Permalink
Browse files

Add function that compacts a set of changes generated by diff

  • Loading branch information...
1 parent 67090e3 commit 15773b7d228d97eb4d1064e0a5c5f035b76b5da5 @hausdorff hausdorff committed Apr 22, 2011
Showing with 106 additions and 0 deletions.
  1. +106 −0 src/libdiff/libdiff.c
View
@@ -321,6 +321,112 @@ static int init_record_classifier(record_classifier *classifier, long size)
}
+// TODO: COMMENT HERE
+// TODO: This is currently a direct port from xdiff/xdiffi.c
+int xdl_change_compact(data_context *xdf, data_context *xdfo, long flags) {
+ long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->num_recs;
+ char *rchg = xdf->weights, *rchgo = xdfo->weights;
+ diff_record **recs = xdf->recs;
+
+ /*
+ * This is the same of what GNU diff does. Move back and forward
+ * change groups for a consistent and pretty diff output. This also
+ * helps in finding joinable change groups and reduce the diff size.
+ */
+ for (ix = ixo = 0;;) {
+ /*
+ * Find the first changed line in the to-be-compacted file.
+ * We need to keep track of both indexes, so if we find a
+ * changed lines group on the other file, while scanning the
+ * to-be-compacted file, we need to skip it properly. Note
+ * that loops that are testing for changed lines on rchg* do
+ * not need index bounding since the array is prepared with
+ * a zero at position -1 and N.
+ */
+ for (; ix < nrec && !rchg[ix]; ix++)
+ while (rchgo[ixo++]);
+ if (ix == nrec)
+ break;
+
+ /*
+ * Record the start of a changed-group in the to-be-compacted file
+ * and find the end of it, on both to-be-compacted and other file
+ * indexes (ix and ixo).
+ */
+ ixs = ix;
+ for (ix++; rchg[ix]; ix++);
+ for (; rchgo[ixo]; ixo++);
+
+ do {
+ grpsiz = ix - ixs;
+
+ /*
+ * If the line before the current change group, is equal to
+ * the last line of the current change group, shift backward
+ * the group.
+ */
+ while (ixs > 0 && recs[ixs - 1]->hash == recs[ix - 1]->hash &&
+ record_match(recs[ixs - 1]->data, recs[ixs - 1]->size, recs[ix - 1]->data, recs[ix - 1]->size, flags)) {
+ rchg[--ixs] = 1;
+ rchg[--ix] = 0;
+
+ /*
+ * This change might have joined two change groups,
+ * so we try to take this scenario in account by moving
+ * the start index accordingly (and so the other-file
+ * end-of-group index).
+ */
+ for (; rchg[ixs - 1]; ixs--);
+ while (rchgo[--ixo]);
+ }
+
+ /*
+ * Record the end-of-group position in case we are matched
+ * with a group of changes in the other file (that is, the
+ * change record before the end-of-group index in the other
+ * file is set).
+ */
+ ixref = rchgo[ixo - 1] ? ix: nrec;
+
+ /*
+ * If the first line of the current change group, is equal to
+ * the line next of the current change group, shift forward
+ * the group.
+ */
+ while (ix < nrec && recs[ixs]->hash == recs[ix]->hash &&
+ record_match(recs[ixs]->data, recs[ixs]->size, recs[ix]->data, recs[ix]->size, flags)) {
+ rchg[ixs++] = 0;
+ rchg[ix++] = 1;
+
+ /*
+ * This change might have joined two change groups,
+ * so we try to take this scenario in account by moving
+ * the start index accordingly (and so the other-file
+ * end-of-group index). Keep tracking the reference
+ * index in case we are shifting together with a
+ * corresponding group of changes in the other file.
+ */
+ for (; rchg[ix]; ix++);
+ while (rchgo[++ixo])
+ ixref = ix;
+ }
+ } while (grpsiz != ix - ixs);
+
+ /*
+ * Try to move back the possibly merged group of changes, to match
+ * the recorded postion in the other file.
+ */
+ while (ixref < ix) {
+ rchg[--ixs] = 1;
+ rchg[--ix] = 0;
+ while (rchgo[--ixo]);
+ }
+ }
+
+ return 0;
+}
+
+
// TODO: COMMENT THIS FUNCTION
int algo_environment(diff_environment *diff_env)
{

0 comments on commit 15773b7

Please sign in to comment.