* Re: [PATCH] strbuf: add strbuf_add_real_path()
2017-02-25 16:00 [PATCH] strbuf: add strbuf_add_real_path() René Scharfe
@ 2017-02-25 20:11 ` Jeff King
2017-02-27 18:22 ` Brandon Williams
1 sibling, 0 replies; 5+ messages in thread
From: Jeff King @ 2017-02-25 20:11 UTC (permalink / raw)
To: René Scharfe; +Cc: Git List, Junio C Hamano, Brandon Williams
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;
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] strbuf: add strbuf_add_real_path()
2017-02-25 16:00 [PATCH] strbuf: add strbuf_add_real_path() René Scharfe
2017-02-25 20:11 ` Jeff King
@ 2017-02-27 18:22 ` Brandon Williams
2017-02-27 22:45 ` René Scharfe
1 sibling, 1 reply; 5+ messages in thread
From: Brandon Williams @ 2017-02-27 18:22 UTC (permalink / raw)
To: René Scharfe; +Cc: Git List, Junio C Hamano
On 02/25, 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.
>
Seems like a reasonable thing to do. When I wrote strbuf_realpath() I
think I looked at the strbuf_getcwd() function for what it did (since it
handled paths) and it simply uses the provided buffer disregarding what
is already stored in it.
> Signed-off-by: Rene Scharfe <l.s.r@web.de>
> ---
> contrib/coccinelle/strbuf.cocci | 6 ++++++
> setup.c | 2 +-
> strbuf.c | 11 +++++++++++
> strbuf.h | 14 ++++++++++++++
> 4 files changed, 32 insertions(+), 1 deletion(-)
>
> diff --git a/contrib/coccinelle/strbuf.cocci b/contrib/coccinelle/strbuf.cocci
> index 63995f22ff..1d580e49b0 100644
> --- a/contrib/coccinelle/strbuf.cocci
> +++ b/contrib/coccinelle/strbuf.cocci
> @@ -38,3 +38,9 @@ expression E1, E2, E3;
> @@
> - strbuf_addstr(E1, find_unique_abbrev(E2, E3));
> + strbuf_add_unique_abbrev(E1, E2, E3);
> +
> +@@
> +expression E1, E2;
> +@@
> +- strbuf_addstr(E1, real_path(E2));
> ++ strbuf_add_real_path(E1, E2);
> diff --git a/setup.c b/setup.c
> index 967f289f1e..f14cbcd338 100644
> --- a/setup.c
> +++ b/setup.c
> @@ -254,7 +254,7 @@ int get_common_dir_noenv(struct strbuf *sb, const char *gitdir)
> if (!is_absolute_path(data.buf))
> strbuf_addf(&path, "%s/", gitdir);
> strbuf_addbuf(&path, &data);
> - strbuf_addstr(sb, real_path(path.buf));
> + strbuf_add_real_path(sb, path.buf);
> ret = 1;
> } else {
> strbuf_addstr(sb, gitdir);
> diff --git a/strbuf.c b/strbuf.cq
> index 8fec6579f7..ace58e7367 100644
> --- a/strbuf.c
> +++ b/strbuf.c
> @@ -707,6 +707,17 @@ void strbuf_add_absolute_path(struct strbuf *sb, const char *path)
> strbuf_addstr(sb, path);
> }
>
> +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);
I know its not required but I would have braces on the 'else' branch
since they were needed on the 'if' branch. But that's up to you and
your style :)
> +}
> +
> int printf_ln(const char *fmt, ...)
> {
> int ret;
> diff --git a/strbuf.h b/strbuf.h
> index cf1b5409e7..cf8e4bf532 100644
> --- a/strbuf.h
> +++ b/strbuf.h
> @@ -441,6 +441,20 @@ extern int strbuf_getcwd(struct strbuf *sb);
> */
> extern void strbuf_add_absolute_path(struct strbuf *sb, const char *path);
>
> +/**
> + * Canonize `path` (make it absolute, resolve symlinks, remove extra
> + * slashes) and append it to `sb`. Die with an informative error
> + * message if there is a problem.
> + *
> + * The directory part of `path` (i.e., everything up to the last
> + * dir_sep) must denote a valid, existing directory, but the last
> + * component need not exist.
> + *
> + * Callers that don't mind links should use the more lightweight
> + * strbuf_add_absolute_path() instead.
> + */
> +extern void strbuf_add_real_path(struct strbuf *sb, const char *path);
> +
>
> /**
> * Normalize in-place the path contained in the strbuf. See
> --
> 2.12.0
>
--
Brandon Williams
^ permalink raw reply [flat|nested] 5+ messages in thread