1 files changed, 158 insertions, 58 deletions

diff --git a/xdiff/xemit.c b/xdiff/xemit.c
index 05bfa41f10..8c88dbde38 100644
--- a/xdiff/xemit.c
+++ b/xdiff/xemit.c
@@ -22,15 +22,6 @@
 
 #include "xinclude.h"
 
-
-
-
-static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec);
-static int xdl_emit_record(xdfile_t *xdf, long ri, char const *pre, xdemitcb_t *ecb);
-
-
-
-
 static long xdl_get_rec(xdfile_t *xdf, long ri, char const **rec) {
 
 	*rec = xdf->recs[ri]->ptr;
@@ -56,16 +47,51 @@ 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 = xchp->next; xch; xchp = xch, xch = xch->next) {
+		long distance = xch->i1 - (xchp->i1 + xchp->chg1);
+		if (distance > max_common)
+			break;
 
-	for (xchp = xscr, xch = xscr->next; xch; xchp = xch, xch = xch->next)
-		if (xch->i1 - (xchp->i1 + xchp->chg1) > max_common)
+		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 xchp;
+	return lxch;
 }
 
 
@@ -73,7 +99,7 @@ static long def_ff(const char *rec, long len, char *buf, long sz, void *priv)
 {
 	if (len > 0 &&
 			(isalpha((unsigned char)*rec) || /* identifier? */
-			 *rec == '_' ||	/* also identifier? */
+			 *rec == '_' || /* also identifier? */
 			 *rec == '$')) { /* identifiers from VMS and other esoterico */
 		if (len > sz)
 			len = sz;
@@ -85,59 +111,104 @@ static long def_ff(const char *rec, long len, char *buf, long sz, void *priv)
 	return -1;
 }
 
-static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll,
-		find_func_t ff, void *ff_priv) {
-
-	/*
-	 * Be quite stupid about this for now.  Find a line in the old file
-	 * before the start of the hunk (and context) which starts with a
-	 * plausible character.
-	 */
-
+static long match_func_rec(xdfile_t *xdf, xdemitconf_t const *xecfg, long ri,
+			   char *buf, long sz)
+{
 	const char *rec;
+	long len = xdl_get_rec(xdf, ri, &rec);
+	if (!xecfg->find_func)
+		return def_ff(rec, len, buf, sz, xecfg->find_func_priv);
+	return xecfg->find_func(rec, len, buf, sz, xecfg->find_func_priv);
+}
+
+struct func_line {
 	long len;
+	char buf[80];
+};
 
-	while (i-- > 0) {
-		len = xdl_get_rec(xf, i, &rec);
-		if ((*ll = ff(rec, len, buf, sz, ff_priv)) >= 0)
-			return;
+static long get_func_line(xdfenv_t *xe, xdemitconf_t const *xecfg,
+			  struct func_line *func_line, long start, long limit)
+{
+	long l, size, step = (start > limit) ? -1 : 1;
+	char *buf, dummy[1];
+
+	buf = func_line ? func_line->buf : dummy;
+	size = func_line ? sizeof(func_line->buf) : sizeof(dummy);
+
+	for (l = start; l != limit && 0 <= l && l < xe->xdf1.nrec; l += step) {
+		long len = match_func_rec(&xe->xdf1, xecfg, l, buf, size);
+		if (len >= 0) {
+			if (func_line)
+				func_line->len = len;
+			return l;
+		}
 	}
-	*ll = 0;
+	return -1;
 }
 
+static int is_empty_rec(xdfile_t *xdf, long ri)
+{
+	const char *rec;
+	long len = xdl_get_rec(xdf, ri, &rec);
 
-static int xdl_emit_common(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
-                           xdemitconf_t const *xecfg) {
-	xdfile_t *xdf = &xe->xdf1;
-	const char *rchg = xdf->rchg;
-	long ix;
-
-	for (ix = 0; ix < xdf->nrec; ix++) {
-		if (rchg[ix])
-			continue;
-		if (xdl_emit_record(xdf, ix, "", ecb))
-			return -1;
+	while (len > 0 && XDL_ISSPACE(*rec)) {
+		rec++;
+		len--;
 	}
-	return 0;
+	return !len;
 }
 
 int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		  xdemitconf_t const *xecfg) {
 	long s1, s2, e1, e2, lctx;
 	xdchange_t *xch, *xche;
-	char funcbuf[80];
-	long funclen = 0;
-	find_func_t ff = xecfg->find_func ?  xecfg->find_func : def_ff;
+	long funclineprev = -1;
+	struct func_line func_line = { 0 };
 
-	if (xecfg->flags & XDL_EMIT_COMMON)
-		return xdl_emit_common(xe, xscr, ecb, xecfg);
-
-	for (xch = xche = xscr; xch; xch = xche->next) {
-		xche = xdl_get_hunk(xch, xecfg);
+	for (xch = xscr; xch; xch = xche->next) {
+		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);
 
+		if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) {
+			long fs1, i1 = xch->i1;
+
+			/* Appended chunk? */
+			if (i1 >= xe->xdf1.nrec) {
+				char dummy[1];
+				long i2 = xch->i2;
+
+				/*
+				 * We don't need additional context if
+				 * a whole function was added.
+				 */
+				while (i2 < xe->xdf2.nrec) {
+					if (match_func_rec(&xe->xdf2, xecfg, i2,
+						dummy, sizeof(dummy)) >= 0)
+						goto post_context_calculation;
+					i2++;
+				}
+
+				/*
+				 * Otherwise get more context from the
+				 * pre-image.
+				 */
+				i1 = xe->xdf1.nrec - 1;
+			}
+
+			fs1 = get_func_line(xe, xecfg, NULL, i1, -1);
+			if (fs1 < 0)
+				fs1 = 0;
+			if (fs1 < s1) {
+				s2 -= s1 - fs1;
+				s1 = fs1;
+			}
+		}
+
+ post_context_calculation:
 		lctx = xecfg->ctxlen;
 		lctx = XDL_MIN(lctx, xe->xdf1.nrec - (xche->i1 + xche->chg1));
 		lctx = XDL_MIN(lctx, xe->xdf2.nrec - (xche->i2 + xche->chg2));
@@ -145,24 +216,53 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		e1 = xche->i1 + xche->chg1 + lctx;
 		e2 = xche->i2 + xche->chg2 + lctx;
 
+		if (xecfg->flags & XDL_EMIT_FUNCCONTEXT) {
+			long fe1 = get_func_line(xe, xecfg, NULL,
+						 xche->i1 + xche->chg1,
+						 xe->xdf1.nrec);
+			while (fe1 > 0 && is_empty_rec(&xe->xdf1, fe1 - 1))
+				fe1--;
+			if (fe1 < 0)
+				fe1 = xe->xdf1.nrec;
+			if (fe1 > e1) {
+				e2 += fe1 - e1;
+				e1 = fe1;
+			}
+
+			/*
+			 * Overlap with next change?  Then include it
+			 * in the current hunk and start over to find
+			 * its new end.
+			 */
+			if (xche->next) {
+				long l = XDL_MIN(xche->next->i1,
+						 xe->xdf1.nrec - 1);
+				if (l - xecfg->ctxlen <= e1 ||
+				    get_func_line(xe, xecfg, NULL, l, e1) < 0) {
+					xche = xche->next;
+					goto post_context_calculation;
+				}
+			}
+		}
+
 		/*
 		 * Emit current hunk header.
 		 */
 
 		if (xecfg->flags & XDL_EMIT_FUNCNAMES) {
-			xdl_find_func(&xe->xdf1, s1, funcbuf,
-				      sizeof(funcbuf), &funclen,
-				      ff, xecfg->find_func_priv);
+			get_func_line(xe, xecfg, &func_line,
+				      s1 - 1, funclineprev);
+			funclineprev = s1 - 1;
 		}
 		if (xdl_emit_hunk_hdr(s1 + 1, e1 - s1, s2 + 1, e2 - s2,
-				      funcbuf, funclen, ecb) < 0)
+				      func_line.buf, func_line.len, ecb) < 0)
 			return -1;
 
 		/*
 		 * Emit pre-context.
 		 */
-		for (; s1 < xch->i1; s1++)
-			if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0)
+		for (; s2 < xch->i2; s2++)
+			if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0)
 				return -1;
 
 		for (s1 = xch->i1, s2 = xch->i2;; xch = xch->next) {
@@ -170,7 +270,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 			 * Merge previous with current change atom.
 			 */
 			for (; s1 < xch->i1 && s2 < xch->i2; s1++, s2++)
-				if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0)
+				if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0)
 					return -1;
 
 			/*
@@ -196,8 +296,8 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		/*
 		 * Emit post-context.
 		 */
-		for (s1 = xche->i1 + xche->chg1; s1 < e1; s1++)
-			if (xdl_emit_record(&xe->xdf1, s1, " ", ecb) < 0)
+		for (s2 = xche->i2 + xche->chg2; s2 < e2; s2++)
+			if (xdl_emit_record(&xe->xdf2, s2, " ", ecb) < 0)
 				return -1;
 	}