mjohnson/espeak-ng
1
0
Fork 0
mirror of https://github.com/rhasspy/espeak-ng.git synced 2026-11-02 22:07:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

isblank: don't include <noBreak> characters, and add tests for this API.

Browse Source
This commit is contained in:
Reece H. Dunn
2017-02-12 11:47:30 +00:00
parent f109bb918f
commit c9f2940373
5 changed files with 19 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ctype.c
+7
View File
@@ -58,6 +58,13 @@ int ucd_isblank(codepoint_t c)
switch (ucd_lookup_category(c))
{
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:
return c == 0x09; // U+0009 : CHARACTER TABULATION
tests/printcdata.c
+1 -1
View File
@@ -248,7 +248,7 @@ int main(int argc, char **argv)
else
{
for (codepoint_t c = 0; c <= 0x10FFFF; ++c)
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %iu %il\n");
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %ib %iu %il\n");
}
return 0;
}
tests/printucddata.c
+1 -1
View File
@@ -243,7 +243,7 @@ int main(int argc, char **argv)
else
{
for (codepoint_t c = 0; c <= 0x10FFFF; ++c)
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %iu %il\n");
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %ib %iu %il\n");
}
return 0;
}
tests/printucddata_cpp.cpp
+1 -1
View File
@@ -243,7 +243,7 @@ int main(int argc, char **argv)
else
{
for (ucd::codepoint_t c = 0; c <= 0x10FFFF; ++c)
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %iu %il\n");
uprintf(stdout, c, format ? format : "%pH %s %C %c %UH %LH %TH %id %ix %is %ib %iu %il\n");
}
return 0;
}
tools/printdata.py
+9 -2
View File
@@ -56,6 +56,13 @@ def isspace(data):
else:
return 0
def isblank(data): # word separator
if data.get('GeneralCategory', 'Cn') == 'Zs' or data['CodePoint'].char() == '\t':
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:
return 1
@@ -85,10 +92,10 @@ if __name__ == '__main__':
if title == null: title = codepoint
if upper == null: upper = codepoint
if lower == null: lower = codepoint
print('%s %s %s %s %s %s %s %s %s %s %s %s' % (
print('%s %s %s %s %s %s %s %s %s %s %s %s %s' % (
codepoint, script,
data.get('GeneralCategory', 'Cn')[0], data.get('GeneralCategory', 'Cn'),
upper, lower, title,
isdigit(data), isxdigit(data),
isspace(data),
isspace(data), isblank(data),
isupper(data), islower(data)))