pythongh-82927: Update files related to HTML entities. (pythonGH-92504)

ezio-melotti · web-flow · commit f28ec34c5c69 · 2022-06-21T22:03:12.000+02:00
diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
@@ -53,6 +53,7 @@ Python/pythonrun.c            @iritkatriel
 /Lib/html/                    @ezio-melotti
 /Lib/_markupbase.py           @ezio-melotti
 /Lib/test/test_html*.py       @ezio-melotti
+/Tools/scripts/*html5*        @ezio-melotti
 
 # Import (including importlib).
 # Ignoring importlib.h so as to not get flagged on
diff --git a/Doc/library/html.entities.rst b/Doc/library/html.entities.rst
@@ -34,12 +34,12 @@ This module defines four dictionaries, :data:`html5`,
 
 .. data:: name2codepoint
 
-   A dictionary that maps HTML entity names to the Unicode code points.
+   A dictionary that maps HTML4 entity names to the Unicode code points.
 
 
 .. data:: codepoint2name
 
-   A dictionary that maps Unicode code points to HTML entity names.
+   A dictionary that maps Unicode code points to HTML4 entity names.
 
 
 .. rubric:: Footnotes
diff --git a/Lib/html/entities.py b/Lib/html/entities.py
@@ -3,8 +3,7 @@
 __all__ = ['html5', 'name2codepoint', 'codepoint2name', 'entitydefs']
 
 
-# maps the HTML entity name to the Unicode code point
-# from https://html.spec.whatwg.org/multipage/named-characters.html
+# maps HTML4 entity name to the Unicode code point
 name2codepoint = {
     'AElig':    0x00c6, # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1
     'Aacute':   0x00c1, # latin capital letter A with acute, U+00C1 ISOlat1
@@ -261,7 +260,11 @@
 }
 
 
-# maps the HTML5 named character references to the equivalent Unicode character(s)
+# HTML5 named character references
+# Generated by 'Tools/scripts/parse_html5_entities.py'
+# from https://html.spec.whatwg.org/entities.json and
+# https://html.spec.whatwg.org/multipage/named-characters.html.
+# Map HTML5 named character references to the equivalent Unicode character(s).
 html5 = {
     'Aacute': '\xc1',
     'aacute': '\xe1',
diff --git a/Misc/NEWS.d/next/Tools-Demos/2022-06-19-14-56-33.gh-issue-86087.R8MkRy.rst b/Misc/NEWS.d/next/Tools-Demos/2022-06-19-14-56-33.gh-issue-86087.R8MkRy.rst
@@ -0,0 +1,2 @@
+The ``Tools/scripts/parseentities.py`` script used to parse HTML4 entities
+has been removed.
diff --git a/Tools/scripts/parse_html5_entities.py b/Tools/scripts/parse_html5_entities.py
@@ -2,10 +2,14 @@
 """
 Utility for parsing HTML5 entity definitions available from:
 
-    http://dev.w3.org/html5/spec/entities.json
+    https://html.spec.whatwg.org/entities.json
+    https://html.spec.whatwg.org/multipage/named-characters.html
 
-Written by Ezio Melotti and Iuliia Proskurnia.
+The page now contains the following note:
+
+    "This list is static and will not be expanded or changed in the future."
 
+Written by Ezio Melotti and Iuliia Proskurnia.
 """
 
 import os
@@ -14,7 +18,9 @@
 from urllib.request import urlopen
 from html.entities import html5
 
-entities_url = 'http://dev.w3.org/html5/spec/entities.json'
+PAGE_URL = 'https://html.spec.whatwg.org/multipage/named-characters.html'
+ENTITIES_URL = 'https://html.spec.whatwg.org/entities.json'
+HTML5_SECTION_START = '# HTML5 named character references'
 
 def get_json(url):
     """Download the json file from the url and returns a decoded object."""
@@ -62,29 +68,32 @@ def write_items(entities, file=sys.stdout):
     # be before their equivalent lowercase version.
     keys = sorted(entities.keys())
     keys = sorted(keys, key=str.lower)
+    print(HTML5_SECTION_START, file=file)
+    print(f'# Generated by {sys.argv[0]!r}\n'
+          f'# from {ENTITIES_URL} and\n'
+          f'# {PAGE_URL}.\n'
+          f'# Map HTML5 named character references to the '
+          f'equivalent Unicode character(s).', file=file)
     print('html5 = {', file=file)
     for name in keys:
-        print('    {!r}: {!a},'.format(name, entities[name]), file=file)
+        print(f'    {name!r}: {entities[name]!a},', file=file)
     print('}', file=file)
 
 
 if __name__ == '__main__':
     # without args print a diff between html.entities.html5 and new_html5
     # with --create print the new html5 dict
     # with --patch patch the Lib/html/entities.py file
-    new_html5 = create_dict(get_json(entities_url))
+    new_html5 = create_dict(get_json(ENTITIES_URL))
     if '--create' in sys.argv:
-        print('# map the HTML5 named character references to the '
-              'equivalent Unicode character(s)')
-        print('# Generated by {}.  Do not edit manually.'.format(__file__))
         write_items(new_html5)
     elif '--patch' in sys.argv:
         fname = 'Lib/html/entities.py'
         temp_fname = fname + '.temp'
         with open(fname) as f1, open(temp_fname, 'w') as f2:
             skip = False
             for line in f1:
-                if line.startswith('html5 = {'):
+                if line.startswith(HTML5_SECTION_START):
                     write_items(new_html5, file=f2)
                     skip = True
                     continue
diff --git a/Tools/scripts/parseentities.py b/Tools/scripts/parseentities.py

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	+The ``Tools/scripts/parseentities.py`` script used to parse HTML4 entities
	`2`	`+has been removed.`