aboutsummaryrefslogtreecommitdiff
path: root/sha1-lookup.c
diff options
context:
space:
mode:
authorChristian Couder <chriscool@tuxfamily.org>2009-04-04 22:59:26 +0200
committerJunio C Hamano <gitster@pobox.com>2009-04-04 22:57:39 -0700
commit96beef8c2efaab06f703991ed7802b8cef4c00e3 (patch)
tree06274738bafabc3d1c523a30732cfa6a92438885 /sha1-lookup.c
parente96f3689ecd95997a2a474c2b7f21b0a67f138b1 (diff)
downloadgit-96beef8c2efaab06f703991ed7802b8cef4c00e3.tar.gz
git-96beef8c2efaab06f703991ed7802b8cef4c00e3.tar.xz
sha1-lookup: add new "sha1_pos" function to efficiently lookup sha1
This function has been copied from the "patch_pos" function in "patch-ids.c" but an additional parameter has been added. The new parameter is a function pointer, that is used to access the sha1 of an element in the table. Signed-off-by: Christian Couder <chriscool@tuxfamily.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'sha1-lookup.c')
-rw-r--r--sha1-lookup.c101
1 files changed, 101 insertions, 0 deletions
diff --git a/sha1-lookup.c b/sha1-lookup.c
index da357479c..055dd87dc 100644
--- a/sha1-lookup.c
+++ b/sha1-lookup.c
@@ -1,6 +1,107 @@
#include "cache.h"
#include "sha1-lookup.h"
+static uint32_t take2(const unsigned char *sha1)
+{
+ return ((sha1[0] << 8) | sha1[1]);
+}
+
+/*
+ * Conventional binary search loop looks like this:
+ *
+ * do {
+ * int mi = (lo + hi) / 2;
+ * int cmp = "entry pointed at by mi" minus "target";
+ * if (!cmp)
+ * return (mi is the wanted one)
+ * if (cmp > 0)
+ * hi = mi; "mi is larger than target"
+ * else
+ * lo = mi+1; "mi is smaller than target"
+ * } while (lo < hi);
+ *
+ * The invariants are:
+ *
+ * - When entering the loop, lo points at a slot that is never
+ * above the target (it could be at the target), hi points at a
+ * slot that is guaranteed to be above the target (it can never
+ * be at the target).
+ *
+ * - We find a point 'mi' between lo and hi (mi could be the same
+ * as lo, but never can be the same as hi), and check if it hits
+ * the target. There are three cases:
+ *
+ * - if it is a hit, we are happy.
+ *
+ * - if it is strictly higher than the target, we update hi with
+ * it.
+ *
+ * - if it is strictly lower than the target, we update lo to be
+ * one slot after it, because we allow lo to be at the target.
+ *
+ * When choosing 'mi', we do not have to take the "middle" but
+ * anywhere in between lo and hi, as long as lo <= mi < hi is
+ * satisfied. When we somehow know that the distance between the
+ * target and lo is much shorter than the target and hi, we could
+ * pick mi that is much closer to lo than the midway.
+ */
+/*
+ * The table should contain "nr" elements.
+ * The sha1 of element i (between 0 and nr - 1) should be returned
+ * by "fn(i, table)".
+ */
+int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
+ sha1_access_fn fn)
+{
+ size_t hi = nr;
+ size_t lo = 0;
+ size_t mi = 0;
+
+ if (!nr)
+ return -1;
+
+ if (nr != 1) {
+ size_t lov, hiv, miv, ofs;
+
+ for (ofs = 0; ofs < 18; ofs += 2) {
+ lov = take2(fn(0, table) + ofs);
+ hiv = take2(fn(nr - 1, table) + ofs);
+ miv = take2(sha1 + ofs);
+ if (miv < lov)
+ return -1;
+ if (hiv < miv)
+ return -1 - nr;
+ if (lov != hiv) {
+ /*
+ * At this point miv could be equal
+ * to hiv (but sha1 could still be higher);
+ * the invariant of (mi < hi) should be
+ * kept.
+ */
+ mi = (nr - 1) * (miv - lov) / (hiv - lov);
+ if (lo <= mi && mi < hi)
+ break;
+ die("oops");
+ }
+ }
+ if (18 <= ofs)
+ die("cannot happen -- lo and hi are identical");
+ }
+
+ do {
+ int cmp;
+ cmp = hashcmp(fn(mi, table), sha1);
+ if (!cmp)
+ return mi;
+ if (cmp > 0)
+ hi = mi;
+ else
+ lo = mi + 1;
+ mi = (hi + lo) / 2;
+ } while (lo < hi);
+ return -lo-1;
+}
+
/*
* Conventional binary search loop looks like this:
*