diff --git a/nfa.go b/nfa.go index ff6fdc6..a7ef67b 100644 --- a/nfa.go +++ b/nfa.go @@ -21,18 +21,22 @@ const ( ) type State struct { - content stateContents // Contents of current state - isEmpty bool // If it is empty - Union operator and Kleene star states will be empty - isLast bool // If it is the last state (acept state) - output []*State // The outputs of the current state ie. the 'outward arrows'. A union operator state will have more than one of these. - transitions map[int][]*State // Transitions to different states (maps a character (int representation) to a _list of states. This is useful if one character can lead multiple states eg. ab|aa) - isKleene bool // Identifies whether current node is a 0-state representing Kleene star - assert assertType // Type of assertion of current node - NONE means that the node doesn't assert anything - zeroMatchFound bool // Whether or not the state has been used for a zero-length match - only relevant for zero states - allChars bool // Whether or not the state represents all characters (eg. a 'dot' metacharacter). A 'dot' node doesn't store any contents directly, as it would take up too much space - except []rune // Only valid if allChars is true - match all characters _except_ the ones in this block. Useful for inverting character classes. - lookaroundRegex string // Only for lookaround states - Contents of the regex that the lookaround state holds - lookaroundNFA *State // Holds the NFA of the lookaroundRegex - if it exists + content stateContents // Contents of current state + isEmpty bool // If it is empty - Union operator and Kleene star states will be empty + isLast bool // If it is the last state (acept state) + output []*State // The outputs of the current state ie. the 'outward arrows'. A union operator state will have more than one of these. + transitions map[int][]*State // Transitions to different states (maps a character (int representation) to a _list of states. This is useful if one character can lead multiple states eg. ab|aa) + isKleene bool // Identifies whether current node is a 0-state representing Kleene star + assert assertType // Type of assertion of current node - NONE means that the node doesn't assert anything + zeroMatchFound bool // Whether or not the state has been used for a zero-length match - only relevant for zero states + allChars bool // Whether or not the state represents all characters (eg. a 'dot' metacharacter). A 'dot' node doesn't store any contents directly, as it would take up too much space + except []rune // Only valid if allChars is true - match all characters _except_ the ones in this block. Useful for inverting character classes. + lookaroundRegex string // Only for lookaround states - Contents of the regex that the lookaround state holds + lookaroundNFA *State // Holds the NFA of the lookaroundRegex - if it exists + lookaroundNumCaptureGroups int // Number of capturing groups if current node is a lookaround + groupBegin bool // Whether or not the node starts a capturing group + groupEnd bool // Whether or not the node ends a capturing group + groupNum int // Which capturing group the node starts / ends } // Clones the NFA starting from the given state. @@ -65,6 +69,9 @@ func cloneStateHelper(state *State, cloneMap map[*State]*State) *State { allChars: state.allChars, except: append([]rune{}, state.except...), lookaroundRegex: state.lookaroundRegex, + groupEnd: state.groupEnd, + groupBegin: state.groupBegin, + groupNum: state.groupNum, } cloneMap[state] = clone for i, s := range state.output { @@ -113,17 +120,17 @@ func (s State) checkAssertion(str []rune, idx int) bool { // 2. Run it on the test string. // 3. Based on the kind of lookaround (and the indices we get), determine what action to take. startState := s.lookaroundNFA - matchIndices := findAllMatches(startState, str) + matchIndices := findAllMatches(startState, str, startState.lookaroundNumCaptureGroups) numMatchesFound := 0 for _, matchIdx := range matchIndices { if s.assert == PLA || s.assert == NLA { // Lookahead - return true (or false) if at least one match starts at the current index - if matchIdx.startIdx == idx { + if matchIdx[0].startIdx == idx { numMatchesFound++ } } if s.assert == PLB || s.assert == NLB { // Lookbehind - return true (or false) if at least one match _ends_ at the current index. - if matchIdx.endIdx == idx { + if matchIdx[0].endIdx == idx { numMatchesFound++ } }