mjohnson/espeak-ng
1
0
Fork 0
mirror of https://github.com/rhasspy/espeak-ng.git synced 2026-11-05 06:45:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

isspace: don't include <noBreak> characters.

Browse Source
This commit is contained in:
Reece H. Dunn
2017-02-12 11:11:52 +00:00
parent 5f9dc111cf
commit f109bb918f
2 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ctype.c
+9 -1
View File
@@ -140,10 +140,18 @@ int ucd_isspace(codepoint_t c)
{
case UCD_CATEGORY_Zl:
case UCD_CATEGORY_Zp:
return 1;
case UCD_CATEGORY_Zs:
switch (c) // Exclude characters with the <noBreak> DispositionType
{
case 0x00A0: // U+00A0 : NO-BREAK SPACE
case 0x2007: // U+2007 : FIGURE SPACE
case 0x202F: // U+202F : NARROW NO-BREAK SPACE
return 0;
}
return 1;
case UCD_CATEGORY_Cc:
switch (c) // Some control characters are also whitespace characters:
switch (c) // Include control characters marked as White_Space
{
case 0x09: // U+0009 : CHARACTER TABULATION
case 0x0A: // U+000A : LINE FEED
tools/printdata.py
+5 -1
View File
@@ -50,7 +50,11 @@ def isxdigit(data):
return 1 if data['CodePoint'].char() in '0123456789ABCDEFabcdef' else 0
def isspace(data):
return data.get('White_Space', 0)
if data.get('White_Space', 0):
dt = data.get('DecompositionType', '')
return 1 if dt == None or not dt.startswith('<noBreak>') else 0
else:
return 0
def isupper(data):
if data.get('LowerCase', null) != null: