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