ref_array: keep track of whether references are sorted
Keep track of how many entries at the beginning of a ref_array are already
sorted. In sort_ref_array(), return early if the the array is already
sorted (i.e., if no new references has been appended to the end of the
list since the last call to sort_ref_array()).
Sort ref_arrays only when needed, namely in search_ref_array() and in
do_for_each_ref(). However, never call sort_ref_array() on the
extra_refs, because extra_refs can contain multiple entries with the same
name and because sort_ref_array() not only sorts, but de-dups its
contents.
This change is currently not useful, because entries are not added to
ref_arrays after they are created. But in a moment they will be...
Implementation note: we could store a binary "sorted" value instead of
an integer, but storing the number of sorted entries leaves the way
open for a couple of possible future optimizations:
* In sort_ref_array(), sort *only* the unsorted entries, then merge
them with the sorted entries. This should be faster if most of the
entries are already sorted.
* Teach search_ref_array() to do a binary search of any sorted
entries, and if unsuccessful do a linear search of any unsorted
entries. This would avoid the need to sort the list every time that
search_ref_array() is called, and (given some intelligence about how
often to sort) could significantly improve the speed in certain
hypothetical usage patterns.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/refs.c b/refs.c
index 6f436f1..3785cc2 100644
--- a/refs.c
+++ b/refs.c
@@ -17,6 +17,15 @@
struct ref_array {
int nr, alloc;
+
+ /*
+ * Entries with index 0 <= i < sorted are sorted by name. New
+ * entries are appended to the list unsorted, and are sorted
+ * only when required; thus we avoid the need to sort the list
+ * after the addition of every reference.
+ */
+ int sorted;
+
struct ref_entry **refs;
};
@@ -105,12 +114,18 @@
}
}
+/*
+ * Sort the entries in array (if they are not already sorted).
+ */
static void sort_ref_array(struct ref_array *array)
{
int i, j;
- /* Nothing to sort unless there are at least two entries */
- if (array->nr < 2)
+ /*
+ * This check also prevents passing a zero-length array to qsort(),
+ * which is a problem on some platforms.
+ */
+ if (array->sorted == array->nr)
return;
qsort(array->refs, array->nr, sizeof(*array->refs), ref_entry_cmp);
@@ -124,7 +139,7 @@
}
array->refs[++i] = array->refs[j];
}
- array->nr = i + 1;
+ array->sorted = array->nr = i + 1;
}
static struct ref_entry *search_ref_array(struct ref_array *array, const char *refname)
@@ -137,7 +152,7 @@
if (!array->nr)
return NULL;
-
+ sort_ref_array(array);
len = strlen(refname) + 1;
e = xmalloc(sizeof(struct ref_entry) + len);
memcpy(e->name, refname, len);
@@ -168,6 +183,10 @@
static struct ref_entry *current_ref;
+/*
+ * Never call sort_ref_array() on the extra_refs, because it is
+ * allowed to contain entries with duplicate names.
+ */
static struct ref_array extra_refs;
static void clear_ref_array(struct ref_array *array)
@@ -176,7 +195,7 @@
for (i = 0; i < array->nr; i++)
free(array->refs[i]);
free(array->refs);
- array->nr = array->alloc = 0;
+ array->sorted = array->nr = array->alloc = 0;
array->refs = NULL;
}
@@ -268,7 +287,6 @@
!get_sha1_hex(refline + 1, sha1))
hashcpy(last->peeled, sha1);
}
- sort_ref_array(array);
}
void add_extra_ref(const char *refname, const unsigned char *sha1, int flag)
@@ -404,7 +422,6 @@
{
if (!refs->did_loose) {
get_ref_dir(refs, "refs", &refs->loose);
- sort_ref_array(&refs->loose);
refs->did_loose = 1;
}
return &refs->loose;
@@ -720,6 +737,8 @@
for (i = 0; i < extra->nr; i++)
retval = do_one_ref(base, fn, trim, flags, cb_data, extra->refs[i]);
+ sort_ref_array(packed);
+ sort_ref_array(loose);
while (p < packed->nr && l < loose->nr) {
struct ref_entry *entry;
int cmp = strcmp(packed->refs[p]->name, loose->refs[l]->name);
