[pkgsrc/trunk]: pkgsrc/textproc/split-thai Update to 0.7

[scole <scole%pkgsrc.org@localhost>]

details:   https://anonhg.NetBSD.org/pkgsrc/rev/797cacdc4483
branches:  trunk
changeset: 437309:797cacdc4483
user:      scole <scole%pkgsrc.org@localhost>
date:      Thu Aug 20 14:20:27 2020 +0000

description:
Update to 0.7
- don't skip strings with numbers [0-9] for st-icu

diffstat:

 textproc/split-thai/Makefile        |  4 ++--
 textproc/split-thai/files/st-icu.cc |  7 ++++---
 2 files changed, 6 insertions(+), 5 deletions(-)

diffs (51 lines):

diff -r 2bf616f39023 -r 797cacdc4483 textproc/split-thai/Makefile
--- a/textproc/split-thai/Makefile      Thu Aug 20 14:01:48 2020 +0000
+++ b/textproc/split-thai/Makefile      Thu Aug 20 14:20:27 2020 +0000
@@ -1,6 +1,6 @@
-# $NetBSD: Makefile,v 1.6 2020/08/19 16:52:25 scole Exp $
+# $NetBSD: Makefile,v 1.7 2020/08/20 14:20:27 scole Exp $
 
-PKGNAME=       split-thai-0.6
+PKGNAME=       split-thai-0.7
 CATEGORIES=    textproc
 MAINTAINER=    pkgsrc-users%NetBSD.org@localhost
 COMMENT=       Utilities to split UTF-8 Thai text into words
diff -r 2bf616f39023 -r 797cacdc4483 textproc/split-thai/files/st-icu.cc
--- a/textproc/split-thai/files/st-icu.cc       Thu Aug 20 14:01:48 2020 +0000
+++ b/textproc/split-thai/files/st-icu.cc       Thu Aug 20 14:20:27 2020 +0000
@@ -7,8 +7,8 @@
 #include <unicode/brkiter.h>
 #include <unicode/regex.h>
 #include <unicode/ucnv.h>
+#include <unicode/ustdio.h>
 #include <unicode/ustream.h>
-#include <unicode/ustdio.h>
 
 using namespace std;
 using namespace icu;
@@ -18,6 +18,7 @@
 const UnicodeString thai_rexp = "[\\u0e00-\\u0e7f]+";
 const UnicodeString thai_consonant = "[\\u0e01-\\u0e2e]+";
 const UnicodeString thai_num_rexp = "[\\u0e50-\\u0e59]+";
+const UnicodeString number_rexp = "[0-9\\u0e50-\\u0e59]+";
 const UnicodeString thai_nonnum_rexp = "[\\u0e01-\\u0e4f\\u0e5a-\\u0e7f]+";
 
 void usage() {
@@ -56,7 +57,7 @@
 // add spaces to string with thai numbers
 UnicodeString space_thai_numbers(const UnicodeString &s) {
        // return string unmodified if no numbers
-       if ( ! matches_regexp(s, thai_num_rexp) ) {
+       if ( ! matches_regexp(s, number_rexp) ) {
                return s;
        }
 
@@ -105,7 +106,7 @@
        }
 
        // only one word found, trim and done
-       if ( vbreak.size() == 1 ) {
+       if ( vbreak.size() <= 1 ) {
                UnicodeString ss(s);
                return ss.trim();
        }