[PATCH 16/27] lib/parse-sexp: handle unprefixed terms.

Subject:[PATCH 16/27] lib/parse-sexp: handle unprefixed terms.

Date:Fri, 30 Jul 2021 09:55:56 -0300

To:notmuch@notmuchmail.org

Cc:David Bremner

From:David Bremner


This is equivalent to adding the same field name "" for multiple
prefixes in the Xapian query parser, but we have to explicitely
construct the resulting query.
---
 lib/parse-sexp.cc         | 36 ++++++++++++++++++++++++++++++++----
 test/T081-sexpr-search.sh | 35 +++++++++++++++++++++++++++++++----
 2 files changed, 63 insertions(+), 8 deletions(-)

diff --git a/lib/parse-sexp.cc b/lib/parse-sexp.cc
index caffbe59..56bd7e4b 100644
--- a/lib/parse-sexp.cc
+++ b/lib/parse-sexp.cc
@@ -164,6 +164,22 @@ _sexp_parse_wildcard (notmuch_database_t *notmuch,
     return NOTMUCH_STATUS_SUCCESS;
 }
 
+static notmuch_status_t
+_sexp_parse_one_term (notmuch_database_t *notmuch, std::string term_prefix, const sexp_t *sx,
+		      Xapian::Query &output)
+{
+    Xapian::Stem stem = *(notmuch->stemmer);
+
+    if (sx->aty == SEXP_BASIC && unicode_word_utf8 (sx->val)) {
+	std::string term = Xapian::Unicode::tolower (sx->val);
+
+	output = Xapian::Query ("Z" + term_prefix + stem (term));
+	return NOTMUCH_STATUS_SUCCESS;
+    } else {
+	return _sexp_parse_phrase (term_prefix, sx->val, output);
+    }
+
+}
 /* Here we expect the s-expression to be a proper list, with first
  * element defining and operation, or as a special case the empty
  * list */
@@ -185,11 +201,23 @@ _sexp_to_xapian_query (notmuch_database_t *notmuch, const _sexp_prefix_t *parent
 	    output = Xapian::Query (term_prefix + sx->val);
 	    return NOTMUCH_STATUS_SUCCESS;
 	}
-	if (sx->aty == SEXP_BASIC && unicode_word_utf8 (sx->val)) {
-	    output = Xapian::Query ("Z" + term_prefix + stem (term));
-	    return NOTMUCH_STATUS_SUCCESS;
+	if (parent) {
+	    return _sexp_parse_one_term (notmuch, term_prefix, sx, output);
 	} else {
-	    return _sexp_parse_phrase (term_prefix, sx->val, output);
+	    Xapian::Query accumulator;
+	    for (_sexp_prefix_t *prefix = prefixes; prefix->name; prefix++) {
+		if (prefix->flags & SEXP_FLAG_FIELD) {
+		    notmuch_status_t status;
+		    Xapian::Query subquery;
+		    term_prefix = _find_prefix (prefix->name);
+		    status = _sexp_parse_one_term (notmuch, term_prefix, sx, subquery);
+		    if (status)
+			return status;
+		    accumulator = Xapian::Query (Xapian::Query::OP_OR, accumulator, subquery);
+		}
+	    }
+	    output = accumulator;
+	    return NOTMUCH_STATUS_SUCCESS;
 	}
     }
 
diff --git a/test/T081-sexpr-search.sh b/test/T081-sexpr-search.sh
index 8ec585bb..13b47324 100755
--- a/test/T081-sexpr-search.sh
+++ b/test/T081-sexpr-search.sh
@@ -111,6 +111,10 @@ add_message '[subject]="body search"' '[date]="Sat, 01 Jan 2000 12:00:00 -0000"'
 output=$(notmuch search --query-syntax=sexp '(body bodysearchtest)' | notmuch_search_sanitize)
 test_expect_equal "$output" "thread:XXX   2000-01-01 [1/1] Notmuch Test Suite; body search (inbox unread)"
 
+test_begin_subtest "Search by body (unprefixed)"
+output=$(notmuch search --query-syntax=sexp '(and bodysearchtest)' | notmuch_search_sanitize)
+test_expect_equal "$output" "thread:XXX   2000-01-01 [1/1] Notmuch Test Suite; body search (inbox unread)"
+
 test_begin_subtest "Search by 'body' (phrase)"
 add_message '[subject]="body search (phrase)"' '[date]="Sat, 01 Jan 2000 12:00:00 -0000"' '[body]="body search (phrase)"'
 add_message '[subject]="negative result"' '[date]="Sat, 01 Jan 2000 12:00:00 -0000"' '[body]="This phrase should not match the body search"'
@@ -122,6 +126,29 @@ add_message '[subject]="utf8-message-body-subject"' '[date]="Sat, 01 Jan 2000 12
 output=$(notmuch search --query-syntax=sexp '(body bödý)' | notmuch_search_sanitize)
 test_expect_equal "$output" "thread:XXX   2000-01-01 [1/1] Notmuch Test Suite; utf8-message-body-subject (inbox unread)"
 
+add_message "[body]=thebody-1" "[subject]=kryptonite-1"
+add_message "[body]=nothing-to-see-here-1" "[subject]=thebody-1"
+
+test_begin_subtest 'search without body: prefix'
+notmuch search thebody > EXPECTED
+notmuch search --query-syntax=sexp '(and thebody)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'negated body: prefix'
+notmuch search thebody and not body:thebody > EXPECTED
+notmuch search --query-syntax=sexp '(and (not (body thebody)) thebody)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'search unprefixed for prefixed term'
+notmuch search kryptonite > EXPECTED
+notmuch search --query-syntax=sexp '(and kryptonite)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest 'search with body: prefix for term only in subject'
+notmuch search body:kryptonite > EXPECTED
+notmuch search --query-syntax=sexp '(body kryptonite)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
 test_begin_subtest "Search by 'from'"
 add_message '[subject]="search by from"' '[date]="Sat, 01 Jan 2000 12:00:00 -0000"' [from]=searchbyfrom
 output=$(notmuch search --query-syntax=sexp '(from searchbyfrom)' | notmuch_search_sanitize)
@@ -287,11 +314,11 @@ output=$(notmuch search --query-syntax=sexp '(attachment (starts-with not))' | n
 test_expect_equal "$output" 'thread:XXX   2009-11-18 [2/2] Lars Kellogg-Stedman; [notmuch] "notmuch help" outputs to stderr? (attachment inbox signed unread)'
 
 test_begin_subtest "starts-with, folder"
-notmuch search --output=files --query-syntax=sexp '(folder (starts-with bad))' | notmuch_dir_sanitize > OUTPUT
+notmuch search --output=files --query-syntax=sexp '(folder (starts-with bad))' | notmuch_dir_sanitize | sed 's/[0-9]*$/XXX/' > OUTPUT
 cat <<EOF > EXPECTED
-MAIL_DIR/bad/msg-010
-MAIL_DIR/bad/news/msg-012
-MAIL_DIR/duplicate/bad/news/msg-012
+MAIL_DIR/bad/msg-XXX
+MAIL_DIR/bad/news/msg-XXX
+MAIL_DIR/duplicate/bad/news/msg-XXX
 EOF
 test_expect_equal_file EXPECTED OUTPUT
 
-- 
2.30.2
_______________________________________________
notmuch mailing list -- notmuch@notmuchmail.org
To unsubscribe send an email to notmuch-leave@notmuchmail.org

Thread: