@@ -7,6 +7,10 @@ These are eSpeak NG specific modifications to the `ucd-tools` project: | |||
* `data/espeak-ng` data files for eSpeak NG extended data. | |||
* espeak-ng PropList property lookup as part of the `ucd_property` API. | |||
## (In Development) | |||
* Make the ispunct ctype compatibility implementation conformant. | |||
## 10.0.0 - 2017-06-25 | |||
* Add `iswblank` and `iswxdigit` compatibility. |
@@ -17,8 +17,8 @@ this information within a C or C++ program. | |||
The project uses and supports the following sources of Unicode codepoint data: | |||
* [Unicode Character Database](http://www.unicode.org/Public/9.0.0/ucd/) 9.0.0 | |||
* [Unicode Emoji](http://www.unicode.org/Public/emoji/4.0/) 4.0 (UTR #51) | |||
* [Unicode Character Database](http://www.unicode.org/Public/10.0.0/ucd/) 10.0.0 | |||
* [Unicode Emoji](http://www.unicode.org/Public/emoji/5.0/) 5.0 (UTR #51) | |||
* [ConScript Unicode Registry](http://www.evertype.com/standards/csur/) | |||
## Build Dependencies |
@@ -1,6 +1,6 @@ | |||
/* ctype-style APIs. | |||
* | |||
* Copyright (C) 2012-2017 Reece H. Dunn | |||
* Copyright (C) 2012-2018 Reece H. Dunn | |||
* | |||
* This file is part of ucd-tools. | |||
* | |||
@@ -151,19 +151,7 @@ int ucd_isprint(codepoint_t c) | |||
int ucd_ispunct(codepoint_t c) | |||
{ | |||
switch (ucd_lookup_category(c)) | |||
{ | |||
case UCD_CATEGORY_Pc: | |||
case UCD_CATEGORY_Pd: | |||
case UCD_CATEGORY_Pe: | |||
case UCD_CATEGORY_Pf: | |||
case UCD_CATEGORY_Pi: | |||
case UCD_CATEGORY_Po: | |||
case UCD_CATEGORY_Ps: | |||
return 1; | |||
default: | |||
return 0; | |||
} | |||
return ucd_isgraph(c) && !ucd_isalnum(c); | |||
} | |||
int ucd_isspace(codepoint_t c) |
@@ -79,10 +79,7 @@ def isblank(data): # word separator | |||
return 0 | |||
def ispunct(data): | |||
if data.get('GeneralCategory', 'Cn')[0] in 'P': | |||
return 1 | |||
else: | |||
return 0 | |||
return 1 if isgraph(data) and not isalnum(data) else 0 | |||
def isprint(data): | |||
if data.get('GeneralCategory', 'Cn')[0] in 'LMNPSZ': # not in 'CI' |