diff --git a/nfa.go b/nfa.go index a3977f5..add1ec6 100644 --- a/nfa.go +++ b/nfa.go @@ -1,14 +1,69 @@ package main +import "slices" + const EPSILON int = 0 +type assertType int + +const ( + NONE assertType = iota + SOS + EOS + WBOUND + NONWBOUND +) + 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 + 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 +} + +// Returns true if the contents of 's' contain the value at the given index of the given string +func (s State) contentContains(str []rune, idx int) bool { + if s.assert == SOS { + return idx == 0 + } + if s.assert == EOS { + return idx == len(str) + } + if s.assert == WBOUND { + if s.assert == WBOUND { + return isWordBoundary(str, idx) + } + if s.assert == NONWBOUND { + return !isWordBoundary(str, idx) + } + } + // Default - s.assert must be NONE + return slices.Contains(s.content, int(str[idx])) +} + +// Returns the matches for the character at the given index of the given string. +// Also returns the number of matches. Returns -1 if an assertion failed. +func (s State) matchesFor(str []rune, idx int) ([]*State, int) { + // Assertions can be viewed as 'checks'. If the check fails, we return + // an empty array and 0. + // If it passes, we treat it like any other state, and return all the transitions. + if s.assert == SOS && idx != 0 { + return make([]*State, 0), -1 + } + if s.assert == EOS && idx != len(str) { + return make([]*State, 0), -1 + } + if s.assert == WBOUND && !isWordBoundary(str, idx) { + return make([]*State, 0), -1 + } + if s.assert == NONWBOUND && isWordBoundary(str, idx) { + return make([]*State, 0), -1 + } + return s.transitions[int(str[idx])], len(s.transitions[int(str[idx])]) } type NFA struct {