1 Commits

Author SHA1 Message Date
Alex Schroeder
a093fc5378 Switch to blackfriday, remove Gemtext instructions 2023-09-11 15:42:06 +02:00
5 changed files with 56 additions and 102 deletions

View File

@@ -47,8 +47,8 @@ some of which are enable by default:
* MathJax is supported (but needs a separte setup)
See the section on
[extensions](https://github.com/gomarkdown/markdown#extensions) in the
Markdown library for information on the various extensions.
[extensions](https://github.com/russross/blackfriday#extensions) in
the Blackfriday library for information on the various extensions.
A table with footers and a columnspan:
@@ -346,50 +346,8 @@ that matches everything:
## Customization (with recompilation)
The Markdown parser can be customized and
[extensions](https://pkg.go.dev/github.com/gomarkdown/markdown/parser#Extensions)
can be added. There's an example in the
[usage](https://github.com/gomarkdown/markdown#usage) section. You'll
need to make changes to the `viewHandler` yourself.
### Render Gemtext
In a first approximation, Gemtext is valid Markdown except for the
rocket links (`=>`). Here's how to modify the `loadPage` so that a
`.gmi` file is loaded if no `.md` is found, and the rocket links are
translated into Markdown:
```go
func loadPage(name string) (*Page, error) {
filename := name + ".md"
body, err := os.ReadFile(filename)
if err == nil {
return &Page{Title: name, Name: name, Body: body}, nil
}
filename = name + ".gmi"
body, err = os.ReadFile(filename)
if err == nil {
re := regexp.MustCompile(`(?m)^=>\s*(\S+)\s+(.+)`)
body = []byte(re.ReplaceAllString(string(body), `* [$2]($1)`))
return &Page{Title: name, Name: name, Body: body}, nil
}
return nil, err
}
```
There is a small problem, however: By default, Markdown expects an
empty line before a list begins. The following change to `renderHtml`
uses the `NoEmptyLineBeforeBlock` extension for the parser:
```go
func (p* Page) renderHtml() {
// Here is where a new extension is added!
extensions := parser.CommonExtensions | parser.NoEmptyLineBeforeBlock
markdownParser := parser.NewWithExtensions(extensions)
maybeUnsafeHTML := markdown.ToHTML(p.Body, markdownParser, nil)
html := bluemonday.UGCPolicy().SanitizeBytes(maybeUnsafeHTML)
p.Html = template.HTML(html);
}
```
[extensions](https://github.com/russross/blackfriday#extensions) can
be added. You'll need to make changes to `renderHtml` yourself.
## Understanding search

8
go.mod
View File

@@ -4,16 +4,20 @@ go 1.21.0
require (
github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0
github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12
github.com/microcosm-cc/bluemonday v1.0.25
github.com/pemistahl/lingua-go v1.4.0
github.com/russross/blackfriday/v2 v2.1.0
)
require (
github.com/aymerick/douceur v0.2.0 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/gorilla/css v1.0.0 // indirect
github.com/pemistahl/lingua-go v1.4.0 // indirect
github.com/pmezard/go-difflib v1.0.0 // indirect
github.com/shopspring/decimal v1.3.1 // indirect
github.com/stretchr/testify v1.8.4 // indirect
golang.org/x/exp v0.0.0-20221106115401-f9659909a136 // indirect
golang.org/x/net v0.12.0 // indirect
google.golang.org/protobuf v1.31.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
)

15
go.sum
View File

@@ -1,19 +1,27 @@
github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0 h1:b+7JSiBM+hnLQjP/lXztks5hnLt1PS46hktG9VOJgzo=
github.com/dgryski/go-trigram v0.0.0-20160407183937-79ec494e1ad0/go.mod h1:qzKC/DpcxK67zaSHdCmIv3L9WJViHVinYXN2S7l3RM8=
github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12 h1:uK3X/2mt4tbSGoHvbLBHUny7CKiuwUip3MArtukol4E=
github.com/gomarkdown/markdown v0.0.0-20230716120725-531d2d74bc12/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
github.com/microcosm-cc/bluemonday v1.0.25 h1:4NEwSfiJ+Wva0VxN5B8OwMicaJvD8r9tlJWm9rtloEg=
github.com/microcosm-cc/bluemonday v1.0.25/go.mod h1:ZIOjCQp1OrzBBPIJmfX4qDYFuhU02nx4bn030ixfHLE=
github.com/pemistahl/lingua-go v1.4.0 h1:ifYhthrlW7iO4icdubwlduYnmwU37V1sbNrwhKBR4rM=
github.com/pemistahl/lingua-go v1.4.0/go.mod h1:ECuM1Hp/3hvyh7k8aWSqNCPlTxLemFZsRjocUf3KgME=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
golang.org/x/exp v0.0.0-20221106115401-f9659909a136 h1:Fq7F/w7MAa1KJ5bt2aJ62ihqp9HDcRuyILskkpIAurw=
golang.org/x/exp v0.0.0-20221106115401-f9659909a136/go.mod h1:CxIveKay+FTh1D0yPZemJVgC/95VzuuOLq5Qi4xnoYc=
golang.org/x/net v0.12.0 h1:cfawfvKITfUsFCeJIHJrbSxpeu/E81khclypR0GVT50=
@@ -22,3 +30,6 @@ golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8T
google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
google.golang.org/protobuf v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=
google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

44
page.go
View File

@@ -3,11 +3,9 @@ package main
import (
"bytes"
"fmt"
"github.com/gomarkdown/markdown"
"github.com/gomarkdown/markdown/ast"
"github.com/gomarkdown/markdown/parser"
"github.com/microcosm-cc/bluemonday"
"github.com/pemistahl/lingua-go"
"github.com/russross/blackfriday/v2"
"html/template"
"os"
"path/filepath"
@@ -103,7 +101,7 @@ func (p *Page) handleTitle(replace bool) {
// renderHtml renders the Page.Body to HTML and sets Page.Html.
func (p *Page) renderHtml() {
maybeUnsafeHTML := markdown.ToHTML(p.Body, nil, nil)
maybeUnsafeHTML := blackfriday.Run(p.Body)
p.Html = sanitizeBytes(maybeUnsafeHTML)
p.Language = language(p.plainText())
}
@@ -112,26 +110,30 @@ func (p *Page) renderHtml() {
// ignoring all the Markdown and all the newlines. The result is one
// long single line of text.
func (p *Page) plainText() string {
parser := parser.New()
doc := markdown.Parse(p.Body, parser)
optList := []blackfriday.Option{blackfriday.WithExtensions(blackfriday.CommonExtensions)}
parser := blackfriday.New(optList...)
ast := parser.Parse(p.Body)
text := []byte("")
ast.WalkFunc(doc, func(node ast.Node, entering bool) ast.WalkStatus {
if entering && node.AsLeaf() != nil {
text = append(text, node.AsLeaf().Literal...)
text = append(text, []byte(" ")...)
ast.Walk(func(node *blackfriday.Node, entering bool) blackfriday.WalkStatus {
if entering && node.Type == blackfriday.Text {
s := node.Literal
if len(s) == 0 {
return blackfriday.GoToNext
}
// Some Markdown still contains newlines
for i, c := range s {
if c == '\n' {
s[i] = ' '
}
}
if len(text) > 0 && text[len(text)-1] != ' ' && s[0] != ' ' {
text = append(text, ' ')
}
text = append(text, s...)
}
return ast.GoToNext
return blackfriday.GoToNext
})
// Some Markdown still contains newlines
for i, c := range text {
if c == '\n' {
text[i] = ' '
}
}
// Remove trailing space
for len(text) > 0 && text[len(text)-1] == ' ' {
text = text[0 : len(text)-1]
}
return string(text)
}

View File

@@ -2,8 +2,9 @@ package main
import (
"os"
"strings"
"regexp"
"testing"
"github.com/stretchr/testify/assert"
)
func TestPageTitle(t *testing.T) {
@@ -12,19 +13,10 @@ My back aches for you
I sit, stare and type for hours
But yearn for blue sky`)}
p.handleTitle(false)
if p.Title != "Ache" {
t.Logf("The page title was not extracted correctly: %s", p.Title)
t.Fail()
}
if !strings.HasPrefix(string(p.Body), "# Ache") {
t.Logf("The page title was removed: %s", p.Body)
t.Fail()
}
assert.Equal(t, "Ache", p.Title)
assert.Regexp(t, regexp.MustCompile("^# Ache"), string(p.Body))
p.handleTitle(true)
if !strings.HasPrefix(string(p.Body), "My back") {
t.Logf("The page title was not removed: %s", p.Body)
t.Fail()
}
assert.Regexp(t, regexp.MustCompile("^My back"), string(p.Body))
}
func TestPagePlainText(t *testing.T) {
@@ -32,12 +24,8 @@ func TestPagePlainText(t *testing.T) {
The air will not come
To inhale is an effort
The summer heat kills`)}
s := p.plainText()
r := "Water The air will not come To inhale is an effort The summer heat kills"
if s != r {
t.Logf("The plain text version is wrong: %s", s)
t.Fail()
}
assert.Equal(t, r, p.plainText())
}
func TestPageHtml(t *testing.T) {
@@ -46,17 +34,13 @@ Silver leaves shine bright
They droop, boneless, weak and sad
A cruel sun stares down`)}
p.renderHtml()
s := string(p.Html)
r := `<h1>Sun</h1>
<p>Silver leaves shine bright
They droop, boneless, weak and sad
A cruel sun stares down</p>
`
if s != r {
t.Logf("The HTML is wrong: %s", s)
t.Fail()
}
assert.Equal(t, r, string(p.Html))
}
func TestPageDir(t *testing.T) {
@@ -68,10 +52,8 @@ A slow shuffle in the dark
Moonlight floods the aisle`)}
p.save()
o, err := loadPage("testdata/moon")
if err != nil || string(o.Body) != string(p.Body) {
t.Logf("File in subdirectory not loaded: %s", p.Name)
t.Fail()
}
assert.NoError(t, err, "load page")
assert.Equal(t, p.Body, o.Body)
t.Cleanup(func() {
_ = os.RemoveAll("testdata")
})
@@ -82,8 +64,5 @@ func TestLanguage(t *testing.T) {
My back hurts at night
My shoulders won't budge today
Winter bones I say`)
if l != "en" {
t.Logf("Language detected: %s", l)
t.Fail()
}
assert.Equal(t, "en", l)
}