patch 8.0.0519: character classes are not well tested

Problem:    Character classes are not well tested. They can differ between
            platforms.
Solution:   Add tests.  In the documentation make clear which classes depend
            on what library function.  Only use :cntrl: and :graph: for ASCII.
            (Kazunobu Kuriyama, Dominique Pelle, closes #1560)
            Update the documentation.

4 files changed, 64 insertions, 15 deletions

diff --git a/src/regexp.c b/src/regexp.c
index 91b8015bb..b4fe7d7eb 100644
--- a/src/regexp.c
+++ b/src/regexp.c
@@ -2555,17 +2555,17 @@ collection:
 				regc('\t');
 				break;
 			    case CLASS_CNTRL:
-				for (cu = 1; cu <= 255; cu++)
+				for (cu = 1; cu <= 127; cu++)
 				    if (iscntrl(cu))
 					regmbc(cu);
 				break;
 			    case CLASS_DIGIT:
-				for (cu = 1; cu <= 255; cu++)
+				for (cu = 1; cu <= 127; cu++)
 				    if (VIM_ISDIGIT(cu))
 					regmbc(cu);
 				break;
 			    case CLASS_GRAPH:
-				for (cu = 1; cu <= 255; cu++)
+				for (cu = 1; cu <= 127; cu++)
 				    if (isgraph(cu))
 					regmbc(cu);
 				break;
diff --git a/src/regexp_nfa.c b/src/regexp_nfa.c
index 20ef1869e..e6d8255e9 100644
--- a/src/regexp_nfa.c
+++ b/src/regexp_nfa.c
@@ -4871,7 +4871,7 @@ check_char_class(int class, int c)
 		return OK;
 	    break;
 	case NFA_CLASS_CNTRL:
-	    if (c >= 1 && c <= 255 && iscntrl(c))
+	    if (c >= 1 && c <= 127 && iscntrl(c))
 		return OK;
 	    break;
 	case NFA_CLASS_DIGIT:
@@ -4879,7 +4879,7 @@ check_char_class(int class, int c)
 		return OK;
 	    break;
 	case NFA_CLASS_GRAPH:
-	    if (c >= 1 && c <= 255 && isgraph(c))
+	    if (c >= 1 && c <= 127 && isgraph(c))
 		return OK;
 	    break;
 	case NFA_CLASS_LOWER:
diff --git a/src/testdir/test_regexp_utf8.vim b/src/testdir/test_regexp_utf8.vim
index d2259835c..47bd7014a 100644
--- a/src/testdir/test_regexp_utf8.vim
+++ b/src/testdir/test_regexp_utf8.vim
@@ -38,12 +38,21 @@ func s:classes_test()
   set isprint=@,161-255
   call assert_equal('Motörhead', matchstr('Motörhead', '[[:print:]]\+'))
 
+  let alnumchars = ''
   let alphachars = ''
+  let backspacechar = ''
+  let blankchars = ''
+  let cntrlchars = ''
+  let digitchars = ''
+  let escapechar = ''
+  let graphchars = ''
   let lowerchars = ''
-  let upperchars = ''
-  let alnumchars = ''
   let printchars = ''
   let punctchars = ''
+  let returnchar = ''
+  let spacechars = ''
+  let tabchar = ''
+  let upperchars = ''
   let xdigitchars = ''
   let i = 1
   while i <= 255
@@ -51,21 +60,48 @@ func s:classes_test()
     if c =~ '[[:alpha:]]'
       let alphachars .= c
     endif
-    if c =~ '[[:lower:]]'
-      let lowerchars .= c
-    endif
-    if c =~ '[[:upper:]]'
-      let upperchars .= c
-    endif
     if c =~ '[[:alnum:]]'
       let alnumchars .= c
     endif
+    if c =~ '[[:backspace:]]'
+      let backspacechar .= c
+    endif
+    if c =~ '[[:blank:]]'
+      let blankchars .= c
+    endif
+    if c =~ '[[:cntrl:]]'
+      let cntrlchars .= c
+    endif
+    if c =~ '[[:digit:]]'
+      let digitchars .= c
+    endif
+    if c =~ '[[:escape:]]'
+      let escapechar .= c
+    endif
+    if c =~ '[[:graph:]]'
+      let graphchars .= c
+    endif
+    if c =~ '[[:lower:]]'
+      let lowerchars .= c
+    endif
     if c =~ '[[:print:]]'
       let printchars .= c
     endif
     if c =~ '[[:punct:]]'
       let punctchars .= c
     endif
+    if c =~ '[[:return:]]'
+      let returnchar .= c
+    endif
+    if c =~ '[[:space:]]'
+      let spacechars .= c
+    endif
+    if c =~ '[[:tab:]]'
+      let tabchar .= c
+    endif
+    if c =~ '[[:upper:]]'
+      let upperchars .= c
+    endif
     if c =~ '[[:xdigit:]]'
       let xdigitchars .= c
     endif
@@ -73,11 +109,22 @@ func s:classes_test()
   endwhile
 
   call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alphachars)
-  call assert_equal('abcdefghijklmnopqrstuvwxyzµßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ', lowerchars)
-  call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ', upperchars)
   call assert_equal('0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alnumchars)
+  call assert_equal("\b", backspacechar)
+  call assert_equal("\t ", blankchars)
+  " Commented out: it succeeds on Linux and Windows, but fails on macOs in Travis.
+  " call assert_equal("\x01\x02\x03\x04\x05\x06\x07\b\t\n\x0b\f\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\e\x1c\x1d\x1e\x1f\x7f", cntrlchars)
+  call assert_equal("0123456789", digitchars)
+  call assert_equal("\<Esc>", escapechar)
+  " Commented out: it succeeds on Linux and Windows, but fails on macOs in Travis.
+  " call assert_equal('!"#$%&''()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~', graphchars)
+  call assert_equal('abcdefghijklmnopqrstuvwxyzµßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ', lowerchars)
   call assert_equal(' !"#$%&''()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ', printchars)
   call assert_equal('!"#$%&''()*+,-./:;<=>?@[\]^_`{|}~', punctchars)
+  call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ', upperchars)
+  call assert_equal("\r", returnchar)
+  call assert_equal("\t\n\x0b\f\r ", spacechars)
+  call assert_equal("\t", tabchar)
   call assert_equal('0123456789ABCDEFabcdef', xdigitchars)
 endfunc
 
diff --git a/src/version.c b/src/version.c
index 45d6e8f73..36adf25a5 100644
--- a/src/version.c
+++ b/src/version.c
@@ -765,6 +765,8 @@ static char *(features[]) =
 static int included_patches[] =
 {   /* Add new patch number below this line */
 /**/
+    519,
+/**/
     518,
 /**/
     517,