diff: add --ignore-blank-lines option

The goal of the patch is to introduce the GNU diff
-B/--ignore-blank-lines as closely as possible. The short option is not
available because it's already used for "break-rewrites".

When this option is used, git-diff will not create hunks that simply
add or remove empty lines, but will still show empty lines
addition/suppression if they are close enough to "valuable" changes.

There are two differences between this option and GNU diff -B option:
- GNU diff doesn't have "--inter-hunk-context", so this must be handled
- The following sequence looks like a bug (context is displayed twice):

    $ seq 5 >file1
    $ cat <<EOF >file2
    change
    1
    2

    3
    4
    5
    change
    EOF
    $ diff -u -B file1 file2
    --- file1	2013-06-08 22:13:04.471517834 +0200
    +++ file2	2013-06-08 22:13:23.275517855 +0200
    @@ -1,5 +1,7 @@
    +change
     1
     2
    +
     3
     4
     5
    @@ -3,3 +5,4 @@
     3
     4
     5
    +change

So here is a more thorough description of the option:
- real changes are interesting
- blank lines that are close enough (less than context size) to
interesting changes are considered interesting (recursive definition)
- "context" lines are used around each hunk of interesting changes
- If two hunks are separated by less than "inter-hunk-context", they
will be merged into one.

The implementation does the "interesting changes selection" in a single
pass.

Signed-off-by: Antoine Pelisse <apelisse@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

7 files changed, 89 insertions, 8 deletions

diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 219a3bbca6..c0339919cc 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -39,6 +39,8 @@ extern "C" {
 #define XDF_DIFF_ALGORITHM_MASK (XDF_PATIENCE_DIFF | XDF_HISTOGRAM_DIFF)
 #define XDF_DIFF_ALG(x) ((x) & XDF_DIFF_ALGORITHM_MASK)
 
+#define XDF_IGNORE_BLANK_LINES (1 << 7)
+
 #define XDL_EMIT_FUNCNAMES (1 << 0)
 #define XDL_EMIT_COMMON (1 << 1)
 #define XDL_EMIT_FUNCCONTEXT (1 << 2)
diff --git a/xdiff/xdiffi.c b/xdiff/xdiffi.c
index b2eb6db2c8..2358a2d632 100644
--- a/xdiff/xdiffi.c
+++ b/xdiff/xdiffi.c
@@ -394,6 +394,7 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
 	xch->i2 = i2;
 	xch->chg1 = chg1;
 	xch->chg2 = chg2;
+	xch->ignore = 0;
 
 	return xch;
 }
@@ -544,7 +545,9 @@ static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 	xdchange_t *xch, *xche;
 
 	for (xch = xscr; xch; xch = xche->next) {
-		xche = xdl_get_hunk(xch, xecfg);
+		xche = xdl_get_hunk(&xch, xecfg);
+		if (!xch)
+			break;
 		if (xecfg->hunk_func(xch->i1, xche->i1 + xche->chg1 - xch->i1,
 				     xch->i2, xche->i2 + xche->chg2 - xch->i2,
 				     ecb->priv) < 0)
@@ -553,6 +556,27 @@ static int xdl_call_hunk_func(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 	return 0;
 }
 
+static void xdl_mark_ignorable(xdchange_t *xscr, xdfenv_t *xe, long flags)
+{
+	xdchange_t *xch;
+
+	for (xch = xscr; xch; xch = xch->next) {
+		int ignore = 1;
+		xrecord_t **rec;
+		long i;
+
+		rec = &xe->xdf1.recs[xch->i1];
+		for (i = 0; i < xch->chg1 && ignore; i++)
+			ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags);
+
+		rec = &xe->xdf2.recs[xch->i2];
+		for (i = 0; i < xch->chg2 && ignore; i++)
+			ignore = xdl_blankline(rec[i]->ptr, rec[i]->size, flags);
+
+		xch->ignore = ignore;
+	}
+}
+
 int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	     xdemitconf_t const *xecfg, xdemitcb_t *ecb) {
 	xdchange_t *xscr;
@@ -571,6 +595,9 @@ int xdl_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		return -1;
 	}
 	if (xscr) {
+		if (xpp->flags & XDF_IGNORE_BLANK_LINES)
+			xdl_mark_ignorable(xscr, &xe, xpp->flags);
+
 		if (ef(&xe, xscr, ecb, xecfg) < 0) {
 
 			xdl_free_script(xscr);
diff --git a/xdiff/xdiffi.h b/xdiff/xdiffi.h
index 7a92ea9c4d..8b81206c9a 100644
--- a/xdiff/xdiffi.h
+++ b/xdiff/xdiffi.h
@@ -41,6 +41,7 @@ typedef struct s_xdchange {
 	struct s_xdchange *next;
 	long i1, i2;
 	long chg1, chg2;
+	int ignore;
 } xdchange_t;
 
 
diff --git a/xdiff/xemit.c b/xdiff/xemit.c
index d11dbf9f13..4d8645867e 100644
--- a/xdiff/xemit.c
+++ b/xdiff/xemit.c
@@ -56,16 +56,51 @@ static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *
 /*
  * Starting at the passed change atom, find the latest change atom to be included
  * inside the differential hunk according to the specified configuration.
+ * Also advance xscr if the first changes must be discarded.
  */
-xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg) {
-	xdchange_t *xch, *xchp;
+xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg)
+{
+	xdchange_t *xch, *xchp, *lxch;
 	long max_common = 2 * xecfg->ctxlen + xecfg->interhunkctxlen;
+	long max_ignorable = xecfg->ctxlen;
+	unsigned long ignored = 0; /* number of ignored blank lines */
+
+	/* remove ignorable changes that are too far before other changes */
+	for (xchp = *xscr; xchp && xchp->ignore; xchp = xchp->next) {
+		xch = xchp->next;
+
+		if (xch == NULL ||
+		    xch->i1 - (xchp->i1 + xchp->chg1) >= max_ignorable)
+			*xscr = xch;
+	}
+
+	if (*xscr == NULL)
+		return NULL;
+
+	lxch = *xscr;
 
-	for (xchp = xscr, xch = xscr->next; xch; xchp = xch, xch = xch->next)
-		if (xch->i1 - (xchp->i1 + xchp->chg1) > max_common)
+	for (xchp = *xscr, xch = xchp->next; xch; xchp = xch, xch = xch->next) {
+		long distance = xch->i1 - (xchp->i1 + xchp->chg1);
+		if (distance > max_common)
 			break;
 
-	return xchp;
+		if (distance < max_ignorable && (!xch->ignore || lxch == xchp)) {
+			lxch = xch;
+			ignored = 0;
+		} else if (distance < max_ignorable && xch->ignore) {
+			ignored += xch->chg2;
+		} else if (lxch != xchp &&
+			   xch->i1 + ignored - (lxch->i1 + lxch->chg1) > max_common) {
+			break;
+		} else if (!xch->ignore) {
+			lxch = xch;
+			ignored = 0;
+		} else {
+			ignored += xch->chg2;
+		}
+	}
+
+	return lxch;
 }
 
 
@@ -139,7 +174,9 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		return xdl_emit_common(xe, xscr, ecb, xecfg);
 
 	for (xch = xscr; xch; xch = xche->next) {
-		xche = xdl_get_hunk(xch, xecfg);
+		xche = xdl_get_hunk(&xch, xecfg);
+		if (!xch)
+			break;
 
 		s1 = XDL_MAX(xch->i1 - xecfg->ctxlen, 0);
 		s2 = XDL_MAX(xch->i2 - xecfg->ctxlen, 0);
diff --git a/xdiff/xemit.h b/xdiff/xemit.h
index c2e2e83027..d29710770c 100644
--- a/xdiff/xemit.h
+++ b/xdiff/xemit.h
@@ -27,7 +27,7 @@
 typedef int (*emit_func_t)(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 			   xdemitconf_t const *xecfg);
 
-xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg);
+xdchange_t *xdl_get_hunk(xdchange_t **xscr, xdemitconf_t const *xecfg);
 int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		  xdemitconf_t const *xecfg);
 
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 9504eaecb8..62cb23dfd3 100644
--- a/xdiff/xutils.c
+++ b/xdiff/xutils.c
@@ -143,6 +143,19 @@ long xdl_guess_lines(mmfile_t *mf, long sample) {
 	return nl + 1;
 }
 
+int xdl_blankline(const char *line, long size, long flags)
+{
+	long i;
+
+	if (!(flags & XDF_WHITESPACE_FLAGS))
+		return (size <= 1);
+
+	for (i = 0; i < size && XDL_ISSPACE(line[i]); i++)
+		;
+
+	return (i == size);
+}
+
 int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
 {
 	int i1, i2;
diff --git a/xdiff/xutils.h b/xdiff/xutils.h
index ad1428ed69..4646ce5752 100644
--- a/xdiff/xutils.h
+++ b/xdiff/xutils.h
@@ -32,6 +32,7 @@ int xdl_cha_init(chastore_t *cha, long isize, long icount);
 void xdl_cha_free(chastore_t *cha);
 void *xdl_cha_alloc(chastore_t *cha);
 long xdl_guess_lines(mmfile_t *mf, long sample);
+int xdl_blankline(const char *line, long size, long flags);
 int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
 unsigned long xdl_hash_record(char const **data, char const *top, long flags);
 unsigned int xdl_hashbits(unsigned int size);