userdiff: better method/property matching for C#

- Support multi-line methods by not requiring closing parenthesis.
- Support multiple generics (comma was missing before).
- Add missing `foreach`, `lock` and  `fixed` keywords to skip over.
- Remove `instanceof` keyword, which isn't C#.
- Also detect non-method keywords not positioned at the start of a line.
- Added tests; none existed before.

The overall strategy is to focus more on what isn't expected for
method/property definitions, instead of what is, but is fully optional.

Signed-off-by: Steven Jeuris <steven.jeuris@gmail.com>
Acked-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 42 insertions, 6 deletions

diff --git a/userdiff.c b/userdiff.c
index 92ef649c99..82bc76b910 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -90,12 +90,48 @@ PATTERNS("cpp",
 	 "|\\.[0-9][0-9]*([Ee][-+]?[0-9]+)?[fFlL]?"
 	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->\\*?|\\.\\*|<=>"),
 PATTERNS("csharp",
-	 /* Keywords */
-	 "!^[ \t]*(do|while|for|if|else|instanceof|new|return|switch|case|throw|catch|using)\n"
-	 /* Methods and constructors */
-	 "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe|async)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[<>@._[:alnum:]]+[ \t]*\\(.*\\))[ \t]*$\n"
-	 /* Properties */
-	 "^[ \t]*(((static|public|internal|private|protected|new|virtual|sealed|override|unsafe)[ \t]+)*[][<>@.~_[:alnum:]]+[ \t]+[@._[:alnum:]]+)[ \t]*$\n"
+	 /*
+	  * Jump over reserved keywords which are illegal method names, but which
+	  * can be followed by parentheses without special characters in between,
+	  * making them look like methods.
+	  */
+	 "!(^|[ \t]+)" /* Start of line or whitespace. */
+		"(do|while|for|foreach|if|else|new|default|return|switch|case|throw"
+		"|catch|using|lock|fixed)"
+		"([ \t(]+|$)\n" /* Whitespace, "(", or end of line. */
+	 /*
+	  * Methods/constructors:
+	  * The strategy is to identify a minimum of two groups (any combination
+	  * of keywords/type/name) before the opening parenthesis, and without
+	  * final unexpected characters, normally only used in ordinary statements.
+	  */
+	 "^[ \t]*" /* Remove leading whitespace. */
+		"(" /* Start chunk header capture. */
+		"(" /* First group. */
+			"[][[:alnum:]@_.]" /* Name. */
+			"(<[][[:alnum:]@_, \t<>]+>)?" /* Optional generic parameters. */
+		")+"
+		"([ \t]+" /* Subsequent groups, prepended with space. */
+			"([][[:alnum:]@_.](<[][[:alnum:]@_, \t<>]+>)?)+"
+		")+"
+		"[ \t]*" /* Optional space before parameters start. */
+		"\\(" /* Start of method parameters. */
+		"[^;]*" /* Allow complex parameters, but exclude statements (;). */
+		")$\n" /* Close chunk header capture. */
+	 /*
+	  * Properties:
+	  * As with methods, expect a minimum of two groups. But, more trivial than
+	  * methods, the vast majority of properties long enough to be worth
+	  * showing a chunk header for don't include "=:;,()" on the line they are
+	  * defined, since they don't have a parameter list.
+	  */
+	 "^[ \t]*("
+		"([][[:alnum:]@_.](<[][[:alnum:]@_, \t<>]+>)?)+"
+		"([ \t]+"
+			"([][[:alnum:]@_.](<[][[:alnum:]@_, \t<>]+>)?)+"
+		")+" /* Up to here, same as methods regex. */
+		"[^;=:,()]*" /* Compared to methods, no parameter list allowed. */
+		")$\n"
 	 /* Type definitions */
 	 "^[ \t]*(((static|public|internal|private|protected|new|unsafe|sealed|abstract|partial)[ \t]+)*(class|enum|interface|struct|record)[ \t]+.*)$\n"
 	 /* Namespace */