Fix morpheme backend info in README and docs

Author: hyunwoongko

README.md

@@ -69,7 +69,7 @@ Split texts into sentences.
 
 Args:
     text (Union[str, List[str], Tuple[str]]): single text or list/tuple of texts
-    backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct' are supported
+    backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct', 'fast' are supported
     num_workers (Union[int, str]): the number of multiprocessing workers
     strip (bool): strip all sentences or not
     return_morphemes (bool): whether to return morphemes or not
@@ -1306,7 +1306,7 @@ This splits texts into sentences.
 
 Args:
 - text (`Union[str, List[str], Tuple[str]]`): single text or list/tuple of texts
-- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab', 'punct' are supported
+- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab', 'punct', 'fast' are supported
 - num_workers (`Union[int, str]`): the number of multiprocessing workers
 - strip (`bool`): strip all sentences or not
 - return_morphemes (`bool`): whether to return morphemes or not
@@ -1332,7 +1332,7 @@ This corrects the spacing of the text.
 
 Args:
 - text (`Union[str, List[str], Tuple[str]]`): single text or list/tuple of texts
-- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab', 'punct' are supported
+- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab' are supported
 - num_workers (`Union[int, str]`): the number of multiprocessing workers
 - reset_whitespaces (`bool`): reset whitespaces or not
 - return_morphemes (`bool`): whether to return morphemes or not
@@ -1359,7 +1359,7 @@ This summarizes the given text, using TextRank algorithm.
 
 Args:
 - text (`Union[str, List[str], Tuple[str]]`): single text or list/tuple of texts
-- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab' are supported.
+- backend (`str`): morpheme analyzer backend. 'mecab', 'pecab', 'punct', 'fast' are supported.
 - num_workers (`Union[int, str]`): the number of multiprocessing workers
 - max_sentences (`int`): the max number of sentences in a summarization result.
 - tolerance (`float`): a threshold for omitting edge weights.

kss/__init__.py

@@ -201,4 +201,4 @@ def _find_closest_module(module, min_distance=0.5):
 
 
 __ALL__ = list(supported_modules.keys()) + ["Kss"]
-__version__ = "6.0.3"
+__version__ = "6.0.4"

kss/_modules/augmentation/augment.py

@@ -5,7 +5,7 @@
 from kss._modules.augmentation.utils import correct_josa
 from kss._utils.logger import highlight_diffs, logger
 from kss._utils.multiprocessing import _run_job
-from kss._utils.sanity_checks import _check_text, _check_type, _check_num_workers, _check_backend_mecab_pecab_only
+from kss._utils.sanity_checks import _check_text, _check_type, _check_num_workers, _check_analyzer_backend_mecab_pecab_only
 
 
 def augment(
@@ -52,7 +52,7 @@ def augment(
     josa_correction = _check_type(josa_correction, "josa_correction", bool)
     verbose = _check_type(verbose, "verbose", bool)
     num_workers = _check_num_workers(text, num_workers)
-    _check_backend_mecab_pecab_only(backend)
+    _check_analyzer_backend_mecab_pecab_only(backend)
 
     if num_workers is not False and verbose:
         verbose = False

kss/_modules/g2p/g2p.py

@@ -32,7 +32,7 @@
 )
 from kss._modules.jamo._jamo import h2j, j2h
 from kss._utils.multiprocessing import _run_job
-from kss._utils.sanity_checks import _check_text, _check_num_workers, _check_type, _check_backend_mecab_pecab_only
+from kss._utils.sanity_checks import _check_text, _check_num_workers, _check_type, _check_analyzer_backend_mecab_pecab_only
 
 
 def g2p(
@@ -89,7 +89,7 @@ def g2p(
                                                      "convert_numbers_to_hangul_phonemes", bool)
     verbose = _check_type(verbose, "verbose", bool)
     num_workers = _check_num_workers(text, num_workers)
-    _check_backend_mecab_pecab_only(backend)
+    _check_analyzer_backend_mecab_pecab_only(backend)
 
     return _run_job(
         func=partial(

kss/_modules/keywords/extract_keywords.py

@@ -3,7 +3,7 @@
 from typing import List, Union, Tuple
 
 from kss._modules.keywords.utils import KRWordRank
-from kss._utils.sanity_checks import _check_text, _check_type, _check_backend_mecab_pecab_only
+from kss._utils.sanity_checks import _check_text, _check_type, _check_analyzer_backend_mecab_pecab_only
 
 
 def extract_keywords(
@@ -67,7 +67,7 @@ def extract_keywords(
     max_word_length = _check_type(max_word_length, "max_word_length", int)
     return_scores = _check_type(return_scores, "return_scores", bool)
     noun_only = _check_type(noun_only, "noun_only", bool)
-    _check_backend_mecab_pecab_only(backend)
+    _check_analyzer_backend_mecab_pecab_only(backend)
 
     if num_workers != "auto":
         raise ValueError("`extract_keywords` does not support `num_workers` argument")

kss/_modules/morphemes/split_morphemes.py

@@ -7,7 +7,7 @@
 from kss._utils.multiprocessing import _run_job
 from kss._utils.sanity_checks import (
     _check_text,
-    _check_analyzer_backend,
+    _check_analyzer_backend_mecab_pecab_only,
     _check_num_workers,
     _check_type,
 )
@@ -47,6 +47,6 @@ def split_morphemes(
         return text
 
     num_workers = _check_num_workers(text, num_workers)
-    backend = _check_analyzer_backend(backend)
+    backend = _check_analyzer_backend_mecab_pecab_only(backend)
     result = _run_job(partial(backend.pos, drop_space=drop_space), text, num_workers)
     return result

kss/_modules/romanization/romanize.py

@@ -10,7 +10,7 @@
 from kss._modules.g2p.g2p import g2p
 from kss._modules.romanization.utils import pronounce, Syllable
 from kss._utils.multiprocessing import _run_job
-from kss._utils.sanity_checks import _check_text, _check_type, _check_num_workers, _check_backend_mecab_pecab_only
+from kss._utils.sanity_checks import _check_text, _check_type, _check_num_workers, _check_analyzer_backend_mecab_pecab_only
 
 vowel = {
     # 단모음 monophthongs
@@ -124,7 +124,7 @@ def romanize(
         return text
 
     use_morpheme_info = _check_type(use_morpheme_info, "use_morpheme_info", bool)
-    _check_backend_mecab_pecab_only(backend)
+    _check_analyzer_backend_mecab_pecab_only(backend)
     convert_english_to_hangul_phonemes = _check_type(convert_english_to_hangul_phonemes,
                                                      "convert_english_to_hangul_phonemes", bool)
     convert_numbers_to_hangul_phonemes = _check_type(convert_numbers_to_hangul_phonemes,

kss/_modules/sentences/split_sentences.py

@@ -38,7 +38,7 @@ def split_sentences(
 
     Args:
         text (Union[str, List[str], Tuple[str]]): single text or list/tuple of texts
-        backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct' are supported
+        backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct', 'fast' are supported
         num_workers (Union[int, str])): the number of multiprocessing workers
         strip (bool): strip all sentences or not
         return_morphemes (bool): whether to return morphemes or not

kss/_modules/spacing/correct_spacing.py

@@ -11,7 +11,7 @@
 from kss._modules.sentences.split_sentences import _split_sentences
 from kss._modules.spacing.utils import postprocess, postprocess_heuristic
 from kss._utils.multiprocessing import _run_job
-from kss._utils.sanity_checks import _check_text, _check_backend_mecab_pecab_only, _check_num_workers
+from kss._utils.sanity_checks import _check_text, _check_analyzer_backend_mecab_pecab_only, _check_num_workers
 
 any_ws = re.compile(r"\s+")
 space_insertable = r"(([^SUWX]|X[RS]|S[EH]).* ([NMI]|V[VAX]|VCN|XR|XPN|S[WLHN]))|(SN ([MI]|N[PR]|NN[GP]|V[VAX]|VCN|XR|XPN|S[WHN]))|((S[FPL]).* ([NMI]|V[VAX]|VCN|XR|XPN|S[WHN]))"
@@ -42,7 +42,7 @@ def correct_spacing(
 
     Args:
         text (Union[str, List[str], Tuple[str]]): single text or list/tuple of texts
-        backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct' are supported
+        backend (str): morpheme analyzer backend. 'mecab', 'pecab' are supported
         num_workers (Union[int, str])): the number of multiprocessing workers
         reset_whitespaces (bool): reset whitespaces or not
         return_morphemes (bool): whether to return morphemes or not
@@ -67,7 +67,7 @@ def correct_spacing(
         return text
 
     backend_string = backend
-    backend = _check_backend_mecab_pecab_only(backend)
+    backend = _check_analyzer_backend_mecab_pecab_only(backend)
     _num_workers = _check_num_workers(text, num_workers)
 
     return _run_job(

kss/_modules/summarization/summarize_sentences.py

@@ -33,7 +33,7 @@ def summarize_sentences(
 
     Args:
         text (Union[str, List[str], Tuple[str]]): single text or list/tuple of texts
-        backend (str): morpheme analyzer backend. 'mecab', 'pecab' are supported.
+        backend (str): morpheme analyzer backend. 'mecab', 'pecab', 'punct', 'fast' are supported.
         num_workers (Union[int, str])): the number of multiprocessing workers
         max_sentences (int): the max number of sentences in a summarization result.
         tolerance (float): a threshold for omitting edge weights.

kss/_utils/sanity_checks.py

@@ -198,7 +198,7 @@ def _check_text(
     return text, finish
 
 
-def _check_backend_mecab_pecab_only(backend: str) -> Analyzer:
+def _check_analyzer_backend_mecab_pecab_only(backend: str) -> Analyzer:
     global MECAB_INFORM, KONLPY_MECAB_INFORM, PECAB_INFORM
 
     if isinstance(backend, str):