[PATCH] Add a topological sort procedure to commit.c

This introduces an in-place topological sort procedure to commit.c.

Given a list of commits, sort_in_topological_order() will perform an in-place
topological sort of that list.

The invariant that applies to the resulting list is:

       a reachable from b => ord(b) < ord(a)

This invariant is weaker than the --merge-order invariant, but is cheaper
to calculate (assuming the list has been identified) and will serve any
purpose where only a minimal topological order guarantee is required.

Signed-off-by: Jon Seymour <jon.seymour@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/commit.c b/commit.c
index 254c902..0bbfa2a 100644 (file)
--- a/commit.c
+++ b/commit.c
@@ -3,6 +3,22 @@
 #include "commit.h"
 #include "cache.h"
 
+struct sort_node
+{
+       /*
+         * the number of children of the associated commit
+         * that also occur in the list being sorted.
+         */
+       unsigned int indegree;
+
+       /*
+         * reference to original list item that we will re-use
+         * on output.
+         */
+       struct commit_list * list_item;
+
+};
+
 const char *commit_type = "commit";
 
 enum cmit_fmt get_commit_format(const char *arg)
@@ -346,3 +362,94 @@ int count_parents(struct commit * commit)
         return count;
 }
 
+/*
+ * Performs an in-place topological sort on the list supplied.
+ */
+void sort_in_topological_order(struct commit_list ** list)
+{
+       struct commit_list * next = *list;
+       struct commit_list * work = NULL;
+       struct commit_list ** pptr = list;
+       struct sort_node * nodes;
+       struct sort_node * next_nodes;
+       int count = 0;
+
+       /* determine the size of the list */
+       while (next) {
+               next = next->next;
+               count++;
+       }
+       /* allocate an array to help sort the list */
+       nodes = xcalloc(count, sizeof(*nodes));
+       /* link the list to the array */
+       next_nodes = nodes;
+       next=*list;
+       while (next) {
+               next_nodes->list_item = next;
+               next->item->object.util = next_nodes;
+               next_nodes++;
+               next = next->next;
+       }
+       /* update the indegree */
+       next=*list;
+       while (next) {
+               struct commit_list * parents = next->item->parents;
+               while (parents) {
+                       struct commit * parent=parents->item;
+                       struct sort_node * pn = (struct sort_node *)parent->object.util;
+                       
+                       if (pn)
+                               pn->indegree++;
+                       parents=parents->next;
+               }
+               next=next->next;
+       }
+       /* 
+         * find the tips
+         *
+         * tips are nodes not reachable from any other node in the list 
+         * 
+         * the tips serve as a starting set for the work queue.
+         */
+       next=*list;
+       while (next) {
+               struct sort_node * node = (struct sort_node *)next->item->object.util;
+
+               if (node->indegree == 0) {
+                       commit_list_insert(next->item, &work);
+               }
+               next=next->next;
+       }
+       /* process the list in topological order */
+       while (work) {
+               struct commit * work_item = pop_commit(&work);
+               struct sort_node * work_node = (struct sort_node *)work_item->object.util;
+               struct commit_list * parents = work_item->parents;
+
+               while (parents) {
+                       struct commit * parent=parents->item;
+                       struct sort_node * pn = (struct sort_node *)parent->object.util;
+                       
+                       if (pn) {
+                               /* 
+                                * parents are only enqueued for emission 
+                                 * when all their children have been emitted thereby
+                                 * guaranteeing topological order.
+                                 */
+                               pn->indegree--;
+                               if (!pn->indegree) 
+                                       commit_list_insert(parent, &work);
+                       }
+                       parents=parents->next;
+               }
+               /*
+                 * work_item is a commit all of whose children
+                 * have already been emitted. we can emit it now.
+                 */
+               *pptr = work_node->list_item;
+               pptr = &(*pptr)->next;
+               *pptr = NULL;
+               work_item->object.util = NULL;
+       }
+       free(nodes);
+}

diff --git a/commit.h b/commit.h
index 491b2c1..c24ab21 100644 (file)
--- a/commit.h
+++ b/commit.h
@@ -54,4 +54,17 @@ struct commit *pop_most_recent_commit(struct commit_list **list,
 struct commit *pop_commit(struct commit_list **stack);
 
 int count_parents(struct commit * commit);
+
+/*
+ * Performs an in-place topological sort of list supplied.
+ *
+ * Pre-conditions:
+ *   all commits in input list and all parents of those
+ *   commits must have object.util == NULL
+ *        
+ * Post-conditions: 
+ *   invariant of resulting list is:
+ *      a reachable from b => ord(b) < ord(a)
+ */
+void sort_in_topological_order(struct commit_list ** list);
 #endif /* COMMIT_H */