sm-journal-plugin/classes/headings.go

package classes

import (
	"bytes"
	"strings"

	xhtml "golang.org/x/net/html"
)

// ConvertH1 turns every h1 element of html into an h2 and returns the
// result with the number of headings it converted. It works on the
// x/net/html tokenizer's raw tokens: only the tag name of an h1 start, end
// or self-closing tag changes, and every other byte (attributes, text,
// comments, the content of script or style) is copied as it is. Text that
// merely looks like a tag inside raw-text elements or comments is not a
// tag and is not touched. html without an h1 comes back unchanged with 0,
// and the bytes of an unfinished tag at the end of html are kept.
func ConvertH1(html string) (string, int) {
	if !containsFold(html, "<h1") && !containsFold(html, "</h1") {
		return html, 0
	}
	z := xhtml.NewTokenizer(strings.NewReader(html))
	var b bytes.Buffer
	b.Grow(len(html))
	count := 0
	consumed := 0
	for {
		tt := z.Next()
		if tt == xhtml.ErrorToken {
			// The input may end inside something the tokenizer reads as a
			// tag ("a <b"): those bytes are kept as they are.
			b.WriteString(html[min(consumed, len(html)):])
			break
		}
		raw := z.Raw()
		consumed += len(raw)
		switch tt {
		case xhtml.StartTagToken, xhtml.SelfClosingTagToken:
			if name, _ := z.TagName(); string(name) == "h1" && len(raw) >= 3 {
				b.WriteString("<h2")
				b.Write(raw[3:])
				count++
				continue
			}
		case xhtml.EndTagToken:
			if name, _ := z.TagName(); string(name) == "h1" && len(raw) >= 4 {
				b.WriteString("</h2")
				b.Write(raw[4:])
				continue
			}
		}
		b.Write(raw)
	}
	if count == 0 && b.String() == html {
		return html, 0
	}
	return b.String(), count
}

// CountH1 is the number of h1 start tags in html, as ConvertH1 counts them.
func CountH1(html string) int {
	_, n := ConvertH1(html)
	return n
}

func containsFold(s, sub string) bool {
	return strings.Contains(strings.ToLower(s), sub)
}

// ConvertContentH1 applies ConvertH1 to a post body and its rendered HTML
// (content and content_html) and returns both with the number of headings
// converted: content_html's count, or content's when content_html had none.
// content is read as markdown, as every render path reads it (FormatHTML
// passes raw HTML through, so an HTML body is HTML blocks and is converted
// as before): an <h1> inside a code block or code span keeps its tag
// whatever the body's first character, so a markdown post that opens with
// an HTML block keeps its code samples (33-REVIEW-GAPFIX WR-01), and a raw
// <h1> outside code becomes <h2>, as in the rendered HTML.
func ConvertContentH1(content, contentHTML string) (string, string, int) {
	contentHTML, nHTML := ConvertH1(contentHTML)
	content, nContent := convertH1OutsideCode(content)
	if nHTML > 0 {
		return content, contentHTML, nHTML
	}
	return content, contentHTML, nContent
}

// convertH1OutsideCode applies ConvertH1 to the parts of markdown md
// outside its fenced and indented code blocks and code spans (goldmark's
// AST, the engine of FormatHTML): an h1 shown in a code sample keeps its
// tag. HTML blocks are not code, so an HTML body is converted whole. md
// without an h1 tag comes back unchanged with 0 without being parsed.
func convertH1OutsideCode(md string) (string, int) {
	if !containsFold(md, "<h1") && !containsFold(md, "</h1") {
		return md, 0
	}
	var b strings.Builder
	b.Grow(len(md))
	count := 0
	last := 0
	apply := func(part string) {
		out, n := ConvertH1(part)
		count += n
		b.WriteString(out)
	}
	for _, r := range markdownCodeRanges(md) {
		apply(md[last:r[0]])
		b.WriteString(md[r[0]:r[1]])
		last = r[1]
	}
	apply(md[last:])
	if count == 0 && b.String() == md {
		return md, 0
	}
	return b.String(), count
}

// ConvertTranslationH1 applies ConvertContentH1 to the string content and
// content_html of one locale's translated attributes, in place, and returns
// the number of headings converted. content is rewritten outside code
// only (ConvertContentH1). Other attributes and values that are not strings are
// left alone.
func ConvertTranslationH1(attrs map[string]any) int {
	if attrs == nil {
		return 0
	}
	content, hasContent := attrs["content"].(string)
	html, hasHTML := attrs["content_html"].(string)
	if !hasContent && !hasHTML {
		return 0
	}
	content, html, n := ConvertContentH1(content, html)
	if hasContent {
		attrs["content"] = content
	}
	if hasHTML {
		attrs["content_html"] = html
	}
	return n
}