mjohnson/espeak-ng
1
0
Fork 0
mirror of https://github.com/rhasspy/espeak-ng.git synced 2026-11-15 01:54:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Do not include supplementary data in the UCD APIs.

Browse Source 
This removes support for the CSUR (ConScript Unicode Registry) data
in the main Unicode APIs. This data should be accessed through a
different API.
This commit is contained in:
Reece H. Dunn
2014-07-14 13:12:22 +01:00
parent 8836af4942
commit ced06ed0f4
6 changed files with 46 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/categories.py
+2 -5
View File
@@ -1,6 +1,6 @@
#!/usr/bin/python
# Copyright (C) 2012 Reece H. Dunn
# Copyright (C) 2012, 2014 Reece H. Dunn
#
# This file is part of ucd-tools.
#
@@ -28,9 +28,6 @@ unicode_chars = {}
for data in ucd.parse_ucd_data(ucd_rootdir, 'UnicodeData'):
for codepoint in data['CodePoint']:
unicode_chars[codepoint] = data['GeneralCategory']
for data in ucd.parse_ucd_data('supplemental', 'Klingon'):
for codepoint in data['CodePoint']:
unicode_chars[codepoint] = data['GeneralCategory']
# This map is a combination of the information in the UnicodeData and Blocks
# data files. It is intended to reduce the number of character tables that
@@ -52,7 +49,7 @@ category_sets = [
# These categories have many pages consisting of just this category:
# Cn -- Unassigned
# Lo -- CJK Ideographs
special_categories = ['Cn', 'Lo', 'Sm', 'So']
special_categories = ['Cn', 'Co', 'Lo', 'Sm', 'So']
category_tables = {}
for codepoints, category, comment in category_sets:
tools/scripts.py
+1 -4
View File
@@ -1,6 +1,6 @@
#!/usr/bin/python
# Copyright (C) 2012 Reece H. Dunn
# Copyright (C) 2012, 2014 Reece H. Dunn
#
# This file is part of ucd-tools.
#
@@ -28,9 +28,6 @@ unicode_chars = {}
for data in ucd.parse_ucd_data(ucd_rootdir, 'Scripts'):
for codepoint in data['Range']:
unicode_chars[codepoint] = data['Script']
for data in ucd.parse_ucd_data('supplemental', 'Klingon'):
for codepoint in data['CodePoint']:
unicode_chars[codepoint] = data['Script']
# This map is a combination of the information in the UnicodeData and Blocks
# data files. It is intended to reduce the number of character tables that