From: Mark Walters <markwalters1009@gmail.com>
To: Michal Sojka <sojkam1@fel.cvut.cz>, notmuch@notmuchmail.org
Subject: Re: [PATCH v2 09/10] cli: address: Add --output=count
In-Reply-To: <1415058622-21162-10-git-send-email-sojkam1@fel.cvut.cz>
References: <1415058622-21162-1-git-send-email-sojkam1@fel.cvut.cz>
	<1415058622-21162-10-git-send-email-sojkam1@fel.cvut.cz>
User-Agent: Notmuch/0.18.1+86~gef5e66a (http://notmuchmail.org) Emacs/23.4.1
	(x86_64-pc-linux-gnu)
Date: Tue, 04 Nov 2014 09:11:35 +0000
Message-ID: <87tx2f2uuw.fsf@qmul.ac.uk>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: list


On Mon, 03 Nov 2014, Michal Sojka <sojkam1@fel.cvut.cz> wrote:
> This output prints how many times was each address encountered during
> search.
> ---
>  completion/notmuch-completion.bash |  2 +-
>  completion/notmuch-completion.zsh  |  2 +-
>  doc/man1/notmuch-address.rst       |  7 ++++++
>  notmuch-search.c                   | 49 ++++++++++++++++++++++++++++++++=
------
>  test/T095-address.sh               | 48 ++++++++++++++++++++++++++++++++=
+++++
>  5 files changed, 99 insertions(+), 9 deletions(-)
>
> diff --git a/completion/notmuch-completion.bash b/completion/notmuch-comp=
letion.bash
> index 94ea2d5..db152f3 100644
> --- a/completion/notmuch-completion.bash
> +++ b/completion/notmuch-completion.bash
> @@ -332,7 +332,7 @@ _notmuch_address()
>  	    return
>  	    ;;
>  	--output)
> -	    COMPREPLY=3D( $( compgen -W "sender recipients" -- "${cur}" ) )
> +	    COMPREPLY=3D( $( compgen -W "sender recipients count" -- "${cur}" )=
 )
>  	    return
>  	    ;;
>  	--sort)
> diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-compl=
etion.zsh
> index c606b75..8968562 100644
> --- a/completion/notmuch-completion.zsh
> +++ b/completion/notmuch-completion.zsh
> @@ -61,7 +61,7 @@ _notmuch_address()
>  {
>    _arguments -s : \
>      '--sort=3D[sort results]:sorting:((newest-first\:"reverse chronologi=
cal order" oldest-first\:"chronological order"))' \
> -    '--output=3D[select what to output]:output:((sender recipients))'
> +    '--output=3D[select what to output]:output:((sender recipients count=
))'
>  }
>=20=20
>  _notmuch()
> diff --git a/doc/man1/notmuch-address.rst b/doc/man1/notmuch-address.rst
> index 96512b7..18473a7 100644
> --- a/doc/man1/notmuch-address.rst
> +++ b/doc/man1/notmuch-address.rst
> @@ -48,6 +48,13 @@ Supported options for **address** include
>              Output all addresses from the *To*, *Cc* and *Bcc*
>              headers.
>=20=20
> +	**count**
> +	    Print the count of how many times was the address
> +	    encountered during search.
> +
> +	    Note: With this option, addresses are printed only after
> +	    the whole search is finished. This may take long time.
> +

Hi

I think count should be added to the --output=3D(sender|recipients) line a
little above this.

Also it should say that count ignores the sort order (or possibly that
should go with sort?)

Best wishes

Mark



>      ``--sort=3D``\ (**newest-first**\ \|\ **oldest-first**)
>          This option can be used to present results in either
>          chronological order (**oldest-first**) or reverse chronological
> diff --git a/notmuch-search.c b/notmuch-search.c
> index 741702a..d99e530 100644
> --- a/notmuch-search.c
> +++ b/notmuch-search.c
> @@ -33,6 +33,7 @@ typedef enum {
>      /* Address command */
>      OUTPUT_SENDER	=3D 1 << 5,
>      OUTPUT_RECIPIENTS	=3D 1 << 6,
> +    OUTPUT_COUNT	=3D 1 << 7,
>  } output_t;
>=20=20
>  typedef enum {
> @@ -59,6 +60,7 @@ typedef struct {
>  typedef struct {
>      const char *name;
>      const char *addr;
> +    int count;
>  } mailbox_t;
>=20=20
>  /* Return two stable query strings that identify exactly the matched
> @@ -247,17 +249,24 @@ is_duplicate (const search_context_t *ctx, const ch=
ar *name, const char *addr)
>  {
>      notmuch_bool_t duplicate;
>      char *key;
> +    mailbox_t *mailbox;
>=20=20
>      key =3D talloc_asprintf (ctx->format, "%s <%s>", name, addr);
>      if (! key)
>  	return FALSE;
>=20=20
> -    duplicate =3D g_hash_table_lookup_extended (ctx->addresses, key, NUL=
L, NULL);
> +    duplicate =3D g_hash_table_lookup_extended (ctx->addresses, key, NUL=
L, (gpointer)&mailbox);
>=20=20
> -    if (! duplicate)
> -	g_hash_table_insert (ctx->addresses, key, NULL);
> -    else
> +    if (! duplicate) {
> +	mailbox =3D talloc (ctx->format, mailbox_t);
> +	mailbox->name =3D talloc_strdup (mailbox, name);
> +	mailbox->addr =3D talloc_strdup (mailbox, addr);
> +	mailbox->count =3D 1;
> +	g_hash_table_insert (ctx->addresses, key, mailbox);
> +    } else {
> +	mailbox->count++;
>  	talloc_free (key);
> +    }
>=20=20
>      return duplicate;
>  }
> @@ -267,6 +276,7 @@ print_mailbox (const search_context_t *ctx, const mai=
lbox_t *mailbox)
>  {
>      const char *name =3D mailbox->name;
>      const char *addr =3D mailbox->addr;
> +    int count =3D mailbox->count;
>      sprinter_t *format =3D ctx->format;
>      InternetAddress *ia =3D internet_address_mailbox_new (name, addr);
>      char *name_addr;
> @@ -276,6 +286,10 @@ print_mailbox (const search_context_t *ctx, const ma=
ilbox_t *mailbox)
>      name_addr =3D internet_address_to_string (ia, FALSE);
>=20=20
>      if (format->is_text_printer) {
> +	if (count > 0) {
> +	    format->integer (format, count);
> +	    format->string (format, "\t");
> +	}
>  	format->string (format, name_addr);
>  	format->separator (format);
>      } else {
> @@ -286,6 +300,10 @@ print_mailbox (const search_context_t *ctx, const ma=
ilbox_t *mailbox)
>  	format->string (format, addr);
>  	format->map_key (format, "name-addr");
>  	format->string (format, name_addr);
> +	if (count > 0) {
> +	    format->map_key (format, "count");
> +	    format->integer (format, count);
> +	}
>  	format->end (format);
>  	format->separator (format);
>      }
> @@ -294,7 +312,7 @@ print_mailbox (const search_context_t *ctx, const mai=
lbox_t *mailbox)
>      g_free (name_addr);
>  }
>=20=20
> -/* Print addresses from InternetAddressList.  */
> +/* Print or prepare for printing addresses from InternetAddressList. */
>  static void
>  process_address_list (const search_context_t *ctx,
>  		      InternetAddressList *list)
> @@ -319,17 +337,21 @@ process_address_list (const search_context_t *ctx,
>  	    mailbox_t mbx =3D {
>  		.name =3D internet_address_get_name (address),
>  		.addr =3D internet_address_mailbox_get_addr (mailbox),
> +		.count =3D 0,
>  	    };
>=20=20
>  	    if (is_duplicate (ctx, mbx.name, mbx.addr))
>  		continue;
>=20=20
> +	    if (ctx->output & OUTPUT_COUNT)
> +		continue;
> +
>  	    print_mailbox (ctx, &mbx);
>  	}
>      }
>  }
>=20=20
> -/* Print addresses from a message header.  */
> +/* Print or prepare for printing addresses from a message header. */
>  static void
>  process_address_header (const search_context_t *ctx, const char *value)
>  {
> @@ -353,6 +375,15 @@ _my_talloc_free_for_g_hash (void *ptr)
>      talloc_free (ptr);
>  }
>=20=20
> +static void
> +print_hash_value (unused (gpointer key), gpointer value, gpointer user_d=
ata)
> +{
> +    const mailbox_t *mailbox =3D value;
> +    search_context_t *ctx =3D user_data;
> +
> +    print_mailbox (ctx, mailbox);
> +}
> +
>  static int
>  _count_filenames (notmuch_message_t *message)
>  {
> @@ -448,6 +479,9 @@ do_search_messages (search_context_t *ctx)
>  	notmuch_message_destroy (message);
>      }
>=20=20
> +    if (ctx->addresses && ctx->output & OUTPUT_COUNT)
> +	g_hash_table_foreach (ctx->addresses, print_hash_value, ctx);
> +
>      notmuch_messages_destroy (messages);
>=20=20
>      format->end (format);
> @@ -685,6 +719,7 @@ notmuch_address_command (notmuch_config_t *config, in=
t argc, char *argv[])
>  	{ NOTMUCH_OPT_KEYWORD_FLAGS, &ctx->output, "output", 'o',
>  	  (notmuch_keyword_t []){ { "sender", OUTPUT_SENDER },
>  				  { "recipients", OUTPUT_RECIPIENTS },
> +				  { "count", OUTPUT_COUNT },
>  				  { 0, 0 } } },
>  	{ NOTMUCH_OPT_INHERIT, &common_options, NULL, 0, 0 },
>  	{ 0, 0, 0, 0, 0 }
> @@ -702,7 +737,7 @@ notmuch_address_command (notmuch_config_t *config, in=
t argc, char *argv[])
>  	return EXIT_FAILURE;
>=20=20
>      ctx->addresses =3D 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);
>=20=20
>      ret =3D do_search_messages (ctx);
>=20=20
> diff --git a/test/T095-address.sh b/test/T095-address.sh
> index 8a256d2..92e17b0 100755
> --- a/test/T095-address.sh
> +++ b/test/T095-address.sh
> @@ -96,5 +96,53 @@ notmuch address --output=3Dsender --output=3Drecipient=
s '*' >OUTPUT
>  # Use EXPECTED from previous subtest
>  test_expect_equal_file OUTPUT EXPECTED
>=20=20
> +test_begin_subtest "--output=3Dsender --output=3Dcount"
> +notmuch address --output=3Dsender --output=3Dcount '*' | sort -n >OUTPUT
> +cat <<EOF >EXPECTED
> +1	Adrian Perez de Castro <aperez@igalia.com>
> +1	Aron Griffis <agriffis@n01se.net>
> +1	Chris Wilson <chris@chris-wilson.co.uk>
> +1	Fran=C3=A7ois Boulogne <boulogne.f@gmail.com>
> +1	Ingmar Vanhassel <ingmar@exherbo.org>
> +1	Israel Herraiz <isra@herraiz.org>
> +1	Olivier Berger <olivier.berger@it-sudparis.eu>
> +1	Rolland Santimano <rollandsantimano@yahoo.com>
> +2	Alex Botero-Lowry <alex.boterolowry@gmail.com>
> +2	Jjgod Jiang <gzjjgod@gmail.com>
> +3	Stewart Smith <stewart@flamingspork.com>
> +4	Alexander Botero-Lowry <alex.boterolowry@gmail.com>
> +4	Jan Janak <jan@ryngle.com>
> +5	Lars Kellogg-Stedman <lars@seas.harvard.edu>
> +5	Mikhail Gusarov <dottedmag@dottedmag.net>
> +7	Keith Packard <keithp@keithp.com>
> +12	Carl Worth <cworth@cworth.org>
> +EOF
> +test_expect_equal_file OUTPUT EXPECTED
> +
> +test_begin_subtest "--output=3Dsender --output=3Dcount --format=3Djson"
> +# Since the iteration order of GHashTable is not specified, we
> +# preprocess and sort the results to keep the order stable here.
> +notmuch address --output=3Dsender --output=3Dcount --format=3Djson '*' |=
 \
> +    sed -e 's/^\[//' -e 's/]$//' -e 's/,$//' | sort >OUTPUT
> +cat <<EOF >EXPECTED
> +{"name": "Adrian Perez de Castro", "address": "aperez@igalia.com", "name=
-addr": "Adrian Perez de Castro <aperez@igalia.com>", "count": 1}
> +{"name": "Alex Botero-Lowry", "address": "alex.boterolowry@gmail.com", "=
name-addr": "Alex Botero-Lowry <alex.boterolowry@gmail.com>", "count": 2}
> +{"name": "Alexander Botero-Lowry", "address": "alex.boterolowry@gmail.co=
m", "name-addr": "Alexander Botero-Lowry <alex.boterolowry@gmail.com>", "co=
unt": 4}
> +{"name": "Aron Griffis", "address": "agriffis@n01se.net", "name-addr": "=
Aron Griffis <agriffis@n01se.net>", "count": 1}
> +{"name": "Carl Worth", "address": "cworth@cworth.org", "name-addr": "Car=
l Worth <cworth@cworth.org>", "count": 12}
> +{"name": "Chris Wilson", "address": "chris@chris-wilson.co.uk", "name-ad=
dr": "Chris Wilson <chris@chris-wilson.co.uk>", "count": 1}
> +{"name": "Fran=C3=A7ois Boulogne", "address": "boulogne.f@gmail.com", "n=
ame-addr": "Fran=C3=A7ois Boulogne <boulogne.f@gmail.com>", "count": 1}
> +{"name": "Ingmar Vanhassel", "address": "ingmar@exherbo.org", "name-addr=
": "Ingmar Vanhassel <ingmar@exherbo.org>", "count": 1}
> +{"name": "Israel Herraiz", "address": "isra@herraiz.org", "name-addr": "=
Israel Herraiz <isra@herraiz.org>", "count": 1}
> +{"name": "Jan Janak", "address": "jan@ryngle.com", "name-addr": "Jan Jan=
ak <jan@ryngle.com>", "count": 4}
> +{"name": "Jjgod Jiang", "address": "gzjjgod@gmail.com", "name-addr": "Jj=
god Jiang <gzjjgod@gmail.com>", "count": 2}
> +{"name": "Keith Packard", "address": "keithp@keithp.com", "name-addr": "=
Keith Packard <keithp@keithp.com>", "count": 7}
> +{"name": "Lars Kellogg-Stedman", "address": "lars@seas.harvard.edu", "na=
me-addr": "Lars Kellogg-Stedman <lars@seas.harvard.edu>", "count": 5}
> +{"name": "Mikhail Gusarov", "address": "dottedmag@dottedmag.net", "name-=
addr": "Mikhail Gusarov <dottedmag@dottedmag.net>", "count": 5}
> +{"name": "Olivier Berger", "address": "olivier.berger@it-sudparis.eu", "=
name-addr": "Olivier Berger <olivier.berger@it-sudparis.eu>", "count": 1}
> +{"name": "Rolland Santimano", "address": "rollandsantimano@yahoo.com", "=
name-addr": "Rolland Santimano <rollandsantimano@yahoo.com>", "count": 1}
> +{"name": "Stewart Smith", "address": "stewart@flamingspork.com", "name-a=
ddr": "Stewart Smith <stewart@flamingspork.com>", "count": 3}
> +EOF
> +test_expect_equal_file OUTPUT EXPECTED
>=20=20
>  test_done
> --=20
> 2.1.1
>
> _______________________________________________
> notmuch mailing list
> notmuch@notmuchmail.org
> http://notmuchmail.org/mailman/listinfo/notmuch