gh-82927: Update files related to HTML entities. (GH-92504)

.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

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

Lib/html/entities.py

@@ -3,8 +3,7 @@
 __all__ = ['html5', 'name2codepoint', 'codepoint2name', 'entitydefs']
 
 
-# maps the HTML entity name to the Unicode code point
+# maps HTML4 entity name to the Unicode code point
-# from https://html.spec.whatwg.org/multipage/named-characters.html
 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 @@ name2codepoint = {
 }
 
 
-# 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',

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.

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
+
+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 @@ import json
 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."""
@@ -62,9 +68,15 @@ 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)
 
 
@@ -72,11 +84,8 @@ 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'
@@ -84,7 +93,7 @@ if __name__ == '__main__':
         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

Tools/scripts/parseentities.py

@@ -1,64 +0,0 @@
-#!/usr/bin/env python3
-""" Utility for parsing HTML entity definitions available from:
-
-      http://www.w3.org/ as e.g.
-      http://www.w3.org/TR/REC-html40/HTMLlat1.ent
-
-    Input is read from stdin, output is written to stdout in form of a
-    Python snippet defining a dictionary "entitydefs" mapping literal
-    entity name to character or numeric entity.
-
-    Marc-Andre Lemburg, mal@lemburg.com, 1999.
-    Use as you like. NO WARRANTIES.
-
-"""
-import re,sys
-
-entityRE = re.compile(r'<!ENTITY +(\w+) +CDATA +"([^"]+)" +-- +((?:.|\n)+?) *-->')
-
-def parse(text,pos=0,endpos=None):
-
-    pos = 0
-    if endpos is None:
-        endpos = len(text)
-    d = {}
-    while 1:
-        m = entityRE.search(text,pos,endpos)
-        if not m:
-            break
-        name,charcode,comment = m.groups()
-        d[name] = charcode,comment
-        pos = m.end()
-    return d
-
-def writefile(f,defs):
-
-    f.write("entitydefs = {\n")
-    items = sorted(defs.items())
-    for name, (charcode,comment) in items:
-        if charcode[:2] == '&#':
-            code = int(charcode[2:-1])
-            if code < 256:
-                charcode = r"'\%o'" % code
-            else:
-                charcode = repr(charcode)
-        else:
-            charcode = repr(charcode)
-        comment = ' '.join(comment.split())
-        f.write("    '%s':\t%s,  \t# %s\n" % (name,charcode,comment))
-    f.write('\n}\n')
-
-if __name__ == '__main__':
-    if len(sys.argv) > 1:
-        with open(sys.argv[1]) as infile:
-            text = infile.read()
-    else:
-        text = sys.stdin.read()
-
-    defs = parse(text)
-
-    if len(sys.argv) > 2:
-        with open(sys.argv[2],'w') as outfile:
-            writefile(outfile, defs)
-    else:
-        writefile(sys.stdout, defs)