color-words: make regex configurable via attributes

Make the --color-words splitting regular expression configurable via
the diff driver's 'wordregex' attribute.  The user can then set the
driver on a file in .gitattributes.  If a regex is given on the
command line, it overrides the driver's setting.

We also provide built-in regexes for the languages that already had
funcname patterns, and add an appropriate diff driver entry for C/++.
(The patterns are designed to run UTF-8 sequences into a single chunk
to make sure they remain readable.)

Signed-off-by: Thomas Rast <trast@student.ethz.ch>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 63 insertions, 15 deletions

diff --git a/userdiff.c b/userdiff.c
index 3681062ebf..2b55509485 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -6,14 +6,20 @@ static struct userdiff_driver *drivers;
 static int ndrivers;
 static int drivers_alloc;
 
-#define FUNCNAME(name, pattern) \
-	{ name, NULL, -1, { pattern, REG_EXTENDED } }
+#define PATTERNS(name, pattern, wordregex)			\
+	{ name, NULL, -1, { pattern, REG_EXTENDED }, wordregex }
 static struct userdiff_driver builtin_drivers[] = {
-FUNCNAME("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$"),
-FUNCNAME("java",
+PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
+	 "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("java",
 	 "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
-	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$"),
-FUNCNAME("objc",
+	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$",
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]="
+	 "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("objc",
 	 /* Negate C statements that can look like functions */
 	 "!^[ \t]*(do|for|if|else|return|switch|while)\n"
 	 /* Objective-C methods */
@@ -21,20 +27,60 @@ FUNCNAME("objc",
 	 /* C functions */
 	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$\n"
 	 /* Objective-C class/protocol definitions */
-	 "^(@(implementation|interface|protocol)[ \t].*)$"),
-FUNCNAME("pascal",
+	 "^(@(implementation|interface|protocol)[ \t].*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("pascal",
 	 "^((procedure|function|constructor|destructor|interface|"
 		"implementation|initialization|finalization)[ \t]*.*)$"
 	 "\n"
-	 "^(.*=[ \t]*(class|record).*)$"),
-FUNCNAME("php", "^[\t ]*((function|class).*)"),
-FUNCNAME("python", "^[ \t]*((class|def)[ \t].*)$"),
-FUNCNAME("ruby", "^[ \t]*((class|module|def)[ \t].*)$"),
-FUNCNAME("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$"),
-FUNCNAME("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$"),
+	 "^(.*=[ \t]*(class|record).*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
+	 "|<>|<=|>=|:=|\\.\\."
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("php", "^[\t ]*((function|class).*)",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
+	 "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"
+	 "|[^[:space:]|[\x80-\xff]+"),
+	 /* -- */
+PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
+	 /* -- */
+	 "(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
+	 "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"
+	 "|[^[:space:]|[\x80-\xff]+"),
+PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+	 "[={}\"]|[^={}\" \t]+"),
+PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
+	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+|[^[:space:]]"),
+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)[^;]*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
 { "default", NULL, -1, { NULL, 0 } },
 };
-#undef FUNCNAME
+#undef PATTERNS
 
 static struct userdiff_driver driver_true = {
 	"diff=true",
@@ -134,6 +180,8 @@ int userdiff_config(const char *k, const char *v)
 		return parse_string(&drv->external, k, v);
 	if ((drv = parse_driver(k, v, "textconv")))
 		return parse_string(&drv->textconv, k, v);
+	if ((drv = parse_driver(k, v, "wordregex")))
+		return parse_string(&drv->word_regex, k, v);
 
 	return 0;
 }