From: Thorsten Glaser <tg@mirbsd.de>
Date: Fri, 14 Jul 2017 12:02:37 +0000 (+0200)
Subject: UnicodeData has precedence over EastAsianWidth
X-Git-Tag: glibc-2.27~1144
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=580be3035d2e0f479c4ac955bf719b0bf936f5cf;p=thirdparty%2Fglibc.git

UnicodeData has precedence over EastAsianWidth

[BZ #19852]
[BZ #21750]
* unicode-gen/utf8_gen.py: Process EastAsianWidth lines before
  UnicodeData lines so the latter have precedence; remove hack
  to group output by EastAsianWidth ranges.
---

diff --git a/localedata/unicode-gen/utf8_gen.py b/localedata/unicode-gen/utf8_gen.py
index ab03e750a66..12f01d89638 100755
--- a/localedata/unicode-gen/utf8_gen.py
+++ b/localedata/unicode-gen/utf8_gen.py
@@ -221,28 +221,20 @@ def process_width(outfile, ulines, elines):
 
     '''
     width_dict = {}
-    for line in ulines:
-        fields = line.split(";")
-        if fields[4] == "NSM" or fields[2] == "Cf":
-            width_dict[int(fields[0], 16)] = unicode_utils.ucs_symbol(
-                int(fields[0], 16)) + '\t0'
-
     for line in elines:
-        # If an entry in EastAsianWidth.txt is found, it overrides entries in
-        # UnicodeData.txt:
         fields = line.split(";")
         if not '..' in fields[0]:
-            width_dict[int(fields[0], 16)] = unicode_utils.ucs_symbol(
-                int(fields[0], 16)) + '\t2'
+            code_points = (fields[0], fields[0])
         else:
             code_points = fields[0].split("..")
-            for key in range(int(code_points[0], 16),
-                             int(code_points[1], 16)+1):
-                if  key in width_dict:
-                    del width_dict[key]
-            width_dict[int(code_points[0], 16)] = '{:s}...{:s}\t2'.format(
-                unicode_utils.ucs_symbol(int(code_points[0], 16)),
-                unicode_utils.ucs_symbol(int(code_points[1], 16)))
+        for key in range(int(code_points[0], 16),
+                         int(code_points[1], 16)+1):
+            width_dict[key] = unicode_utils.ucs_symbol(key) + '\t2'
+    for line in ulines:
+        fields = line.split(";")
+        if fields[4] == "NSM" or fields[2] == "Cf":
+            width_dict[int(fields[0], 16)] = unicode_utils.ucs_symbol(
+                int(fields[0], 16)) + '\t0'
 
     for key in sorted(width_dict):
         outfile.write(width_dict[key]+'\n')