From 0a416552aee2805937bf81eda5d05c70858016b1 Mon Sep 17 00:00:00 2001 From: Michal Sojka Date: Fri, 31 Oct 2014 00:06:26 +0100 Subject: [PATCH] cli: address: Add --filter-by option to configure address filtering This option allows to configure the criterion for duplicate address filtering. Without this option, all unique combinations of name and address parts are printed. This option allows to filter the output more, for example to only contain unique address parts. --- completion/notmuch-completion.bash | 6 ++- completion/notmuch-completion.zsh | 3 +- doc/man1/notmuch-address.rst | 36 ++++++++++++++- notmuch-search.c | 51 +++++++++++++++++++-- test/T097-address-filter-by.sh | 73 ++++++++++++++++++++++++++++++ 5 files changed, 163 insertions(+), 6 deletions(-) create mode 100755 test/T097-address-filter-by.sh diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash index 39320f8d..5a7199e7 100644 --- a/completion/notmuch-completion.bash +++ b/completion/notmuch-completion.bash @@ -313,7 +313,7 @@ _notmuch_search() ! $split && case "${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}) ) ;; @@ -346,6 +346,10 @@ _notmuch_address() COMPREPLY=( $( compgen -W "true false flag all" -- "${cur}" ) ) return ;; + --filter-by) + COMPREPLY=( $( compgen -W "nameaddr name addr addrfold nameaddrfold" -- "${cur}" ) ) + return + ;; esac ! $split && diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-completion.zsh index 89685620..c5bad216 100644 --- a/completion/notmuch-completion.zsh +++ b/completion/notmuch-completion.zsh @@ -61,7 +61,8 @@ _notmuch_address() { _arguments -s : \ '--sort=[sort results]:sorting:((newest-first\:"reverse chronological order" oldest-first\:"chronological order"))' \ - '--output=[select what to output]:output:((sender recipients count))' + '--output=[select what to output]:output:((sender recipients count))' \ + '--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-address.rst b/doc/man1/notmuch-address.rst index 9570095b..14034249 100644 --- a/doc/man1/notmuch-address.rst +++ b/doc/man1/notmuch-address.rst @@ -11,7 +11,8 @@ DESCRIPTION =========== Search for messages matching the given search terms, and display the -addresses from them. Duplicate addresses are filtered out. +addresses from them. Duplicate addresses are filtered out. Filtering +can be configured with the --filter-by option. See **notmuch-search-terms(7)** for details of the supported syntax for . @@ -77,6 +78,39 @@ Supported options for **address** include **false** allows excluded messages to match search terms and appear in displayed results. + ``--filter-by=``\ (**nameaddr**\ \|\ **name** \|\ **addr**\ \|\ **addrfold**\ \|\ **nameaddrfold**\) + + Controls how 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: + + **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 + " and "John Doe " will be + considered duplicate. + + **addr** means that only the address part is compared (in + case-sensitive manner). For example, the addresses "John Doe + " and "Dr. John Doe " will + be considered duplicate. + + **addrfold** is like **addr**, but comparison is done in + canse-insensitive manner. For example, the addresses "John Doe + " and "Dr. John Doe " will + be considered duplicate. + + **nameaddrfold** is like **nameaddr**, but address comparison + is done in canse-insensitive manner. For example, the + addresses "John Doe " and "John Doe + " will be considered duplicate. + EXIT STATUS =========== diff --git a/notmuch-search.c b/notmuch-search.c index 14b9f01c..8116cae8 100644 --- a/notmuch-search.c +++ b/notmuch-search.c @@ -43,6 +43,14 @@ typedef enum { NOTMUCH_FORMAT_SEXP } format_sel_t; +typedef enum { + FILTER_BY_NAMEADDR = 0, + FILTER_BY_NAME, + FILTER_BY_ADDR, + FILTER_BY_ADDRFOLD, + FILTER_BY_NAMEADDRFOLD, +} filter_by_t; + typedef struct { notmuch_database_t *notmuch; format_sel_t format_sel; @@ -55,6 +63,7 @@ typedef struct { int limit; int dupe; GHashTable *addresses; + filter_by_t filter_by; } search_context_t; typedef struct { @@ -243,16 +252,44 @@ 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. */ +/* Returns TRUE iff name and/or addr is considered 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; + gchar *addrfold = NULL; mailbox_t *mailbox; - key = talloc_asprintf (ctx->format, "%s <%s>", name, addr); + if (ctx->filter_by == FILTER_BY_ADDRFOLD || + ctx->filter_by == FILTER_BY_NAMEADDRFOLD) + addrfold = g_utf8_casefold (addr, -1); + + switch (ctx->filter_by) { + case FILTER_BY_NAMEADDR: + key = talloc_asprintf (ctx->format, "%s <%s>", name, addr); + break; + case FILTER_BY_NAMEADDRFOLD: + key = talloc_asprintf (ctx->format, "%s <%s>", name, addrfold); + break; + case FILTER_BY_NAME: + key = talloc_strdup (ctx->format, name); /* !name results in !key */ + break; + case FILTER_BY_ADDR: + key = talloc_strdup (ctx->format, addr); + break; + case FILTER_BY_ADDRFOLD: + key = talloc_strdup (ctx->format, addrfold); + break; + default: + INTERNAL_ERROR("invalid --filter-by flags"); + } + + if (addrfold) + g_free (addrfold); + if (! key) return FALSE; @@ -727,10 +764,18 @@ notmuch_address_command (notmuch_config_t *config, int argc, char *argv[]) (notmuch_keyword_t []){ { "true", NOTMUCH_EXCLUDE_TRUE }, { "false", NOTMUCH_EXCLUDE_FALSE }, { 0, 0 } } }, + { NOTMUCH_OPT_KEYWORD, &ctx->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 } } }, { NOTMUCH_OPT_INHERIT, &common_options, NULL, 0, 0 }, { 0, 0, 0, 0, 0 } }; + ctx->filter_by = FILTER_BY_NAMEADDR, opt_index = parse_arguments (argc, argv, options, 1); if (opt_index < 0) return EXIT_FAILURE; diff --git a/test/T097-address-filter-by.sh b/test/T097-address-filter-by.sh new file mode 100755 index 00000000..544d8e80 --- /dev/null +++ b/test/T097-address-filter-by.sh @@ -0,0 +1,73 @@ +#!/usr/bin/env bash +test_description='duplicite address filtering in "notmuch address"' +. ./test-lib.sh + +add_message '[to]="John Doe , John Doe "' +add_message '[to]="\"Doe, John\" "' '[cc]="John Doe "' +add_message '[to]="\"Doe, John\" "' '[bcc]="John Doe "' + +test_begin_subtest "--output=recipients" +notmuch address --output=recipients "*" >OUTPUT +cat <EXPECTED +John Doe +John Doe +"Doe, John" +John Doe +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=nameaddr" +notmuch address --output=recipients --filter-by=nameaddr "*" >OUTPUT +# The same as above +cat <EXPECTED +John Doe +John Doe +"Doe, John" +John Doe +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=name" +notmuch address --output=recipients --filter-by=name "*" >OUTPUT +cat <EXPECTED +John Doe +"Doe, John" +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=addr" +notmuch address --output=recipients --filter-by=addr "*" >OUTPUT +cat <EXPECTED +John Doe +John Doe +John Doe +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=addrfold" +notmuch address --output=recipients --filter-by=addrfold "*" >OUTPUT +cat <EXPECTED +John Doe +John Doe +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=nameaddrfold" +notmuch address --output=recipients --filter-by=nameaddrfold "*" >OUTPUT +cat <EXPECTED +John Doe +John Doe +"Doe, John" +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_begin_subtest "--output=recipients --filter-by=nameaddrfold --output=count" +notmuch address --output=recipients --filter-by=nameaddrfold --output=count "*" | sort -n >OUTPUT +cat <EXPECTED +1 John Doe +2 "Doe, John" +3 John Doe +EOF +test_expect_equal_file OUTPUT EXPECTED + +test_done -- 2.39.2