[PATCH v6 7/7] cli: search: Add --filter-by option to configure address filtering

Michal Sojka sojkam1 at fel.cvut.cz
Fri Oct 31 14:54:01 PDT 2014


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-search.rst        | 39 +++++++++++++++++++-
 notmuch-search.c                   | 53 +++++++++++++++++++++++++--
 test/T095-search-filter-by.sh      | 73 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 169 insertions(+), 5 deletions(-)
 create mode 100755 test/T095-search-filter-by.sh

diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash
index 39cd829..b625b02 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 d7e5a5e..c1ccc32 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 count))'
+    '--output=[select what to output]:output:((summary threads messages files tags 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-search.rst b/doc/man1/notmuch-search.rst
index ec89200..3a5556b 100644
--- a/doc/man1/notmuch-search.rst
+++ b/doc/man1/notmuch-search.rst
@@ -85,7 +85,8 @@ 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.
+            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
@@ -158,6 +159,42 @@ 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 following
+	keywords:
+
+	**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 4b39dfc..a350f06 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -35,6 +35,14 @@ typedef enum {
 
 #define OUTPUT_ADDRESS_FLAGS (OUTPUT_SENDER | OUTPUT_RECIPIENTS | OUTPUT_COUNT)
 
+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;
@@ -43,6 +51,7 @@ typedef struct {
     int offset;
     int limit;
     int dupe;
+    filter_by_t filter_by;
 } search_options_t;
 
 typedef struct {
@@ -231,15 +240,42 @@ do_search_threads (search_options_t *opt)
     return 0;
 }
 
-/* Returns TRUE iff name and addr is duplicate. */
+/* Returns TRUE iff name and/or addr is considered duplicate. */
 static notmuch_bool_t
 is_duplicate (const search_options_t *opt, GHashTable *addrs, const char *name, const char *addr)
 {
     notmuch_bool_t duplicate;
     char *key;
+    gchar *addrfold = NULL;
     mailbox_t *mailbox;
 
-    key = talloc_asprintf (opt->format, "%s <%s>", name, addr);
+    if (opt->filter_by == FILTER_BY_ADDRFOLD ||
+	opt->filter_by == FILTER_BY_NAMEADDRFOLD)
+	addrfold = g_utf8_casefold (addr, -1);
+
+    switch (opt->filter_by) {
+    case FILTER_BY_NAMEADDR:
+	key = talloc_asprintf (opt->format, "%s <%s>", name, addr);
+	break;
+    case FILTER_BY_NAMEADDRFOLD:
+	key = talloc_asprintf (opt->format, "%s <%s>", name, addrfold);
+	break;
+    case FILTER_BY_NAME:
+	key = talloc_strdup (opt->format, name); /* !name results in !key */
+	break;
+    case FILTER_BY_ADDR:
+	key = talloc_strdup (opt->format, addr);
+	break;
+    case FILTER_BY_ADDRFOLD:
+	key = talloc_strdup (opt->format, addrfold);
+	break;
+    default:
+	INTERNAL_ERROR("invalid --filter-by flags");
+    }
+
+    if (addrfold)
+	g_free (addrfold);
+
     if (! key)
 	return FALSE;
 
@@ -523,6 +559,7 @@ 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;
@@ -567,6 +604,13 @@ 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 }
     };
 
@@ -577,6 +621,11 @@ 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/T095-search-filter-by.sh b/test/T095-search-filter-by.sh
new file mode 100755
index 0000000..15c9f77
--- /dev/null
+++ b/test/T095-search-filter-by.sh
@@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+test_description='duplicite address filtering in "notmuch search --output=recipients"'
+. ./test-lib.sh
+
+add_message '[to]="John Doe <foo at example.com>, John Doe <bar at example.com>"'
+add_message '[to]="\"Doe, John\" <foo at example.com>"' '[cc]="John Doe <Bar at Example.COM>"'
+add_message '[to]="\"Doe, John\" <foo at example.com>"' '[bcc]="John Doe <Bar at Example.COM>"'
+
+test_begin_subtest "--output=recipients"
+notmuch search --output=recipients "*" >OUTPUT
+cat <<EOF >EXPECTED
+John Doe <foo at example.com>
+John Doe <bar at example.com>
+"Doe, John" <foo at example.com>
+John Doe <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
+John Doe <foo at example.com>
+John Doe <bar at example.com>
+"Doe, John" <foo at example.com>
+John Doe <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
+John Doe <foo at example.com>
+"Doe, John" <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
+John Doe <foo at example.com>
+John Doe <bar at example.com>
+John Doe <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
+John Doe <foo at example.com>
+John Doe <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
+John Doe <foo at example.com>
+John Doe <bar at example.com>
+"Doe, John" <foo at example.com>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=recipients --filter-by=nameaddrfold --output=count"
+notmuch search --output=recipients --filter-by=nameaddrfold --output=count "*" | sort -n >OUTPUT
+cat <<EOF >EXPECTED
+1	John Doe <foo at example.com>
+2	"Doe, John" <foo at example.com>
+3	John Doe <bar at example.com>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_done
-- 
2.1.1



More information about the notmuch mailing list