Use gitattributes to define per-path whitespace rule

The `core.whitespace` configuration variable allows you to define what
`diff` and `apply` should consider whitespace errors for all paths in
the project (See gitlink:git-config[1]).  This attribute gives you finer
control per path.

For example, if you have these in the .gitattributes:

    frotz   whitespace
    nitfol  -whitespace
    xyzzy   whitespace=-trailing

all types of whitespace problems known to git are noticed in path 'frotz'
(i.e. diff shows them in diff.whitespace color, and apply warns about
them), no whitespace problem is noticed in path 'nitfol', and the
default types of whitespace problems except "trailing whitespace" are
noticed for path 'xyzzy'.  A project with mixed Python and C might want
to have:

    *.c    whitespace
    *.py   whitespace=-indent-with-non-tab

in its toplevel .gitattributes file.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 96 insertions, 0 deletions

diff --git a/ws.c b/ws.c
new file mode 100644
index 0000000000..52c10caf35
--- /dev/null
+++ b/ws.c
@@ -0,0 +1,96 @@
+/*
+ * Whitespace rules
+ *
+ * Copyright (c) 2007 Junio C Hamano
+ */
+
+#include "cache.h"
+#include "attr.h"
+
+static struct whitespace_rule {
+	const char *rule_name;
+	unsigned rule_bits;
+} whitespace_rule_names[] = {
+	{ "trailing-space", WS_TRAILING_SPACE },
+	{ "space-before-tab", WS_SPACE_BEFORE_TAB },
+	{ "indent-with-non-tab", WS_INDENT_WITH_NON_TAB },
+};
+
+unsigned parse_whitespace_rule(const char *string)
+{
+	unsigned rule = WS_DEFAULT_RULE;
+
+	while (string) {
+		int i;
+		size_t len;
+		const char *ep;
+		int negated = 0;
+
+		string = string + strspn(string, ", \t\n\r");
+		ep = strchr(string, ',');
+		if (!ep)
+			len = strlen(string);
+		else
+			len = ep - string;
+
+		if (*string == '-') {
+			negated = 1;
+			string++;
+			len--;
+		}
+		if (!len)
+			break;
+		for (i = 0; i < ARRAY_SIZE(whitespace_rule_names); i++) {
+			if (strncmp(whitespace_rule_names[i].rule_name,
+				    string, len))
+				continue;
+			if (negated)
+				rule &= ~whitespace_rule_names[i].rule_bits;
+			else
+				rule |= whitespace_rule_names[i].rule_bits;
+			break;
+		}
+		string = ep;
+	}
+	return rule;
+}
+
+static void setup_whitespace_attr_check(struct git_attr_check *check)
+{
+	static struct git_attr *attr_whitespace;
+
+	if (!attr_whitespace)
+		attr_whitespace = git_attr("whitespace", 10);
+	check[0].attr = attr_whitespace;
+}
+
+unsigned whitespace_rule(const char *pathname)
+{
+	struct git_attr_check attr_whitespace_rule;
+
+	setup_whitespace_attr_check(&attr_whitespace_rule);
+	if (!git_checkattr(pathname, 1, &attr_whitespace_rule)) {
+		const char *value;
+
+		value = attr_whitespace_rule.value;
+		if (ATTR_TRUE(value)) {
+			/* true (whitespace) */
+			unsigned all_rule = 0;
+			int i;
+			for (i = 0; i < ARRAY_SIZE(whitespace_rule_names); i++)
+				all_rule |= whitespace_rule_names[i].rule_bits;
+			return all_rule;
+		} else if (ATTR_FALSE(value)) {
+			/* false (-whitespace) */
+			return 0;
+		} else if (ATTR_UNSET(value)) {
+			/* reset to default (!whitespace) */
+			return whitespace_rule_cfg;
+		} else {
+			/* string */
+			return parse_whitespace_rule(value);
+		}
+	} else {
+		return whitespace_rule_cfg;
+	}
+}