patch 9.1.0101: upper-case of German sharp s should be U+1E9E

Problem:  upper-case of ß should be U+1E9E (CAPITAL LETTER SHARP S)
          (fenuks)
Solution: Make gU, ~ and g~ convert the U+00DF LATIN SMALL LETTER SHARP S (ß)
          to U+1E9E LATIN CAPITAL LETTER SHARP S (ẞ), update tests
          (glepnir)

This is part of Unicode 5.1.0 from April 2008, so should be fairly safe
to use now and since 2017 is part of the German standard orthography,
according to Wikipedia:
https://en.wikipedia.org/wiki/Capital_%E1%BA%9E#cite_note-auto-12

There is however one exception: UnicodeData.txt for U+00DF
LATIN SMALL LETTER SHARP S does NOT define U+1E9E LATIN CAPITAL LETTER
SHARP S as its upper case version. Therefore, toupper() won't be able
to convert from lower sharp s to upper case sharp s (the other way
around however works, since U+00DF is considered the lower case
character of U+1E9E and therefore tolower() works correctly for the
upper case version).

fixes: #5573
closes: #14018

Signed-off-by: glepnir <glephunter@gmail.com>
Signed-off-by: Christian Brabandt <cb@256bit.org>

diff --git a/src/mbyte.c b/src/mbyte.c
index 2d18a2796a913a616ad2c2e381198062ad0b3af0..0427f0ce3c71f1b1f476629f577bb2a241e9e187 100644 (file)
--- a/src/mbyte.c
+++ b/src/mbyte.c
@@ -3454,6 +3454,8 @@ static convertStruct toLower[] =
        {0x1e900,0x1e921,1,34}
 };
 
+// Note: UnicodeData.txt does not define U+1E9E as being the corresponding upper
+// case letter for U+00DF (ß), however it is part of the toLower table
 static convertStruct toUpper[] =
 {
        {0x61,0x7a,1,-32},

diff --git a/src/ops.c b/src/ops.c
index f6d765bd71d1f9f9bd9f28406af0b64d49e7b76a..3fefbc8a401700d6f75a2230aa8d9bae104f66c0 100644 (file)
--- a/src/ops.c
+++ b/src/ops.c
@@ -1431,18 +1431,19 @@ swapchar(int op_type, pos_T *pos)
     if (c >= 0x80 && op_type == OP_ROT13)
        return FALSE;
 
-    if (op_type == OP_UPPER && c == 0xdf
-                     && (enc_latin1like || STRCMP(p_enc, "iso-8859-2") == 0))
+    // ~ is OP_NOP, g~ is OP_TILDE, gU is OP_UPPER
+    if ((op_type == OP_UPPER || op_type == OP_NOP || op_type == OP_TILDE)
+           && c == 0xdf
+           && (enc_latin1like || STRCMP(p_enc, "iso-8859-2") == 0))
     {
        pos_T   sp = curwin->w_cursor;
 
-       // Special handling of German sharp s: change to "SS".
+       // Special handling for lowercase German sharp s (ß): convert to uppercase (ẞ).
        curwin->w_cursor = *pos;
        del_char(FALSE);
-       ins_char('S');
-       ins_char('S');
+       ins_char(0x1E9E);
        curwin->w_cursor = sp;
-       inc(pos);
+       return TRUE;
     }
 
     if (enc_dbcs != 0 && c >= 0x100)   // No lower/uppercase letter

diff --git a/src/testdir/test_normal.vim b/src/testdir/test_normal.vim
index fb9c3ded53c0a3118a1ab8ae0582dc6ac55a277a..dc68a158a19536d07e26bc1ee90af73c6569af65 100644 (file)
--- a/src/testdir/test_normal.vim
+++ b/src/testdir/test_normal.vim
@@ -2347,19 +2347,19 @@ func Test_normal30_changecase()
   norm! 1ggVu
   call assert_equal('this is a simple test: äüöß', getline('.'))
   norm! VU
-  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖSS', getline('.'))
+  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖẞ', getline('.'))
   norm! guu
-  call assert_equal('this is a simple test: äüöss', getline('.'))
+  call assert_equal('this is a simple test: äüöß', getline('.'))
   norm! gUgU
-  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖSS', getline('.'))
+  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖẞ', getline('.'))
   norm! gugu
-  call assert_equal('this is a simple test: äüöss', getline('.'))
+  call assert_equal('this is a simple test: äüöß', getline('.'))
   norm! gUU
-  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖSS', getline('.'))
+  call assert_equal('THIS IS A SIMPLE TEST: ÄÜÖẞ', getline('.'))
   norm! 010~
-  call assert_equal('this is a SIMPLE TEST: ÄÜÖSS', getline('.'))
+  call assert_equal('this is a SIMPLE TEST: ÄÜÖẞ', getline('.'))
   norm! V~
-  call assert_equal('THIS IS A simple test: äüöss', getline('.'))
+  call assert_equal('THIS IS A simple test: äüöß', getline('.'))
   call assert_beeps('norm! c~')
   %d
   call assert_beeps('norm! ~')

diff --git a/src/testdir/test_utf8_comparisons.vim b/src/testdir/test_utf8_comparisons.vim
index 3431226adae6a9e517feb65c267c9427b2c7f373..20b5762c9dd90b8f805b43be4e18ba451db79dbd 100644 (file)
--- a/src/testdir/test_utf8_comparisons.vim
+++ b/src/testdir/test_utf8_comparisons.vim
@@ -93,4 +93,39 @@ func Test_gap()
   call assert_equal(["ABCD", "", "defg"], getline(1,3))
 endfunc
 
+" test that g~, ~ and gU correclty upper-cases ß
+func Test_uppercase_sharp_ss()
+  new
+  call setline(1, repeat(['ß'], 4))
+
+  call cursor(1, 1)
+  norm! ~
+  call assert_equal('ẞ', getline(line('.')))
+  norm! ~
+  call assert_equal('ß', getline(line('.')))
+
+  call cursor(2, 1)
+  norm! g~l
+  call assert_equal('ẞ', getline(line('.')))
+  norm! g~l
+  call assert_equal('ß', getline(line('.')))
+
+  call cursor(3, 1)
+  norm! gUl
+  call assert_equal('ẞ', getline(line('.')))
+  norm! vgU
+  call assert_equal('ẞ', getline(line('.')))
+  norm! vgu
+  call assert_equal('ß', getline(line('.')))
+  norm! gul
+  call assert_equal('ß', getline(line('.')))
+
+  call cursor(4, 1)
+  norm! vgU
+  call assert_equal('ẞ', getline(line('.')))
+  norm! vgu
+  call assert_equal('ß', getline(line('.')))
+  bw!
+endfunc
+
 " vim: shiftwidth=2 sts=2 expandtab

diff --git a/src/testdir/test_visual.vim b/src/testdir/test_visual.vim
index f0d8edcf848ebae84a45c2dcd1dbe1372be50429..066d7ebb25145a116ce386436e1c380da6fc4662 100644 (file)
--- a/src/testdir/test_visual.vim
+++ b/src/testdir/test_visual.vim
@@ -1020,9 +1020,9 @@ func Test_visual_change_case()
   exe "normal Oblah di\rdoh dut\<Esc>VkUj\r"
   " Uppercase part of two lines
   exe "normal ddppi333\<Esc>k0i222\<Esc>fyllvjfuUk"
-  call assert_equal(['the YOUTUSSEUU end', '- yOUSSTUSSEXu -',
-        \ 'THE YOUTUSSEUU END', '111THE YOUTUSSEUU END', 'BLAH DI', 'DOH DUT',
-        \ '222the yoUTUSSEUU END', '333THE YOUTUßeuu end'], getline(2, '$'))
+  call assert_equal(['the YOUTUẞEUU end', '- yOUẞTUẞEXu -',
+        \ 'THE YOUTUẞEUU END', '111THE YOUTUẞEUU END', 'BLAH DI', 'DOH DUT',
+        \ '222the yoUTUẞEUU END', '333THE YOUTUßeuu end'], getline(2, '$'))
   bwipe!
 endfunc
 

diff --git a/src/version.c b/src/version.c
index 602a2f96a8106b5a160e75f94f71c78c8d238077..fec82525d5dc5543906397322b89cf41e99c91be 100644 (file)
--- a/src/version.c
+++ b/src/version.c
@@ -704,6 +704,8 @@ static char *(features[]) =
 
 static int included_patches[] =
 {   /* Add new patch number below this line */
+/**/
+    101,
 /**/
     100,
 /**/