From af7ffaa2798148e2a1b249da2330200bc032d7b1 Mon Sep 17 00:00:00 2001
From: mrsdizzie <info@mrsdizzie.com>
Date: Tue, 30 Jun 2020 17:34:03 -0400
Subject: 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>
---
 modules/markup/markdown/markdown.go | 26 ++++++++++++++++++++++++++
 modules/markup/sanitizer.go         |  8 ++++----
 2 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'modules/markup')

diff --git a/modules/markup/markdown/markdown.go b/modules/markup/markdown/markdown.go
index 128268bc88..9197dd2fe1 100644
--- a/modules/markup/markdown/markdown.go
+++ b/modules/markup/markdown/markdown.go
@@ -15,7 +15,9 @@ import (
 	"code.gitea.io/gitea/modules/setting"
 	giteautil "code.gitea.io/gitea/modules/util"
 
+	chromahtml "github.com/alecthomas/chroma/formatters/html"
 	"github.com/yuin/goldmark"
+	"github.com/yuin/goldmark-highlighting"
 	meta "github.com/yuin/goldmark-meta"
 	"github.com/yuin/goldmark/extension"
 	"github.com/yuin/goldmark/parser"
@@ -49,6 +51,30 @@ func render(body []byte, urlPrefix string, metas map[string]string, wikiMarkdown
 				extension.TaskList,
 				extension.DefinitionList,
 				common.FootnoteExtension,
+				highlighting.NewHighlighting(
+					highlighting.WithFormatOptions(
+						chromahtml.WithClasses(true),
+						chromahtml.PreventSurroundingPre(true),
+					),
+					highlighting.WithWrapperRenderer(func(w util.BufWriter, c highlighting.CodeBlockContext, entering bool) {
+						language, _ := c.Language()
+						if language == nil {
+							language = []byte("text")
+						}
+						if entering {
+							// include language-x class as part of commonmark spec
+							_, err := w.WriteString("<pre><code class=\"chroma language-" + string(language) + "\">")
+							if err != nil {
+								return
+							}
+						} else {
+							_, err := w.WriteString("</code></pre>")
+							if err != nil {
+								return
+							}
+						}
+					}),
+				),
 				meta.Meta,
 			),
 			goldmark.WithParserOptions(
diff --git a/modules/markup/sanitizer.go b/modules/markup/sanitizer.go
index 1041d56a32..e5f6e75084 100644
--- a/modules/markup/sanitizer.go
+++ b/modules/markup/sanitizer.go
@@ -37,8 +37,8 @@ func NewSanitizer() {
 // ReplaceSanitizer replaces the current sanitizer to account for changes in settings
 func ReplaceSanitizer() {
 	sanitizer.policy = bluemonday.UGCPolicy()
-	// We only want to allow HighlightJS specific classes for code blocks
-	sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^language-[\w-]+$`)).OnElements("code")
+	// For Chroma markdown plugin
+	sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^(chroma )?language-[\w-]+$`)).OnElements("code")
 
 	// Checkboxes
 	sanitizer.policy.AllowAttrs("type").Matching(regexp.MustCompile(`^checkbox$`)).OnElements("input")
@@ -65,8 +65,8 @@ func ReplaceSanitizer() {
 	// Allow classes for emojis
 	sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`emoji`)).OnElements("img")
 
-	// Allow icons, checkboxes and emojis on span
-	sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^((icon(\s+[\p{L}\p{N}_-]+)+)|(ui checkbox)|(ui checked checkbox)|(emoji))$`)).OnElements("span")
+	// Allow icons, checkboxes, emojis, and chroma syntax on span
+	sanitizer.policy.AllowAttrs("class").Matching(regexp.MustCompile(`^((icon(\s+[\p{L}\p{N}_-]+)+)|(ui checkbox)|(ui checked checkbox)|(emoji))$|^([a-z][a-z0-9]{0,2})$`)).OnElements("span")
 
 	// Allow generally safe attributes
 	generalSafeAttrs := []string{"abbr", "accept", "accept-charset",
-- 
cgit v1.2.3