cli: address: Do not output duplicate addresses

This filters out duplicate addresses from address command output.

It also also adds tests for the address command.

The code here is an extended version of a patch from Jani Nikula.

doc/man1/notmuch-address.rst

@@ -11,7 +11,7 @@ DESCRIPTION
 ===========
 
 Search for messages matching the given search terms, and display the
-addresses from them.
+addresses from them. Duplicate addresses are filtered out.
 
 See **notmuch-search-terms(7)** for details of the supported syntax for
 <search-terms>.

notmuch-search.c

@@ -53,6 +53,7 @@ typedef struct {
     int offset;
     int limit;
     int dupe;
+    GHashTable *addresses;
 } search_context_t;
 
 typedef struct {
@@ -240,6 +241,28 @@ do_search_threads (search_context_t *ctx)
     return 0;
 }
 
+/* Returns TRUE iff name and addr is duplicate. If not, stores the
+ * name/addr pair in order to detect subsequent duplicates. */
+static notmuch_bool_t
+is_duplicate (const search_context_t *ctx, const char *name, const char *addr)
+{
+    notmuch_bool_t duplicate;
+    char *key;
+
+    key = talloc_asprintf (ctx->format, "%s <%s>", name, addr);
+    if (! key)
+	return FALSE;
+
+    duplicate = g_hash_table_lookup_extended (ctx->addresses, key, NULL, NULL);
+
+    if (! duplicate)
+	g_hash_table_insert (ctx->addresses, key, NULL);
+    else
+	talloc_free (key);
+
+    return duplicate;
+}
+
 static void
 print_mailbox (const search_context_t *ctx, const mailbox_t *mailbox)
 {
@@ -274,7 +297,8 @@ print_mailbox (const search_context_t *ctx, const mailbox_t *mailbox)
 
 /* Print addresses from InternetAddressList.  */
 static void
-process_address_list (const search_context_t *ctx, InternetAddressList *list)
+process_address_list (const search_context_t *ctx,
+		      InternetAddressList *list)
 {
     InternetAddress *address;
     int i;
@@ -298,6 +322,9 @@ process_address_list (const search_context_t *ctx, InternetAddressList *list)
 		.addr = internet_address_mailbox_get_addr (mailbox),
 	    };
 
+	    if (is_duplicate (ctx, mbx.name, mbx.addr))
+		continue;
+
 	    print_mailbox (ctx, &mbx);
 	}
     }
@@ -321,6 +348,13 @@ process_address_header (const search_context_t *ctx, const char *value)
     g_object_unref (list);
 }
 
+/* Destructor for talloc-allocated GHashTable keys and values. */
+static void
+_talloc_free_for_g_hash (void *ptr)
+{
+    talloc_free (ptr);
+}
+
 static int
 _count_filenames (notmuch_message_t *message)
 {
@@ -673,8 +707,14 @@ notmuch_address_command (notmuch_config_t *config, int argc, char *argv[])
 				 argc - opt_index, argv + opt_index))
 	return EXIT_FAILURE;
 
+    ctx->addresses = g_hash_table_new_full (g_str_hash, g_str_equal,
+					    _talloc_free_for_g_hash, NULL);
+
     ret = do_search_messages (ctx);
 
+    g_hash_table_unref (ctx->addresses);
+
+
     _notmuch_search_cleanup (ctx);
 
     return ret ? EXIT_FAILURE : EXIT_SUCCESS;

test/T095-address.sh

@@ -0,0 +1,99 @@
+#!/usr/bin/env bash
+test_description='"notmuch address" in several variants'
+. ./test-lib.sh
+
+add_email_corpus
+
+test_begin_subtest "--output=sender"
+notmuch address --output=sender '*' >OUTPUT
+cat <<EOF >EXPECTED
+François Boulogne <boulogne.f@gmail.com>
+Olivier Berger <olivier.berger@it-sudparis.eu>
+Chris Wilson <chris@chris-wilson.co.uk>
+Carl Worth <cworth@cworth.org>
+Alexander Botero-Lowry <alex.boterolowry@gmail.com>
+Keith Packard <keithp@keithp.com>
+Jjgod Jiang <gzjjgod@gmail.com>
+Rolland Santimano <rollandsantimano@yahoo.com>
+Jan Janak <jan@ryngle.com>
+Stewart Smith <stewart@flamingspork.com>
+Lars Kellogg-Stedman <lars@seas.harvard.edu>
+Alex Botero-Lowry <alex.boterolowry@gmail.com>
+Ingmar Vanhassel <ingmar@exherbo.org>
+Aron Griffis <agriffis@n01se.net>
+Adrian Perez de Castro <aperez@igalia.com>
+Israel Herraiz <isra@herraiz.org>
+Mikhail Gusarov <dottedmag@dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=sender --format=json"
+notmuch address --output=sender --format=json '*' >OUTPUT
+cat <<EOF >EXPECTED
+[{"name": "François Boulogne", "address": "boulogne.f@gmail.com", "name-addr": "François Boulogne <boulogne.f@gmail.com>"},
+{"name": "Olivier Berger", "address": "olivier.berger@it-sudparis.eu", "name-addr": "Olivier Berger <olivier.berger@it-sudparis.eu>"},
+{"name": "Chris Wilson", "address": "chris@chris-wilson.co.uk", "name-addr": "Chris Wilson <chris@chris-wilson.co.uk>"},
+{"name": "Carl Worth", "address": "cworth@cworth.org", "name-addr": "Carl Worth <cworth@cworth.org>"},
+{"name": "Alexander Botero-Lowry", "address": "alex.boterolowry@gmail.com", "name-addr": "Alexander Botero-Lowry <alex.boterolowry@gmail.com>"},
+{"name": "Keith Packard", "address": "keithp@keithp.com", "name-addr": "Keith Packard <keithp@keithp.com>"},
+{"name": "Jjgod Jiang", "address": "gzjjgod@gmail.com", "name-addr": "Jjgod Jiang <gzjjgod@gmail.com>"},
+{"name": "Rolland Santimano", "address": "rollandsantimano@yahoo.com", "name-addr": "Rolland Santimano <rollandsantimano@yahoo.com>"},
+{"name": "Jan Janak", "address": "jan@ryngle.com", "name-addr": "Jan Janak <jan@ryngle.com>"},
+{"name": "Stewart Smith", "address": "stewart@flamingspork.com", "name-addr": "Stewart Smith <stewart@flamingspork.com>"},
+{"name": "Lars Kellogg-Stedman", "address": "lars@seas.harvard.edu", "name-addr": "Lars Kellogg-Stedman <lars@seas.harvard.edu>"},
+{"name": "Alex Botero-Lowry", "address": "alex.boterolowry@gmail.com", "name-addr": "Alex Botero-Lowry <alex.boterolowry@gmail.com>"},
+{"name": "Ingmar Vanhassel", "address": "ingmar@exherbo.org", "name-addr": "Ingmar Vanhassel <ingmar@exherbo.org>"},
+{"name": "Aron Griffis", "address": "agriffis@n01se.net", "name-addr": "Aron Griffis <agriffis@n01se.net>"},
+{"name": "Adrian Perez de Castro", "address": "aperez@igalia.com", "name-addr": "Adrian Perez de Castro <aperez@igalia.com>"},
+{"name": "Israel Herraiz", "address": "isra@herraiz.org", "name-addr": "Israel Herraiz <isra@herraiz.org>"},
+{"name": "Mikhail Gusarov", "address": "dottedmag@dottedmag.net", "name-addr": "Mikhail Gusarov <dottedmag@dottedmag.net>"}]
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients"
+notmuch address --output=recipients '*' >OUTPUT
+cat <<EOF >EXPECTED
+Allan McRae <allan@archlinux.org>
+"Discussion about the Arch User Repository (AUR)" <aur-general@archlinux.org>
+olivier.berger@it-sudparis.eu
+notmuch@notmuchmail.org
+notmuch <notmuch@notmuchmail.org>
+Keith Packard <keithp@keithp.com>
+Mikhail Gusarov <dottedmag@dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=sender --output=recipients"
+notmuch address --output=sender --output=recipients '*' >OUTPUT
+cat <<EOF >EXPECTED
+François Boulogne <boulogne.f@gmail.com>
+Allan McRae <allan@archlinux.org>
+"Discussion about the Arch User Repository (AUR)" <aur-general@archlinux.org>
+Olivier Berger <olivier.berger@it-sudparis.eu>
+olivier.berger@it-sudparis.eu
+Chris Wilson <chris@chris-wilson.co.uk>
+notmuch@notmuchmail.org
+Carl Worth <cworth@cworth.org>
+Alexander Botero-Lowry <alex.boterolowry@gmail.com>
+Keith Packard <keithp@keithp.com>
+Jjgod Jiang <gzjjgod@gmail.com>
+Rolland Santimano <rollandsantimano@yahoo.com>
+Jan Janak <jan@ryngle.com>
+Stewart Smith <stewart@flamingspork.com>
+Lars Kellogg-Stedman <lars@seas.harvard.edu>
+notmuch <notmuch@notmuchmail.org>
+Alex Botero-Lowry <alex.boterolowry@gmail.com>
+Ingmar Vanhassel <ingmar@exherbo.org>
+Aron Griffis <agriffis@n01se.net>
+Adrian Perez de Castro <aperez@igalia.com>
+Israel Herraiz <isra@herraiz.org>
+Mikhail Gusarov <dottedmag@dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "without --output"
+notmuch address '*' >OUTPUT
+# Use EXPECTED from previous subtest
+test_expect_equal_file OUTPUT EXPECTED
+
+test_done