Add type hints to core test suite functions

pythainlp/corpus/common.py

@@ -11,7 +11,7 @@
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
-    from typing import Union
+    from typing import Any, Union
 
 __all__ = [
     "countries",
@@ -384,10 +384,12 @@ def find_synonyms(word: str) -> list[str]:
         # output: ['จรุก', 'วราหะ', 'วราห์', 'ศูกร', 'สุกร']
     """
     synonyms = thai_synonyms()  # get a dictionary of {word, synonym}
-    list_synonym = []
+    list_synonym: list[Any] = []
 
     if word in synonyms["word"]:  # find by word
-        list_synonym.extend(synonyms["synonym"][synonyms["word"].index(word)])
+        word_list = synonyms["word"]
+        if isinstance(word_list, list):
+            list_synonym.extend(synonyms["synonym"][word_list.index(word)])  # type: ignore[arg-type]
 
     for idx, words in enumerate(synonyms["synonym"]):  # find by synonym
         if word in words:

pythainlp/corpus/core.py

@@ -20,7 +20,7 @@
 from pythainlp.tools import get_full_data_path
 
 if TYPE_CHECKING:
-    from typing import Optional
+    from typing import Any, Optional
 
 _CHECK_MODE = os.getenv("PYTHAINLP_READ_MODE")
 _USER_AGENT = (
@@ -38,10 +38,10 @@ def __init__(self, response: HTTPResponse) -> None:
         self.headers = response.headers
         self._content = response.read()
 
-    def json(self) -> dict[str, str]:
+    def json(self) -> dict[str, Any]:
         """Parse JSON content from response."""
         try:
-            return json.loads(self._content.decode("utf-8"))
+            return json.loads(self._content.decode("utf-8"))  # type: ignore[no-any-return]
         except (json.JSONDecodeError, UnicodeDecodeError) as err:
             raise ValueError(f"Failed to parse JSON response: {err}") from err
 
@@ -73,7 +73,7 @@ def get_corpus_db(url: str) -> Optional[_ResponseWrapper]:
     return corpus_db
 
 
-def get_corpus_db_detail(name: str, version: str = "") -> dict[str, str]:
+def get_corpus_db_detail(name: str, version: str = "") -> dict[str, Any]:
     """Get details about a corpus, using information from local catalog.
 
     :param str name: name of corpus
@@ -86,11 +86,11 @@ def get_corpus_db_detail(name: str, version: str = "") -> dict[str, str]:
     if not version:
         for corpus in local_db["_default"].values():
             if corpus["name"] == name:
-                return corpus
+                return corpus  # type: ignore[no-any-return]
     else:
         for corpus in local_db["_default"].values():
             if corpus["name"] == name and corpus["version"] == version:
-                return corpus
+                return corpus  # type: ignore[no-any-return]
 
     return {}
 
@@ -550,14 +550,14 @@ def _check_version(cause: str) -> bool:
         temp = cause.replace(">", "")
         check = v > _version2int(temp)
     elif cause.startswith(">=") and "<=" not in cause and "<" in cause:
-        temp = cause.replace(">=", "").split("<")
-        check = _version2int(temp[0]) <= v < _version2int(temp[1])
+        temp_parts = cause.replace(">=", "").split("<")
+        check = _version2int(temp_parts[0]) <= v < _version2int(temp_parts[1])
     elif cause.startswith(">=") and "<=" in cause:
-        temp = cause.replace(">=", "").split("<=")
-        check = _version2int(temp[0]) <= v <= _version2int(temp[1])
+        temp_parts = cause.replace(">=", "").split("<=")
+        check = _version2int(temp_parts[0]) <= v <= _version2int(temp_parts[1])
     elif cause.startswith(">") and "<" in cause:
-        temp = cause.replace(">", "").split("<")
-        check = _version2int(temp[0]) < v < _version2int(temp[1])
+        temp_parts = cause.replace(">", "").split("<")
+        check = _version2int(temp_parts[0]) < v < _version2int(temp_parts[1])
     elif cause.startswith("<="):
         temp = cause.replace("<=", "")
         check = v <= _version2int(temp[0])
@@ -608,14 +608,14 @@ def download(name: str, force: bool = False, url: str = "", version: str = "") -
         print(f"Cannot download corpus catalog from: {url}")
         return False
 
-    corpus_db = corpus_db.json()
+    corpus_db_dict = corpus_db.json()
 
     # check if corpus is available
-    if name in corpus_db:
+    if name in corpus_db_dict:
         with open(corpus_db_path(), encoding="utf-8-sig") as f:
             local_db = json.load(f)
 
-        corpus = corpus_db[name]
+        corpus = corpus_db_dict[name]
         print("Corpus:", name)
         if not version:
             for v, file in corpus["versions"].items():
@@ -842,4 +842,4 @@ def get_hf_hub(repo_id: str, filename: str = "") -> str:
         )
     else:
         output_path = snapshot_download(repo_id=repo_id, local_dir=root_project)
-    return output_path
+    return output_path  # type: ignore[no-any-return]

pythainlp/tag/named_entity.py

@@ -49,9 +49,9 @@ def load_engine(self, engine: str, corpus: str) -> None:
                     model="pythainlp/thainer-corpus-v2-base-model"
                 )
             elif engine == "wangchanberta":
-                from pythainlp.wangchanberta import ThaiNameTagger as WangchanbertaThaiNameTagger  # type: ignore[assignment]  # noqa: I001,E501
+                from pythainlp.wangchanberta import ThaiNameTagger as WangchanbertaThaiNameTagger  # noqa: I001,E501
 
-                self.engine = WangchanbertaThaiNameTagger(dataset_name=corpus)  # type: ignore[call-arg]
+                self.engine = WangchanbertaThaiNameTagger(dataset_name=corpus)
         elif corpus == "thainer-v2":
             if engine == "phayathaibert":
                 from pythainlp.phayathaibert.core import NamedEntityTagger
@@ -101,7 +101,7 @@ def tag(
             >>> ner.tag("ทดสอบ นายวรรณพงษ์ ภัททิยไพบูลย์", tag=True)
             'ทดสอบ <PERSON>นายวรรณพงษ์ ภัททิยไพบูลย์</PERSON>'
         """
-        return self.engine.get_ner(text, tag=tag, pos=pos)  # type: ignore[union-attr]
+        return self.engine.get_ner(text, tag=tag, pos=pos)  # type: ignore[no-any-return]
 
 
 class NNER:

pythainlp/tag/unigram.py

@@ -38,15 +38,15 @@ def _orchid_tagger() -> dict:
     if not _ORCHID_TAGGER:
         with open(_ORCHID_PATH, encoding="utf-8-sig") as fh:
             _ORCHID_TAGGER = json.load(fh)
-    return _ORCHID_TAGGER
+    return _ORCHID_TAGGER  # type: ignore[no-any-return]
 
 
 def _pud_tagger() -> dict:
     global _PUD_TAGGER
     if not _PUD_TAGGER:
         with open(_PUD_PATH, encoding="utf-8-sig") as fh:
             _PUD_TAGGER = json.load(fh)
-    return _PUD_TAGGER
+    return _PUD_TAGGER  # type: ignore[no-any-return]
 
 
 def _blackboard_tagger() -> dict:
@@ -57,23 +57,23 @@ def _blackboard_tagger() -> dict:
             raise ValueError(f"Corpus path not found for {_BLACKBOARD_NAME}")
         with open(path, encoding="utf-8-sig") as fh:
             _BLACKBOARD_TAGGER = json.load(fh)
-    return _BLACKBOARD_TAGGER
+    return _BLACKBOARD_TAGGER  # type: ignore[no-any-return]
 
 
 def _thai_tdtb() -> dict:
     global _TDTB_TAGGER
     if not _TDTB_TAGGER:
         with open(_TDTB_PATH, encoding="utf-8-sig") as fh:
             _TDTB_TAGGER = json.load(fh)
-    return _TDTB_TAGGER
+    return _TDTB_TAGGER  # type: ignore[no-any-return]
 
 
 def _tud_tagger() -> dict:
     global _TUD_TAGGER
     if not _TUD_TAGGER:
         with open(_TUD_PATH, encoding="utf-8-sig") as fh:
             _TUD_TAGGER = json.load(fh)
-    return _TUD_TAGGER
+    return _TUD_TAGGER  # type: ignore[no-any-return]
 
 
 def _find_tag(

pythainlp/transliterate/core.py

@@ -169,19 +169,19 @@ def transliterate(
     if engine in ("icu", "pyicu"):
         from pythainlp.transliterate.pyicu import transliterate
     elif engine == "ipa":
-        from pythainlp.transliterate.ipa import transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.ipa import transliterate  # noqa: I001
     elif engine == "tltk_g2p":
-        from pythainlp.transliterate.tltk import tltk_g2p as transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.tltk import tltk_g2p as transliterate  # noqa: I001
     elif engine == "tltk_ipa":
-        from pythainlp.transliterate.tltk import tltk_ipa as transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.tltk import tltk_ipa as transliterate  # noqa: I001
     elif engine == "iso_11940":
-        from pythainlp.transliterate.iso_11940 import transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.iso_11940 import transliterate  # type: ignore[assignment]  # noqa: I001
     elif engine == "thaig2p_v2":
-        from pythainlp.transliterate.thaig2p_v2 import transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.thaig2p_v2 import transliterate  # noqa: I001
     elif engine == "umt5_thaig2p":
-        from pythainlp.translate.umt5_thaig2p import transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.translate.umt5_thaig2p import transliterate  # type: ignore[import-not-found, no-redef]  # noqa: I001
     else:  # use default engine: "thaig2p"
-        from pythainlp.transliterate.thaig2p import transliterate  # type: ignore[no-redef]  # noqa: I001
+        from pythainlp.transliterate.thaig2p import transliterate  # noqa: I001
 
     return transliterate(text)
 

pythainlp/transliterate/lookup.py

@@ -36,7 +36,7 @@ def follow_rtgs(text: str) -> Optional[bool]:
     except IndexError:
         return None
     else:
-        return follow
+        return follow  # type: ignore[return-value]
 
 
 def _romanize(text: str, fallback_func: Callable[[str], str]) -> str:
@@ -49,9 +49,9 @@ def _romanize(text: str, fallback_func: Callable[[str], str]) -> str:
     except IndexError:
         return fallback_func(text)
     except TypeError as e:
-        raise TypeError(f"`fallback_engine` is not callable. {e}")
+        raise TypeError(f"`fallback_engine` is not callable. {e}") from e
     else:
-        return lookup
+        return lookup  # type: ignore[return-value]
 
 
 def romanize(text: str, fallback_func: Callable[[str], str]) -> str:

pythainlp/util/spell_words.py

@@ -24,9 +24,9 @@
     for i, j in zip(list(thai_tonemarks), ["เอก", "โท", "ตรี", "จัตวา"])
 }
 
-rule1 = [i.replace("-", f"([{thai_letters}](thai_tonemarks)?)") for i in _r1]
-rule2 = [i.replace("–", f"([{thai_letters}])").replace(":", "") for i in _r2]
-rule3 = [
+rule1: list[str] = [i.replace("-", f"([{thai_letters}](thai_tonemarks)?)") for i in _r1]
+rule2: list[str] = [i.replace("–", f"([{thai_letters}])").replace(":", "") for i in _r2]
+rule3: list[str] = [
     i.replace("–", f"([{thai_letters}])").replace(":", f"([{thai_tonemarks}])")
     for i in _r2
 ]