[PATCH 4/5] cli: Add configurable address deduplication for --output=addresses
Michal Sojka
sojkam1 at fel.cvut.cz
Mon Sep 22 02:37:58 PDT 2014
The code here is an extended version of a path from Jani Nikula.
---
completion/notmuch-completion.bash | 6 ++-
completion/notmuch-completion.zsh | 3 +-
doc/man1/notmuch-search.rst | 33 ++++++++++++
notmuch-search.c | 101 ++++++++++++++++++++++++++++++++++---
4 files changed, 135 insertions(+), 8 deletions(-)
diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash
index c37ddf5..8bc7874 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
;;
+ --unique)
+ COMPREPLY=( $( compgen -W "none addr addrfold name" -- "${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= --unique="
compopt -o nospace
COMPREPLY=( $(compgen -W "$options" -- ${cur}) )
;;
diff --git a/completion/notmuch-completion.zsh b/completion/notmuch-completion.zsh
index bff8fd5..cf4968c 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 addresses))'
+ '--output=[select what to output]:output:((summary threads messages files tags sender recipients addresses))' \
+ '--unique=[address deduplication]:unique:((none\:"no deduplication" addr\:"deduplicate by address" addrfold\:"deduplicate by case-insensitive address" name\:"deduplicate by name"))'
}
_notmuch()
diff --git a/doc/man1/notmuch-search.rst b/doc/man1/notmuch-search.rst
index 6094906..a92779a 100644
--- a/doc/man1/notmuch-search.rst
+++ b/doc/man1/notmuch-search.rst
@@ -85,6 +85,9 @@ Supported options for **search** include
(--format=text0), as a JSON array (--format=json), or as
an S-Expression list (--format=sexp).
+ Handling of duplicate addresses and/or names can be
+ controlled with the --unique option.
+
Note: Searching for **sender** should much be faster than
searching for **recipients** or **addresses**, because
sender addresses are cached directly in the database
@@ -151,6 +154,36 @@ Supported options for **search** include
prefix. The prefix matches messages based on filenames. This
option filters filenames of the matching messages.
+ ``--unique=``\ (**none**\ \|\ **addr**\ \|\ **addrfold**\ \|\ **name**)[,\ ...]
+
+ Can be used with ``--output=addresses``, ``--output=sender``
+ or ``--output=recipients`` to control the address
+ deduplication algorithm.
+
+ **none** means that no deduplication is performed. The same
+ address can appear multiple times in the output.
+
+ **addr** means that case-sensitive deduplication is performed
+ on the address part. For example, given the addresses "John
+ Doe <john at example.com>" and "Dr. John Doe <john at example.com>",
+ only one will be printed.
+
+ **addrfold** means that case-insensitive deduplication is
+ performed on the address part. For example, given the
+ addresses "John Doe <john at example.com>" and "John Doe
+ <JOHN at EXAMPLE.COM>", only one will be printed. This is the
+ default.
+
+ **name** means that case-sensitive deduplication is performed
+ on the name part. For example, given the addresses "John Doe
+ <john at example.com>" and "John Doe <john at doe.name>", only one
+ will be printed.
+
+ It is possible to combine the above flags (except **none**) by
+ separating them with comma. For example,
+ ``--unique=name,addr`` will print unique case-sensitive
+ combinations of name and address.
+
EXIT STATUS
===========
diff --git a/notmuch-search.c b/notmuch-search.c
index 0614f10..00d6771 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -33,6 +33,15 @@ typedef enum {
OUTPUT_ADDRESSES = OUTPUT_SENDER | OUTPUT_RECIPIENTS,
} output_t;
+typedef enum {
+ UNIQUE_NONE = 1 << 0,
+ UNIQUE_ADDR = 1 << 1,
+ UNIQUE_NAME = 1 << 2,
+ UNIQUE_ADDR_CASEFOLD = 1 << 3,
+
+ UNIQUE_BOTH = UNIQUE_NAME | UNIQUE_ADDR,
+} unique_t;
+
typedef struct {
sprinter_t *format;
notmuch_query_t *query;
@@ -41,6 +50,7 @@ typedef struct {
int offset;
int limit;
int dupe;
+ unique_t unique;
} search_options_t;
/* Return two stable query strings that identify exactly the matched
@@ -223,8 +233,51 @@ do_search_threads (search_options_t *o)
return 0;
}
+/* Returns TRUE iff name and/or addr is considered unique. */
+static notmuch_bool_t
+check_unique (const search_options_t *o, GHashTable *addrs, const char *name, const char *addr)
+{
+ notmuch_bool_t unique;
+ char *key;
+
+ if (o->unique == UNIQUE_NONE)
+ return TRUE;
+
+ if (o->unique & UNIQUE_ADDR_CASEFOLD) {
+ gchar *folded = g_utf8_casefold (addr, -1);
+ addr = talloc_strdup (o->format, folded);
+ g_free (folded);
+ }
+ switch (o->unique & UNIQUE_BOTH) {
+ case UNIQUE_NAME:
+ key = talloc_strdup (o->format, name); /* !name results in !key */
+ break;
+ case UNIQUE_ADDR:
+ key = talloc_strdup (o->format, addr);
+ break;
+ case UNIQUE_BOTH:
+ key = talloc_asprintf (o->format, "%s <%s>", name, addr);
+ break;
+ default:
+ INTERNAL_ERROR("invalid --unique flags");
+ }
+
+ if (! key)
+ return FALSE;
+
+ unique = !g_hash_table_lookup_extended (addrs, key, NULL, NULL);
+
+ if (unique)
+ g_hash_table_insert (addrs, key, NULL);
+ else
+ talloc_free (key);
+
+ return unique;
+}
+
static void
-print_address_list (const search_options_t *o, InternetAddressList *list)
+print_address_list (const search_options_t *o, GHashTable *addrs,
+ InternetAddressList *list)
{
InternetAddress *address;
int i;
@@ -240,7 +293,7 @@ print_address_list (const search_options_t *o, InternetAddressList *list)
if (group_list == NULL)
continue;
- print_address_list (o, group_list);
+ print_address_list (o, addrs, group_list);
} else {
InternetAddressMailbox *mailbox;
const char *name;
@@ -252,6 +305,9 @@ print_address_list (const search_options_t *o, InternetAddressList *list)
name = internet_address_get_name (address);
addr = internet_address_mailbox_get_addr (mailbox);
+ if (!check_unique (o, addrs, name, addr))
+ continue;
+
if (name && *name)
full_address = talloc_asprintf (o->format, "%s <%s>", name, addr);
else
@@ -270,7 +326,7 @@ print_address_list (const search_options_t *o, InternetAddressList *list)
}
static void
-print_address_string (const search_options_t *o, const char *recipients)
+print_address_string (const search_options_t *o, GHashTable *addrs, const char *recipients)
{
InternetAddressList *list;
@@ -281,7 +337,13 @@ print_address_string (const search_options_t *o, const char *recipients)
if (list == NULL)
return;
- print_address_list (o, list);
+ print_address_list (o, addrs, list);
+}
+
+static void
+_my_talloc_free_for_g_hash (void *ptr)
+{
+ talloc_free (ptr);
}
static int
@@ -291,8 +353,13 @@ do_search_messages (search_options_t *o)
notmuch_messages_t *messages;
notmuch_filenames_t *filenames;
sprinter_t *format = o->format;
+ GHashTable *addresses = NULL;
int i;
+ if (o->output & OUTPUT_ADDRESSES)
+ addresses = g_hash_table_new_full (g_str_hash, g_str_equal,
+ _my_talloc_free_for_g_hash, NULL);
+
if (o->offset < 0) {
o->offset += notmuch_query_count_messages (o->query);
if (o->offset < 0)
@@ -340,7 +407,7 @@ do_search_messages (search_options_t *o)
const char *addrs;
addrs = notmuch_message_get_header (message, "from");
- print_address_string (o, addrs);
+ print_address_string (o, addresses, addrs);
}
if (o->output & OUTPUT_RECIPIENTS) {
@@ -350,7 +417,7 @@ do_search_messages (search_options_t *o)
for (j = 0; j < ARRAY_SIZE (hdrs); j++) {
addrs = notmuch_message_get_header (message, hdrs[j]);
- print_address_string (o, addrs);
+ print_address_string (o, addresses, addrs);
}
}
}
@@ -358,6 +425,9 @@ do_search_messages (search_options_t *o)
notmuch_message_destroy (message);
}
+ if (addresses)
+ g_hash_table_unref (addresses);
+
notmuch_messages_destroy (messages);
format->end (format);
@@ -423,6 +493,7 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
.offset = 0,
.limit = -1, /* unlimited */
.dupe = -1,
+ .unique = 0,
};
char *query_str;
int opt_index, ret;
@@ -467,6 +538,12 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
{ NOTMUCH_OPT_INT, &o.offset, "offset", 'O', 0 },
{ NOTMUCH_OPT_INT, &o.limit, "limit", 'L', 0 },
{ NOTMUCH_OPT_INT, &o.dupe, "duplicate", 'D', 0 },
+ { NOTMUCH_OPT_FLAGS, &o.unique, "unique", 'u',
+ (notmuch_keyword_t []){ { "none", UNIQUE_NONE },
+ { "name", UNIQUE_NAME },
+ { "addr", UNIQUE_ADDR },
+ { "addrfold", UNIQUE_ADDR | UNIQUE_ADDR_CASEFOLD },
+ { 0, 0 } } },
{ 0, 0, 0, 0, 0 }
};
@@ -474,6 +551,18 @@ notmuch_search_command (notmuch_config_t *config, int argc, char *argv[])
if (opt_index < 0)
return EXIT_FAILURE;
+ if (o.unique && (o.output & ~OUTPUT_ADDRESSES)) {
+ fprintf (stderr, "Error: --unique can only be used with address output.\n");
+ return EXIT_FAILURE;
+ }
+ if ((o.unique & UNIQUE_NONE) &&
+ (o.unique & ~UNIQUE_NONE)) {
+ fprintf (stderr, "Error: --unique=none cannot be combined with other flags.\n");
+ return EXIT_FAILURE;
+ }
+ if (! o.unique)
+ o.unique = UNIQUE_ADDR | UNIQUE_ADDR_CASEFOLD;
+
switch (format_sel) {
case NOTMUCH_FORMAT_TEXT:
o.format = sprinter_text_create (config, stdout);
--
2.1.0
More information about the notmuch
mailing list