129 lines
4.0 KiB
Go
129 lines
4.0 KiB
Go
package outboundtext
|
|
|
|
import "strings"
|
|
|
|
func NormalizeMath(markdown string) string {
|
|
if !carriesMath(markdown) {
|
|
return markdown
|
|
}
|
|
content := mathSpanRE.ReplaceAllStringFunc(markdown, convertMathSpan)
|
|
// Outside math spans only LaTeX commands are converted. Identifiers and URLs
|
|
// (resource://…_pltQ) must never be rewritten: a mangled reference can no
|
|
// longer be published, and the outbound sanitizer then drops the whole image.
|
|
content = commandRE.ReplaceAllStringFunc(content, replaceCommand)
|
|
content = blankRunRE.ReplaceAllString(content, " ")
|
|
return content
|
|
}
|
|
|
|
func convertMathSpan(span string) string {
|
|
inner := span
|
|
switch {
|
|
case strings.HasPrefix(inner, "$$"):
|
|
inner = strings.TrimSuffix(strings.TrimPrefix(inner, "$$"), "$$")
|
|
return "\n" + convertMath(inner) + "\n"
|
|
case strings.HasPrefix(inner, `\[`):
|
|
inner = strings.TrimSuffix(strings.TrimPrefix(inner, `\[`), `\]`)
|
|
case strings.HasPrefix(inner, `\(`):
|
|
inner = strings.TrimSuffix(strings.TrimPrefix(inner, `\(`), `\)`)
|
|
default:
|
|
inner = strings.TrimSuffix(strings.TrimPrefix(inner, "$"), "$")
|
|
}
|
|
return convertMath(inner)
|
|
}
|
|
|
|
func convertMath(inner string) string {
|
|
content := inner
|
|
for from, to := range escapedPunctuation {
|
|
content = strings.ReplaceAll(content, from, to)
|
|
}
|
|
for i := 0; i < 3; i++ {
|
|
next := sqrtRE.ReplaceAllStringFunc(content, expandRoot)
|
|
next = fracRE.ReplaceAllString(next, "($1)/($2)")
|
|
next = supBracedRE.ReplaceAllStringFunc(next, convertSuperscript)
|
|
next = subBracedRE.ReplaceAllStringFunc(next, convertSubscript)
|
|
next = supCharRE.ReplaceAllStringFunc(next, convertSuperscript)
|
|
next = subCharRE.ReplaceAllStringFunc(next, convertSubscript)
|
|
if next == content {
|
|
break
|
|
}
|
|
content = next
|
|
}
|
|
content = commandRE.ReplaceAllStringFunc(content, replaceCommand)
|
|
content = braceDelimRE.ReplaceAllString(content, "$1")
|
|
return content
|
|
}
|
|
|
|
func carriesMath(markdown string) bool {
|
|
if !strings.Contains(markdown, "$") && !strings.Contains(markdown, `\(`) &&
|
|
!strings.Contains(markdown, `\[`) && !strings.Contains(markdown, `\sqrt`) &&
|
|
!strings.Contains(markdown, `\frac`) && !strings.Contains(markdown, `\times`) &&
|
|
!strings.Contains(markdown, `\times`) {
|
|
return false
|
|
}
|
|
return true
|
|
}
|
|
|
|
func expandRoot(match string) string {
|
|
parts := sqrtRE.FindStringSubmatch(match)
|
|
degree, radicand := strings.TrimSpace(parts[1]), strings.TrimSpace(parts[2])
|
|
if degree != "" {
|
|
return "√[" + degree + "](" + radicand + ")"
|
|
}
|
|
return "√(" + radicand + ")"
|
|
}
|
|
|
|
func convertSuperscript(match string) string {
|
|
body := strings.TrimPrefix(match, "^")
|
|
body = strings.TrimSuffix(strings.TrimPrefix(body, "{"), "}")
|
|
if mapped, ok := mapRun(body, superscripts); ok {
|
|
return mapped
|
|
}
|
|
return "^(" + body + ")"
|
|
}
|
|
|
|
func convertSubscript(match string) string {
|
|
body := strings.TrimPrefix(match, "_")
|
|
body = strings.TrimSuffix(strings.TrimPrefix(body, "{"), "}")
|
|
if mapped, ok := mapRun(body, subscripts); ok {
|
|
return mapped
|
|
}
|
|
return "_(" + body + ")"
|
|
}
|
|
|
|
func mapRun(body string, table map[rune]string) (string, bool) {
|
|
if body == "" {
|
|
return "", false
|
|
}
|
|
var b strings.Builder
|
|
for _, r := range body {
|
|
mapped, ok := table[r]
|
|
if !ok {
|
|
return "", false
|
|
}
|
|
b.WriteString(mapped)
|
|
}
|
|
return b.String(), true
|
|
}
|
|
|
|
func replaceCommand(match string) string {
|
|
name := strings.TrimPrefix(match, `\`)
|
|
if mapped, ok := mathCommands[name]; ok {
|
|
return mapped
|
|
}
|
|
return name
|
|
}
|
|
|
|
var superscripts = map[rune]string{
|
|
'0': "⁰", '1': "¹", '2': "²", '3': "³", '4': "⁴", '5': "⁵", '6': "⁶",
|
|
'7': "⁷", '8': "⁸", '9': "⁹", '+': "⁺", '-': "⁻", '=': "⁼",
|
|
'(': "⁽", ')': "⁾", 'n': "ⁿ", 'i': "ⁱ", 'T': "ᵀ",
|
|
}
|
|
|
|
var subscripts = map[rune]string{
|
|
'0': "₀", '1': "₁", '2': "₂", '3': "₃", '4': "₄", '5': "₅", '6': "₆",
|
|
'7': "₇", '8': "₈", '9': "₉", '+': "₊", '-': "₋", '=': "₌",
|
|
'(': "₍", ')': "₎", 'a': "ₐ", 'e': "ₑ", 'i': "ᵢ", 'j': "ⱼ", 'k': "ₖ",
|
|
'n': "ₙ", 'o': "ₒ", 'p': "ₚ", 'r': "ᵣ", 's': "ₛ", 't': "ₜ", 'u': "ᵤ",
|
|
'v': "ᵥ", 'x': "ₓ",
|
|
}
|