[RFC PATCH, WAS: "weird diff output?"] Implement better chunk heuristics.
TODO(sbeller):
* describe the discussion on why this is better
* see if this can be tested?
Signed-off-by: Stefan Beller <sbeller@google.com>
---
xdiff/xdiffi.c | 39 +++++++++++++++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index 2358a2d..24eb9a0 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -400,9 +400,16 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
}
+static int starts_with_emptyline(const char *recs)
+{
+ return recs[0] == '\n'; /* CRLF not covered here */
+}
+
+
int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->nrec;
char *rchg = xdf->rchg, *rchgo = xdfo->rchg;
+ unsigned char has_emptyline;
xrecord_t **recs = xdf->recs;
/*
@@ -436,6 +443,7 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
do {
grpsiz = ix - ixs;
+ has_emptyline = 0;
/*
* If the line before the current change group, is equal to
@@ -447,6 +455,8 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
rchg[--ixs] = 1;
rchg[--ix] = 0;
+ has_emptyline |=
+ starts_with_emptyline(recs[ix]->ptr);
/*
* This change might have joined two change groups,
* so we try to take this scenario in account by moving
@@ -475,6 +485,9 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
rchg[ixs++] = 0;
rchg[ix++] = 1;
+ has_emptyline |=
+ starts_with_emptyline(recs[ix]->ptr);
+
/*
* This change might have joined two change groups,
* so we try to take this scenario in account by moving
@@ -498,6 +511,32 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
rchg[--ix] = 0;
while (rchgo[--ixo]);
}
+
+ /*
+ * If a group can be moved back and forth, see if there is an
+ * empty line in the moving space. If there is an empty line,
+ * make sure the last empty line is the end of the group.
+ *
+ * As we shifted the group forward as far as possible, we only
+ * need to shift it back if at all.
+ */
+ if (has_emptyline) {
+ while (ixs > 0 && recs[ixs - 1]->ha == recs[ix - 1]->ha &&
+ xdl_recmatch(recs[ixs - 1]->ptr, recs[ixs - 1]->size, recs[ix - 1]->ptr, recs[ix - 1]->size, flags) &&
+ !starts_with_emptyline(recs[ix - 1]->ptr)) {
+ rchg[--ixs] = 1;
+ rchg[--ix] = 0;
+
+ /*
+ * This change did not join two change groups,
+ * as we did that before already, so there is no
+ * need to adapt the other-file, i.e.
+ * running
+ * for (; rchg[ixs - 1]; ixs--);
+ * while (rchgo[--ixo]);
+ */
+ }
+ }
}
return 0;
--
2.8.1.474.gffdc890.dirty
Stefan Beller <sbeller@google.com>