PublicArchive/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2026-05-06 04:37:33 -04:00
Code Issues Packages Projects Releases Wiki Activity

gh-144882: Optimize name tables in unicodedata by excluding names derived by rule NR2 (GH-144883)

Browse Source 
Since the code for rule NR2 is already here, to support CJK unified
ideographs and Tangut ideographs, it can also be used for other names
derived by rule NR2.
This commit is contained in:
Serhiy Storchaka
2026-02-18 12:58:21 +02:00
committed by GitHub
parent e49bfca87c
commit 767b4d02e2
2 changed files with 11509 additions and 12701 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Modules/unicodename_db.h
Generated
+11486 -12698
View File
File diff suppressed because it is too large Load Diff
Tools/unicode/makeunicodedata.py
+23 -3
View File
@@ -764,11 +764,11 @@ def makeunicodename(unicode, trace):
fprint('static const derived_name_range derived_name_ranges[] = {')
for name_range in unicode.derived_name_ranges:
fprint(' {0x%s, 0x%s, %d},' % name_range)
fprint(' {0x%s, 0x%s, %d},' % tuple(name_range))
fprint('};')
fprint('static const char * const derived_name_prefixes[] = {')
for _, prefix in derived_name_range_names:
for prefix in unicode.derived_name_prefixes:
fprint(' "%s",' % prefix)
fprint('};')
@@ -997,6 +997,10 @@ class UnicodeData:
table[char] = from_row(s)
self.derived_name_ranges = []
self.derived_name_prefixes = {
prefix: i
for i, (_, prefix) in enumerate(derived_name_range_names)
}
# expand first-last ranges
field = None
@@ -1017,8 +1021,24 @@ class UnicodeData:
break
s.name = ""
field = None
else:
codepoint = s.codepoint
if s.name.endswith(codepoint):
prefix = s.name[:-len(codepoint)]
j = self.derived_name_prefixes.get(prefix)
if j is None:
j = len(self.derived_name_prefixes)
self.derived_name_prefixes[prefix] = j
if (self.derived_name_ranges
and self.derived_name_ranges[-1][2] == j
and int(self.derived_name_ranges[-1][1], 16) == i - 1):
self.derived_name_ranges[-1][1] = codepoint
else:
self.derived_name_ranges.append(
[codepoint, codepoint, j])
s.name = ""
elif field:
table[i] = from_row(('%X' % i,) + field[1:])
table[i] = from_row(('%04X' % i,) + field[1:])
# public attributes
self.filename = UNICODE_DATA % ''