Rockingcool/kleingrep
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Restructured code into 'cmd' module with CLI and 'greg' module with regex library; export necessary struct fields and methods

Browse Source
This commit is contained in:
Aadhavan Srinivasan
2025-01-30 08:56:03 -05:00
parent 54df6f1815
commit 1a2f1b7ca9
17 changed files with 37 additions and 35 deletions

0
cmd/helpers.go Normal file

8
main.go → cmd/main.go

@@ -8,11 +8,13 @@ import (
"os" "os"
"github.com/fatih/color" "github.com/fatih/color"
"gitea.twomorecents.org/Rockingcool/kg/greg"
) )
func main() { func main() {
// Flags for the regex Compile function // Flags for the regex Compile function
flagsToCompile := make([]ReFlag, 0) flagsToCompile := make([]greg.ReFlag, 0)
invertFlag := flag.Bool("v", false, "Invert match.") invertFlag := flag.Bool("v", false, "Invert match.")
// This flag has two 'modes': // This flag has two 'modes':
@@ -29,10 +31,10 @@ func main() {
// These flags have to be passed to the Compile function // These flags have to be passed to the Compile function
if *multiLineFlag { if *multiLineFlag {
flagsToCompile = append(flagsToCompile, RE_MULTILINE, RE_SINGLE_LINE) flagsToCompile = append(flagsToCompile, greg.RE_MULTILINE, greg.RE_SINGLE_LINE)
} }
if *caseInsensitiveFlag { if *caseInsensitiveFlag {
flagsToCompile = append(flagsToCompile, RE_CASE_INSENSITIVE) flagsToCompile = append(flagsToCompile, greg.RE_CASE_INSENSITIVE)
} }
// -l and -o are mutually exclusive: -o overrides -l // -l and -o are mutually exclusive: -o overrides -l

0
unique_array.go → cmd/unique_array.go

2
go.mod

@@ -1,4 +1,4 @@
module re module gitea.twomorecents.org/Rockingcool/kg
go 1.23.1 go 1.23.1

2
compile.go → greg/compile.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"fmt" "fmt"

44
matching.go → greg/matching.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"fmt" "fmt"
@@ -10,15 +10,15 @@ type Match []Group
// a Group represents a group. It contains the start index and end index of the match // a Group represents a group. It contains the start index and end index of the match
type Group struct { type Group struct {
startIdx int StartIdx int
endIdx int EndIdx int
} }
func newMatch(size int) Match { func newMatch(size int) Match {
toRet := make([]Group, size) toRet := make([]Group, size)
for i := range toRet { for i := range toRet {
toRet[i].startIdx = -1 toRet[i].StartIdx = -1
toRet[i].endIdx = -1 toRet[i].EndIdx = -1
} }
return toRet return toRet
} }
@@ -27,7 +27,7 @@ func newMatch(size int) Match {
func (m Match) numValidGroups() int { func (m Match) numValidGroups() int {
numValid := 0 numValid := 0
for _, g := range m { for _, g := range m {
if g.startIdx >= 0 && g.endIdx >= 0 { if g.StartIdx >= 0 && g.EndIdx >= 0 {
numValid++ numValid++
} }
} }
@@ -35,7 +35,7 @@ func (m Match) numValidGroups() int {
} }
// Returns a string containing the indices of all (valid) groups in the match // Returns a string containing the indices of all (valid) groups in the match
func (m Match) toString() string { func (m Match) ToString() string {
var toRet string var toRet string
for i, g := range m { for i, g := range m {
if g.isValid() { if g.isValid() {
@@ -49,12 +49,12 @@ func (m Match) toString() string {
// Converts the Group into a string representation: // Converts the Group into a string representation:
func (idx Group) toString() string { func (idx Group) toString() string {
return fmt.Sprintf("%d\t%d", idx.startIdx, idx.endIdx) return fmt.Sprintf("%d\t%d", idx.StartIdx, idx.EndIdx)
} }
// Returns whether a group contains valid indices // Returns whether a group contains valid indices
func (g Group) isValid() bool { func (g Group) isValid() bool {
return g.startIdx >= 0 && g.endIdx >= 0 return g.StartIdx >= 0 && g.EndIdx >= 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
@@ -70,11 +70,11 @@ func takeZeroState(states []*State, numGroups int, idx int) (rtv []*State, isZer
} }
copy(s.threadGroups, state.threadGroups) copy(s.threadGroups, state.threadGroups)
if s.groupBegin { if s.groupBegin {
s.threadGroups[s.groupNum].startIdx = idx s.threadGroups[s.groupNum].StartIdx = idx
// openParenGroups = append(openParenGroups, s.groupNum) // openParenGroups = append(openParenGroups, s.groupNum)
} }
if s.groupEnd { if s.groupEnd {
s.threadGroups[s.groupNum].endIdx = idx s.threadGroups[s.groupNum].EndIdx = idx
// closeParenGroups = append(closeParenGroups, s.groupNum) // closeParenGroups = append(closeParenGroups, s.groupNum)
} }
} }
@@ -118,17 +118,17 @@ func zeroMatchPossible(str []rune, idx int, numGroups int, states ...*State) boo
func pruneIndices(indices []Match) []Match { func pruneIndices(indices []Match) []Match {
// First, sort the slice by the start indices // First, sort the slice by the start indices
sort.Slice(indices, func(i, j int) bool { sort.Slice(indices, func(i, j int) bool {
return indices[i][0].startIdx < indices[j][0].startIdx return indices[i][0].StartIdx < indices[j][0].StartIdx
}) })
toRet := make([]Match, 0, len(indices)) toRet := make([]Match, 0, len(indices))
current := indices[0] current := indices[0]
for _, idx := range indices[1:] { for _, idx := range indices[1:] {
// idx doesn't overlap with current (starts after current ends), so add current to result // idx doesn't overlap with current (starts after current ends), so add current to result
// and update the current. // and update the current.
if idx[0].startIdx >= current[0].endIdx { if idx[0].StartIdx >= current[0].EndIdx {
toRet = append(toRet, current) toRet = append(toRet, current)
current = idx current = idx
} else if idx[0].endIdx > current[0].endIdx { } else if idx[0].EndIdx > current[0].EndIdx {
// idx overlaps, but it is longer, so update current // idx overlaps, but it is longer, so update current
current = idx current = idx
} }
@@ -147,7 +147,7 @@ func FindString(regex Reg, str string) string {
if err != nil { if err != nil {
return "" return ""
} }
return str[match[0].startIdx:match[0].endIdx] return str[match[0].StartIdx:match[0].EndIdx]
} }
// FindAllString is the 'all' version of FindString. // FindAllString is the 'all' version of FindString.
@@ -247,7 +247,7 @@ func findAllMatchesHelper(start *State, str []rune, offset int, numGroups int) (
start.threadGroups = newMatch(numGroups + 1) start.threadGroups = newMatch(numGroups + 1)
// Check if the start state begins a group - if so, add the start index to our list // Check if the start state begins a group - if so, add the start index to our list
if start.groupBegin { if start.groupBegin {
start.threadGroups[start.groupNum].startIdx = i start.threadGroups[start.groupNum].StartIdx = i
// tempIndices[start.groupNum].startIdx = i // tempIndices[start.groupNum].startIdx = i
} }
@@ -356,10 +356,10 @@ func findAllMatchesHelper(start *State, str []rune, offset int, numGroups int) (
// i++ // i++
// } // }
if tempIndices.numValidGroups() > 0 && tempIndices[0].isValid() { if tempIndices.numValidGroups() > 0 && tempIndices[0].isValid() {
if tempIndices[0].startIdx == tempIndices[0].endIdx { // If we have a zero-length match, we have to shift the index at which we start. Otherwise we keep looking at the same paert of the string over and over. if tempIndices[0].StartIdx == tempIndices[0].EndIdx { // If we have a zero-length match, we have to shift the index at which we start. Otherwise we keep looking at the same paert of the string over and over.
return true, tempIndices, tempIndices[0].endIdx + 1 return true, tempIndices, tempIndices[0].EndIdx + 1
} else { } else {
return true, tempIndices, tempIndices[0].endIdx return true, tempIndices, tempIndices[0].EndIdx
} }
} }
return false, []Group{}, startIdx return false, []Group{}, startIdx
@@ -402,10 +402,10 @@ func findAllMatchesHelper(start *State, str []rune, offset int, numGroups int) (
} }
if tempIndices.numValidGroups() > 0 { if tempIndices.numValidGroups() > 0 {
if tempIndices[0].startIdx == tempIndices[0].endIdx { // If we have a zero-length match, we have to shift the index at which we start. Otherwise we keep looking at the same paert of the string over and over. if tempIndices[0].StartIdx == tempIndices[0].EndIdx { // If we have a zero-length match, we have to shift the index at which we start. Otherwise we keep looking at the same paert of the string over and over.
return true, tempIndices, tempIndices[0].endIdx + 1 return true, tempIndices, tempIndices[0].EndIdx + 1
} else { } else {
return true, tempIndices, tempIndices[0].endIdx return true, tempIndices, tempIndices[0].EndIdx
} }
} }
if startIdx == startingFrom { // Increment starting index if we haven't moved in the string. Prevents us from matching the same part of the string over and over. if startIdx == startingFrom { // Increment starting index if we haven't moved in the string. Prevents us from matching the same part of the string over and over.

2
misc.go → greg/misc.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"slices" "slices"

2
nfa.go → greg/nfa.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"fmt" "fmt"

0
noteOnPCREBackreferences.txt → greg/noteOnPCREBackreferences.txt

2
postfixNode.go → greg/postfixNode.go

@@ -1,4 +1,4 @@
package main package greg
import "fmt" import "fmt"

2
range2regex.go → greg/range2regex.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"fmt" "fmt"

4
re_test.go → greg/re_test.go

@@ -1,4 +1,4 @@
package main package greg
import ( import (
"fmt" "fmt"
@@ -703,7 +703,7 @@ func TestFindString(t *testing.T) {
t.Errorf("Expected no match got %v\n", foundString) t.Errorf("Expected no match got %v\n", foundString)
} }
} else { } else {
expectedString := test.str[test.result[0].startIdx:test.result[0].endIdx] expectedString := test.str[test.result[0].StartIdx:test.result[0].EndIdx]
if foundString != expectedString { if foundString != expectedString {
t.Errorf("Wanted %v Got %v\n", expectedString, foundString) t.Errorf("Wanted %v Got %v\n", expectedString, foundString)
} }

0
re_tests.py → greg/re_tests.py

0
re_tests_uniq.py → greg/re_tests_uniq.py

2
sliceQueue.go → greg/sliceQueue.go

@@ -1,4 +1,4 @@
package main package greg
import "errors" import "errors"

2
stateContents.go → greg/stateContents.go

@@ -1,4 +1,4 @@
package main package greg
type stateContents []int // Represents the contents of the current state - character classes can have multiple contents, which is why it is represented as a slice type stateContents []int // Represents the contents of the current state - character classes can have multiple contents, which is why it is represented as a slice

0
todo.txt → greg/todo.txt