package main // a matchIndex represents a match. It contains the start index and end index of the match type matchIndex struct { startIdx int endIdx int } // 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 } // findAllMatches tries to findAllMatches the regex represented by given start-state, with // the given string func findAllMatches(start *State, str string) (indices []matchIndex) { return findAllMatchesHelper(start, str, make([]matchIndex, 0), 0) } func findAllMatchesHelper(start *State, str string, indices []matchIndex, offset int) []matchIndex { // 'Base case' - exit if string is empty. if len(str) == 0 { // If the start is a Kleene star, then it should also match an empty string. if start.isKleene && start.isLast { indices, _ = unique_append(indices, matchIndex{offset, offset}) } return indices } foundPath := false startIdx := 0 endIdx := 0 currentStates := make([]*State, 0) tempStates := make([]*State, 0) // Used to store states that should be used in next loop iteration i := 0 // Index in string startingFrom := i // Store starting index // Increment until we hit a character matching the start state (assuming not 0-state) if start.isEmpty == false { for i < len(str) && !start.content.contains(int(str[i])) { i++ } startIdx = i startingFrom = i i++ // Advance to next character (if we aren't at a 0-state, which doesn't match anything), so that we can check for transitions. If we advance at a 0-state, we will never get a chance to match the first character } currentStates = append(currentStates, start) // Hold a list of match indices for the current run. When we // can no longer find a match, the match with the largest range is // chosen as the match for the entire string. // This allows us to pick the longest possible match (which is how greedy matching works). tempIndices := make([]matchIndex, 0) // Main loop for i < len(str) { foundPath = false zeroStates := make([]*State, 0) // Keep taking zero-states, until there are no more left to take // Objective: If any of our current states have transitions to 0-states, replace them with the 0-state. Do this until there are no more transitions to 0-states, or there are no more unique 0-states to take. zeroStates, isZero := takeZeroState(currentStates) tempStates = append(tempStates, zeroStates...) num_appended := 0 for isZero == true { zeroStates, isZero = takeZeroState(tempStates) tempStates, num_appended = unique_append(tempStates, zeroStates...) if num_appended == 0 { // Break if we haven't appended any more unique values break } } currentStates, _ = unique_append(currentStates, tempStates...) tempStates = nil // Take any transitions corresponding to current character for _, state := range currentStates { if len(state.transitions[int(str[i])]) > 0 { tempStates = append(tempStates, state.transitions[int(str[i])]...) foundPath = true } if state.isLast { endIdx = i tempIndices, _ = unique_append(tempIndices, matchIndex{startIdx + offset, endIdx + offset}) } } // Recursion - match with rest of string if we have nowhere to go. If we haven't moved in the string, increment the counter by 1 to ensure we don't keep trying the same string over and over if foundPath == false { if i == startingFrom { i++ } // Get the maximum index-range from the list if len(tempIndices) > 0 { indexToAdd := Reduce(tempIndices, func(i1 matchIndex, i2 matchIndex) matchIndex { r1 := i1.endIdx - i1.startIdx r2 := i2.endIdx - i2.startIdx if r1 >= r2 { return i1 } return i2 }) indices, _ = unique_append(indices, indexToAdd) } return findAllMatchesHelper(start, str[i:], indices, offset+i) } currentStates = make([]*State, len(tempStates)) copy(currentStates, tempStates) tempStates = nil i++ } // End-of-string reached. Go to any 0-states, until there are no more 0-states to go to. Then check if any of our states are in the end position. // This is the exact same algorithm used inside the loop, so I should probably put it in a function. zeroStates, isZero := takeZeroState(currentStates) tempStates = append(tempStates, zeroStates...) num_appended := 0 // Number of unique states addded to tempStates for isZero == true { zeroStates, isZero = takeZeroState(tempStates) tempStates, num_appended = unique_append(tempStates, zeroStates...) if num_appended == 0 { // Break if we haven't appended any more unique values break } } currentStates = append(currentStates, tempStates...) tempStates = nil for _, state := range currentStates { // Only add the match if the start index is in bounds if state.isLast && startIdx+offset < len(str)+offset { endIdx = i tempIndices, _ = unique_append(tempIndices, matchIndex{startIdx + offset, endIdx + offset}) } } // Get the maximum index-range from the list if len(tempIndices) > 0 { indexToAdd := Reduce(tempIndices, func(i1 matchIndex, i2 matchIndex) matchIndex { r1 := i1.endIdx - i1.startIdx r2 := i2.endIdx - i2.startIdx if r1 >= r2 { return i1 } return i2 }) indices, _ = unique_append(indices, indexToAdd) } // Default return indices }