[PATCH 19/25] lib/parse-sexp: add support for regexp fields

Subject: [PATCH 19/25] lib/parse-sexp: add support for regexp fields

Date: Sat, 17 Jul 2021 23:40:15 -0300

To: notmuch@notmuchmail.org

Cc: David Bremner

From: David Bremner


This commit connects the previously added keyword / flag handling with
the previously refactored regexp to query refactoring.
---
 lib/parse-sexp.cc         | 35 +++++++++++++++--------
 lib/regexp-fields.h       |  8 +++---
 test/T081-sexpr-search.sh | 59 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 86 insertions(+), 16 deletions(-)

diff --git a/lib/parse-sexp.cc b/lib/parse-sexp.cc
index 95ee7c99..c0d0b596 100644
--- a/lib/parse-sexp.cc
+++ b/lib/parse-sexp.cc
@@ -1,8 +1,8 @@
-#include <xapian.h>
-#include "notmuch-private.h"
+#include "database-private.h"
 #include "sexp.h"
 #include "parse-time-vrp.h"
 #include "query-fp.h"
+#include "regexp-fields.h"
 
 typedef struct  {
     const char *name;
@@ -13,6 +13,7 @@ typedef struct  {
 typedef enum {
     SEXP_FLAG_NONE	= 0,
     SEXP_FLAG_WILDCARD	= 1 << 0,
+    SEXP_FLAG_REGEXP	= 1 << 1,
 } _sexp_flag_t;
 
 /*
@@ -51,18 +52,18 @@ static _sexp_field_t fields[] =
     { "attachment",   Xapian::Query::OP_PHRASE,       SEXP_FLAG_WILDCARD },
     { "body",         Xapian::Query::OP_PHRASE,       SEXP_FLAG_NONE },
     { "date",         Xapian::Query::OP_INVALID,      SEXP_FLAG_NONE },
-    { "from",         Xapian::Query::OP_PHRASE,       SEXP_FLAG_NONE },
-    { "folder",       Xapian::Query::OP_OR,           SEXP_FLAG_NONE },
-    { "id",           Xapian::Query::OP_OR,           SEXP_FLAG_NONE },
-    { "is",           Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD },
-    { "mid",          Xapian::Query::OP_OR,           SEXP_FLAG_NONE },
+    { "from",         Xapian::Query::OP_PHRASE,       SEXP_FLAG_REGEXP },
+    { "folder",       Xapian::Query::OP_OR,           SEXP_FLAG_REGEXP },
+    { "id",           Xapian::Query::OP_OR,           SEXP_FLAG_REGEXP },
+    { "is",           Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEXP },
+    { "mid",          Xapian::Query::OP_OR,           SEXP_FLAG_REGEXP },
     { "mimetype",     Xapian::Query::OP_PHRASE,       SEXP_FLAG_NONE },
-    { "path",         Xapian::Query::OP_OR,           SEXP_FLAG_NONE },
-    { "property",     Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD },
+    { "path",         Xapian::Query::OP_OR,           SEXP_FLAG_REGEXP },
+    { "property",     Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEXP },
     { "query",        Xapian::Query::OP_INVALID,      SEXP_FLAG_NONE },
-    { "subject",      Xapian::Query::OP_PHRASE,       SEXP_FLAG_NONE },
-    { "tag",          Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD },
-    { "thread",       Xapian::Query::OP_OR,           SEXP_FLAG_NONE },
+    { "subject",      Xapian::Query::OP_PHRASE,       SEXP_FLAG_REGEXP },
+    { "tag",          Xapian::Query::OP_AND,          SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEXP },
+    { "thread",       Xapian::Query::OP_OR,           SEXP_FLAG_REGEXP },
     { "to",           Xapian::Query::OP_PHRASE,       SEXP_FLAG_NONE },
     { }
 };
@@ -76,6 +77,7 @@ static _sexp_keyword_t keywords[] =
 {
     { "any", SEXP_FLAG_WILDCARD },
     { "*", SEXP_FLAG_WILDCARD },
+    { "rx", SEXP_FLAG_REGEXP },
     { }
 };
 
@@ -305,6 +307,15 @@ _sexp_to_xapian_query (notmuch_database_t *notmuch, const sexp_t *sx, Xapian::Qu
 		}
 		output = Xapian::Query (Xapian::Query::OP_WILDCARD, term_prefix);
 		return NOTMUCH_STATUS_SUCCESS;
+	    } else if (flags & SEXP_FLAG_REGEXP) {
+		if (! rest || ! rest->val) {
+		    _notmuch_database_log (notmuch, "missing regular expression\n");
+		    return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+		} else {
+		    std::string msg; /* ignored */
+		    return _notmuch_regexp_to_query (notmuch, Xapian::BAD_VALUENO, field->name,
+						     rest->val, output, msg);
+		}
 	    } else {
 		return _sexp_combine_field (term_prefix, field->xapian_op, rest,
 					    output);
diff --git a/lib/regexp-fields.h b/lib/regexp-fields.h
index 9c871de7..aa8fd81c 100644
--- a/lib/regexp-fields.h
+++ b/lib/regexp-fields.h
@@ -27,13 +27,13 @@
 
 #include <sys/types.h>
 #include <regex.h>
-#include "database-private.h"
 #include "notmuch-private.h"
+#include "database-private.h"
 
 notmuch_status_t
-_notmuch_regex_to_query (notmuch_database_t *notmuch, Xapian::valueno slot, std::string field,
-			 std::string regexp_str,
-			 Xapian::Query &output, std::string &msg);
+_notmuch_regexp_to_query (notmuch_database_t *notmuch, Xapian::valueno slot, std::string field,
+			  std::string regexp_str,
+			  Xapian::Query &output, std::string &msg);
 
 /* A posting source that returns documents where a value matches a
  * regexp.
diff --git a/test/T081-sexpr-search.sh b/test/T081-sexpr-search.sh
index 04eba2c0..281a9bf7 100755
--- a/test/T081-sexpr-search.sh
+++ b/test/T081-sexpr-search.sh
@@ -377,4 +377,63 @@ output=$(notmuch search --query-syntax=sexp '(subject deleted)' | notmuch_search
 test_expect_equal "$output" "thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; Not deleted (inbox unread)
 thread:XXX   2001-01-05 [2/2] Notmuch Test Suite; Deleted (deleted inbox unread)"
 
+test_begin_subtest "illegal regexp search"
+test_expect_code 1 "notmuch search --query-syntax=sexp '(body :rx foo)'"
+
+notmuch search --output=messages from:cworth > cworth.msg-ids
+
+test_begin_subtest "regexp 'folder' search"
+notmuch search 'folder:/^bar$/' | notmuch_search_sanitize > EXPECTED
+notmuch search --query-syntax=sexp '(folder :rx ^bar$)' | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "regexp from search"
+notmuch search --output=messages --query-syntax=sexp '(from :rx cworth)' > OUTPUT
+test_expect_equal_file cworth.msg-ids OUTPUT
+
+test_begin_subtest "regexp search for 'from' 2"
+notmuch search from:/cworth@cworth.org/ and subject:patch | notmuch_search_sanitize > EXPECTED
+notmuch search --query-syntax=sexp '(and (from :rx cworth@cworth.org) (subject patch))' \
+    | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "regexp 'id' search"
+notmuch search --output=messages --query-syntax=sexp '(id :rx yoom)' > OUTPUT
+test_expect_equal_file cworth.msg-ids OUTPUT
+
+test_begin_subtest "unanchored 'is' search"
+notmuch search tag:signed or tag:inbox > EXPECTED
+notmuch search --query-syntax=sexp '(is :rx i)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "anchored 'is' search"
+notmuch search tag:signed > EXPECTED
+notmuch search --query-syntax=sexp '(is :rx ^si)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "combine regexp mid and subject"
+notmuch search subject:/-C/ and mid:/y..m/ | notmuch_search_sanitize > EXPECTED
+notmuch search --query-syntax=sexp '(and (subject :rx -C) (mid :rx y..m))' | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "regexp 'path' search"
+notmuch search 'path:/^bar$/' | notmuch_search_sanitize > EXPECTED
+notmuch search --query-syntax=sexp '(path :rx ^bar$)' | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "regexp 'property' search"
+notmuch search property:foo=bar > EXPECTED
+notmuch search --query-syntax=sexp '(property :rx foo=.*)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "anchored 'tag' search"
+notmuch search tag:signed > EXPECTED
+notmuch search --query-syntax=sexp '(tag :rx ^si)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "regexp 'thread' search"
+notmuch search --output=threads '*' | grep '7$' > EXPECTED
+notmuch search --output=threads --query-syntax=sexp '(thread :rx 7$)' > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
 test_done
-- 
2.30.2
_______________________________________________
notmuch mailing list -- notmuch@notmuchmail.org
To unsubscribe send an email to notmuch-leave@notmuchmail.org

Thread: