From 11dd6aeb7c3bbb0f911eb8cbc414b18b40f53803 Mon Sep 17 00:00:00 2001
From: Aadhavan Srinivasan <aadhavan@twomorecents.org>
Date: Wed, 23 Oct 2024 10:26:50 -0400
Subject: [PATCH] More Kleene star fixes

---
 go.mod      |  2 +-
 main.go     |  8 +++++++-
 matching.go | 36 ++++++++++++++++++++++++++++--------
 3 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/go.mod b/go.mod
index b422ea0..0e521ea 100644
--- a/go.mod
+++ b/go.mod
@@ -3,7 +3,7 @@ module re
 go 1.23.1
 
 require (
-	github.com/fatih/color v1.18.0 // indirect
+	github.com/fatih/color v1.18.0
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	golang.org/x/sys v0.25.0 // indirect
diff --git a/main.go b/main.go
index 1ca719b..3be83e8 100644
--- a/main.go
+++ b/main.go
@@ -143,7 +143,8 @@ func thompson(re string) *State {
 			s2 := pop(&nfa)
 			s3 := State{}
 			s3.transitions = make(map[int][]*State)
-			s3.output = append(s3.output, s1, s2)
+			s3.output = append(s3.output, s1.output...)
+			s3.output = append(s3.output, s2.output...)
 			s3.transitions[s1.content] = append(s3.transitions[s1.content], s1)
 			s3.transitions[s2.content] = append(s3.transitions[s2.content], s2)
 			s3.content = EPSILON
@@ -163,6 +164,11 @@ func thompson(re string) *State {
 }
 
 func main() {
+	// Process:
+	// 1. Convert regex into postfix notation (Shunting-Yard algorithm)
+	// 		a. Add explicit concatenation operators to facilitate this
+	// 2. Build NFA from postfix representation (Thompson's algorithm)
+	// 3. Run the string against the NFA
 	if len(os.Args) < 3 {
 		fmt.Println("ERROR: Missing cmdline args")
 		os.Exit(22)
diff --git a/matching.go b/matching.go
index fc060ac..f9c7645 100644
--- a/matching.go
+++ b/matching.go
@@ -1,5 +1,22 @@
 package main
 
+// takeZeroState takes the 0-state (if such a transition exists) for all states in the
+// given slice. It returns the resulting states. If any of the resulting states is a 0-state,
+// the second parameter is true.
+func takeZeroState(states []*State) (rtv []*State, isZero bool) {
+	for _, state := range states {
+		if len(state.transitions[EPSILON]) > 0 {
+			rtv = append(rtv, state.transitions[EPSILON]...)
+		}
+	}
+	for _, state := range rtv {
+		if len(state.transitions[EPSILON]) > 0 {
+			return rtv, true
+		}
+	}
+	return rtv, false
+}
+
 // match tries to match the regex represented by given start-state, with
 // the given string
 func match(start *State, str string) (startIdx int, endIdx int, matched bool) {
@@ -18,14 +35,16 @@ func match(start *State, str string) (startIdx int, endIdx int, matched bool) {
 
 	// Main loop
 	for i < len(str) {
-		// If there are any 0-transitions, take those
-		// TODO: Maybe I need to keep taking 0-transitions until I don't have anymore. Needs to be tested
-		for _, state := range currentStates {
-			if len(state.transitions[EPSILON]) > 0 {
-				tempStates = append(tempStates, state.transitions[EPSILON]...)
-			}
+		zeroStates := make([]*State, 0)
+		// Keep taking zero-states, until there are no more left to take
+		zeroStates, isZero := takeZeroState(currentStates)
+		tempStates = append(tempStates, zeroStates...)
+		for isZero == true {
+			zeroStates, isZero = takeZeroState(tempStates)
+			tempStates = append(tempStates, zeroStates...)
 		}
-		copy(currentStates, tempStates)
+
+		currentStates = append(currentStates, tempStates...)
 		tempStates = nil
 
 		// Take any transitions corresponding to current character
@@ -40,6 +59,7 @@ func match(start *State, str string) (startIdx int, endIdx int, matched bool) {
 				}
 			}
 		}
+		currentStates = make([]*State, len(tempStates))
 		copy(currentStates, tempStates)
 		tempStates = nil
 
@@ -52,7 +72,7 @@ func match(start *State, str string) (startIdx int, endIdx int, matched bool) {
 			tempStates = append(tempStates, state.transitions[EPSILON]...)
 		}
 	}
-	copy(currentStates, tempStates)
+	currentStates = append(currentStates, tempStates...)
 	tempStates = nil
 
 	for _, state := range currentStates {