character-encoding-utils 0.0.8__tar.gz → 0.0.10__tar.gz

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/PKG-INFO

@@ -1,18 +1,19 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: character-encoding-utils
-Version: 0.0.8
-Summary: Some character encoding utils.
-Project-URL: homepage, https://github.com/TakWolf/character-encoding-utils
-Project-URL: source, https://github.com/TakWolf/character-encoding-utils
-Project-URL: issues, https://github.com/TakWolf/character-encoding-utils/issues
+Version: 0.0.10
+Summary: Some character encoding utils
+Keywords: encoding,gb2312,big5,shift-jis,ksx1001
 Author: TakWolf
-Maintainer: TakWolf
-License: MIT License
-License-File: LICENSE
-Keywords: big5,encoding,gb2312,ksx1001,shift-jis
+License-Expression: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
+Maintainer: TakWolf
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 
@@ -76,4 +77,4 @@ assert ksx1001.decode(bs) == 'abc가쳰'
 
 ## License
 
-Under the [MIT license](LICENSE).
+[MIT License](LICENSE)

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/README.md

@@ -58,4 +58,4 @@ assert ksx1001.decode(bs) == 'abc가쳰'
 
 ## License
 
-Under the [MIT license](LICENSE).
+[MIT License](LICENSE)

character_encoding_utils-0.0.10/pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "character-encoding-utils"
+version = "0.0.10"
+description = "Some character encoding utils"
+readme = "README.md"
+license = "MIT"
+authors = [
+    { name = "TakWolf" },
+]
+maintainers = [
+    { name = "TakWolf" },
+]
+keywords = ["encoding", "gb2312", "big5", "shift-jis", "ksx1001"]
+requires-python = ">=3.10"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[dependency-groups]
+dev = [
+    "pytest>=8.4.2",
+]
+
+[build-system]
+requires = ["uv_build"]
+build-backend = "uv_build"

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/src/character_encoding_utils/big5.py

@@ -4,31 +4,35 @@ class Big5Exception(Exception):
 
 
 class Big5EncodeError(Big5Exception):
-    object: str
+    obj: str
     position: int
     reason: str
 
     def __init__(self, obj: str, position: int, reason: str):
-        super().__init__(f"'big5' codec can't encode character '\\u{ord(obj):x}' in position {position}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        return f"'big5' codec can't encode character '\\u{ord(self.obj):x}' in position {self.position}: {self.reason}"
+
 
 class Big5DecodeError(Big5Exception):
-    object: bytes
+    obj: bytes
     position: int
     reason: str
 
     def __init__(self, obj: bytes, position: int, reason: str):
-        if len(obj) <= 1:
-            super().__init__(f"'big5' codec can't decode byte 0x{obj[0]:x} in position {position}: {reason}")
-        else:
-            super().__init__(f"'big5' codec can't decode bytes in position {position}-{position + len(obj) - 1}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        if len(self.obj) <= 1:
+            return f"'big5' codec can't decode byte 0x{self.obj[0]:x} in position {self.position}: {self.reason}"
+        else:
+            return f"'big5' codec can't decode bytes in position {self.position}-{self.position + len(self.obj) - 1}: {self.reason}"
+
 
 def encode(cs: str) -> bytes:
     bs = bytearray()
@@ -110,9 +114,9 @@ def query_code(c: str) -> int:
     try:
         bs = encode(c)
     except Big5EncodeError as e:
-        raise Big5Exception(f"'{c}' is not a 'big5' character") from e
+        raise Big5Exception(f"'\\u{ord(c):x}' is not a 'big5' character") from e
     if len(bs) == 1:
-        raise Big5Exception(f"'{c}' is a ascii character")
+        raise Big5Exception(f"'\\u{ord(c):x}' is a ascii character")
     code = int(f'{bs[0]:02x}{bs[1]:02x}', 16)
     return code
 

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/src/character_encoding_utils/gb2312.py

@@ -7,31 +7,35 @@ class GB2312Exception(Exception):
 
 
 class GB2312EncodeError(GB2312Exception):
-    object: str
+    obj: str
     position: int
     reason: str
 
     def __init__(self, obj: str, position: int, reason: str):
-        super().__init__(f"'gb2312' codec can't encode character '\\u{ord(obj):x}' in position {position}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        return f"'gb2312' codec can't encode character '\\u{ord(self.obj):x}' in position {self.position}: {self.reason}"
+
 
 class GB2312DecodeError(GB2312Exception):
-    object: bytes
+    obj: bytes
     position: int
     reason: str
 
     def __init__(self, obj: bytes, position: int, reason: str):
-        if len(obj) <= 1:
-            super().__init__(f"'gb2312' codec can't decode byte 0x{obj[0]:x} in position {position}: {reason}")
-        else:
-            super().__init__(f"'gb2312' codec can't decode bytes in position {position}-{position + len(obj) - 1}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        if len(self.obj) <= 1:
+            return f"'gb2312' codec can't decode byte 0x{self.obj[0]:x} in position {self.position}: {self.reason}"
+        else:
+            return f"'gb2312' codec can't decode bytes in position {self.position}-{self.position + len(self.obj) - 1}: {self.reason}"
+
 
 def encode(cs: str) -> bytes:
     bs = bytearray()
@@ -72,9 +76,9 @@ def query_coord(c: str) -> tuple[int, int]:
     try:
         bs = encode(c)
     except GB2312EncodeError as e:
-        raise GB2312Exception(f"'{c}' is not a 'gb2312' character") from e
+        raise GB2312Exception(f"'\\u{ord(c):x}' is not a 'gb2312' character") from e
     if len(bs) == 1:
-        raise GB2312Exception(f"'{c}' is a ascii character")
+        raise GB2312Exception(f"'\\u{ord(c):x}' is a ascii character")
     row = bs[0] - _EUC_OFFSET
     col = bs[1] - _EUC_OFFSET
     return row, col

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/src/character_encoding_utils/ksx1001.py

@@ -7,31 +7,35 @@ class KSX1001Exception(Exception):
 
 
 class KSX1001EncodeError(KSX1001Exception):
-    object: str
+    obj: str
     position: int
     reason: str
 
     def __init__(self, obj: str, position: int, reason: str):
-        super().__init__(f"'ksx1001' codec can't encode character '\\u{ord(obj):x}' in position {position}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        return f"'ksx1001' codec can't encode character '\\u{ord(self.obj):x}' in position {self.position}: {self.reason}"
+
 
 class KSX1001DecodeError(KSX1001Exception):
-    object: bytes
+    obj: bytes
     position: int
     reason: str
 
     def __init__(self, obj: bytes, position: int, reason: str):
-        if len(obj) <= 1:
-            super().__init__(f"'ksx1001' codec can't decode byte 0x{obj[0]:x} in position {position}: {reason}")
-        else:
-            super().__init__(f"'ksx1001' codec can't decode bytes in position {position}-{position + len(obj) - 1}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        if len(self.obj) <= 1:
+            return f"'ksx1001' codec can't decode byte 0x{self.obj[0]:x} in position {self.position}: {self.reason}"
+        else:
+            return f"'ksx1001' codec can't decode bytes in position {self.position}-{self.position + len(self.obj) - 1}: {self.reason}"
+
 
 def encode(cs: str) -> bytes:
     bs = bytearray()
@@ -86,11 +90,11 @@ def query_coord(c: str) -> tuple[int, int]:
     try:
         bs = encode(c)
     except KSX1001EncodeError as e:
-        raise KSX1001Exception(f"'{c}' is not a 'ksx1001' character") from e
+        raise KSX1001Exception(f"'\\u{ord(c):x}' is not a 'ksx1001' character") from e
     if len(bs) == 1:
-        raise KSX1001Exception(f"'{c}' is a ascii character")
+        raise KSX1001Exception(f"'\\u{ord(c):x}' is a ascii character")
     elif bs.startswith(b'\xa4\xd4') and len(bs) > 2:
-        raise KSX1001Exception(f"'{c}' is not a 'ksx1001' character")
+        raise KSX1001Exception(f"'\\u{ord(c):x}' is not a 'ksx1001' character")
     row = bs[0] - _EUC_OFFSET
     col = bs[1] - _EUC_OFFSET
     return row, col

{character_encoding_utils-0.0.8 → character_encoding_utils-0.0.10}/src/character_encoding_utils/shiftjis.py

@@ -6,31 +6,35 @@ class ShiftJISException(Exception):
 
 
 class ShiftJISEncodeError(ShiftJISException):
-    object: str
+    obj: str
     position: int
     reason: str
 
     def __init__(self, obj: str, position: int, reason: str):
-        super().__init__(f"'shift-jis' codec can't encode character '\\u{ord(obj):x}' in position {position}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        return f"'shift-jis' codec can't encode character '\\u{ord(self.obj):x}' in position {self.position}: {self.reason}"
+
 
 class ShiftJISDecodeError(ShiftJISException):
-    object: bytes
+    obj: bytes
     position: int
     reason: str
 
     def __init__(self, obj: bytes, position: int, reason: str):
-        if len(obj) <= 1:
-            super().__init__(f"'shift-jis' codec can't decode byte 0x{obj[0]:x} in position {position}: {reason}")
-        else:
-            super().__init__(f"'shift-jis' codec can't decode bytes in position {position}-{position + len(obj) - 1}: {reason}")
-        self.object = obj
+        self.obj = obj
         self.position = position
         self.reason = reason
 
+    def __str__(self) -> str:
+        if len(self.obj) <= 1:
+            return f"'shift-jis' codec can't decode byte 0x{self.obj[0]:x} in position {self.position}: {self.reason}"
+        else:
+            return f"'shift-jis' codec can't decode bytes in position {self.position}-{self.position + len(self.obj) - 1}: {self.reason}"
+
 
 def encode(cs: str) -> bytes:
     bs = bytearray()

character_encoding_utils-0.0.8/.github/workflows/publish.yml

@@ -1,29 +0,0 @@
-name: Publish
-
-on:
-  release:
-    types: [published]
-
-jobs:
-  publish:
-    runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/project/character-encoding-utils/
-    permissions:
-      id-token: write
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v4
-    - name: Setup Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.x'
-    - name: Install dependencies
-      run: |
-        python -m pip install pip --upgrade
-        python -m pip install build
-    - name: Build
-      run: python -m build
-    - name: Publish
-      uses: pypa/gh-action-pypi-publish@release/v1

character_encoding_utils-0.0.8/.github/workflows/test.yml

@@ -1,24 +0,0 @@
-name: Test
-
-on: [push, pull_request]
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.10", "3.11", "3.12"]
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v4
-    - name: Setup Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install pip --upgrade
-        python -m pip install -r requirements.txt
-    - name: Test
-      run: python -m pytest

character_encoding_utils-0.0.8/.gitignore

@@ -1,141 +0,0 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-.idea/

character_encoding_utils-0.0.8/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2023 TakWolf
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.

character_encoding_utils-0.0.8/pyproject.toml

@@ -1,34 +0,0 @@
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[project]
-name = "character-encoding-utils"
-version = "0.0.8"
-description = "Some character encoding utils."
-readme = "README.md"
-license = { text = "MIT License" }
-requires-python = ">=3.10"
-authors = [
-    { name = "TakWolf" },
-]
-maintainers = [
-    { name = "TakWolf" },
-]
-keywords = ["encoding", "gb2312", "big5", "shift-jis", "ksx1001"]
-classifiers = [
-    "Programming Language :: Python :: 3",
-    "License :: OSI Approved :: MIT License",
-    "Operating System :: OS Independent",
-]
-
-[project.urls]
-homepage = "https://github.com/TakWolf/character-encoding-utils"
-source = "https://github.com/TakWolf/character-encoding-utils"
-issues = "https://github.com/TakWolf/character-encoding-utils/issues"
-
-[tool.pytest.ini_options]
-pythonpath = "src"
-addopts = [
-    "--import-mode=importlib",
-]

character_encoding_utils-0.0.8/requirements.txt

@@ -1 +0,0 @@
-pytest==8.2.0

character_encoding_utils-0.0.8/tests/test_big5.py

@@ -1,173 +0,0 @@
-import pytest
-
-from character_encoding_utils import big5
-from character_encoding_utils.big5 import Big5Exception, Big5EncodeError, Big5DecodeError
-
-
-def test_codec():
-    assert big5.encode('abc中國') == 'abc中國'.encode('big5')
-    assert big5.decode(b'abc\xa4\xa4\xb0\xea') == b'abc\xa4\xa4\xb0\xea'.decode('big5')
-
-    with pytest.raises(Big5EncodeError) as info:
-        big5.encode('abc가')
-    assert info.value.object == '가'
-    assert info.value.position == 3
-    assert info.value.reason == 'illegal multibyte sequence'
-
-    with pytest.raises(Big5DecodeError) as info:
-        big5.decode(b'abc\xa4\xa4\xb0')
-    assert info.value.object == b'\xb0'
-    assert info.value.position == 5
-    assert info.value.reason == 'incomplete multibyte sequence'
-
-    c = '〸'
-    assert ord(c) == 0x3038
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '〹'
-    assert ord(c) == 0x3039
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '〺'
-    assert ord(c) == 0x303A
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '十'
-    assert ord(c) == 0x5341
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '卄'
-    assert ord(c) == 0x5344
-    with pytest.raises(Big5EncodeError):
-        big5.encode(c)
-
-    c = '卅'
-    assert ord(c) == 0x5345
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '／'
-    assert ord(c) == 0xFF0F
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '＼'
-    assert ord(c) == 0xFF3C
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '∕'
-    assert ord(c) == 0x2215
-    assert big5.decode(big5.encode(c)) == c
-
-    c = '﹨'
-    assert ord(c) == 0xFE68
-    assert big5.decode(big5.encode(c)) == c
-
-
-def test_query_code():
-    assert big5.query_code('　') == 0xA140
-    assert big5.query_code('¢') == 0xA246
-    assert big5.query_code('一') == 0xA440
-    assert big5.query_code('訐') == 0xB050
-    assert big5.query_code('乂') == 0xC940
-    assert big5.query_code('綃') == 0xDF60
-
-    with pytest.raises(Big5Exception):
-        big5.query_code('abc')
-    with pytest.raises(Big5Exception):
-        big5.query_code('d')
-
-    with pytest.raises(Big5Exception) as info:
-        big5.query_code('가')
-    assert isinstance(info.value.__cause__, Big5EncodeError)
-
-
-def test_query_chr():
-    assert big5.query_chr(0xA140) == '　'
-    assert big5.query_chr(0xA246) == '¢'
-    assert big5.query_chr(0xA440) == '一'
-    assert big5.query_chr(0xB050) == '訐'
-    assert big5.query_chr(0xC940) == '乂'
-    assert big5.query_chr(0xDF60) == '綃'
-
-    with pytest.raises(Big5Exception) as info:
-        big5.query_chr(0xA000)
-    assert isinstance(info.value.__cause__, Big5DecodeError)
-    with pytest.raises(Big5Exception) as info:
-        big5.query_chr(0xFFFF)
-    assert isinstance(info.value.__cause__, Big5DecodeError)
-
-
-def test_query_category():
-    categories = big5.get_categories()
-    assert len(categories) == 3
-    assert 'other' in categories
-    assert 'level-1' in categories
-    assert 'level-2' in categories
-
-    assert big5.query_category('■') == 'other'
-    assert big5.query_category('一') == 'level-1'
-    assert big5.query_category('乂') == 'level-2'
-    assert big5.query_category('A') is None
-    assert big5.query_category('가') is None
-
-
-def test_alphabet():
-    alphabet = big5.get_alphabet_other()
-    assert len(alphabet) == 408
-    for c in alphabet:
-        code = big5.query_code(c)
-        assert big5.query_chr(code) == c
-        assert big5.query_category(c) == 'other'
-
-    alphabet = big5.get_alphabet_level_1()
-    assert len(alphabet) == 5401
-    for c in alphabet:
-        code = big5.query_code(c)
-        assert big5.query_chr(code) == c
-        assert big5.query_category(c) == 'level-1'
-
-    alphabet = big5.get_alphabet_level_2()
-    assert len(alphabet) == 7652
-    for c in alphabet:
-        code = big5.query_code(c)
-        assert big5.query_chr(code) == c
-        assert big5.query_category(c) == 'level-2'
-
-    alphabet = big5.get_alphabet()
-    assert len(alphabet) == 13461
-    for c in alphabet:
-        code = big5.query_code(c)
-        assert big5.query_chr(code) == c
-        assert big5.query_category(c) is not None
-
-
-def test_count():
-    assert big5.get_other_count() == 408
-    assert big5.get_level_1_count() == 5401
-    assert big5.get_level_2_count() == 7652
-    assert big5.get_count() == 13461
-
-
-def test_unicode():
-    alphabet_other = []
-    alphabet_level_1 = []
-    alphabet_level_2 = []
-    alphabet = []
-
-    for code_point in range(0, 0x10FFFF + 1):
-        c = chr(code_point)
-        category = big5.query_category(c)
-
-        if category == 'other':
-            alphabet_other.append(c)
-        elif category == 'level-1':
-            alphabet_level_1.append(c)
-        elif category == 'level-2':
-            alphabet_level_2.append(c)
-
-        if category is not None:
-            alphabet.append(c)
-
-    assert len(alphabet_other) == big5.get_other_count()
-    assert len(alphabet_level_1) == big5.get_level_1_count()
-    assert len(alphabet_level_2) == big5.get_level_2_count()
-    assert len(alphabet) == big5.get_count()

character_encoding_utils-0.0.8/tests/test_gb2312.py

@@ -1,131 +0,0 @@
-import pytest
-
-from character_encoding_utils import gb2312
-from character_encoding_utils.gb2312 import GB2312Exception, GB2312EncodeError, GB2312DecodeError
-
-
-def test_codec():
-    assert gb2312.encode('abc中国') == 'abc中国'.encode('gb2312')
-    assert gb2312.decode(b'abc\xd6\xd0\xb9\xfa') == b'abc\xd6\xd0\xb9\xfa'.decode('gb2312')
-
-    with pytest.raises(GB2312EncodeError) as info:
-        gb2312.encode('abc가')
-    assert info.value.object == '가'
-    assert info.value.position == 3
-    assert info.value.reason == 'illegal multibyte sequence'
-
-    with pytest.raises(GB2312DecodeError) as info:
-        gb2312.decode(b'abc\xd6\xd0\xb9')
-    assert info.value.object == b'\xb9'
-    assert info.value.position == 5
-    assert info.value.reason == 'incomplete multibyte sequence'
-
-
-def test_query_coord():
-    assert gb2312.query_coord('＄') == (1, 71)
-    assert gb2312.query_coord('拿') == (36, 35)
-    assert gb2312.query_coord('贽') == (74, 62)
-    assert gb2312.query_coord('魍') == (87, 45)
-
-    with pytest.raises(GB2312Exception):
-        gb2312.query_coord('abc')
-    with pytest.raises(GB2312Exception):
-        gb2312.query_coord('d')
-
-    with pytest.raises(GB2312Exception) as info:
-        gb2312.query_coord('가')
-    assert isinstance(info.value.__cause__, GB2312EncodeError)
-
-
-def test_query_chr():
-    assert gb2312.query_chr(1, 79) == '★'
-    assert gb2312.query_chr(16, 1) == '啊'
-    assert gb2312.query_chr(26, 26) == '汉'
-    assert gb2312.query_chr(55, 54) == '字'
-    assert gb2312.query_chr(87, 94) == '齄'
-
-    with pytest.raises(GB2312Exception):
-        gb2312.query_chr(-1, 50)
-    with pytest.raises(GB2312Exception):
-        gb2312.query_chr(20, 500)
-
-    with pytest.raises(GB2312Exception) as info:
-        gb2312.query_chr(94, 94)
-    assert isinstance(info.value.__cause__, GB2312DecodeError)
-
-
-def test_query_category():
-    categories = gb2312.get_categories()
-    assert len(categories) == 3
-    assert 'other' in categories
-    assert 'level-1' in categories
-    assert 'level-2' in categories
-
-    assert gb2312.query_category('■') == 'other'
-    assert gb2312.query_category('闭') == 'level-1'
-    assert gb2312.query_category('踔') == 'level-2'
-    assert gb2312.query_category('A') is None
-    assert gb2312.query_category('가') is None
-
-
-def test_alphabet():
-    alphabet = gb2312.get_alphabet_other()
-    assert len(alphabet) == 682
-    for c in alphabet:
-        row, col = gb2312.query_coord(c)
-        assert gb2312.query_chr(row, col) == c
-        assert gb2312.query_category(c) == 'other'
-
-    alphabet = gb2312.get_alphabet_level_1()
-    assert len(alphabet) == 3755
-    for c in alphabet:
-        row, col = gb2312.query_coord(c)
-        assert gb2312.query_chr(row, col) == c
-        assert gb2312.query_category(c) == 'level-1'
-
-    alphabet = gb2312.get_alphabet_level_2()
-    assert len(alphabet) == 3008
-    for c in alphabet:
-        row, col = gb2312.query_coord(c)
-        assert gb2312.query_chr(row, col) == c
-        assert gb2312.query_category(c) == 'level-2'
-
-    alphabet = gb2312.get_alphabet()
-    assert len(alphabet) == 7445
-    for c in alphabet:
-        row, col = gb2312.query_coord(c)
-        assert gb2312.query_chr(row, col) == c
-        assert gb2312.query_category(c) is not None
-
-
-def test_count():
-    assert gb2312.get_other_count() == 682
-    assert gb2312.get_level_1_count() == 3755
-    assert gb2312.get_level_2_count() == 3008
-    assert gb2312.get_count() == 7445
-
-
-def test_unicode():
-    alphabet_other = []
-    alphabet_level_1 = []
-    alphabet_level_2 = []
-    alphabet = []
-
-    for code_point in range(0, 0x10FFFF + 1):
-        c = chr(code_point)
-        category = gb2312.query_category(c)
-
-        if category == 'other':
-            alphabet_other.append(c)
-        elif category == 'level-1':
-            alphabet_level_1.append(c)
-        elif category == 'level-2':
-            alphabet_level_2.append(c)
-
-        if category is not None:
-            alphabet.append(c)
-
-    assert len(alphabet_other) == gb2312.get_other_count()
-    assert len(alphabet_level_1) == gb2312.get_level_1_count()
-    assert len(alphabet_level_2) == gb2312.get_level_2_count()
-    assert len(alphabet) == gb2312.get_count()

character_encoding_utils-0.0.8/tests/test_ksx1001.py

@@ -1,139 +0,0 @@
-import pytest
-
-from character_encoding_utils import ksx1001
-from character_encoding_utils.ksx1001 import KSX1001Exception, KSX1001EncodeError, KSX1001DecodeError
-
-
-def test_codec():
-    assert ksx1001.encode('abc가쳰') == 'abc가쳰'.encode('ksx1001')
-    assert ksx1001.decode(b'abc\xb0\xa1\xc3\xc8') == b'abc\xb0\xa1\xc3\xc8'.decode('ksx1001')
-
-    with pytest.raises(KSX1001EncodeError) as info:
-        ksx1001.encode('abc😈')
-    assert info.value.object == '😈'
-    assert info.value.position == 3
-    assert info.value.reason == 'illegal multibyte sequence'
-
-    with pytest.raises(KSX1001DecodeError) as info:
-        ksx1001.decode(b'abc\xb0\xa1\xc3')
-    assert info.value.object == b'\xc3'
-    assert info.value.position == 5
-    assert info.value.reason == 'incomplete multibyte sequence'
-
-    assert ksx1001.decode(ksx1001.encode(chr(0x3164))) == chr(0x3164)
-
-    for code_point in range(0xAC00, 0xD7A4):
-        c = chr(code_point)
-        assert ksx1001.decode(ksx1001.encode(c)) == c
-
-
-def test_query_coord():
-    assert ksx1001.query_coord('ㆌ') == (4, 92)
-    assert ksx1001.query_coord('φ') == (5, 85)
-    assert ksx1001.query_coord('떰') == (22, 22)
-    assert ksx1001.query_coord('틘') == (38, 24)
-    assert ksx1001.query_coord('紺') == (42, 90)
-    assert ksx1001.query_coord('絿') == (47, 29)
-
-    with pytest.raises(KSX1001Exception):
-        ksx1001.query_coord('abc')
-    with pytest.raises(KSX1001Exception):
-        ksx1001.query_coord('d')
-
-    with pytest.raises(KSX1001Exception) as info:
-        ksx1001.query_coord('😈')
-    assert isinstance(info.value.__cause__, KSX1001EncodeError)
-
-
-def test_query_chr():
-    assert ksx1001.query_chr(1, 50) == '⌒'
-    assert ksx1001.query_chr(16, 1) == '가'
-    assert ksx1001.query_chr(35, 40) == '쳰'
-    assert ksx1001.query_chr(50, 54) == '壟'
-    assert ksx1001.query_chr(93, 94) == '詰'
-
-    with pytest.raises(KSX1001Exception):
-        ksx1001.query_chr(-1, 50)
-    with pytest.raises(KSX1001Exception):
-        ksx1001.query_chr(20, 500)
-
-    with pytest.raises(KSX1001Exception) as info:
-        ksx1001.query_chr(94, 94)
-    assert isinstance(info.value.__cause__, KSX1001DecodeError)
-
-
-def test_query_category():
-    categories = ksx1001.get_categories()
-    assert len(categories) == 3
-    assert 'other' in categories
-    assert 'syllable' in categories
-    assert 'hanja' in categories
-
-    assert ksx1001.query_category('ぜ') == 'other'
-    assert ksx1001.query_category('룝') == 'syllable'
-    assert ksx1001.query_category('絿') == 'hanja'
-    assert ksx1001.query_category('A') is None
-    assert ksx1001.query_category('😈') is None
-
-
-def test_alphabet():
-    alphabet = ksx1001.get_alphabet_other()
-    assert len(alphabet) == 988
-    for c in alphabet:
-        row, col = ksx1001.query_coord(c)
-        assert ksx1001.query_chr(row, col) == c
-        assert ksx1001.query_category(c) == 'other'
-
-    alphabet = ksx1001.get_alphabet_syllable()
-    assert len(alphabet) == 2350
-    for c in alphabet:
-        row, col = ksx1001.query_coord(c)
-        assert ksx1001.query_chr(row, col) == c
-        assert ksx1001.query_category(c) == 'syllable'
-
-    alphabet = ksx1001.get_alphabet_hanja()
-    assert len(alphabet) == 4888
-    for c in alphabet:
-        row, col = ksx1001.query_coord(c)
-        assert ksx1001.query_chr(row, col) == c
-        assert ksx1001.query_category(c) == 'hanja'
-
-    alphabet = ksx1001.get_alphabet()
-    assert len(alphabet) == 8226
-    for c in alphabet:
-        row, col = ksx1001.query_coord(c)
-        assert ksx1001.query_chr(row, col) == c
-        assert ksx1001.query_category(c) is not None
-
-
-def test_count():
-    assert ksx1001.get_other_count() == 988
-    assert ksx1001.get_syllable_count() == 2350
-    assert ksx1001.get_hanja_count() == 4888
-    assert ksx1001.get_count() == 8226
-
-
-def test_unicode():
-    alphabet_other = []
-    alphabet_syllable = []
-    alphabet_hanja = []
-    alphabet = []
-
-    for code_point in range(0, 0x10FFFF + 1):
-        c = chr(code_point)
-        category = ksx1001.query_category(c)
-
-        if category == 'other':
-            alphabet_other.append(c)
-        elif category == 'syllable':
-            alphabet_syllable.append(c)
-        elif category == 'hanja':
-            alphabet_hanja.append(c)
-
-        if category is not None:
-            alphabet.append(c)
-
-    assert len(alphabet_other) == ksx1001.get_other_count()
-    assert len(alphabet_syllable) == ksx1001.get_syllable_count()
-    assert len(alphabet_hanja) == ksx1001.get_hanja_count()
-    assert len(alphabet) == ksx1001.get_count()

character_encoding_utils-0.0.8/tests/test_shiftjis.py

@@ -1,130 +0,0 @@
-import pytest
-
-from character_encoding_utils import shiftjis
-from character_encoding_utils.shiftjis import ShiftJISEncodeError, ShiftJISDecodeError
-
-
-def test_codec():
-    assert shiftjis.encode('abc日本') == 'abc日本'.encode('shift-jis')
-    assert shiftjis.decode(b'abc\x93\xfa\x96\x7b') == b'abc\x93\xfa\x96\x7b'.decode('shift-jis')
-
-    with pytest.raises(ShiftJISEncodeError) as info:
-        shiftjis.encode('abc가')
-    assert info.value.object == '가'
-    assert info.value.position == 3
-    assert info.value.reason == 'illegal multibyte sequence'
-
-    with pytest.raises(ShiftJISDecodeError) as info:
-        shiftjis.decode(b'abc\x93\xfa\x96')
-    assert info.value.object == b'\x96'
-    assert info.value.position == 5
-    assert info.value.reason == 'incomplete multibyte sequence'
-
-    with pytest.raises(ShiftJISEncodeError) as info:
-        shiftjis.encode('\\')
-    assert info.value.object == '\\'
-    assert info.value.position == 0
-    assert '\\' in info.value.reason
-    assert '¥' in info.value.reason
-
-    with pytest.raises(ShiftJISEncodeError) as info:
-        shiftjis.encode('~')
-    assert info.value.object == '~'
-    assert info.value.position == 0
-    assert '~' in info.value.reason
-    assert '‾' in info.value.reason
-
-    assert shiftjis.decode(shiftjis.encode('¥')) == '¥'
-    assert shiftjis.decode(shiftjis.encode('‾')) == '‾'
-
-
-def test_query_category():
-    categories = shiftjis.get_categories()
-    assert len(categories) == 5
-    assert 'single-byte-ascii-control' in categories
-    assert 'single-byte-ascii-printable' in categories
-    assert 'single-byte-half-width-katakana' in categories
-    assert 'double-byte-other' in categories
-    assert 'double-byte-kanji' in categories
-
-    assert shiftjis.query_category('\n') == 'single-byte-ascii-control'
-    assert shiftjis.query_category('A') == 'single-byte-ascii-printable'
-    assert shiftjis.query_category('ｱ') == 'single-byte-half-width-katakana'
-    assert shiftjis.query_category('あ') == 'double-byte-other'
-    assert shiftjis.query_category('辻') == 'double-byte-kanji'
-    assert shiftjis.query_category('가') is None
-
-
-def test_alphabet():
-    alphabet = shiftjis.get_alphabet_single_byte_ascii_control()
-    assert len(alphabet) == 33
-    for c in alphabet:
-        assert shiftjis.query_category(c) == 'single-byte-ascii-control'
-
-    alphabet = shiftjis.get_alphabet_single_byte_ascii_printable()
-    assert len(alphabet) == 95
-    for c in alphabet:
-        assert shiftjis.query_category(c) == 'single-byte-ascii-printable'
-
-    alphabet = shiftjis.get_alphabet_single_byte_half_width_katakana()
-    assert len(alphabet) == 63
-    for c in alphabet:
-        assert shiftjis.query_category(c) == 'single-byte-half-width-katakana'
-
-    alphabet = shiftjis.get_alphabet_double_byte_other()
-    assert len(alphabet) == 524
-    for c in alphabet:
-        assert shiftjis.query_category(c) == 'double-byte-other'
-
-    alphabet = shiftjis.get_alphabet_double_byte_kanji()
-    assert len(alphabet) == 6355
-    for c in alphabet:
-        assert shiftjis.query_category(c) == 'double-byte-kanji'
-
-    alphabet = shiftjis.get_alphabet()
-    assert len(alphabet) == 7070
-    for c in alphabet:
-        assert shiftjis.query_category(c) is not None
-
-
-def test_count():
-    assert shiftjis.get_single_byte_ascii_control_count() == 33
-    assert shiftjis.get_single_byte_ascii_printable_count() == 95
-    assert shiftjis.get_single_byte_half_width_katakana_count() == 63
-    assert shiftjis.get_double_byte_other_count() == 524
-    assert shiftjis.get_double_byte_kanji_count() == 6355
-    assert shiftjis.get_count() == 7070
-
-
-def test_unicode():
-    alphabet_single_byte_ascii_control = []
-    alphabet_single_byte_ascii_printable = []
-    alphabet_single_byte_half_width_katakana = []
-    alphabet_double_byte_other = []
-    alphabet_double_byte_kanji = []
-    alphabet = []
-
-    for code_point in range(0, 0x10FFFF + 1):
-        c = chr(code_point)
-        category = shiftjis.query_category(c)
-
-        if category == 'single-byte-ascii-control':
-            alphabet_single_byte_ascii_control.append(c)
-        elif category == 'single-byte-ascii-printable':
-            alphabet_single_byte_ascii_printable.append(c)
-        elif category == 'single-byte-half-width-katakana':
-            alphabet_single_byte_half_width_katakana.append(c)
-        elif category == 'double-byte-other':
-            alphabet_double_byte_other.append(c)
-        elif category == 'double-byte-kanji':
-            alphabet_double_byte_kanji.append(c)
-
-        if category is not None:
-            alphabet.append(c)
-
-    assert len(alphabet_single_byte_ascii_control) == shiftjis.get_single_byte_ascii_control_count()
-    assert len(alphabet_single_byte_ascii_printable) == shiftjis.get_single_byte_ascii_printable_count()
-    assert len(alphabet_single_byte_half_width_katakana) == shiftjis.get_single_byte_half_width_katakana_count()
-    assert len(alphabet_double_byte_other) == shiftjis.get_double_byte_other_count()
-    assert len(alphabet_double_byte_kanji) == shiftjis.get_double_byte_kanji_count()
-    assert len(alphabet) == shiftjis.get_count()