haven/hswg/asciidoc.go

55 lines
1.4 KiB
Go

package main
import (
"bytes"
"io"
"strings"
"unicode"
"unicode/utf8"
)
// isTitle returns the title level if the lines seem to form a title,
// zero otherwise. Input lines may inclide trailing newlines.
func isTitle(line1, line2 []byte) int {
// This is a very naïve method, we should target graphemes (thus at least
// NFC normalize the lines first) and account for wide characters.
diff := utf8.RuneCount(line1) - utf8.RuneCount(line2)
if len(line2) < 2 || diff < -1 || diff > 1 {
return 0
}
// "Don't be fooled by back-to-back delimited blocks."
// Still gets fooled by other things, though.
if bytes.IndexFunc(line1, func(r rune) bool {
return unicode.IsLetter(r) || unicode.IsNumber(r)
}) < 0 {
return 0
}
// The underline must be homogenous.
for _, r := range bytes.TrimRight(line2, "\r\n") {
if r != line2[0] {
return 0
}
}
return 1 + strings.IndexByte("=-~^+", line2[0])
}
func writeLine(w *io.PipeWriter, cur, next []byte) []byte {
if level := isTitle(cur, next); level > 0 {
w.Write(append(bytes.Repeat([]byte{'='}, level), ' '))
next = nil
}
w.Write(cur)
return next
}
// ConvertTitles converts AsciiDoc two-line (underlined) titles to single-line.
func ConvertTitles(w *io.PipeWriter, input []byte) {
var last []byte
for _, cur := range bytes.SplitAfter(input, []byte{'\n'}) {
last = writeLine(w, last, cur)
}
writeLine(w, last, nil)
}