Merge branch 'js/userdiff-cc'

Improves the pattern to match the hunk-header for C/C++.

* js/userdiff-cc:
  userdiff: have 'cpp' hunk header pattern catch more C++ anchor points
  t4018: test cases showing that the cpp pattern misses many anchor points
  t4018: test cases for the built-in cpp pattern
  t4018: reduce test files for pattern compilation tests
  t4018: convert custom pattern test to the new infrastructure
  t4018: convert java pattern test to the new infrastructure
  t4018: convert perl pattern tests to the new infrastructure
  t4018: an infrastructure to test hunk headers
  userdiff: support unsigned and long long suffixes of integer constants
  userdiff: support C++ ->* and .* operators in the word regexp

33 files changed, 303 insertions, 160 deletions

diff --git a/t/t4018-diff-funcname.sh b/t/t4018-diff-funcname.sh
index 38a092a0da..34591c23da 100755
--- a/t/t4018-diff-funcname.sh
+++ b/t/t4018-diff-funcname.sh
@@ -7,179 +7,103 @@ test_description='Test custom diff function name patterns'
 
 . ./test-lib.sh
 
-LF='
-'
-cat >Beer.java <<\EOF
-public class Beer
-{
-	int special;
-	public static void main(String args[])
-	{
-		String s=" ";
-		for(int x = 99; x > 0; x--)
-		{
-			System.out.print(x + " bottles of beer on the wall "
-				+ x + " bottles of beer\n"
-				+ "Take one down, pass it around, " + (x - 1)
-				+ " bottles of beer on the wall.\n");
-		}
-		System.out.print("Go to the store, buy some more,\n"
-			+ "99 bottles of beer on the wall.\n");
-	}
-}
-EOF
-sed 's/beer\\/beer,\\/' <Beer.java >Beer-correct.java
-cat >Beer.perl <<\EOT
-package Beer;
-
-use strict;
-use warnings;
-use parent qw(Exporter);
-our @EXPORT_OK = qw(round finalround);
-
-sub other; # forward declaration
-
-# hello
-
-sub round {
-	my ($n) = @_;
-	print "$n bottles of beer on the wall ";
-	print "$n bottles of beer\n";
-	print "Take one down, pass it around, ";
-	$n = $n - 1;
-	print "$n bottles of beer on the wall.\n";
-}
-
-sub finalround
-{
-	print "Go to the store, buy some more\n";
-	print "99 bottles of beer on the wall.\n");
-}
-
-sub withheredocument {
-	print <<"EOF"
-decoy here-doc
-EOF
-	# some lines of context
-	# to pad it out
-	print "hello\n";
-}
-
-__END__
-
-=head1 NAME
-
-Beer - subroutine to output fragment of a drinking song
-
-=head1 SYNOPSIS
-
-	use Beer qw(round finalround);
-
-	sub song {
-		for (my $i = 99; $i > 0; $i--) {
-			round $i;
-		}
-		finalround;
-	}
+test_expect_success 'setup' '
+	# a non-trivial custom pattern
+	git config diff.custom1.funcname "!static
+!String
+[^ 	].*s.*" &&
 
-	song;
+	# a custom pattern which matches to end of line
+	git config diff.custom2.funcname "......Beer\$" &&
 
-=cut
-EOT
-sed -e '
-	s/hello/goodbye/
-	s/beer\\/beer,\\/
-	s/more\\/more,\\/
-	s/song;/song();/
-' <Beer.perl >Beer-correct.perl
+	# alternation in pattern
+	git config diff.custom3.funcname "Beer$" &&
+	git config diff.custom3.xfuncname "^[ 	]*((public|static).*)$" &&
 
-test_expect_funcname () {
-	lang=${2-java}
-	test_expect_code 1 git diff --no-index -U1 \
-		"Beer.$lang" "Beer-correct.$lang" >diff &&
-	grep "^@@.*@@ $1" diff
-}
+	# for regexp compilation tests
+	echo A >A.java &&
+	echo B >B.java
+'
 
-for p in ada bibtex cpp csharp fortran html java matlab objc pascal perl php python ruby tex
+diffpatterns="
+	ada
+	bibtex
+	cpp
+	csharp
+	fortran
+	html
+	java
+	matlab
+	objc
+	pascal
+	perl
+	php
+	python
+	ruby
+	tex
+	custom1
+	custom2
+	custom3
+"
+
+for p in $diffpatterns
 do
 	test_expect_success "builtin $p pattern compiles" '
 		echo "*.java diff=$p" >.gitattributes &&
 		test_expect_code 1 git diff --no-index \
-			Beer.java Beer-correct.java 2>msg &&
-		! grep fatal msg &&
-		! grep error msg
+			A.java B.java 2>msg &&
+		! test_i18ngrep fatal msg &&
+		! test_i18ngrep error msg
 	'
 	test_expect_success "builtin $p wordRegex pattern compiles" '
 		echo "*.java diff=$p" >.gitattributes &&
 		test_expect_code 1 git diff --no-index --word-diff \
-			Beer.java Beer-correct.java 2>msg &&
-		! grep fatal msg &&
-		! grep error msg
+			A.java B.java 2>msg &&
+		! test_i18ngrep fatal msg &&
+		! test_i18ngrep error msg
 	'
 done
 
-test_expect_success 'default behaviour' '
-	rm -f .gitattributes &&
-	test_expect_funcname "public class Beer\$"
-'
-
-test_expect_success 'set up .gitattributes declaring drivers to test' '
-	cat >.gitattributes <<-\EOF
-	*.java diff=java
-	*.perl diff=perl
-	EOF
-'
-
-test_expect_success 'preset java pattern' '
-	test_expect_funcname "public static void main("
-'
-
-test_expect_success 'preset perl pattern' '
-	test_expect_funcname "sub round {\$" perl
-'
-
-test_expect_success 'perl pattern accepts K&R style brace placement, too' '
-	test_expect_funcname "sub finalround\$" perl
-'
-
-test_expect_success 'but is not distracted by end of <<here document' '
-	test_expect_funcname "sub withheredocument {\$" perl
-'
-
-test_expect_success 'perl pattern is not distracted by sub within POD' '
-	test_expect_funcname "=head" perl
-'
-
-test_expect_success 'perl pattern gets full line of POD header' '
-	test_expect_funcname "=head1 SYNOPSIS\$" perl
-'
-
-test_expect_success 'perl pattern is not distracted by forward declaration' '
-	test_expect_funcname "package Beer;\$" perl
-'
-
-test_expect_success 'custom pattern' '
-	test_config diff.java.funcname "!static
-!String
-[^ 	].*s.*" &&
-	test_expect_funcname "int special;\$"
-'
-
 test_expect_success 'last regexp must not be negated' '
+	echo "*.java diff=java" >.gitattributes &&
 	test_config diff.java.funcname "!static" &&
-	test_expect_code 128 git diff --no-index Beer.java Beer-correct.java 2>msg &&
-	grep ": Last expression must not be negated:" msg
+	test_expect_code 128 git diff --no-index A.java B.java 2>msg &&
+	test_i18ngrep ": Last expression must not be negated:" msg
 '
 
-test_expect_success 'pattern which matches to end of line' '
-	test_config diff.java.funcname "Beer\$" &&
-	test_expect_funcname "Beer\$"
+test_expect_success 'setup hunk header tests' '
+	for i in $diffpatterns
+	do
+		echo "$i-* diff=$i"
+	done > .gitattributes &&
+
+	# add all test files to the index
+	(
+		cd "$TEST_DIRECTORY"/t4018 &&
+		git --git-dir="$TRASH_DIRECTORY/.git" add .
+	) &&
+
+	# place modified files in the worktree
+	for i in $(git ls-files)
+	do
+		sed -e "s/ChangeMe/IWasChanged/" <"$TEST_DIRECTORY/t4018/$i" >"$i" || return 1
+	done
 '
 
-test_expect_success 'alternation in pattern' '
-	test_config diff.java.funcname "Beer$" &&
-	test_config diff.java.xfuncname "^[ 	]*((public|static).*)$" &&
-	test_expect_funcname "public static void main("
-'
+# check each individual file
+for i in $(git ls-files)
+do
+	if grep broken "$i" >/dev/null 2>&1
+	then
+		result=failure
+	else
+		result=success
+	fi
+	test_expect_$result "hunk header: $i" "
+		test_when_finished 'cat actual' &&	# for debugging only
+		git diff -U1 $i >actual &&
+		grep '@@ .* @@.*RIGHT' actual
+	"
+done
 
 test_done
diff --git a/t/t4018/README b/t/t4018/README
new file mode 100644
index 0000000000..283e01cca1
--- /dev/null
+++ b/t/t4018/README
@@ -0,0 +1,18 @@
+How to write RIGHT test cases
+=============================
+
+Insert the word "ChangeMe" (exactly this form) at a distance of
+at least two lines from the line that must appear in the hunk header.
+
+The text that must appear in the hunk header must contain the word
+"right", but in all upper-case, like in the title above.
+
+To mark a test case that highlights a malfunction, insert the word
+BROKEN in all lower-case somewhere in the file.
+
+This text is a bit twisted and out of order, but it is itself a
+test case for the default hunk header pattern. Know what you are doing
+if you change it.
+
+BTW, this tests that the head line goes to the hunk header, not the line
+of equal signs.
diff --git a/t/t4018/cpp-c++-function b/t/t4018/cpp-c++-function
new file mode 100644
index 0000000000..9ee6bbef55
--- /dev/null
+++ b/t/t4018/cpp-c++-function
@@ -0,0 +1,4 @@
+Item RIGHT::DoSomething( Args with_spaces )
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-class-constructor b/t/t4018/cpp-class-constructor
new file mode 100644
index 0000000000..ec4f115c25
--- /dev/null
+++ b/t/t4018/cpp-class-constructor
@@ -0,0 +1,4 @@
+Item::Item(int RIGHT)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-class-constructor-mem-init b/t/t4018/cpp-class-constructor-mem-init
new file mode 100644
index 0000000000..49a69f37e1
--- /dev/null
+++ b/t/t4018/cpp-class-constructor-mem-init
@@ -0,0 +1,5 @@
+Item::Item(int RIGHT) :
+	member(0)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-class-definition b/t/t4018/cpp-class-definition
new file mode 100644
index 0000000000..11b61da3b7
--- /dev/null
+++ b/t/t4018/cpp-class-definition
@@ -0,0 +1,4 @@
+class RIGHT
+{
+	int ChangeMe;
+};
diff --git a/t/t4018/cpp-class-definition-derived b/t/t4018/cpp-class-definition-derived
new file mode 100644
index 0000000000..3b98cd09ab
--- /dev/null
+++ b/t/t4018/cpp-class-definition-derived
@@ -0,0 +1,5 @@
+class RIGHT :
+	public Baseclass
+{
+	int ChangeMe;
+};
diff --git a/t/t4018/cpp-class-destructor b/t/t4018/cpp-class-destructor
new file mode 100644
index 0000000000..5487665096
--- /dev/null
+++ b/t/t4018/cpp-class-destructor
@@ -0,0 +1,4 @@
+RIGHT::~RIGHT()
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-function-returning-global-type b/t/t4018/cpp-function-returning-global-type
new file mode 100644
index 0000000000..1084d5990e
--- /dev/null
+++ b/t/t4018/cpp-function-returning-global-type
@@ -0,0 +1,4 @@
+::Item get::it::RIGHT()
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-function-returning-nested b/t/t4018/cpp-function-returning-nested
new file mode 100644
index 0000000000..d9750aa61a
--- /dev/null
+++ b/t/t4018/cpp-function-returning-nested
@@ -0,0 +1,5 @@
+get::Item get::it::RIGHT()
+{
+	ChangeMe;
+}
+
diff --git a/t/t4018/cpp-function-returning-pointer b/t/t4018/cpp-function-returning-pointer
new file mode 100644
index 0000000000..ef15657ea8
--- /dev/null
+++ b/t/t4018/cpp-function-returning-pointer
@@ -0,0 +1,4 @@
+const char *get_it_RIGHT(char *ptr)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-function-returning-reference b/t/t4018/cpp-function-returning-reference
new file mode 100644
index 0000000000..01b051df70
--- /dev/null
+++ b/t/t4018/cpp-function-returning-reference
@@ -0,0 +1,4 @@
+string& get::it::RIGHT(char *ptr)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-gnu-style-function b/t/t4018/cpp-gnu-style-function
new file mode 100644
index 0000000000..08c7c7565a
--- /dev/null
+++ b/t/t4018/cpp-gnu-style-function
@@ -0,0 +1,5 @@
+const char *
+RIGHT(int arg)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-namespace-definition b/t/t4018/cpp-namespace-definition
new file mode 100644
index 0000000000..6749980241
--- /dev/null
+++ b/t/t4018/cpp-namespace-definition
@@ -0,0 +1,4 @@
+namespace RIGHT
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-operator-definition b/t/t4018/cpp-operator-definition
new file mode 100644
index 0000000000..1acd827159
--- /dev/null
+++ b/t/t4018/cpp-operator-definition
@@ -0,0 +1,4 @@
+Value operator+(Value LEFT, Value RIGHT)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-skip-access-specifiers b/t/t4018/cpp-skip-access-specifiers
new file mode 100644
index 0000000000..4d4a9dbb9d
--- /dev/null
+++ b/t/t4018/cpp-skip-access-specifiers
@@ -0,0 +1,8 @@
+class RIGHT : public Baseclass
+{
+public:
+protected:
+private:
+	void DoSomething();
+	int ChangeMe;
+};
diff --git a/t/t4018/cpp-skip-comment-block b/t/t4018/cpp-skip-comment-block
new file mode 100644
index 0000000000..3800b9967a
--- /dev/null
+++ b/t/t4018/cpp-skip-comment-block
@@ -0,0 +1,9 @@
+struct item RIGHT(int i)
+// Do not
+// pick up
+/* these
+** comments.
+*/
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-skip-labels b/t/t4018/cpp-skip-labels
new file mode 100644
index 0000000000..b9c10aba22
--- /dev/null
+++ b/t/t4018/cpp-skip-labels
@@ -0,0 +1,8 @@
+void RIGHT (void)
+{
+repeat:		// C++ comment
+next:		/* C comment */
+	do_something();
+
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-struct-definition b/t/t4018/cpp-struct-definition
new file mode 100644
index 0000000000..521c59fd15
--- /dev/null
+++ b/t/t4018/cpp-struct-definition
@@ -0,0 +1,9 @@
+struct RIGHT {
+	unsigned
+	/* this bit field looks like a label and should not be picked up */
+		decoy_bitfield: 2,
+		more : 1;
+	int filler;
+
+	int ChangeMe;
+};
diff --git a/t/t4018/cpp-struct-single-line b/t/t4018/cpp-struct-single-line
new file mode 100644
index 0000000000..a0de5fb800
--- /dev/null
+++ b/t/t4018/cpp-struct-single-line
@@ -0,0 +1,7 @@
+void wrong()
+{
+}
+
+struct RIGHT_iterator_tag {};
+
+int ChangeMe;
diff --git a/t/t4018/cpp-template-function-definition b/t/t4018/cpp-template-function-definition
new file mode 100644
index 0000000000..0cdf5ba5bd
--- /dev/null
+++ b/t/t4018/cpp-template-function-definition
@@ -0,0 +1,4 @@
+template<class T> int RIGHT(T arg)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/cpp-union-definition b/t/t4018/cpp-union-definition
new file mode 100644
index 0000000000..7ec94df697
--- /dev/null
+++ b/t/t4018/cpp-union-definition
@@ -0,0 +1,4 @@
+union RIGHT {
+	double v;
+	int ChangeMe;
+};
diff --git a/t/t4018/cpp-void-c-function b/t/t4018/cpp-void-c-function
new file mode 100644
index 0000000000..153081e872
--- /dev/null
+++ b/t/t4018/cpp-void-c-function
@@ -0,0 +1,4 @@
+void RIGHT (void)
+{
+	ChangeMe;
+}
diff --git a/t/t4018/custom1-pattern b/t/t4018/custom1-pattern
new file mode 100644
index 0000000000..e8fd59f884
--- /dev/null
+++ b/t/t4018/custom1-pattern
@@ -0,0 +1,17 @@
+public class Beer
+{
+	int special, RIGHT;
+	public static void main(String args[])
+	{
+		String s=" ";
+		for(int x = 99; x > 0; x--)
+		{
+			System.out.print(x + " bottles of beer on the wall "
+				+ x + " bottles of beer\n" // ChangeMe
+				+ "Take one down, pass it around, " + (x - 1)
+				+ " bottles of beer on the wall.\n");
+		}
+		System.out.print("Go to the store, buy some more,\n"
+			+ "99 bottles of beer on the wall.\n");
+	}
+}
diff --git a/t/t4018/custom2-match-to-end-of-line b/t/t4018/custom2-match-to-end-of-line
new file mode 100644
index 0000000000..f88ac318b7
--- /dev/null
+++ b/t/t4018/custom2-match-to-end-of-line
@@ -0,0 +1,8 @@
+public class RIGHT_Beer
+{
+	int special;
+	public static void main(String args[])
+	{
+		System.out.print("ChangeMe");
+	}
+}
diff --git a/t/t4018/custom3-alternation-in-pattern b/t/t4018/custom3-alternation-in-pattern
new file mode 100644
index 0000000000..5f3769c64f
--- /dev/null
+++ b/t/t4018/custom3-alternation-in-pattern
@@ -0,0 +1,17 @@
+public class Beer
+{
+	int special;
+	public static void main(String RIGHT[])
+	{
+		String s=" ";
+		for(int x = 99; x > 0; x--)
+		{
+			System.out.print(x + " bottles of beer on the wall "
+				+ x + " bottles of beer\n" // ChangeMe
+				+ "Take one down, pass it around, " + (x - 1)
+				+ " bottles of beer on the wall.\n");
+		}
+		System.out.print("Go to the store, buy some more,\n"
+			+ "99 bottles of beer on the wall.\n");
+	}
+}
diff --git a/t/t4018/java-class-member-function b/t/t4018/java-class-member-function
new file mode 100644
index 0000000000..298bc7a71b
--- /dev/null
+++ b/t/t4018/java-class-member-function
@@ -0,0 +1,8 @@
+public class Beer
+{
+	int special;
+	public static void main(String RIGHT[])
+	{
+		System.out.print("ChangeMe");
+	}
+}
diff --git a/t/t4018/perl-skip-end-of-heredoc b/t/t4018/perl-skip-end-of-heredoc
new file mode 100644
index 0000000000..c22d39b256
--- /dev/null
+++ b/t/t4018/perl-skip-end-of-heredoc
@@ -0,0 +1,8 @@
+sub RIGHTwithheredocument {
+	print <<"EOF"
+decoy here-doc
+EOF
+	# some lines of context
+	# to pad it out
+	print "ChangeMe\n";
+}
diff --git a/t/t4018/perl-skip-forward-decl b/t/t4018/perl-skip-forward-decl
new file mode 100644
index 0000000000..a98cb8bdad
--- /dev/null
+++ b/t/t4018/perl-skip-forward-decl
@@ -0,0 +1,10 @@
+package RIGHT;
+
+use strict;
+use warnings;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(round finalround);
+
+sub other; # forward declaration
+
+# ChangeMe
diff --git a/t/t4018/perl-skip-sub-in-pod b/t/t4018/perl-skip-sub-in-pod
new file mode 100644
index 0000000000..e39f02462e
--- /dev/null
+++ b/t/t4018/perl-skip-sub-in-pod
@@ -0,0 +1,18 @@
+=head1 NAME
+
+Beer - subroutine to output fragment of a drinking song
+
+=head1 SYNOPSIS_RIGHT
+
+	use Beer qw(round finalround);
+
+	sub song {
+		for (my $i = 99; $i > 0; $i--) {
+			round $i;
+		}
+		finalround;
+	}
+
+	ChangeMe;
+
+=cut
diff --git a/t/t4018/perl-sub-definition b/t/t4018/perl-sub-definition
new file mode 100644
index 0000000000..a507d1f645
--- /dev/null
+++ b/t/t4018/perl-sub-definition
@@ -0,0 +1,4 @@
+sub RIGHT {
+	my ($n) = @_;
+	print "ChangeMe";
+}
diff --git a/t/t4018/perl-sub-definition-kr-brace b/t/t4018/perl-sub-definition-kr-brace
new file mode 100644
index 0000000000..330b3df114
--- /dev/null
+++ b/t/t4018/perl-sub-definition-kr-brace
@@ -0,0 +1,4 @@
+sub RIGHT
+{
+	print "ChangeMe\n";
+}
diff --git a/userdiff.c b/userdiff.c
index 10b61ec37d..fad52d6392 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -125,15 +125,13 @@ PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
 	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+"),
 PATTERNS("cpp",
 	 /* Jump targets or access declarations */
-	 "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:.*$\n"
-	 /* C/++ functions/methods at top level */
-	 "^([A-Za-z_][A-Za-z_0-9]*([ \t*]+[A-Za-z_][A-Za-z_0-9]*([ \t]*::[ \t]*[^[:space:]]+)?){1,}[ \t]*\\([^;]*)$\n"
-	 /* compound type at top level */
-	 "^((struct|class|enum)[^;]*)$",
+	 "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:[[:space:]]*($|/[/*])\n"
+	 /* functions/methods, variables, and compounds at top level */
+	 "^((::[[:space:]]*)?[A-Za-z_].*)$",
 	 /* -- */
 	 "[a-zA-Z_][a-zA-Z0-9_]*"
-	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
-	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lLuU]*"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*"),
 PATTERNS("csharp",
 	 /* Keywords */
 	 "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"