[notmuch] [PATCH] lib: Add a new prefix "listid" to the search-terms syntax.

[Pablo Oliveira]

Add support for indexing and searching the message's List-ID header.
This is useful when matching all the messages belonging to a particular
mailing list.

Signed-off-by: Pablo Oliveira <pablo at sifflez.org>
---
 lib/database.cc |    3 ++-
 lib/index.cc    |   49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 notmuch.1       |    2 ++
 notmuch.c       |    1 +
 4 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/lib/database.cc b/lib/database.cc
index b6c4d07..f5d695c 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -124,7 +124,8 @@ prefix_t PROBABILISTIC_PREFIX[]= {
     { "from", "XFROM" },
     { "to", "XTO" },
     { "attachment", "XATTACHMENT" },
-    { "subject", "XSUBJECT"}
+    { "subject", "XSUBJECT"},
+    { "listid", "XLISTID"}
 };
 
 int
diff --git a/lib/index.cc b/lib/index.cc
index 125fa6c..b27a1dc 100644
--- a/lib/index.cc
+++ b/lib/index.cc
@@ -254,6 +254,50 @@ _index_mime_part (notmuch_message_t *message,
     free (body);
 }
 
+static void
+_index_listid (notmuch_message_t *message,
+               const char *list_id_header)
+{
+    const char *begin_list_id, *end_list_id;
+
+    if (list_id_header == NULL)
+	return;
+
+    /* RFC2919 says that the list-id is found at the end of the header
+     * and enclosed between angle brackets. If we cannot find a
+     * matching pair of brackets containing at least one character,
+     * we ignore the list id header. */
+
+    begin_list_id = strrchr (list_id_header, '<');
+    if (!begin_list_id)
+	return;
+
+    end_list_id = strrchr(begin_list_id, '>');
+    if (!end_list_id || (end_list_id - begin_list_id < 2))
+	return;
+
+    void *local = talloc_new (NULL);
+
+    /* We extract the list id between the angle brackets */
+    const char *list_id = talloc_strndup(local, begin_list_id + 1,
+					 end_list_id - begin_list_id - 1);
+
+    /* All the text before is the description of the list */
+    const char *description = talloc_strndup(local, list_id_header,
+					     begin_list_id - list_id_header);
+
+    /* Description may be RFC2047 encoded */
+    char *decoded_desc = g_mime_utils_header_decode_phrase(description);
+
+    _notmuch_message_gen_terms(message, "listid", list_id);
+
+    if (decoded_desc)
+	_notmuch_message_gen_terms(message, "listid", decoded_desc);
+
+    free(decoded_desc);
+    talloc_free (local);
+}
+
 notmuch_status_t
 _notmuch_message_index_file (notmuch_message_t *message,
 			     const char *filename)
@@ -263,7 +307,7 @@ _notmuch_message_index_file (notmuch_message_t *message,
     GMimeMessage *mime_message = NULL;
     InternetAddressList *addresses;
     FILE *file = NULL;
-    const char *from, *subject;
+    const char *from, *subject, *listid;
     notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
     static int initialized = 0;
 
@@ -298,6 +342,9 @@ _notmuch_message_index_file (notmuch_message_t *message,
     subject = skip_re_in_subject (subject);
     _notmuch_message_gen_terms (message, "subject", subject);
 
+    listid = g_mime_object_get_header (GMIME_OBJECT(mime_message), "List-Id");
+    _index_listid (message, listid);
+
     _index_mime_part (message, g_mime_message_get_mime_part (mime_message));
 
   DONE:
diff --git a/notmuch.1 b/notmuch.1
index 369ecba..2be7056 100644
--- a/notmuch.1
+++ b/notmuch.1
@@ -362,6 +362,8 @@ terms to match against specific portions of an email, (where
 
 	thread:<thread-id>
 
+	listid:<list-id>
+
 The
 .B from:
 prefix is used to match the name or address of the sender of an email
diff --git a/notmuch.c b/notmuch.c
index 2ac8a59..cc9233b 100644
--- a/notmuch.c
+++ b/notmuch.c
@@ -55,6 +55,7 @@ static const char search_terms_help[] =
     "\t\t\ttag:<tag>\n"
     "\t\t\tid:<message-id>\n"
     "\t\t\tthread:<thread-id>\n"
+    "\t\t\tlistid:<list-id>\n"
     "\n"
     "\t\tThe from: prefix is used to match the name or address of\n"
     "\t\tthe sender of an email message.\n"
-- 
1.6.3.3