[PATCH] lib: add 'body:' field, stop indexing headers twice.

Subject: [PATCH] lib: add 'body:' field, stop indexing headers twice.

Date: Sun, 3 Mar 2019 22:29:12 -0400

To: David Bremner, notmuch@notmuchmail.org

Cc:

From: David Bremner

The new `body:` field (in Xapian terms) or prefix (in slightly
sloppier notmuch) terms allows matching terms that occur only in the
body.

Unprefixed query terms should continue to match anywhere (header or
body) in the message.

This follows a suggestion of Olly Betts to use the facility (since
Xapian 1.0.4) to add the same field with multiple prefixes. The double
indexing of previous versions is thus replaced with a query time
expension of unprefixed query terms to the various prefixed
equivalent.

Reindexing will be needed for negated 'body:' searches to work
correctly.
---
 doc/man7/notmuch-search-terms.rst |  5 +++-
 lib/database.cc                   |  6 +++++
 lib/message.cc                    | 10 +++----
 test/T730-body.sh                 | 43 +++++++++++++++++++++++++++++++
 4 files changed, 58 insertions(+), 6 deletions(-)
 create mode 100755 test/T730-body.sh

diff --git a/doc/man7/notmuch-search-terms.rst b/doc/man7/notmuch-search-terms.rst
index f7a39ceb..fd8bf634 100644
--- a/doc/man7/notmuch-search-terms.rst
+++ b/doc/man7/notmuch-search-terms.rst
@@ -44,6 +44,9 @@ results to those whose value matches a regular expression (see
 
    notmuch search 'from:"/bob@.*[.]example[.]com/"'
 
+body:<word-or-quoted-phrase>
+    Match terms in the body of messages.
+
 from:<name-or-address> or from:/<regex>/
     The **from:** prefix is used to match the name or address of
     the sender of an email message.
@@ -249,7 +252,7 @@ follows.
 Boolean
    **tag:**, **id:**, **thread:**, **folder:**, **path:**, **property:**
 Probabilistic
-  **to:**, **attachment:**, **mimetype:**
+  **body:**, **to:**, **attachment:**, **mimetype:**
 Special
    **from:**, **query:**, **subject:**
 
diff --git a/lib/database.cc b/lib/database.cc
index 9cf8062c..27c2d042 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -259,6 +259,8 @@ prefix_t prefix_table[] = {
     { "directory",		"XDIRECTORY",	NOTMUCH_FIELD_NO_FLAGS },
     { "file-direntry",		"XFDIRENTRY",	NOTMUCH_FIELD_NO_FLAGS },
     { "directory-direntry",	"XDDIRENTRY",	NOTMUCH_FIELD_NO_FLAGS },
+    { "body",			"",		NOTMUCH_FIELD_EXTERNAL |
+						NOTMUCH_FIELD_PROBABILISTIC},
     { "thread",			"G",		NOTMUCH_FIELD_EXTERNAL |
 						NOTMUCH_FIELD_PROCESSOR },
     { "tag",			"K",		NOTMUCH_FIELD_EXTERNAL |
@@ -302,6 +304,8 @@ prefix_t prefix_table[] = {
 static void
 _setup_query_field_default (const prefix_t *prefix, notmuch_database_t *notmuch)
 {
+    if (prefix->prefix)
+	notmuch->query_parser->add_prefix("",prefix->prefix);
     if (prefix->flags & NOTMUCH_FIELD_PROBABILISTIC)
 	notmuch->query_parser->add_prefix (prefix->name, prefix->prefix);
     else
@@ -326,6 +330,8 @@ _setup_query_field (const prefix_t *prefix, notmuch_database_t *notmuch)
 					    *notmuch->query_parser, notmuch))->release ();
 
 	/* we treat all field-processor fields as boolean in order to get the raw input */
+	if (prefix->prefix)
+	    notmuch->query_parser->add_prefix("",prefix->prefix);
 	notmuch->query_parser->add_boolean_prefix (prefix->name, fp);
     } else {
 	_setup_query_field_default (prefix, notmuch);
diff --git a/lib/message.cc b/lib/message.cc
index 6f2f6345..64349f83 100644
--- a/lib/message.cc
+++ b/lib/message.cc
@@ -1443,13 +1443,13 @@ _notmuch_message_gen_terms (notmuch_message_t *message,
 	message->termpos = term_gen->get_termpos () + 100;
 
 	_notmuch_message_invalidate_metadata (message, prefix_name);
+    } else {
+	term_gen->set_termpos (message->termpos);
+	term_gen->index_text (text);
+	/* Create a term gap, as above. */
+	message->termpos = term_gen->get_termpos () + 100;
     }
 
-    term_gen->set_termpos (message->termpos);
-    term_gen->index_text (text);
-    /* Create a term gap, as above. */
-    message->termpos = term_gen->get_termpos () + 100;
-
     return NOTMUCH_PRIVATE_STATUS_SUCCESS;
 }
 
diff --git a/test/T730-body.sh b/test/T730-body.sh
new file mode 100755
index 00000000..548b30a4
--- /dev/null
+++ b/test/T730-body.sh
@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+test_description='search body'
+. $(dirname "$0")/test-lib.sh || exit 1
+
+add_message "[body]=thebody-1" "[subject]=subject-1"
+add_message "[body]=nothing-to-see-here-1" "[subject]=thebody-1"
+
+test_begin_subtest 'search with body: prefix'
+notmuch search body:thebody | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; subject-1 (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'search without body: prefix'
+notmuch search thebody | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; subject-1 (inbox unread)
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; thebody-1 (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'negated body: prefix'
+notmuch search thebody and not body:thebody | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; thebody-1 (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'search unprefixed for prefixed term'
+notmuch search subject | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; subject-1 (inbox unread)
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'search with body: prefix for term only in subject'
+notmuch search body:subject | notmuch_search_sanitize > OUTPUT
+cat <<EOF > EXPECTED
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_done
-- 
2.20.1

_______________________________________________
notmuch mailing list
notmuch@notmuchmail.org
https://notmuchmail.org/mailman/listinfo/notmuch

Thread: