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
Subject: [Patch v4 04/12] lib: refactor notmuch_database_add_message header parsing
Date: Fri, 21 Jul 2017 07:58:32 -0300	[thread overview]
Message-ID: <20170721105840.4737-5-david@tethera.net> (raw)
In-Reply-To: <20170721105840.4737-1-david@tethera.net>

This function is large and hard to understand and modify. Start to
break it down into meaningful pieces.
---
 lib/add-message.cc    | 54 +++-----------------------------
 lib/message-file.c    | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++
 lib/notmuch-private.h | 11 +++++++
 3 files changed, 101 insertions(+), 50 deletions(-)

diff --git a/lib/add-message.cc b/lib/add-message.cc
index f09094af..2922eaa9 100644
--- a/lib/add-message.cc
+++ b/lib/add-message.cc
@@ -468,7 +468,7 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
     notmuch_private_status_t private_status;
     notmuch_bool_t is_ghost = FALSE, is_new = FALSE;
 
-    const char *date, *header;
+    const char *date;
     const char *from, *to, *subject;
     char *message_id = NULL;
 
@@ -489,57 +489,12 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
     if (ret)
 	goto DONE;
 
-    /* Parse message up front to get better error status. */
-    ret = _notmuch_message_file_parse (message_file);
+    ret = _notmuch_message_file_get_headers (message_file,
+					     &from, &subject, &to, &date,
+					     &message_id);
     if (ret)
 	goto DONE;
 
-    /* Before we do any real work, (especially before doing a
-     * potential SHA-1 computation on the entire file's contents),
-     * let's make sure that what we're looking at looks like an
-     * actual email message.
-     */
-    from = _notmuch_message_file_get_header (message_file, "from");
-    subject = _notmuch_message_file_get_header (message_file, "subject");
-    to = _notmuch_message_file_get_header (message_file, "to");
-
-    if ((from == NULL || *from == '\0') &&
-	(subject == NULL || *subject == '\0') &&
-	(to == NULL || *to == '\0')) {
-	ret = NOTMUCH_STATUS_FILE_NOT_EMAIL;
-	goto DONE;
-    }
-
-    /* Now that we're sure it's mail, the first order of business
-     * is to find a message ID (or else create one ourselves).
-     */
-    header = _notmuch_message_file_get_header (message_file, "message-id");
-    if (header && *header != '\0') {
-	message_id = _notmuch_message_id_parse (message_file, header, NULL);
-
-	/* So the header value isn't RFC-compliant, but it's
-	 * better than no message-id at all.
-	 */
-	if (message_id == NULL)
-	    message_id = talloc_strdup (message_file, header);
-    }
-
-    if (message_id == NULL ) {
-	/* No message-id at all, let's generate one by taking a
-	 * hash over the file's contents.
-	 */
-	char *sha1 = _notmuch_sha1_of_file (filename);
-
-	/* If that failed too, something is really wrong. Give up. */
-	if (sha1 == NULL) {
-	    ret = NOTMUCH_STATUS_FILE_ERROR;
-	    goto DONE;
-	}
-
-	message_id = talloc_asprintf (message_file, "notmuch-sha1-%s", sha1);
-	free (sha1);
-    }
-
     try {
 	/* Now that we have a message ID, we get a message object,
 	 * (which may or may not reference an existing document in the
@@ -579,7 +534,6 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
 	    if (ret)
 		goto DONE;
 
-	    date = _notmuch_message_file_get_header (message_file, "date");
 	    _notmuch_message_set_header_values (message, date, from, subject);
 
 	    ret = _notmuch_message_index_file (message, message_file);
diff --git a/lib/message-file.c b/lib/message-file.c
index d7acf0d5..b90df305 100644
--- a/lib/message-file.c
+++ b/lib/message-file.c
@@ -92,6 +92,12 @@ _notmuch_message_file_open (notmuch_database_t *notmuch,
     return _notmuch_message_file_open_ctx (notmuch, NULL, filename);
 }
 
+const char *
+_notmuch_message_file_get_filename (notmuch_message_file_t *message_file)
+{
+    return message_file->filename;
+}
+
 void
 _notmuch_message_file_close (notmuch_message_file_t *message)
 {
@@ -345,3 +351,83 @@ _notmuch_message_file_get_header (notmuch_message_file_t *message,
 
     return decoded;
 }
+
+notmuch_status_t
+_notmuch_message_file_get_headers (notmuch_message_file_t *message_file,
+				   const char **from_out,
+				   const char **subject_out,
+				   const char **to_out,
+				   const char **date_out,
+				   char **message_id_out)
+{
+    notmuch_status_t ret;
+    const char *header;
+    const char *from, *to, *subject, *date;
+    char *message_id = NULL;
+
+    /* Parse message up front to get better error status. */
+    ret = _notmuch_message_file_parse (message_file);
+    if (ret)
+	goto DONE;
+
+    /* Before we do any real work, (especially before doing a
+     * potential SHA-1 computation on the entire file's contents),
+     * let's make sure that what we're looking at looks like an
+     * actual email message.
+     */
+    from = _notmuch_message_file_get_header (message_file, "from");
+    subject = _notmuch_message_file_get_header (message_file, "subject");
+    to = _notmuch_message_file_get_header (message_file, "to");
+    date = _notmuch_message_file_get_header (message_file, "date");
+
+    if ((from == NULL || *from == '\0') &&
+	(subject == NULL || *subject == '\0') &&
+	(to == NULL || *to == '\0')) {
+	ret = NOTMUCH_STATUS_FILE_NOT_EMAIL;
+	goto DONE;
+    }
+
+    /* Now that we're sure it's mail, the first order of business
+     * is to find a message ID (or else create one ourselves).
+     */
+    header = _notmuch_message_file_get_header (message_file, "message-id");
+    if (header && *header != '\0') {
+	message_id = _notmuch_message_id_parse (message_file, header, NULL);
+
+	/* So the header value isn't RFC-compliant, but it's
+	 * better than no message-id at all.
+	 */
+	if (message_id == NULL)
+	    message_id = talloc_strdup (message_file, header);
+    }
+
+    if (message_id == NULL ) {
+	/* No message-id at all, let's generate one by taking a
+	 * hash over the file's contents.
+	 */
+	char *sha1 = _notmuch_sha1_of_file (_notmuch_message_file_get_filename (message_file));
+
+	/* If that failed too, something is really wrong. Give up. */
+	if (sha1 == NULL) {
+	    ret = NOTMUCH_STATUS_FILE_ERROR;
+	    goto DONE;
+	}
+
+	message_id = talloc_asprintf (message_file, "notmuch-sha1-%s", sha1);
+	free (sha1);
+    }
+ DONE:
+    if (ret == NOTMUCH_STATUS_SUCCESS) {
+	if (from_out)
+	    *from_out = from;
+	if (subject_out)
+	    *subject_out = subject;
+	if (to_out)
+	    *to_out = to;
+	if (date_out)
+	    *date_out = date;
+	if (message_id_out)
+	    *message_id_out = message_id;
+    }
+    return ret;
+}
diff --git a/lib/notmuch-private.h b/lib/notmuch-private.h
index 9957164d..57c61639 100644
--- a/lib/notmuch-private.h
+++ b/lib/notmuch-private.h
@@ -425,6 +425,17 @@ const char *
 _notmuch_message_file_get_header (notmuch_message_file_t *message,
 				 const char *header);
 
+notmuch_status_t
+_notmuch_message_file_get_headers (notmuch_message_file_t *message_file,
+				   const char **from_out,
+				   const char **subject_out,
+				   const char **to_out,
+				   const char **date_out,
+				   char **message_id_out);
+
+const char *
+_notmuch_message_file_get_filename (notmuch_message_file_t *message);
+
 /* index.cc */
 
 notmuch_status_t
-- 
2.13.2

  parent reply	other threads:[~2017-07-21 10:59 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 ` David Bremner [this message]
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 ` [Patch v4 11/12] lib: add notmuch_message_reindex David Bremner
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=20170721105840.4737-5-david@tethera.net \
    --to=david@tethera.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).