From: Jeff King <peff@peff.net>
To: "René Scharfe" <l.s.r@web.de>
Cc: Git List <git@vger.kernel.org>,
Junio C Hamano <gitster@pobox.com>,
Brandon Williams <bmwill@google.com>
Subject: Re: [PATCH] strbuf: add strbuf_add_real_path()
Date: Sat, 25 Feb 2017 15:11:23 -0500 [thread overview]
Message-ID: <20170225201123.ozrrfgim2rdctczv@sigill.intra.peff.net> (raw)
In-Reply-To: <4d191b86-d36c-e3ec-99c6-d15baa6b659a@web.de>
On Sat, Feb 25, 2017 at 05:00:33PM +0100, René Scharfe wrote:
> Add a function for appending the canonized absolute pathname of a given
> path to a strbuf. It keeps the existing contents intact, as expected of
> a function of the strbuf_add() family, while avoiding copying the result
> if the given strbuf is empty. It's more consistent with the rest of the
> strbuf API than strbuf_realpath(), which it's wrapping.
>
> Also add a semantic patch demonstrating its intended usage and apply it
> to the current tree. Using strbuf_add_real_path() instead of calling
> strbuf_addstr() and real_path() avoids an extra copy to a static buffer.
It's also re-entrant, which real_path() is not.
> +void strbuf_add_real_path(struct strbuf *sb, const char *path)
> +{
> + if (sb->len) {
> + struct strbuf resolved = STRBUF_INIT;
> + strbuf_realpath(&resolved, path, 1);
> + strbuf_addbuf(sb, &resolved);
> + strbuf_release(&resolved);
> + } else
> + strbuf_realpath(sb, path, 1);
> +}
The wrapping here seems a little backwards. If strbuf_add_real_path()
were the inner one, then we would not need this extra allocation. I know
that the reasons are historical, but I don't think it would be
impossible to teach the realpath code to do it.
OTOH, it may not be worth the effort. It's not like strbuf_realpath()
doesn't allocate secondary strbufs for its work already, so dropping one
more is probably not that exciting. And certainly think your patch is an
incremental improvement.
Out of curiosity, I took a stab at the patch, which is below. Only
lightly tested by me, and it does make the logic a bit more complicated
to read, as you have to adjust for the original "base" in several
places.
diff --git a/abspath.c b/abspath.c
index 2f0c26e0e..286072f48 100644
--- a/abspath.c
+++ b/abspath.c
@@ -12,9 +12,9 @@ int is_directory(const char *path)
}
/* removes the last path component from 'path' except if 'path' is root */
-static void strip_last_component(struct strbuf *path)
+static void strip_last_component(struct strbuf *path, size_t base)
{
- size_t offset = offset_1st_component(path->buf);
+ size_t offset = base + offset_1st_component(path->buf + base);
size_t len = path->len;
/* Find start of the last component */
@@ -49,14 +49,15 @@ static void get_next_component(struct strbuf *next, struct strbuf *remaining)
}
/* copies root part from remaining to resolved, canonicalizing it on the way */
-static void get_root_part(struct strbuf *resolved, struct strbuf *remaining)
+static void get_root_part(struct strbuf *resolved, struct strbuf *remaining,
+ size_t base)
{
int offset = offset_1st_component(remaining->buf);
- strbuf_reset(resolved);
+ strbuf_setlen(resolved, base);
strbuf_add(resolved, remaining->buf, offset);
#ifdef GIT_WINDOWS_NATIVE
- convert_slashes(resolved->buf);
+ convert_slashes(resolved->buf + base);
#endif
strbuf_remove(remaining, 0, offset);
}
@@ -78,8 +79,8 @@ static void get_root_part(struct strbuf *resolved, struct strbuf *remaining)
* informative error message if there is a problem. Otherwise, return
* NULL on errors (without generating any output).
*/
-char *strbuf_realpath(struct strbuf *resolved, const char *path,
- int die_on_error)
+char *strbuf_add_real_path(struct strbuf *resolved, const char *path,
+ int die_on_error)
{
struct strbuf remaining = STRBUF_INIT;
struct strbuf next = STRBUF_INIT;
@@ -87,6 +88,7 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
char *retval = NULL;
int num_symlinks = 0;
struct stat st;
+ size_t base = resolved->len;
if (!*path) {
if (die_on_error)
@@ -96,9 +98,9 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
}
strbuf_addstr(&remaining, path);
- get_root_part(resolved, &remaining);
+ get_root_part(resolved, &remaining, base);
- if (!resolved->len) {
+ if (resolved->len == base) {
/* relative path; can use CWD as the initial resolved path */
if (strbuf_getcwd(resolved)) {
if (die_on_error)
@@ -118,7 +120,7 @@ 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, base);
continue;
}
@@ -127,12 +129,12 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
strbuf_addch(resolved, '/');
strbuf_addbuf(resolved, &next);
- if (lstat(resolved->buf, &st)) {
+ if (lstat(resolved->buf + base, &st)) {
/* error out unless this was the last component */
if (errno != ENOENT || remaining.len) {
if (die_on_error)
die_errno("Invalid path '%s'",
- resolved->buf);
+ resolved->buf + base);
else
goto error_out;
}
@@ -150,7 +152,7 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
goto error_out;
}
- len = strbuf_readlink(&symlink, resolved->buf,
+ len = strbuf_readlink(&symlink, resolved->buf + base,
st.st_size);
if (len < 0) {
if (die_on_error)
@@ -162,14 +164,14 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
if (is_absolute_path(symlink.buf)) {
/* absolute symlink; set resolved to root */
- get_root_part(resolved, &symlink);
+ get_root_part(resolved, &symlink, base);
} else {
/*
* relative symlink
* strip off the last component since it will
* be replaced with the contents of the symlink
*/
- strip_last_component(resolved);
+ strip_last_component(resolved, base);
}
/*
@@ -202,6 +204,12 @@ char *strbuf_realpath(struct strbuf *resolved, const char *path,
return retval;
}
+char *strbuf_realpath(struct strbuf *sb, const char *path, int die_on_error)
+{
+ strbuf_reset(sb);
+ return strbuf_add_real_path(sb, path, die_on_error);
+}
+
const char *real_path(const char *path)
{
static struct strbuf realpath = STRBUF_INIT;
next prev parent reply other threads:[~2017-02-25 20:13 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-25 16:00 [PATCH] strbuf: add strbuf_add_real_path() René Scharfe
2017-02-25 20:11 ` Jeff King [this message]
2017-02-27 18:22 ` Brandon Williams
2017-02-27 22:45 ` René Scharfe
2017-02-28 20:42 ` Brandon Williams
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
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170225201123.ozrrfgim2rdctczv@sigill.intra.peff.net \
--to=peff@peff.net \
--cc=bmwill@google.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=l.s.r@web.de \
/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.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
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 read-only IMAP folder(s) and NNTP newsgroup(s).