From 78b187fe71dba0f3710be978050e08fde81efd85 Mon Sep 17 00:00:00 2001
From: "jan.nijtmans" <nijtmans@users.sourceforge.net>
Date: Fri, 8 Apr 2016 12:23:50 +0000
Subject: Fix [8663689908d3304a74fee525cd04aa4162e86391|8663689908d3]: regexp
 \\w missing characters

---
 generic/regc_lex.c | 19 ++++++++++++++++---
 tests/utf.test     |  2 +-
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/generic/regc_lex.c b/generic/regc_lex.c
index 8d07c59..51cf8a4 100644
--- a/generic/regc_lex.c
+++ b/generic/regc_lex.c
@@ -256,20 +256,33 @@ static const chr brbacks[] = {	/* \s within brackets */
     CHR('s'), CHR('p'), CHR('a'), CHR('c'), CHR('e'),
     CHR(':'), CHR(']')
 };
+
+#define PUNCT_CONN \
+	CHR('_'), \
+	0x203f /* UNDERTIE */, \
+	0x2040 /* CHARACTER TIE */,\
+	0x2054 /* INVERTED UNDERTIE */,\
+	0xfe33 /* PRESENTATION FORM FOR VERTICAL LOW LINE */, \
+	0xfe34 /* PRESENTATION FORM FOR VERTICAL WAVY LOW LINE */, \
+	0xfe4d /* DASHED LOW LINE */, \
+	0xfe4e /* CENTRELINE LOW LINE */, \
+	0xfe4f /* WAVY LOW LINE */, \
+	0xff3f /* FULLWIDTH LOW LINE */
+
 static const chr backw[] = {	/* \w */
     CHR('['), CHR('['), CHR(':'),
     CHR('a'), CHR('l'), CHR('n'), CHR('u'), CHR('m'),
-    CHR(':'), CHR(']'), CHR('_'), CHR(']')
+    CHR(':'), CHR(']'), PUNCT_CONN, CHR(']')
 };
 static const chr backW[] = {	/* \W */
     CHR('['), CHR('^'), CHR('['), CHR(':'),
     CHR('a'), CHR('l'), CHR('n'), CHR('u'), CHR('m'),
-    CHR(':'), CHR(']'), CHR('_'), CHR(']')
+    CHR(':'), CHR(']'), PUNCT_CONN, CHR(']')
 };
 static const chr brbackw[] = {	/* \w within brackets */
     CHR('['), CHR(':'),
     CHR('a'), CHR('l'), CHR('n'), CHR('u'), CHR('m'),
-    CHR(':'), CHR(']'), CHR('_')
+    CHR(':'), CHR(']'), PUNCT_CONN
 };
 
 /*
diff --git a/tests/utf.test b/tests/utf.test
index 30200c1..e8ee374 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -283,7 +283,7 @@ test utf-21.1 {TclUniCharIsAlnum} {
 } {1}
 test utf-21.2 {unicode alnum char in regc_locale.c} {
     # this returns 1 with Unicode 7 compliance
-    list [regexp {^[[:alnum:]]+$} \u1040\u021f\u0220] [regexp {^\w+$} \u1040\u021f\u0220]
+    list [regexp {^[[:alnum:]]+$} \u1040\u021f\u0220] [regexp {^\w+$} \u1040\u021f\u0220_\u203f\u2040\u2054\ufe33\ufe34\ufe4d\ufe4e\ufe4f\uff3f]
 } {1 1}
 test utf-21.3 {unicode print char in regc_locale.c} {
     # this returns 1 with Unicode 7 compliance
-- 
cgit v0.12