Improve clip() and width() with hyperlinks and overtyping

.github/workflows/ci.yml

@@ -72,10 +72,6 @@ jobs:
           - "3.12"
           - "3.13"
           - "3.14"
-          - "pypy-3.8"
-          - "pypy-3.9"
-          - "pypy-3.10"
-          - "pypy-3.11"
 
     runs-on: ${{ matrix.os }}
     container: ${{ matrix.container }}

bin/update-tables.py

@@ -1,13 +1,14 @@
 #!/usr/bin/env python
 """
-Update the Unicode code tables for wcwidth.  This is code generation using jinja2.
+Update the Unicode code tables for wcwidth.
 
-This is typically executed through tox,
+This is code generation using jinja2. This is typically executed through tox,
 
 $ tox -e update
 
 https://github.com/jquast/wcwidth
 """
+
 from __future__ import annotations
 
 # std imports
@@ -24,7 +25,7 @@
 from pathlib import Path
 from dataclasses import field, fields, dataclass
 
-from typing import Any, Mapping, Iterable, Iterator, Sequence, Collection
+from typing import Any, Mapping, Iterable, Iterator, Optional, Sequence, Collection
 
 try:
     from typing import Self
@@ -108,9 +109,10 @@ def _bisearch(ucs, table):
 @dataclass(order=True, frozen=True)
 class UnicodeVersion:
     """A class for comparable unicode version."""
+
     major: int
     minor: int
-    micro: int | None
+    micro: Optional[int]
 
     @classmethod
     def parse(cls, version_str: str) -> UnicodeVersion:
@@ -138,7 +140,8 @@ def __str__(self) -> str:
 @dataclass(frozen=True)
 class TableEntry:
     """An entry of a unicode table."""
-    code_range: tuple[int, int] | None
+
+    code_range: Optional[tuple[int, int]]
     properties: tuple[str, ...]
     comment: str
 
@@ -255,6 +258,7 @@ class UnicodeTableRenderCtx(RenderContext):
 @dataclass
 class RenderDefinition:
     """Base class, do not instantiate it directly."""
+
     jinja_filename: str
     output_filename: str
     render_context: RenderContext
@@ -330,6 +334,7 @@ def new(cls, filename: str, context: UnicodeTableRenderCtx) -> Self:
 @dataclass(frozen=True)
 class GraphemeTableRenderCtx(RenderContext):
     """Render context for grapheme tables (latest version only)."""
+
     unicode_version: str
     tables: Mapping[str, TableDef]
 
@@ -880,7 +885,6 @@ def fetch_table_grapheme_data() -> GraphemeTableRenderCtx:
     tables.update(parse_indic_syllabic_category(
         UnicodeDataFile.IndicSyllabicCategory(latest_version)
     ))
-
     return GraphemeTableRenderCtx(str(latest_version), tables)
 
 
@@ -895,6 +899,7 @@ class UnicodeDataFile:
     TestEmojiVariationSequences, these files should be forcefully re-fetched CLI argument '--no-
     check-last-modified'.
     """
+
     URL_DERIVED_AGE = 'https://www.unicode.org/Public/UCD/latest/ucd/DerivedAge.txt'
     URL_EASTASIAN_WIDTH = 'https://www.unicode.org/Public/{version}/ucd/EastAsianWidth.txt'
     URL_DERIVED_CATEGORY = 'https://www.unicode.org/Public/{version}/ucd/extracted/DerivedGeneralCategory.txt'

bin/verify-table-integrity.py

@@ -65,6 +65,7 @@
     +DerivedGeneralCategory-8.0.0.txt:19B0..19C9    ; Lo #  [26] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2
 
 """
+
 # std imports
 import logging
 

bin/wcwidth-browser.py

@@ -376,6 +376,7 @@ def page_size(self):
 
 class Pager:
     """A less(1)-like browser for browsing unicode characters."""
+
     # pylint: disable=too-many-instance-attributes
 
     #: screen state for next draw method(s).
@@ -520,14 +521,13 @@ def run(self, writer, reader):
         """
         Pager entry point.
 
-        In interactive mode (terminal is a tty), run until
-        ``process_keystroke()`` detects quit keystroke ('q').  In
-        non-interactive mode, exit after displaying all unicode points.
+        In interactive mode (terminal is a tty), run until ``process_keystroke()`` detects quit
+        keystroke ('q').  In non-interactive mode, exit after displaying all unicode points.
 
         :param writer: callable writes to output stream, receiving unicode.
         :type writer: callable
-        :param reader: callable reads keystrokes from input stream, sending
-                       instance of blessed.keyboard.Keystroke.
+        :param reader: callable reads keystrokes from input stream, sending instance of
+            blessed.keyboard.Keystroke.
         :type reader: callable
         """
         self.initialize_page_data()
@@ -720,8 +720,8 @@ def draw_heading(self, writer):
         """
         Conditionally redraw screen when ``dirty`` attribute is valued REFRESH.
 
-        When Pager attribute ``dirty`` is ``STATE_REFRESH``, cursor is moved
-        to (0,0), screen is cleared, and heading is displayed.
+        When Pager attribute ``dirty`` is ``STATE_REFRESH``, cursor is moved to (0,0), screen is
+        cleared, and heading is displayed.
 
         :param callable writer: callable writes to output stream, receiving unicode.
         :return: True if class attribute ``dirty`` is ``STATE_REFRESH``.
@@ -787,8 +787,8 @@ def page_view(self, data):
         """
         Generator yields text to be displayed for the current unicode pageview.
 
-        :param list[(unicode, unicode)] data: The current page's data as tuple
-            of ``(ucs, name)``.
+        :param list[(unicode, unicode)] data: The current page's data as tuple     of ``(ucs,
+        name)``.
         :returns: generator for full-page text for display
         """
         if self.term.is_a_tty:

bin/wcwidth-libc-comparator.py

@@ -13,6 +13,7 @@
 This program accepts one optional command-line argument, the unicode version
 level for our library to use when comparing to libc.
 """
+
 # pylint: disable=C0103
 #         Invalid module name "wcwidth-libc-comparator"
 

code_templates/grapheme_table.py.j2

@@ -4,7 +4,7 @@ Exports grapheme cluster break property tables for Unicode version {{ unicode_ve
 This module provides lookup tables for Unicode grapheme cluster break properties as defined in UAX
 #29: Unicode Text Segmentation.
 
-This code generated by {{this_filepath}} on {{utc_now}}.
+This code generated by python wcwidth project.
 """
 # pylint: disable=duplicate-code
 {%- for var_name, table_def in tables.items() %}

code_templates/python_table.py.j2

@@ -1,7 +1,7 @@
 """
 Exports {{ variable_name }} table keyed by supporting unicode version level.
 
-This code generated by {{this_filepath}} on {{utc_now}}.
+This code generated by python wcwidth project.
 """
 # pylint: disable=duplicate-code
 {{ variable_name }} = {

code_templates/unicode_versions.py.j2

@@ -1,7 +1,7 @@
 """
 Exports function list_versions() for unicode version level support.
 
-This code generated by {{this_filepath}} on {{utc_now}}.
+This code generated by python wcwidth project.
 """
 
 from __future__ import annotations

docs/api.rst

@@ -36,4 +36,8 @@ requirements.txt or equivalent. Their signatures will never change.
 
 .. autofunction:: wcwidth.list_versions
 
+.. autofunction:: wcwidth.Hyperlink
+
+.. autofunction:: wcwidth.HyperlinkParams
+
 .. _SEMVER: https://semver.org