From e5209e1c3d5d5dca3bb3e9417c062cc160987903 Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Wed, 2 Apr 2014 22:49:38 +2000 Subject: [PATCH] Re: [Patch v5 4/6] restore: transparently support gzipped input --- 00/44ca8b46f3cdc54d53a11a1075a3c78935d9da | 228 ++++++++++++++++++++++ 1 file changed, 228 insertions(+) create mode 100644 00/44ca8b46f3cdc54d53a11a1075a3c78935d9da diff --git a/00/44ca8b46f3cdc54d53a11a1075a3c78935d9da b/00/44ca8b46f3cdc54d53a11a1075a3c78935d9da new file mode 100644 index 000000000..58e9ec0a5 --- /dev/null +++ b/00/44ca8b46f3cdc54d53a11a1075a3c78935d9da @@ -0,0 +1,228 @@ +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 16B52431FBF + for ; Tue, 1 Apr 2014 19:49:52 -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 Oxu4OOMTlZ+0 for ; + Tue, 1 Apr 2014 19:49:44 -0700 (PDT) +Received: from dmz-mailsec-scanner-1.mit.edu (dmz-mailsec-scanner-1.mit.edu + [18.9.25.12]) + (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id A9B5C431FBD + for ; Tue, 1 Apr 2014 19:49:43 -0700 (PDT) +X-AuditID: 1209190c-f794a6d000000c27-c9-533b7ac5e591 +Received: from mailhub-auth-3.mit.edu ( [18.9.21.43]) + (using TLS with cipher AES256-SHA (256/256 bits)) + (Client did not present a certificate) + by dmz-mailsec-scanner-1.mit.edu (Symantec Messaging Gateway) with SMTP + id C8.93.03111.5CA7B335; Tue, 1 Apr 2014 22:49:41 -0400 (EDT) +Received: from outgoing.mit.edu (outgoing-auth-1.mit.edu [18.9.28.11]) + by mailhub-auth-3.mit.edu (8.13.8/8.9.2) with ESMTP id s322nedP017188; + Tue, 1 Apr 2014 22:49:41 -0400 +Received: from awakening.csail.mit.edu (awakening.csail.mit.edu [18.26.4.91]) + (authenticated bits=0) + (User authenticated as amdragon@ATHENA.MIT.EDU) + by outgoing.mit.edu (8.13.8/8.12.4) with ESMTP id s322ncZu028902 + (version=TLSv1/SSLv3 cipher=DHE-RSA-AES128-SHA bits=128 verify=NOT); + Tue, 1 Apr 2014 22:49:40 -0400 +Received: from amthrax by awakening.csail.mit.edu with local (Exim 4.80) + (envelope-from ) + id 1WVBFC-0004Ib-M1; Tue, 01 Apr 2014 22:49:38 -0400 +Date: Tue, 1 Apr 2014 22:49:38 -0400 +From: Austin Clements +To: David Bremner +Subject: Re: [Patch v5 4/6] restore: transparently support gzipped input +Message-ID: <20140402024938.GA25677@mit.edu> +References: <1396401381-18128-1-git-send-email-david@tethera.net> + <1396401381-18128-5-git-send-email-david@tethera.net> +MIME-Version: 1.0 +Content-Type: text/plain; charset=us-ascii +Content-Disposition: inline +In-Reply-To: <1396401381-18128-5-git-send-email-david@tethera.net> +User-Agent: Mutt/1.5.21 (2010-09-15) +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFmpileLIzCtJLcpLzFFi42IR4hTV1j1aZR1sMOOzhsWN1m5Gi+s3ZzI7 + MHk8W3WL2WPLoffMAUxRXDYpqTmZZalF+nYJXBmrTp1lLziqXjH7bWUD43W5LkZODgkBE4lv + e/6wQNhiEhfurWfrYuTiEBKYzSQx8+w2dghnA6NEy7WJrBDOKSaJZa+7GCGcJYwSmxf0MIH0 + swioSHydtYsZxGYT0JDYtn85I4gtIqAqcXXbZDYQm1lAWuLb72awemEBD4lt25aD7eYV0JGY + t+s0UA0H0NBKiUcXZSHCghInZz5hgWjVkrjx7yUTSAnImOX/OEDCnAJOEudWrmUHsUWBLphy + chvbBEahWUi6ZyHpnoXQvYCReRWjbEpulW5uYmZOcWqybnFyYl5eapGuoV5uZoleakrpJkZw + UEvy7GB8c1DpEKMAB6MSD++B81bBQqyJZcWVuYcYJTmYlER5OYKtg4X4kvJTKjMSizPii0pz + UosPMUpwMCuJ8H73BcrxpiRWVqUW5cOkpDlYlMR531oDTRJITyxJzU5NLUgtgsnKcHAoSfBO + rQRqFCxKTU+tSMvMKUFIM3FwggznARqeC1LDW1yQmFucmQ6RP8WoKCXOuwQkIQCSyCjNg+uF + JZ1XjOJArwjzfgep4gEmLLjuV0CDmYAGc6+zAhlckoiQkmpgrGmMecNWrfjNPcHLviriXWJ5 + 3JzCExKzZqpO+X7z8iFJxTOcQuteMxXEhDFdqshfZFOgq6Ptr7A7q8i222DvPrZXaZ1TG/R8 + 9n9iz2qvqM38W6+S5pyWoib0kyU5+36QqOjKkrbImM2358rpT27ZU8nyNeLHsi9vD18+/OGQ + arKwftcujv1KLMUZiYZazEXFiQAImOYMFQMAAA== +Cc: notmuch@notmuchmail.org +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: Wed, 02 Apr 2014 02:49:52 -0000 + +Quoth David Bremner on Apr 01 at 10:16 pm: +> We rely completely on zlib to do the right thing in detecting gzipped +> input. Since our dump format is chosen to be 7 bit ascii, this should +> be fine. +> --- +> doc/man1/notmuch-restore.rst | 8 ++++++++ +> notmuch-restore.c | 37 +++++++++++++++++++++---------------- +> test/T240-dump-restore.sh | 14 ++++++++++++++ +> 3 files changed, 43 insertions(+), 16 deletions(-) +> +> diff --git a/doc/man1/notmuch-restore.rst b/doc/man1/notmuch-restore.rst +> index d6cf19a..936b138 100644 +> --- a/doc/man1/notmuch-restore.rst +> +++ b/doc/man1/notmuch-restore.rst +> @@ -50,6 +50,14 @@ Supported options for **restore** include +> format, this heuristic, based the fact that batch-tag format +> contains no parentheses, should be accurate. +> +> +GZIPPED INPUT +> +============= +> + +> +\ **notmuch restore** will detect if the input is compressed in +> +**gzip(1)** format and automatically decompress it while reading. This +> +detection does not depend on file naming and in particular works for +> +standard input. +> + +> SEE ALSO +> ======== +> +> diff --git a/notmuch-restore.c b/notmuch-restore.c +> index c54d513..86bce20 100644 +> --- a/notmuch-restore.c +> +++ b/notmuch-restore.c +> @@ -22,6 +22,7 @@ +> #include "hex-escape.h" +> #include "tag-util.h" +> #include "string-util.h" +> +#include "zlib-extra.h" +> +> static regex_t regex; +> +> @@ -128,7 +129,7 @@ notmuch_restore_command (notmuch_config_t *config, int argc, char *argv[]) +> tag_op_list_t *tag_ops; +> +> char *input_file_name = NULL; +> - FILE *input = stdin; +> + gzFile input; +> char *line = NULL; +> void *line_ctx = NULL; +> size_t line_size; +> @@ -163,13 +164,15 @@ notmuch_restore_command (notmuch_config_t *config, int argc, char *argv[]) +> if (! accumulate) +> flags |= TAG_FLAG_REMOVE_ALL; +> +> - if (input_file_name) { +> - input = fopen (input_file_name, "r"); +> - if (input == NULL) { +> - fprintf (stderr, "Error opening %s for reading: %s\n", +> - input_file_name, strerror (errno)); +> - return EXIT_FAILURE; +> - } +> + if (input_file_name) +> + input = gzopen (input_file_name, "r"); +> + else +> + input = gzdopen (fileno (stdin), "r"); + +As for patch 2, we also need to gzclose input on all paths out of this +function, which also means we probably need to dup stdin above. + +> + +> + if (input == NULL) { +> + fprintf (stderr, "Error opening %s for (gzip) reading: %s\n", +> + input_file_name ? input_file_name : "stdin", strerror (errno)); +> + return EXIT_FAILURE; +> } +> +> if (opt_index < argc) { +> @@ -184,12 +187,17 @@ notmuch_restore_command (notmuch_config_t *config, int argc, char *argv[]) +> } +> +> do { +> - line_len = getline (&line, &line_size, input); +> + util_status_t status; +> + +> + status = gz_getline (line_ctx, &line, &line_size, &line_len, input); +> +> /* empty input file not considered an error */ +> - if (line_len < 0) +> + if (status == UTIL_EOF) +> return EXIT_SUCCESS; +> +> + if (status) +> + return EXIT_FAILURE; +> + +> } while ((line_len == 0) || +> (line[0] == '#') || +> /* the cast is safe because we checked about for line_len < 0 */ +> @@ -254,7 +262,7 @@ notmuch_restore_command (notmuch_config_t *config, int argc, char *argv[]) +> if (ret) +> break; +> +> - } while ((line_len = getline (&line, &line_size, input)) != -1); +> + } while (gz_getline (line_ctx, &line, &line_size, &line_len, input) == UTIL_SUCCESS); +> +> if (line_ctx != NULL) +> talloc_free (line_ctx); +> @@ -262,13 +270,10 @@ notmuch_restore_command (notmuch_config_t *config, int argc, char *argv[]) +> if (input_format == DUMP_FORMAT_SUP) +> regfree (®ex); +> +> - if (line) +> - free (line); +> - +> notmuch_database_destroy (notmuch); +> +> - if (input != stdin) +> - fclose (input); +> + if (input_file_name != NULL) +> + gzclose_r (input); +> +> return ret ? EXIT_FAILURE : EXIT_SUCCESS; +> } +> diff --git a/test/T240-dump-restore.sh b/test/T240-dump-restore.sh +> index d79aca8..50d4d48 100755 +> --- a/test/T240-dump-restore.sh +> +++ b/test/T240-dump-restore.sh +> @@ -80,6 +80,20 @@ notmuch dump --gzip --output=dump-gzip-outfile.gz +> gunzip dump-gzip-outfile.gz +> test_expect_equal_file dump.expected dump-gzip-outfile +> +> +test_begin_subtest "restoring gzipped stdin" +> +notmuch dump --gzip --output=backup.gz +> +notmuch tag +new_tag '*' +> +notmuch restore < backup.gz +> +notmuch dump --output=dump.actual +> +test_expect_equal_file dump.expected dump.actual +> + +> +test_begin_subtest "restoring gzipped file" +> +notmuch dump --gzip --output=backup.gz +> +notmuch tag +new_tag '*' +> +notmuch restore --input=backup.gz +> +notmuch dump --output=dump.actual +> +test_expect_equal_file dump.expected dump.actual +> + +> # Note, we assume all messages from cworth have a message-id +> # containing cworth.org +> -- 2.26.2