From bcc0a1b5bb9536dc6ae0e81987738d0273fd2f8b Mon Sep 17 00:00:00 2001 From: Austin Clements Date: Wed, 26 Dec 2012 00:57:55 +1900 Subject: [PATCH] [PATCH 4/5] dump/restore: Use Xapian queries for batch-tag format --- 90/f306841772634191534a31f513d1d6a0e56927 | 215 ++++++++++++++++++++++ 1 file changed, 215 insertions(+) create mode 100644 90/f306841772634191534a31f513d1d6a0e56927 diff --git a/90/f306841772634191534a31f513d1d6a0e56927 b/90/f306841772634191534a31f513d1d6a0e56927 new file mode 100644 index 000000000..380b23be2 --- /dev/null +++ b/90/f306841772634191534a31f513d1d6a0e56927 @@ -0,0 +1,215 @@ +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 18F26431FD2 + for ; Mon, 24 Dec 2012 21:58:20 -0800 (PST) +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 VjhCfDf3T6RL for ; + Mon, 24 Dec 2012 21:58:18 -0800 (PST) +Received: from dmz-mailsec-scanner-7.mit.edu (DMZ-MAILSEC-SCANNER-7.MIT.EDU + [18.7.68.36]) + by olra.theworths.org (Postfix) with ESMTP id 61E96431FC0 + for ; Mon, 24 Dec 2012 21:58:14 -0800 (PST) +X-AuditID: 12074424-b7f4e6d0000004ca-2a-50d94076303e +Received: from mailhub-auth-4.mit.edu ( [18.7.62.39]) + by dmz-mailsec-scanner-7.mit.edu (Symantec Messaging Gateway) with SMTP + id 80.FE.01226.67049D05; Tue, 25 Dec 2012 00:58:14 -0500 (EST) +Received: from outgoing.mit.edu (OUTGOING-AUTH.MIT.EDU [18.7.22.103]) + by mailhub-auth-4.mit.edu (8.13.8/8.9.2) with ESMTP id qBP5wCKx008906; + Tue, 25 Dec 2012 00:58:12 -0500 +Received: from drake.dyndns.org (c-76-21-105-205.hsd1.ca.comcast.net + [76.21.105.205]) (authenticated bits=0) + (User authenticated as amdragon@ATHENA.MIT.EDU) + by outgoing.mit.edu (8.13.6/8.12.4) with ESMTP id qBP5w7WY011707 + (version=TLSv1/SSLv3 cipher=AES256-SHA bits=256 verify=NOT); + Tue, 25 Dec 2012 00:58:10 -0500 (EST) +Received: from amthrax by drake.dyndns.org with local (Exim 4.77) + (envelope-from ) + id 1TnNWg-0001Xu-RP; Tue, 25 Dec 2012 00:58:06 -0500 +From: Austin Clements +To: notmuch@notmuchmail.org +Subject: [PATCH 4/5] dump/restore: Use Xapian queries for batch-tag format +Date: Tue, 25 Dec 2012 00:57:55 -0500 +Message-Id: <1356415076-5692-5-git-send-email-amdragon@mit.edu> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1356415076-5692-1-git-send-email-amdragon@mit.edu> +References: <1356415076-5692-1-git-send-email-amdragon@mit.edu> +X-Brightmail-Tracker: + H4sIAAAAAAAAA+NgFjrHIsWRmVeSWpSXmKPExsUixG6nrlvmcDPAYO4/bosbrd2MFk3TnS1W + z+WxuH5zJrMDi8fOWXfZPW7df83u8WzVLWaPLYfeMwewRHHZpKTmZJalFunbJXBlrJ5wl7Hg + v2rF91sfmRsY98h2MXJwSAiYSJyamdrFyAlkiklcuLeerYuRi0NIYB+jxKXzl6GcDYwS654f + YodwLjJJHD84GSozl1Hi8Y+3LCD9bAIaEtv2L2cEsUUEpCV23p3NCmIzC+RJPHy0lR1knbCA + l8T1GUkgYRYBVYkdp86DtfIK2Eu0/PzCBnGGokT3swlgNqeAg8TcPyvBaoSAar7O3cwygZF/ + ASPDKkbZlNwq3dzEzJzi1GTd4uTEvLzUIl1zvdzMEr3UlNJNjOBgc1HZwdh8SOkQowAHoxIP + b8HkGwFCrIllxZW5hxglOZiURHlf290MEOJLyk+pzEgszogvKs1JLT7EKMHBrCTCa8IDlONN + SaysSi3Kh0lJc7AoifNeT7npLySQnliSmp2aWpBaBJOV4eBQkuAttQdqFCxKTU+tSMvMKUFI + M3FwggznARoeClLDW1yQmFucmQ6RP8WoKCXOWwmSEABJZJTmwfXCksErRnGgV4R5T4NU8QAT + CVz3K6DBTECDY/lugAwuSURISTUwsgUJpFv4xp1yuMukcFHqRfGf7/4L2KQ3sh6vevDIxrxk + W8SvxPO7ZyYpZnKdOFnWrOS4eHHrqxs+9z2StvisTvruuYzfKOmf9pQp5j2SYkd1bPeEvpso + 29r1qXNfbfD+s7uqOuMX5mlya6nL/TZPXFIiGLznZNQtNq/Kff/nmRfEu0zs9f6ixFKckWio + xVxUnAgArX5+tuECAAA= +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, 25 Dec 2012 05:58:20 -0000 + +This switches the new batch-tag format away from using a home-grown +hex-encoding scheme for message IDs in the dump to simply using Xapian +queries with Xapian quoting syntax. + +This has a variety of advantages beyond presenting a cleaner and more +consistent interface. Foremost is that it will dramatically simplify +the quoting for batch tagging, which shares the same input format. +While the hex-encoding is no better or worse for the simple ID queries +used by dump/restore, it becomes onerous for general-purpose queries +used in batch tagging. It also better handles strange cases like +"id:foo and bar", since this is no longer syntactically valid. +--- + notmuch-dump.c | 9 +++++---- + notmuch-restore.c | 22 ++++++++++------------ + tag-util.c | 6 ------ + test/dump-restore | 11 +++++------ + 4 files changed, 20 insertions(+), 28 deletions(-) + +diff --git a/notmuch-dump.c b/notmuch-dump.c +index 29d79da..bf01a39 100644 +--- a/notmuch-dump.c ++++ b/notmuch-dump.c +@@ -20,6 +20,7 @@ + + #include "notmuch-client.h" + #include "dump-restore-private.h" ++#include "string-util.h" + + int + notmuch_dump_command (unused (void *ctx), int argc, char *argv[]) +@@ -141,13 +142,13 @@ notmuch_dump_command (unused (void *ctx), int argc, char *argv[]) + fprintf (stderr, "Error: cannot dump message id containing line break: %s\n", message_id); + return 1; + } +- if (hex_encode (notmuch, message_id, +- &buffer, &buffer_size) != HEX_SUCCESS) { +- fprintf (stderr, "Error: failed to hex-encode msg-id %s\n", ++ if (make_boolean_term (notmuch, "id", message_id, ++ &buffer, &buffer_size)) { ++ fprintf (stderr, "Error: failed to quote message id %s\n", + message_id); + return 1; + } +- fprintf (output, " -- id:%s\n", buffer); ++ fprintf (output, " -- %s\n", buffer); + } + + notmuch_message_destroy (message); +diff --git a/notmuch-restore.c b/notmuch-restore.c +index 9ed9b51..77a4c27 100644 +--- a/notmuch-restore.c ++++ b/notmuch-restore.c +@@ -207,7 +207,7 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[]) + INTERNAL_ERROR ("compile time constant regex failed."); + + do { +- char *query_string; ++ char *query_string, *prefix, *term; + + if (line_ctx != NULL) + talloc_free (line_ctx); +@@ -220,19 +220,17 @@ notmuch_restore_command (unused (void *ctx), int argc, char *argv[]) + &query_string, tag_ops); + + if (ret == 0) { +- if (strncmp ("id:", query_string, 3) != 0) { +- fprintf (stderr, "Warning: unsupported query: %s\n", query_string); ++ ret = parse_boolean_term (line_ctx, query_string, ++ &prefix, &term); ++ if (ret) { ++ fprintf (stderr, "Warning: cannot parse query: %s\n", ++ query_string); ++ continue; ++ } else if (strcmp ("id", prefix) != 0) { ++ fprintf (stderr, "Warning: not an id query: %s\n", query_string); + continue; + } +- /* delete id: from front of string; tag_message +- * expects a raw message-id. +- * +- * XXX: Note that query string id:foo and bar will be +- * interpreted as a message id "foo and bar". This +- * should eventually be fixed to give a better error +- * message. +- */ +- query_string = query_string + 3; ++ query_string = term; + } + } + +diff --git a/tag-util.c b/tag-util.c +index 705b7ba..e4e5dda 100644 +--- a/tag-util.c ++++ b/tag-util.c +@@ -124,12 +124,6 @@ parse_tag_line (void *ctx, char *line, + } + + /* tok now points to the query string */ +- if (hex_decode_inplace (tok) != HEX_SUCCESS) { +- ret = line_error (TAG_PARSE_INVALID, line_for_error, +- "hex decoding of query %s failed", tok); +- goto DONE; +- } +- + *query_string = tok; + + DONE: +diff --git a/test/dump-restore b/test/dump-restore +index 6a989b6..aecc393 100755 +--- a/test/dump-restore ++++ b/test/dump-restore +@@ -195,23 +195,22 @@ a + + # the previous line was blank; also no yelling please + +%zz -- id:whatever +-+e +f id:%yy +++e +f id:" +++e +f tag:abc + # the next non-comment line should report an an empty tag error for + # batch tagging, but not for restore + + +e -- id:20091117232137.GA7669@griffis1.net +-# highlight the sketchy id parsing; this should be last +-+g -- id:foo and bar + EOF + + cat < EXPECTED +-Warning: unsupported query: a ++Warning: cannot parse query: a + Warning: no query string [+0] + Warning: no query string [+a +b] + Warning: missing query string [+a +b ] + Warning: no query string after -- [+c +d --] + Warning: hex decoding of tag %zz failed [+%zz -- id:whatever] +-Warning: hex decoding of query id:%yy failed [+e +f id:%yy] +-Warning: cannot apply tags to missing message: foo and bar ++Warning: cannot parse query: id:" ++Warning: not an id query: tag:abc + EOF + + test_expect_equal_file EXPECTED OUTPUT +-- +1.7.10.4 + -- 2.26.2