Added function and examples for ReplaceAllFunc()

regex/compile.go

@@ -31,6 +31,22 @@ func (re Reg) String() string {
 	return re.str
 }
 
+// MarshalText implements [encoding.TextMarshaler]. The output is equivalent to that of [Reg.String].
+// Any flags passed as arguments (including calling [Reg.Longest]) are lost.
+func (re *Reg) MarshalText() ([]byte, error) {
+	return []byte(re.String()), nil
+}
+
+// UnmarshalText implements [encoding.TextUnmarshaler]. It calls [Reg.Compile] on the given byte-slice. If it returns successfully,
+// then the result of the compilation is stored in re. The result of [Reg.Compile] is returned.
+func (re *Reg) UnmarshalText(text []byte) error {
+	newReg, err := Compile(string(text))
+	if err == nil {
+		*re = newReg
+	}
+	return err
+}
+
 func (re *Reg) Longest() {
 	re.preferLongest = true
 }

regex/doc.go

@@ -33,7 +33,7 @@ Perl classes:
 	\d				Match any digit character ([0-9])
 	\D				Match any non-digit character ([^0-9])
 	\w				Match any word character ([a-zA-Z0-9_])
-	\W				Match any word character ([^a-zA-Z0-9_])
+	\W				Match any non-word character ([^a-zA-Z0-9_])
 	\s				Match any whitespace character ([ \t\n])
 	\S				Match any non-whitespace character ([^ \t\n])
 
@@ -105,23 +105,7 @@ The key differences are mentioned below.
 
 1. Greediness:
 
-This engine does not support non-greedy operators. All operators are always greedy in nature, and will try
+This engine currently does not support non-greedy operators.
-to match as much as they can, while still allowing for a successful match. For example, given the regex:
-
-	y*y
-
-The engine will match as many 'y's as it can, while still allowing the trailing 'y' to be matched.
-
-Another, more subtle example is the following regex:
-
-	x|xx
-
-While the stdlib implementation (and most other engines) will prefer matching the first item of the alternation,
-this engine will go for the longest possible match, regardless of the order of the alternation. Although this
-strays from the convention, it results in a nice rule-of-thumb - the engine is ALWAYS greedy.
-
-The stdlib implementation has a function [regexp.Regexp.Longest] which makes future searches prefer the longest match.
-That is the default (and unchangable) behavior in this engine.
 
 2. Byte-slices and runes:
 
@@ -166,7 +150,7 @@ The following features from [regexp] are (currently) NOT supported:
  1. Named capturing groups
  2. Non-greedy operators
  3. Unicode character classes
- 4. Embedded flags (flags are passed as arguments to [Compile])
+ 4. Embedded flags (flags are instead passed as arguments to [Compile])
  5. Literal text with \Q ... \E
 
 The following features are not available in [regexp], but are supported in my engine:

regex/example_test.go

@@ -2,6 +2,7 @@ package regex_test
 
 import (
 	"fmt"
+	"strings"
 
 	"gitea.twomorecents.org/Rockingcool/kleingrep/regex"
 )
@@ -32,12 +33,12 @@ func ExampleReg_FindAll() {
 }
 
 func ExampleReg_FindString() {
-	regexStr := `\d+`
+	regexStr := `\w+\s+(?=sheep)`
 	regexComp := regex.MustCompile(regexStr)
 
-	matchStr := regexComp.FindString("The year of our lord, 2025")
+	matchStr := regexComp.FindString("pink cows and yellow sheep")
 	fmt.Println(matchStr)
-	// Output: 2025
+	// Output: yellow
 }
 
 func ExampleReg_FindSubmatch() {
@@ -53,6 +54,71 @@ func ExampleReg_FindSubmatch() {
 	// 2	3
 }
 
+func ExampleReg_FindStringSubmatch() {
+	regexStr := `(\d{4})-(\d{2})-(\d{2})`
+	regexComp := regex.MustCompile(regexStr)
+	inputStr := `The date is 2025-02-10`
+
+	match := regexComp.FindStringSubmatch(inputStr)
+	fmt.Println(match[1])
+	fmt.Println(match[3])
+	// Output: 2025
+	// 10
+}
+
+func ExampleReg_FindAllSubmatch() {
+	regexStr := `(\d)\.(\d)(\d)`
+	regexComp := regex.MustCompile(regexStr)
+
+	matches := regexComp.FindAllSubmatch("3.14+8.97")
+	fmt.Println(matches[0][0]) // 0-group (entire match) of 1st match (0-indexed)
+	fmt.Println(matches[0][1]) // 1st group of 1st match
+	fmt.Println(matches[1][0]) // 0-group of 2nd match
+	fmt.Println(matches[1][1]) // 1st group of 2nd math
+	// Output: 0	4
+	// 0	1
+	// 5	9
+	// 5	6
+}
+
+func ExampleReg_FindAllString() {
+	regexStr := `<0-255>\.<0-255>\.<0-255>\.<0-255>`
+	inputStr := `192.168.220.7 pings 9.9.9.9`
+	regexComp := regex.MustCompile(regexStr)
+
+	matchStrs := regexComp.FindAllString(inputStr)
+
+	fmt.Println(matchStrs[0])
+	fmt.Println(matchStrs[1])
+	// Output: 192.168.220.7
+	// 9.9.9.9
+}
+
+func ExampleReg_FindAllStringSubmatch() {
+	// 'https' ...
+	// followed by 1 or more alphanumeric characters (including period) ...
+	// then a forward slash ...
+	// followed by one more of :
+	// 		word character,
+	// 		question mark,
+	// 		period,
+	// 		equals sign
+	regexStr := `https://([a-z0-9\.]+)/([\w.?=]+)`
+	regexComp := regex.MustCompile(regexStr, regex.RE_CASE_INSENSITIVE)
+	inputStr := `You can find me at https://twomorecents.org/index.html and https://news.ycombinator.com/user?id=aadhavans`
+
+	matchIndices := regexComp.FindAllStringSubmatch(inputStr)
+	fmt.Println(matchIndices[0][1]) // 1st group of 1st match (0-indexed)
+	fmt.Println(matchIndices[0][2]) // 2nd group of 1st match
+	fmt.Println(matchIndices[1][1]) // 1st group of 2nd match
+	fmt.Println(matchIndices[1][2]) // 2nd group of 2nd match
+	// Output: twomorecents.org
+	// index.html
+	// news.ycombinator.com
+	// user?id=aadhavans
+
+}
+
 func ExampleReg_Expand() {
 	inputStr := `option1: value1
 	option2: value2`
@@ -89,3 +155,27 @@ func ExampleReg_Longest() {
 	// Output: x
 	// xx
 }
+
+func ExampleReg_ReplaceAll() {
+	regexStr := `(\d)(\w)`
+	inputStr := "5d9t"
+	regexComp := regex.MustCompile(regexStr)
+	fmt.Println(regexComp.ReplaceAll(inputStr, `$2$1`))
+	// Output: d5t9
+}
+
+func ExampleReg_ReplaceAllLiteral() {
+	regexStr := `fox|dog`
+	inputStr := "the quick brown fox jumped over the lazy dog"
+	regexComp := regex.MustCompile(regexStr)
+	fmt.Println(regexComp.ReplaceAllLiteral(inputStr, `duck`))
+	// Output: the quick brown duck jumped over the lazy duck
+}
+
+func ExampleReg_ReplaceAllFunc() {
+	regexStr := `\w{5,}`
+	inputStr := `all five or more letter words in this string are capitalized`
+	regexComp := regex.MustCompile(regexStr)
+	fmt.Println(regexComp.ReplaceAllFunc(inputStr, strings.ToUpper))
+	// Output: all five or more LETTER WORDS in this STRING are CAPITALIZED
+}

regex/matching.go

@@ -205,6 +205,29 @@ func (re Reg) FindAllSubmatch(str string) []Match {
 	return indices
 }
 
+// FindAllSubmatch returns a double-slice of strings. Each slice contains the text of a match, including all submatches.
+// A return value of nil indicates no match.
+func (re Reg) FindAllStringSubmatch(str string) [][]string {
+	match := re.FindAllSubmatch(str)
+	if len(match) == 0 {
+		return nil
+	}
+	rtv := make([][]string, len(match))
+	for i := range rtv {
+		rtv[i] = make([]string, re.numGroups+1)
+	}
+	rtv = funcMap(match, func(m Match) []string {
+		return funcMap(m, func(g Group) string {
+			if g.IsValid() {
+				return str[g.StartIdx:g.EndIdx]
+			} else {
+				return ""
+			}
+		})
+	})
+	return rtv
+}
+
 func addStateToList(str []rune, idx int, list []nfaState, state nfaState, threadGroups []Group, visited []nfaState, preferLongest bool) []nfaState {
 	if stateExists(list, state) || stateExists(visited, state) {
 		return list
@@ -327,7 +350,7 @@ func (re Reg) Expand(dst string, template string, src string, match Match) strin
 				i++
 			} else {
 				numStr := ""
-				for unicode.IsDigit(templateRuneSlc[i]) {
+				for i < len(templateRuneSlc) && unicode.IsDigit(templateRuneSlc[i]) {
 					numStr += string(templateRuneSlc[i])
 					i++
 				}
@@ -372,3 +395,66 @@ func (re Reg) LiteralPrefix() (prefix string, complete bool) {
 	}
 	return prefix, complete
 }
+
+// ReplaceAll replaces all matches of the expression in src, with the text in repl. In repl, variables are interpreted
+// as they are in [Reg.Expand]. The resulting string is returned.
+func (re Reg) ReplaceAll(src string, repl string) string {
+	matches := re.FindAllSubmatch(src)
+	i := 0
+	currentMatch := 0
+	dst := ""
+	for i < len(src) {
+		if currentMatch < len(matches) && matches[currentMatch][0].IsValid() && i == matches[currentMatch][0].StartIdx {
+			dst += re.Expand("", repl, src, matches[currentMatch])
+			i = matches[currentMatch][0].EndIdx
+			currentMatch++
+		} else {
+			dst += string(src[i])
+			i++
+		}
+	}
+	return dst
+}
+
+// ReplaceAllLiteral replaces all matches of the expression in src, with the text in repl. The text is replaced directly,
+// without any expansion.
+func (re Reg) ReplaceAllLiteral(src string, repl string) string {
+	zerogroups := re.FindAll(src)
+	currentMatch := 0
+	i := 0
+	dst := ""
+
+	for i < len(src) {
+		if currentMatch < len(zerogroups) && i == zerogroups[currentMatch].StartIdx {
+			dst += repl
+			i = zerogroups[currentMatch].EndIdx
+			currentMatch += 1
+		} else {
+			dst += string(src[i])
+			i++
+		}
+	}
+	return dst
+}
+
+// ReplaceAllFunc replaces every match of the expression in src, with the return value of the function replFunc.
+// replFunc takes in the matched string. The return value is substituted in directly without expasion.
+func (re Reg) ReplaceAllFunc(src string, replFunc func(string) string) string {
+	zerogroups := re.FindAll(src)
+	currentMatch := 0
+	i := 0
+	dst := ""
+
+	for i < len(src) {
+		if currentMatch < len(zerogroups) && i == zerogroups[currentMatch].StartIdx {
+			dst += replFunc(src[zerogroups[currentMatch].StartIdx:zerogroups[currentMatch].EndIdx])
+			i = zerogroups[currentMatch].EndIdx
+			currentMatch += 1
+		} else {
+			dst += string(src[i])
+			i++
+		}
+	}
+	return dst
+
+}

regex/re_test.go

@@ -861,6 +861,60 @@ func TestFindStringSubmatch(t *testing.T) {
 		})
 	}
 }
+
+func TestFindAllStringSubmatch(t *testing.T) {
+	for _, test := range groupTests {
+		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)
+				}
+			}
+			matchStrs := regComp.FindAllStringSubmatch(test.str)
+			if matchStrs == nil {
+				if len(test.result) != 0 {
+					expectedStrs := funcMap(test.result, func(m Match) []string {
+						return funcMap(m, func(g Group) string {
+							if g.IsValid() {
+								return test.str[g.StartIdx:g.EndIdx]
+							} else {
+								return ""
+							}
+						})
+					})
+					t.Errorf("Wanted %v got no match\n", expectedStrs)
+				}
+			} else if len(test.result) == 0 {
+				t.Errorf("Wanted no match got %v\n", matchStrs)
+			} else {
+				expectedStrs := funcMap(test.result, func(m Match) []string {
+					return funcMap(m, func(g Group) string {
+						if g.IsValid() {
+							return test.str[g.StartIdx:g.EndIdx]
+						} else {
+							return ""
+						}
+					})
+				})
+				for i, matchStr := range matchStrs {
+					for j, groupStr := range matchStr {
+						if groupStr == "" {
+							if j < len(expectedStrs[i]) && expectedStrs[i][j] != "" {
+								t.Errorf("Wanted %v	Got %v\n", expectedStrs, matchStrs)
+							}
+						} else {
+							if expectedStrs[i][j] != groupStr {
+								t.Errorf("Wanted %v	Got %v\n", expectedStrs, matchStrs)
+							}
+						}
+					}
+				}
+			}
+		})
+	}
+}
+
 func TestFindAllSubmatch(t *testing.T) {
 	for _, test := range groupTests {
 		t.Run(test.re+"	"+test.str, func(t *testing.T) {