[PATCH v2 1/2] abspath: add a function to resolve paths with missing components

["brian m. carlson" <sandals@xxxxxxxxxxxxxxxxxxxx>]

We'd like to canonicalize paths such that we can preserve any number of
trailing components that may be missing.  Let's add a function to do
that that calls strbuf_realpath to find the canonical path for the
portion we do have and then append the missing part.  We adjust
strip_last_component to return us the component it has stripped and use
that to help us accumulate the missing part.

Note that it is intentional that we invoke strbuf_realpath here,
repeatedly if necessary, because on Windows that function is replaced
with a version that uses the proper system semantics for
canonicalization.  Trying to adjust strbuf_realpath to perform this kind
of canonicalization with an additional option would fail to work
properly on Windows.  The present approach is equivalent to
strbuf_realpath for cases where the path exists, and the only other
cases where we will use this function the additional overhead of
multiple invocations is not significant.

Signed-off-by: brian m. carlson <sandals@xxxxxxxxxxxxxxxxxxxx>
---
 abspath.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++----
 cache.h   |  1 +
 2 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/abspath.c b/abspath.c
index 6f15a418bb..092bb33b64 100644
--- a/abspath.c
+++ b/abspath.c
@@ -11,8 +11,12 @@ int is_directory(const char *path)
 	return (!stat(path, &st) && S_ISDIR(st.st_mode));
 }
 
-/* removes the last path component from 'path' except if 'path' is root */
-static void strip_last_component(struct strbuf *path)
+/*
+ * Removes the last path component from 'path' except if 'path' is root.
+ *
+ * If last is not NULL, the last path component is copied to last.
+ */
+static void strip_last_component(struct strbuf *path, struct strbuf *last)
 {
 	size_t offset = offset_1st_component(path->buf);
 	size_t len = path->len;
@@ -20,6 +24,10 @@ static void strip_last_component(struct strbuf *path)
 	/* Find start of the last component */
 	while (offset < len && !is_dir_sep(path->buf[len - 1]))
 		len--;
+
+	if (last)
+		strbuf_addstr(last, path->buf + len);
+
 	/* Skip sequences of multiple path-separators */
 	while (offset < len && is_dir_sep(path->buf[len - 1]))
 		len--;
@@ -118,7 +126,7 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
 			continue; /* '.' component */
 		} else if (next.len == 2 && !strcmp(next.buf, "..")) {
 			/* '..' component; strip the last path component */
-			strip_last_component(resolved);
+			strip_last_component(resolved, NULL);
 			continue;
 		}
 
@@ -169,7 +177,7 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
 				 * strip off the last component since it will
 				 * be replaced with the contents of the symlink
 				 */
-				strip_last_component(resolved);
+				strip_last_component(resolved, NULL);
 			}
 
 			/*
@@ -202,6 +210,40 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
 	return retval;
 }
 
+/*
+ * Like strbuf_realpath, but trailing components which do not exist are copied
+ * through.
+ */
+char *strbuf_realpath_missing(struct strbuf *resolved, const char *path)
+{
+	struct strbuf remaining = STRBUF_INIT;
+	struct strbuf trailing = STRBUF_INIT;
+	struct strbuf component = STRBUF_INIT;
+
+	strbuf_addstr(&remaining, path);
+
+	while (remaining.len) {
+		if (strbuf_realpath(resolved, remaining.buf, 0)) {
+			strbuf_addbuf(resolved, &trailing);
+
+			strbuf_release(&component);
+			strbuf_release(&remaining);
+			strbuf_release(&trailing);
+
+			return resolved->buf;
+		}
+		strip_last_component(&remaining, &component);
+		strbuf_insertstr(&trailing, 0, "/");
+		strbuf_insertstr(&trailing, 1, component.buf);
+		strbuf_reset(&component);
+	}
+
+	strbuf_release(&component);
+	strbuf_release(&remaining);
+	strbuf_release(&trailing);
+	return NULL;
+}
+
 char *real_pathdup(const char *path, int die_on_error)
 {
 	struct strbuf realpath = STRBUF_INIT;
diff --git a/cache.h b/cache.h
index c0072d43b1..e1e17e108e 100644
--- a/cache.h
+++ b/cache.h
@@ -1320,6 +1320,7 @@ static inline int is_absolute_path(const char *path)
 int is_directory(const char *);
 char *strbuf_realpath(struct strbuf *resolved, const char *path,
 		      int die_on_error);
+char *strbuf_realpath_missing(struct strbuf *resolved, const char *path);
 char *real_pathdup(const char *path, int die_on_error);
 const char *absolute_path(const char *path);
 char *absolute_pathdup(const char *path);