--- /dev/null
+Return-Path: <sojkam1@fel.cvut.cz>\r
+X-Original-To: notmuch@notmuchmail.org\r
+Delivered-To: notmuch@notmuchmail.org\r
+Received: from localhost (localhost [127.0.0.1])\r
+ by olra.theworths.org (Postfix) with ESMTP id 91A25431FDC\r
+ for <notmuch@notmuchmail.org>; Sun, 12 Oct 2014 14:42:04 -0700 (PDT)\r
+X-Virus-Scanned: Debian amavisd-new at olra.theworths.org\r
+X-Spam-Flag: NO\r
+X-Spam-Score: -2.3\r
+X-Spam-Level: \r
+X-Spam-Status: No, score=-2.3 tagged_above=-999 required=5\r
+ tests=[RCVD_IN_DNSWL_MED=-2.3] autolearn=disabled\r
+Received: from olra.theworths.org ([127.0.0.1])\r
+ by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024)\r
+ with ESMTP id 88L-L+bd0e5d for <notmuch@notmuchmail.org>;\r
+ Sun, 12 Oct 2014 14:41:59 -0700 (PDT)\r
+Received: from max.feld.cvut.cz (max.feld.cvut.cz [147.32.192.36])\r
+ by olra.theworths.org (Postfix) with ESMTP id 90689431FDE\r
+ for <notmuch@notmuchmail.org>; Sun, 12 Oct 2014 14:41:52 -0700 (PDT)\r
+Received: from localhost (unknown [192.168.200.7])\r
+ by max.feld.cvut.cz (Postfix) with ESMTP id 3BE655CCF10\r
+ for <notmuch@notmuchmail.org>; Sun, 12 Oct 2014 23:41:50 +0200 (CEST)\r
+X-Virus-Scanned: IMAP STYX AMAVIS\r
+Received: from max.feld.cvut.cz ([192.168.200.1])\r
+ by localhost (styx.feld.cvut.cz [192.168.200.7]) (amavisd-new,\r
+ port 10044) with ESMTP id RUoNIur_7BCd for <notmuch@notmuchmail.org>;\r
+ Sun, 12 Oct 2014 23:41:46 +0200 (CEST)\r
+Received: from imap.feld.cvut.cz (imap.feld.cvut.cz [147.32.192.34])\r
+ by max.feld.cvut.cz (Postfix) with ESMTP id 463D35CCF22\r
+ for <notmuch@notmuchmail.org>; Sun, 12 Oct 2014 23:41:45 +0200 (CEST)\r
+Received: from wsh by steelpick.2x.cz with local (Exim 4.84)\r
+ (envelope-from <sojkam1@fel.cvut.cz>)\r
+ id 1XdQtb-0002CM-7J; Sun, 12 Oct 2014 23:41:43 +0200\r
+From: Michal Sojka <sojkam1@fel.cvut.cz>\r
+To: notmuch@notmuchmail.org\r
+Subject: [PATCH v3 4/4] cli: Add an option to filter our duplicate addresses\r
+Date: Sun, 12 Oct 2014 23:41:33 +0200\r
+Message-Id: <1413150093-8383-5-git-send-email-sojkam1@fel.cvut.cz>\r
+X-Mailer: git-send-email 2.1.1\r
+In-Reply-To: <1413150093-8383-1-git-send-email-sojkam1@fel.cvut.cz>\r
+References: <87zjd51phx.fsf@steelpick.2x.cz>\r
+ <1413150093-8383-1-git-send-email-sojkam1@fel.cvut.cz>\r
+X-BeenThere: notmuch@notmuchmail.org\r
+X-Mailman-Version: 2.1.13\r
+Precedence: list\r
+List-Id: "Use and development of the notmuch mail system."\r
+ <notmuch.notmuchmail.org>\r
+List-Unsubscribe: <http://notmuchmail.org/mailman/options/notmuch>,\r
+ <mailto:notmuch-request@notmuchmail.org?subject=unsubscribe>\r
+List-Archive: <http://notmuchmail.org/pipermail/notmuch>\r
+List-Post: <mailto:notmuch@notmuchmail.org>\r
+List-Help: <mailto:notmuch-request@notmuchmail.org?subject=help>\r
+List-Subscribe: <http://notmuchmail.org/mailman/listinfo/notmuch>,\r
+ <mailto:notmuch-request@notmuchmail.org?subject=subscribe>\r
+X-List-Received-Date: Sun, 12 Oct 2014 21:42:04 -0000\r
+\r
+This adds a --filter-by option to "notmuch search". It can be used to\r
+filter out duplicate addresses in --output=sender/receivers.\r
+\r
+The code here is an extended version of a patch from Jani Nikula.\r
+---\r
+ completion/notmuch-completion.bash | 6 ++-\r
+ completion/notmuch-completion.zsh | 3 +-\r
+ doc/man1/notmuch-search.rst | 32 +++++++++++++\r
+ notmuch-search.c | 93 +++++++++++++++++++++++++++++++++++---\r
+ test/T095-search-filter-by.sh | 55 ++++++++++++++++++++++\r
+ 5 files changed, 181 insertions(+), 8 deletions(-)\r
+ create mode 100755 test/T095-search-filter-by.sh\r
+\r
+diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash\r
+index cfbd389..41dd85b 100644\r
+--- a/completion/notmuch-completion.bash\r
++++ b/completion/notmuch-completion.bash\r
+@@ -305,12 +305,16 @@ _notmuch_search()\r
+ COMPREPLY=( $( compgen -W "true false flag all" -- "${cur}" ) )\r
+ return\r
+ ;;\r
++ --filter-by)\r
++ COMPREPLY=( $( compgen -W "addr addrfold name" -- "${cur}" ) )\r
++ return\r
++ ;;\r
+ esac\r
+ \r
+ ! $split &&\r
+ case "${cur}" in\r
+ -*)\r
+- local options="--format= --output= --sort= --offset= --limit= --exclude= --duplicate="\r
++ local options="--format= --output= --sort= --offset= --limit= --exclude= --duplicate= --filter-by="\r
+ compopt -o nospace\r
+ COMPREPLY=( $(compgen -W "$options" -- ${cur}) )\r
+ ;;\r
+diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-completion.zsh\r
+index 3e52a00..17b345f 100644\r
+--- a/completion/notmuch-completion.zsh\r
++++ b/completion/notmuch-completion.zsh\r
+@@ -53,7 +53,8 @@ _notmuch_search()\r
+ '--max-threads=[display only the first x threads from the search results]:number of threads to show: ' \\r
+ '--first=[omit the first x threads from the search results]:number of threads to omit: ' \\r
+ '--sort=[sort results]:sorting:((newest-first\:"reverse chronological order" oldest-first\:"chronological order"))' \\r
+- '--output=[select what to output]:output:((summary threads messages files tags sender recipients))'\r
++ '--output=[select what to output]:output:((summary threads messages files tags sender recipients))' \\r
++ '--filter-by=[filter out duplicate addresses]:filter-by:((addr\:"address part" addrfold\:"case-insensitive address part" name\:"name part"))'\r
+ }\r
+ \r
+ _notmuch()\r
+diff --git a/doc/man1/notmuch-search.rst b/doc/man1/notmuch-search.rst\r
+index c9d38b1..0fed76e 100644\r
+--- a/doc/man1/notmuch-search.rst\r
++++ b/doc/man1/notmuch-search.rst\r
+@@ -85,6 +85,9 @@ Supported options for **search** include\r
+ (--format=text0), as a JSON array (--format=json), or as\r
+ an S-Expression list (--format=sexp).\r
+ \r
++ Handling of duplicate addresses and/or names can be\r
++ controlled with the --filter-by option.\r
++\r
+ Note: Searching for **sender** should be much faster than\r
+ searching for **recipients**, because sender addresses are\r
+ cached directly in the database whereas other addresses\r
+@@ -151,6 +154,35 @@ Supported options for **search** include\r
+ prefix. The prefix matches messages based on filenames. This\r
+ option filters filenames of the matching messages.\r
+ \r
++ ``--filter-by=``\ (**addr**\ \|\ **addrfold**\ \|\ **name**)\r
++\r
++ Can be used with ``--output=sender`` or\r
++ ``--output=recipients`` to filter out duplicate addresses. The\r
++ filtering algorithm receives a sequence of email addresses and\r
++ outputs the same sequence without the addresses that are\r
++ considered a duplicate of a previously output address. What is\r
++ considered a duplicate depends on how two addresses are\r
++ compared and this can be controlled by the follwing flags:\r
++\r
++ **addr** means that the address part is compared in\r
++ case-sensitive manner. For example, the addresses "John Doe\r
++ <john@example.com>" and "Dr. John Doe <john@example.com>" will\r
++ be considered duplicate.\r
++\r
++ **addrfold** is similar to **addr**, but in addition to it\r
++ case folding is performed before comparison. For example, the\r
++ addresses "John Doe <john@example.com>" and "Dr. John Doe\r
++ <JOHN@EXAMPLE.COM>" will be considered duplicate.\r
++\r
++ **name** means that the name part is compared in case-sensitive\r
++ manner. For example, the addresses "John Doe <me@example.com>"\r
++ and "John Doe <john@doe.name>" will be considered duplicate.\r
++\r
++ This option can be given multiple times to combine the effects\r
++ of the flags. For example,\r
++ ``--filter-by=name --filter-by=addr`` will print unique\r
++ case-sensitive combinations of both name and address parts.\r
++\r
+ EXIT STATUS\r
+ ===========\r
+ \r
+diff --git a/notmuch-search.c b/notmuch-search.c\r
+index 74588f8..df678ad 100644\r
+--- a/notmuch-search.c\r
++++ b/notmuch-search.c\r
+@@ -33,6 +33,12 @@ typedef enum {\r
+ OUTPUT_ADDRESSES = OUTPUT_SENDER | OUTPUT_RECIPIENTS,\r
+ } output_t;\r
+ \r
++typedef enum {\r
++ FILTER_FLAG_ADDR = 1 << 0,\r
++ FILTER_FLAG_NAME = 1 << 1,\r
++ FILTER_FLAG_AFOLD = 1 << 2,\r
++} filter_flag_t;\r
++\r
+ typedef struct {\r
+ sprinter_t *format;\r
+ notmuch_query_t *query;\r
+@@ -41,6 +47,7 @@ typedef struct {\r
+ int offset;\r
+ int limit;\r
+ int dupe;\r
++ filter_flag_t filter_flags;\r
+ } search_options_t;\r
+ \r
+ /* Return two stable query strings that identify exactly the matched\r
+@@ -223,8 +230,54 @@ do_search_threads (search_options_t *o)\r
+ return 0;\r
+ }\r
+ \r
++/* Returns TRUE iff name and/or addr is considered duplicite. */\r
++static notmuch_bool_t\r
++check_duplicite (const search_options_t *o, GHashTable *addrs, const char *name, const char *addr)\r
++{\r
++ notmuch_bool_t duplicite;\r
++ char *key;\r
++\r
++ if (o->filter_flags == 0)\r
++ return FALSE;\r
++\r
++ if (o->filter_flags & FILTER_FLAG_AFOLD) {\r
++ gchar *folded = g_utf8_casefold (addr, -1);\r
++ addr = talloc_strdup (o->format, folded);\r
++ g_free (folded);\r
++ }\r
++ switch (o->filter_flags & (FILTER_FLAG_ADDR | FILTER_FLAG_NAME)) {\r
++ case FILTER_FLAG_NAME:\r
++ key = talloc_strdup (o->format, name); /* !name results in !key */\r
++ break;\r
++ case FILTER_FLAG_ADDR:\r
++ key = talloc_strdup (o->format, addr);\r
++ break;\r
++ case FILTER_FLAG_NAME | FILTER_FLAG_ADDR:\r
++ key = talloc_asprintf (o->format, "%s <%s>", name, addr);\r
++ break;\r
++ default:\r
++ INTERNAL_ERROR("invalid --filter_by flags");\r
++ }\r
++\r
++ if (o->filter_flags & FILTER_FLAG_AFOLD)\r
++ talloc_free ((char*)addr);\r
++\r
++ if (! key)\r
++ return FALSE;\r
++\r
++ duplicite = g_hash_table_lookup_extended (addrs, key, NULL, NULL);\r
++\r
++ if (!duplicite)\r
++ g_hash_table_insert (addrs, key, NULL);\r
++ else\r
++ talloc_free (key);\r
++\r
++ return duplicite;\r
++}\r
++\r
+ static void\r
+-print_address_list (const search_options_t *o, InternetAddressList *list)\r
++print_address_list (const search_options_t *o, GHashTable *addrs,\r
++ InternetAddressList *list)\r
+ {\r
+ InternetAddress *address;\r
+ int i;\r
+@@ -240,7 +293,7 @@ print_address_list (const search_options_t *o, InternetAddressList *list)\r
+ if (group_list == NULL)\r
+ continue;\r
+ \r
+- print_address_list (o, group_list);\r
++ print_address_list (o, addrs, group_list);\r
+ } else {\r
+ InternetAddressMailbox *mailbox;\r
+ const char *name;\r
+@@ -252,6 +305,9 @@ print_address_list (const search_options_t *o, InternetAddressList *list)\r
+ name = internet_address_get_name (address);\r
+ addr = internet_address_mailbox_get_addr (mailbox);\r
+ \r
++ if (check_duplicite (o, addrs, name, addr))\r
++ continue;\r
++\r
+ if (name && *name)\r
+ full_address = talloc_asprintf (o->format, "%s <%s>", name, addr);\r
+ else\r
+@@ -270,7 +326,7 @@ print_address_list (const search_options_t *o, InternetAddressList *list)\r
+ }\r
+ \r
+ static void\r
+-print_address_string (const search_options_t *o, const char *recipients)\r
++print_address_string (const search_options_t *o, GHashTable *addrs, const char *recipients)\r
+ {\r
+ InternetAddressList *list;\r
+ \r
+@@ -281,7 +337,13 @@ print_address_string (const search_options_t *o, const char *recipients)\r
+ if (list == NULL)\r
+ return;\r
+ \r
+- print_address_list (o, list);\r
++ print_address_list (o, addrs, list);\r
++}\r
++\r
++static void\r
++_my_talloc_free_for_g_hash (void *ptr)\r
++{\r
++ talloc_free (ptr);\r
+ }\r
+ \r
+ static int\r
+@@ -291,8 +353,13 @@ do_search_messages (search_options_t *o)\r
+ notmuch_messages_t *messages;\r
+ notmuch_filenames_t *filenames;\r
+ sprinter_t *format = o->format;\r
++ GHashTable *addresses = NULL;\r
+ int i;\r
+ \r
++ if (o->output & OUTPUT_ADDRESSES)\r
++ addresses = g_hash_table_new_full (g_str_hash, g_str_equal,\r
++ _my_talloc_free_for_g_hash, NULL);\r
++\r
+ if (o->offset < 0) {\r
+ o->offset += notmuch_query_count_messages (o->query);\r
+ if (o->offset < 0)\r
+@@ -340,7 +407,7 @@ do_search_messages (search_options_t *o)\r
+ const char *addrs;\r
+ \r
+ addrs = notmuch_message_get_header (message, "from");\r
+- print_address_string (o, addrs);\r
++ print_address_string (o, addresses, addrs);\r
+ }\r
+ \r
+ if (o->output & OUTPUT_RECIPIENTS) {\r
+@@ -350,7 +417,7 @@ do_search_messages (search_options_t *o)\r
+ \r
+ for (j = 0; j < ARRAY_SIZE (hdrs); j++) {\r
+ addrs = notmuch_message_get_header (message, hdrs[j]);\r
+- print_address_string (o, addrs);\r
++ print_address_string (o, addresses, addrs);\r
+ }\r
+ }\r
+ }\r
+@@ -358,6 +425,9 @@ do_search_messages (search_options_t *o)\r
+ notmuch_message_destroy (message);\r
+ }\r
+ \r
++ if (addresses)\r
++ g_hash_table_unref (addresses);\r
++\r
+ notmuch_messages_destroy (messages);\r
+ \r
+ format->end (format);\r
+@@ -423,6 +493,7 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ .offset = 0,\r
+ .limit = -1, /* unlimited */\r
+ .dupe = -1,\r
++ .filter_flags = 0,\r
+ };\r
+ char *query_str;\r
+ int opt_index, ret;\r
+@@ -466,6 +537,11 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ { NOTMUCH_OPT_INT, &o.offset, "offset", 'O', 0 },\r
+ { NOTMUCH_OPT_INT, &o.limit, "limit", 'L', 0 },\r
+ { NOTMUCH_OPT_INT, &o.dupe, "duplicate", 'D', 0 },\r
++ { NOTMUCH_OPT_KEYWORD_FLAGS, &o.filter_flags, "filter-by", 'b',\r
++ (notmuch_keyword_t []){ { "name", FILTER_FLAG_NAME },\r
++ { "addr", FILTER_FLAG_ADDR },\r
++ { "addrfold", FILTER_FLAG_ADDR | FILTER_FLAG_AFOLD },\r
++ { 0, 0 } } },\r
+ { 0, 0, 0, 0, 0 }\r
+ };\r
+ \r
+@@ -476,6 +552,11 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ if (! o.output)\r
+ o.output = OUTPUT_SUMMARY;\r
+ \r
++ if (o.filter_flags && (o.output & ~OUTPUT_ADDRESSES)) {\r
++ fprintf (stderr, "Error: --filter_flag can only be used with address output.\n");\r
++ return EXIT_FAILURE;\r
++ }\r
++\r
+ switch (format_sel) {\r
+ case NOTMUCH_FORMAT_TEXT:\r
+ o.format = sprinter_text_create (config, stdout);\r
+diff --git a/test/T095-search-filter-by.sh b/test/T095-search-filter-by.sh\r
+new file mode 100755\r
+index 0000000..20d6a34\r
+--- /dev/null\r
++++ b/test/T095-search-filter-by.sh\r
+@@ -0,0 +1,55 @@\r
++#!/usr/bin/env bash\r
++test_description='address deduplication in "notmuch search --output=addresses"'\r
++. ./test-lib.sh\r
++\r
++add_message '[to]="Real Name <foo@example.com>, Real Name <bar@example.com>"'\r
++add_message '[to]="Nickname <foo@example.com>"' '[cc]="Real Name <Bar@Example.COM>"'\r
++add_message '[to]="Nickname <foo@example.com>"' '[bcc]="Real Name <Bar@Example.COM>"'\r
++\r
++test_begin_subtest "--output=recipients"\r
++notmuch search --output=recipients "*" >OUTPUT\r
++cat <<EOF >EXPECTED\r
++Real Name <foo@example.com>\r
++Real Name <bar@example.com>\r
++Nickname <foo@example.com>\r
++Real Name <Bar@Example.COM>\r
++Nickname <foo@example.com>\r
++Real Name <Bar@Example.COM>\r
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_begin_subtest "--output=recipients --filter-by=addr"\r
++notmuch search --output=recipients --filter-by=addr "*" >OUTPUT\r
++cat <<EOF >EXPECTED\r
++Real Name <foo@example.com>\r
++Real Name <bar@example.com>\r
++Real Name <Bar@Example.COM>\r
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_begin_subtest "--output=recipients --filter-by=addrfold"\r
++notmuch search --output=recipients --filter-by=addrfold "*" >OUTPUT\r
++cat <<EOF >EXPECTED\r
++Real Name <foo@example.com>\r
++Real Name <bar@example.com>\r
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_begin_subtest "--output=recipients --filter-by=name"\r
++notmuch search --output=recipients --filter-by=name "*" >OUTPUT\r
++cat <<EOF >EXPECTED\r
++Real Name <foo@example.com>\r
++Nickname <foo@example.com>\r
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_begin_subtest "--output=recipients --filter-by=name --filter-by=addrfold"\r
++notmuch search --output=recipients --filter-by=name --filter-by=addrfold "*" >OUTPUT\r
++cat <<EOF >EXPECTED\r
++Real Name <foo@example.com>\r
++Real Name <bar@example.com>\r
++Nickname <foo@example.com>\r
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_done\r
+-- \r
+2.1.1\r
+\r
projects / notmuch-archives.git / commitdiff