// 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.
alwaysTrueAssert// An assertion that is always true
)
typestate struct{
contentstateContents// Contents of current state
isEmptybool// If it is empty - Union operator and Kleene star states will be empty
isLastbool// 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.
transitionsmap[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)
isKleenebool// Identifies whether current node is a 0-state representing Kleene star
assertassertType// Type of assertion of current node - NONE means that the node doesn't assert anything
allCharsbool// 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.
lookaroundRegexstring// Only for lookaround states - Contents of the regex that the lookaround state holds
lookaroundNFA*state // Holds the NFA of the lookaroundRegex - if it exists
lookaroundNumCaptureGroupsint// Number of capturing groups in lookaround regex if current node is a lookaround
groupBeginbool// Whether or not the node starts a capturing group
groupEndbool// Whether or not the node ends a capturing group
groupNumint// Which capturing group the node starts / ends
typenfaState struct{
contentstateContents// Contents of current state
isEmptybool// If it is empty - Union operator and Kleene star states will be empty
isLastbool// If it is the last state (acept state)
output[]*nfaState // The outputs of the current state ie. the 'outward arrows'. A union operator state will have more than one of these.
transitionsmap[int][]*nfaState // 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)
isKleenebool// Identifies whether current node is a 0-state representing Kleene star
assertassertType// Type of assertion of current node - NONE means that the node doesn't assert anything
allCharsbool// 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.
lookaroundRegexstring// Only for lookaround states - Contents of the regex that the lookaround state holds
lookaroundNFA*nfaState // Holds the NFA of the lookaroundRegex - if it exists
lookaroundNumCaptureGroupsint// Number of capturing groups in lookaround regex if current node is a lookaround
groupBeginbool// Whether or not the node starts a capturing group
groupEndbool// Whether or not the node ends a capturing group
groupNumint// Which capturing group the node starts / ends
// The following properties depend on the current match - I should think about resetting them for every match.
zeroMatchFoundbool// Whether or not the state has been used for a zero-length match - only relevant for zero states
threadGroups[]Group// Assuming that a state is part of a 'thread' in the matching process, this array stores the indices of capturing groups in the current thread. As matches are found for this state, its groups will be copied over.
ifst.isKleene{// A State representing a Kleene Star has transitions going out, which loop back to it. If all those transitions point to the same (single) state, then it must be a last state
