forgejo/vendor/github.com/alecthomas/chroma/delegate.go
mrsdizzie af7ffaa279
Server-side syntax highlighting for all code (#12047)
* Server-side syntax hilighting for all code

This PR does a few things:

* Remove all traces of highlight.js
* Use chroma library to provide fast syntax hilighting directly on the server
* Provide syntax hilighting for diffs
* Re-style both unified and split diffs views
* Add custom syntax hilighting styling for both regular and arc-green

Fixes #7729
Fixes #10157
Fixes #11825
Fixes #7728
Fixes #3872
Fixes #3682

And perhaps gets closer to #9553

* fix line marker

* fix repo search

* Fix single line select

* properly load settings

* npm uninstall highlight.js

* review suggestion

* code review

* forgot to call function

* fix test

* Apply suggestions from code review

suggestions from @silverwind thanks

Co-authored-by: silverwind <me@silverwind.io>

* code review

* copy/paste error

* Use const for highlight size limit

* Update web_src/less/_repository.less

Co-authored-by: Lauris BH <lauris@nix.lv>

* update size limit to 1MB and other styling tweaks

* fix highlighting for certain diff sections

* fix test

* add worker back as suggested

Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: Lauris BH <lauris@nix.lv>
2020-07-01 00:34:03 +03:00

137 lines
3.2 KiB
Go
Vendored

package chroma
import (
"bytes"
)
type delegatingLexer struct {
root Lexer
language Lexer
}
// DelegatingLexer combines two lexers to handle the common case of a language embedded inside another, such as PHP
// inside HTML or PHP inside plain text.
//
// It takes two lexer as arguments: a root lexer and a language lexer. First everything is scanned using the language
// lexer, which must return "Other" for unrecognised tokens. Then all "Other" tokens are lexed using the root lexer.
// Finally, these two sets of tokens are merged.
//
// The lexers from the template lexer package use this base lexer.
func DelegatingLexer(root Lexer, language Lexer) Lexer {
return &delegatingLexer{
root: root,
language: language,
}
}
func (d *delegatingLexer) Config() *Config {
return d.language.Config()
}
// An insertion is the character range where language tokens should be inserted.
type insertion struct {
start, end int
tokens []Token
}
func (d *delegatingLexer) Tokenise(options *TokeniseOptions, text string) (Iterator, error) { // nolint: gocognit
tokens, err := Tokenise(Coalesce(d.language), options, text)
if err != nil {
return nil, err
}
// Compute insertions and gather "Other" tokens.
others := &bytes.Buffer{}
insertions := []*insertion{}
var insert *insertion
offset := 0
var last Token
for _, t := range tokens {
if t.Type == Other {
if last != EOF && insert != nil && last.Type != Other {
insert.end = offset
}
others.WriteString(t.Value)
} else {
if last == EOF || last.Type == Other {
insert = &insertion{start: offset}
insertions = append(insertions, insert)
}
insert.tokens = append(insert.tokens, t)
}
last = t
offset += len(t.Value)
}
if len(insertions) == 0 {
return d.root.Tokenise(options, text)
}
// Lex the other tokens.
rootTokens, err := Tokenise(Coalesce(d.root), options, others.String())
if err != nil {
return nil, err
}
// Interleave the two sets of tokens.
var out []Token
offset = 0 // Offset into text.
tokenIndex := 0
nextToken := func() Token {
if tokenIndex >= len(rootTokens) {
return EOF
}
t := rootTokens[tokenIndex]
tokenIndex++
return t
}
insertionIndex := 0
nextInsertion := func() *insertion {
if insertionIndex >= len(insertions) {
return nil
}
i := insertions[insertionIndex]
insertionIndex++
return i
}
t := nextToken()
i := nextInsertion()
for t != EOF || i != nil {
// fmt.Printf("%d->%d:%q %d->%d:%q\n", offset, offset+len(t.Value), t.Value, i.start, i.end, Stringify(i.tokens...))
if t == EOF || (i != nil && i.start < offset+len(t.Value)) {
var l Token
l, t = splitToken(t, i.start-offset)
if l != EOF {
out = append(out, l)
offset += len(l.Value)
}
out = append(out, i.tokens...)
offset += i.end - i.start
if t == EOF {
t = nextToken()
}
i = nextInsertion()
} else {
out = append(out, t)
offset += len(t.Value)
t = nextToken()
}
}
return Literator(out...), nil
}
func splitToken(t Token, offset int) (l Token, r Token) {
if t == EOF {
return EOF, EOF
}
if offset == 0 {
return EOF, t
}
if offset == len(t.Value) {
return t, EOF
}
l = t.Clone()
r = t.Clone()
l.Value = l.Value[:offset]
r.Value = r.Value[offset:]
return
}