[PATCH 1/2] lib: Add regexp searching for mid: prefix

Subject: [PATCH 1/2] lib: Add regexp searching for mid: prefix

Date: Fri, 24 Mar 2017 09:14:35 -0300

To: notmuch@notmuchmail.org

Cc:

From: David Bremner


The bulk of the change is passing in the field options to the regexp
field processor, so that we can properly handle the
fallback (non-regexp case).
---
 doc/man7/notmuch-search-terms.rst | 26 +++++++++++++++-----------
 lib/database.cc                   |  6 ++++--
 lib/regexp-fields.cc              | 22 +++++++++++++++++-----
 lib/regexp-fields.h               |  4 +++-
 test/T650-regexp-query.sh         | 16 ++++++++++++++++
 5 files changed, 55 insertions(+), 19 deletions(-)

diff --git a/doc/man7/notmuch-search-terms.rst b/doc/man7/notmuch-search-terms.rst
index 47cab48d..a8ba5e02 100644
--- a/doc/man7/notmuch-search-terms.rst
+++ b/doc/man7/notmuch-search-terms.rst
@@ -50,6 +50,10 @@ indicate user-supplied values):
 
 -  id:<message-id>
 
+-  mid:<message-id>
+
+-  mid:/<regex>/
+
 -  thread:<thread-id>
 
 -  folder:<maildir-folder>
@@ -75,15 +79,6 @@ subject of an email. Searching for a phrase in the subject is supported
 by including quotation marks around the phrase, immediately following
 **subject:**.
 
-If notmuch is built with **Xapian Field Processors** (see below) the
-**from:** and **subject** prefix can be also used to restrict the
-results to those whose from/subject value matches a regular expression
-(see **regex(7)**) delimited with //.
-
-::
-
-   notmuch search 'from:/bob@.*[.]example[.]com/'
-
 The **attachment:** prefix can be used to search for specific filenames
 (or extensions) of attachments to email messages.
 
@@ -95,8 +90,8 @@ For **tag:** and **is:** valid tag values include **inbox** and
 **unread** by default for new messages added by **notmuch new** as well
 as any other tag values added manually with **notmuch tag**.
 
-For **id:**, message ID values are the literal contents of the
-Message-ID: header of email messages, but without the '<', '>'
+For **id:** and **mid**, message ID values are the literal contents of
+the Message-ID: header of email messages, but without the '<', '>'
 delimiters.
 
 The **thread:** prefix can be used with the thread ID values that are
@@ -159,6 +154,15 @@ The **property:** prefix searches for messages with a particular
 (and extensions) to add metadata to messages. A given key can be
 present on a given message with several different values.
 
+If notmuch is built with **Xapian Field Processors** (see below) the
+**from:**, **mid:** (but not **id:**), and **subject** prefix can be
+also used to restrict the results to those whose from/subject value
+matches a regular expression (see **regex(7)**) delimited with //.
+
+::
+
+   notmuch search 'from:/bob@.*[.]example[.]com/'
+
 Operators
 ---------
 
diff --git a/lib/database.cc b/lib/database.cc
index 5bc131a3..49b3849c 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -262,7 +262,8 @@ prefix_t prefix_table[] = {
     { "tag",			"K",		NOTMUCH_FIELD_EXTERNAL },
     { "is",			"K",		NOTMUCH_FIELD_EXTERNAL },
     { "id",			"Q",		NOTMUCH_FIELD_EXTERNAL },
-    { "mid",			"Q",		NOTMUCH_FIELD_EXTERNAL },
+    { "mid",			"Q",		NOTMUCH_FIELD_EXTERNAL |
+						NOTMUCH_FIELD_PROCESSOR },
     { "path",			"P",		NOTMUCH_FIELD_EXTERNAL },
     { "property",		"XPROPERTY",	NOTMUCH_FIELD_EXTERNAL },
     /*
@@ -313,7 +314,8 @@ _setup_query_field (const prefix_t *prefix, notmuch_database_t *notmuch)
 	else if (STRNCMP_LITERAL(prefix->name, "query") == 0)
 	    fp = (new QueryFieldProcessor (*notmuch->query_parser, notmuch))->release ();
 	else
-	    fp = (new RegexpFieldProcessor (prefix->name, *notmuch->query_parser, notmuch))->release ();
+	    fp = (new RegexpFieldProcessor (prefix->name, prefix->flags,
+					    *notmuch->query_parser, notmuch))->release ();
 
 	/* we treat all field-processor fields as boolean in order to get the raw input */
 	notmuch->query_parser->add_boolean_prefix (prefix->name, fp);
diff --git a/lib/regexp-fields.cc b/lib/regexp-fields.cc
index 08c6ccb5..fb1e951f 100644
--- a/lib/regexp-fields.cc
+++ b/lib/regexp-fields.cc
@@ -135,21 +135,33 @@ static inline Xapian::valueno _find_slot (std::string prefix)
 	return NOTMUCH_VALUE_FROM;
     else if (prefix == "subject")
 	return NOTMUCH_VALUE_SUBJECT;
+    else if (prefix == "mid")
+	return NOTMUCH_VALUE_MESSAGE_ID;
     else
 	throw Xapian::QueryParserError ("unsupported regexp field '" + prefix + "'");
 }
 
-RegexpFieldProcessor::RegexpFieldProcessor (std::string prefix, Xapian::QueryParser &parser_, notmuch_database_t *notmuch_)
-	: slot (_find_slot (prefix)), term_prefix (_find_prefix (prefix.c_str ())),
-	  parser (parser_), notmuch (notmuch_)
+RegexpFieldProcessor::RegexpFieldProcessor (std::string prefix,
+					    notmuch_field_flag_t options_,
+					    Xapian::QueryParser &parser_,
+					    notmuch_database_t *notmuch_)
+	: slot (_find_slot (prefix)),
+	  term_prefix (_find_prefix (prefix.c_str ())),
+	  options (options_),
+	  parser (parser_),
+	  notmuch (notmuch_)
 {
 };
 
 Xapian::Query
 RegexpFieldProcessor::operator() (const std::string & str)
 {
-    if (str.size () == 0)
-	return Xapian::Query::MatchAll;
+    if (str.size () == 0) {
+	if (options & NOTMUCH_FIELD_PROBABILISTIC)
+	    return Xapian::Query::MatchAll;
+	else
+	    return Xapian::Query(term_prefix);
+    }
 
     if (str.at (0) == '/') {
 	if (str.at (str.size () - 1) == '/'){
diff --git a/lib/regexp-fields.h b/lib/regexp-fields.h
index a4ba7ad8..d5f93445 100644
--- a/lib/regexp-fields.h
+++ b/lib/regexp-fields.h
@@ -65,11 +65,13 @@ class RegexpFieldProcessor : public Xapian::FieldProcessor {
  protected:
     Xapian::valueno slot;
     std::string term_prefix;
+    notmuch_field_flag_t options;
     Xapian::QueryParser &parser;
     notmuch_database_t *notmuch;
 
  public:
-    RegexpFieldProcessor (std::string prefix, Xapian::QueryParser &parser_, notmuch_database_t *notmuch_);
+    RegexpFieldProcessor (std::string prefix, notmuch_field_flag_t options,
+			  Xapian::QueryParser &parser_, notmuch_database_t *notmuch_);
 
     ~RegexpFieldProcessor () { };
 
diff --git a/test/T650-regexp-query.sh b/test/T650-regexp-query.sh
index 05c244c9..5bd24086 100755
--- a/test/T650-regexp-query.sh
+++ b/test/T650-regexp-query.sh
@@ -94,4 +94,20 @@ Query string was: from:/unbalanced[/
 EOF
 test_expect_equal_file EXPECTED OUTPUT
 
+test_begin_subtest "empty mid search"
+notmuch search --output=messages mid:yoom > OUTPUT
+cp /dev/null EXPECTED
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "non-empty mid regex search"
+notmuch search --output=messages mid:/yoom/ > OUTPUT
+test_expect_equal_file cworth.msg-ids OUTPUT
+
+test_begin_subtest "combine regexp mid and subject"
+notmuch search  subject:/-C/ and mid:/y..m/ | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2009-11-18 [1/2] Carl Worth| Jan Janak; [notmuch] [PATCH] Older versions of install do not support -C. (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
 test_done
-- 
2.11.0


Thread: