From faa2c71c7832e2115923d9bbd39a0ed9cd11dc0c Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 8 May 2012 07:58:28 +0000 Subject: [PATCH] Re: [PATCH v2 2/2] new: Centralize file type stat-ing logic --- 42/450e0c3f881fd1db066ddd273333454831076b | 258 ++++++++++++++++++++++ 1 file changed, 258 insertions(+) create mode 100644 42/450e0c3f881fd1db066ddd273333454831076b diff --git a/42/450e0c3f881fd1db066ddd273333454831076b b/42/450e0c3f881fd1db066ddd273333454831076b new file mode 100644 index 000000000..446baf64f --- /dev/null +++ b/42/450e0c3f881fd1db066ddd273333454831076b @@ -0,0 +1,258 @@ +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 3AF1A431FAF + for ; Tue, 8 May 2012 00:58:36 -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 y4o8OzivJ0Rr for ; + Tue, 8 May 2012 00:58:34 -0700 (PDT) +Received: from mail-qc0-f181.google.com (mail-qc0-f181.google.com + [209.85.216.181]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id C3993431FAE + for ; Tue, 8 May 2012 00:58:34 -0700 (PDT) +Received: by qcsk26 with SMTP id k26so152066qcs.26 + for ; Tue, 08 May 2012 00:58:33 -0700 (PDT) +X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; + d=google.com; s=20120113; + h=from:to:cc:subject:in-reply-to:references:user-agent:date + :message-id:mime-version:content-type:x-gm-message-state; + bh=AvnmJ/5kI/eNjOsRv0F9hhkYVq2Ln0xarqnCHxcmBXw=; + b=i23hCtM6IMjfmjQDi7EQA7txBP9Zvs3E0FBPIto9SVU68UiIW5O5XHDLTzddbqWtGO + 0pZwJLoRsFxKAyeS6xEwENNWQYgJvefBRHdbuPWlNzGwDqD5dNKfy0zm1NIZCDhAPapk + 2rxfFidneztRtz3k6IUlXpC+yX8JaXYF/MOa0Zfs2GxfXkqExss47hm+ADc8Ouuf7fC6 + 1/D5YF/yxzueCsLx1gSLTLUd8ABa97++EK4XFL6NfSutlF5ZtKf2/57Z0QzSIYSRxywt + o3I2MfIBP4NkOk3l6u0oMlEPg90+lvBXu4PDjrDgBuWkVSYRKb8KWG1WzjyQqZiNokhI + PD9g== +Received: by 10.224.205.6 with SMTP id fo6mr10210783qab.73.1336463912954; + Tue, 08 May 2012 00:58:32 -0700 (PDT) +Received: from localhost (nikula.org. [92.243.24.172]) + by mx.google.com with ESMTPS id bm15sm2680690qab.17.2012.05.08.00.58.30 + (version=SSLv3 cipher=OTHER); Tue, 08 May 2012 00:58:32 -0700 (PDT) +From: Jani Nikula +To: Austin Clements , notmuch@notmuchmail.org +Subject: Re: [PATCH v2 2/2] new: Centralize file type stat-ing logic +In-Reply-To: <1336429240-1114-3-git-send-email-amdragon@mit.edu> +References: <1336414186-15293-1-git-send-email-amdragon@mit.edu> + <1336429240-1114-1-git-send-email-amdragon@mit.edu> + <1336429240-1114-3-git-send-email-amdragon@mit.edu> +User-Agent: Notmuch/0.11.1+222~ga47a98c (http://notmuchmail.org) Emacs/23.1.1 + (i686-pc-linux-gnu) +Date: Tue, 08 May 2012 07:58:28 +0000 +Message-ID: <87r4uvdryz.fsf@nikula.org> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +X-Gm-Message-State: + ALoCoQl9ItXHqbHEak1VBDEU3KqrTo5GO5ue8xuA/6kGn/FOJzkzG/L7EUE8aMGQMSGTOZ6ZMPs7 +Cc: Vladimir Marek +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: Tue, 08 May 2012 07:58:36 -0000 + +On Mon, 7 May 2012 18:20:40 -0400, Austin Clements wrote: +> 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). + +LGTM. + +> --- +> 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 cb720cc..8955677 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; +> + int i, num_fs_entries, entry_type; +> notmuch_directory_t *directory; +> notmuch_filenames_t *db_files = NULL; +> notmuch_filenames_t *db_subdirs = NULL; +> @@ -317,7 +359,7 @@ 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) +> @@ -325,17 +367,16 @@ 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; +> } +> +> @@ -425,31 +466,13 @@ 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 26253db..e3900f5 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 "$output" \ +> -"Error reading directory /run/shm/nm/tmp.new/mail/broken: No such file or directory +> +"Error reading file /run/shm/nm/tmp.new/mail/broken: No such file or directory +> Note: A fatal error was encountered: Something went wrong trying to read or write a file +> No new mail." +> rm "${MAIL_DIR}/broken" +> -- +> 1.7.10 +> +> _______________________________________________ +> notmuch mailing list +> notmuch@notmuchmail.org +> http://notmuchmail.org/mailman/listinfo/notmuch -- 2.26.2