From: Atharva Raykar <raykar.ath@gmail.com>
To: raykar.ath@gmail.com
Cc: avarab@gmail.com, christian.couder@gmail.com,
congdanhqx@gmail.com, emilyshaffer@google.com,
git@vger.kernel.org, gitster@pobox.com, jrnieder@gmail.com,
kaartic.sivaraam@gmail.com, pc44800@gmail.com,
periperidip@gmail.com, rafaeloliveira.cs@gmail.com,
sunshine@sunshineco.com
Subject: [GSoC] [PATCH v4 4/8] dir: libify and export helper functions from clone.c
Date: Sat, 7 Aug 2021 12:46:09 +0530 [thread overview]
Message-ID: <20210807071613.99610-5-raykar.ath@gmail.com> (raw)
In-Reply-To: <20210807071613.99610-1-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 | 10 ++++
3 files changed, 126 insertions(+), 116 deletions(-)
diff --git a/builtin/clone.c b/builtin/clone.c
index 66fe66679c..5ba24b7ae7 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 = git_url_basename(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..6d26db3189 100644
--- a/dir.c
+++ b/dir.c
@@ -2970,6 +2970,120 @@ int is_empty_dir(const char *path)
return ret;
}
+char *git_url_basename(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..a4a6fd7371 100644
--- a/dir.h
+++ b/dir.h
@@ -453,6 +453,16 @@ static inline int is_dot_or_dotdot(const char *name)
int is_empty_dir(const char *dir);
+/*
+ * Retrieve the "humanish" basename of the given Git URL.
+ *
+ * For example:
+ * /path/to/repo.git => "repo"
+ * host.xz.foo/.git => "foo"
+ */
+char *git_url_basename(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
next prev parent reply other threads:[~2021-08-07 7:17 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-05 7:19 [GSoC] [PATCH 0/8] submodule: convert the rest of 'add' to C Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 1/8] submodule--helper: refactor resolve_relative_url() helper Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 2/8] submodule--helper: remove repeated code in sync_submodule() Atharva Raykar
2021-08-06 0:53 ` Đoàn Trần Công Danh
2021-08-06 9:06 ` Christian Couder
2021-08-06 10:06 ` Atharva Raykar
2021-08-06 16:21 ` Junio C Hamano
2021-08-05 7:19 ` [GSoC] [PATCH 3/8] dir: libify and export helper functions from clone.c Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 4/8] submodule--helper: remove constness of sm_path Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 5/8] submodule--helper: convert the bulk of cmd_add() to C Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 6/8] submodule--helper: remove add-clone subcommand Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 7/8] submodule--helper: remove add-config subcommand Atharva Raykar
2021-08-05 7:19 ` [GSoC] [PATCH 8/8] submodule--helper: remove resolve-relative-url subcommand Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 0/9] submodule: convert the rest of 'add' to C Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 1/9] submodule--helper: add options for compute_submodule_clone_url() Atharva Raykar
2021-08-05 20:05 ` Junio C Hamano
2021-08-05 7:40 ` [GSoC] [PATCH v2 2/9] submodule--helper: refactor resolve_relative_url() helper Atharva Raykar
2021-08-05 20:13 ` Junio C Hamano
2021-08-05 7:40 ` [GSoC] [PATCH v2 3/9] submodule--helper: remove repeated code in sync_submodule() Atharva Raykar
2021-08-05 20:20 ` Junio C Hamano
2021-08-05 7:40 ` [GSoC] [PATCH v2 4/9] dir: libify and export helper functions from clone.c Atharva Raykar
2021-08-05 20:37 ` Junio C Hamano
2021-08-06 11:12 ` Atharva Raykar
2021-08-06 16:36 ` Junio C Hamano
2021-08-07 7:15 ` Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 5/9] submodule--helper: remove constness of sm_path Atharva Raykar
2021-08-05 20:40 ` Junio C Hamano
2021-08-06 11:16 ` Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 6/9] submodule--helper: convert the bulk of cmd_add() to C Atharva Raykar
2021-08-06 1:14 ` Đoàn Trần Công Danh
2021-08-06 11:33 ` Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 7/9] submodule--helper: remove add-clone subcommand Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 8/9] submodule--helper: remove add-config subcommand Atharva Raykar
2021-08-05 7:40 ` [GSoC] [PATCH v2 9/9] submodule--helper: remove resolve-relative-url subcommand Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 0/8] submodule: convert the rest of 'add' to C Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 1/8] submodule--helper: add options for compute_submodule_clone_url() Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 2/8] submodule--helper: refactor resolve_relative_url() helper Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 3/8] submodule--helper: remove repeated code in sync_submodule() Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 4/8] dir: libify and export helper functions from clone.c Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 5/8] submodule--helper: convert the bulk of cmd_add() to C Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 6/8] submodule--helper: remove add-clone subcommand Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 7/8] submodule--helper: remove add-config subcommand Atharva Raykar
2021-08-06 12:01 ` [GSoC] [PATCH v3 8/8] submodule--helper: remove resolve-relative-url subcommand Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 0/8] submodule: convert the rest of 'add' to C Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 1/8] submodule--helper: add options for compute_submodule_clone_url() Atharva Raykar
2021-08-08 17:41 ` Kaartic Sivaraam
2021-08-08 18:26 ` Kaartic Sivaraam
2021-08-09 7:29 ` Atharva Raykar
2021-08-09 8:47 ` Atharva Raykar
2021-08-10 17:36 ` Kaartic Sivaraam
2021-08-07 7:16 ` [GSoC] [PATCH v4 2/8] submodule--helper: refactor resolve_relative_url() helper Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 3/8] submodule--helper: remove repeated code in sync_submodule() Atharva Raykar
2021-08-08 19:00 ` Kaartic Sivaraam
2021-08-09 7:36 ` Atharva Raykar
2021-08-07 7:16 ` Atharva Raykar [this message]
2021-08-08 19:23 ` [GSoC] [PATCH v4 4/8] dir: libify and export helper functions from clone.c Kaartic Sivaraam
2021-08-09 8:02 ` Atharva Raykar
2021-08-10 17:53 ` Kaartic Sivaraam
2021-08-10 21:27 ` Junio C Hamano
2021-08-11 10:25 ` Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 5/8] submodule--helper: convert the bulk of cmd_add() to C Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 6/8] submodule--helper: remove add-clone subcommand Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 7/8] submodule--helper: remove add-config subcommand Atharva Raykar
2021-08-07 7:16 ` [GSoC] [PATCH v4 8/8] submodule--helper: remove resolve-relative-url subcommand Atharva Raykar
2021-08-08 18:01 ` [GSoC] [PATCH v4 0/8] submodule: convert the rest of 'add' to C Kaartic Sivaraam
2021-08-10 11:46 ` [GSoC] [PATCH v5 0/9] " Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 1/9] submodule--helper: add options for compute_submodule_clone_url() Atharva Raykar
2021-08-11 6:44 ` Bagas Sanjaya
2021-08-11 10:30 ` Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 2/9] submodule--helper: refactor resolve_relative_url() helper Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 3/9] submodule--helper: remove repeated code in sync_submodule() Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 4/9] dir: libify and export helper functions from clone.c Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 5/9] submodule--helper: convert the bulk of cmd_add() to C Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 6/9] submodule--helper: remove add-clone subcommand Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 7/9] submodule--helper: remove add-config subcommand Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 8/9] submodule--helper: remove resolve-relative-url subcommand Atharva Raykar
2021-08-10 11:46 ` [GSoC] [PATCH v5 9/9] submodule--helper: rename compute_submodule_clone_url() Atharva Raykar
2021-09-08 0:31 ` [GSoC] [PATCH v5 0/9] submodule: convert the rest of 'add' to C Junio C Hamano
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210807071613.99610-5-raykar.ath@gmail.com \
--to=raykar.ath@gmail.com \
--cc=avarab@gmail.com \
--cc=christian.couder@gmail.com \
--cc=congdanhqx@gmail.com \
--cc=emilyshaffer@google.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=jrnieder@gmail.com \
--cc=kaartic.sivaraam@gmail.com \
--cc=pc44800@gmail.com \
--cc=periperidip@gmail.com \
--cc=rafaeloliveira.cs@gmail.com \
--cc=sunshine@sunshineco.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).