[pull] master from PaulSonOfLars:master

.github/workflows/go.yml

@@ -13,12 +13,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Set up Go
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@v5
         with:
-          go-version: '1.19'
+          go-version: 'stable'
 
       - name: Check out code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Get dependencies
         run: go mod download
@@ -33,15 +33,17 @@ jobs:
     name: Lint
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-go@v3
+      - uses: actions/setup-go@v5
         with:
-          go-version: '1.19'
+          go-version: 'stable'
 
       - name: Check out code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: golangci-lint
-        uses: golangci/golangci-lint-action@v3
+        uses: golangci/golangci-lint-action@v8
         with:
-          # Optional: version of golangci-lint to use in form of v1.2 or v1.2.3 or `latest` to use the latest version
           version: latest
+          # skip cache to avoid flakes (and avoid using gh-action storage)
+          skip-cache: true
+          skip-save-cache: true

common.go

@@ -18,11 +18,11 @@ func validStart(pos int, input []rune) bool {
 	}
 
 	// If the previous char is alphanumeric, it is an invalid start char.
-	return !(unicode.IsLetter(input[pos-1]) || unicode.IsDigit(input[pos-1]))
+	return !unicode.IsLetter(input[pos-1]) && !unicode.IsDigit(input[pos-1])
 }
 
 func validEnd(pos int, input []rune) bool {
-	// First char is not a valid end char.
+	// First char is not a valid end char; we do NOT allow empty entities.
 	// If the end char has a space before it, its not valid either.
 	if pos == 0 || unicode.IsSpace(input[pos-1]) {
 		return false
@@ -34,17 +34,7 @@ func validEnd(pos int, input []rune) bool {
 	}
 
 	// If the next char is alphanumeric, it is an invalid end char.
-	return !(unicode.IsLetter(input[pos+1]) || unicode.IsDigit(input[pos+1]))
-}
-
-func contains(r rune, rr []rune) bool {
-	for _, x := range rr {
-		if r == x {
-			return true
-		}
-	}
-
-	return false
+	return !unicode.IsLetter(input[pos+1]) && !unicode.IsDigit(input[pos+1])
 }
 
 var link = regexp.MustCompile(`a href="(.*)"`)

commonV2.go

@@ -4,8 +4,22 @@ import (
 	"strings"
 )
 
+func hasPrefix(s string, tgPrefixes []string) bool {
+	rest, ok := strings.CutPrefix(s, "tg://")
+	if !ok {
+		return false
+	}
+
+	for _, prefix := range tgPrefixes {
+		if strings.HasPrefix(rest, prefix) {
+			return true
+		}
+	}
+	return false
+}
+
 // finds the middle '](' section of in a link markdown
-func findLinkMidSectionIdx(in []rune, emoji bool) int {
+func findLinkMidSectionIdx(in []rune, tgSpecial bool) int {
 	var textEnd int
 	var offset int
 	for offset < len(in) {
@@ -15,8 +29,8 @@ func findLinkMidSectionIdx(in []rune, emoji bool) int {
 		}
 		textEnd = offset + idx
 		if !IsEscaped(in, textEnd) {
-			isEmoji := strings.HasPrefix(string(in[textEnd+2:]), "tg://emoji?id=")
-			if (isEmoji && emoji) || (!isEmoji && !emoji) {
+			prefixed := hasPrefix(string(in[textEnd+2:]), []string{"emoji?", "time?"})
+			if (prefixed && tgSpecial) || (!prefixed && !tgSpecial) {
 				return textEnd
 			}
 		}
@@ -44,8 +58,8 @@ func findLinkEndSectionIdx(in []rune) int {
 }
 
 // finds the middle and closing sections of in a link markdown
-func findLinkSectionsIdx(in []rune, isEmojiLink bool) (int, int) {
-	textEnd := findLinkMidSectionIdx(in, isEmojiLink)
+func findLinkSectionsIdx(in []rune, tgSpecial bool) (int, int) {
+	textEnd := findLinkMidSectionIdx(in, tgSpecial)
 	if textEnd < 0 {
 		return -1, -1
 	}
@@ -60,7 +74,7 @@ func findLinkSectionsIdx(in []rune, isEmojiLink bool) (int, int) {
 	// Now, we iterate over the text in between the mid and end sections to see if any other mid sections exist.
 	// If yes, we choose those instead - it would be invalid in a URL anyway.
 	for textEnd < offsetLinkEnd {
-		newTextEnd := findLinkMidSectionIdx(in[textEnd+1:offsetLinkEnd], isEmojiLink)
+		newTextEnd := findLinkMidSectionIdx(in[textEnd+1:offsetLinkEnd], tgSpecial)
 		if newTextEnd == -1 {
 			break
 		}
@@ -70,9 +84,9 @@ func findLinkSectionsIdx(in []rune, isEmojiLink bool) (int, int) {
 	return textEnd, offsetLinkEnd
 }
 
-func getLinkContents(in []rune, emoji bool) (bool, []rune, string, int) {
+func getLinkContents(in []rune, tgSpecial bool) (bool, []rune, string, int) {
 	// find ]( and then )
-	textEndIdx, urlEndIdx := findLinkSectionsIdx(in, emoji)
+	textEndIdx, urlEndIdx := findLinkSectionsIdx(in, tgSpecial)
 	if textEndIdx < 0 || urlEndIdx < 0 {
 		return false, nil, "", 0
 	}
@@ -82,6 +96,13 @@ func getLinkContents(in []rune, emoji bool) (bool, []rune, string, int) {
 	return true, text, content, urlEndIdx + 1
 }
 
+func isCodeBlockNewlineEnd(in []rune, offset int, item string) bool {
+	if item != "```" {
+		return false
+	}
+	return offset == 0 || in[offset-1] == '\n'
+}
+
 func getValidEnd(in []rune, s string) int {
 	offset := 0
 	for offset < len(in) {
@@ -92,7 +113,7 @@ func getValidEnd(in []rune, s string) int {
 
 		end := offset + idx
 		// validEnd check has double logic to account for multi char strings
-		if validEnd(end, in) && validEnd(end+len(s)-1, in) && !IsEscaped(in, end) {
+		if (validEnd(end, in) || isCodeBlockNewlineEnd(in, end, s)) && validEnd(end+len(s)-1, in) && !IsEscaped(in, end) {
 			idx = stringIndex(in[end+1:], s)
 			for idx == 0 {
 				end++
@@ -148,7 +169,7 @@ func isClosingTag(in []rune, pos int) bool {
 	return false
 }
 
-func getClosingTag(in []rune, tag string) (int, int) {
+func getClosingTag(in []rune, openingTag string, closingTag string) (int, int) {
 	offset := 0
 	subtags := 0
 	for offset < len(in) {
@@ -164,9 +185,9 @@ func getClosingTag(in []rune, tag string) (int, int) {
 		}
 
 		closingTagIdx := openingTagIdx + 2 + c
-		if string(in[openingTagIdx+1:closingTagIdx]) == tag { // found a nested tag, this is annoying
+		if string(in[openingTagIdx+1:closingTagIdx]) == openingTag { // found a nested tag, this is annoying
 			subtags++
-		} else if isClosingTag(in, openingTagIdx) && string(in[openingTagIdx+2:closingTagIdx]) == tag {
+		} else if isClosingTag(in, openingTagIdx) && string(in[openingTagIdx+2:closingTagIdx]) == closingTag {
 			if subtags == 0 {
 				return openingTagIdx, closingTagIdx
 			}

common_test.go

@@ -0,0 +1,14 @@
+package tg_md2html_test
+
+import "github.com/PaulSonOfLars/gotg_md2html"
+
+func testConverter() *tg_md2html.ConverterV2 {
+	return tg_md2html.NewV2(map[string]string{
+		"url":  "buttonurl",
+		"text": "buttontext",
+	}, map[string]string{
+		"primary": "primary",
+		"success": "success",
+		"danger":  "danger",
+	})
+}

go.mod

@@ -1,8 +1,8 @@
 module github.com/PaulSonOfLars/gotg_md2html
 
-go 1.19
+go 1.24
 
-require github.com/stretchr/testify v1.8.4
+require github.com/stretchr/testify v1.11.1
 
 require (
 	github.com/davecgh/go-spew v1.1.1 // indirect

go.sum

@@ -2,8 +2,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
-github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

md2html.go

@@ -2,6 +2,8 @@ package tg_md2html
 
 import (
 	"html"
+	"maps"
+	"slices"
 	"strings"
 )
 
@@ -102,7 +104,7 @@ func (cv *Converter) md2html(input []rune, buttons bool) (string, []Button) {
 			v[char] = append(v[char], pos-offset)
 			containedMDChars = append(containedMDChars, char)
 		case '\\':
-			if len(input) <= pos+1 || !contains(input[pos+1], allMdChars) {
+			if len(input) <= pos+1 || !slices.Contains(allMdChars, input[pos+1]) {
 				continue
 			}
 			escaped = true
@@ -192,9 +194,7 @@ func (cv *Converter) md2html(input []rune, buttons bool) (string, []Button) {
 			}
 			i = cnt // set i to copy
 
-			for x, y := range bkp {
-				v[x] = y
-			}
+			maps.Copy(v, bkp)
 
 		case '[':
 			nameOpen, rest := posArr[0], posArr[1:]
@@ -405,7 +405,7 @@ func (cv *Converter) stripHTML(r []rune) string {
 func EscapeMarkdown(r []rune, toEscape []rune) string {
 	out := strings.Builder{}
 	for i, x := range r {
-		if contains(x, toEscape) {
+		if slices.Contains(toEscape, x) {
 			if i == 0 || i == len(r)-1 || validEnd(i, r) || validStart(i, r) {
 				out.WriteRune('\\')
 			}