unicodedata-reader 0.1.6__tar.gz → 0.2.0__tar.gz

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/PKG-INFO

@@ -1,17 +1,20 @@
 Metadata-Version: 2.1
 Name: unicodedata-reader
-Version: 0.1.6
+Version: 0.2.0
 Summary: 
 Home-page: https://github.com/kojiishi/unicodedata-reader
 License: Apache-2.0
 Author: Koji Ishii
 Author-email: kojii@chromium.org
-Requires-Python: >=3.8,<3.10
+Requires-Python: >=3.8
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
-Requires-Dist: platformdirs (>=2.2.0,<3.0.0)
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: platformdirs (>=2.2,<5.0)
 Project-URL: Repository, https://github.com/kojiishi/unicodedata-reader
 Description-Content-Type: text/markdown
 
@@ -36,6 +39,7 @@ that can read the property values of the [Unicode Character Database]
 in browsers.
 Please see the [JavaScript] section below.
 
+[General_Category property]: http://unicode.org/reports/tr44/#General_Category
 [Line_Break property]: http://unicode.org/reports/tr44/#Line_Break
 [Unicode Character Database]: https://unicode.org/reports/tr44/
 [unicodedata]: https://docs.python.org/3/library/unicodedata.html
@@ -79,10 +83,21 @@ The [`UnicodeDataCompressor` class] in this package
 can generate JavaScript functions that can read the property values
 of the [Unicode Character Database] in browsers.
 
-Please see [LineBreak.js] for an example of the generated functions
-and [LineBreak.html] for an example usage.
+Following examples are available in the "`js`" directory:
+* [GeneralCategory.js] is a generated JavaScript file
+  for the Unicode [General_Category property].
+* [LineBreak.js] is a generated JavaScript file
+  for the Unicode [Line_Break property].
+* [LineBreak.html] for an example usage of [LineBreak.js].
+
+The following command generates a JavaScript file for the [Line_Break property]
+using `js/template.js` as the template file:
+```sh
+unicodedata-reader lb -t js/template.js
+```
 
 [`UnicodeDataCompressor` class]: https://github.com/kojiishi/unicodedata-reader/blob/main/unicodedata_reader/compressor.py
+[GeneralCategory.js]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/GeneralCategory.js
 [LineBreak.html]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.html
 [LineBreak.js]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.js
 

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/README.md

@@ -19,6 +19,7 @@ that can read the property values of the [Unicode Character Database]
 in browsers.
 Please see the [JavaScript] section below.
 
+[General_Category property]: http://unicode.org/reports/tr44/#General_Category
 [Line_Break property]: http://unicode.org/reports/tr44/#Line_Break
 [Unicode Character Database]: https://unicode.org/reports/tr44/
 [unicodedata]: https://docs.python.org/3/library/unicodedata.html
@@ -62,9 +63,20 @@ The [`UnicodeDataCompressor` class] in this package
 can generate JavaScript functions that can read the property values
 of the [Unicode Character Database] in browsers.
 
-Please see [LineBreak.js] for an example of the generated functions
-and [LineBreak.html] for an example usage.
+Following examples are available in the "`js`" directory:
+* [GeneralCategory.js] is a generated JavaScript file
+  for the Unicode [General_Category property].
+* [LineBreak.js] is a generated JavaScript file
+  for the Unicode [Line_Break property].
+* [LineBreak.html] for an example usage of [LineBreak.js].
+
+The following command generates a JavaScript file for the [Line_Break property]
+using `js/template.js` as the template file:
+```sh
+unicodedata-reader lb -t js/template.js
+```
 
 [`UnicodeDataCompressor` class]: https://github.com/kojiishi/unicodedata-reader/blob/main/unicodedata_reader/compressor.py
+[GeneralCategory.js]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/GeneralCategory.js
 [LineBreak.html]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.html
 [LineBreak.js]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.js

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "unicodedata-reader"
-version = "0.1.6"
+version = "0.2.0"
 description = ""
 authors = ["Koji Ishii <kojii@chromium.org>"]
 readme = "README.md"
@@ -12,14 +12,14 @@ repository = "https://github.com/kojiishi/unicodedata-reader"
 license = "Apache-2.0"
 
 [tool.poetry.dependencies]
-python = ">=3.8,<3.10"
-platformdirs = "^2.2.0"
+python = ">=3.8"
+platformdirs = ">=2.2,<5.0"
 
 [tool.poetry.dev-dependencies]
-pytest = "^6.2.4"
-pytype = "*"
-tox = "^3.24.3"
-yapf = "^0.31.0"
+pytest = "*"
+pytype = {version = "*", python = "<3.10"}
+tox = "^4.14.2"
+yapf = "^0.40.2"
 
 [tool.poetry.scripts]
 unicodedata-reader = 'unicodedata_reader.__main__:main'

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/__init__.py

@@ -2,3 +2,4 @@ from .entry import *
 from .reader import *
 from .compressor import *
 from .cli import *
+from .set import *

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/__main__.py

@@ -2,6 +2,7 @@ import pathlib
 import sys
 
 import unicodedata_reader.bidi_brackets as bidi_brackets
+import unicodedata_reader.east_asian_width as ea
 import unicodedata_reader.emoji as emoji
 import unicodedata_reader.general_category as gc
 import unicodedata_reader.line_break as lb
@@ -12,6 +13,7 @@ def main():
     args = sys.argv
     sub_commands = {
         'bidi': lambda: bidi_brackets.dump_bidi_brackets(),
+        'ea': lambda: ea.UnicodeEastAsianWidthDataCli().main(),
         'emoji': lambda: emoji.UnicodeEmojiDataCli().main(),
         'gc': lambda: gc.UnicodeGeneralCategoryDataCli().main(),
         'lb': lambda: lb.UnicodeLineBreakDataCli().main(),

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/cli.py

@@ -73,14 +73,15 @@ def _init_logging(verbose):
 
 
 class UnicodeDataCli(object):
+
     def __init__(self):
-        self.parse_args()
+        self._parse_args()
 
     def _columns(self) -> Dict[str, Callable[[int, str], Any]]:
         columns = self._core_columns()
         columns = dict(
             itertools.chain({
-                'Code': lambda code, ch: u_hex(code),
+                'Code': lambda code, ch: 'U' + u_hex(code),
                 'Char': lambda code, ch: u_printable_chr(ch),
             }.items(), columns.items(), {
                 'Name': lambda code, ch: u_name_or_empty(ch),
@@ -119,17 +120,22 @@ class UnicodeDataCli(object):
         compressor = UnicodeDataCompressor(entries)
         compressor.substitute_template(template, name=self.name, output=output)
 
-    def parse_args(self):
+    def _parse_args(self):
         parser = argparse.ArgumentParser()
-        parser.add_argument('text', nargs='*')
+        parser.add_argument('text',
+                            nargs='*',
+                            help='show properties for the text')
         parser.add_argument('-f', '--no-cache', action='store_true')
-        parser.add_argument('-n', '--name')
-        parser.add_argument('-t', '--template', type=pathlib.Path)
+        parser.add_argument('--name', help='$NAME in the template')
+        parser.add_argument('-t',
+                            '--template',
+                            type=pathlib.Path,
+                            help='generate a file from the template')
         parser.add_argument('-o', '--output', type=pathlib.Path)
-        parser.add_argument("-v",
-                            "--verbose",
-                            help="increase output verbosity",
-                            action="count",
+        parser.add_argument('-v',
+                            '--verbose',
+                            help='increase output verbosity',
+                            action='count',
                             default=0)
         parser.parse_args(namespace=self)
         _init_logging(self.verbose)  # pytype: disable=attribute-error

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/compressor.py

@@ -22,6 +22,7 @@ def _init_logging(verbose: int):
 
 
 class UnicodeDataCompressor(object):
+
     def __init__(self, entries: UnicodeDataEntries):
         self._entries = entries
 
@@ -82,8 +83,8 @@ class UnicodeDataCompressor(object):
                      len(bytes), len(base64bytes), len(values_for_int),
                      value_bits)
         mapping = {
-            'PROP_NAME': name,
-            'BASE64': base64bytes.decode('ascii'),
+            'NAME': name,
+            'BASE64BYTES': base64bytes.decode('ascii'),
             'VALUE_BITS': str(value_bits),
             'VALUE_MASK': str((1 << value_bits) - 1),
             'VALUE_LIST': ','.join(f'"{v}"' for v in values_for_int),

unicodedata_reader-0.2.0/unicodedata_reader/east_asian_width.py

@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+import unicodedata
+from typing import Any
+from typing import Callable
+from typing import Dict
+
+from unicodedata_reader import *
+
+
+class UnicodeEastAsianWidthDataCli(UnicodeDataCli):
+
+    def __init__(self):
+        super().__init__()
+        self._entries = UnicodeDataReader.default.east_asian_width()
+
+    def _core_columns(self) -> Dict[str, Callable[[int, str], Any]]:
+        return {
+            'EA': lambda code, ch: self._entries.value(code),
+            'GC': lambda code, ch: unicodedata.category(ch),
+            'EAW': lambda code, ch: unicodedata.east_asian_width(ch),
+            'cp932': lambda code, ch: u_enc(ch, 'cp932'),
+            'sjis04': lambda code, ch: u_enc(ch, 'sjis_2004'),
+            'cp936': lambda code, ch: u_enc(ch, 'cp936'),
+            'cp949': lambda code, ch: u_enc(ch, 'cp949'),
+            'cp950': lambda code, ch: u_enc(ch, 'cp950'),
+        }
+
+
+if __name__ == '__main__':
+    UnicodeEastAsianWidthDataCli().main()

unicodedata_reader-0.2.0/unicodedata_reader/emoji.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+from typing import Any
+from typing import Callable
+from typing import Dict
+
+from unicodedata_reader import *
+
+
+class UnicodeEmojiDataCli(UnicodeDataCli):
+
+    def __init__(self):
+        super().__init__()
+        self._entries = UnicodeDataReader.default.emoji()
+
+    def _emoji_flag_func(self, mask: EmojiType):
+        return lambda code, ch: 1 if self._entries.value(code) & mask else 0
+
+    def _core_columns(self) -> Dict[str, Callable[[int, str], Any]]:
+        return {
+            'Emoji':
+            self._emoji_flag_func(EmojiType.Emoji),
+            'Emoji_Presentation':
+            self._emoji_flag_func(EmojiType.Emoji_Presentation),
+            'Emoji_Modifier':
+            self._emoji_flag_func(EmojiType.Emoji_Modifier),
+            'Emoji_Modifier_Base':
+            self._emoji_flag_func(EmojiType.Emoji_Modifier_Base),
+            'Emoji_Component':
+            self._emoji_flag_func(EmojiType.Emoji_Component),
+            'Extended_Pictographic':
+            self._emoji_flag_func(EmojiType.Extended_Pictographic),
+            'EmojiCombined':
+            lambda code, ch: self._entries.value(code),
+        }
+
+
+if __name__ == '__main__':
+    UnicodeEmojiDataCli().main()

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/entry.py

@@ -27,6 +27,7 @@ def u_enc(c, encoding):
 
 
 class BidiBrackets(object):
+
     def __init__(self, pair: int, type: str):
         self.pair = pair
         self.type = type
@@ -55,6 +56,9 @@ class UnicodeDataEntry(object):
 
     [Unicode character database]: https://unicode.org/reports/tr44/
     """
+
+    max_code_point = 0x10FFFF
+
     def __init__(self, min: int, max: int, value):
         self.min = min
         self.max = max
@@ -134,19 +138,22 @@ class UnicodeDataEntry(object):
         min = -1
         last_code = -1
         for code, value in values:
+            assert code > last_code
             if value == last_value and code == last_code + 1:
                 last_code = code
                 continue
-            if min >= 0 and last_value is not None:
+            if min >= 0:
                 yield UnicodeDataEntry(min, last_code, last_value)
             last_value = value
             min = last_code = code
-        if min >= 0 and last_value is not None:
+        if min >= 0:
             yield UnicodeDataEntry(min, code, last_value)
 
     @staticmethod
     def from_values(values: Iterable[Any]):
-        return UnicodeDataEntry.from_pairs(enumerate(values))
+        pairs = enumerate(values)
+        pairs = (p for p in pairs if p[1] is not None)
+        return UnicodeDataEntry.from_pairs(pairs)
 
     @staticmethod
     def values_for_code(entries, missing_value) -> Iterable[Any]:
@@ -163,6 +170,7 @@ class UnicodeDataEntries(object):
     or a list of `UnicodeDataEntry`.
     [Unicode character database]: https://unicode.org/reports/tr44/
     """
+
     def __init__(self,
                  entries: Optional[Union[Iterable[UnicodeDataEntry],
                                          Sequence[UnicodeDataEntry]]] = None,
@@ -171,12 +179,15 @@ class UnicodeDataEntries(object):
                  converter=None):
         self._missing_entries = self._default_missing_entries()
         self.name = name
+        self._values_for_int = None  # type: list
+
         if entries is not None:
+            assert lines is None
+            assert converter is None
             self._entries = entries
         else:
             assert lines is not None
             self._load_lines(lines, converter=converter)
-        self._values_for_int = None  # type: list
 
     def _default_missing_entries(self) -> List[UnicodeDataEntry]:
         return []
@@ -193,16 +204,16 @@ class UnicodeDataEntries(object):
             self._missing_entries.extend(entries)
             assert self._missing_entries
 
-    def ensure_multi_iterable(self):
+    def _ensure_multi_iterable(self):
         if isinstance(self._entries, types.GeneratorType):
             self._entries = tuple(self._entries)
 
     def __iter__(self):
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         return self._entries.__iter__()
 
     def __len__(self):
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         return len(self._entries)
 
     def missing_value(self, code: int):
@@ -235,12 +246,12 @@ class UnicodeDataEntries(object):
 
     def unicodes(self) -> Iterable[int]:
         """Returns a list of Unicode code points defined in this entries."""
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         return itertools.chain(*(e.range() for e in self._entries))
 
     def value(self, code: int):
         """Returns the value for the given code point."""
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         for entry in self._entries:
             if code < entry.min:
                 return self.missing_value(code)
@@ -254,7 +265,7 @@ class UnicodeDataEntries(object):
         The list includes missing values,
         so that `tuple(values_for_code())[code]` is equal to `value(code)`.
         """
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         return UnicodeDataEntry.values_for_code(self._entries,
                                                 self.missing_value)
 
@@ -278,8 +289,8 @@ class UnicodeDataEntries(object):
 
         On return, the original values are stored in `self.value_list`.
         """
-        assert self.values_for_int() is None
-        self.ensure_multi_iterable()
+        assert self._values_for_int is None
+        self._ensure_multi_iterable()
         value_map = {}
         for entry in self._entries:
             assert not isinstance(entry.value, int)
@@ -295,7 +306,7 @@ class UnicodeDataEntries(object):
 
     def to_dict(self) -> Dict[int, Any]:
         """Returns a `dict` of values with a Unicode code point as the key."""
-        self.ensure_multi_iterable()
+        self._ensure_multi_iterable()
         dict = {}
         for entry in self._entries:
             for code in entry.range():
@@ -304,12 +315,14 @@ class UnicodeDataEntries(object):
 
 
 class UnicodeBidiBracketsDataEntries(UnicodeDataEntries):
+
     def _load_lines(self, lines: Iterable[str], converter=None):
         converter = converter or BidiBrackets.from_values
         super()._load_lines(lines, converter=converter)
 
 
 class UnicodeEmojiDataEntries(UnicodeDataEntries):
+
     def _load_lines(self, lines: Iterable[str], converter=None):
         converter = converter or (lambda v: EmojiType[v])
         super()._load_lines(lines, converter=converter)
@@ -334,6 +347,7 @@ class UnicodeEmojiDataEntries(UnicodeDataEntries):
 
 
 class UnicodeLineBreakDataEntries(UnicodeDataEntries):
+
     def _load_comment(self, comment: str, start_index: int):
         # Load missing value entries. See the comments in:
         # https://www.unicode.org/Public/UNIDATA/LineBreak.txt
@@ -356,12 +370,14 @@ class UnicodeLineBreakDataEntries(UnicodeDataEntries):
 
 
 class UnicodeScriptExtensionsDataEntries(UnicodeDataEntries):
+
     def _load_lines(self, lines: Iterable[str], converter=None):
         converter = converter or (lambda v: v.split())
         super()._load_lines(lines, converter=converter)
 
 
 class UnicodeVerticalOrientationDataEntries(UnicodeDataEntries):
+
     def _load_comment(self, comment: str, start_index: int):
         # Load missing value entries. See the comments in:
         # https://www.unicode.org/Public/UNIDATA/VerticalOrientation.txt

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/general_category.py

@@ -8,6 +8,7 @@ from unicodedata_reader import *
 
 
 class UnicodeGeneralCategoryDataCli(UnicodeDataCli):
+
     def __init__(self):
         super().__init__()
         self._entries = UnicodeDataReader.default.general_category()

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/line_break.py

@@ -8,6 +8,7 @@ from unicodedata_reader import *
 
 
 class UnicodeLineBreakDataCli(UnicodeDataCli):
+
     def __init__(self):
         super().__init__()
         self._entries = UnicodeDataReader.default.line_break()

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/reader.py

@@ -33,6 +33,11 @@ class UnicodeDataReader(object):
         lines = self.read_lines(name)
         return UnicodeDataEntries(name=name, lines=lines)
 
+    def east_asian_width(self) -> UnicodeDataEntries:
+        name = 'EastAsianWidth'
+        lines = self.read_lines(name)
+        return UnicodeDataEntries(name=name, lines=lines)
+
     def emoji(self) -> UnicodeDataEntries:
         lines = self.read_lines('emoji/emoji-data')
         return UnicodeEmojiDataEntries(name='Emoji', lines=lines)

unicodedata_reader-0.2.0/unicodedata_reader/set.py

@@ -0,0 +1,72 @@
+from typing import Callable
+
+from unicodedata_reader.entry import *
+from unicodedata_reader.reader import *
+
+
+class Set(object):
+    """A simple set of Unicode code points."""
+
+    def __init__(self) -> None:
+        self.set = set()  # type: set[int]
+
+    def __contains__(self, code_point: int) -> bool:
+        return code_point in self.set
+
+    def __iter__(self) -> Iterable[int]:
+        return self.set.__iter__()
+
+    def __isub__(self, other: 'Set') -> None:
+        self.set -= other.set
+
+    def __iand__(self, other: 'Set') -> None:
+        self.set &= other.set
+
+    def __ior__(self, other: 'Set') -> None:
+        self.set |= other.set
+
+    def add(self, code: int) -> None:
+        self.set.add(code)
+
+    def remove(self, code: int) -> None:
+        self.set.discard(code)
+
+    def add_entries(self, entries: UnicodeDataEntries, pred: Callable[[Any],
+                                                                      bool]):
+        for entry in entries:
+            if pred(entry.value):
+                for code in entry.range():
+                    self.set.add(code)
+
+    @staticmethod
+    def east_asian_width(
+            value: str,
+            reader: UnicodeDataReader = UnicodeDataReader.default) -> 'Set':
+        set = Set()
+        set.add_entries(reader.east_asian_width(), lambda v: v == value)
+        return set
+
+    @staticmethod
+    def general_category(
+            value: str,
+            reader: UnicodeDataReader = UnicodeDataReader.default) -> 'Set':
+        set = Set()
+        set.add_entries(reader.general_category(),
+                        lambda v: v.startswith(value))
+        return set
+
+    @staticmethod
+    def scripts(
+            value: str,
+            reader: UnicodeDataReader = UnicodeDataReader.default) -> 'Set':
+        set = Set()
+        set.add_entries(reader.scripts(), lambda v: v == value)
+        return set
+
+    @staticmethod
+    def script_extensions(
+            value: str,
+            reader: UnicodeDataReader = UnicodeDataReader.default) -> 'Set':
+        set = Set()
+        set.add_entries(reader.script_extensions(), lambda v: value in v)
+        return set

{unicodedata-reader-0.1.6 → unicodedata_reader-0.2.0}/unicodedata_reader/vertical_orientation.py

@@ -8,6 +8,7 @@ from unicodedata_reader import *
 
 
 class UnicodeVerticalOrientationDataCli(UnicodeDataCli):
+
     def __init__(self):
         super().__init__()
         self._entries = UnicodeDataReader.default.vertical_orientation()

unicodedata-reader-0.1.6/setup.py

@@ -1,34 +0,0 @@
-# -*- coding: utf-8 -*-
-from setuptools import setup
-
-packages = \
-['unicodedata_reader']
-
-package_data = \
-{'': ['*']}
-
-install_requires = \
-['platformdirs>=2.2.0,<3.0.0']
-
-entry_points = \
-{'console_scripts': ['unicodedata-reader = unicodedata_reader.__main__:main']}
-
-setup_kwargs = {
-    'name': 'unicodedata-reader',
-    'version': '0.1.6',
-    'description': '',
-    'long_description': '[![CI](https://github.com/kojiishi/unicodedata-reader/actions/workflows/ci.yml/badge.svg)](https://github.com/kojiishi/unicodedata-reader/actions/workflows/ci.yml)\n[![PyPI](https://img.shields.io/pypi/v/unicodedata-reader.svg)](https://pypi.org/project/unicodedata-reader/)\n[![Dependencies](https://badgen.net/github/dependabot/kojiishi/unicodedata-reader)](https://github.com/kojiishi/unicodedata-reader/network/updates)\n\n\n# unicodedata-reader\n\nThis package reads and parses the [Unicode Character Database] files.\n\nMany of them are available in the [unicodedata] module,\nor in other 3rd party modules.\nWhen the desired data is not in any existing modules,\nsuch as the [Line_Break property] or the [Vertical_Orientation property],\nthis package can read the data files\nat <https://www.unicode.org/Public/UNIDATA/>.\n\nThis package can also generate JavaScript functions\nthat can read the property values of the [Unicode Character Database]\nin browsers.\nPlease see the [JavaScript] section below.\n\n[Line_Break property]: http://unicode.org/reports/tr44/#Line_Break\n[Unicode Character Database]: https://unicode.org/reports/tr44/\n[unicodedata]: https://docs.python.org/3/library/unicodedata.html\n[Vertical_Orientation property]: http://unicode.org/reports/tr44/#Vertical_Orientation\n\n## Install\n\n```sh\npip install unicodedata-reader\n```\nIf you want to clone and install using [poetry]:\n```sh\ngit clone https://github.com/kojiishi/unicodedata-reader\ncd unicodedata-reader\npoetry install\npoetry shell\n```\n\n[poetry]: https://github.com/python-poetry/poetry\n\n\n## Python\n\n```python\nimport unicodedata_reader\n\nreader = unicodedata_reader.UnicodeDataReader.default\nlb = reader.line_break()\nprint(lb.value(0x41))\n```\nThe example above prints `AL`,\nthe [Line_Break property] value for U+0041.\nPlease also see [line_break_test.py] for more usages.\n\n[line_break_test.py]: https://github.com/kojiishi/unicodedata-reader/blob/main/tests/line_break_test.py\n\n## JavaScript\n[JavaScript]: #javascript\n\nThe [`UnicodeDataCompressor` class] in this package\ncan generate JavaScript functions that can read the property values\nof the [Unicode Character Database] in browsers.\n\nPlease see [LineBreak.js] for an example of the generated functions\nand [LineBreak.html] for an example usage.\n\n[`UnicodeDataCompressor` class]: https://github.com/kojiishi/unicodedata-reader/blob/main/unicodedata_reader/compressor.py\n[LineBreak.html]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.html\n[LineBreak.js]: https://github.com/kojiishi/unicodedata-reader/blob/main/js/LineBreak.js\n',
-    'author': 'Koji Ishii',
-    'author_email': 'kojii@chromium.org',
-    'maintainer': None,
-    'maintainer_email': None,
-    'url': 'https://github.com/kojiishi/unicodedata-reader',
-    'packages': packages,
-    'package_data': package_data,
-    'install_requires': install_requires,
-    'entry_points': entry_points,
-    'python_requires': '>=3.8,<3.10',
-}
-
-
-setup(**setup_kwargs)

unicodedata-reader-0.1.6/unicodedata_reader/emoji.py

@@ -1,21 +0,0 @@
-#!/usr/bin/env python3
-from typing import Any
-from typing import Callable
-from typing import Dict
-
-from unicodedata_reader import *
-
-
-class UnicodeEmojiDataCli(UnicodeDataCli):
-    def __init__(self):
-        super().__init__()
-        self._entries = UnicodeDataReader.default.emoji()
-
-    def _core_columns(self) -> Dict[str, Callable[[int, str], Any]]:
-        return {
-            'Emoji': lambda code, ch: self._entries.value(code),
-        }
-
-
-if __name__ == '__main__':
-    UnicodeEmojiDataCli().main()