string_list: add a new function, string_list_remove_duplicates()

Add a function that deletes duplicate entries from a sorted
string_list.

Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 60 insertions, 0 deletions

diff --git a/Documentation/technical/api-string-list.txt b/Documentation/technical/api-string-list.txt
index 300b301093..0f8b7cee36 100644
--- a/Documentation/technical/api-string-list.txt
+++ b/Documentation/technical/api-string-list.txt
@@ -30,6 +30,9 @@ member (you need this if you add things later) and you should set the
 
 . Can sort an unsorted list using `sort_string_list`.
 
+. Can remove duplicate items from a sorted list using
+  `string_list_remove_duplicates`.
+
 . Can remove individual items of an unsorted list using
   `unsorted_string_list_delete_item`.
 
@@ -108,6 +111,12 @@ write `string_list_insert(...)->util = ...;`.
 	Look up a given string in the string_list, returning the containing
 	string_list_item. If the string is not found, NULL is returned.
 
+`string_list_remove_duplicates`::
+
+	Remove all but the first of consecutive entries that have the
+	same string value.  If free_util is true, call free() on the
+	util members of any items that have to be deleted.
+
 * Functions for unsorted lists only
 
 `string_list_append`::
diff --git a/string-list.c b/string-list.c
index 179fde4210..decfa747fc 100644
--- a/string-list.c
+++ b/string-list.c
@@ -92,6 +92,23 @@ struct string_list_item *string_list_lookup(struct string_list *list, const char
 	return list->items + i;
 }
 
+void string_list_remove_duplicates(struct string_list *list, int free_util)
+{
+	if (list->nr > 1) {
+		int src, dst;
+		for (src = dst = 1; src < list->nr; src++) {
+			if (!strcmp(list->items[dst - 1].string, list->items[src].string)) {
+				if (list->strdup_strings)
+					free(list->items[src].string);
+				if (free_util)
+					free(list->items[src].util);
+			} else
+				list->items[dst++] = list->items[src];
+		}
+		list->nr = dst;
+	}
+}
+
 int for_each_string_list(struct string_list *list,
 			 string_list_each_func_t fn, void *cb_data)
 {
diff --git a/string-list.h b/string-list.h
index 7d18e622ec..3a6a6dc392 100644
--- a/string-list.h
+++ b/string-list.h
@@ -48,6 +48,13 @@ struct string_list_item *string_list_insert_at_index(struct string_list *list,
 						     int insert_at, const char *string);
 struct string_list_item *string_list_lookup(struct string_list *list, const char *string);
 
+/*
+ * Remove all but the first of consecutive entries with the same
+ * string value.  If free_util is true, call free() on the util
+ * members of any items that have to be deleted.
+ */
+void string_list_remove_duplicates(struct string_list *sorted_list, int free_util);
+
 
 /* Use these functions only on unsorted lists: */
 
diff --git a/t/t0063-string-list.sh b/t/t0063-string-list.sh
index a5f05cd206..dbfc05ebdc 100755
--- a/t/t0063-string-list.sh
+++ b/t/t0063-string-list.sh
@@ -71,4 +71,21 @@ test_expect_success "test filter_string_list" '
 	test "x-" = "x$(test-string-list filter x1:x2 y)"
 '
 
+test_expect_success "test remove_duplicates" '
+	test "x-" = "x$(test-string-list remove_duplicates -)" &&
+	test "x" = "x$(test-string-list remove_duplicates "")" &&
+	test a = "$(test-string-list remove_duplicates a)" &&
+	test a = "$(test-string-list remove_duplicates a:a)" &&
+	test a = "$(test-string-list remove_duplicates a:a:a:a:a)" &&
+	test a:b = "$(test-string-list remove_duplicates a:b)" &&
+	test a:b = "$(test-string-list remove_duplicates a:a:b)" &&
+	test a:b = "$(test-string-list remove_duplicates a:b:b)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:b:c)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:a:b:c)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:b:b:c)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:b:c:c)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:a:b:b:c:c)" &&
+	test a:b:c = "$(test-string-list remove_duplicates a:a:a:b:b:b:c:c:c)"
+'
+
 test_done
diff --git a/test-string-list.c b/test-string-list.c
index 702276c1fc..2d6eda707e 100644
--- a/test-string-list.c
+++ b/test-string-list.c
@@ -87,6 +87,16 @@ int main(int argc, char **argv)
 		return 0;
 	}
 
+	if (argc == 3 && !strcmp(argv[1], "remove_duplicates")) {
+		struct string_list list = STRING_LIST_INIT_DUP;
+
+		parse_string_list(&list, argv[2]);
+		string_list_remove_duplicates(&list, 0);
+		write_list_compact(&list);
+		string_list_clear(&list, 0);
+		return 0;
+	}
+
 	fprintf(stderr, "%s: unknown function name: %s\n", argv[0],
 		argv[1] ? argv[1] : "(there was none)");
 	return 1;