xdiff: post-process hunks to make them consistent.

2 files changed, 110 insertions, 5 deletions

diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index 641362d05..b95ade2c1 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -45,6 +45,8 @@ static long xdl_split(unsigned long const *ha1, long off1, long lim1,
 		      long *kvdf, long *kvdb, int need_min, xdpsplit_t *spl,
 		      xdalgoenv_t *xenv);
 static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1, long chg2);
+static int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo);
+
 
 
 
@@ -395,6 +397,110 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
 }
 
 
+static int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo) {
+	long ix, ixo, ixs, ixref, grpsiz, nrec = xdf->nrec;
+	char *rchg = xdf->rchg, *rchgo = xdfo->rchg;
+	xrecord_t **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 joineable 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]->ha == recs[ix - 1]->ha &&
+			       XDL_RECMATCH(recs[ixs - 1], recs[ix - 1])) {
+				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 enf-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]->ha == recs[ix]->ha &&
+			       XDL_RECMATCH(recs[ixs], recs[ix])) {
+				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;
+}
+
+
 int xdl_build_script(xdfenv_t *xe, xdchange_t **xscr) {
 	xdchange_t *cscr = NULL, *xch;
 	char *rchg1 = xe->xdf1.rchg, *rchg2 = xe->xdf2.rchg;
@@ -440,13 +546,13 @@ int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 
 		return -1;
 	}
-
-	if (xdl_build_script(&xe, &xscr) < 0) {
+	if (xdl_change_compact(&xe.xdf1, &xe.xdf2) < 0 ||
+	    xdl_change_compact(&xe.xdf2, &xe.xdf1) < 0 ||
+	    xdl_build_script(&xe, &xscr) < 0) {
 
 		xdl_free_env(&xe);
 		return -1;
 	}
-
 	if (xscr) {
 		if (xdl_emit_diff(&xe, xscr, ecb, xecfg) < 0) {
 
@@ -454,10 +560,8 @@ int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 			xdl_free_env(&xe);
 			return -1;
 		}
-
 		xdl_free_script(xscr);
 	}
-
 	xdl_free_env(&xe);
 
 	return 0;
diff --git a/xdiff/xmacros.h b/xdiff/xmacros.h
index 4c2fde80c..78f02603b 100644
--- a/xdiff/xmacros.h
+++ b/xdiff/xmacros.h
@@ -33,6 +33,7 @@
 #define XDL_ISDIGIT(c) ((c) >= '0' && (c) <= '9')
 #define XDL_HASHLONG(v, b) (((unsigned long)(v) * GR_PRIME) >> ((CHAR_BIT * sizeof(unsigned long)) - (b)))
 #define XDL_PTRFREE(p) do { if (p) { xdl_free(p); (p) = NULL; } } while (0)
+#define XDL_RECMATCH(r1, r2) ((r1)->size == (r2)->size && memcmp((r1)->ptr, (r2)->ptr, (r1)->size) == 0)
 #define XDL_LE32_PUT(p, v) \
 do { \
 	unsigned char *__p = (unsigned char *) (p); \