[PATCH v4 6/6] cli: search: Add --output=count

Michal Sojka sojkam1 at fel.cvut.cz
Mon Oct 27 07:50:55 PDT 2014


This output can be used with --output=recipients or --output=sender and
in addition to the mailboxes, it prints how many times was each mailbox
encountered during search.
---
 completion/notmuch-completion.bash |  2 +-
 completion/notmuch-completion.zsh  |  2 +-
 doc/man1/notmuch-search.rst        |  9 +++++--
 notmuch-search.c                   | 47 ++++++++++++++++++++++++++++++-----
 test/T090-search-output.sh         | 50 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 100 insertions(+), 10 deletions(-)

diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash
index 6b6d43a..b625b02 100644
--- a/completion/notmuch-completion.bash
+++ b/completion/notmuch-completion.bash
@@ -294,7 +294,7 @@ _notmuch_search()
 	    return
 	    ;;
 	--output)
-	    COMPREPLY=( $( compgen -W "summary threads messages files tags sender recipients" -- "${cur}" ) )
+	    COMPREPLY=( $( compgen -W "summary threads messages files tags sender recipients count" -- "${cur}" ) )
 	    return
 	    ;;
 	--sort)
diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-completion.zsh
index 3e535df..c1ccc32 100644
--- a/completion/notmuch-completion.zsh
+++ b/completion/notmuch-completion.zsh
@@ -53,7 +53,7 @@ _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 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"))'
 }
 
diff --git a/doc/man1/notmuch-search.rst b/doc/man1/notmuch-search.rst
index 84af2da..4b408f6 100644
--- a/doc/man1/notmuch-search.rst
+++ b/doc/man1/notmuch-search.rst
@@ -97,9 +97,14 @@ Supported options for **search** include
             Like **sender** but for addresses from *To*, *Cc* and
 	    *Bcc* headers.
 
+	**count**
+	    Can be used in combination with **sender** or
+	    **recipients** to print the count of how many times was
+	    the address encountered during search.
+
 	This option can be given multiple times to combine different
-	outputs. Currently, this is only supported for **sender** and
-	**recipients** outputs.
+	outputs. Currently, this is only supported for **sender**,
+	**recipients** and **count** outputs.
 
     ``--sort=``\ (**newest-first**\ \|\ **oldest-first**)
         This option can be used to present results in either
diff --git a/notmuch-search.c b/notmuch-search.c
index 47aa979..41f4107 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -30,9 +30,10 @@ typedef enum {
     OUTPUT_TAGS		= 1 << 4,
     OUTPUT_SENDER	= 1 << 5,
     OUTPUT_RECIPIENTS	= 1 << 6,
+    OUTPUT_COUNT	= 1 << 7,
 } output_t;
 
-#define OUTPUT_ADDRESS_FLAGS (OUTPUT_SENDER | OUTPUT_RECIPIENTS)
+#define OUTPUT_ADDRESS_FLAGS (OUTPUT_SENDER | OUTPUT_RECIPIENTS | OUTPUT_COUNT)
 
 typedef enum {
     FILTER_BY_NAMEADDR = 0,
@@ -56,6 +57,7 @@ typedef struct {
 typedef struct {
     const char *name;
     const char *addr;
+    int count;
 } mailbox_t;
 
 /* Return two stable query strings that identify exactly the matched
@@ -244,6 +246,7 @@ check_duplicite (const search_options_t *opt, GHashTable *addrs, const char *nam
 {
     notmuch_bool_t duplicite;
     char *key;
+    mailbox_t *mailbox;
 
     if (opt->filter_by == FILTER_BY_ADDRFOLD ||
 	opt->filter_by == FILTER_BY_NAMEADDRFOLD) {
@@ -274,12 +277,18 @@ check_duplicite (const search_options_t *opt, GHashTable *addrs, const char *nam
     if (! key)
 	return FALSE;
 
-    duplicite = g_hash_table_lookup_extended (addrs, key, NULL, NULL);
+    duplicite = g_hash_table_lookup_extended (addrs, key, NULL, (gpointer)&mailbox);
 
-    if (! duplicite)
-	g_hash_table_insert (addrs, key, NULL);
-    else
+    if (! duplicite) {
+	mailbox = talloc (opt->format, mailbox_t);
+	mailbox->name = talloc_strdup (mailbox, name);
+	mailbox->addr = talloc_strdup (mailbox, addr);
+	mailbox->count = 1;
+	g_hash_table_insert (addrs, key, mailbox);
+    } else {
+	mailbox->count++;
 	talloc_free (key);
+    }
 
     return duplicite;
 }
@@ -289,6 +298,7 @@ print_mailbox (const search_options_t *opt, const mailbox_t *mailbox)
 {
     const char *name = mailbox->name;
     const char *addr = mailbox->addr;
+    int count = mailbox->count;
 
     if (opt->format->is_text_printer) {
 	char *mailbox_str;
@@ -302,6 +312,10 @@ print_mailbox (const search_options_t *opt, const mailbox_t *mailbox)
 	    fprintf (stderr, "Error: out of memory\n");
 	    return;
 	}
+	if (count > 0) {
+	    opt->format->integer (opt->format, count);
+	    opt->format->string (opt->format, "\t");
+	}
 	opt->format->string (opt->format, mailbox_str);
 	opt->format->separator (opt->format);
 
@@ -312,6 +326,10 @@ print_mailbox (const search_options_t *opt, const mailbox_t *mailbox)
 	opt->format->string (opt->format, name);
 	opt->format->map_key (opt->format, "address");
 	opt->format->string (opt->format, addr);
+	if (count > 0) {
+	    opt->format->map_key (opt->format, "count");
+	    opt->format->integer (opt->format, count);
+	}
 	opt->format->end (opt->format);
 	opt->format->separator (opt->format);
     }
@@ -341,11 +359,15 @@ process_address_list (const search_options_t *opt, GHashTable *addrs,
 	    mailbox_t mbx = {
 		.name = internet_address_get_name (address),
 		.addr = internet_address_mailbox_get_addr (mailbox),
+		.count = 0,
 	    };
 
 	    if (check_duplicite (opt, addrs, mbx.name, mbx.addr))
 		continue;
 
+	    if (opt->output & OUTPUT_COUNT)
+		continue;
+
 	    print_mailbox (opt, &mbx);
 	}
     }
@@ -372,6 +394,15 @@ _my_talloc_free_for_g_hash (void *ptr)
     talloc_free (ptr);
 }
 
+static void
+print_hash_value (unused (gpointer key), gpointer value, gpointer user_data)
+{
+    const mailbox_t *mailbox = value;
+    search_options_t *opt = user_data;
+
+    print_mailbox (opt, mailbox);
+}
+
 static int
 do_search_messages (search_options_t *opt)
 {
@@ -384,7 +415,7 @@ do_search_messages (search_options_t *opt)
 
     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);
+					   _my_talloc_free_for_g_hash, _my_talloc_free_for_g_hash);
 
     if (opt->offset < 0) {
 	opt->offset += notmuch_query_count_messages (opt->query);
@@ -451,6 +482,9 @@ do_search_messages (search_options_t *opt)
 	notmuch_message_destroy (message);
     }
 
+    if (addresses && opt->output & OUTPUT_COUNT)
+	g_hash_table_foreach (addresses, print_hash_value, opt);
+
     if (addresses)
 	g_hash_table_unref (addresses);
 
@@ -554,6 +588,7 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
 				  { "recipients", OUTPUT_RECIPIENTS },
 				  { "files", OUTPUT_FILES },
 				  { "tags", OUTPUT_TAGS },
+				  { "count", OUTPUT_COUNT },
 				  { 0, 0 } } },
         { NOTMUCH_OPT_KEYWORD, &exclude, "exclude", 'x',
           (notmuch_keyword_t []){ { "true", NOTMUCH_EXCLUDE_TRUE },
diff --git a/test/T090-search-output.sh b/test/T090-search-output.sh
index 841a721..5a9bbc9 100755
--- a/test/T090-search-output.sh
+++ b/test/T090-search-output.sh
@@ -433,6 +433,56 @@ cat <<EOF >EXPECTED
 EOF
 test_expect_equal_file OUTPUT EXPECTED
 
+test_begin_subtest "--output=sender --output=count"
+notmuch search --output=sender --output=count '*' | sort -n >OUTPUT
+cat <<EOF >EXPECTED
+1	Adrian Perez de Castro <aperez at igalia.com>
+1	Aron Griffis <agriffis at n01se.net>
+1	Chris Wilson <chris at chris-wilson.co.uk>
+1	François Boulogne <boulogne.f at gmail.com>
+1	Ingmar Vanhassel <ingmar at exherbo.org>
+1	Israel Herraiz <isra at herraiz.org>
+1	Olivier Berger <olivier.berger at it-sudparis.eu>
+1	Rolland Santimano <rollandsantimano at yahoo.com>
+2	Alex Botero-Lowry <alex.boterolowry at gmail.com>
+2	Jjgod Jiang <gzjjgod at gmail.com>
+3	Stewart Smith <stewart at flamingspork.com>
+4	Alexander Botero-Lowry <alex.boterolowry at gmail.com>
+4	Jan Janak <jan at ryngle.com>
+5	Lars Kellogg-Stedman <lars at seas.harvard.edu>
+5	Mikhail Gusarov <dottedmag at dottedmag.net>
+7	Keith Packard <keithp at keithp.com>
+12	Carl Worth <cworth at cworth.org>
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
+test_begin_subtest "--output=sender --output=count --format=json"
+# Since the iteration order of GHashTable is not specified, we
+# preprocess and sort the results to keep the order stable here.
+notmuch search --output=sender --output=count --format=json '*' | \
+    sed -e 's/^\[//' -e 's/]$//' -e 's/,$//' | \
+    sort --field-separator=":" --key=4n --key=2 >OUTPUT
+cat <<EOF >EXPECTED
+{"name": "Adrian Perez de Castro", "address": "aperez at igalia.com", "count": 1}
+{"name": "Aron Griffis", "address": "agriffis at n01se.net", "count": 1}
+{"name": "Chris Wilson", "address": "chris at chris-wilson.co.uk", "count": 1}
+{"name": "François Boulogne", "address": "boulogne.f at gmail.com", "count": 1}
+{"name": "Ingmar Vanhassel", "address": "ingmar at exherbo.org", "count": 1}
+{"name": "Israel Herraiz", "address": "isra at herraiz.org", "count": 1}
+{"name": "Olivier Berger", "address": "olivier.berger at it-sudparis.eu", "count": 1}
+{"name": "Rolland Santimano", "address": "rollandsantimano at yahoo.com", "count": 1}
+{"name": "Alex Botero-Lowry", "address": "alex.boterolowry at gmail.com", "count": 2}
+{"name": "Jjgod Jiang", "address": "gzjjgod at gmail.com", "count": 2}
+{"name": "Stewart Smith", "address": "stewart at flamingspork.com", "count": 3}
+{"name": "Alexander Botero-Lowry", "address": "alex.boterolowry at gmail.com", "count": 4}
+{"name": "Jan Janak", "address": "jan at ryngle.com", "count": 4}
+{"name": "Lars Kellogg-Stedman", "address": "lars at seas.harvard.edu", "count": 5}
+{"name": "Mikhail Gusarov", "address": "dottedmag at dottedmag.net", "count": 5}
+{"name": "Keith Packard", "address": "keithp at keithp.com", "count": 7}
+{"name": "Carl Worth", "address": "cworth at cworth.org", "count": 12}
+EOF
+test_expect_equal_file OUTPUT EXPECTED
+
 test_begin_subtest "--output=recipients"
 notmuch search --output=recipients '*' >OUTPUT
 cat <<EOF >EXPECTED
-- 
2.1.1



More information about the notmuch mailing list