Move the tests for split /\s/ and Unicode from split.t to split_unico…

…de.t Skip split_unicode.t under minitest, as it uses charnames, which uses File::Spec, which may not be available. [Experimentation reveals that git blame by default won't attribute lines past this commit, unless --find-copies-harder is used. The alternative approach, copy t/op/split.t as t/op/split_unicode.t as 1 commit, then prune both, fares no better - by default git blame can't attribute through that *either*. Again, --find-copies-harder works. Hence, do the partition as this one commit, as it is simpler, and all other things are equal]
Perl · Mar 6, 2011 · ab08a36 · ab08a36
1 parent cedc31d
commit ab08a36
Show file tree

Hide file tree

Showing 3 changed files with 66 additions and 57 deletions.
diff --git a/MANIFEST b/MANIFEST
@@ -4950,6 +4950,7 @@ t/op/smartmatch.t		See if the ~~ operator works
 t/op/sort.t			See if sort works
 t/op/splice.t			See if splice works
 t/op/split.t			See if split works
+t/op/split_unicode.t		Test split /\s/ and Unicode
 t/op/sprintf2.t			See if sprintf works
 t/op/sprintf.t			See if sprintf works
 t/op/srand.t			See if srand works

diff --git a/t/op/split.t b/t/op/split.t
@@ -6,7 +6,7 @@ BEGIN {
     require './test.pl';
 }
 
-plan tests => 252;
+plan tests => 102;
 
 $FS = ':';
 
@@ -388,62 +388,6 @@ is($cnt, scalar(@ary));
     $x = \$a[2];
     is (ref $x, 'SCALAR', '#28938 - garbage after extend');
 }
-{
-    # check the special casing of split /\s/ and unicode
-    use charnames qw(:full);
-    # below test data is extracted from
-    # PropList-5.0.0.txt
-    # Date: 2006-06-07, 23:22:52 GMT [MD]
-    #
-    # Unicode Character Database
-    # Copyright (c) 1991-2006 Unicode, Inc.
-    # For terms of use, see http://www.unicode.org/terms_of_use.html
-    # For documentation, see UCD.html
-    my @spaces=(
-	ord("\t"),      # Cc       <control-0009>
-	ord("\n"),      # Cc       <control-000A>
-	# not PerlSpace # Cc       <control-000B>
-	ord("\f"),      # Cc       <control-000C>
-	ord("\r"),      # Cc       <control-000D>
-	ord(" "),       # Zs       SPACE
-	ord("\N{NEL}"), # Cc       <control-0085>
-	ord("\N{NO-BREAK SPACE}"),
-			# Zs       NO-BREAK SPACE
-        0x1680,         # Zs       OGHAM SPACE MARK
-        0x180E,         # Zs       MONGOLIAN VOWEL SEPARATOR
-        0x2000..0x200A, # Zs  [11] EN QUAD..HAIR SPACE
-        0x2028,         # Zl       LINE SEPARATOR
-        0x2029,         # Zp       PARAGRAPH SEPARATOR
-        0x202F,         # Zs       NARROW NO-BREAK SPACE
-        0x205F,         # Zs       MEDIUM MATHEMATICAL SPACE
-        0x3000          # Zs       IDEOGRAPHIC SPACE
-    );
-    #diag "Have @{[0+@spaces]} to test\n";
-    foreach my $cp (@spaces) {
-	my $msg = sprintf "Space: U+%04x", $cp;
-        my $space = chr($cp);
-        my $str="A:$space:B\x{FFFD}";
-        chop $str;
-
-        my @res=split(/\s+/,$str);
-        my $cnt=split(/\s+/,$str);
-        ok(@res == 2 && join('-',@res) eq "A:-:B", "$msg - /\\s+/");
-	is($cnt, scalar(@res), "$msg - /\\s+/ (count)");
-
-        my $s2 = "$space$space:A:$space$space:B\x{FFFD}";
-        chop $s2;
-
-        my @r2 = split(' ',$s2);
-	my $c2 = split(' ',$s2);
-        ok(@r2 == 2 && join('-', @r2) eq ":A:-:B",  "$msg - ' '");
-	is($c2, scalar(@r2), "$msg - ' ' (count)");
-
-        my @r3 = split(/\s+/, $s2);
-        my $c3 = split(/\s+/, $s2);
-        ok(@r3 == 3 && join('-', @r3) eq "-:A:-:B", "$msg - /\\s+/ No.2");
-	is($c3, scalar(@r3), "$msg - /\\s+/ No.2 (count)");
-    }
-}
 
 {
     my $src = "ABC \0 FOO \0  XYZ";

diff --git a/t/op/split_unicode.t b/t/op/split_unicode.t
@@ -0,0 +1,64 @@
+#!./perl
+
+BEGIN {
+    require './test.pl';
+    skip_all_if_miniperl("no dynamic loading on miniperl, no File::Spec (used by charnames)");
+    plan(tests => 150);
+}
+
+{
+    # check the special casing of split /\s/ and unicode
+    use charnames qw(:full);
+    # below test data is extracted from
+    # PropList-5.0.0.txt
+    # Date: 2006-06-07, 23:22:52 GMT [MD]
+    #
+    # Unicode Character Database
+    # Copyright (c) 1991-2006 Unicode, Inc.
+    # For terms of use, see http://www.unicode.org/terms_of_use.html
+    # For documentation, see UCD.html
+    my @spaces=(
+	ord("\t"),      # Cc       <control-0009>
+	ord("\n"),      # Cc       <control-000A>
+	# not PerlSpace # Cc       <control-000B>
+	ord("\f"),      # Cc       <control-000C>
+	ord("\r"),      # Cc       <control-000D>
+	ord(" "),       # Zs       SPACE
+	ord("\N{NEL}"), # Cc       <control-0085>
+	ord("\N{NO-BREAK SPACE}"),
+			# Zs       NO-BREAK SPACE
+        0x1680,         # Zs       OGHAM SPACE MARK
+        0x180E,         # Zs       MONGOLIAN VOWEL SEPARATOR
+        0x2000..0x200A, # Zs  [11] EN QUAD..HAIR SPACE
+        0x2028,         # Zl       LINE SEPARATOR
+        0x2029,         # Zp       PARAGRAPH SEPARATOR
+        0x202F,         # Zs       NARROW NO-BREAK SPACE
+        0x205F,         # Zs       MEDIUM MATHEMATICAL SPACE
+        0x3000          # Zs       IDEOGRAPHIC SPACE
+    );
+    #diag "Have @{[0+@spaces]} to test\n";
+    foreach my $cp (@spaces) {
+	my $msg = sprintf "Space: U+%04x", $cp;
+        my $space = chr($cp);
+        my $str="A:$space:B\x{FFFD}";
+        chop $str;
+
+        my @res=split(/\s+/,$str);
+        my $cnt=split(/\s+/,$str);
+        ok(@res == 2 && join('-',@res) eq "A:-:B", "$msg - /\\s+/");
+	is($cnt, scalar(@res), "$msg - /\\s+/ (count)");
+
+        my $s2 = "$space$space:A:$space$space:B\x{FFFD}";
+        chop $s2;
+
+        my @r2 = split(' ',$s2);
+	my $c2 = split(' ',$s2);
+        ok(@r2 == 2 && join('-', @r2) eq ":A:-:B",  "$msg - ' '");
+	is($c2, scalar(@r2), "$msg - ' ' (count)");
+
+        my @r3 = split(/\s+/, $s2);
+        my $c3 = split(/\s+/, $s2);
+        ok(@r3 == 3 && join('-', @r3) eq "-:A:-:B", "$msg - /\\s+/ No.2");
+	is($c3, scalar(@r3), "$msg - /\\s+/ No.2 (count)");
+    }
+}