character-encoding-utils 0.0.12__tar.gz → 0.0.13__tar.gz

character_encoding_utils-0.0.13/LICENSE

@@ -0,0 +1,21 @@
+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-0.0.12 → character_encoding_utils-0.0.13}/PKG-INFO

@@ -1,29 +1,30 @@
 Metadata-Version: 2.4
 Name: character-encoding-utils
-Version: 0.0.12
+Version: 0.0.13
 Summary: Some character encoding utils
 Keywords: encoding,gb2312,big5,shift-jis,ksx1001
 Author: TakWolf
 License-Expression: MIT
+License-File: LICENSE
 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: Programming Language :: Python :: 3.15
 Classifier: Operating System :: OS Independent
 Maintainer: TakWolf
 Requires-Python: >=3.10
 Project-URL: Homepage, https://github.com/TakWolf/character-encoding-utils
-Project-URL: Issues, https://github.com/TakWolf/character-encoding-utils/issues
 Project-URL: Source, https://github.com/TakWolf/character-encoding-utils
+Project-URL: Issues, https://github.com/TakWolf/character-encoding-utils/issues
 Description-Content-Type: text/markdown
 
 # Character Encoding Utils
 
-[![Python](https://img.shields.io/badge/python-3.10-brightgreen)](https://www.python.org)
-[![PyPI](https://img.shields.io/pypi/v/character-encoding-utils)](https://pypi.org/project/character-encoding-utils/)
+[![Python](https://img.shields.io/badge/python-3.10-brightgreen?style=flat-square)](https://www.python.org)
+[![PyPI](https://img.shields.io/pypi/v/character-encoding-utils?style=flat-square)](https://pypi.org/project/character-encoding-utils/)
 
 Some [character encoding](https://en.wikipedia.org/wiki/Character_encoding) utils.
 

{character_encoding_utils-0.0.12 → character_encoding_utils-0.0.13}/README.md

@@ -1,7 +1,7 @@
 # Character Encoding Utils
 
-[![Python](https://img.shields.io/badge/python-3.10-brightgreen)](https://www.python.org)
-[![PyPI](https://img.shields.io/pypi/v/character-encoding-utils)](https://pypi.org/project/character-encoding-utils/)
+[![Python](https://img.shields.io/badge/python-3.10-brightgreen?style=flat-square)](https://www.python.org)
+[![PyPI](https://img.shields.io/pypi/v/character-encoding-utils?style=flat-square)](https://pypi.org/project/character-encoding-utils/)
 
 Some [character encoding](https://en.wikipedia.org/wiki/Character_encoding) utils.
 

character_encoding_utils-0.0.13/pyproject.toml

@@ -0,0 +1,46 @@
+[project]
+name = "character-encoding-utils"
+version = "0.0.13"
+description = "Some character encoding utils"
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+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",
+    "Programming Language :: Python :: 3.15",
+    "Operating System :: OS Independent",
+]
+
+[[project.authors]]
+name = "TakWolf"
+
+[[project.maintainers]]
+name = "TakWolf"
+
+[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"
+
+[dependency-groups]
+dev = ["pytest>=9.1.1"]
+
+[build-system]
+requires = ["uv_build"]
+build-backend = "uv_build"
+
+[tool.pytest.ini_options]
+addopts = ["--import-mode=importlib"]

character_encoding_utils-0.0.12/pyproject.toml → character_encoding_utils-0.0.13/pyproject.toml.orig

@@ -1,13 +1,10 @@
-[build-system]
-requires = ["uv_build"]
-build-backend = "uv_build"
-
 [project]
 name = "character-encoding-utils"
-version = "0.0.12"
+version = "0.0.13"
 description = "Some character encoding utils"
 readme = "README.md"
 license = "MIT"
+license-files = ["LICENSE"]
 authors = [
     { name = "TakWolf" },
 ]
@@ -23,16 +20,25 @@ classifiers = [
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: 3.14",
-    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.15",
     "Operating System :: OS Independent",
 ]
 
 [dependency-groups]
 dev = [
-    "pytest>=9.0.2",
+    "pytest>=9.1.1",
 ]
 
 [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"
+
+[build-system]
+requires = ["uv_build"]
+build-backend = "uv_build"
+
+[tool.pytest.ini_options]
+addopts = [
+    "--import-mode=importlib",
+]

{character_encoding_utils-0.0.12 → character_encoding_utils-0.0.13}/src/character_encoding_utils/big5.py

@@ -8,7 +8,7 @@ class Big5EncodeError(Big5Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: str, position: int, reason: str):
+    def __init__(self, obj: str, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -22,7 +22,7 @@ class Big5DecodeError(Big5Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: bytes, position: int, reason: str):
+    def __init__(self, obj: bytes, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -112,7 +112,7 @@ def decode(bs: bytes | bytearray) -> str:
 
 def query_code(c: str) -> int:
     if len(c) != 1:
-        raise Big5Exception('Must be one character')
+        raise Big5Exception('must be one character')
     try:
         bs = encode(c)
     except Big5EncodeError as e:
@@ -160,39 +160,39 @@ def _build_alphabet_by_codes_between(code_start: int, code_end: int) -> list[str
     return alphabet
 
 
-_alphabet_other = _build_alphabet_by_codes_between(0xA140, 0xA3BF)
-_alphabet_level_1 = _build_alphabet_by_codes_between(0xA440, 0xC67E)
-_alphabet_level_2 = _build_alphabet_by_codes_between(0xC940, 0xF9D5)
-_alphabet = _alphabet_other + _alphabet_level_1 + _alphabet_level_2
+_ALPHABET_OTHER = _build_alphabet_by_codes_between(0xA140, 0xA3BF)
+_ALPHABET_LEVEL_1 = _build_alphabet_by_codes_between(0xA440, 0xC67E)
+_ALPHABET_LEVEL_2 = _build_alphabet_by_codes_between(0xC940, 0xF9D5)
+_ALPHABET = _ALPHABET_OTHER + _ALPHABET_LEVEL_1 + _ALPHABET_LEVEL_2
 
 
 def get_alphabet_other() -> list[str]:
-    return list(_alphabet_other)
+    return _ALPHABET_OTHER.copy()
 
 
 def get_alphabet_level_1() -> list[str]:
-    return list(_alphabet_level_1)
+    return _ALPHABET_LEVEL_1.copy()
 
 
 def get_alphabet_level_2() -> list[str]:
-    return list(_alphabet_level_2)
+    return _ALPHABET_LEVEL_2.copy()
 
 
 def get_alphabet() -> list[str]:
-    return list(_alphabet)
+    return _ALPHABET.copy()
 
 
 def get_other_count() -> int:
-    return len(_alphabet_other)
+    return len(_ALPHABET_OTHER)
 
 
 def get_level_1_count() -> int:
-    return len(_alphabet_level_1)
+    return len(_ALPHABET_LEVEL_1)
 
 
 def get_level_2_count() -> int:
-    return len(_alphabet_level_2)
+    return len(_ALPHABET_LEVEL_2)
 
 
 def get_count() -> int:
-    return len(_alphabet)
+    return len(_ALPHABET)

{character_encoding_utils-0.0.12 → character_encoding_utils-0.0.13}/src/character_encoding_utils/gb2312.py

@@ -11,7 +11,7 @@ class GB2312EncodeError(GB2312Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: str, position: int, reason: str):
+    def __init__(self, obj: str, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -25,7 +25,7 @@ class GB2312DecodeError(GB2312Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: bytes, position: int, reason: str):
+    def __init__(self, obj: bytes, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -72,7 +72,7 @@ def decode(bs: bytes | bytearray) -> str:
 
 def query_coord(c: str) -> tuple[int, int]:
     if len(c) != 1:
-        raise GB2312Exception('Must be one character')
+        raise GB2312Exception('must be one character')
     try:
         bs = encode(c)
     except GB2312EncodeError as e:
@@ -124,39 +124,39 @@ def _build_alphabet_by_rows_between(row_start: int, row_end: int) -> list[str]:
     return alphabet
 
 
-_alphabet_other = _build_alphabet_by_rows_between(1, 9)
-_alphabet_level_1 = _build_alphabet_by_rows_between(16, 55)
-_alphabet_level_2 = _build_alphabet_by_rows_between(56, 87)
-_alphabet = _alphabet_other + _alphabet_level_1 + _alphabet_level_2
+_ALPHABET_OTHER = _build_alphabet_by_rows_between(1, 9)
+_ALPHABET_LEVEL_1 = _build_alphabet_by_rows_between(16, 55)
+_ALPHABET_LEVEL_2 = _build_alphabet_by_rows_between(56, 87)
+_ALPHABET = _ALPHABET_OTHER + _ALPHABET_LEVEL_1 + _ALPHABET_LEVEL_2
 
 
 def get_alphabet_other() -> list[str]:
-    return list(_alphabet_other)
+    return _ALPHABET_OTHER.copy()
 
 
 def get_alphabet_level_1() -> list[str]:
-    return list(_alphabet_level_1)
+    return _ALPHABET_LEVEL_1.copy()
 
 
 def get_alphabet_level_2() -> list[str]:
-    return list(_alphabet_level_2)
+    return _ALPHABET_LEVEL_2.copy()
 
 
 def get_alphabet() -> list[str]:
-    return list(_alphabet)
+    return _ALPHABET.copy()
 
 
 def get_other_count() -> int:
-    return len(_alphabet_other)
+    return len(_ALPHABET_OTHER)
 
 
 def get_level_1_count() -> int:
-    return len(_alphabet_level_1)
+    return len(_ALPHABET_LEVEL_1)
 
 
 def get_level_2_count() -> int:
-    return len(_alphabet_level_2)
+    return len(_ALPHABET_LEVEL_2)
 
 
 def get_count() -> int:
-    return len(_alphabet)
+    return len(_ALPHABET)

{character_encoding_utils-0.0.12 → character_encoding_utils-0.0.13}/src/character_encoding_utils/ksx1001.py

@@ -11,7 +11,7 @@ class KSX1001EncodeError(KSX1001Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: str, position: int, reason: str):
+    def __init__(self, obj: str, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -25,7 +25,7 @@ class KSX1001DecodeError(KSX1001Exception):
     position: int
     reason: str
 
-    def __init__(self, obj: bytes, position: int, reason: str):
+    def __init__(self, obj: bytes, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -41,7 +41,7 @@ def encode(cs: str) -> bytes:
     bs = bytearray()
     for position, c in enumerate(cs):
         try:
-            bs.extend(c.encode('ksx1001'))
+            bs.extend(c.encode('euc_kr'))
         except UnicodeEncodeError as e:
             raise KSX1001EncodeError(c, position, e.reason) from e
     return bytes(bs)
@@ -77,7 +77,7 @@ def decode(bs: bytes | bytearray) -> str:
             cs.append(chr(0x3164))  # Hangul Filler
         else:
             try:
-                cs.append(bc.decode('ksx1001'))
+                cs.append(bc.decode('euc_kr'))
             except UnicodeDecodeError as e:
                 raise KSX1001DecodeError(bc, passed, e.reason) from e
         passed += len(bc)
@@ -86,7 +86,7 @@ def decode(bs: bytes | bytearray) -> str:
 
 def query_coord(c: str) -> tuple[int, int]:
     if len(c) != 1:
-        raise KSX1001Exception('Must be one character')
+        raise KSX1001Exception('must be one character')
     try:
         bs = encode(c)
     except KSX1001EncodeError as e:
@@ -100,7 +100,7 @@ def query_coord(c: str) -> tuple[int, int]:
     return row, col
 
 
-def query_chr(row: int, col: int):
+def query_chr(row: int, col: int) -> str:
     if row < 1 or row > 94 or col < 1 or col > 94:
         raise KSX1001Exception(f"'row' and 'col' must between 1 and 94")
     try:
@@ -140,39 +140,39 @@ def _build_alphabet_by_rows_between(row_start: int, row_end: int) -> list[str]:
     return alphabet
 
 
-_alphabet_other = _build_alphabet_by_rows_between(1, 12)
-_alphabet_syllable = _build_alphabet_by_rows_between(16, 40)
-_alphabet_hanja = _build_alphabet_by_rows_between(42, 93)
-_alphabet = _alphabet_other + _alphabet_syllable + _alphabet_hanja
+_ALPHABET_OTHER = _build_alphabet_by_rows_between(1, 12)
+_ALPHABET_SYLLABLE = _build_alphabet_by_rows_between(16, 40)
+_ALPHABET_HANJA = _build_alphabet_by_rows_between(42, 93)
+_ALPHABET = _ALPHABET_OTHER + _ALPHABET_SYLLABLE + _ALPHABET_HANJA
 
 
 def get_alphabet_other() -> list[str]:
-    return list(_alphabet_other)
+    return _ALPHABET_OTHER.copy()
 
 
 def get_alphabet_syllable() -> list[str]:
-    return list(_alphabet_syllable)
+    return _ALPHABET_SYLLABLE.copy()
 
 
 def get_alphabet_hanja() -> list[str]:
-    return list(_alphabet_hanja)
+    return _ALPHABET_HANJA.copy()
 
 
 def get_alphabet() -> list[str]:
-    return list(_alphabet)
+    return _ALPHABET.copy()
 
 
 def get_other_count() -> int:
-    return len(_alphabet_other)
+    return len(_ALPHABET_OTHER)
 
 
 def get_syllable_count() -> int:
-    return len(_alphabet_syllable)
+    return len(_ALPHABET_SYLLABLE)
 
 
 def get_hanja_count() -> int:
-    return len(_alphabet_hanja)
+    return len(_ALPHABET_HANJA)
 
 
 def get_count() -> int:
-    return len(_alphabet)
+    return len(_ALPHABET)

{character_encoding_utils-0.0.12 → character_encoding_utils-0.0.13}/src/character_encoding_utils/shiftjis.py

@@ -10,7 +10,7 @@ class ShiftJISEncodeError(ShiftJISException):
     position: int
     reason: str
 
-    def __init__(self, obj: str, position: int, reason: str):
+    def __init__(self, obj: str, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -24,7 +24,7 @@ class ShiftJISDecodeError(ShiftJISException):
     position: int
     reason: str
 
-    def __init__(self, obj: bytes, position: int, reason: str):
+    def __init__(self, obj: bytes, position: int, reason: str) -> None:
         self.obj = obj
         self.position = position
         self.reason = reason
@@ -172,58 +172,58 @@ def _build_alphabet_double_byte_kanji() -> list[str]:
     return alphabet
 
 
-_alphabet_single_byte_ascii_control = _build_alphabet_single_byte(0x00, 0x1F)
-_alphabet_single_byte_ascii_control.append(chr(0x7F))
-_alphabet_single_byte_ascii_printable = _build_alphabet_single_byte(0x20, 0x7E)
-_alphabet_single_byte_half_width_katakana = _build_alphabet_single_byte(0xA1, 0xDF)
-_alphabet_double_byte_other = _build_alphabet_double_byte_other()
-_alphabet_double_byte_kanji = _build_alphabet_double_byte_kanji()
-_alphabet = _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_SINGLE_BYTE_ASCII_CONTROL = _build_alphabet_single_byte(0x00, 0x1F)
+_ALPHABET_SINGLE_BYTE_ASCII_CONTROL.append(chr(0x7F))
+_ALPHABET_SINGLE_BYTE_ASCII_PRINTABLE = _build_alphabet_single_byte(0x20, 0x7E)
+_ALPHABET_SINGLE_BYTE_HALF_WIDTH_KATAKANA = _build_alphabet_single_byte(0xA1, 0xDF)
+_ALPHABET_DOUBLE_BYTE_OTHER = _build_alphabet_double_byte_other()
+_ALPHABET_DOUBLE_BYTE_KANJI = _build_alphabet_double_byte_kanji()
+_ALPHABET = _ALPHABET_SINGLE_BYTE_ASCII_CONTROL + _ALPHABET_SINGLE_BYTE_ASCII_PRINTABLE + _ALPHABET_SINGLE_BYTE_HALF_WIDTH_KATAKANA + _ALPHABET_DOUBLE_BYTE_OTHER + _ALPHABET_DOUBLE_BYTE_KANJI
 
 
 def get_alphabet_single_byte_ascii_control() -> list[str]:
-    return list(_alphabet_single_byte_ascii_control)
+    return _ALPHABET_SINGLE_BYTE_ASCII_CONTROL.copy()
 
 
 def get_alphabet_single_byte_ascii_printable() -> list[str]:
-    return list(_alphabet_single_byte_ascii_printable)
+    return _ALPHABET_SINGLE_BYTE_ASCII_PRINTABLE.copy()
 
 
 def get_alphabet_single_byte_half_width_katakana() -> list[str]:
-    return list(_alphabet_single_byte_half_width_katakana)
+    return _ALPHABET_SINGLE_BYTE_HALF_WIDTH_KATAKANA.copy()
 
 
 def get_alphabet_double_byte_other() -> list[str]:
-    return list(_alphabet_double_byte_other)
+    return _ALPHABET_DOUBLE_BYTE_OTHER.copy()
 
 
 def get_alphabet_double_byte_kanji() -> list[str]:
-    return list(_alphabet_double_byte_kanji)
+    return _ALPHABET_DOUBLE_BYTE_KANJI.copy()
 
 
 def get_alphabet() -> list[str]:
-    return list(_alphabet)
+    return _ALPHABET.copy()
 
 
 def get_single_byte_ascii_control_count() -> int:
-    return len(_alphabet_single_byte_ascii_control)
+    return len(_ALPHABET_SINGLE_BYTE_ASCII_CONTROL)
 
 
 def get_single_byte_ascii_printable_count() -> int:
-    return len(_alphabet_single_byte_ascii_printable)
+    return len(_ALPHABET_SINGLE_BYTE_ASCII_PRINTABLE)
 
 
 def get_single_byte_half_width_katakana_count() -> int:
-    return len(_alphabet_single_byte_half_width_katakana)
+    return len(_ALPHABET_SINGLE_BYTE_HALF_WIDTH_KATAKANA)
 
 
 def get_double_byte_other_count() -> int:
-    return len(_alphabet_double_byte_other)
+    return len(_ALPHABET_DOUBLE_BYTE_OTHER)
 
 
 def get_double_byte_kanji_count() -> int:
-    return len(_alphabet_double_byte_kanji)
+    return len(_ALPHABET_DOUBLE_BYTE_KANJI)
 
 
 def get_count() -> int:
-    return len(_alphabet)
+    return len(_ALPHABET)