[PATCH 1/2] cli: add user address matching helpers for notmuch reply

[PATCH 1/2] cli: add user address matching helpers for notmuch reply

[Jani Nikula]

Add a multi-purpose address_match() function for matching strings
against user's configured primary and other email addresses. Add thin
wrappers user_address_in_string() and string_in_user_address() for
ease of use, and also convert existing address_is_users() to wrapper
for the same.

No functional changes.

Signed-off-by: Jani Nikula <jani@nikula.org>
---
 notmuch-reply.c |   72 +++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 62 insertions(+), 10 deletions(-)

diff --git a/notmuch-reply.c b/notmuch-reply.c
index 7184a5d..0c82755 100644
--- a/notmuch-reply.c
+++ b/notmuch-reply.c
@@ -98,25 +98,77 @@ format_part_reply (mime_node_t *node)
 	format_part_reply (mime_node_child (node, i));
 }
 
-/* Is the given address configured as one of the user's "personal" or
- * "other" addresses. */
-static int
-address_is_users (const char *address, notmuch_config_t *config)
+typedef enum {
+    USER_ADDRESS_IN_STRING,
+    STRING_IN_USER_ADDRESS,
+    STRING_IS_USER_ADDRESS,
+} address_match_t;
+
+/* Match given string against given address according to mode. */
+static notmuch_bool_t
+match_address (const char *str, const char *address, address_match_t mode)
+{
+    switch (mode) {
+    case USER_ADDRESS_IN_STRING:
+	return strcasestr (str, address) != NULL;
+    case STRING_IN_USER_ADDRESS:
+	return strcasestr (address, str) != NULL;
+    case STRING_IS_USER_ADDRESS:
+	return strcasecmp (address, str) == 0;
+    }
+
+    return FALSE;
+}
+
+/* Match given string against user's configured "primary" and "other"
+ * addresses according to mode. */
+static const char *
+address_match (const char *str, notmuch_config_t *config, address_match_t mode)
 {
     const char *primary;
     const char **other;
     size_t i, other_len;
 
+    if (!str || *str == '\0')
+	return NULL;
+
     primary = notmuch_config_get_user_primary_email (config);
-    if (strcasecmp (primary, address) == 0)
-	return 1;
+    if (match_address (str, primary, mode))
+	return primary;
 
     other = notmuch_config_get_user_other_email (config, &other_len);
-    for (i = 0; i < other_len; i++)
-	if (strcasecmp (other[i], address) == 0)
-	    return 1;
+    for (i = 0; i < other_len; i++) {
+	if (match_address (str, other[i], mode))
+	    return other[i];
+    }
 
-    return 0;
+    return NULL;
+}
+
+/* Does the given string contain an address configured as one of the
+ * user's "primary" or "other" addresses. If so, return the matching
+ * address, NULL otherwise. */
+static const char *
+user_address_in_string (const char *str, notmuch_config_t *config)
+{
+    return address_match (str, config, USER_ADDRESS_IN_STRING);
+}
+
+/* Do any of the addresses configured as one of the user's "primary"
+ * or "other" addresses contain the given string. If so, return the
+ * matching address, NULL otherwise. */
+static const char *
+string_in_user_address (const char *str, notmuch_config_t *config)
+{
+    return address_match (str, config, STRING_IN_USER_ADDRESS);
+}
+
+/* Is the given address configured as one of the user's "primary" or
+ * "other" addresses. */
+static notmuch_bool_t
+address_is_users (const char *address, notmuch_config_t *config)
+{
+    return address_match (address, config, STRING_IS_USER_ADDRESS) != NULL;
 }
 
 /* Scan addresses in 'list'.
-- 
1.7.9.5

[PATCH 2/2] cli: clean up user address matching code in guess_from_received_header()

[Jani Nikula]

Get rid of user address matching code duplication in
guess_from_received_header() by using the new address matching
helpers.

No functional changes.

Signed-off-by: Jani Nikula <jani@nikula.org>
---
 notmuch-reply.c |   64 +++++++++++++++++--------------------------------------
 1 file changed, 19 insertions(+), 45 deletions(-)

diff --git a/notmuch-reply.c b/notmuch-reply.c
index 0c82755..51cb6de 100644
--- a/notmuch-reply.c
+++ b/notmuch-reply.c
@@ -377,20 +377,15 @@ add_recipients_from_message (GMimeMessage *reply,
 static const char *
 guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message)
 {
-    const char *received,*primary,*by;
-    const char **other;
-    char *tohdr;
+    const char *addr, *received, *by;
     char *mta,*ptr,*token;
     char *domain=NULL;
     char *tld=NULL;
     const char *delim=". \t";
-    size_t i,j,other_len;
+    size_t i;
 
     const char *to_headers[] = {"Envelope-to", "X-Original-To"};
 
-    primary = notmuch_config_get_user_primary_email (config);
-    other = notmuch_config_get_user_other_email (config, &other_len);
-
     /* sadly, there is no standard way to find out to which email
      * address a mail was delivered - what is in the headers depends
      * on the MTAs used along the way. So we are trying a number of
@@ -405,23 +400,13 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
      *    'by' part of Received headers
      * If none of these work, we give up and return NULL
      */
-    for (i = 0; i < sizeof(to_headers)/sizeof(*to_headers); i++) {
-	tohdr = xstrdup(notmuch_message_get_header (message, to_headers[i]));
-	if (tohdr && *tohdr) {
-	    /* tohdr is potentialy a list of email addresses, so here we
-	     * check if one of the email addresses is a substring of tohdr
-	     */
-	    if (strcasestr(tohdr, primary)) {
-		free(tohdr);
-		return primary;
-	    }
-	    for (j = 0; j < other_len; j++)
-		if (strcasestr (tohdr, other[j])) {
-		    free(tohdr);
-		    return other[j];
-		}
-	    free(tohdr);
-	}
+    for (i = 0; i < ARRAY_SIZE (to_headers); i++) {
+	const char *tohdr = notmuch_message_get_header (message, to_headers[i]);
+
+	/* Note: tohdr potentially contains a list of email addresses. */
+	addr = user_address_in_string (tohdr, config);
+	if (addr)
+	    return addr;
     }
 
     /* We get the concatenated Received: headers and search from the
@@ -439,19 +424,12 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
      * header
      */
     ptr = strstr (received, " for ");
-    if (ptr) {
-	/* the text following is potentialy a list of email addresses,
-	 * so again we check if one of the email addresses is a
-	 * substring of ptr
-	 */
-	if (strcasestr(ptr, primary)) {
-	    return primary;
-	}
-	for (i = 0; i < other_len; i++)
-	    if (strcasestr (ptr, other[i])) {
-		return other[i];
-	    }
-    }
+
+    /* Note: ptr potentially contains a list of email addresses. */
+    addr = user_address_in_string (ptr, config);
+    if (addr)
+	return addr;
+
     /* Finally, we parse all the " by MTA ..." headers to guess the
      * email address that this was originally delivered to.
      * We extract just the MTA here by removing leading whitespace and
@@ -492,15 +470,11 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
 	     */
 	    *(tld-1) = '.';
 
-	    if (strcasestr(primary, domain)) {
-		free(mta);
-		return primary;
+	    addr = string_in_user_address (domain, config);
+	    if (addr) {
+		free (mta);
+		return addr;
 	    }
-	    for (i = 0; i < other_len; i++)
-		if (strcasestr (other[i],domain)) {
-		    free(mta);
-		    return other[i];
-		}
 	}
 	free (mta);
     }
-- 
1.7.9.5

Re: [PATCH 2/2] cli: clean up user address matching code in guess_from_received_header()

[Austin Clements]

Series LGTM.  This is a nice cleanup.

My one comment is that it seems like we should be stricter about
matching email address lists, since a naive substring match could
yield strange results.  That's not something that should be changed in
this patch, though.

Does the context of this patch conflict with
id:"21a946917c5c8dd63295b7c87b7c2d1ebcb6e71e.1336746160.git.jani@nikula.org"
?  It seems like both have context that's changed by the other patch.

Quoth Jani Nikula on May 11 at  5:33 pm:
> Get rid of user address matching code duplication in
> guess_from_received_header() by using the new address matching
> helpers.
> 
> No functional changes.
> 
> Signed-off-by: Jani Nikula <jani@nikula.org>
> ---
>  notmuch-reply.c |   64 +++++++++++++++++--------------------------------------
>  1 file changed, 19 insertions(+), 45 deletions(-)
> 
> diff --git a/notmuch-reply.c b/notmuch-reply.c
> index 0c82755..51cb6de 100644
> --- a/notmuch-reply.c
> +++ b/notmuch-reply.c
> @@ -377,20 +377,15 @@ add_recipients_from_message (GMimeMessage *reply,
>  static const char *
>  guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message)
>  {
> -    const char *received,*primary,*by;
> -    const char **other;
> -    char *tohdr;
> +    const char *addr, *received, *by;
>      char *mta,*ptr,*token;
>      char *domain=NULL;
>      char *tld=NULL;
>      const char *delim=". \t";
> -    size_t i,j,other_len;
> +    size_t i;
>  
>      const char *to_headers[] = {"Envelope-to", "X-Original-To"};
>  
> -    primary = notmuch_config_get_user_primary_email (config);
> -    other = notmuch_config_get_user_other_email (config, &other_len);
> -
>      /* sadly, there is no standard way to find out to which email
>       * address a mail was delivered - what is in the headers depends
>       * on the MTAs used along the way. So we are trying a number of
> @@ -405,23 +400,13 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>       *    'by' part of Received headers
>       * If none of these work, we give up and return NULL
>       */
> -    for (i = 0; i < sizeof(to_headers)/sizeof(*to_headers); i++) {
> -	tohdr = xstrdup(notmuch_message_get_header (message, to_headers[i]));
> -	if (tohdr && *tohdr) {
> -	    /* tohdr is potentialy a list of email addresses, so here we
> -	     * check if one of the email addresses is a substring of tohdr
> -	     */
> -	    if (strcasestr(tohdr, primary)) {
> -		free(tohdr);
> -		return primary;
> -	    }
> -	    for (j = 0; j < other_len; j++)
> -		if (strcasestr (tohdr, other[j])) {
> -		    free(tohdr);
> -		    return other[j];
> -		}
> -	    free(tohdr);
> -	}
> +    for (i = 0; i < ARRAY_SIZE (to_headers); i++) {
> +	const char *tohdr = notmuch_message_get_header (message, to_headers[i]);
> +
> +	/* Note: tohdr potentially contains a list of email addresses. */
> +	addr = user_address_in_string (tohdr, config);
> +	if (addr)
> +	    return addr;
>      }
>  
>      /* We get the concatenated Received: headers and search from the
> @@ -439,19 +424,12 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>       * header
>       */
>      ptr = strstr (received, " for ");
> -    if (ptr) {
> -	/* the text following is potentialy a list of email addresses,
> -	 * so again we check if one of the email addresses is a
> -	 * substring of ptr
> -	 */
> -	if (strcasestr(ptr, primary)) {
> -	    return primary;
> -	}
> -	for (i = 0; i < other_len; i++)
> -	    if (strcasestr (ptr, other[i])) {
> -		return other[i];
> -	    }
> -    }
> +
> +    /* Note: ptr potentially contains a list of email addresses. */
> +    addr = user_address_in_string (ptr, config);
> +    if (addr)
> +	return addr;
> +
>      /* Finally, we parse all the " by MTA ..." headers to guess the
>       * email address that this was originally delivered to.
>       * We extract just the MTA here by removing leading whitespace and
> @@ -492,15 +470,11 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>  	     */
>  	    *(tld-1) = '.';
>  
> -	    if (strcasestr(primary, domain)) {
> -		free(mta);
> -		return primary;
> +	    addr = string_in_user_address (domain, config);
> +	    if (addr) {
> +		free (mta);
> +		return addr;
>  	    }
> -	    for (i = 0; i < other_len; i++)
> -		if (strcasestr (other[i],domain)) {
> -		    free(mta);
> -		    return other[i];
> -		}
>  	}
>  	free (mta);
>      }

Re: [PATCH 2/2] cli: clean up user address matching code in guess_from_received_header()

[Jani Nikula]

On Sat, 12 May 2012, Austin Clements <amdragon@MIT.EDU> wrote:
> Series LGTM.  This is a nice cleanup.

Thanks for the review.

> My one comment is that it seems like we should be stricter about
> matching email address lists, since a naive substring match could
> yield strange results.  That's not something that should be changed in
> this patch, though.

Agreed. Especially the Received: header matching should be scrutinized,
as *all* the Received: headers in a message are merged into one by
notmuch_message_file_get_header(). But that should be another patch,
another time.

> Does the context of this patch conflict with
> id:"21a946917c5c8dd63295b7c87b7c2d1ebcb6e71e.1336746160.git.jani@nikula.org"
> ?  It seems like both have context that's changed by the other patch.

Ooops, you're right. The two series do *merge* on top of each other in
either order, but as patches they apply only on master. I wanted to keep
the series separate. Once either gets pushed, I'll rebase the other.

BR,
Jani.

>
> Quoth Jani Nikula on May 11 at  5:33 pm:
>> Get rid of user address matching code duplication in
>> guess_from_received_header() by using the new address matching
>> helpers.
>> 
>> No functional changes.
>> 
>> Signed-off-by: Jani Nikula <jani@nikula.org>
>> ---
>>  notmuch-reply.c |   64 +++++++++++++++++--------------------------------------
>>  1 file changed, 19 insertions(+), 45 deletions(-)
>> 
>> diff --git a/notmuch-reply.c b/notmuch-reply.c
>> index 0c82755..51cb6de 100644
>> --- a/notmuch-reply.c
>> +++ b/notmuch-reply.c
>> @@ -377,20 +377,15 @@ add_recipients_from_message (GMimeMessage *reply,
>>  static const char *
>>  guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message)
>>  {
>> -    const char *received,*primary,*by;
>> -    const char **other;
>> -    char *tohdr;
>> +    const char *addr, *received, *by;
>>      char *mta,*ptr,*token;
>>      char *domain=NULL;
>>      char *tld=NULL;
>>      const char *delim=". \t";
>> -    size_t i,j,other_len;
>> +    size_t i;
>>  
>>      const char *to_headers[] = {"Envelope-to", "X-Original-To"};
>>  
>> -    primary = notmuch_config_get_user_primary_email (config);
>> -    other = notmuch_config_get_user_other_email (config, &other_len);
>> -
>>      /* sadly, there is no standard way to find out to which email
>>       * address a mail was delivered - what is in the headers depends
>>       * on the MTAs used along the way. So we are trying a number of
>> @@ -405,23 +400,13 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>>       *    'by' part of Received headers
>>       * If none of these work, we give up and return NULL
>>       */
>> -    for (i = 0; i < sizeof(to_headers)/sizeof(*to_headers); i++) {
>> -	tohdr = xstrdup(notmuch_message_get_header (message, to_headers[i]));
>> -	if (tohdr && *tohdr) {
>> -	    /* tohdr is potentialy a list of email addresses, so here we
>> -	     * check if one of the email addresses is a substring of tohdr
>> -	     */
>> -	    if (strcasestr(tohdr, primary)) {
>> -		free(tohdr);
>> -		return primary;
>> -	    }
>> -	    for (j = 0; j < other_len; j++)
>> -		if (strcasestr (tohdr, other[j])) {
>> -		    free(tohdr);
>> -		    return other[j];
>> -		}
>> -	    free(tohdr);
>> -	}
>> +    for (i = 0; i < ARRAY_SIZE (to_headers); i++) {
>> +	const char *tohdr = notmuch_message_get_header (message, to_headers[i]);
>> +
>> +	/* Note: tohdr potentially contains a list of email addresses. */
>> +	addr = user_address_in_string (tohdr, config);
>> +	if (addr)
>> +	    return addr;
>>      }
>>  
>>      /* We get the concatenated Received: headers and search from the
>> @@ -439,19 +424,12 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>>       * header
>>       */
>>      ptr = strstr (received, " for ");
>> -    if (ptr) {
>> -	/* the text following is potentialy a list of email addresses,
>> -	 * so again we check if one of the email addresses is a
>> -	 * substring of ptr
>> -	 */
>> -	if (strcasestr(ptr, primary)) {
>> -	    return primary;
>> -	}
>> -	for (i = 0; i < other_len; i++)
>> -	    if (strcasestr (ptr, other[i])) {
>> -		return other[i];
>> -	    }
>> -    }
>> +
>> +    /* Note: ptr potentially contains a list of email addresses. */
>> +    addr = user_address_in_string (ptr, config);
>> +    if (addr)
>> +	return addr;
>> +
>>      /* Finally, we parse all the " by MTA ..." headers to guess the
>>       * email address that this was originally delivered to.
>>       * We extract just the MTA here by removing leading whitespace and
>> @@ -492,15 +470,11 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message
>>  	     */
>>  	    *(tld-1) = '.';
>>  
>> -	    if (strcasestr(primary, domain)) {
>> -		free(mta);
>> -		return primary;
>> +	    addr = string_in_user_address (domain, config);
>> +	    if (addr) {
>> +		free (mta);
>> +		return addr;
>>  	    }
>> -	    for (i = 0; i < other_len; i++)
>> -		if (strcasestr (other[i],domain)) {
>> -		    free(mta);
>> -		    return other[i];
>> -		}
>>  	}
>>  	free (mta);
>>      }

Re: [PATCH 1/2] cli: add user address matching helpers for notmuch reply

[David Bremner]

Jani Nikula <jani@nikula.org> writes:

> Add a multi-purpose address_match() function for matching strings
> against user's configured primary and other email addresses. Add thin
> wrappers user_address_in_string() and string_in_user_address() for
> ease of use, and also convert existing address_is_users() to wrapper
> for the same.

pushed

d

P.S. I marked the other series as stale.