add dependencies and goldmark cleanup

This commit is contained in:
Antoni Sawicki 2024-07-02 00:36:45 -07:00
parent d00b1d5d7f
commit 7673e15b9e
3 changed files with 3 additions and 58 deletions

5
go.mod
View File

@ -7,8 +7,10 @@ require (
github.com/MaxHalford/halfgone v0.0.0-20171017091812-482157b86ccb github.com/MaxHalford/halfgone v0.0.0-20171017091812-482157b86ccb
github.com/chromedp/cdproto v0.0.0-20240519224452-66462be74baa github.com/chromedp/cdproto v0.0.0-20240519224452-66462be74baa
github.com/chromedp/chromedp v0.9.5 github.com/chromedp/chromedp v0.9.5
github.com/gomarkdown/markdown v0.0.0-20240419095408-642f0ee99ae2 github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646
github.com/soniakeys/quant v1.0.0 github.com/soniakeys/quant v1.0.0
github.com/yuin/goldmark v1.7.2
golang.org/x/image v0.18.0
) )
require ( require (
@ -20,7 +22,6 @@ require (
github.com/gobwas/ws v1.4.0 // indirect github.com/gobwas/ws v1.4.0 // indirect
github.com/josharian/intern v1.0.0 // indirect github.com/josharian/intern v1.0.0 // indirect
github.com/mailru/easyjson v0.7.7 // indirect github.com/mailru/easyjson v0.7.7 // indirect
github.com/yuin/goldmark v1.7.2 // indirect
golang.org/x/net v0.25.0 // indirect golang.org/x/net v0.25.0 // indirect
golang.org/x/sys v0.20.0 // indirect golang.org/x/sys v0.20.0 // indirect
gopkg.in/yaml.v2 v2.4.0 // indirect gopkg.in/yaml.v2 v2.4.0 // indirect

3
go.sum
View File

@ -22,8 +22,6 @@ github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6Wezm
github.com/gobwas/ws v1.3.2/go.mod h1:hRKAFb8wOxFROYNsT1bqfWnhX+b5MFeJM9r2ZSwg/KY= github.com/gobwas/ws v1.3.2/go.mod h1:hRKAFb8wOxFROYNsT1bqfWnhX+b5MFeJM9r2ZSwg/KY=
github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs= github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs=
github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc= github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc=
github.com/gomarkdown/markdown v0.0.0-20240419095408-642f0ee99ae2 h1:yEt5djSYb4iNtmV9iJGVday+i4e9u6Mrn5iP64HH5QM=
github.com/gomarkdown/markdown v0.0.0-20240419095408-642f0ee99ae2/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY= github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y= github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI= github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
@ -53,7 +51,6 @@ github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
github.com/yuin/goldmark v1.7.1 h1:3bajkSilaCbjdKVsKdZjZCLBNPL9pYzrCakKaf4U49U=
github.com/yuin/goldmark v1.7.1/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E= github.com/yuin/goldmark v1.7.1/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E=
github.com/yuin/goldmark v1.7.2 h1:NjGd7lO7zrUn/A7eKwn5PEOt4ONYGqpxSEeZuduvgxc= github.com/yuin/goldmark v1.7.2 h1:NjGd7lO7zrUn/A7eKwn5PEOt4ONYGqpxSEeZuduvgxc=
github.com/yuin/goldmark v1.7.2/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E= github.com/yuin/goldmark v1.7.2/go.mod h1:uzxRWxtg69N339t3louHJ7+O03ezfj6PlliRlaOzY1E=

53
wrp.go
View File

@ -35,8 +35,6 @@ import (
"text/template" "text/template"
"time" "time"
h2m "github.com/JohannesKaufmann/html-to-markdown"
"github.com/JohannesKaufmann/html-to-markdown/plugin"
"github.com/MaxHalford/halfgone" "github.com/MaxHalford/halfgone"
"github.com/chromedp/cdproto/css" "github.com/chromedp/cdproto/css"
"github.com/chromedp/cdproto/emulation" "github.com/chromedp/cdproto/emulation"
@ -44,12 +42,6 @@ import (
"github.com/chromedp/cdproto/page" "github.com/chromedp/cdproto/page"
"github.com/chromedp/chromedp" "github.com/chromedp/chromedp"
"github.com/soniakeys/quant/median" "github.com/soniakeys/quant/median"
"github.com/yuin/goldmark"
"github.com/yuin/goldmark/ast"
"github.com/yuin/goldmark/extension"
"github.com/yuin/goldmark/parser"
"github.com/yuin/goldmark/text"
"github.com/yuin/goldmark/util"
) )
const version = "4.7.0" const version = "4.7.0"
@ -430,51 +422,6 @@ func asciify(s []byte) []byte {
return a return a
} }
type astTransformer struct{}
func (t *astTransformer) Transform(node *ast.Document, reader text.Reader, pc parser.Context) {
ast.Walk(node, func(n ast.Node, entering bool) (ast.WalkStatus, error) {
if link, ok := n.(*ast.Link); ok && entering {
link.Destination = append([]byte("?t=txt&url="), link.Destination...)
}
if _, ok := n.(*ast.Image); ok && entering {
// TODO: perhaps instead of deleting images convert them to links
// smaller images or ascii? https://github.com/TheZoraiz/ascii-image-converter
n.Parent().RemoveChildren(n)
}
return ast.WalkContinue, nil
})
}
func (rq *wrpReq) captureMarkdown() {
log.Printf("Processing Markdown conversion request for %v", rq.url)
// TODO: bug - DomainFromURL always prefixes with http:// instead of https
// this causes issues on some websites, fix or write a smarter DomainFromURL
c := h2m.NewConverter(h2m.DomainFromURL(rq.url), true, nil)
c.Use(plugin.GitHubFlavored())
md, err := c.ConvertURL(rq.url) // We could also get inner html from chromedp
if err != nil {
http.Error(rq.w, err.Error(), http.StatusInternalServerError)
return
}
log.Printf("Got %v bytes md from %v", len(md), rq.url)
gm := goldmark.New(
goldmark.WithExtensions(extension.GFM),
goldmark.WithParserOptions(parser.WithASTTransformers(util.Prioritized(&astTransformer{}, 100))),
)
var ht bytes.Buffer
err = gm.Convert([]byte(md), &ht)
if err != nil {
http.Error(rq.w, err.Error(), http.StatusInternalServerError)
return
}
log.Printf("Rendered %v bytes html for %v", len(ht.String()), rq.url)
rq.printHTML(printParams{
text: string(asciify([]byte(ht.String()))),
bgColor: "#FFFFFF",
})
}
// Process HTTP requests to WRP '/' url // Process HTTP requests to WRP '/' url
func pageServer(w http.ResponseWriter, r *http.Request) { func pageServer(w http.ResponseWriter, r *http.Request) {
log.Printf("%s Page Request for %s [%+v]\n", r.RemoteAddr, r.URL.Path, r.URL.RawQuery) log.Printf("%s Page Request for %s [%+v]\n", r.RemoteAddr, r.URL.Path, r.URL.RawQuery)