convert: permit passing additional metadata to filter processes

There are a variety of situations where a filter process can make use of
some additional metadata.  For example, some people find the ident
filter too limiting and would like to include the commit or the branch
in their smudged files.  This information isn't available during
checkout as HEAD hasn't been updated at that point, and it wouldn't be
available in archives either.

Let's add a way to pass this metadata down to the filter.  We pass the
blob we're operating on, the treeish (preferring the commit over the
tree if one exists), and the ref we're operating on.  Note that we won't
pass this information in all cases, such as when renormalizing or when
we're performing diffs, since it doesn't make sense in those cases.

The data we currently get from the filter process looks like the
following:

  command=smudge
  pathname=git.c
  0000

With this change, we'll get data more like this:

  command=smudge
  pathname=git.c
  refname=refs/tags/v2.25.1
  treeish=c522f061d551c9bb8684a7c3859b2ece4499b56b
  blob=7be7ad34bd053884ec48923706e70c81719a8660
  0000

There are a couple things to note about this approach.  For operations
like checkout, treeish will always be a commit, since we cannot check
out individual trees, but for other operations, like archive, we can end
up operating on only a particular tree, so we'll provide only a tree as
the treeish.  Similar comments apply for refname, since there are a
variety of cases in which we won't have a ref.

This commit wires up the code to print this information, but doesn't
pass any of it at this point.  In a future commit, we'll have various
code paths pass the actual useful data down.

Signed-off-by: brian m. carlson <bk2204@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

apply.c

@@ -4349,7 +4349,7 @@ static int try_create_file(struct apply_state *state, const char *path,
 	if (fd < 0)
 		return 1;
 
-	if (convert_to_working_tree(state->repo->index, path, buf, size, &nbuf)) {
+	if (convert_to_working_tree(state->repo->index, path, buf, size, &nbuf, NULL)) {
 		size = nbuf.len;
 		buf  = nbuf.buf;
 	}

archive.c

@@ -85,7 +85,7 @@ void *object_file_to_archive(const struct archiver_args *args,
 		size_t size = 0;
 
 		strbuf_attach(&buf, buffer, *sizep, *sizep + 1);
-		convert_to_working_tree(args->repo->index, path, buf.buf, buf.len, &buf);
+		convert_to_working_tree(args->repo->index, path, buf.buf, buf.len, &buf, NULL);
 		if (commit)
 			format_subst(commit, buf.buf, buf.len, &buf);
 		buffer = strbuf_detach(&buf, &size);

builtin/cat-file.c

@@ -42,7 +42,7 @@ static int filter_object(const char *path, unsigned mode,
 			     oid_to_hex(oid), path);
 	if ((type == OBJ_BLOB) && S_ISREG(mode)) {
 		struct strbuf strbuf = STRBUF_INIT;
-		if (convert_to_working_tree(&the_index, path, *buf, *size, &strbuf)) {
+		if (convert_to_working_tree(&the_index, path, *buf, *size, &strbuf, NULL)) {
 			free(*buf);
 			*size = strbuf.len;
 			*buf = strbuf_detach(&strbuf, NULL);

convert.c

@@ -797,6 +797,7 @@ static void handle_filter_error(const struct strbuf *filter_status,
 static int apply_multi_file_filter(const char *path, const char *src, size_t len,
 				   int fd, struct strbuf *dst, const char *cmd,
 				   const unsigned int wanted_capability,
+				   const struct checkout_metadata *meta,
 				   struct delayed_checkout *dco)
 {
 	int err;
@@ -855,6 +856,24 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	if (err)
 		goto done;
 
+	if (meta && meta->refname) {
+		err = packet_write_fmt_gently(process->in, "ref=%s\n", meta->refname);
+		if (err)
+			goto done;
+	}
+
+	if (meta && !is_null_oid(&meta->treeish)) {
+		err = packet_write_fmt_gently(process->in, "treeish=%s\n", oid_to_hex(&meta->treeish));
+		if (err)
+			goto done;
+	}
+
+	if (meta && !is_null_oid(&meta->blob)) {
+		err = packet_write_fmt_gently(process->in, "blob=%s\n", oid_to_hex(&meta->blob));
+		if (err)
+			goto done;
+	}
+
 	if ((entry->supported_capabilities & CAP_DELAY) &&
 	    dco && dco->state == CE_CAN_DELAY) {
 		can_delay = 1;
@@ -971,6 +990,7 @@ static struct convert_driver {
 static int apply_filter(const char *path, const char *src, size_t len,
 			int fd, struct strbuf *dst, struct convert_driver *drv,
 			const unsigned int wanted_capability,
+			const struct checkout_metadata *meta,
 			struct delayed_checkout *dco)
 {
 	const char *cmd = NULL;
@@ -990,7 +1010,7 @@ static int apply_filter(const char *path, const char *src, size_t len,
 		return apply_single_file_filter(path, src, len, fd, dst, cmd);
 	else if (drv->process && *drv->process)
 		return apply_multi_file_filter(path, src, len, fd, dst,
-			drv->process, wanted_capability, dco);
+			drv->process, wanted_capability, meta, dco);
 
 	return 0;
 }
@@ -1368,7 +1388,7 @@ int would_convert_to_git_filter_fd(const struct index_state *istate, const char
 	if (!ca.drv->required)
 		return 0;
 
-	return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL);
+	return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL, NULL);
 }
 
 const char *get_convert_attr_ascii(const struct index_state *istate, const char *path)
@@ -1406,7 +1426,7 @@ int convert_to_git(const struct index_state *istate,
 
 	convert_attrs(istate, &ca, path);
 
-	ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL);
+	ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL, NULL);
 	if (!ret && ca.drv && ca.drv->required)
 		die(_("%s: clean filter '%s' failed"), path, ca.drv->name);
 
@@ -1441,7 +1461,7 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 	assert(ca.drv);
 	assert(ca.drv->clean || ca.drv->process);
 
-	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL))
+	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL, NULL))
 		die(_("%s: clean filter '%s' failed"), path, ca.drv->name);
 
 	encode_to_git(path, dst->buf, dst->len, dst, ca.working_tree_encoding, conv_flags);
@@ -1452,7 +1472,9 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 static int convert_to_working_tree_internal(const struct index_state *istate,
 					    const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
-					    int normalizing, struct delayed_checkout *dco)
+					    int normalizing,
+					    const struct checkout_metadata *meta,
+					    struct delayed_checkout *dco)
 {
 	int ret = 0, ret_filter = 0;
 	struct conv_attrs ca;
@@ -1484,7 +1506,7 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 	}
 
 	ret_filter = apply_filter(
-		path, src, len, -1, dst, ca.drv, CAP_SMUDGE, dco);
+		path, src, len, -1, dst, ca.drv, CAP_SMUDGE, meta, dco);
 	if (!ret_filter && ca.drv && ca.drv->required)
 		die(_("%s: smudge filter %s failed"), path, ca.drv->name);
 
@@ -1494,22 +1516,24 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 int async_convert_to_working_tree(const struct index_state *istate,
 				  const char *path, const char *src,
 				  size_t len, struct strbuf *dst,
+				  const struct checkout_metadata *meta,
 				  void *dco)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, dco);
+	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, dco);
 }
 
 int convert_to_working_tree(const struct index_state *istate,
 			    const char *path, const char *src,
-			    size_t len, struct strbuf *dst)
+			    size_t len, struct strbuf *dst,
+			    const struct checkout_metadata *meta)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, NULL);
+	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, NULL);
 }
 
 int renormalize_buffer(const struct index_state *istate, const char *path,
 		       const char *src, size_t len, struct strbuf *dst)
 {
-	int ret = convert_to_working_tree_internal(istate, path, src, len, dst, 1, NULL);
+	int ret = convert_to_working_tree_internal(istate, path, src, len, dst, 1, NULL, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;

convert.h

@@ -4,10 +4,10 @@
 #ifndef CONVERT_H
 #define CONVERT_H
 
+#include "hash.h"
 #include "string-list.h"
 
 struct index_state;
-struct object_id;
 struct strbuf;
 
 #define CONV_EOL_RNDTRP_DIE   (1<<0) /* Die if CRLF to LF to CRLF is different */
@@ -57,6 +57,12 @@ struct delayed_checkout {
 	struct string_list paths;
 };
 
+struct checkout_metadata {
+	const char *refname;
+	struct object_id treeish;
+	struct object_id blob;
+};
+
 extern enum eol core_eol;
 extern char *check_roundtrip_encoding;
 const char *get_cached_convert_stats_ascii(const struct index_state *istate,
@@ -71,10 +77,12 @@ int convert_to_git(const struct index_state *istate,
 		   struct strbuf *dst, int conv_flags);
 int convert_to_working_tree(const struct index_state *istate,
 			    const char *path, const char *src,
-			    size_t len, struct strbuf *dst);
+			    size_t len, struct strbuf *dst,
+			    const struct checkout_metadata *meta);
 int async_convert_to_working_tree(const struct index_state *istate,
 				  const char *path, const char *src,
 				  size_t len, struct strbuf *dst,
+				  const struct checkout_metadata *meta,
 				  void *dco);
 int async_query_available_blobs(const char *cmd,
 				struct string_list *available_paths);

diff.c

@@ -4071,7 +4071,7 @@ static void prep_temp_blob(struct index_state *istate,
 	if (!temp->tempfile)
 		die_errno("unable to create temp-file");
 	if (convert_to_working_tree(istate, path,
-			(const char *)blob, (size_t)size, &buf)) {
+			(const char *)blob, (size_t)size, &buf, NULL)) {
 		blob = buf.buf;
 		size = buf.len;
 	}

entry.c

@@ -315,13 +315,13 @@ static int write_entry(struct cache_entry *ce,
 		 */
 		if (dco && dco->state != CE_NO_DELAY) {
 			ret = async_convert_to_working_tree(state->istate, ce->name, new_blob,
-							    size, &buf, dco);
+							    size, &buf, NULL, dco);
 			if (ret && string_list_has_string(&dco->paths, ce->name)) {
 				free(new_blob);
 				goto delayed;
 			}
 		} else
-			ret = convert_to_working_tree(state->istate, ce->name, new_blob, size, &buf);
+			ret = convert_to_working_tree(state->istate, ce->name, new_blob, size, &buf, NULL);
 
 		if (ret) {
 			free(new_blob);

merge-recursive.c

@@ -958,7 +958,7 @@ static int update_file_flags(struct merge_options *opt,
 		if (S_ISREG(contents->mode)) {
 			struct strbuf strbuf = STRBUF_INIT;
 			if (convert_to_working_tree(opt->repo->index,
-						    path, buf, size, &strbuf)) {
+						    path, buf, size, &strbuf, NULL)) {
 				free(buf);
 				size = strbuf.len;
 				buf = strbuf_detach(&strbuf, NULL);