Merge branch 'jk/xdiff-interface'

The interface into "xdiff" library used to discover the offset and
size of a generated patch hunk by first formatting it into the
textual hunk header "@@ -n,m +k,l @@" and then parsing the numbers
out.  A new interface has been introduced to allow callers a more
direct access to them.

* jk/xdiff-interface:
  xdiff-interface: drop parse_hunk_header()
  range-diff: use a hunk callback
  diff: convert --check to use a hunk callback
  combine-diff: use an xdiff hunk callback
  diff: use hunk callback for word-diff
  diff: discard hunk headers for patch-ids earlier
  diff: avoid generating unused hunk header lines
  xdiff-interface: provide a separate consume callback for hunks
  xdiff: provide a separate emit callback for hunks

10 files changed, 143 insertions, 115 deletions

diff --git a/builtin/merge-tree.c b/builtin/merge-tree.c
index 8fc108d..70f6fc9 100644
--- a/builtin/merge-tree.c
+++ b/builtin/merge-tree.c
@@ -110,7 +110,8 @@ static void show_diff(struct merge_list *entry)
 	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	xecfg.ctxlen = 3;
-	ecb.outf = show_outf;
+	ecb.out_hunk = NULL;
+	ecb.out_line = show_outf;
 	ecb.priv = NULL;
 
 	src.ptr = origin(entry, &size);
diff --git a/builtin/rerere.c b/builtin/rerere.c
index e89ccbc..d78eeae 100644
--- a/builtin/rerere.c
+++ b/builtin/rerere.c
@@ -41,7 +41,8 @@ static int diff_two(const char *file1, const char *label1,
 	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	xecfg.ctxlen = 3;
-	ecb.outf = outf;
+	ecb.out_hunk = NULL;
+	ecb.out_line = outf;
 	ret = xdi_diff(&minus, &plus, &xpp, &xecfg, &ecb);
 
 	free(minus.ptr);
diff --git a/combine-diff.c b/combine-diff.c
index 10155e0..ad7752e 100644
--- a/combine-diff.c
+++ b/combine-diff.c
@@ -345,38 +345,43 @@ struct combine_diff_state {
 	struct sline *lost_bucket;
 };
 
-static void consume_line(void *state_, char *line, unsigned long len)
+static void consume_hunk(void *state_,
+			 long ob, long on,
+			 long nb, long nn,
+			 const char *funcline, long funclen)
 {
 	struct combine_diff_state *state = state_;
-	if (5 < len && !memcmp("@@ -", line, 4)) {
-		if (parse_hunk_header(line, len,
-				      &state->ob, &state->on,
-				      &state->nb, &state->nn))
-			return;
-		state->lno = state->nb;
-		if (state->nn == 0) {
-			/* @@ -X,Y +N,0 @@ removed Y lines
-			 * that would have come *after* line N
-			 * in the result.  Our lost buckets hang
-			 * to the line after the removed lines,
-			 *
-			 * Note that this is correct even when N == 0,
-			 * in which case the hunk removes the first
-			 * line in the file.
-			 */
-			state->lost_bucket = &state->sline[state->nb];
-			if (!state->nb)
-				state->nb = 1;
-		} else {
-			state->lost_bucket = &state->sline[state->nb-1];
-		}
-		if (!state->sline[state->nb-1].p_lno)
-			state->sline[state->nb-1].p_lno =
-				xcalloc(state->num_parent,
-					sizeof(unsigned long));
-		state->sline[state->nb-1].p_lno[state->n] = state->ob;
-		return;
+
+	state->ob = ob;
+	state->on = on;
+	state->nb = nb;
+	state->nn = nn;
+	state->lno = state->nb;
+	if (state->nn == 0) {
+		/* @@ -X,Y +N,0 @@ removed Y lines
+		 * that would have come *after* line N
+		 * in the result.  Our lost buckets hang
+		 * to the line after the removed lines,
+		 *
+		 * Note that this is correct even when N == 0,
+		 * in which case the hunk removes the first
+		 * line in the file.
+		 */
+		state->lost_bucket = &state->sline[state->nb];
+		if (!state->nb)
+			state->nb = 1;
+	} else {
+		state->lost_bucket = &state->sline[state->nb-1];
 	}
+	if (!state->sline[state->nb-1].p_lno)
+		state->sline[state->nb-1].p_lno =
+			xcalloc(state->num_parent, sizeof(unsigned long));
+	state->sline[state->nb-1].p_lno[state->n] = state->ob;
+}
+
+static void consume_line(void *state_, char *line, unsigned long len)
+{
+	struct combine_diff_state *state = state_;
 	if (!state->lost_bucket)
 		return; /* not in any hunk yet */
 	switch (line[0]) {
@@ -421,8 +426,8 @@ static void combine_diff(struct repository *r,
 	state.num_parent = num_parent;
 	state.n = n;
 
-	if (xdi_diff_outf(&parent_file, result_file, consume_line, &state,
-			  &xpp, &xecfg))
+	if (xdi_diff_outf(&parent_file, result_file, consume_hunk,
+			  consume_line, &state, &xpp, &xecfg))
 		die("unable to generate combined diff for %s",
 		    oid_to_hex(parent));
 	free(parent_file.ptr);
diff --git a/diff.c b/diff.c
index 8647db3..e38d1ec 100644
--- a/diff.c
+++ b/diff.c
@@ -1912,19 +1912,17 @@ static int color_words_output_graph_prefix(struct diff_words_data *diff_words)
 	}
 }
 
-static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
+static void fn_out_diff_words_aux(void *priv,
+				  long minus_first, long minus_len,
+				  long plus_first, long plus_len,
+				  const char *func, long funclen)
 {
 	struct diff_words_data *diff_words = priv;
 	struct diff_words_style *style = diff_words->style;
-	int minus_first, minus_len, plus_first, plus_len;
 	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 	struct diff_options *opt = diff_words->opt;
 	const char *line_prefix;
 
-	if (line[0] != '@' || parse_hunk_header(line, len,
-			&minus_first, &minus_len, &plus_first, &plus_len))
-		return;
-
 	assert(opt);
 	line_prefix = diff_line_prefix(opt);
 
@@ -2074,8 +2072,8 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	xpp.flags = 0;
 	/* as only the hunk header will be parsed, we need a 0-context */
 	xecfg.ctxlen = 0;
-	if (xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
-			  &xpp, &xecfg))
+	if (xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, NULL,
+			  diff_words, &xpp, &xecfg))
 		die("unable to generate word diff");
 	free(minus.ptr);
 	free(plus.ptr);
@@ -3130,6 +3128,15 @@ static int is_conflict_marker(const char *line, int marker_size, unsigned long l
 	return 1;
 }
 
+static void checkdiff_consume_hunk(void *priv,
+				   long ob, long on, long nb, long nn,
+				   const char *func, long funclen)
+
+{
+	struct checkdiff_t *data = priv;
+	data->lineno = nb - 1;
+}
+
 static void checkdiff_consume(void *priv, char *line, unsigned long len)
 {
 	struct checkdiff_t *data = priv;
@@ -3165,12 +3172,6 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len)
 			      data->o->file, set, reset, ws);
 	} else if (line[0] == ' ') {
 		data->lineno++;
-	} else if (line[0] == '@') {
-		char *plus = strchr(line, '+');
-		if (plus)
-			data->lineno = strtol(plus, NULL, 10) - 1;
-		else
-			die("invalid diff");
 	}
 }
 
@@ -3526,8 +3527,8 @@ static void builtin_diff(const char *name_a,
 			xecfg.ctxlen = strtoul(v, NULL, 10);
 		if (o->word_diff)
 			init_diff_words_data(&ecbdata, o, one, two);
-		if (xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
-				  &xpp, &xecfg))
+		if (xdi_diff_outf(&mf1, &mf2, NULL, fn_out_consume,
+				  &ecbdata, &xpp, &xecfg))
 			die("unable to generate diff for %s", one->path);
 		if (o->word_diff)
 			free_diff_words_data(&ecbdata);
@@ -3637,8 +3638,8 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 		xpp.anchors_nr = o->anchors_nr;
 		xecfg.ctxlen = o->context;
 		xecfg.interhunkctxlen = o->interhunkcontext;
-		if (xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
-				  &xpp, &xecfg))
+		if (xdi_diff_outf(&mf1, &mf2, discard_hunk_line,
+				  diffstat_consume, diffstat, &xpp, &xecfg))
 			die("unable to generate diffstat for %s", one->path);
 	}
 
@@ -3686,7 +3687,8 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 		memset(&xecfg, 0, sizeof(xecfg));
 		xecfg.ctxlen = 1; /* at least one context line */
 		xpp.flags = 0;
-		if (xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
+		if (xdi_diff_outf(&mf1, &mf2, checkdiff_consume_hunk,
+				  checkdiff_consume, &data,
 				  &xpp, &xecfg))
 			die("unable to generate checkdiff for %s", one->path);
 
@@ -5666,10 +5668,6 @@ static void patch_id_consume(void *priv, char *line, unsigned long len)
 	struct patch_id_t *data = priv;
 	int new_len;
 
-	/* Ignore line numbers when computing the SHA1 of the patch */
-	if (starts_with(line, "@@ -"))
-		return;
-
 	new_len = remove_space(line, len);
 
 	git_SHA1_Update(data->ctx, line, new_len);
@@ -5771,8 +5769,8 @@ static int diff_get_patch_id(struct diff_options *options, struct object_id *oid
 		xpp.flags = 0;
 		xecfg.ctxlen = 3;
 		xecfg.flags = 0;
-		if (xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data,
-				  &xpp, &xecfg))
+		if (xdi_diff_outf(&mf1, &mf2, discard_hunk_line,
+				  patch_id_consume, &data, &xpp, &xecfg))
 			return error("unable to generate patch-id diff for %s",
 				     p->one->path);
 	}
diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index d2361e0..69fc55e 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -62,7 +62,8 @@ static int diff_grep(mmfile_t *one, mmfile_t *two,
 	ecbdata.hit = 0;
 	xecfg.ctxlen = o->context;
 	xecfg.interhunkctxlen = o->interhunkcontext;
-	if (xdi_diff_outf(one, two, diffgrep_consume, &ecbdata, &xpp, &xecfg))
+	if (xdi_diff_outf(one, two, discard_hunk_line, diffgrep_consume,
+			  &ecbdata, &xpp, &xecfg))
 		return 0;
 	return ecbdata.hit;
 }
diff --git a/range-diff.c b/range-diff.c
index bd8083f..3958720 100644
--- a/range-diff.c
+++ b/range-diff.c
@@ -197,6 +197,12 @@ static void diffsize_consume(void *data, char *line, unsigned long len)
 	(*(int *)data)++;
 }
 
+static void diffsize_hunk(void *data, long ob, long on, long nb, long nn,
+			  const char *funcline, long funclen)
+{
+	diffsize_consume(data, NULL, 0);
+}
+
 static int diffsize(const char *a, const char *b)
 {
 	xpparam_t pp = { 0 };
@@ -210,7 +216,9 @@ static int diffsize(const char *a, const char *b)
 	mf2.size = strlen(b);
 
 	cfg.ctxlen = 3;
-	if (!xdi_diff_outf(&mf1, &mf2, diffsize_consume, &count, &pp, &cfg))
+	if (!xdi_diff_outf(&mf1, &mf2,
+			   diffsize_hunk, diffsize_consume, &count,
+			   &pp, &cfg))
 		return count;
 
 	error(_("failed to generate diff"));
diff --git a/xdiff-interface.c b/xdiff-interface.c
index e7af95d..80f060d 100644
--- a/xdiff-interface.c
+++ b/xdiff-interface.c
@@ -9,54 +9,26 @@
 #include "xdiff/xutils.h"
 
 struct xdiff_emit_state {
-	xdiff_emit_consume_fn consume;
+	xdiff_emit_hunk_fn hunk_fn;
+	xdiff_emit_line_fn line_fn;
 	void *consume_callback_data;
 	struct strbuf remainder;
 };
 
-static int parse_num(char **cp_p, int *num_p)
+static int xdiff_out_hunk(void *priv_,
+			  long old_begin, long old_nr,
+			  long new_begin, long new_nr,
+			  const char *func, long funclen)
 {
-	char *cp = *cp_p;
-	int num = 0;
+	struct xdiff_emit_state *priv = priv_;
 
-	while ('0' <= *cp && *cp <= '9')
-		num = num * 10 + *cp++ - '0';
-	if (!(cp - *cp_p))
-		return -1;
-	*cp_p = cp;
-	*num_p = num;
-	return 0;
-}
+	if (priv->remainder.len)
+		BUG("xdiff emitted hunk in the middle of a line");
 
-int parse_hunk_header(char *line, int len,
-		      int *ob, int *on,
-		      int *nb, int *nn)
-{
-	char *cp;
-	cp = line + 4;
-	if (parse_num(&cp, ob)) {
-	bad_line:
-		return error("malformed diff output: %s", line);
-	}
-	if (*cp == ',') {
-		cp++;
-		if (parse_num(&cp, on))
-			goto bad_line;
-	}
-	else
-		*on = 1;
-	if (*cp++ != ' ' || *cp++ != '+')
-		goto bad_line;
-	if (parse_num(&cp, nb))
-		goto bad_line;
-	if (*cp == ',') {
-		cp++;
-		if (parse_num(&cp, nn))
-			goto bad_line;
-	}
-	else
-		*nn = 1;
-	return -!!memcmp(cp, " @@", 3);
+	priv->hunk_fn(priv->consume_callback_data,
+		      old_begin, old_nr, new_begin, new_nr,
+		      func, funclen);
+	return 0;
 }
 
 static void consume_one(void *priv_, char *s, unsigned long size)
@@ -67,7 +39,7 @@ static void consume_one(void *priv_, char *s, unsigned long size)
 		unsigned long this_size;
 		ep = memchr(s, '\n', size);
 		this_size = (ep == NULL) ? size : (ep - s + 1);
-		priv->consume(priv->consume_callback_data, s, this_size);
+		priv->line_fn(priv->consume_callback_data, s, this_size);
 		size -= this_size;
 		s += this_size;
 	}
@@ -78,6 +50,9 @@ static int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf)
 	struct xdiff_emit_state *priv = priv_;
 	int i;
 
+	if (!priv->line_fn)
+		return 0;
+
 	for (i = 0; i < nbuf; i++) {
 		if (mb[i].ptr[mb[i].size-1] != '\n') {
 			/* Incomplete line */
@@ -140,8 +115,16 @@ int xdi_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdemitconf_t co
 	return xdl_diff(&a, &b, xpp, xecfg, xecb);
 }
 
+void discard_hunk_line(void *priv,
+		       long ob, long on, long nb, long nn,
+		       const char *func, long funclen)
+{
+}
+
 int xdi_diff_outf(mmfile_t *mf1, mmfile_t *mf2,
-		  xdiff_emit_consume_fn fn, void *consume_callback_data,
+		  xdiff_emit_hunk_fn hunk_fn,
+		  xdiff_emit_line_fn line_fn,
+		  void *consume_callback_data,
 		  xpparam_t const *xpp, xdemitconf_t const *xecfg)
 {
 	int ret;
@@ -149,10 +132,13 @@ int xdi_diff_outf(mmfile_t *mf1, mmfile_t *mf2,
 	xdemitcb_t ecb;
 
 	memset(&state, 0, sizeof(state));
-	state.consume = fn;
+	state.hunk_fn = hunk_fn;
+	state.line_fn = line_fn;
 	state.consume_callback_data = consume_callback_data;
 	memset(&ecb, 0, sizeof(ecb));
-	ecb.outf = xdiff_outf;
+	if (hunk_fn)
+		ecb.out_hunk = xdiff_out_hunk;
+	ecb.out_line = xdiff_outf;
 	ecb.priv = &state;
 	strbuf_init(&state.remainder, 0);
 	ret = xdi_diff(mf1, mf2, xpp, xecfg, &ecb);
diff --git a/xdiff-interface.h b/xdiff-interface.h
index 135fc05..2d41fff 100644
--- a/xdiff-interface.h
+++ b/xdiff-interface.h
@@ -11,15 +11,18 @@
  */
 #define MAX_XDIFF_SIZE (1024UL * 1024 * 1023)
 
-typedef void (*xdiff_emit_consume_fn)(void *, char *, unsigned long);
+typedef void (*xdiff_emit_line_fn)(void *, char *, unsigned long);
+typedef void (*xdiff_emit_hunk_fn)(void *data,
+				   long old_begin, long old_nr,
+				   long new_begin, long new_nr,
+				   const char *func, long funclen);
 
 int xdi_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdemitconf_t const *xecfg, xdemitcb_t *ecb);
 int xdi_diff_outf(mmfile_t *mf1, mmfile_t *mf2,
-		  xdiff_emit_consume_fn fn, void *consume_callback_data,
+		  xdiff_emit_hunk_fn hunk_fn,
+		  xdiff_emit_line_fn line_fn,
+		  void *consume_callback_data,
 		  xpparam_t const *xpp, xdemitconf_t const *xecfg);
-int parse_hunk_header(char *line, int len,
-		      int *ob, int *on,
-		      int *nb, int *nn);
 int read_mmfile(mmfile_t *ptr, const char *filename);
 void read_mmblob(mmfile_t *ptr, const struct object_id *oid);
 int buffer_is_binary(const char *ptr, unsigned long size);
@@ -30,6 +33,14 @@ extern int git_xmerge_config(const char *var, const char *value, void *cb);
 extern int git_xmerge_style;
 
 /*
+ * Can be used as a no-op hunk_fn for xdi_diff_outf(), since a NULL
+ * one just sends the hunk line to the line_fn callback).
+ */
+void discard_hunk_line(void *priv,
+		       long ob, long on, long nb, long nn,
+		       const char *func, long funclen);
+
+/*
  * Compare the strings l1 with l2 which are of size s1 and s2 respectively.
  * Returns 1 if the strings are deemed equal, 0 otherwise.
  * The `flags` given as XDF_WHITESPACE_FLAGS determine how white spaces
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 2356da5..b158369 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -86,7 +86,11 @@ typedef struct s_xpparam {
 
 typedef struct s_xdemitcb {
 	void *priv;
-	int (*outf)(void *, mmbuffer_t *, int);
+	int (*out_hunk)(void *,
+			long old_begin, long old_nr,
+			long new_begin, long new_nr,
+			const char *func, long funclen);
+	int (*out_line)(void *, mmbuffer_t *, int);
 } xdemitcb_t;
 
 typedef long (*find_func_t)(const char *line, long line_len, char *buffer, long buffer_size, void *priv);
diff --git a/xdiff/xutils.c b/xdiff/xutils.c
index 88e5995..963e1c5 100644
--- a/xdiff/xutils.c
+++ b/xdiff/xutils.c
@@ -54,7 +54,7 @@ int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize,
 		mb[2].size = strlen(mb[2].ptr);
 		i++;
 	}
-	if (ecb->outf(ecb->priv, mb, i) < 0) {
+	if (ecb->out_line(ecb->priv, mb, i) < 0) {
 
 		return -1;
 	}
@@ -344,8 +344,9 @@ int xdl_num_out(char *out, long val) {
 	return str - out;
 }
 
-int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,
-		      const char *func, long funclen, xdemitcb_t *ecb) {
+static int xdl_format_hunk_hdr(long s1, long c1, long s2, long c2,
+			       const char *func, long funclen,
+			       xdemitcb_t *ecb) {
 	int nb = 0;
 	mmbuffer_t mb;
 	char buf[128];
@@ -387,9 +388,21 @@ int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,
 
 	mb.ptr = buf;
 	mb.size = nb;
-	if (ecb->outf(ecb->priv, &mb, 1) < 0)
+	if (ecb->out_line(ecb->priv, &mb, 1) < 0)
 		return -1;
+	return 0;
+}
 
+int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,
+		      const char *func, long funclen,
+		      xdemitcb_t *ecb) {
+	if (!ecb->out_hunk)
+		return xdl_format_hunk_hdr(s1, c1, s2, c2, func, funclen, ecb);
+	if (ecb->out_hunk(ecb->priv,
+			  c1 ? s1 : s1 - 1, c1,
+			  c2 ? s2 : s2 - 1, c2,
+			  func, funclen) < 0)
+		return -1;
 	return 0;
 }