type projection: str | None
     #[pyo3(
         text_signature="(self, /, mode=None, fields=None, handler=None, *, projection=None) -> tokenizers.PreTokenizer",
         signature=(mode=None, fields=None, handler=None, *, projection=None)
@@ -352,8 +372,8 @@ impl PyDictionary {
     ///     See https://worksapplications.github.io/sudachi.rs/python/topics/out_param.html for details.
     ///
     /// :type surface: str
-    /// :type out: MorphemeList
-    #[pyo3(text_signature="(self, /, surface, out=None) -> MorphemeList")]
+    /// :type out: MorphemeList | None
+    #[pyo3(text_signature = "(self, /, surface, out=None) -> MorphemeList")]
     fn lookup<'p>(
         &'p self,
         py: Python<'p>,
@@ -381,7 +401,7 @@ impl PyDictionary {
     }
 
     /// Close this dictionary.
-    #[pyo3(text_signature="(self, /) -> ()")]
+    #[pyo3(text_signature = "(self, /) -> ()")]
     fn close(&mut self) {
         self.dictionary = None;
     }
@@ -390,7 +410,9 @@ impl PyDictionary {
     ///
     /// :param pos_id: POS id
     /// :return: POS tuple with the given id or None for non existing id.
-    #[pyo3(text_signature="(self, /, pos_id: int) -> tuple[str, str, str, str, str, str] | None")]
+    ///
+    /// :type pos_id: int
+    #[pyo3(text_signature = "(self, /, pos_id: int) -> tuple[str, str, str, str, str, str] | None")]
     fn pos_of<'p>(&'p self, py: Python<'p>, pos_id: usize) -> Option<&'p PyTuple> {
         let dic = self.dictionary.as_ref().unwrap();
         dic.pos.get(pos_id).map(|x| x.as_ref(py))

python/src/morpheme.rs

@@ -94,7 +94,7 @@ impl PyMorphemeListWrapper {
 impl PyMorphemeListWrapper {
     /// Returns an empty morpheme list with dictionary.
     #[classmethod]
-    #[pyo3(text_signature="(dict: Dictionary) -> MorphemeList")]
+    #[pyo3(text_signature = "(dict: Dictionary) -> MorphemeList")]
     fn empty(_cls: &PyType, py: Python, dict: &PyDictionary) -> PyResult<Self> {
         let cat = PyModule::import(py, "builtins")?.getattr("DeprecationWarning")?;
         PyErr::warn(
@@ -113,13 +113,13 @@ impl PyMorphemeListWrapper {
     }
 
     /// Returns the total cost of the path.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn get_internal_cost(&self, py: Python) -> i32 {
         self.internal(py).get_internal_cost()
     }
 
     /// Returns the number of morpheme in this list.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn size(&self, py: Python) -> usize {
         self.internal(py).len()
     }
@@ -282,14 +282,14 @@ impl PyMorpheme {
 #[pymethods]
 impl PyMorpheme {
     /// Returns the begin index of this in the input text.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn begin(&self, py: Python) -> usize {
         // call codepoint version
         self.morph(py).begin_c()
     }
 
     /// Returns the end index of this in the input text.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn end(&self, py: Python) -> usize {
         // call codepoint version
         self.morph(py).end_c()
@@ -298,7 +298,7 @@ impl PyMorpheme {
     /// Returns the substring of input text corresponding to the morpheme, or a projection if one is configured.
     ///
     /// See `Config.projection`.
-    #[pyo3(text_signature="(self, /) -> str")]
+    #[pyo3(text_signature = "(self, /) -> str")]
     fn surface<'py>(&'py self, py: Python<'py>) -> &'py PyString {
         let list = self.list(py);
         let morph = self.morph(py);
@@ -311,14 +311,14 @@ impl PyMorpheme {
     /// Returns the substring of input text corresponding to the morpheme regardless the configured projection.
     ///
     /// See `Config.projection`.
-    #[pyo3(text_signature="(self, /) -> str")]
+    #[pyo3(text_signature = "(self, /) -> str")]
     fn raw_surface<'py>(&'py self, py: Python<'py>) -> &'py PyString {
         PyString::new(py, self.morph(py).surface().deref())
     }
 
     /// Returns the part of speech as a six-element tuple.
     /// Tuple elements are four POS levels, conjugation type and conjugation form.
-    #[pyo3(text_signature="(self, /) -> tuple[str, str, str, str, str, str]")]
+    #[pyo3(text_signature = "(self, /) -> tuple[str, str, str, str, str, str]")]
     fn part_of_speech<'py>(&'py self, py: Python<'py>) -> Py<PyTuple> {
         let pos_id = self.part_of_speech_id(py);
         self.list(py)
@@ -329,25 +329,25 @@ impl PyMorpheme {
     }
 
     /// Returns the id of the part of speech in the dictionary.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     pub fn part_of_speech_id(&self, py: Python) -> u16 {
         self.morph(py).part_of_speech_id()
     }
 
     /// Returns the dictionary form.
-    #[pyo3(text_signature="(self, /) -> str")]
+    #[pyo3(text_signature = "(self, /) -> str")]
     fn dictionary_form<'py>(&'py self, py: Python<'py>) -> PyObject {
         self.morph(py).get_word_info().dictionary_form().into_py(py)
     }
 
     /// Returns the normalized form.
-    #[pyo3(text_signature="(self, /) -> str")]
+    #[pyo3(text_signature = "(self, /) -> str")]
     fn normalized_form<'py>(&'py self, py: Python<'py>) -> PyObject {
         self.morph(py).get_word_info().normalized_form().into_py(py)
     }
 
     /// Returns the reading form.
-    #[pyo3(text_signature="(self, /) -> str")]
+    #[pyo3(text_signature = "(self, /) -> str")]
     fn reading_form<'py>(&'py self, py: Python<'py>) -> PyObject {
         self.morph(py).get_word_info().reading_form().into_py(py)
     }
@@ -362,12 +362,10 @@ impl PyMorpheme {
     /// :param add_single: return lists with the current morpheme if the split hasn't produced any elements.
     ///     When False is passed, empty lists are returned instead.
     ///
-    /// :type mode: sudachipy.SplitMode    
-    /// :type out: Optional[sudachipy.MorphemeList]
+    /// :type mode: SplitMode | None
+    /// :type out: MorphemeList | None
     /// :type add_single: bool
-    #[pyo3(
-        text_signature="(self, /, mode, out=None, add_single=False) -> MorphemeList"
-    )]
+    #[pyo3(text_signature = "(self, /, mode, out=None, add_single=False) -> MorphemeList")]
     fn split<'py>(
         &'py self,
         py: Python<'py>,
@@ -410,19 +408,19 @@ impl PyMorpheme {
     }
 
     /// Returns whether if this is out of vocabulary word.
-    #[pyo3(text_signature="(self, /) -> bool")]
+    #[pyo3(text_signature = "(self, /) -> bool")]
     fn is_oov(&self, py: Python) -> bool {
         self.morph(py).is_oov()
     }
 
     /// Returns word id of this word in the dictionary.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn word_id(&self, py: Python) -> u32 {
         self.morph(py).word_id().as_raw()
     }
 
     /// Returns the dictionary id which this word belongs.
-    #[pyo3(text_signature="(self, /) -> int")]
+    #[pyo3(text_signature = "(self, /) -> int")]
     fn dictionary_id(&self, py: Python) -> i32 {
         let word_id = self.morph(py).word_id();
         if word_id.is_oov() {
@@ -433,15 +431,15 @@ impl PyMorpheme {
     }
 
     /// Returns the list of synonym group ids.
-    #[pyo3(text_signature="(self, /) -> List[int]")]
+    #[pyo3(text_signature = "(self, /) -> List[int]")]
     fn synonym_group_ids<'py>(&'py self, py: Python<'py>) -> &'py PyList {
         let mref = self.morph(py);
         let ids = mref.get_word_info().synonym_group_ids();
         PyList::new(py, ids)
     }
 
     /// Returns the word info.
-    #[pyo3(text_signature="(self, /) -> WordInfo")]
+    #[pyo3(text_signature = "(self, /) -> WordInfo")]
     fn get_word_info(&self, py: Python) -> PyResult<PyWordInfo> {
         let cat = PyModule::import(py, "builtins")?.getattr("DeprecationWarning")?;
         PyErr::warn(py, cat, "Users should not touch the raw WordInfo.", 1)?;

python/src/pos_matcher.rs

@@ -125,8 +125,10 @@ impl PyPosMatcher {
 impl PyPosMatcher {
     /// Checks whether a morpheme has matching POS.
     ///
-    /// :param m: morpheme.
+    /// :param m: a morpheme to check.
     /// :return: if morpheme has matching POS.
+    ///
+    /// :type m: Morpheme
     pub fn __call__<'py>(&'py self, py: Python<'py>, m: &'py PyMorpheme) -> bool {
         let pos_id = m.part_of_speech_id(py);
         self.matcher.matches_id(pos_id)

python/src/tokenizer.rs

@@ -36,6 +36,9 @@ use crate::morpheme::{PyMorphemeListWrapper, PyProjector};
 /// C == long mode
 ///
 /// :param mode: string representation of the split mode. One of [A,B,C] in captital or lower case.
+///     If None, returns SplitMode.C.
+///
+/// :type mode: str | None
 #[pyclass(module = "sudachipy.tokenizer", name = "SplitMode", frozen)]
 #[derive(Clone, PartialEq, Eq, Copy, Debug)]
 #[repr(u8)]
@@ -67,9 +70,12 @@ impl From<Mode> for PySplitMode {
 
 #[pymethods]
 impl PySplitMode {
-    /// Parse SplitMode from a character.
+    /// Creates a split mode from a string value.
+    ///
+    /// :param mode: string representation of the split mode. One of [A,B,C] in captital or lower case.
+    ///     If None, returns SplitMode.C.
     ///
-    /// :param mode: str to parse. One of [A,B,C] in captital or lower case.
+    /// :type mode: str | None
     #[new]
     #[pyo3(
         text_signature="(mode=None) -> SplitMode",
@@ -133,8 +139,8 @@ impl PyTokenizer {
     ///    See https://worksapplications.github.io/sudachi.rs/python/topics/out_param.html for details.
     ///
     /// :type text: str
-    /// :type mode: sudachipy.SplitMode
-    /// :type out: sudachipy.MorphemeList
+    /// :type mode: SplitMode | str | None
+    /// :type out: MorphemeList
     #[pyo3(
         text_signature="(self, /, text: str, mode=None, logger=None, out=None) -> MorphemeList",
         signature=(text, mode=None, logger=None, out=None)