unofficial mirror of notmuch@notmuchmail.org
 help / color / mirror / code / Atom feed
From: David Bremner <david@tethera.net>
To: notmuch@notmuchmail.org, notmuch@freelists.org
Cc: Daniel Kahn Gillmor <dkg@fifthhorseman.net>
Subject: [Patch v4 11/12] lib: add notmuch_message_reindex
Date: Fri, 21 Jul 2017 07:58:39 -0300	[thread overview]
Message-ID: <20170721105840.4737-12-david@tethera.net> (raw)
In-Reply-To: <20170721105840.4737-1-david@tethera.net>

From: Daniel Kahn Gillmor <dkg@fifthhorseman.net>

This new function asks the database to reindex a given message.
The parameter `indexopts` is currently ignored, but is intended to
provide an extensible API to support e.g. changing the encryption or
filtering status (e.g. whether and how certain non-plaintext parts are
indexed).
---
 lib/add-message.cc    |   2 +-
 lib/message.cc        | 108 +++++++++++++++++++++++++++++++++++++++++++++++++-
 lib/notmuch-private.h |   6 +++
 lib/notmuch.h         |  15 +++++++
 4 files changed, 129 insertions(+), 2 deletions(-)

diff --git a/lib/add-message.cc b/lib/add-message.cc
index f0a80c4f..711ed9fa 100644
--- a/lib/add-message.cc
+++ b/lib/add-message.cc
@@ -220,7 +220,7 @@ _my_talloc_free_for_g_hash (void *ptr)
     talloc_free (ptr);
 }
 
-static notmuch_status_t
+notmuch_status_t
 _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
 					   notmuch_message_t *message,
 					   notmuch_message_file_t *message_file,
diff --git a/lib/message.cc b/lib/message.cc
index a1c3cd78..539d3320 100644
--- a/lib/message.cc
+++ b/lib/message.cc
@@ -579,7 +579,9 @@ void
 _notmuch_message_remove_terms (notmuch_message_t *message, const char *prefix)
 {
     Xapian::TermIterator i;
-    size_t prefix_len = strlen (prefix);
+    size_t prefix_len = 0;
+
+    prefix_len = strlen (prefix);
 
     while (1) {
 	i = message->doc.termlist_begin ();
@@ -1934,3 +1936,107 @@ _notmuch_message_frozen (notmuch_message_t *message)
 {
     return message->frozen;
 }
+
+notmuch_status_t
+notmuch_message_reindex (notmuch_message_t *message,
+			 notmuch_param_t unused (*indexopts))
+{
+    notmuch_database_t *notmuch = NULL;
+    notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
+    notmuch_private_status_t private_status;
+    notmuch_filenames_t *orig_filenames = NULL;
+    const char *orig_thread_id = NULL;
+    notmuch_message_file_t *message_file = NULL;
+
+    int found = 0;
+
+    if (message == NULL)
+	return NOTMUCH_STATUS_NULL_POINTER;
+
+    /* Save in case we need to delete message */
+    orig_thread_id = notmuch_message_get_thread_id (message);
+    if (!orig_thread_id) {
+	/* XXX TODO: make up new error return? */
+	INTERNAL_ERROR ("message without thread-id");
+    }
+
+    /* strdup it because the metadata may be invalidated */
+    orig_thread_id = talloc_strdup (message, orig_thread_id);
+
+    notmuch = _notmuch_message_database (message);
+
+    ret = _notmuch_database_ensure_writable (notmuch);
+    if (ret)
+	return ret;
+
+    orig_filenames = notmuch_message_get_filenames (message);
+
+    private_status = _notmuch_message_remove_indexed_terms (message);
+    if (private_status) {
+	ret = COERCE_STATUS(private_status, "error removing terms");
+	goto DONE;
+    }
+
+    /* re-add the filenames with the associated indexopts */
+    for (; notmuch_filenames_valid (orig_filenames);
+	 notmuch_filenames_move_to_next (orig_filenames)) {
+
+	const char *date;
+	const char *from, *to, *subject;
+	char *message_id = NULL;
+	const char *thread_id = NULL;
+
+	const char *filename = notmuch_filenames_get (orig_filenames);
+
+	message_file = _notmuch_message_file_open (notmuch, filename);
+	if (message_file == NULL)
+	    continue;
+
+	ret = _notmuch_message_file_get_headers (message_file,
+						 &from, &subject, &to, &date,
+						 &message_id);
+	if (ret)
+	    goto DONE;
+
+	/* XXX TODO: deal with changing message id? */
+
+	_notmuch_message_add_filename (message, filename);
+
+	ret = _notmuch_database_link_message_to_parents (notmuch, message,
+							 message_file,
+							 &thread_id);
+	if (ret)
+	    goto DONE;
+
+	if (thread_id == NULL)
+	    thread_id = orig_thread_id;
+
+	_notmuch_message_add_term (message, "thread", thread_id);
+	_notmuch_message_set_header_values (message, date, from, subject);
+
+	ret = _notmuch_message_index_file (message, message_file);
+
+	if (ret == NOTMUCH_STATUS_FILE_ERROR)
+	    continue;
+	if (ret)
+	    goto DONE;
+
+	found++;
+	_notmuch_message_file_close (message_file);
+	message_file = NULL;
+    }
+    if (found == 0) {
+	/* put back thread id to help cleanup */
+	_notmuch_message_add_term (message, "thread", orig_thread_id);
+	ret = _notmuch_message_delete (message);
+    } else {
+	_notmuch_message_sync (message);
+    }
+
+ DONE:
+    if (message_file)
+	_notmuch_message_file_close (message_file);
+
+    /* XXX TODO destroy orig_filenames? */
+    return ret;
+}
diff --git a/lib/notmuch-private.h b/lib/notmuch-private.h
index c8934b8b..b187a80f 100644
--- a/lib/notmuch-private.h
+++ b/lib/notmuch-private.h
@@ -436,6 +436,12 @@ _notmuch_message_file_get_headers (notmuch_message_file_t *message_file,
 const char *
 _notmuch_message_file_get_filename (notmuch_message_file_t *message);
 
+/* add-message.cc */
+notmuch_status_t
+_notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
+					   notmuch_message_t *message,
+					   notmuch_message_file_t *message_file,
+					   const char **thread_id);
 /* index.cc */
 
 notmuch_status_t
diff --git a/lib/notmuch.h b/lib/notmuch.h
index 4c03a893..f78b3473 100644
--- a/lib/notmuch.h
+++ b/lib/notmuch.h
@@ -219,6 +219,7 @@ typedef struct _notmuch_tags notmuch_tags_t;
 typedef struct _notmuch_directory notmuch_directory_t;
 typedef struct _notmuch_filenames notmuch_filenames_t;
 typedef struct _notmuch_config_list notmuch_config_list_t;
+typedef struct _notmuch_param notmuch_param_t;
 #endif /* __DOXYGEN__ */
 
 /**
@@ -1394,6 +1395,20 @@ notmuch_filenames_t *
 notmuch_message_get_filenames (notmuch_message_t *message);
 
 /**
+ * Re-index the e-mail corresponding to 'message' using the supplied index options
+ *
+ * Returns the status of the re-index operation.  (see the return
+ * codes documented in notmuch_database_add_message)
+ *
+ * After reindexing, the user should discard the message object passed
+ * in here by calling notmuch_message_destroy, since it refers to the
+ * original message, not to the reindexed message.
+ */
+notmuch_status_t
+notmuch_message_reindex (notmuch_message_t *message,
+			 notmuch_param_t *indexopts);
+
+/**
  * Message flags.
  */
 typedef enum _notmuch_message_flag {
-- 
2.13.2

  parent reply	other threads:[~2017-07-21 10:58 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-21 10:58 v4 of index multiple files per msg-id, add reindex command David Bremner
2017-07-21 10:58 ` [Patch v4 01/12] lib: isolate n_d_add_message and helper functions into own file David Bremner
2017-07-21 10:58 ` [Patch v4 02/12] lib/n_d_add_message: refactor test for new/ghost messages David Bremner
2017-07-21 10:58 ` [Patch v4 03/12] lib: factor out message-id parsing to separate file David Bremner
2017-07-21 10:58 ` [Patch v4 04/12] lib: refactor notmuch_database_add_message header parsing David Bremner
2017-07-21 10:58 ` [Patch v4 05/12] test: add known broken tests for duplicate message id David Bremner
2017-07-21 10:58 ` [Patch v4 06/12] lib: index message files with duplicate message-ids David Bremner
2017-07-21 10:58 ` [Patch v4 07/12] lib: add notmuch_message_count_files David Bremner
2017-07-21 10:58 ` [Patch v4 08/12] lib: add notmuch_thread_get_total_files David Bremner
2017-07-21 10:58 ` [Patch v4 09/12] cli/search: print total number of files matched in summary output David Bremner
2017-07-21 10:58 ` [Patch v4 10/12] lib: add _notmuch_message_remove_indexed_terms David Bremner
2017-07-21 10:58 ` David Bremner [this message]
2017-07-21 10:58 ` [Patch v4 12/12] add "notmuch reindex" subcommand David Bremner
2017-08-02  2:53 ` v4 of index multiple files per msg-id, add reindex command David Bremner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://notmuchmail.org/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170721105840.4737-12-david@tethera.net \
    --to=david@tethera.net \
    --cc=dkg@fifthhorseman.net \
    --cc=notmuch@freelists.org \
    --cc=notmuch@notmuchmail.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://yhetil.org/notmuch.git/

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).