--- /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 2677C431FDF\r
+ for <notmuch@notmuchmail.org>; Thu, 30 Oct 2014 17:00:12 -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 NcJ1EEB2t2CV for <notmuch@notmuchmail.org>;\r
+ Thu, 30 Oct 2014 17:00:06 -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 0192A431E84\r
+ for <notmuch@notmuchmail.org>; Thu, 30 Oct 2014 16:59:49 -0700 (PDT)\r
+Received: from localhost (unknown [192.168.200.7])\r
+ by max.feld.cvut.cz (Postfix) with ESMTP id 654CB5CCFF6\r
+ for <notmuch@notmuchmail.org>; Fri, 31 Oct 2014 00:59:48 +0100 (CET)\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 BU1HWu43zUQ7 for <notmuch@notmuchmail.org>;\r
+ Fri, 31 Oct 2014 00:59:44 +0100 (CET)\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 2E5B35CCFFC\r
+ for <notmuch@notmuchmail.org>; Fri, 31 Oct 2014 00:59:41 +0100 (CET)\r
+Received: from wsh by steelpick.2x.cz with local (Exim 4.84)\r
+ (envelope-from <sojkam1@fel.cvut.cz>)\r
+ id 1Xjzcs-0005bg-Th; Fri, 31 Oct 2014 00:59:34 +0100\r
+From: Michal Sojka <sojkam1@fel.cvut.cz>\r
+To: notmuch@notmuchmail.org\r
+Subject: [PATCH v5 7/7] cli: search: Add --filter-by option to configure\r
+ address filtering\r
+Date: Fri, 31 Oct 2014 00:59:33 +0100\r
+Message-Id: <1414713573-21461-8-git-send-email-sojkam1@fel.cvut.cz>\r
+X-Mailer: git-send-email 2.1.1\r
+In-Reply-To: <1414713573-21461-1-git-send-email-sojkam1@fel.cvut.cz>\r
+References: <1414713573-21461-1-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: Fri, 31 Oct 2014 00:00:12 -0000\r
+\r
+This option allows to configure the criterion for duplicate address\r
+filtering. Without this option, all unique combinations of name and\r
+address parts are printed. This option allows to filter the output\r
+more, for example to only contain unique address parts.\r
+---\r
+ completion/notmuch-completion.bash | 6 +++-\r
+ completion/notmuch-completion.zsh | 3 +-\r
+ doc/man1/notmuch-search.rst | 39 ++++++++++++++++++++++-\r
+ notmuch-search.c | 51 ++++++++++++++++++++++++++++--\r
+ test/T095-search-filter-by.sh | 64 ++++++++++++++++++++++++++++++++++++++\r
+ 5 files changed, 158 insertions(+), 5 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 39cd829..b625b02 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=( $( compgen -W "nameaddr name addr addrfold nameaddrfold" -- "${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 d7e5a5e..c1ccc32 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 count))'\r
++ '--output=[select what to output]:output:((summary threads messages files tags sender recipients count))' \\r
++ '--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"))'\r
+ }\r
+ \r
+ _notmuch()\r
+diff --git a/doc/man1/notmuch-search.rst b/doc/man1/notmuch-search.rst\r
+index ec89200..3a5556b 100644\r
+--- a/doc/man1/notmuch-search.rst\r
++++ b/doc/man1/notmuch-search.rst\r
+@@ -85,7 +85,8 @@ 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
+- Duplicate addresses are filtered out.\r
++ Duplicate addresses are filtered out. Filtering can be\r
++ configured 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
+@@ -158,6 +159,42 @@ 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=``\ (**nameaddr**\ \|\ **name** \|\ **addr**\ \|\ **addrfold**\ \|\ **nameaddrfold**\)\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 the two addresses are\r
++ compared and this can be controlled with the following\r
++ keywords:\r
++\r
++ **nameaddr** means that both name and address parts are\r
++ compared in case-sensitive manner. Therefore, all same looking\r
++ addresses strings are considered duplicate. This is the\r
++ default.\r
++\r
++ **name** means that only the name part is compared (in\r
++ case-sensitive manner). For example, the addresses "John Doe\r
++ <me@example.com>" and "John Doe <john@doe.name>" will be\r
++ considered duplicate.\r
++\r
++ **addr** means that only 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 like **addr**, but comparison is done in\r
++ canse-insensitive 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
++ **nameaddrfold** is like **nameaddr**, but address comparison\r
++ is done in canse-insensitive manner. For example, the\r
++ addresses "John Doe <john@example.com>" and "John Doe\r
++ <JOHN@EXAMPLE.COM>" will be considered duplicate.\r
++\r
+ EXIT STATUS\r
+ ===========\r
+ \r
+diff --git a/notmuch-search.c b/notmuch-search.c\r
+index 15527c4..8bc80d3 100644\r
+--- a/notmuch-search.c\r
++++ b/notmuch-search.c\r
+@@ -35,6 +35,14 @@ typedef enum {\r
+ \r
+ #define OUTPUT_ADDRESS_FLAGS (OUTPUT_SENDER | OUTPUT_RECIPIENTS | OUTPUT_COUNT)\r
+ \r
++typedef enum {\r
++ FILTER_BY_NAMEADDR = 0,\r
++ FILTER_BY_NAME,\r
++ FILTER_BY_ADDR,\r
++ FILTER_BY_ADDRFOLD,\r
++ FILTER_BY_NAMEADDRFOLD,\r
++} filter_by_t;\r
++\r
+ typedef struct {\r
+ sprinter_t *format;\r
+ notmuch_query_t *query;\r
+@@ -43,6 +51,7 @@ typedef struct {\r
+ int offset;\r
+ int limit;\r
+ int dupe;\r
++ filter_by_t filter_by;\r
+ } search_options_t;\r
+ \r
+ typedef struct {\r
+@@ -231,7 +240,7 @@ do_search_threads (search_options_t *opt)\r
+ return 0;\r
+ }\r
+ \r
+-/* Returns TRUE iff name and addr is duplicate. */\r
++/* Returns TRUE iff name and/or addr is considered duplicate. */\r
+ static notmuch_bool_t\r
+ is_duplicate (const search_options_t *opt, GHashTable *addrs, const char *name, const char *addr)\r
+ {\r
+@@ -239,7 +248,32 @@ is_duplicate (const search_options_t *opt, GHashTable *addrs, const char *name,\r
+ char *key;\r
+ mailbox_t *mailbox;\r
+ \r
+- key = talloc_asprintf (opt->format, "%s <%s>", name, addr);\r
++ if (opt->filter_by == FILTER_BY_ADDRFOLD ||\r
++ opt->filter_by == FILTER_BY_NAMEADDRFOLD) {\r
++ gchar *folded = g_utf8_casefold (addr, -1);\r
++ addr = talloc_strdup (opt->format, folded);\r
++ g_free (folded);\r
++ }\r
++ switch (opt->filter_by) {\r
++ case FILTER_BY_NAMEADDR:\r
++ case FILTER_BY_NAMEADDRFOLD:\r
++ key = talloc_asprintf (opt->format, "%s <%s>", name, addr);\r
++ break;\r
++ case FILTER_BY_NAME:\r
++ key = talloc_strdup (opt->format, name); /* !name results in !key */\r
++ break;\r
++ case FILTER_BY_ADDR:\r
++ case FILTER_BY_ADDRFOLD:\r
++ key = talloc_strdup (opt->format, addr);\r
++ break;\r
++ default:\r
++ INTERNAL_ERROR("invalid --filter-by flags");\r
++ }\r
++\r
++ if (opt->filter_by == FILTER_BY_ADDRFOLD ||\r
++ opt->filter_by == FILTER_BY_NAMEADDRFOLD)\r
++ talloc_free ((char*)addr);\r
++\r
+ if (! key)\r
+ return FALSE;\r
+ \r
+@@ -523,6 +557,7 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ .offset = 0,\r
+ .limit = -1, /* unlimited */\r
+ .dupe = -1,\r
++ .filter_by = FILTER_BY_NAMEADDR,\r
+ };\r
+ char *query_str;\r
+ int opt_index, ret;\r
+@@ -567,6 +602,13 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ { NOTMUCH_OPT_INT, &opt.offset, "offset", 'O', 0 },\r
+ { NOTMUCH_OPT_INT, &opt.limit, "limit", 'L', 0 },\r
+ { NOTMUCH_OPT_INT, &opt.dupe, "duplicate", 'D', 0 },\r
++ { NOTMUCH_OPT_KEYWORD, &opt.filter_by, "filter-by", 'b',\r
++ (notmuch_keyword_t []){ { "nameaddr", FILTER_BY_NAMEADDR },\r
++ { "name", FILTER_BY_NAME },\r
++ { "addr", FILTER_BY_ADDR },\r
++ { "addrfold", FILTER_BY_ADDRFOLD },\r
++ { "nameaddrfold", FILTER_BY_NAMEADDRFOLD },\r
++ { 0, 0 } } },\r
+ { 0, 0, 0, 0, 0 }\r
+ };\r
+ \r
+@@ -577,6 +619,11 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])\r
+ if (! opt.output)\r
+ opt.output = OUTPUT_SUMMARY;\r
+ \r
++ if (opt.filter_by && !(opt.output & OUTPUT_ADDRESS_FLAGS)) {\r
++ fprintf (stderr, "Error: --filter-by can only be used with address output.\n");\r
++ return EXIT_FAILURE;\r
++ }\r
++\r
+ switch (format_sel) {\r
+ case NOTMUCH_FORMAT_TEXT:\r
+ opt.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..97d9a9b\r
+--- /dev/null\r
++++ b/test/T095-search-filter-by.sh\r
+@@ -0,0 +1,64 @@\r
++#!/usr/bin/env bash\r
++test_description='duplicite address filtering in "notmuch search --output=recipients"'\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
++EOF\r
++test_expect_equal_file OUTPUT EXPECTED\r
++\r
++test_begin_subtest "--output=recipients --filter-by=nameaddr"\r
++notmuch search --output=recipients --filter-by=nameaddr "*" >OUTPUT\r
++# The same as above\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
++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=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=nameaddrfold"\r
++notmuch search --output=recipients --filter-by=nameaddrfold "*" >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