Per-path attribute based hunk header selection.

This makes"diff -p" hunk headers customizable via gitattributes mechanism.
It is based on Johannes's earlier patch that allowed to define a single
regexp to be used for everything.

The mechanism to arrive at the regexp that is used to define hunk header
is the same as other use of gitattributes.  You assign an attribute, funcname
(because "diff -p" typically uses the name of the function the patch is about
as the hunk header), a simple string value.  This can be one of the names of
built-in pattern (currently, "java" is defined) or a custom pattern name, to
be looked up from the configuration file.

  (in .gitattributes)
  *.java   funcname=java
  *.perl   funcname=perl

  (in .git/config)
  [funcname]
    java = ... # ugly and complicated regexp to override the built-in one.
    perl = ... # another ugly and complicated regexp to define a new one.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 27 insertions, 14 deletions

diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 9402bb0799..c00ddaa6e9 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -73,9 +73,13 @@ typedef struct s_xdemitcb {
 	int (*outf)(void *, mmbuffer_t *, int);
 } xdemitcb_t;
 
+typedef long (*find_func_t)(const char *line, long line_len, char *buffer, long buffer_size, void *priv);
+
 typedef struct s_xdemitconf {
 	long ctxlen;
 	unsigned long flags;
+	find_func_t find_func;
+	void *find_func_priv;
 } xdemitconf_t;
 
 typedef struct s_bdiffparam {
diff --git a/xdiff/xemit.c b/xdiff/xemit.c
index 4b6e639112..d3d9c845c6 100644
--- a/xdiff/xemit.c
+++ b/xdiff/xemit.c
@@ -69,7 +69,24 @@ static xdchange_t *xdl_get_hunk(xdchange_t *xscr, xdemitconf_t const *xecfg) {
 }
 
 
-static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll) {
+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 == '$')) { /* identifiers from VMS and other esoterico */
+		if (len > sz)
+			len = sz;
+		while (0 < len && isspace((unsigned char)rec[len - 1]))
+			len--;
+		memcpy(buf, rec, len);
+		return len;
+	}
+	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
@@ -80,22 +97,12 @@ static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll) {
 	const char *rec;
 	long len;
 
-	*ll = 0;
 	while (i-- > 0) {
 		len = xdl_get_rec(xf, i, &rec);
-		if (len > 0 &&
-		    (isalpha((unsigned char)*rec) || /* identifier? */
-		     *rec == '_' ||	/* also identifier? */
-		     *rec == '$')) {	/* mysterious GNU diff's invention */
-			if (len > sz)
-				len = sz;
-			while (0 < len && isspace((unsigned char)rec[len - 1]))
-				len--;
-			memcpy(buf, rec, len);
-			*ll = len;
+		if ((*ll = ff(rec, len, buf, sz, ff_priv)) >= 0)
 			return;
-		}
 	}
+	*ll = 0;
 }
 
 
@@ -120,6 +127,7 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 	xdchange_t *xch, *xche;
 	char funcbuf[80];
 	long funclen = 0;
+	find_func_t ff = xecfg->find_func ?  xecfg->find_func : def_ff;
 
 	if (xecfg->flags & XDL_EMIT_COMMON)
 		return xdl_emit_common(xe, xscr, ecb, xecfg);
@@ -143,7 +151,8 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 
 		if (xecfg->flags & XDL_EMIT_FUNCNAMES) {
 			xdl_find_func(&xe->xdf1, s1, funcbuf,
-				      sizeof(funcbuf), &funclen);
+				      sizeof(funcbuf), &funclen,
+				      ff, xecfg->find_func_priv);
 		}
 		if (xdl_emit_hunk_hdr(s1 + 1, e1 - s1, s2 + 1, e2 - s2,
 				      funcbuf, funclen, ecb) < 0)