From 216a1d1937f2844d311f703e5a8e0ee41806c7f2 Mon Sep 17 00:00:00 2001 From: "jan.nijtmans" Date: Mon, 9 Dec 2019 19:36:21 +0000 Subject: Attempt to fix [5f236bc67a]: valgrind report for Tcl_UniCharToUtf --- generic/tclEncoding.c | 2 +- tests/encoding.test | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) diff --git a/generic/tclEncoding.c b/generic/tclEncoding.c index ffa23f3..8990385 100644 --- a/generic/tclEncoding.c +++ b/generic/tclEncoding.c @@ -2365,7 +2365,7 @@ UtfToUtfProc( /* A surrogate character is detected, handle especially */ Tcl_UniChar low = *chPtr; size_t len = (src <= srcEnd-3) ? Tcl_UtfToUniChar(src, &low) : 0; - if (((low | 0x3FF) != 0xDFFF) || !(*chPtr & 0x800)) { + if (((low | 0x3FF) != 0xDFFF) || (*chPtr & 0x400)) { *dst++ = (char) (((*chPtr >> 12) | 0xE0) & 0xEF); *dst++ = (char) (((*chPtr >> 6) | 0x80) & 0xBF); *dst++ = (char) ((*chPtr | 0x80) & 0xBF); diff --git a/tests/encoding.test b/tests/encoding.test index b5a44df..1c7ee11 100644 --- a/tests/encoding.test +++ b/tests/encoding.test @@ -362,6 +362,42 @@ test encoding-15.9 {UtfToUtfProc emoji character output} { binary scan $y H* z list [string length $x] [string length $y] $z } {3 7 edb882eda0bd58} +test encoding-15.10 {UtfToUtfProc high surrogate character output} { + set x \uDE02\xE9 + set y [encoding convertto utf-8 \uDE02\xE9] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {2 5 edb882c3a9} +test encoding-15.11 {UtfToUtfProc low surrogate character output} { + set x \uDA02\xE9 + set y [encoding convertto utf-8 \uDA02\xE9] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {2 5 eda882c3a9} +test encoding-15.12 {UtfToUtfProc high surrogate character output} { + set x \uDE02Y + set y [encoding convertto utf-8 \uDE02Y] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {2 4 edb88259} +test encoding-15.13 {UtfToUtfProc low surrogate character output} { + set x \uDA02Y + set y [encoding convertto utf-8 \uDA02Y] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {2 4 eda88259} +test encoding-15.14 {UtfToUtfProc high surrogate character output} { + set x \uDE02 + set y [encoding convertto utf-8 \uDE02] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {1 3 edb882} +test encoding-15.15 {UtfToUtfProc low surrogate character output} { + set x \uDA02 + set y [encoding convertto utf-8 \uDA02] + binary scan $y H* z + list [string length $x] [string length $y] $z +} {1 3 eda882} test encoding-16.1 {UnicodeToUtfProc} { set val [encoding convertfrom unicode NN] -- cgit v0.12