[PATCH v4 5/6] cli: search: Add configurable way to filter out duplicate addresses

Michal Sojka sojkam1 at fel.cvut.cz
Mon Oct 27 07:50:54 PDT 2014


This adds an algorithm to filter out duplicate addresses from address
outputs (sender, receivers). The algorithm can be configured with
--filter-by command line option.

The code here is an extended version of a patch from Jani Nikula.
---
 completion/notmuch-completion.bash |  6 ++-
 completion/notmuch-completion.zsh  |  3 +-
 doc/man1/notmuch-search.rst        | 38 +++++++++++++++
 notmuch-search.c                   | 98 +++++++++++++++++++++++++++++++++++---
 test/T090-search-output.sh         | 87 +++++++++++++++++++++++++++++++++
 test/T095-search-filter-by.sh      | 64 +++++++++++++++++++++++++
 6 files changed, 288 insertions(+), 8 deletions(-)
 create mode 100755 test/T095-search-filter-by.sh

diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash
index cfbd389..6b6d43a 100644
--- a/completion/notmuch-completion.bash
+++ b/completion/notmuch-completion.bash
@@ -305,12 +305,16 @@ _notmuch_search()
 	    COMPREPLY=( $( compgen -W "true false flag all" -- "${cur}" ) )
 	    return
 	    ;;
+	--filter-by)
+	    COMPREPLY=( $( compgen -W "nameaddr name addr addrfold nameaddrfold" -- "${cur}" ) )
+	    return
+	    ;;
     esac
 
     ! $split &&
     case "${cur}" in
 	-*)
-	    local options="--format= --output= --sort= --offset= --limit= --exclude= --duplicate="
+	    local options="--format= --output= --sort= --offset= --limit= --exclude= --duplicate= --filter-by="
 	    compopt -o nospace
 	    COMPREPLY=( $(compgen -W "$options" -- ${cur}) )
 	    ;;
diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-completion.zsh
index 3e52a00..3e535df 100644
--- a/completion/notmuch-completion.zsh
+++ b/completion/notmuch-completion.zsh
@@ -53,7 +53,8 @@ _notmuch_search()
     '--max-threads=[display only the first x threads from the search results]:number of threads to show: ' \
     '--first=[omit the first x threads from the search results]:number of threads to omit: ' \
     '--sort=[sort results]:sorting:((newest-first\:"reverse chronological order" oldest-first\:"chronological order"))' \
-    '--output=[select what to output]:output:((summary threads messages files tags sender recipients))'
+    '--output=[select what to output]:output:((summary threads messages files tags sender recipients))' \
+    '--filter-by=[filter out duplicate addresses]:filter-by:((nameaddr\:"both name and address part" name\:"name part" addr\:"address part" addrfold\:"case-insensitive address part" nameaddrfold\:"name and case-insensitive address part"))'
 }
 
 _notmuch()
diff --git a/doc/man1/notmuch-search.rst b/doc/man1/notmuch-search.rst
index b6607c9..84af2da 100644
--- a/doc/man1/notmuch-search.rst
+++ b/doc/man1/notmuch-search.rst
@@ -85,6 +85,9 @@ Supported options for **search** include
             (--format=text0), as a JSON array (--format=json), or as
             an S-Expression list (--format=sexp).
 
+            Duplicate addresses are filtered out. Filtering can be
+            configured with the --filter-by option.
+
 	    Note: Searching for **sender** should be much faster than
 	    searching for **recipients**, because sender addresses are
 	    cached directly in the database whereas other addresses
@@ -151,6 +154,41 @@ Supported options for **search** include
         prefix. The prefix matches messages based on filenames. This
         option filters filenames of the matching messages.
 
+    ``--filter-by=``\ (**nameaddr**\ \|\ **name** \|\ **addr**\ \|\ **addrfold**\ \|\ **nameaddrfold**\)
+
+	Can be used with ``--output=sender`` or
+	``--output=recipients`` to filter out duplicate addresses. The
+	filtering algorithm receives a sequence of email addresses and
+	outputs the same sequence without the addresses that are
+	considered a duplicate of a previously output address. What is
+	considered a duplicate depends on how the two addresses are
+	compared and this can be controlled with the follwing flags:
+
+	**nameaddr** means that both name and address parts are
+	compared in case-sensitive manner. Therefore, all same looking
+	addresses strings are considered duplicate. This is the
+	default.
+
+	**name** means that only the name part is compared (in
+	case-sensitive manner). For example, the addresses "John Doe
+	<me at example.com>" and "John Doe <john at doe.name>" will be
+	considered duplicate.
+
+	**addr** means that only the address part is compared (in
+	case-sensitive manner). For example, the addresses "John Doe
+	<john at example.com>" and "Dr. John Doe <john at example.com>" will
+	be considered duplicate.
+
+	**addrfold** is like **addr**, but comparison is done in
+	canse-insensitive manner. For example, the addresses "John Doe
+	<john at example.com>" and "Dr. John Doe <JOHN at EXAMPLE.COM>" will
+	be considered duplicate.
+
+	**nameaddrfold** is like **nameaddr**, but address comparison
+	is done in canse-insensitive manner. For example, the
+	addresses "John Doe <john at example.com>" and "John Doe
+	<JOHN at EXAMPLE.COM>" will be considered duplicate.
+
 EXIT STATUS
 ===========
 
diff --git a/notmuch-search.c b/notmuch-search.c
index ce3bfb2..47aa979 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -34,6 +34,14 @@ typedef enum {
 
 #define OUTPUT_ADDRESS_FLAGS (OUTPUT_SENDER | OUTPUT_RECIPIENTS)
 
+typedef enum {
+    FILTER_BY_NAMEADDR = 0,
+    FILTER_BY_NAME,
+    FILTER_BY_ADDR,
+    FILTER_BY_ADDRFOLD,
+    FILTER_BY_NAMEADDRFOLD,
+} filter_by_t;
+
 typedef struct {
     sprinter_t *format;
     notmuch_query_t *query;
@@ -42,6 +50,7 @@ typedef struct {
     int offset;
     int limit;
     int dupe;
+    filter_by_t filter_by;
 } search_options_t;
 
 typedef struct {
@@ -229,6 +238,52 @@ do_search_threads (search_options_t *opt)
     return 0;
 }
 
+/* Returns TRUE iff name and/or addr is considered duplicite. */
+static notmuch_bool_t
+check_duplicite (const search_options_t *opt, GHashTable *addrs, const char *name, const char *addr)
+{
+    notmuch_bool_t duplicite;
+    char *key;
+
+    if (opt->filter_by == FILTER_BY_ADDRFOLD ||
+	opt->filter_by == FILTER_BY_NAMEADDRFOLD) {
+	gchar *folded = g_utf8_casefold (addr, -1);
+	addr = talloc_strdup (opt->format, folded);
+	g_free (folded);
+    }
+    switch (opt->filter_by) {
+    case FILTER_BY_NAMEADDR:
+    case FILTER_BY_NAMEADDRFOLD:
+	key = talloc_asprintf (opt->format, "%s <%s>", name, addr);
+	break;
+    case FILTER_BY_NAME:
+	key = talloc_strdup (opt->format, name); /* !name results in !key */
+	break;
+    case FILTER_BY_ADDR:
+    case FILTER_BY_ADDRFOLD:
+	key = talloc_strdup (opt->format, addr);
+	break;
+    default:
+	INTERNAL_ERROR("invalid --filter-by flags");
+    }
+
+    if (opt->filter_by == FILTER_BY_ADDRFOLD ||
+	opt->filter_by == FILTER_BY_NAMEADDRFOLD)
+	talloc_free ((char*)addr);
+
+    if (! key)
+	return FALSE;
+
+    duplicite = g_hash_table_lookup_extended (addrs, key, NULL, NULL);
+
+    if (! duplicite)
+	g_hash_table_insert (addrs, key, NULL);
+    else
+	talloc_free (key);
+
+    return duplicite;
+}
+
 static void
 print_mailbox (const search_options_t *opt, const mailbox_t *mailbox)
 {
@@ -263,7 +318,8 @@ print_mailbox (const search_options_t *opt, const mailbox_t *mailbox)
 }
 
 static void
-process_address_list (const search_options_t *opt, InternetAddressList *list)
+process_address_list (const search_options_t *opt, GHashTable *addrs,
+		      InternetAddressList *list)
 {
     InternetAddress *address;
     int i;
@@ -279,7 +335,7 @@ process_address_list (const search_options_t *opt, InternetAddressList *list)
 	    if (group_list == NULL)
 		continue;
 
-	    process_address_list (opt, group_list);
+	    process_address_list (opt, addrs, group_list);
 	} else {
 	    InternetAddressMailbox *mailbox = INTERNET_ADDRESS_MAILBOX (address);
 	    mailbox_t mbx = {
@@ -287,13 +343,16 @@ process_address_list (const search_options_t *opt, InternetAddressList *list)
 		.addr = internet_address_mailbox_get_addr (mailbox),
 	    };
 
+	    if (check_duplicite (opt, addrs, mbx.name, mbx.addr))
+		continue;
+
 	    print_mailbox (opt, &mbx);
 	}
     }
 }
 
 static void
-process_address_header (const search_options_t *opt, const char *value)
+process_address_header (const search_options_t *opt, GHashTable *addrs, const char *value)
 {
     InternetAddressList *list;
 
@@ -304,7 +363,13 @@ process_address_header (const search_options_t *opt, const char *value)
     if (list == NULL)
 	return;
 
-    process_address_list (opt, list);
+    process_address_list (opt, addrs, list);
+}
+
+static void
+_my_talloc_free_for_g_hash (void *ptr)
+{
+    talloc_free (ptr);
 }
 
 static int
@@ -314,8 +379,13 @@ do_search_messages (search_options_t *opt)
     notmuch_messages_t *messages;
     notmuch_filenames_t *filenames;
     sprinter_t *format = opt->format;
+    GHashTable *addresses = NULL;
     int i;
 
+    if (opt->output & OUTPUT_ADDRESS_FLAGS)
+	addresses = g_hash_table_new_full (g_str_hash, g_str_equal,
+					   _my_talloc_free_for_g_hash, NULL);
+
     if (opt->offset < 0) {
 	opt->offset += notmuch_query_count_messages (opt->query);
 	if (opt->offset < 0)
@@ -363,7 +433,7 @@ do_search_messages (search_options_t *opt)
 		const char *addrs;
 
 		addrs = notmuch_message_get_header (message, "from");
-		process_address_header (opt, addrs);
+		process_address_header (opt, addresses, addrs);
 	    }
 
 	    if (opt->output & OUTPUT_RECIPIENTS) {
@@ -373,7 +443,7 @@ do_search_messages (search_options_t *opt)
 
 		for (j = 0; j < ARRAY_SIZE (hdrs); j++) {
 		    addrs = notmuch_message_get_header (message, hdrs[j]);
-		    process_address_header (opt, addrs);
+		    process_address_header (opt, addresses, addrs);
 		}
 	    }
 	}
@@ -381,6 +451,9 @@ do_search_messages (search_options_t *opt)
 	notmuch_message_destroy (message);
     }
 
+    if (addresses)
+	g_hash_table_unref (addresses);
+
     notmuch_messages_destroy (messages);
 
     format->end (format);
@@ -447,6 +520,7 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
 	.offset = 0,
 	.limit = -1, /* unlimited */
 	.dupe = -1,
+	.filter_by = FILTER_BY_NAMEADDR,
     };
     char *query_str;
     int opt_index, ret;
@@ -490,6 +564,13 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
 	{ NOTMUCH_OPT_INT, &opt.offset, "offset", 'O', 0 },
 	{ NOTMUCH_OPT_INT, &opt.limit, "limit", 'L', 0  },
 	{ NOTMUCH_OPT_INT, &opt.dupe, "duplicate", 'D', 0  },
+	{ NOTMUCH_OPT_KEYWORD, &opt.filter_by, "filter-by", 'b',
+	  (notmuch_keyword_t []){ { "nameaddr", FILTER_BY_NAMEADDR },
+				  { "name", FILTER_BY_NAME },
+				  { "addr", FILTER_BY_ADDR },
+				  { "addrfold", FILTER_BY_ADDRFOLD },
+				  { "nameaddrfold", FILTER_BY_NAMEADDRFOLD },
+				  { 0, 0 } } },
 	{ 0, 0, 0, 0, 0 }
     };
 
@@ -500,6 +581,11 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
     if (! opt.output)
 	opt.output = OUTPUT_SUMMARY;
 
+    if (opt.filter_by && !(opt.output & OUTPUT_ADDRESS_FLAGS)) {
+	fprintf (stderr, "Error: --filter-by can only be used with address output.\n");
+	return EXIT_FAILURE;
+    }
+
     switch (format_sel) {
     case NOTMUCH_FORMAT_TEXT:
 	opt.format = sprinter_text_create (config, stdout);
diff --git a/test/T090-search-output.sh b/test/T090-search-output.sh
index 947d572..841a721 100755
--- a/test/T090-search-output.sh
+++ b/test/T090-search-output.sh
@@ -387,6 +387,93 @@ cat <<EOF >EXPECTED
 EOF
 test_expect_equal_file OUTPUT EXPECTED
 
+test_begin_subtest "--output=sender"
+notmuch search --output=sender '*' >OUTPUT
+cat <<EOF >EXPECTED
+François Boulogne <boulogne.f at gmail.com>
+Olivier Berger <olivier.berger at it-sudparis.eu>
+Chris Wilson <chris at chris-wilson.co.uk>
+Carl Worth <cworth at cworth.org>
+Alexander Botero-Lowry <alex.boterolowry at gmail.com>
+Keith Packard <keithp at keithp.com>
+Jjgod Jiang <gzjjgod at gmail.com>
+Rolland Santimano <rollandsantimano at yahoo.com>
+Jan Janak <jan at ryngle.com>
+Stewart Smith <stewart at flamingspork.com>
+Lars Kellogg-Stedman <lars at seas.harvard.edu>
+Alex Botero-Lowry <alex.boterolowry at gmail.com>
+Ingmar Vanhassel <ingmar at exherbo.org>
+Aron Griffis <agriffis at n01se.net>
+Adrian Perez de Castro <aperez at igalia.com>
+Israel Herraiz <isra at herraiz.org>
+Mikhail Gusarov <dottedmag at dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=sender --format=json"
+notmuch search --output=sender --format=json '*' >OUTPUT
+cat <<EOF >EXPECTED
+[{"name": "François Boulogne", "address": "boulogne.f at gmail.com"},
+{"name": "Olivier Berger", "address": "olivier.berger at it-sudparis.eu"},
+{"name": "Chris Wilson", "address": "chris at chris-wilson.co.uk"},
+{"name": "Carl Worth", "address": "cworth at cworth.org"},
+{"name": "Alexander Botero-Lowry", "address": "alex.boterolowry at gmail.com"},
+{"name": "Keith Packard", "address": "keithp at keithp.com"},
+{"name": "Jjgod Jiang", "address": "gzjjgod at gmail.com"},
+{"name": "Rolland Santimano", "address": "rollandsantimano at yahoo.com"},
+{"name": "Jan Janak", "address": "jan at ryngle.com"},
+{"name": "Stewart Smith", "address": "stewart at flamingspork.com"},
+{"name": "Lars Kellogg-Stedman", "address": "lars at seas.harvard.edu"},
+{"name": "Alex Botero-Lowry", "address": "alex.boterolowry at gmail.com"},
+{"name": "Ingmar Vanhassel", "address": "ingmar at exherbo.org"},
+{"name": "Aron Griffis", "address": "agriffis at n01se.net"},
+{"name": "Adrian Perez de Castro", "address": "aperez at igalia.com"},
+{"name": "Israel Herraiz", "address": "isra at herraiz.org"},
+{"name": "Mikhail Gusarov", "address": "dottedmag at dottedmag.net"}]
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients"
+notmuch search --output=recipients '*' >OUTPUT
+cat <<EOF >EXPECTED
+Allan McRae <allan at archlinux.org>
+Discussion about the Arch User Repository (AUR) <aur-general at archlinux.org>
+olivier.berger at it-sudparis.eu
+notmuch at notmuchmail.org
+notmuch <notmuch at notmuchmail.org>
+Keith Packard <keithp at keithp.com>
+Mikhail Gusarov <dottedmag at dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=sender --output=recipients"
+notmuch search --output=sender --output=recipients '*' >OUTPUT
+cat <<EOF >EXPECTED
+François Boulogne <boulogne.f at gmail.com>
+Allan McRae <allan at archlinux.org>
+Discussion about the Arch User Repository (AUR) <aur-general at archlinux.org>
+Olivier Berger <olivier.berger at it-sudparis.eu>
+olivier.berger at it-sudparis.eu
+Chris Wilson <chris at chris-wilson.co.uk>
+notmuch at notmuchmail.org
+Carl Worth <cworth at cworth.org>
+Alexander Botero-Lowry <alex.boterolowry at gmail.com>
+Keith Packard <keithp at keithp.com>
+Jjgod Jiang <gzjjgod at gmail.com>
+Rolland Santimano <rollandsantimano at yahoo.com>
+Jan Janak <jan at ryngle.com>
+Stewart Smith <stewart at flamingspork.com>
+Lars Kellogg-Stedman <lars at seas.harvard.edu>
+notmuch <notmuch at notmuchmail.org>
+Alex Botero-Lowry <alex.boterolowry at gmail.com>
+Ingmar Vanhassel <ingmar at exherbo.org>
+Aron Griffis <agriffis at n01se.net>
+Adrian Perez de Castro <aperez at igalia.com>
+Israel Herraiz <isra at herraiz.org>
+Mikhail Gusarov <dottedmag at dottedmag.net>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
 test_begin_subtest "sanitize output for quoted-printable line-breaks in author and subject"
 add_message "[subject]='two =?ISO-8859-1?Q?line=0A_subject?=
 	headers'"
diff --git a/test/T095-search-filter-by.sh b/test/T095-search-filter-by.sh
new file mode 100755
index 0000000..97d9a9b
--- /dev/null
+++ b/test/T095-search-filter-by.sh
@@ -0,0 +1,64 @@
+#!/usr/bin/env bash
+test_description='duplicite address filtering in "notmuch search --output=recipients"'
+. ./test-lib.sh
+
+add_message '[to]="Real Name <foo at example.com>, Real Name <bar at example.com>"'
+add_message '[to]="Nickname <foo at example.com>"' '[cc]="Real Name <Bar at Example.COM>"'
+add_message '[to]="Nickname <foo at example.com>"' '[bcc]="Real Name <Bar at Example.COM>"'
+
+test_begin_subtest "--output=recipients"
+notmuch search --output=recipients "*" >OUTPUT
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Real Name <bar at example.com>
+Nickname <foo at example.com>
+Real Name <Bar at Example.COM>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=nameaddr"
+notmuch search --output=recipients --filter-by=nameaddr "*" >OUTPUT
+# The same as above
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Real Name <bar at example.com>
+Nickname <foo at example.com>
+Real Name <Bar at Example.COM>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=name"
+notmuch search --output=recipients --filter-by=name "*" >OUTPUT
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Nickname <foo at example.com>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=addr"
+notmuch search --output=recipients --filter-by=addr "*" >OUTPUT
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Real Name <bar at example.com>
+Real Name <Bar at Example.COM>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=addrfold"
+notmuch search --output=recipients --filter-by=addrfold "*" >OUTPUT
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Real Name <bar at example.com>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=nameaddrfold"
+notmuch search --output=recipients --filter-by=nameaddrfold "*" >OUTPUT
+cat <<EOF >EXPECTED
+Real Name <foo at example.com>
+Real Name <bar at example.com>
+Nickname <foo at example.com>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_done
-- 
2.1.1



More information about the notmuch mailing list