From 7baf714b397ae64e3be04c9c1fb9926f025cf66b Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Fri, 25 May 2012 18:01:11 +2000 Subject: [PATCH] [PATCH v4 2/4] new: Centralize file type stat-ing logic --- c8/f84fff91117e2876eec814dd8fd53aa6bf6cf5 | 253 ++++++++++++++++++++++ 1 file changed, 253 insertions(+) create mode 100644 c8/f84fff91117e2876eec814dd8fd53aa6bf6cf5 diff --git a/c8/f84fff91117e2876eec814dd8fd53aa6bf6cf5 b/c8/f84fff91117e2876eec814dd8fd53aa6bf6cf5 new file mode 100644 index 000000000..c0d45845d --- /dev/null +++ b/c8/f84fff91117e2876eec814dd8fd53aa6bf6cf5 @@ -0,0 +1,253 @@ +Return-Path: +X-Original-To: notmuch@notmuchmail.org +Delivered-To: notmuch@notmuchmail.org +Received: from localhost (localhost [127.0.0.1]) + by olra.theworths.org (Postfix) with ESMTP id CB113431FCF + for ; Thu, 24 May 2012 15:01:24 -0700 (PDT) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: -0.7 +X-Spam-Level: +X-Spam-Status: No, score=-0.7 tagged_above=-999 required=5 + tests=[RCVD_IN_DNSWL_LOW=-0.7] autolearn=disabled +Received: from olra.theworths.org ([127.0.0.1]) + by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) + with ESMTP id K4UuqnPAvr5r for ; + Thu, 24 May 2012 15:01:23 -0700 (PDT) +Received: from dmz-mailsec-scanner-1.mit.edu (DMZ-MAILSEC-SCANNER-1.MIT.EDU + [18.9.25.12]) + by olra.theworths.org (Postfix) with ESMTP id 0B502431FC3 + for ; Thu, 24 May 2012 15:01:22 -0700 (PDT) +X-AuditID: 1209190c-b7fad6d000000920-98-4fbeafb20d2f +Received: from mailhub-auth-3.mit.edu ( [18.9.21.43]) + by dmz-mailsec-scanner-1.mit.edu (Symantec Messaging Gateway) with SMTP + id 04.7B.02336.2BFAEBF4; Thu, 24 May 2012 18:01:22 -0400 (EDT) +Received: from outgoing.mit.edu (OUTGOING-AUTH.MIT.EDU [18.7.22.103]) + by mailhub-auth-3.mit.edu (8.13.8/8.9.2) with ESMTP id q4OM1Mcp018141; + Thu, 24 May 2012 18:01:22 -0400 +Received: from drake.mit.edu (26-4-163.dynamic.csail.mit.edu [18.26.4.163]) + (authenticated bits=0) + (User authenticated as amdragon@ATHENA.MIT.EDU) + by outgoing.mit.edu (8.13.6/8.12.4) with ESMTP id q4OM1LtJ009159 + (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NOT); + Thu, 24 May 2012 18:01:22 -0400 (EDT) +Received: from amthrax by drake.mit.edu with local (Exim 4.77) + (envelope-from ) + id 1SXg5v-00064W-MR; Thu, 24 May 2012 18:01:19 -0400 +From: Austin Clements +To: notmuch@notmuchmail.org +Subject: [PATCH v4 2/4] new: Centralize file type stat-ing logic +Date: Thu, 24 May 2012 18:01:11 -0400 +Message-Id: <1337896873-23253-3-git-send-email-amdragon@mit.edu> +X-Mailer: git-send-email 1.7.10 +In-Reply-To: <1337896873-23253-1-git-send-email-amdragon@mit.edu> +References: <1337887922-13163-1-git-send-email-amdragon@mit.edu> + <1337896873-23253-1-git-send-email-amdragon@mit.edu> +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFtrIIsWRmVeSWpSXmKPExsUixCmqrbtp/T5/g38HVCyu35zJ7MDo8WzV + LeYAxigum5TUnMyy1CJ9uwSujLebv7IXXDKqaHi6gr2BcaF6FyMnh4SAicTUv9+ZIGwxiQv3 + 1rN1MXJxCAnsY5Q433yWGcLZwCixcmcXE4RznEli5u9/bCAtQgKzGCWuP5MCsdkENCS27V/O + CGKLCEhL7Lw7m7WLkYODWUBN4k+XCkhYWMBB4vPD/6wgNouAqsSP3h8sICW8QPGpq7MhjpCX + eHq/D2w6p4CjxOOzvxghNpVLXL4xl2UCI/8CRoZVjLIpuVW6uYmZOcWpybrFyYl5ealFuoZ6 + uZkleqkppZsYwSEjybOD8c1BpUOMAhyMSjy8zNH7/IVYE8uKK3MPMUpyMCmJ8v5YDRTiS8pP + qcxILM6ILyrNSS0+xCjBwawkwisYCZTjTUmsrEotyodJSXOwKInzrtTc7S8kkJ5YkpqdmlqQ + WgSTleHgUJLgPbgOqFGwKDU9tSItM6cEIc3EwQkynAdo+GeQGt7igsTc4sx0iPwpRkUpcd4n + IAkBkERGaR5cLyymXzGKA70izPsdpIoHmA7gul8BDWYCGrzl8V6QwSWJCCmpBkaHD+pKwWsE + LY4/LTe7OatjUvK03kUiT1s6bQ7MWWT6YsXOGrO2I9XTl6ue91XeUzt962KjYEelx6aXvO+c + 2bFzi09qklNqXVhTJq/l1PbHyi+65t99waM7VdAr86NL4NQbd697TmXrag5Yb57JL9x1uWbB + ZzajXoWe0+wT+lkS7P07pvDv363EUpyRaKjFXFScCAAuaQe2xAIAAA== +X-BeenThere: notmuch@notmuchmail.org +X-Mailman-Version: 2.1.13 +Precedence: list +List-Id: "Use and development of the notmuch mail system." + +List-Unsubscribe: , + +List-Archive: +List-Post: +List-Help: +List-Subscribe: , + +X-List-Received-Date: Thu, 24 May 2012 22:01:25 -0000 + +This moves our logic to get a file's type into one function. This has +several benefits: we can support OSes and file systems that do not +provide dirent.d_type or always return DT_UNKNOWN, complex +symlink-handling logic has been replaced by a simple stat fall-through +in one place, and the error message for un-stat-able file is more +accurate (previously, the error always mentioned directories, even +though a broken symlink is not a directory). +--- + notmuch-new.c | 103 +++++++++++++++++++++++++++++++++++---------------------- + test/new | 2 +- + 2 files changed, 64 insertions(+), 41 deletions(-) + +diff --git a/notmuch-new.c b/notmuch-new.c +index 72dd558..c64f1a7 100644 +--- a/notmuch-new.c ++++ b/notmuch-new.c +@@ -154,6 +154,48 @@ dirent_sort_strcmp_name (const struct dirent **a, const struct dirent **b) + return strcmp ((*a)->d_name, (*b)->d_name); + } + ++/* Return the type of a directory entry relative to path as a stat(2) ++ * mode. Like stat, this follows symlinks. Returns -1 and sets errno ++ * if the file's type cannot be determined (which includes dangling ++ * symlinks). ++ */ ++static int ++dirent_type (const char *path, const struct dirent *entry) ++{ ++ struct stat statbuf; ++ char *abspath; ++ int err, saved_errno; ++ ++#ifdef _DIRENT_HAVE_D_TYPE ++ /* Mapping from d_type to stat mode_t. We omit DT_LNK so that ++ * we'll fall through to stat and get the real file type. */ ++ static const mode_t modes[] = { ++ [DT_BLK] = S_IFBLK, ++ [DT_CHR] = S_IFCHR, ++ [DT_DIR] = S_IFDIR, ++ [DT_FIFO] = S_IFIFO, ++ [DT_REG] = S_IFREG, ++ [DT_SOCK] = S_IFSOCK ++ }; ++ if (entry->d_type < ARRAY_SIZE(modes) && modes[entry->d_type]) ++ return modes[entry->d_type]; ++#endif ++ ++ abspath = talloc_asprintf (NULL, "%s/%s", path, entry->d_name); ++ if (!abspath) { ++ errno = ENOMEM; ++ return -1; ++ } ++ err = stat(abspath, &statbuf); ++ saved_errno = errno; ++ talloc_free (abspath); ++ if (err < 0) { ++ errno = saved_errno; ++ return -1; ++ } ++ return statbuf.st_mode & S_IFMT; ++} ++ + /* Test if the directory looks like a Maildir directory. + * + * Search through the array of directory entries to see if we can find all +@@ -162,12 +204,12 @@ dirent_sort_strcmp_name (const struct dirent **a, const struct dirent **b) + * Return 1 if the directory looks like a Maildir and 0 otherwise. + */ + static int +-_entries_resemble_maildir (struct dirent **entries, int count) ++_entries_resemble_maildir (const char *path, struct dirent **entries, int count) + { + int i, found = 0; + + for (i = 0; i < count; i++) { +- if (entries[i]->d_type != DT_DIR && entries[i]->d_type != DT_UNKNOWN) ++ if (dirent_type (path, entries[i]) != S_IFDIR) + continue; + + if (strcmp(entries[i]->d_name, "new") == 0 || +@@ -250,7 +292,7 @@ add_files_recursive (notmuch_database_t *notmuch, + notmuch_status_t status, ret = NOTMUCH_STATUS_SUCCESS; + notmuch_message_t *message = NULL; + struct dirent **fs_entries = NULL; +- int i, num_fs_entries = 0; ++ int i, num_fs_entries = 0, entry_type; + notmuch_directory_t *directory; + notmuch_filenames_t *db_files = NULL; + notmuch_filenames_t *db_subdirs = NULL; +@@ -300,7 +342,7 @@ add_files_recursive (notmuch_database_t *notmuch, + } + + /* Pass 1: Recurse into all sub-directories. */ +- is_maildir = _entries_resemble_maildir (fs_entries, num_fs_entries); ++ is_maildir = _entries_resemble_maildir (path, fs_entries, num_fs_entries); + + for (i = 0; i < num_fs_entries; i++) { + if (interrupted) +@@ -308,17 +350,16 @@ add_files_recursive (notmuch_database_t *notmuch, + + entry = fs_entries[i]; + +- /* We only want to descend into directories. +- * But symlinks can be to directories too, of course. +- * +- * And if the filesystem doesn't tell us the file type in the +- * scandir results, then it might be a directory (and if not, +- * then we'll stat and return immediately in the next level of +- * recursion). */ +- if (entry->d_type != DT_DIR && +- entry->d_type != DT_LNK && +- entry->d_type != DT_UNKNOWN) +- { ++ /* We only want to descend into directories (and symlinks to ++ * directories). */ ++ entry_type = dirent_type (path, entry); ++ if (entry_type == -1) { ++ /* Be pessimistic, e.g. so we don't lose lots of mail just ++ * because a user broke a symlink. */ ++ fprintf (stderr, "Error reading file %s/%s: %s\n", ++ path, entry->d_name, strerror (errno)); ++ return NOTMUCH_STATUS_FILE_ERROR; ++ } else if (entry_type != S_IFDIR) { + continue; + } + +@@ -407,31 +448,13 @@ add_files_recursive (notmuch_database_t *notmuch, + notmuch_filenames_move_to_next (db_subdirs); + } + +- /* If we're looking at a symlink, we only want to add it if it +- * links to a regular file, (and not to a directory, say). +- * +- * Similarly, if the file is of unknown type (due to filesystem +- * limitations), then we also need to look closer. +- * +- * In either case, a stat does the trick. +- */ +- if (entry->d_type == DT_LNK || entry->d_type == DT_UNKNOWN) { +- int err; +- +- next = talloc_asprintf (notmuch, "%s/%s", path, entry->d_name); +- err = stat (next, &st); +- talloc_free (next); +- next = NULL; +- +- /* Don't emit an error for a link pointing nowhere, since +- * the directory-traversal pass will have already done +- * that. */ +- if (err) +- continue; +- +- if (! S_ISREG (st.st_mode)) +- continue; +- } else if (entry->d_type != DT_REG) { ++ /* Only add regular files (and symlinks to regular files). */ ++ entry_type = dirent_type (path, entry); ++ if (entry_type == -1) { ++ fprintf (stderr, "Error reading file %s/%s: %s\n", ++ path, entry->d_name, strerror (errno)); ++ return NOTMUCH_STATUS_FILE_ERROR; ++ } else if (entry_type != S_IFREG) { + continue; + } + +diff --git a/test/new b/test/new +index a7bc146..cab7c01 100755 +--- a/test/new ++++ b/test/new +@@ -140,7 +140,7 @@ test_begin_subtest "Broken symlink aborts" + ln -s does-not-exist "${MAIL_DIR}/broken" + output=$(NOTMUCH_NEW 2>&1) + test_expect_equal "$output" \ +-"Error reading directory ${MAIL_DIR}/broken: No such file or directory ++"Error reading file ${MAIL_DIR}/broken: No such file or directory + Note: A fatal error was encountered: Something went wrong trying to read or write a file + No new mail." + rm "${MAIL_DIR}/broken" +-- +1.7.10 + -- 2.26.2