Compare commits
8 Commits
0d19664044
...
ac05bceda3
| Author | SHA1 | Date | |
|---|---|---|---|
| ac05bceda3 | |||
| 037ac75ea6 | |||
| e9d4e857cf | |||
| b685d2fd5f | |||
| 8eda5055ff | |||
| 45b6566b2c | |||
| e22822e619 | |||
| 692de2a32b |
@@ -121,12 +121,12 @@ func main() {
|
|||||||
}
|
}
|
||||||
matchIndices := make([]reg.Match, 0)
|
matchIndices := make([]reg.Match, 0)
|
||||||
if matchNumFlagEnabled {
|
if matchNumFlagEnabled {
|
||||||
tmp, err := reg.FindNthMatch(regComp, test_str, *matchNum)
|
tmp, err := regComp.FindNthMatch(test_str, *matchNum)
|
||||||
if err == nil {
|
if err == nil {
|
||||||
matchIndices = append(matchIndices, tmp)
|
matchIndices = append(matchIndices, tmp)
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
matchIndices = reg.FindAllMatches(regComp, test_str)
|
matchIndices = regComp.FindAllSubmatch(test_str)
|
||||||
}
|
}
|
||||||
|
|
||||||
if *printMatchesFlag {
|
if *printMatchesFlag {
|
||||||
|
|||||||
11
regex/doc.go
11
regex/doc.go
@@ -84,6 +84,17 @@ Assertions:
|
|||||||
\b Match at a word boundary (a word character followed by a non-word character, or vice-versa)
|
\b Match at a word boundary (a word character followed by a non-word character, or vice-versa)
|
||||||
\B Match at a non-word boundary (a word character followed by a word character, or vice-versa)
|
\B Match at a non-word boundary (a word character followed by a word character, or vice-versa)
|
||||||
|
|
||||||
|
Lookarounds:
|
||||||
|
|
||||||
|
x(?=y) Positive lookahead - Match x if followed by y
|
||||||
|
x(?!y) Negative lookahead - Match x if NOT followed by y
|
||||||
|
(?<=x)y Positive lookbehind - Match y if preceded by x
|
||||||
|
(?<!x)y Negative lookbehind - Match y if NOT preceded by x
|
||||||
|
|
||||||
|
Numeric ranges:
|
||||||
|
|
||||||
|
<x-y> Match any number from x to y (inclusive) (x and y must be positive numbers)
|
||||||
|
|
||||||
# Flags
|
# Flags
|
||||||
|
|
||||||
Flags are used to change the behavior of the engine. None of them are enabled by default. They are passed as variadic arguments to [Compile].
|
Flags are used to change the behavior of the engine. None of them are enabled by default. They are passed as variadic arguments to [Compile].
|
||||||
|
|||||||
@@ -57,6 +57,11 @@ func (g Group) isValid() bool {
|
|||||||
return g.StartIdx >= 0 && g.EndIdx >= 0
|
return g.StartIdx >= 0 && g.EndIdx >= 0
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Simple function, makes it easier to map this over a list of matches
|
||||||
|
func getZeroGroup(m Match) Group {
|
||||||
|
return m[0]
|
||||||
|
}
|
||||||
|
|
||||||
// takeZeroState takes the 0-state (if such a transition exists) for all states in the
|
// 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,
|
// given slice. It returns the resulting states. If any of the resulting states is a 0-state,
|
||||||
// the second ret val is true.
|
// the second ret val is true.
|
||||||
@@ -138,36 +143,58 @@ func pruneIndices(indices []Match) []Match {
|
|||||||
return toRet
|
return toRet
|
||||||
}
|
}
|
||||||
|
|
||||||
// FindString returns a string containing the text of the leftmost match of the regex in the given string.
|
// Find returns the 0-group of the leftmost match of the regex in the given string.
|
||||||
|
// An error value != nil indicates that no match was found.
|
||||||
|
func (regex Reg) Find(str string) (Group, error) {
|
||||||
|
match, err := regex.FindNthMatch(str, 1)
|
||||||
|
if err != nil {
|
||||||
|
return Group{}, nil
|
||||||
|
}
|
||||||
|
return getZeroGroup(match), nil
|
||||||
|
}
|
||||||
|
|
||||||
|
// FindAll returns a slice containing all the 0-groups of the regex in the given string.
|
||||||
|
// A 0-group represents the match without any submatches.
|
||||||
|
func (regex Reg) FindAll(str string) []Group {
|
||||||
|
indices := regex.FindAllSubmatch(str)
|
||||||
|
zeroGroups := funcMap(indices, getZeroGroup)
|
||||||
|
return zeroGroups
|
||||||
|
}
|
||||||
|
|
||||||
|
// FindString returns the text of the leftmost match of the regex in the given string.
|
||||||
// The return value will be an empty string in two situations:
|
// The return value will be an empty string in two situations:
|
||||||
// 1. No match was found
|
// 1. No match was found
|
||||||
// 2. The match was an empty string
|
// 2. The match was an empty string
|
||||||
func (regex Reg) FindString(str string) string {
|
func (regex Reg) FindString(str string) string {
|
||||||
match, err := FindNthMatch(regex, str, 1)
|
match, err := regex.FindNthMatch(str, 1)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return ""
|
return ""
|
||||||
}
|
}
|
||||||
return str[match[0].StartIdx:match[0].EndIdx]
|
zeroGroup := getZeroGroup(match)
|
||||||
|
return str[zeroGroup.StartIdx:zeroGroup.EndIdx]
|
||||||
}
|
}
|
||||||
|
|
||||||
// FindAllString is the 'all' version of FindString.
|
// FindAllString is the 'all' version of FindString.
|
||||||
// It returns a slice of strings containing the text of all matches of
|
// It returns a slice of strings containing the text of all matches of
|
||||||
// the regex in the given string.
|
// the regex in the given string.
|
||||||
func FindAllString(regex Reg, str []string) []string {
|
func (regex Reg) FindAllString(str string) []string {
|
||||||
return []string{}
|
zerogroups := regex.FindAll(str)
|
||||||
|
matchStrs := funcMap(zerogroups, func(g Group) string {
|
||||||
|
return str[g.StartIdx:g.EndIdx]
|
||||||
|
})
|
||||||
|
return matchStrs
|
||||||
}
|
}
|
||||||
|
|
||||||
// FindNthMatch finds the 'n'th match of the regex represented by the given start-state, with
|
// FindNthMatch return the 'n'th match of the regex in the given string.
|
||||||
// the given string.
|
|
||||||
// It returns an error (!= nil) if there are fewer than 'n' matches in the string.
|
// It returns an error (!= nil) if there are fewer than 'n' matches in the string.
|
||||||
func FindNthMatch(regex Reg, str string, n int) (Match, error) {
|
func (regex Reg) FindNthMatch(str string, n int) (Match, error) {
|
||||||
idx := 0
|
idx := 0
|
||||||
matchNum := 0
|
matchNum := 0
|
||||||
str_runes := []rune(str)
|
str_runes := []rune(str)
|
||||||
var matchFound bool
|
var matchFound bool
|
||||||
var matchIdx Match
|
var matchIdx Match
|
||||||
for idx <= len(str_runes) {
|
for idx <= len(str_runes) {
|
||||||
matchFound, matchIdx, idx = findAllMatchesHelper(regex.start, str_runes, idx, regex.numGroups)
|
matchFound, matchIdx, idx = findAllSubmatchHelper(regex.start, str_runes, idx, regex.numGroups)
|
||||||
if matchFound {
|
if matchFound {
|
||||||
matchNum++
|
matchNum++
|
||||||
}
|
}
|
||||||
@@ -179,16 +206,15 @@ func FindNthMatch(regex Reg, str string, n int) (Match, error) {
|
|||||||
return nil, fmt.Errorf("invalid match index - too few matches found")
|
return nil, fmt.Errorf("invalid match index - too few matches found")
|
||||||
}
|
}
|
||||||
|
|
||||||
// FindAllMatches tries to find all matches of the regex represented by given start-state, with
|
// FindAllSubmatch returns a slice of matches in the given string.
|
||||||
// the given string
|
func (regex Reg) FindAllSubmatch(str string) []Match {
|
||||||
func FindAllMatches(regex Reg, str string) []Match {
|
|
||||||
idx := 0
|
idx := 0
|
||||||
str_runes := []rune(str)
|
str_runes := []rune(str)
|
||||||
var matchFound bool
|
var matchFound bool
|
||||||
var matchIdx Match
|
var matchIdx Match
|
||||||
indices := make([]Match, 0)
|
indices := make([]Match, 0)
|
||||||
for idx <= len(str_runes) {
|
for idx <= len(str_runes) {
|
||||||
matchFound, matchIdx, idx = findAllMatchesHelper(regex.start, str_runes, idx, regex.numGroups)
|
matchFound, matchIdx, idx = findAllSubmatchHelper(regex.start, str_runes, idx, regex.numGroups)
|
||||||
if matchFound {
|
if matchFound {
|
||||||
indices = append(indices, matchIdx)
|
indices = append(indices, matchIdx)
|
||||||
}
|
}
|
||||||
@@ -196,6 +222,7 @@ func FindAllMatches(regex Reg, str string) []Match {
|
|||||||
if len(indices) > 0 {
|
if len(indices) > 0 {
|
||||||
return pruneIndices(indices)
|
return pruneIndices(indices)
|
||||||
}
|
}
|
||||||
|
|
||||||
return indices
|
return indices
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -204,7 +231,7 @@ func FindAllMatches(regex Reg, str string) []Match {
|
|||||||
// the next search should start from.
|
// the next search should start from.
|
||||||
//
|
//
|
||||||
// Might return duplicates or overlapping indices, so care must be taken to prune the resulting array.
|
// Might return duplicates or overlapping indices, so care must be taken to prune the resulting array.
|
||||||
func findAllMatchesHelper(start *nfaState, str []rune, offset int, numGroups int) (bool, Match, int) {
|
func findAllSubmatchHelper(start *nfaState, str []rune, offset int, numGroups int) (bool, Match, int) {
|
||||||
// Base case - exit if offset exceeds string's length
|
// Base case - exit if offset exceeds string's length
|
||||||
if offset > len(str) {
|
if offset > len(str) {
|
||||||
// The second value here shouldn't be used, because we should exit when the third return value is > than len(str)
|
// The second value here shouldn't be used, because we should exit when the third return value is > than len(str)
|
||||||
|
|||||||
@@ -156,17 +156,18 @@ func (s nfaState) checkAssertion(str []rune, idx int) bool {
|
|||||||
strToMatch = string(runesToMatch)
|
strToMatch = string(runesToMatch)
|
||||||
}
|
}
|
||||||
|
|
||||||
matchIndices := FindAllMatches(Reg{startState, s.lookaroundNumCaptureGroups}, strToMatch)
|
regComp := Reg{startState, s.lookaroundNumCaptureGroups}
|
||||||
|
matchIndices := regComp.FindAll(strToMatch)
|
||||||
|
|
||||||
numMatchesFound := 0
|
numMatchesFound := 0
|
||||||
for _, matchIdx := range matchIndices {
|
for _, matchIdx := range matchIndices {
|
||||||
if s.assert == plaAssert || s.assert == nlaAssert { // Lookahead - return true (or false) if at least one match starts at 0. Zero is used because the test-string _starts_ from idx.
|
if s.assert == plaAssert || s.assert == nlaAssert { // Lookahead - return true (or false) if at least one match starts at 0. Zero is used because the test-string _starts_ from idx.
|
||||||
if matchIdx[0].StartIdx == 0 {
|
if matchIdx.StartIdx == 0 {
|
||||||
numMatchesFound++
|
numMatchesFound++
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
if s.assert == plbAssert || s.assert == nlbAssert { // Lookbehind - return true (or false) if at least one match _ends_ at the current index.
|
if s.assert == plbAssert || s.assert == nlbAssert { // Lookbehind - return true (or false) if at least one match _ends_ at the current index.
|
||||||
if matchIdx[0].EndIdx == idx {
|
if matchIdx.EndIdx == idx {
|
||||||
numMatchesFound++
|
numMatchesFound++
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -682,13 +682,9 @@ func TestFindAllMatches(t *testing.T) {
|
|||||||
panic(fmt.Errorf("Test Error: %v", err))
|
panic(fmt.Errorf("Test Error: %v", err))
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
matchIndices := FindAllMatches(regComp, test.str)
|
matchIndices := regComp.FindAll(test.str)
|
||||||
zeroGroups := make([]Group, len(matchIndices))
|
if !slices.Equal(test.result, matchIndices) {
|
||||||
for i, m := range matchIndices {
|
t.Errorf("Wanted %v Got %v\n", test.result, matchIndices)
|
||||||
zeroGroups[i] = m[0]
|
|
||||||
}
|
|
||||||
if !slices.Equal(test.result, zeroGroups) {
|
|
||||||
t.Errorf("Wanted %v Got %v\n", test.result, zeroGroups)
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
@@ -720,6 +716,31 @@ func TestFindString(t *testing.T) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestFindAllStrings(t *testing.T) {
|
||||||
|
for _, test := range reTests {
|
||||||
|
t.Run(test.re+" "+test.str, func(t *testing.T) {
|
||||||
|
regComp, err := Compile(test.re, test.flags...)
|
||||||
|
if err != nil {
|
||||||
|
if test.result != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
foundStrings := regComp.FindAllString(test.str)
|
||||||
|
if len(test.result) != len(foundStrings) {
|
||||||
|
t.Errorf("Differing number of matches: Wanted %v matches Got %v matches\n", len(test.result), len(foundStrings))
|
||||||
|
} else {
|
||||||
|
for idx, group := range test.result {
|
||||||
|
groupStr := test.str[group.StartIdx:group.EndIdx]
|
||||||
|
if groupStr != foundStrings[idx] {
|
||||||
|
t.Errorf("Wanted %v Got %v\n", groupStr, foundStrings[idx])
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
func TestFindAllGroups(t *testing.T) {
|
func TestFindAllGroups(t *testing.T) {
|
||||||
for _, test := range groupTests {
|
for _, test := range groupTests {
|
||||||
t.Run(test.re+" "+test.str, func(t *testing.T) {
|
t.Run(test.re+" "+test.str, func(t *testing.T) {
|
||||||
@@ -729,7 +750,7 @@ func TestFindAllGroups(t *testing.T) {
|
|||||||
panic(err)
|
panic(err)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
matchIndices := FindAllMatches(regComp, test.str)
|
matchIndices := regComp.FindAllSubmatch(test.str)
|
||||||
for i := range matchIndices {
|
for i := range matchIndices {
|
||||||
for j := range matchIndices[i] {
|
for j := range matchIndices[i] {
|
||||||
if matchIndices[i][j].isValid() {
|
if matchIndices[i][j].isValid() {
|
||||||
|
|||||||
Reference in New Issue
Block a user