msx-charset 0.1.0__tar.gz

msx_charset-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Your Name
+
+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. 

msx_charset-0.1.0/MANIFEST.in

@@ -0,0 +1,34 @@
+# MANIFEST.in
+include LICENSE
+
+# Include README
+include README.md
+
+# Include all Python files
+include msx_charset/*.py
+include msx_charset/tests/*.py
+
+# Include test data if any
+include msx_charset/tests/data/*
+
+# Include documentation
+include docs/*.md
+include docs/*.rst
+
+# Include type hints
+include msx_charset/py.typed
+
+# Exclude unnecessary files
+exclude .git*
+exclude .github/*
+exclude .vscode/*
+exclude __pycache__/*
+exclude *.pyc
+exclude *.pyo
+exclude *.pyd
+exclude .coverage
+exclude .pytest_cache/*
+exclude .tox/*
+exclude build/*
+exclude dist/*
+exclude *.egg-info/*

msx_charset-0.1.0/PKG-INFO

@@ -0,0 +1,117 @@
+Metadata-Version: 2.4
+Name: msx-charset
+Version: 0.1.0
+Summary: MSX character set codecs for Python
+Home-page: https://github.com/yamamo-to/msx-charset
+Author: yamamo-to
+Author-email: yamamo-to <humorum@gmail.com>
+License-Expression: MIT
+Project-URL: Repository, https://github.com/yamamo-to/msx-charset
+Project-URL: Issue, https://github.com/yamamo-to/msx-charset/issues
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+# MSX Character Set Converter
+
+[![Test](https://github.com/yamamo-to/msx-charset/actions/workflows/test.yml/badge.svg)](https://github.com/yamamo-to/msx-charset/actions/workflows/test.yml)
+
+A Python package for converting between Unicode and MSX character sets, supporting Japanese, International, and Brazilian character sets.
+
+## Features
+
+- Support for MSX character set conversion:
+  - Japanese version
+  - International version
+  - Brazilian version
+- Compatible with Python 3.8 and later
+
+## Installation
+
+```bash
+pip install msx-charset
+```
+
+## Usage
+
+### Japanese Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "こんにちは"
+encoded = text.encode('msx-jp')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-jp')
+print(decoded)  # "こんにちは"
+```
+
+### International Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "áéíóú"
+encoded = text.encode('msx-intl')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-intl')
+print(decoded)  # "áéíóú"
+```
+
+### Brazilian Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "Olá, mundo!"
+encoded = text.encode('msx-br')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-br')
+print(decoded)  # "Olá, mundo!"
+```
+
+## Development
+
+### Setup
+
+```bash
+# Create virtual environment
+python -m venv venv
+source venv/bin/activate  # Windows: venv\Scripts\activate
+
+# Install development package
+pip install -e .
+```
+
+### Running Tests
+
+```bash
+python -m unittest discover -s msx_charset/tests
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+MIT License 

msx_charset-0.1.0/README.md

@@ -0,0 +1,93 @@
+# MSX Character Set Converter
+
+[![Test](https://github.com/yamamo-to/msx-charset/actions/workflows/test.yml/badge.svg)](https://github.com/yamamo-to/msx-charset/actions/workflows/test.yml)
+
+A Python package for converting between Unicode and MSX character sets, supporting Japanese, International, and Brazilian character sets.
+
+## Features
+
+- Support for MSX character set conversion:
+  - Japanese version
+  - International version
+  - Brazilian version
+- Compatible with Python 3.8 and later
+
+## Installation
+
+```bash
+pip install msx-charset
+```
+
+## Usage
+
+### Japanese Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "こんにちは"
+encoded = text.encode('msx-jp')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-jp')
+print(decoded)  # "こんにちは"
+```
+
+### International Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "áéíóú"
+encoded = text.encode('msx-intl')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-intl')
+print(decoded)  # "áéíóú"
+```
+
+### Brazilian Character Set
+
+```python
+import msx_charset
+
+# Encoding
+text = "Olá, mundo!"
+encoded = text.encode('msx-br')
+print(encoded)  # MSX code byte sequence
+
+# Decoding
+decoded = encoded.decode('msx-br')
+print(decoded)  # "Olá, mundo!"
+```
+
+## Development
+
+### Setup
+
+```bash
+# Create virtual environment
+python -m venv venv
+source venv/bin/activate  # Windows: venv\Scripts\activate
+
+# Install development package
+pip install -e .
+```
+
+### Running Tests
+
+```bash
+python -m unittest discover -s msx_charset/tests
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+MIT License 

msx_charset-0.1.0/msx_charset/__init__.py

@@ -0,0 +1,21 @@
+import codecs
+from .codec_jp import msx_codec_jp
+from .codec_intl import msx_codec_intl
+from .codec_br import msx_codec_br
+
+__version__ = "0.1.0"
+__all__ = ["msx_codec_jp", "msx_codec_intl", "msx_codec_br"]
+
+
+def msx_charset(name):
+    if name.lower() in ('msx-jp', 'msx_jp'):
+        return msx_codec_jp
+    elif name.lower() in ('msx-intl', 'msx_intl'):
+        return msx_codec_intl
+    elif name.lower() in ('msx-br', 'msx_br'):
+        return msx_codec_br
+    raise LookupError(f"unknown encoding: {name}")
+
+
+# Register codec
+codecs.register(msx_charset)

msx_charset-0.1.0/msx_charset/codec_base.py

@@ -0,0 +1,60 @@
+import codecs
+
+class MSXCodecBase:
+    """Base class for MSX character set codecs"""
+    
+    def __init__(self, name, custom_map, graphic_map):
+        self.name = name
+        
+        # ASCII (0x00-0x7F) range mapping
+        self.ascii_map = {
+            i: chr(i) for i in range(0x80)
+            if chr(i).isprintable() or chr(i) in '\x00\x07\x08\x09\x0A\x0D\x1B\x20'
+        }
+        
+        # Character mappings
+        self.char_map = {**self.ascii_map, **custom_map}
+        self.char_reverse_map = {v: k for k, v in self.char_map.items()}
+        self.graphic_map = graphic_map
+        self.graphic_reverse_map = {v: k for k, v in graphic_map.items()}
+        
+        # Create codec info
+        self.codec_info = codecs.CodecInfo(
+            name=name,
+            encode=self.encode,
+            decode=self.decode
+        )
+
+    def encode(self, text, errors='strict'):
+        """Convert UTF-8 string to MSX code byte sequence"""
+        result = bytearray()
+        for char in text:
+            if char in self.graphic_map:
+                result.extend(self.graphic_map[char])
+            else:
+                result.append(self.char_reverse_map.get(char, 0x3F))
+        return bytes(result), len(text)
+
+    def decode(self, codes, errors='strict'):
+        """Convert MSX code byte sequence to UTF-8 string"""
+        result = []
+        i = 0
+        codes_len = len(codes)
+        
+        while i < codes_len:
+            code = codes[i]
+            
+            # Handle graphic characters
+            if code == 0x01 and i + 1 < codes_len:
+                next_code = codes[i + 1]
+                char = self.graphic_reverse_map.get((code, next_code))
+                if char:
+                    result.append(char)
+                    i += 2
+                    continue
+            
+            # Handle regular characters
+            result.append(self.char_map.get(code, '?'))
+            i += 1
+            
+        return ''.join(result), len(codes) 

msx_charset-0.1.0/msx_charset/codec_br.py

@@ -0,0 +1,84 @@
+import codecs
+from .codec_base import MSXCodecBase
+
+# Define data first
+# ASCII (0x00-0x7F) range mapping (some control characters are allowed)
+MSX_ASCII_MAP = {
+    i: chr(i) for i in range(0x80)
+    if chr(i).isprintable() or chr(i) in '\x00\x07\x08\x09\x0A\x0D\x1B\x20'
+}
+
+# MSX Brazilian
+MSX_CUSTOM_MAP_BR = {
+    0x80: 'Ç', 0x81: 'ü', 0x82: 'é', 0x83: 'â',
+    0x84: 'Á', 0x85: 'à', 0x86: '¨', 0x87: 'ç',
+    0x88: 'ê', 0x89: 'Í', 0x8A: 'Ó', 0x8B: 'Ú',
+    0x8C: 'Â', 0x8D: 'Ê', 0x8E: 'Ô', 0x8F: 'À',
+    0x90: 'É', 0x91: 'æ', 0x92: 'Æ', 0x93: 'ô',
+    0x94: 'ö', 0x95: 'ò', 0x96: 'û', 0x97: 'ù',
+    0x98: 'ÿ', 0x99: 'Ö', 0x9A: 'Ü', 0x9B: '¢',
+    0x9C: '£', 0x9D: '¥', 0x9E: 'Cz', 0x9F: 'ƒ',
+
+    0xA0: 'á', 0xA1: 'í', 0xA2: 'ó', 0xA3: 'ú',
+    0xA4: 'ñ', 0xA5: 'Ñ', 0xA6: 'ª', 0xA7: 'º',
+    0xA8: '¿', 0xA9: '⌐', 0xAA: '¬', 0xAB: '½',
+    0xAC: '¼', 0xAD: '¡', 0xAE: '«', 0xAF: '»',
+    0xB0: 'Ã', 0xB1: 'ã', 0xB2: 'Ĩ', 0xB3: 'ĩ',
+    0xB4: 'Õ', 0xB5: 'õ', 0xB6: 'Ű', 0xB7: 'ű',
+    0xB8: 'IJ', 0xB9: 'ij', 0xBA: '¾', 0xBB: '∽',
+    0xBC: '◊', 0xBD: '‰', 0xBE: '¶', 0xBF: '§',
+														
+    0xC0: '▂', 0xC1: '▚', 0xC2: '▆', 0xC3: '🮂',
+    0xC4: '▬', 0xC5: '🮅', 0xC6: '▎', 0xC7: '▞',
+    0xC8: '▊', 0xC9: '🮇', 0xCA: '🮊', 0xCB: '🮙',
+    0xCC: '🮘', 0xCD: '🭭', 0xCE: '🭯', 0xCF: '🭬',																    
+    0xD0: '🭮', 0xD1: '🮚', 0xD2: '🮛', 0xD3: '▘',
+    0xD4: '▗', 0xD5: '▝', 0xD6: '▖', 0xD7: '🮖',
+    0xD8: 'Δ', 0xD9: '‡', 0xDA: 'ω', 0xDB: '█',
+    0xDC: '▄', 0xDD: '▌', 0xDE: '▐', 0xDF: '▀',
+
+    0xE0: 'α', 0xE1: 'ß', 0xE2: 'Γ', 0xE3: 'π',
+    0xE4: 'Σ', 0xE5: 'σ', 0xE6: 'µ', 0xE7: 'τ',
+    0xE8: 'Φ', 0xE9: 'Θ', 0xEA: 'Ω', 0xEB: 'δ',
+    0xEC: '∞', 0xED: '⌀', 0xEE: '∈', 0xEF: '∩',
+    0xF0: '≡', 0xF1: '±', 0xF2: '≥', 0xF3: '≤',
+    0xF4: '⌠', 0xF5: '⌡', 0xF6: '÷', 0xF7: '≈',
+    0xF8: '°', 0xF9: '∙', 0xFA: '·', 0xFB: '√',
+    0xFC: 'ⁿ', 0xFD: '²', 0xFE: '■'
+}
+
+# Combined map (MSX code to character)
+MSX_CHAR_MAP_BR = dict(MSX_ASCII_MAP)
+MSX_CHAR_MAP_BR.update(MSX_CUSTOM_MAP_BR)
+
+# Reverse lookup (character to MSX code)
+MSX_CHAR_REVERSE_MAP_BR = {v: k for k, v in MSX_CHAR_MAP_BR.items()}
+
+# Graphic character mapping (2-byte characters)
+GRAPHIC_CHAR_MAP_BR = {
+    '☺': (0x01, 0x41), '☻': (0x01, 0x42), '♥': (0x01, 0x43),
+    '♦': (0x01, 0x44), '♣': (0x01, 0x45), '♠': (0x01, 0x46),
+    '•': (0x01, 0x47), '◘': (0x01, 0x48), '○': (0x01, 0x49),
+    '◙': (0x01, 0x4A), '♂': (0x01, 0x4B), '♀': (0x01, 0x4C),
+    '♪': (0x01, 0x4D), '♫': (0x01, 0x4E), '☼': (0x01, 0x4F),
+    '⟊': (0x01, 0x50), '┴': (0x01, 0x51), '┬': (0x01, 0x52),
+    '┤': (0x01, 0x53), '├': (0x01, 0x54), '┼': (0x01, 0x55),
+    '│': (0x01, 0x56), '─': (0x01, 0x57), '┌': (0x01, 0x58),
+    '┐': (0x01, 0x59), '└': (0x01, 0x5A), '┘': (0x01, 0x5B),
+    '╳': (0x01, 0x5C), '╱': (0x01, 0x5D), '╲': (0x01, 0x5E),
+    '🮯': (0x01, 0x5F)
+}
+
+# Reverse lookup for graphic characters
+GRAPHIC_CHAR_REVERSE_MAP_BR = {v: k for k, v in GRAPHIC_CHAR_MAP_BR.items()}
+
+
+class MSXBrazilianCodec(MSXCodecBase):
+    """Brazilian MSX character set codec"""
+    
+    def __init__(self):
+        super().__init__('msx-br', MSX_CUSTOM_MAP_BR, GRAPHIC_CHAR_MAP_BR)
+
+
+# Create codec instance
+msx_codec_br = MSXBrazilianCodec().codec_info

msx_charset-0.1.0/msx_charset/codec_intl.py

@@ -0,0 +1,85 @@
+import codecs
+from .codec_base import MSXCodecBase
+
+# Define data first
+# ASCII (0x00-0x7F) range mapping (some control characters are allowed)
+MSX_ASCII_MAP = {
+    i: chr(i) for i in range(0x80)
+    if chr(i).isprintable() or chr(i) in '\x00\x07\x08\x09\x0A\x0D\x1B\x20'
+}
+
+# MSX International
+MSX_CUSTOM_MAP_INTL = {
+    0x80: 'Ç', 0x81: 'ü', 0x82: 'é', 0x83: 'â',
+    0x84: 'ä', 0x85: 'à', 0x86: 'å', 0x87: 'ç',
+    0x88: 'ê', 0x89: 'ë', 0x8A: 'è', 0x8B: 'ï',
+    0x8C: 'î', 0x8D: 'ì', 0x8E: 'Ä', 0x8F: 'Å',
+    0x90: 'É', 0x91: 'æ', 0x92: 'Æ', 0x93: 'ô',
+    0x94: 'ö', 0x95: 'ò', 0x96: 'û', 0x97: 'ù',
+    0x98: 'ÿ', 0x99: 'Ö', 0x9A: 'Ü', 0x9B: '¢',
+    0x9C: '£', 0x9D: '¥', 0x9E: '₧', 0x9F: 'ƒ',
+
+    0xA0: 'á', 0xA1: 'í', 0xA2: 'ó', 0xA3: 'ú',
+    0xA4: 'ñ', 0xA5: 'Ñ', 0xA6: 'ª', 0xA7: 'º',
+    0xA8: '¿', 0xA9: '⌐', 0xAA: '¬', 0xAB: '½',
+    0xAC: '¼', 0xAD: '¡', 0xAE: '«', 0xAF: '»',
+    0xB0: 'Ã', 0xB1: 'ã', 0xB2: 'Ĩ', 0xB3: 'ĩ',
+    0xB4: 'Õ', 0xB5: 'õ', 0xB6: 'Ű', 0xB7: 'ű',
+    0xB8: 'IJ', 0xB9: 'ij', 0xBA: '¾', 0xBB: '∽',
+    0xBC: '◊', 0xBD: '‰', 0xBE: '¶', 0xBF: '§',
+														
+    0xC0: '▂', 0xC1: '▚', 0xC2: '▆', 0xC3: '🮂',
+    0xC4: '▬', 0xC5: '🮅', 0xC6: '▎', 0xC7: '▞',
+    0xC8: '▊', 0xC9: '🮇', 0xCA: '🮊', 0xCB: '🮙',
+    0xCC: '🮘', 0xCD: '🭭', 0xCE: '🭯', 0xCF: '🭬',																    
+    0xD0: '🭮', 0xD1: '🮚', 0xD2: '🮛', 0xD3: '▘',
+    0xD4: '▗', 0xD5: '▝', 0xD6: '▖', 0xD7: '🮖',
+    0xD8: 'Δ', 0xD9: '‡', 0xDA: 'ω', 0xDB: '█',
+    0xDC: '▄', 0xDD: '▌', 0xDE: '▐', 0xDF: '▀',
+
+    0xE0: 'α', 0xE1: 'ß', 0xE2: 'Γ', 0xE3: 'π',
+    0xE4: 'Σ', 0xE5: 'σ', 0xE6: 'µ', 0xE7: 'τ',
+    0xE8: 'Φ', 0xE9: 'Θ', 0xEA: 'Ω', 0xEB: 'δ',
+    0xEC: '∞', 0xED: '⌀', 0xEE: '∈', 0xEF: '∩',
+    0xF0: '≡', 0xF1: '±', 0xF2: '≥', 0xF3: '≤',
+    0xF4: '⌠', 0xF5: '⌡', 0xF6: '÷', 0xF7: '≈',
+    0xF8: '°', 0xF9: '∙', 0xFA: '·', 0xFB: '√',
+    0xFC: 'ⁿ', 0xFD: '²', 0xFE: '■'
+}
+
+# Combined map (MSX code to character)
+MSX_CHAR_MAP_INTL = dict(MSX_ASCII_MAP)
+MSX_CHAR_MAP_INTL.update(MSX_CUSTOM_MAP_INTL)
+
+# Reverse lookup (character to MSX code)
+MSX_CHAR_REVERSE_MAP_INTL = {v: k for k, v in MSX_CHAR_MAP_INTL.items()}
+
+														
+# Graphic character mapping (2-byte characters)
+GRAPHIC_CHAR_MAP_INTL = {
+    '☺': (0x01, 0x41), '☻': (0x01, 0x42), '♥': (0x01, 0x43),
+    '♦': (0x01, 0x44), '♣': (0x01, 0x45), '♠': (0x01, 0x46),
+    '•': (0x01, 0x47), '◘': (0x01, 0x48), '○': (0x01, 0x49),
+    '◙': (0x01, 0x4A), '♂': (0x01, 0x4B), '♀': (0x01, 0x4C),
+    '♪': (0x01, 0x4D), '♫': (0x01, 0x4E), '☼': (0x01, 0x4F),
+    '⟊': (0x01, 0x50), '┴': (0x01, 0x51), '┬': (0x01, 0x52),
+    '┤': (0x01, 0x53), '├': (0x01, 0x54), '┼': (0x01, 0x55),
+    '│': (0x01, 0x56), '─': (0x01, 0x57), '┌': (0x01, 0x58),
+    '┐': (0x01, 0x59), '└': (0x01, 0x5A), '┘': (0x01, 0x5B),
+    '╳': (0x01, 0x5C), '╱': (0x01, 0x5D), '╲': (0x01, 0x5E),
+    '🮯': (0x01, 0x5F)
+}
+
+# Reverse lookup for graphic characters
+GRAPHIC_CHAR_REVERSE_MAP_INTL = {v: k for k, v in GRAPHIC_CHAR_MAP_INTL.items()}
+
+
+class MSXInternationalCodec(MSXCodecBase):
+    """International MSX character set codec"""
+    
+    def __init__(self):
+        super().__init__('msx-intl', MSX_CUSTOM_MAP_INTL, GRAPHIC_CHAR_MAP_INTL)
+
+
+# Create codec instance
+msx_codec_intl = MSXInternationalCodec().codec_info

msx_charset-0.1.0/msx_charset/codec_jp.py

@@ -0,0 +1,144 @@
+from .codec_base import MSXCodecBase
+
+# MSX-specific Japanese and symbol characters (0x80-0xFE)
+MSX_CUSTOM_MAP_JP = {
+    # Column 1 (0x80-0x9F): Special characters and hiragana
+    0x80: '♠', 0x81: '♥', 0x82: '♣', 0x83: '♦',
+    0x84: '○', 0x85: '●', 0x86: 'を', 0x87: 'ぁ',
+    0x88: 'ぃ', 0x89: 'ぅ', 0x8A: 'ぇ', 0x8B: 'ぉ',
+    0x8C: 'ゃ', 0x8D: 'ゅ', 0x8E: 'ょ', 0x8F: 'っ',
+    0x90: '　', 0x91: 'あ', 0x92: 'い', 0x93: 'う',
+    0x94: 'え', 0x95: 'お', 0x96: 'か', 0x97: 'き',
+    0x98: 'く', 0x99: 'け', 0x9A: 'こ', 0x9B: 'さ',
+    0x9C: 'し', 0x9D: 'す', 0x9E: 'せ', 0x9F: 'そ',
+
+    # Column 2 (0xA0-0xBF): Symbols and katakana
+    0xA0: '　', 0xA1: '。', 0xA2: '「', 0xA3: '」',
+    0xA4: '、', 0xA5: '・', 0xA6: 'ヲ', 0xA7: 'ァ',
+    0xA8: 'ィ', 0xA9: 'ゥ', 0xAA: 'ェ', 0xAB: 'ォ',
+    0xAC: 'ャ', 0xAD: 'ュ', 0xAE: 'ョ', 0xAF: 'ッ',
+    0xB0: 'ー', 0xB1: 'ア', 0xB2: 'イ', 0xB3: 'ウ',
+    0xB4: 'エ', 0xB5: 'オ', 0xB6: 'カ', 0xB7: 'キ',
+    0xB8: 'ク', 0xB9: 'ケ', 0xBA: 'コ', 0xBB: 'サ',
+    0xBC: 'シ', 0xBD: 'ス', 0xBE: 'セ', 0xBF: 'ソ',
+
+    # Column 3 (0xC0-0xDF): Katakana (continued)
+    0xC0: 'タ', 0xC1: 'チ', 0xC2: 'ツ', 0xC3: 'テ',
+    0xC4: 'ト', 0xC5: 'ナ', 0xC6: 'ニ', 0xC7: 'ヌ',
+    0xC8: 'ネ', 0xC9: 'ノ', 0xCA: 'ハ', 0xCB: 'ヒ',
+    0xCC: 'フ', 0xCD: 'ヘ', 0xCE: 'ホ', 0xCF: 'マ',
+    0xD0: 'ミ', 0xD1: 'ム', 0xD2: 'メ', 0xD3: 'モ',
+    0xD4: 'ヤ', 0xD5: 'ユ', 0xD6: 'ヨ', 0xD7: 'ラ',
+    0xD8: 'リ', 0xD9: 'ル', 0xDA: 'レ', 0xDB: 'ロ',
+    0xDC: 'ワ', 0xDD: 'ン', 0xDE: '゛', 0xDF: '゜',
+
+    # Column 4 (0xE0-0xFE): Hiragana (continued)
+    0xE0: 'た', 0xE1: 'ち', 0xE2: 'つ', 0xE3: 'て',
+    0xE4: 'と', 0xE5: 'な', 0xE6: 'に', 0xE7: 'ぬ',
+    0xE8: 'ね', 0xE9: 'の', 0xEA: 'は', 0xEB: 'ひ',
+    0xEC: 'ふ', 0xED: 'へ', 0xEE: 'ほ', 0xEF: 'ま',
+    0xF0: 'み', 0xF1: 'む', 0xF2: 'め', 0xF3: 'も',
+    0xF4: 'や', 0xF5: 'ゆ', 0xF6: 'よ', 0xF7: 'ら',
+    0xF8: 'り', 0xF9: 'る', 0xFA: 'れ', 0xFB: 'ろ',
+    0xFC: 'わ', 0xFD: 'ん', 0xFE: '！'  # Full-width exclamation mark
+}
+
+# Graphic character mapping (2-byte characters)
+GRAPHIC_CHAR_MAP_JP = {
+    '月': (0x01, 0x41), '火': (0x01, 0x42), '水': (0x01, 0x43),
+    '木': (0x01, 0x44), '金': (0x01, 0x45), '土': (0x01, 0x46),
+    '日': (0x01, 0x47), '年': (0x01, 0x48), '円': (0x01, 0x49),
+    '時': (0x01, 0x4A), '分': (0x01, 0x4B), '秒': (0x01, 0x4C),
+    '百': (0x01, 0x4D), '千': (0x01, 0x4E), '万': (0x01, 0x4F),
+    'π': (0x01, 0x50), '┴': (0x01, 0x51), '┬': (0x01, 0x52),
+    '┤': (0x01, 0x53), '├': (0x01, 0x54), '┼': (0x01, 0x55),
+    '│': (0x01, 0x56), '─': (0x01, 0x57), '┌': (0x01, 0x58),
+    '┐': (0x01, 0x59), '└': (0x01, 0x5A), '┘': (0x01, 0x5B),
+    '×': (0x01, 0x5C), '大': (0x01, 0x5D), '中': (0x01, 0x5E),
+    '小': (0x01, 0x5F)
+}
+
+# Voiced sound mark and semi-voiced sound mark mapping
+DAKUTEN_MAP = {
+    'が': ('か', 0xDE), 'ぎ': ('き', 0xDE), 'ぐ': ('く', 0xDE),
+    'げ': ('け', 0xDE), 'ご': ('こ', 0xDE),
+    'ざ': ('さ', 0xDE), 'じ': ('し', 0xDE), 'ず': ('す', 0xDE),
+    'ぜ': ('せ', 0xDE), 'ぞ': ('そ', 0xDE),
+    'だ': ('た', 0xDE), 'ぢ': ('ち', 0xDE), 'づ': ('つ', 0xDE),
+    'で': ('て', 0xDE), 'ど': ('と', 0xDE),
+    'ば': ('は', 0xDE), 'び': ('ひ', 0xDE), 'ぶ': ('ふ', 0xDE),
+    'べ': ('へ', 0xDE), 'ぼ': ('ほ', 0xDE),
+    'ぱ': ('は', 0xDF), 'ぴ': ('ひ', 0xDF), 'ぷ': ('ふ', 0xDF),
+    'ぺ': ('へ', 0xDF), 'ぽ': ('ほ', 0xDF),
+    'ガ': ('カ', 0xDE), 'ギ': ('キ', 0xDE), 'グ': ('ク', 0xDE),
+    'ゲ': ('ケ', 0xDE), 'ゴ': ('コ', 0xDE),
+    'ザ': ('サ', 0xDE), 'ジ': ('シ', 0xDE), 'ズ': ('ス', 0xDE),
+    'ゼ': ('セ', 0xDE), 'ゾ': ('ソ', 0xDE),
+    'ダ': ('タ', 0xDE), 'ヂ': ('チ', 0xDE), 'ヅ': ('ツ', 0xDE),
+    'デ': ('テ', 0xDE), 'ド': ('ト', 0xDE),
+    'バ': ('ハ', 0xDE), 'ビ': ('ヒ', 0xDE), 'ブ': ('フ', 0xDE),
+    'ベ': ('ヘ', 0xDE), 'ボ': ('ホ', 0xDE),
+    'パ': ('ハ', 0xDF), 'ピ': ('ヒ', 0xDF), 'プ': ('フ', 0xDF),
+    'ペ': ('ヘ', 0xDF), 'ポ': ('ホ', 0xDF)
+}
+
+
+class MSXJapaneseCodec(MSXCodecBase):
+    """Japanese MSX character set codec"""
+    
+    def __init__(self):
+        super().__init__('msx-jp', MSX_CUSTOM_MAP_JP, GRAPHIC_CHAR_MAP_JP)
+        self.dakuten_map = DAKUTEN_MAP
+        self.dakuten_reverse_map = {(v, m): k for k, (v, m) in DAKUTEN_MAP.items()}
+
+    def encode(self, text, errors='strict'):
+        """Convert UTF-8 string to MSX code byte sequence (Japanese)"""
+        result = bytearray()
+        for char in text:
+            if char in self.graphic_map:
+                result.extend(self.graphic_map[char])
+            elif char in self.dakuten_map:
+                base, mark = self.dakuten_map[char]
+                result.extend([self.char_reverse_map.get(base, 0x3F), mark])
+            else:
+                result.append(self.char_reverse_map.get(char, 0x3F))
+        return bytes(result), len(text)
+
+    def decode(self, codes, errors='strict'):
+        """Convert MSX code byte sequence to UTF-8 string"""
+        result = []
+        i = 0
+        codes_len = len(codes)
+        
+        while i < codes_len:
+            code = codes[i]
+            
+            # Handle graphic characters
+            if code == 0x01 and i + 1 < codes_len:
+                next_code = codes[i + 1]
+                char = self.graphic_reverse_map.get((code, next_code))
+                if char:
+                    result.append(char)
+                    i += 2
+                    continue
+            
+            # Handle dakuten/handakuten
+            if i + 1 < codes_len and codes[i + 1] in (0xDE, 0xDF):
+                base_char = self.char_map.get(code)
+                mark = codes[i + 1]
+                composed = self.dakuten_reverse_map.get((base_char, mark))
+                if composed:
+                    result.append(composed)
+                else:
+                    mark_char = '゛' if mark == 0xDE else '゜'
+                    result.append(base_char + mark_char)
+                i += 2
+            else:
+                result.append(self.char_map.get(code, '?'))
+                i += 1
+                
+        return ''.join(result), len(codes)
+
+
+# Create codec instance
+msx_codec_jp = MSXJapaneseCodec().codec_info

msx_charset-0.1.0/msx_charset/tests/__init__.py

@@ -0,0 +1 @@
+# Test package initialization file 

msx_charset-0.1.0/msx_charset/tests/test_charset_br.py

@@ -0,0 +1,70 @@
+import unittest
+import codecs
+from msx_charset import msx_charset
+
+
+class TestMSXCharsetBR(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        # テスト実行前に文字セットを登録
+        codecs.register(msx_charset)
+
+    def test_encode_decode_ascii(self):
+        text = "Hello, World!"
+        encoded = text.encode("msx-br")
+        decoded = encoded.decode("msx-br")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_accented_chars(self):
+        text = "Á¨ÍÓÚÂÊÔÀ"
+        encoded = text.encode("msx-br")
+        decoded = encoded.decode("msx-br")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_graphic_chars(self):
+        text = "☺☻♥♦♣♠"
+        encoded = text.encode("msx-br")
+        decoded = encoded.decode("msx-br")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_mixed(self):
+        text = "Olá, mundo!"
+        encoded = text.encode("msx-br")
+        decoded = encoded.decode("msx-br")
+        self.assertEqual(text, decoded)
+
+    def test_codec_registration(self):
+        self.assertIsNotNone(codecs.lookup("msx-br"))
+        self.assertIsNotNone(codecs.lookup("msx_br"))
+
+    def test_encode_bytes_ascii(self):
+        # ASCII文字のバイト列テスト
+        text = "Hello!"
+        expected = bytes([0x48, 0x65, 0x6C, 0x6C, 0x6F, 0x21])
+        encoded = text.encode("msx-br")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_accented(self):
+        # アクセント付き文字のバイト列テスト
+        text = "Á¨ÍÓÚÂÊÔÀ"
+        expected = bytes([0x84, 0x86, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F])  # MSXブラジル文字セットの対応するバイト値
+        encoded = text.encode("msx-br")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_graphic(self):
+        # グラフィック文字のバイト列テスト
+        text = "☺☻"
+        expected = bytes([0x01, 0x41, 0x01, 0x42])  # MSXブラジル文字セットの対応するバイト値
+        encoded = text.encode("msx-br")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_mixed(self):
+        # 混合文字のバイト列テスト
+        text = "Aá"
+        expected = bytes([0x41, 0xA0])  # MSXブラジル文字セットの対応するバイト値
+        encoded = text.encode("msx-br")
+        self.assertEqual(encoded, expected)
+
+
+if __name__ == "__main__":
+    unittest.main()

msx_charset-0.1.0/msx_charset/tests/test_charset_intl.py

@@ -0,0 +1,77 @@
+import unittest
+import codecs
+from msx_charset import msx_charset
+
+
+
+class TestMSXCharsetIntl(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        # テスト実行前にコーデックを登録
+        codecs.register(msx_charset)
+
+    def test_encode_decode_ascii(self):
+        text = "Hello, World!"
+        encoded = text.encode("msx-intl")
+        decoded = encoded.decode("msx-intl")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_accented_chars(self):
+        text = "áéíóúàèìòùâêîôû"
+        encoded = text.encode("msx-intl")
+        decoded = encoded.decode("msx-intl")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_graphic_chars(self):
+        text = "☺☻♥♦♣♠"
+        encoded = text.encode("msx-intl")
+        decoded = encoded.decode("msx-intl")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_mixed(self):
+        text = "Hello, áéíóú!"
+        encoded = text.encode("msx-intl")
+        decoded = encoded.decode("msx-intl")
+        self.assertEqual(text, decoded)
+
+    def test_codec_registration(self):
+        self.assertIsNotNone(codecs.lookup("msx-intl"))
+        self.assertIsNotNone(codecs.lookup("msx_intl"))
+
+    def test_encode_bytes_ascii(self):
+        # ASCII文字のバイト列テスト
+        text = "Hello!"
+        expected = bytes([0x48, 0x65, 0x6C, 0x6C, 0x6F, 0x21])
+        encoded = text.encode("msx-intl")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_accented(self):
+        # アクセント付き文字のバイト列テスト
+        text = "áé"
+        expected = bytes([0xA0, 0x82])  # MSXインターナショナル文字セットの対応するバイト値
+        encoded = text.encode("msx-intl")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_graphic(self):
+        # グラフィック文字のバイト列テスト
+        text = "☺☻"
+        expected = bytes([0x01, 0x41, 0x01, 0x42])  # MSXインターナショナル文字セットの対応するバイト値
+        encoded = text.encode("msx-intl")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_mixed(self):
+        # 混合文字のバイト列テスト
+        text = "Aá"
+        expected = bytes([0x41, 0xA0])  # MSXインターナショナル文字セットの対応するバイト値
+        encoded = text.encode("msx-intl")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_decode_currency(self):
+        text = "£$¥"
+        encoded = text.encode("msx-intl")
+        decoded = encoded.decode("msx-intl")
+        self.assertEqual(text, decoded)
+
+
+if __name__ == "__main__":
+    unittest.main() 

msx_charset-0.1.0/msx_charset/tests/test_charset_jp.py

@@ -0,0 +1,109 @@
+import unittest
+import codecs
+from msx_charset import msx_charset
+
+
+class TestMSXCharsetJP(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        # テスト実行前にコーデックを登録
+        codecs.register(msx_charset)
+
+    def test_encode_decode_ascii(self):
+        text = "Hello, World!"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_hiragana(self):
+        text = "こんにちは"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_katakana(self):
+        text = "コンニチハ"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_dakuten(self):
+        text = "がぎぐげご"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_handakuten(self):
+        text = "ぱぴぷぺぽ"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_graphic_chars(self):
+        text = "月火水木金土日"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_encode_decode_mixed(self):
+        text = "Hello、こんにちは！"
+        encoded = text.encode("msx-jp")
+        decoded = encoded.decode("msx-jp")
+        self.assertEqual(text, decoded)
+
+    def test_codec_registration(self):
+        self.assertIsNotNone(codecs.lookup("msx-jp"))
+        self.assertIsNotNone(codecs.lookup("msx_jp"))
+
+    def test_encode_bytes_ascii(self):
+        # ASCII文字のバイト列テスト
+        text = "Hello!"
+        expected = bytes([0x48, 0x65, 0x6C, 0x6C, 0x6F, 0x21])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_hiragana(self):
+        # ひらがなのバイト列テスト
+        text = "こんにちは"
+        expected = bytes([0x9A, 0xFD, 0xE6, 0xE1, 0xEA])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_katakana(self):
+        # カタカナのバイト列テスト
+        text = "コンニチハ"
+        expected = bytes([0xBA, 0xDD, 0xC6, 0xC1, 0xCA])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_dakuten(self):
+        # 濁点文字のバイト列テスト
+        text = "がぎ"
+        expected = bytes([0x96, 0xDE, 0x97, 0xDE])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_handakuten(self):
+        # 半濁点文字のバイト列テスト
+        text = "ぱぴ"
+        expected = bytes([0xEA, 0xDF, 0xEB, 0xDF])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_graphic(self):
+        # グラフィック文字のバイト列テスト
+        text = "月火"
+        expected = bytes([0x01, 0x41, 0x01, 0x42])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+    def test_encode_bytes_mixed(self):
+        # 混合文字のバイト列テスト
+        text = "A、あ"
+        expected = bytes([0x41, 0xA4, 0x91])
+        encoded = text.encode("msx-jp")
+        self.assertEqual(encoded, expected)
+
+
+if __name__ == "__main__":
+    unittest.main()

msx_charset-0.1.0/msx_charset.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+setup.py
+msx_charset/__init__.py
+msx_charset/codec_base.py
+msx_charset/codec_br.py
+msx_charset/codec_intl.py
+msx_charset/codec_jp.py
+msx_charset/tests/__init__.py
+msx_charset/tests/test_charset_br.py
+msx_charset/tests/test_charset_intl.py
+msx_charset/tests/test_charset_jp.py

msx_charset-0.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "msx-charset"
+version = "0.1.0"
+authors = [
+    {name = "yamamo-to", email = "humorum@gmail.com"}
+]
+description = "MSX character set codecs for Python"
+readme = "README.md"
+requires-python = ">=3.7"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+license = "MIT"
+
+[tool.setuptools]
+packages = ["msx_charset"]
+license-files = []
+
+[tool.pytest.ini_options]
+testpaths = ["msx_charset/tests"]
+python_files = ["test_*.py"] 
+
+[project.urls]
+Repository = "https://github.com/yamamo-to/msx-charset"
+Issue = "https://github.com/yamamo-to/msx-charset/issues"
+

msx_charset-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

msx_charset-0.1.0/setup.py

@@ -0,0 +1,24 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="msx-charset",
+    version="0.1.0",
+    packages=find_packages(),
+    install_requires=[],
+    python_requires=">=3.8",
+    author="yamamo-to",
+    author_email="humorum@gmail.com",
+    description="MSX Japanese, International, and Brazilian character codec for Python",
+    long_description=open("README.md", encoding='utf-8').read(),
+    long_description_content_type="text/markdown",
+    url="https://github.com/yamamo-to/msx-charset",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Operating System :: OS Independent",
+    ],
+)