feat(eKoNLPy): this is a BREAKING CHANGE.

.envrc

@@ -0,0 +1,11 @@
+export PYTHON_KEYRING_BACKEND=keyring.backends.null.Keyring
+export PROJECT_NAME="eKoNLPy"
+export PROJECT_ROOT="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+VIRTUAL_ENV="${WORKON_HOME}/${PROJECT_NAME}"
+if [ -e "${VIRTUAL_ENV}/bin/activate" ]; then
+    source "${VIRTUAL_ENV}/bin/activate"
+else
+    python3 -m venv "${VIRTUAL_ENV}"
+    source "${VIRTUAL_ENV}/bin/activate"
+    pip install --upgrade pip setuptools wheel
+fi

.pre-commit-config.yaml

@@ -14,7 +14,7 @@ repos:
     rev: v1.10.0
     hooks:
       - id: python-check-blanket-noqa
-      - id: python-check-blanket-type-ignore
+      # - id: python-check-blanket-type-ignore
       - id: python-check-mock-methods
       - id: python-no-eval
       - id: python-no-log-warn

README.md

@@ -22,7 +22,6 @@
 [codecov-url]: https://codecov.io/gh/entelecheia/eKoNLPy
 [zenodo-image]: https://zenodo.org/badge/DOI/10.5281/zenodo.7809447.svg
 [zenodo-url]: https://doi.org/10.5281/zenodo.7809447
-
 [repo-url]: https://github.com/entelecheia/eKoNLPy
 [pypi-url]: https://pypi.org/project/ekonlpy
 [docs-url]: https://ekonlpy.entelecheia.ai
@@ -34,7 +33,7 @@
 `eKoNLPy` is a Korean Natural Language Processing (NLP) Python library specifically designed for economic analysis. It extends the functionality of the `MeCab` tagger from KoNLPy to improve the handling of economic terms, financial institutions, and company names, classifying them as single nouns. Additionally, it incorporates sentiment analysis features to determine the tone of monetary policy statements, such as Hawkish or Dovish.
 
 > **Note**
-> 
+>
 > eKoNLPy is built on the [fugashi](https://github.com/polm/fugashi) and [mecab-ko-dic](https://github.com/LuminosoInsight/mecab-ko-dic) libraries. For more information on using the `Mecab` tagger, please refer to the [fugashi documentation](https://github.com/polm/fugashi). As eKoNLPy no longer relies on the [KoNLPy](https://konlpy.org) library, Java is not required for its use. This makes eKoNLPy compatible with Windows, Linux, and Mac OS, without the need for Java installation. You can also use eKoNLPy on Google Colab.
 
 If you wish to tokenize general Korean text with eKoNLPy, you do not need to install the `KoNLPy` library. Instead, utilize `ekonlpy.mecab.MeCab` as a replacement for `ekonlpy.tag.Mecab`.
@@ -56,20 +55,28 @@ pip install ekonlpy
 To use the part of speech tagging feature, input `Mecab.pos(phrase)` just like KoNLPy. First, the input is processed using KoNLPy's Mecab morpheme analyzer. Then, if a combination of consecutive tokens matches a term in the user dictionary, the phrase is separated into compound nouns.
 
 ```python
-from ekonlpy.tag import Mecab
+from ekonlpy import Mecab
 
 mecab = Mecab()
 mecab.pos('금통위는 따라서 물가안정과 병행, 경기상황에 유의하는 금리정책을 펼쳐나가기로 했다고 밝혔다.')
 ```
 
 > [('금', 'MAJ'), ('통', 'MAG'), ('위', 'NNG'), ('는', 'JX'), ('따라서', 'MAJ'), ('물가', 'NNG'), ('안정', 'NNG'), ('과', 'JC'), ('병행', 'NNG'), (',', 'SC'), ('경기', 'NNG'), ('상황', 'NNG'), ('에', 'JKB'), ('유의', 'NNG'), ('하', 'XSV'), ('는', 'ETM'), ('금리', 'NNG'), ('정책', 'NNG'), ('을', 'JKO'), ('펼쳐', 'VV+EC'), ('나가', 'VX'), ('기', 'ETN'), ('로', 'JKB'), ('했', 'VV+EP'), ('다고', 'EC'), ('밝혔', 'VV+EP'), ('다', 'EF'), ('.', 'SF')]
 
+You can also use the Command Line Interface (CLI) to perform part of speech tagging:
+
+```bash
+ekonlpy --input "안녕하세요"
+```
+
+> [('안녕', 'NNG'), ('하', 'XSV'), ('세요', 'EP')]
+
 ### cf. MeCab POS Tagging (fugashi)
 
 ```python
-from ekonlpy.mecab import MeCab # Be careful! `C` is capital.
+from ekonlpy import Mecab
 
-mecab = MeCab()
+mecab = Mecab(use_original_tagger=True) # set use_original_tagger=True
 mecab.pos('금통위는 따라서 물가안정과 병행, 경기상황에 유의하는 금리정책을 펼쳐나가기로 했다고 밝혔다.')
 ```
 

pyproject.toml

@@ -17,6 +17,9 @@ include = [
     "src/ekonlpy/data/model/*",
 ]
 
+[tool.poetry.scripts]
+ekonlpy = "ekonlpy.__cli__:main"
+
 [tool.poe]
 include = [".tasks.toml", ".tasks-extra.toml"]
 
@@ -27,11 +30,12 @@ mecab-ko-dic = "^1.0.0"
 nltk = "^3.8.1"
 scipy = "^1.10.1"
 pandas = "^1.5.3"
+click = "^8.1.6"
 
 [tool.poetry.group.dev.dependencies]
 python-semantic-release = "^7.33.1"
 isort = "^5.12.0"
-black = "^23.1.0"
+black = ">=23.0.0,<=23.3.0"
 flake8 = "^6.0.0"
 mypy = "^1.0.0"
 flake8-pyproject = "^1.2.2"
@@ -134,7 +138,7 @@ branch = "master"
 version_toml = "pyproject.toml:tool.poetry.version"
 version_variable = "src/ekonlpy/_version.py:__version__"
 version_source = "tag"
-commit_version_number = true                                          # required for version_source = "tag"
+commit_version_number = true                                    # required for version_source = "tag"
 commit_subject = "chore(release): :rocket: {version} [skip ci]"
 prerelease_tag = "rc"
 major_on_zero = true
@@ -143,7 +147,7 @@ changelog_file = "CHANGELOG.md"
 upload_to_repository = true
 upload_to_release = true
 build_command = "poetry build --no-cache"
-hvcs = "github"                                                       # hosting version control system, gitlab is also supported
+hvcs = "github"                                                 # hosting version control system, gitlab is also supported
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]

src/ekonlpy/__cli__.py

@@ -0,0 +1,45 @@
+"""Command line interface for eKoNLPy"""
+
+# Importing the libraries
+
+import click
+
+from ._version import __version__
+
+CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
+
+
+@click.command(context_settings=CONTEXT_SETTINGS)
+@click.version_option(__version__)
+@click.option(
+    "--tagger",
+    "-t",
+    show_default=True,
+    default="ekonlpy",
+    help="The tagger to use. [ekonlpy|mecab]]",
+)
+@click.option("--input", "-i", help="The input text to tag.")
+@click.pass_context
+def main(ctk, tagger, input):
+    """This is the command line interface for eKoNLPy.
+
+    It is used to tag Korean text with a Korean morphological analyzer.
+    """
+    # Print a message to the user.
+    if input:
+        click.echo(tag(tagger, input))
+    else:
+        # Print usage message to the user.
+        click.echo(ctk.get_help())
+
+
+def tag(tagger: str, text: str) -> list:
+    from ekonlpy import Mecab
+
+    mecab = Mecab(use_original_tagger=tagger == "mecab")
+    return mecab.pos(text)
+
+
+# main function for the main module
+if __name__ == "__main__":
+    main()

src/ekonlpy/__init__.py

@@ -1,9 +1,19 @@
-from . import etag, tag
 from ._version import __version__
+from .mecab import MecabDicConfig
+from .tag import Mecab
 from .utils.dictionary import TermDictionary
-from .utils.io import installpath, load_dictionary, load_txt
+from .utils.io import installpath
 
 
 def get_version() -> str:
     """This function returns the version of ekonlpy."""
     return __version__
+
+
+__all__ = [
+    "Mecab",
+    "MecabDicConfig",
+    "TermDictionary",
+    "installpath",
+    "get_version",
+]

src/ekonlpy/base/__init__.py

@@ -0,0 +1,3 @@
+from .base import BaseMecab
+
+__all__ = ["BaseMecab"]

src/ekonlpy/base/base.py

@@ -0,0 +1,46 @@
+import logging
+from typing import List, Optional, Tuple
+
+logger = logging.getLogger(__name__)
+
+
+class BaseMecab:
+    """Abstract class for MeCab tagger"""
+
+    def parse(
+        self,
+        text: str,
+    ) -> List[Tuple[str, str]]:
+        raise NotImplementedError
+
+    def pos(
+        self,
+        text: str,
+    ) -> List[Tuple[str, str]]:
+        return self.parse(text)
+
+    def tokenize(
+        self,
+        text: str,
+        strip_pos: bool = False,
+        postag_delim: str = "/",
+    ) -> List[str]:
+        tokens = self.parse(text)
+
+        return [
+            token_pos[0] if strip_pos else f"{token_pos[0]}{postag_delim}{token_pos[1]}"
+            for token_pos in tokens
+        ]
+
+    def morphs(self, text: str) -> List[str]:
+        return self.tokenize(text, strip_pos=True)
+
+    def nouns(
+        self,
+        text: str,
+        flatten: bool = True,
+        noun_pos: Optional[List[str]] = None,
+    ) -> List[str]:
+        if not noun_pos:
+            noun_pos = []
+        return [surface for surface, pos in self.pos(text) if pos in noun_pos]

src/ekonlpy/etag/__init__.py

@@ -1 +1,3 @@
 from ._template import ExtTagger
+
+__all__ = ["ExtTagger"]

src/ekonlpy/etag/_template.py

@@ -1,4 +1,4 @@
-from ..data.tagset import nouns_tags, pass_tags, skip_chk_tags, skip_tags
+from ekonlpy.data.tagset import nouns_tags, pass_tags, skip_chk_tags, skip_tags
 
 
 class ExtTagger:
@@ -20,13 +20,13 @@ def add_skip_tags(self, tags):
 
     def pos(self, tokens):
         def ctagger(
-                ctokens,
-                max_ngram,
-                cnouns_tags,
-                cpass_tags,
-                cskip_chk_tags,
-                cskip_tags,
-                cdictionary,
+            ctokens,
+            max_ngram,
+            cnouns_tags,
+            cpass_tags,
+            cskip_chk_tags,
+            cskip_tags,
+            cdictionary,
         ):
             tokens_org = ctokens
             num_tokens = len(ctokens)
@@ -65,7 +65,9 @@ def ctagger(
                         for j in range(ngram):
                             if tmp_tags[j] not in cskip_tags:
                                 new_word += tokens_org[ipos + j][0]
-                            num_word += "n" if tmp_tags[j] == "SN" else tokens_org[ipos + j][0]
+                            num_word += (
+                                "n" if tmp_tags[j] == "SN" else tokens_org[ipos + j][0]
+                            )
                         dict_tag = cdictionary.get_tags(num_word.lower())
                         if dict_tag:
                             new_word = num_word

src/ekonlpy/mecab/__init__.py

@@ -1,2 +1,4 @@
-from ._mecab import MeCab
+from ._mecab import Mecab
 from ._userdic import MecabDicConfig
+
+__all__ = ["Mecab", "MecabDicConfig"]