Expr/Val: Add support for in set[pattern]

src/Expr.cc

@@ -3815,12 +3815,12 @@ InExpr::InExpr(ExprPtr arg_op1, ExprPtr arg_op2) : BinaryExpr(EXPR_IN, std::move
         }
     }
 
-    // Support <string> in table[pattern] of X
+    // Support <string> in table[pattern] / set[pattern]
     if ( op1->GetType()->Tag() == TYPE_STRING ) {
         if ( op2->GetType()->Tag() == TYPE_TABLE ) {
             const auto& table_type = op2->GetType()->AsTableType();
 
-            if ( table_type->IsPatternIndex() && table_type->Yield() ) {
+            if ( table_type->IsPatternIndex() ) {
                 SetType(base_type(TYPE_BOOL));
                 return;
             }
@@ -3868,8 +3868,9 @@ ValPtr InExpr::Fold(Val* v1, Val* v2) const {
     else {
         const auto& table_val = v2->AsTableVal();
         const auto& table_type = table_val->GetType<zeek::TableType>();
-        if ( table_type->IsPatternIndex() && table_type->Yield() && v1->GetType()->Tag() == TYPE_STRING )
-            res = table_val->LookupPattern({NewRef{}, v1->AsStringVal()})->Size() > 0;
+        // Special table[pattern] / set[pattern] in expression.
+        if ( table_type->IsPatternIndex() && v1->GetType()->Tag() == TYPE_STRING )
+            res = table_val->MatchPattern({NewRef{}, v1->AsStringVal()});
         else
             res = (bool)v2->AsTableVal()->Find({NewRef{}, v1});
     }

src/Val.cc

@@ -1443,6 +1443,9 @@ public:
 
     VectorValPtr Lookup(const StringValPtr& s);
 
+    // Delegate to matcher->MatchAll().
+    bool MatchAll(const StringValPtr& s);
+
     void GetStats(detail::DFA_State_Cache_Stats* stats) const {
         if ( matcher && matcher->DFA() )
             matcher->DFA()->Cache()->GetStats(stats);
@@ -1490,6 +1493,17 @@ VectorValPtr detail::TablePatternMatcher::Lookup(const StringValPtr& s) {
     return results;
 }
 
+bool detail::TablePatternMatcher::MatchAll(const StringValPtr& s) {
+    if ( ! matcher ) {
+        if ( tbl->Get()->Length() == 0 )
+            return false;
+
+        Build();
+    }
+
+    return matcher->MatchAll(s->AsString());
+}
+
 void detail::TablePatternMatcher::Build() {
     matcher_yields.clear();
     matcher_yields.push_back(nullptr);
@@ -1556,7 +1570,7 @@ void TableVal::Init(TableTypePtr t, bool ordered) {
     else
         subnets = nullptr;
 
-    if ( table_type->IsPatternIndex() && table_type->Yield() )
+    if ( table_type->IsPatternIndex() )
         pattern_matcher = new detail::TablePatternMatcher(this, table_type->Yield());
 
     table_hash = new detail::CompositeHash(table_type->GetIndices());
@@ -1674,7 +1688,7 @@ bool TableVal::Assign(ValPtr index, ValPtr new_val, bool broker_forward, bool* i
     }
 
     if ( pattern_matcher )
-        pattern_matcher->Insert(index->AsListVal()->Idx(0), new_val);
+        pattern_matcher->Insert(index, new_val);
 
     return Assign(std::move(index), std::move(k), std::move(new_val), broker_forward, iterators_invalidated);
 }
@@ -2032,12 +2046,19 @@ TableValPtr TableVal::LookupSubnetValues(const SubNetVal* search) {
 }
 
 VectorValPtr TableVal::LookupPattern(const StringValPtr& s) {
-    if ( ! pattern_matcher )
+    if ( ! pattern_matcher || ! GetType()->Yield() )
         reporter->InternalError("LookupPattern called on wrong table type");
 
     return pattern_matcher->Lookup(s);
 }
 
+bool TableVal::MatchPattern(const StringValPtr& s) {
+    if ( ! pattern_matcher )
+        reporter->InternalError("LookupPattern called on wrong table type");
+
+    return pattern_matcher->MatchAll(s);
+}
+
 void TableVal::GetPatternMatcherStats(detail::DFA_State_Cache_Stats* stats) const {
     if ( ! pattern_matcher )
         reporter->InternalError("GetPatternMatcherStats called on wrong table type");

src/Val.h

@@ -871,6 +871,11 @@ public:
     // Causes an internal error if called for any other kind of table.
     VectorValPtr LookupPattern(const StringValPtr& s);
 
+    // For a table[pattern] or set[pattern], returns True if any of the
+    // patterns in the index matches the given string, else False.
+    // Causes an internal error if called for any other kind of table.
+    bool MatchPattern(const StringValPtr& s);
+
     // For a table[pattern], fill stats with information about
     // the DFA's state for introspection.
     void GetPatternMatcherStats(detail::DFA_State_Cache_Stats* stats) const;

testing/btest/Baseline/language.pattern-sets/.stderr

@@ -0,0 +1 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.

testing/btest/Baseline/language.pattern-sets/out

@@ -0,0 +1,14 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+in empty, F
+single insert, foo in, T
+single insert, foox not-in, T
+multiple inserts, x not-in, T
+multiple insert, foo in, T
+multiple insert, bletch in, T
+multiple insert, foobletch not-in, T
+single delete, bletch in, T
+single delete, foo in, T
+two deletes, bletch not-in, T
+two deletes, foo not-in, T
+two deletes, bar in, T
+clear_table, bar not-in, T

testing/btest/Baseline/language.pattern-tables-stats/out

@@ -10,3 +10,12 @@ reset stats after delete, [matchers=1, nfa_states=0, dfa_states=0, computed=0, m
 [], [3], [1, 3]
 after even more lookup stats, [matchers=1, nfa_states=29, dfa_states=13, computed=13, mem=7056, hits=0, misses=13]
 reset after reassignment, [matchers=1, nfa_states=0, dfa_states=0, computed=0, mem=0, hits=0, misses=0]
+set initial stats, [matchers=1, nfa_states=0, dfa_states=0, computed=0, mem=0, hits=0, misses=0]
+set populated stats, [matchers=1, nfa_states=0, dfa_states=0, computed=0, mem=0, hits=0, misses=0]
+T, F
+set after lookup stats, [matchers=1, nfa_states=10, dfa_states=6, computed=6, mem=2368, hits=0, misses=6]
+set reset stats, [matchers=1, nfa_states=0, dfa_states=0, computed=0, mem=0, hits=0, misses=0]
+F, T
+set after more lookup stats, [matchers=1, nfa_states=24, dfa_states=9, computed=9, mem=5336, hits=0, misses=9]
+set reset stats after delete, [matchers=1, nfa_states=24, dfa_states=9, computed=9, mem=5336, hits=0, misses=9]
+set reset after reassignment, [matchers=1, nfa_states=0, dfa_states=0, computed=0, mem=0, hits=0, misses=0]

testing/btest/language/pattern-sets.zeek

@@ -0,0 +1,53 @@
+# @TEST-DOC: set[pattern] also supports parallel RE matching using in expression
+
+# @TEST-EXEC: zeek -b %INPUT >out
+# @TEST-EXEC: btest-diff out
+# @TEST-EXEC: btest-diff .stderr
+
+global ps: set[pattern];
+
+event zeek_init()
+	{
+	assert "foo" !in ps;
+	print "in empty", "foo" in ps;
+
+	add ps[/foo/];
+
+	assert "foo" in ps;
+	assert "foox" !in ps;
+	print "single insert, foo in", "foo" in ps;
+	print "single insert, foox not-in", "foox" !in ps;
+
+	add ps[/bar/];
+	add ps[/(foo|bletch)/];
+
+	assert "x" !in ps;
+	assert "bar" in ps;
+	assert "foo" in ps;
+	assert "bletch" in ps;
+	assert "foobletch" !in ps;
+
+	print "multiple inserts, x not-in", "x" !in ps;
+	print "multiple insert, foo in", "foo" in ps;
+	print "multiple insert, bletch in", "bletch" in ps;
+	print "multiple insert, foobletch not-in", "foobletch" !in ps;
+
+	# After delete of /foo/, still matches "foo" due to /(foo|bletch)/
+	delete ps[/foo/];
+	assert "foo" in ps;
+	assert "bletch" in ps;
+	print "single delete, bletch in", "bletch" in ps;
+	print "single delete, foo in", "foo" in ps;
+
+	delete ps[/(foo|bletch)/];
+	assert "foo" !in ps;
+	assert "bar" in ps;
+	assert "bletch" !in ps;
+	print "two deletes, bletch not-in", "bletch" !in ps;
+	print "two deletes, foo not-in", "foo" !in ps;
+	print "two deletes, bar in", "bar" in ps;
+
+	clear_table(ps);
+	assert "bar" !in ps;
+	print "clear_table, bar not-in", "bar" !in ps;
+	}

testing/btest/language/pattern-tables-stats.zeek

@@ -4,6 +4,7 @@
 # @TEST-EXEC: btest-diff .stderr
 
 global pt: table[pattern] of count;
+global ps: set[pattern];
 
 event zeek_init()
 	{
@@ -30,3 +31,26 @@ event zeek_init()
 	pt = table();
 	print "reset after reassignment", table_pattern_matcher_stats(pt);
 	}
+
+event zeek_init() &priority=-10
+	{
+	print "set initial stats", table_pattern_matcher_stats(ps);
+	add ps[/foo/];
+	print "set populated stats", table_pattern_matcher_stats(ps);
+
+	print "foo" in ps, "foox" in ps;
+	print "set after lookup stats", table_pattern_matcher_stats(ps);
+
+	add ps[/bar/];
+	add ps[/(foo|bletch)/];
+	print "set reset stats", table_pattern_matcher_stats(ps);
+
+	print "x" in ps, "bletch" in ps;
+	print "set after more lookup stats", table_pattern_matcher_stats(ps);
+
+	delete pt[/bar/];
+	print "set reset stats after delete", table_pattern_matcher_stats(ps);
+
+	ps = set();
+	print "set reset after reassignment", table_pattern_matcher_stats(pt);
+	}