1 files changed, 164 insertions, 129 deletions

diff --git a/abspath.c b/abspath.c
index ca33558a91..b02e068aa3 100644
--- a/abspath.c
+++ b/abspath.c
@@ -11,48 +11,83 @@ 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)
+{
+	size_t offset = offset_1st_component(path->buf);
+	size_t len = path->len;
+
+	/* Find start of the last component */
+	while (offset < len && !is_dir_sep(path->buf[len - 1]))
+		len--;
+	/* Skip sequences of multiple path-separators */
+	while (offset < len && is_dir_sep(path->buf[len - 1]))
+		len--;
+
+	strbuf_setlen(path, len);
+}
+
+/* get (and remove) the next component in 'remaining' and place it in 'next' */
+static void get_next_component(struct strbuf *next, struct strbuf *remaining)
+{
+	char *start = NULL;
+	char *end = NULL;
+
+	strbuf_reset(next);
+
+	/* look for the next component */
+	/* Skip sequences of multiple path-separators */
+	for (start = remaining->buf; is_dir_sep(*start); start++)
+		; /* nothing */
+	/* Find end of the path component */
+	for (end = start; *end && !is_dir_sep(*end); end++)
+		; /* nothing */
+
+	strbuf_add(next, start, end - start);
+	/* remove the component from 'remaining' */
+	strbuf_remove(remaining, 0, end - remaining->buf);
+}
+
+/* copies root part from remaining to resolved, canonicalizing it on the way */
+static void get_root_part(struct strbuf *resolved, struct strbuf *remaining)
+{
+	int offset = offset_1st_component(remaining->buf);
+
+	strbuf_reset(resolved);
+	strbuf_add(resolved, remaining->buf, offset);
+#ifdef GIT_WINDOWS_NATIVE
+	convert_slashes(resolved->buf);
+#endif
+	strbuf_remove(remaining, 0, offset);
+}
+
 /* We allow "recursive" symbolic links. Only within reason, though. */
-#define MAXDEPTH 5
+#ifndef MAXSYMLINKS
+#define MAXSYMLINKS 32
+#endif
 
 /*
  * Return the real path (i.e., absolute path, with symlinks resolved
  * and extra slashes removed) equivalent to the specified path.  (If
  * you want an absolute path but don't mind links, use
- * absolute_path().)  The return value is a pointer to a static
- * buffer.
+ * absolute_path().)  Places the resolved realpath in the provided strbuf.
  *
- * The input and all intermediate paths must be shorter than MAX_PATH.
  * 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.  If die_on_error is set, then die with an
  * informative error message if there is a problem.  Otherwise, return
  * NULL on errors (without generating any output).
- *
- * If path is our buffer, then return path, as it's already what the
- * user wants.
  */
-static const char *real_path_internal(const char *path, int die_on_error)
+char *strbuf_realpath(struct strbuf *resolved, const char *path,
+		      int die_on_error)
 {
-	static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1];
+	struct strbuf remaining = STRBUF_INIT;
+	struct strbuf next = STRBUF_INIT;
+	struct strbuf symlink = STRBUF_INIT;
 	char *retval = NULL;
-
-	/*
-	 * If we have to temporarily chdir(), store the original CWD
-	 * here so that we can chdir() back to it at the end of the
-	 * function:
-	 */
-	char cwd[1024] = "";
-
-	int buf_index = 1;
-
-	int depth = MAXDEPTH;
-	char *last_elem = NULL;
+	int num_symlinks = 0;
 	struct stat st;
 
-	/* We've already done it */
-	if (path == buf || path == next_buf)
-		return path;
-
 	if (!*path) {
 		if (die_on_error)
 			die("The empty string is not a valid path");
@@ -60,152 +95,155 @@ static const char *real_path_internal(const char *path, int die_on_error)
 			goto error_out;
 	}
 
-	if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) {
-		if (die_on_error)
-			die("Too long path: %.*s", 60, path);
-		else
-			goto error_out;
+	strbuf_addstr(&remaining, path);
+	get_root_part(resolved, &remaining);
+
+	if (!resolved->len) {
+		/* relative path; can use CWD as the initial resolved path */
+		if (strbuf_getcwd(resolved)) {
+			if (die_on_error)
+				die_errno("unable to get current working directory");
+			else
+				goto error_out;
+		}
 	}
 
-	while (depth--) {
-		if (!is_directory(buf)) {
-			char *last_slash = find_last_dir_sep(buf);
-			if (last_slash) {
-				last_elem = xstrdup(last_slash + 1);
-				last_slash[1] = '\0';
-			} else {
-				last_elem = xstrdup(buf);
-				*buf = '\0';
-			}
+	/* Iterate over the remaining path components */
+	while (remaining.len > 0) {
+		get_next_component(&next, &remaining);
+
+		if (next.len == 0) {
+			continue; /* empty component */
+		} else if (next.len == 1 && !strcmp(next.buf, ".")) {
+			continue; /* '.' component */
+		} else if (next.len == 2 && !strcmp(next.buf, "..")) {
+			/* '..' component; strip the last path component */
+			strip_last_component(resolved);
+			continue;
 		}
 
-		if (*buf) {
-			if (!*cwd && !getcwd(cwd, sizeof(cwd))) {
-				if (die_on_error)
-					die_errno("Could not get current working directory");
-				else
-					goto error_out;
-			}
+		/* append the next component and resolve resultant path */
+		if (!is_dir_sep(resolved->buf[resolved->len - 1]))
+			strbuf_addch(resolved, '/');
+		strbuf_addbuf(resolved, &next);
 
-			if (chdir(buf)) {
+		if (lstat(resolved->buf, &st)) {
+			/* error out unless this was the last component */
+			if (errno != ENOENT || remaining.len) {
 				if (die_on_error)
-					die_errno("Could not switch to '%s'", buf);
+					die_errno("Invalid path '%s'",
+						  resolved->buf);
 				else
 					goto error_out;
 			}
-		}
-		if (!getcwd(buf, PATH_MAX)) {
-			if (die_on_error)
-				die_errno("Could not get current working directory");
-			else
-				goto error_out;
-		}
+		} else if (S_ISLNK(st.st_mode)) {
+			ssize_t len;
+			strbuf_reset(&symlink);
+
+			if (num_symlinks++ > MAXSYMLINKS) {
+				errno = ELOOP;
 
-		if (last_elem) {
-			size_t len = strlen(buf);
-			if (len + strlen(last_elem) + 2 > PATH_MAX) {
 				if (die_on_error)
-					die("Too long path name: '%s/%s'",
-					    buf, last_elem);
+					die("More than %d nested symlinks "
+					    "on path '%s'", MAXSYMLINKS, path);
 				else
 					goto error_out;
 			}
-			if (len && !is_dir_sep(buf[len - 1]))
-				buf[len++] = '/';
-			strcpy(buf + len, last_elem);
-			free(last_elem);
-			last_elem = NULL;
-		}
 
-		if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) {
-			ssize_t len = readlink(buf, next_buf, PATH_MAX);
+			len = strbuf_readlink(&symlink, resolved->buf,
+					      st.st_size);
 			if (len < 0) {
 				if (die_on_error)
-					die_errno("Invalid symlink '%s'", buf);
+					die_errno("Invalid symlink '%s'",
+						  resolved->buf);
 				else
 					goto error_out;
 			}
-			if (PATH_MAX <= len) {
-				if (die_on_error)
-					die("symbolic link too long: %s", buf);
-				else
-					goto error_out;
+
+			if (is_absolute_path(symlink.buf)) {
+				/* absolute symlink; set resolved to root */
+				get_root_part(resolved, &symlink);
+			} else {
+				/*
+				 * relative symlink
+				 * strip off the last component since it will
+				 * be replaced with the contents of the symlink
+				 */
+				strip_last_component(resolved);
+			}
+
+			/*
+			 * if there are still remaining components to resolve
+			 * then append them to symlink
+			 */
+			if (remaining.len) {
+				strbuf_addch(&symlink, '/');
+				strbuf_addbuf(&symlink, &remaining);
 			}
-			next_buf[len] = '\0';
-			buf = next_buf;
-			buf_index = 1 - buf_index;
-			next_buf = bufs[buf_index];
-		} else
-			break;
+
+			/*
+			 * use the symlink as the remaining components that
+			 * need to be resloved
+			 */
+			strbuf_swap(&symlink, &remaining);
+		}
 	}
 
-	retval = buf;
+	retval = resolved->buf;
+
 error_out:
-	free(last_elem);
-	if (*cwd && chdir(cwd))
-		die_errno("Could not change back to '%s'", cwd);
+	strbuf_release(&remaining);
+	strbuf_release(&next);
+	strbuf_release(&symlink);
+
+	if (!retval)
+		strbuf_reset(resolved);
 
 	return retval;
 }
 
 const char *real_path(const char *path)
 {
-	return real_path_internal(path, 1);
+	static struct strbuf realpath = STRBUF_INIT;
+	return strbuf_realpath(&realpath, path, 1);
 }
 
 const char *real_path_if_valid(const char *path)
 {
-	return real_path_internal(path, 0);
+	static struct strbuf realpath = STRBUF_INIT;
+	return strbuf_realpath(&realpath, path, 0);
 }
 
-static const char *get_pwd_cwd(void)
+char *real_pathdup(const char *path, int die_on_error)
 {
-	static char cwd[PATH_MAX + 1];
-	char *pwd;
-	struct stat cwd_stat, pwd_stat;
-	if (getcwd(cwd, PATH_MAX) == NULL)
-		return NULL;
-	pwd = getenv("PWD");
-	if (pwd && strcmp(pwd, cwd)) {
-		stat(cwd, &cwd_stat);
-		if ((cwd_stat.st_dev || cwd_stat.st_ino) &&
-		    !stat(pwd, &pwd_stat) &&
-		    pwd_stat.st_dev == cwd_stat.st_dev &&
-		    pwd_stat.st_ino == cwd_stat.st_ino) {
-			strlcpy(cwd, pwd, PATH_MAX);
-		}
-	}
-	return cwd;
+	struct strbuf realpath = STRBUF_INIT;
+	char *retval = NULL;
+
+	if (strbuf_realpath(&realpath, path, die_on_error))
+		retval = strbuf_detach(&realpath, NULL);
+
+	strbuf_release(&realpath);
+
+	return retval;
 }
 
 /*
  * Use this to get an absolute path from a relative one. If you want
  * to resolve links, you should use real_path.
- *
- * If the path is already absolute, then return path. As the user is
- * never meant to free the return value, we're safe.
  */
 const char *absolute_path(const char *path)
 {
-	static char buf[PATH_MAX + 1];
+	static struct strbuf sb = STRBUF_INIT;
+	strbuf_reset(&sb);
+	strbuf_add_absolute_path(&sb, path);
+	return sb.buf;
+}
 
-	if (!*path) {
-		die("The empty string is not a valid path");
-	} else if (is_absolute_path(path)) {
-		if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	} else {
-		size_t len;
-		const char *fmt;
-		const char *cwd = get_pwd_cwd();
-		if (!cwd)
-			die_errno("Cannot determine the current working directory");
-		len = strlen(cwd);
-		fmt = (len > 0 && is_dir_sep(cwd[len - 1])) ? "%s%s" : "%s/%s";
-		if (snprintf(buf, PATH_MAX, fmt, cwd, path) >= PATH_MAX)
-			die("Too long path: %.*s", 60, path);
-	}
-	return buf;
+char *absolute_pathdup(const char *path)
+{
+	struct strbuf sb = STRBUF_INIT;
+	strbuf_add_absolute_path(&sb, path);
+	return strbuf_detach(&sb, NULL);
 }
 
 /*
@@ -223,7 +261,6 @@ const char *prefix_filename(const char *pfx, int pfx_len, const char *arg)
 	strbuf_add(&path, pfx, pfx_len);
 	strbuf_addstr(&path, arg);
 #else
-	char *p;
 	/* don't add prefix to absolute paths, but still replace '\' by '/' */
 	strbuf_reset(&path);
 	if (is_absolute_path(arg))
@@ -231,9 +268,7 @@ const char *prefix_filename(const char *pfx, int pfx_len, const char *arg)
 	else if (pfx_len)
 		strbuf_add(&path, pfx, pfx_len);
 	strbuf_addstr(&path, arg);
-	for (p = path.buf + pfx_len; *p; p++)
-		if (*p == '\\')
-			*p = '/';
+	convert_slashes(path.buf + pfx_len);
 #endif
 	return path.buf;
 }