[GSoC] [PATCH v3 4/8] dir: libify and export helper functions from clone.c

[Atharva Raykar <raykar.ath@gmail.com>]

These functions can be useful to other parts of Git. Let's move them to
dir.c, while renaming them to be make their functionality more explicit.

Signed-off-by: Atharva Raykar <raykar.ath@gmail.com>
Mentored-by: Christian Couder <christian.couder@gmail.com>
Mentored-by: Shourya Shukla <periperidip@gmail.com>
---
 builtin/clone.c | 118 +-----------------------------------------------
 dir.c           | 114 ++++++++++++++++++++++++++++++++++++++++++++++
 dir.h           |  11 +++++
 3 files changed, 127 insertions(+), 116 deletions(-)

diff --git a/builtin/clone.c b/builtin/clone.c
index 66fe66679c..fab0a3cef6 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -217,120 +217,6 @@ static char *get_repo_path(const char *repo, int *is_bundle)
 	return canon;
 }
 
-static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
-{
-	const char *end = repo + strlen(repo), *start, *ptr;
-	size_t len;
-	char *dir;
-
-	/*
-	 * Skip scheme.
-	 */
-	start = strstr(repo, "://");
-	if (start == NULL)
-		start = repo;
-	else
-		start += 3;
-
-	/*
-	 * Skip authentication data. The stripping does happen
-	 * greedily, such that we strip up to the last '@' inside
-	 * the host part.
-	 */
-	for (ptr = start; ptr < end && !is_dir_sep(*ptr); ptr++) {
-		if (*ptr == '@')
-			start = ptr + 1;
-	}
-
-	/*
-	 * Strip trailing spaces, slashes and /.git
-	 */
-	while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
-		end--;
-	if (end - start > 5 && is_dir_sep(end[-5]) &&
-	    !strncmp(end - 4, ".git", 4)) {
-		end -= 5;
-		while (start < end && is_dir_sep(end[-1]))
-			end--;
-	}
-
-	/*
-	 * Strip trailing port number if we've got only a
-	 * hostname (that is, there is no dir separator but a
-	 * colon). This check is required such that we do not
-	 * strip URI's like '/foo/bar:2222.git', which should
-	 * result in a dir '2222' being guessed due to backwards
-	 * compatibility.
-	 */
-	if (memchr(start, '/', end - start) == NULL
-	    && memchr(start, ':', end - start) != NULL) {
-		ptr = end;
-		while (start < ptr && isdigit(ptr[-1]) && ptr[-1] != ':')
-			ptr--;
-		if (start < ptr && ptr[-1] == ':')
-			end = ptr - 1;
-	}
-
-	/*
-	 * Find last component. To remain backwards compatible we
-	 * also regard colons as path separators, such that
-	 * cloning a repository 'foo:bar.git' would result in a
-	 * directory 'bar' being guessed.
-	 */
-	ptr = end;
-	while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
-		ptr--;
-	start = ptr;
-
-	/*
-	 * Strip .{bundle,git}.
-	 */
-	len = end - start;
-	strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");
-
-	if (!len || (len == 1 && *start == '/'))
-		die(_("No directory name could be guessed.\n"
-		      "Please specify a directory on the command line"));
-
-	if (is_bare)
-		dir = xstrfmt("%.*s.git", (int)len, start);
-	else
-		dir = xstrndup(start, len);
-	/*
-	 * Replace sequences of 'control' characters and whitespace
-	 * with one ascii space, remove leading and trailing spaces.
-	 */
-	if (*dir) {
-		char *out = dir;
-		int prev_space = 1 /* strip leading whitespace */;
-		for (end = dir; *end; ++end) {
-			char ch = *end;
-			if ((unsigned char)ch < '\x20')
-				ch = '\x20';
-			if (isspace(ch)) {
-				if (prev_space)
-					continue;
-				prev_space = 1;
-			} else
-				prev_space = 0;
-			*out++ = ch;
-		}
-		*out = '\0';
-		if (out > dir && prev_space)
-			out[-1] = '\0';
-	}
-	return dir;
-}
-
-static void strip_trailing_slashes(char *dir)
-{
-	char *end = dir + strlen(dir);
-
-	while (dir < end - 1 && is_dir_sep(end[-1]))
-		end--;
-	*end = '\0';
-}
-
 static int add_one_reference(struct string_list_item *item, void *cb_data)
 {
 	struct strbuf err = STRBUF_INIT;
@@ -1041,8 +927,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (argc == 2)
 		dir = xstrdup(argv[1]);
 	else
-		dir = guess_dir_name(repo_name, is_bundle, option_bare);
-	strip_trailing_slashes(dir);
+		dir = guess_target_dir_from_git_url(repo_name, is_bundle, option_bare);
+	strip_dir_trailing_slashes(dir);
 
 	dest_exists = path_exists(dir);
 	if (dest_exists && !is_empty_dir(dir))
diff --git a/dir.c b/dir.c
index 03c4d21267..9a9ab135c4 100644
--- a/dir.c
+++ b/dir.c
@@ -2970,6 +2970,120 @@ int is_empty_dir(const char *path)
 	return ret;
 }
 
+char *guess_target_dir_from_git_url(const char *repo, int is_bundle, int is_bare)
+{
+	const char *end = repo + strlen(repo), *start, *ptr;
+	size_t len;
+	char *dir;
+
+	/*
+	 * Skip scheme.
+	 */
+	start = strstr(repo, "://");
+	if (start == NULL)
+		start = repo;
+	else
+		start += 3;
+
+	/*
+	 * Skip authentication data. The stripping does happen
+	 * greedily, such that we strip up to the last '@' inside
+	 * the host part.
+	 */
+	for (ptr = start; ptr < end && !is_dir_sep(*ptr); ptr++) {
+		if (*ptr == '@')
+			start = ptr + 1;
+	}
+
+	/*
+	 * Strip trailing spaces, slashes and /.git
+	 */
+	while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
+		end--;
+	if (end - start > 5 && is_dir_sep(end[-5]) &&
+	    !strncmp(end - 4, ".git", 4)) {
+		end -= 5;
+		while (start < end && is_dir_sep(end[-1]))
+			end--;
+	}
+
+	/*
+	 * Strip trailing port number if we've got only a
+	 * hostname (that is, there is no dir separator but a
+	 * colon). This check is required such that we do not
+	 * strip URI's like '/foo/bar:2222.git', which should
+	 * result in a dir '2222' being guessed due to backwards
+	 * compatibility.
+	 */
+	if (memchr(start, '/', end - start) == NULL
+	    && memchr(start, ':', end - start) != NULL) {
+		ptr = end;
+		while (start < ptr && isdigit(ptr[-1]) && ptr[-1] != ':')
+			ptr--;
+		if (start < ptr && ptr[-1] == ':')
+			end = ptr - 1;
+	}
+
+	/*
+	 * Find last component. To remain backwards compatible we
+	 * also regard colons as path separators, such that
+	 * cloning a repository 'foo:bar.git' would result in a
+	 * directory 'bar' being guessed.
+	 */
+	ptr = end;
+	while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
+		ptr--;
+	start = ptr;
+
+	/*
+	 * Strip .{bundle,git}.
+	 */
+	len = end - start;
+	strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");
+
+	if (!len || (len == 1 && *start == '/'))
+		die(_("No directory name could be guessed.\n"
+		      "Please specify a directory on the command line"));
+
+	if (is_bare)
+		dir = xstrfmt("%.*s.git", (int)len, start);
+	else
+		dir = xstrndup(start, len);
+	/*
+	 * Replace sequences of 'control' characters and whitespace
+	 * with one ascii space, remove leading and trailing spaces.
+	 */
+	if (*dir) {
+		char *out = dir;
+		int prev_space = 1 /* strip leading whitespace */;
+		for (end = dir; *end; ++end) {
+			char ch = *end;
+			if ((unsigned char)ch < '\x20')
+				ch = '\x20';
+			if (isspace(ch)) {
+				if (prev_space)
+					continue;
+				prev_space = 1;
+			} else
+				prev_space = 0;
+			*out++ = ch;
+		}
+		*out = '\0';
+		if (out > dir && prev_space)
+			out[-1] = '\0';
+	}
+	return dir;
+}
+
+void strip_dir_trailing_slashes(char *dir)
+{
+	char *end = dir + strlen(dir);
+
+	while (dir < end - 1 && is_dir_sep(end[-1]))
+		end--;
+	*end = '\0';
+}
+
 static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 {
 	DIR *dir;
diff --git a/dir.h b/dir.h
index b3e1a54a97..6f0abdfe04 100644
--- a/dir.h
+++ b/dir.h
@@ -453,6 +453,17 @@ static inline int is_dot_or_dotdot(const char *name)
 
 int is_empty_dir(const char *dir);
 
+/*
+ * Retrieve a target directory name by reading "humanish" part of the
+ * given Git URL.
+ *
+ * For example:
+ * 	/path/to/repo.git => "repo"
+ * 	host.xz.foo/.git => "foo"
+ */
+char *guess_target_dir_from_git_url(const char *repo, int is_bundle, int is_bare);
+void strip_dir_trailing_slashes(char *dir);
+
 void setup_standard_excludes(struct dir_struct *dir);
 
 char *get_sparse_checkout_filename(void);
-- 
2.32.0