From 42865570a76373c1d9639242e11a5629bd7494b7 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Sat, 30 Nov 2013 17:33:51 +0200 Subject: [PATCH] [PATCH v2 2/7] cli: refactor reply from guessing --- c2/bf6053828a9574bf8e19564c55840d90babdd1 | 304 ++++++++++++++++++++++ 1 file changed, 304 insertions(+) create mode 100644 c2/bf6053828a9574bf8e19564c55840d90babdd1 diff --git a/c2/bf6053828a9574bf8e19564c55840d90babdd1 b/c2/bf6053828a9574bf8e19564c55840d90babdd1 new file mode 100644 index 000000000..d9cf43527 --- /dev/null +++ b/c2/bf6053828a9574bf8e19564c55840d90babdd1 @@ -0,0 +1,304 @@ +Return-Path: +X-Original-To: notmuch@notmuchmail.org +Delivered-To: notmuch@notmuchmail.org +Received: from localhost (localhost [127.0.0.1]) + by olra.theworths.org (Postfix) with ESMTP id 583E4431FDB + for ; Sat, 30 Nov 2013 07:34:16 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Amavis-Alert: BAD HEADER SECTION, Duplicate header field: "References" +X-Spam-Flag: NO +X-Spam-Score: -0.7 +X-Spam-Level: +X-Spam-Status: No, score=-0.7 tagged_above=-999 required=5 + tests=[RCVD_IN_DNSWL_LOW=-0.7] autolearn=disabled +Received: from olra.theworths.org ([127.0.0.1]) + by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) + with ESMTP id XzhUjj97E1Rg for ; + Sat, 30 Nov 2013 07:34:09 -0800 (PST) +Received: from mail-ea0-f172.google.com (mail-ea0-f172.google.com + [209.85.215.172]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 3F7B6431FBC + for ; Sat, 30 Nov 2013 07:34:06 -0800 (PST) +Received: by mail-ea0-f172.google.com with SMTP id q10so7520437ead.17 + for ; Sat, 30 Nov 2013 07:34:05 -0800 (PST) +X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; + d=1e100.net; s=20130820; + h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to + :references:in-reply-to:references; + bh=zoe9OLsyJ3LsuNeOyW7iaJql4J5nfEBgb4WIHrp3w80=; + b=AlrPC0vcIV01vOF6eqvsnr+4wAPHrRBG+TC8E3lmkI9VPFWepaZYZueBHt7K9sWF1a + 8zOI491KcMpOTxHJNW6a0ugdwRnHPzUZ9ZAWNSTwfoZij2HAtMa8n9F4NiM47eb1EvbG + 7gb1iYMuMEEd9sOE6Gu34cwT6rzXKmr4ST2K/okE/BWL4iM25LU1jDHmm4WXWksGcWjJ + RhltnRci+qhxfzLIrR9KceecJhfqBWyrp9CQIOSOODYW94sP0lBaZhx4D5aGKGe2dXbJ + IiqQi7teBOJ8K0qcw1QbqZOvQ/uQfGVOcHH0jWrz0AgmXOs1705MaGqS4p86KWOJAOLh + BDoQ== +X-Gm-Message-State: + ALoCoQkxdJzqLxjO6L8RyLdoRYc4yowXg5yJ3+vyz7N/bbGrBx4ci+d6GYS/saYeq+Znhz/5Y7X/ +X-Received: by 10.15.101.9 with SMTP id bo9mr7572255eeb.32.1385825645230; + Sat, 30 Nov 2013 07:34:05 -0800 (PST) +Received: from localhost (dsl-hkibrasgw2-58c36f-91.dhcp.inet.fi. + [88.195.111.91]) by mx.google.com with ESMTPSA id + o47sm52032280eem.21.2013.11.30.07.34.03 for + (version=TLSv1.2 cipher=RC4-SHA bits=128/128); + Sat, 30 Nov 2013 07:34:04 -0800 (PST) +From: Jani Nikula +To: notmuch@notmuchmail.org +Subject: [PATCH v2 2/7] cli: refactor reply from guessing +Date: Sat, 30 Nov 2013 17:33:51 +0200 +Message-Id: + +X-Mailer: git-send-email 1.8.4.2 +In-Reply-To: +References: +In-Reply-To: +References: +X-BeenThere: notmuch@notmuchmail.org +X-Mailman-Version: 2.1.13 +Precedence: list +List-Id: "Use and development of the notmuch mail system." + +List-Unsubscribe: , + +List-Archive: +List-Post: +List-Help: +List-Subscribe: , + +X-List-Received-Date: Sat, 30 Nov 2013 15:34:16 -0000 + +The guess_from_received_header() function had grown quite big. Chop it +up into smaller functions. + +No functional changes. +--- + notmuch-reply.c | 178 +++++++++++++++++++++++++++++++++----------------------- + 1 file changed, 105 insertions(+), 73 deletions(-) + +diff --git a/notmuch-reply.c b/notmuch-reply.c +index 9d6f843..ca41405 100644 +--- a/notmuch-reply.c ++++ b/notmuch-reply.c +@@ -369,78 +369,44 @@ add_recipients_from_message (GMimeMessage *reply, + return from_addr; + } + ++/* ++ * Look for the user's address in " for " in the ++ * received headers. ++ * ++ * Return the address that was found, if any, and NULL otherwise. ++ */ + static const char * +-guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message) ++guess_from_received_for (notmuch_config_t *config, const char *received) + { +- const char *addr, *received, *by; +- char *mta,*ptr,*token; +- char *domain=NULL; +- char *tld=NULL; +- const char *delim=". \t"; +- size_t i; +- +- const char *to_headers[] = { +- "Envelope-to", +- "X-Original-To", +- "Delivered-To", +- }; +- +- /* 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 +- * heuristics which hopefully will answer this question. +- +- * We only got here if none of the users email addresses are in +- * the To: or Cc: header. From here we try the following in order: +- * 1) check for an Envelope-to: header +- * 2) check for an X-Original-To: header +- * 3) check for a Delivered-To: header +- * 4) check for a (for ) clause in Received: headers +- * 5) check for the domain part of known email addresses in the +- * 'by' part of Received headers +- * If none of these work, we give up and return NULL +- */ +- 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; +- } ++ const char *ptr; + +- /* We get the concatenated Received: headers and search from the +- * front (last Received: header added) and try to extract from +- * them indications to which email address this message was +- * delivered. +- * The Received: header is special in our get_header function +- * and is always concatenated. +- */ +- received = notmuch_message_get_header (message, "received"); +- if (received == NULL) ++ ptr = strstr (received, " for "); ++ if (! ptr) + return NULL; + +- /* First we look for a " for " in the received +- * header +- */ +- ptr = strstr (received, " for "); ++ return user_address_in_string (ptr, config); ++} + +- /* 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 +- * assuming that the MTA name ends at the next whitespace. +- * We test for *(by+4) to be non-'\0' to make sure there's +- * something there at all - and then assume that the first +- * whitespace delimited token that follows is the receiving +- * system in this step of the receive chain +- */ +- by = received; +- while((by = strstr (by, " by ")) != NULL) { ++/* ++ * Parse all the " by MTA ..." parts in received headers to guess the ++ * email address that this was originally delivered to. ++ * ++ * Extract just the MTA here by removing leading whitespace and ++ * assuming that the MTA name ends at the next whitespace. Test for ++ * *(by+4) to be non-'\0' to make sure there's something there at all ++ * - and then assume that the first whitespace delimited token that ++ * follows is the receiving system in this step of the receive chain. ++ * ++ * Return the address that was found, if any, and NULL otherwise. ++ */ ++static const char * ++guess_from_received_by (notmuch_config_t *config, const char *received) ++{ ++ const char *addr; ++ const char *by = received; ++ char *domain, *tld, *mta, *ptr, *token; ++ ++ while ((by = strstr (by, " by ")) != NULL) { + by += 4; + if (*by == '\0') + break; +@@ -454,7 +420,7 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message + * as domain and tld. + */ + domain = tld = NULL; +- while ((ptr = strsep (&token, delim)) != NULL) { ++ while ((ptr = strsep (&token, ". \t")) != NULL) { + if (*ptr == '\0') + continue; + domain = tld; +@@ -462,13 +428,13 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message + } + + if (domain) { +- /* Recombine domain and tld and look for it among the configured +- * email addresses. +- * This time we have a known domain name and nothing else - so +- * the test is the other way around: we check if this is a +- * substring of one of the email addresses. ++ /* Recombine domain and tld and look for it among the ++ * configured email addresses. This time we have a known ++ * domain name and nothing else - so the test is the other ++ * way around: we check if this is a substring of one of ++ * the email addresses. + */ +- *(tld-1) = '.'; ++ *(tld - 1) = '.'; + + addr = string_in_user_address (domain, config); + if (addr) { +@@ -482,6 +448,63 @@ guess_from_received_header (notmuch_config_t *config, notmuch_message_t *message + return NULL; + } + ++/* ++ * Get the concatenated Received: headers and search from the front ++ * (last Received: header added) and try to extract from them ++ * indications to which email address this message was delivered. ++ * ++ * The Received: header is special in our get_header function and is ++ * always concatenated. ++ * ++ * Return the address that was found, if any, and NULL otherwise. ++ */ ++static const char * ++guess_from_received_header (notmuch_config_t *config, ++ notmuch_message_t *message) ++{ ++ const char *received, *addr; ++ ++ received = notmuch_message_get_header (message, "received"); ++ if (! received) ++ return NULL; ++ ++ addr = guess_from_received_for (config, received); ++ if (! addr) ++ addr = guess_from_received_by (config, received); ++ ++ return addr; ++} ++ ++/* ++ * Try to find user's email address in one of the extra To-like ++ * headers, such as Envelope-To, X-Original-To, and ++ * Delivered-To. ++ * ++ * Return the address that was found, if any, and NULL otherwise. ++ */ ++static const char * ++from_from_to_headers (notmuch_config_t *config, notmuch_message_t *message) ++{ ++ size_t i; ++ const char *tohdr, *addr; ++ const char *to_headers[] = { ++ "Envelope-to", ++ "X-Original-To", ++ "Delivered-To", ++ }; ++ ++ for (i = 0; i < ARRAY_SIZE (to_headers); i++) { ++ 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; ++ } ++ ++ return NULL; ++} ++ + static GMimeMessage * + create_reply_message(void *ctx, + notmuch_config_t *config, +@@ -508,6 +531,15 @@ create_reply_message(void *ctx, + from_addr = add_recipients_from_message (reply, config, + message, reply_all); + ++ /* ++ * 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 ++ * heuristics which hopefully will answer this question. ++ */ ++ if (from_addr == NULL) ++ from_addr = from_from_to_headers (config, message); ++ + if (from_addr == NULL) + from_addr = guess_from_received_header (config, message); + +-- +1.8.4.2 + -- 2.26.2