Skip to content

Commit

Permalink
Change sanitization library to avoid extra / at the end of links. Fixes
Browse files Browse the repository at this point in the history
  • Loading branch information
piqoni committed Jun 5, 2024
1 parent 1773b91 commit f59c80d
Show file tree
Hide file tree
Showing 5 changed files with 27 additions and 15 deletions.
2 changes: 2 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
.vscode/
.DS_STORE
hn-text
bin/
build/
2 changes: 1 addition & 1 deletion go.mod
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,8 @@ require (
github.com/PuerkitoBio/goquery v1.9.2
github.com/gdamore/tcell/v2 v2.7.4
github.com/gelembjuk/articletext v0.0.0-20231013143648-bc7a97ba132a
github.com/k3a/html2text v1.2.1
github.com/rivo/tview v0.0.0-20240524063012-037df494fb76
jaytaylor.com/html2text v0.0.0-20230321000545-74c2419ad056
)

require (
Expand Down
14 changes: 2 additions & 12 deletions go.sum
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,8 @@ github.com/gdamore/tcell/v2 v2.7.4 h1:sg6/UnTM9jGpZU+oFYAsDahfchWAFW8Xx2yFinNSAY
github.com/gdamore/tcell/v2 v2.7.4/go.mod h1:dSXtXTSK0VsW1biw65DZLZ2NKr7j0qP/0J7ONmsraWg=
github.com/gelembjuk/articletext v0.0.0-20231013143648-bc7a97ba132a h1:qiro+IlH6Wj1YAEnLGYYGNuqEEQUyrDDWThnHL5Xgzo=
github.com/gelembjuk/articletext v0.0.0-20231013143648-bc7a97ba132a/go.mod h1:MEAzbitBZyN3cjFntWZJnfeForJTU+VNDLR69SdHesA=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
github.com/jaytaylor/html2text v0.0.0-20230321000545-74c2419ad056 h1:iCHtR9CQyktQ5+f3dMVZfwD2KWJUgm7M0gdL9NGr8KA=
github.com/jaytaylor/html2text v0.0.0-20230321000545-74c2419ad056/go.mod h1:CVKlgaMiht+LXvHG173ujK6JUhZXKb2u/BQtjPDIvyk=
github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
github.com/k3a/html2text v1.2.1 h1:nvnKgBvBR/myqrwfLuiqecUtaK1lB9hGziIJKatNFVY=
github.com/k3a/html2text v1.2.1/go.mod h1:ieEXykM67iT8lTvEWBh6fhpH4B23kB9OMKPdIBmgUqA=
github.com/lucasb-eyer/go-colorful v1.2.0 h1:1nnpGOrhyZZuNyfu1QjKiUICQ74+3FNCN69Aj6K7nkY=
github.com/lucasb-eyer/go-colorful v1.2.0/go.mod h1:R4dSotOR9KMtayYi1e77YzuveK+i7ruzyGqttikkLy0=
github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
Expand All @@ -31,18 +25,13 @@ github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJ
github.com/rivo/uniseg v0.4.3/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d h1:zE9ykElWQ6/NYmHa3jpm/yHnI4xSofP+UP6SpjHcSeM=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
github.com/smartystreets/goconvey v1.6.4 h1:fv0U8FUIMPNf1L9lnHLvLhgicrIVChEkdzIKYqbNC9s=
github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
github.com/ssor/bom v0.0.0-20170718123548-6386211fdfcf h1:pvbZ0lM0XWPBqUKqFU8cmavspvIl9nulOYwdy6IFRRo=
github.com/ssor/bom v0.0.0-20170718123548-6386211fdfcf/go.mod h1:RJID2RhlZKId02nZ62WenDCkgHFerpIOmW0iT7GKmXM=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
Expand Down Expand Up @@ -78,10 +67,11 @@ golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/neurosnap/sentences.v1 v1.0.7 h1:gpTUYnqthem4+o8kyTLiYIB05W+IvdQFYR29erfe8uU=
gopkg.in/neurosnap/sentences.v1 v1.0.7/go.mod h1:YlK+SN+fLQZj+kY3r8DkGDhDr91+S3JmTb5LSxFRQo0=
jaytaylor.com/html2text v0.0.0-20230321000545-74c2419ad056 h1:6YFJoB+0fUH6X3xU/G2tQqCYg+PkGtnZ5nMR5rpw72g=
jaytaylor.com/html2text v0.0.0-20230321000545-74c2419ad056/go.mod h1:OxvTsCwKosqQ1q7B+8FwXqg4rKZ/UG9dUW+g/VL2xH4=
5 changes: 3 additions & 2 deletions web.go
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ import (
"net/http"
"strings"

"github.com/k3a/html2text"
"jaytaylor.com/html2text"
)

func fetchWebpage(url string) (string, error) {
Expand All @@ -34,7 +34,8 @@ type Comment struct {
}

func sanitize(input string) string {
return html2text.HTML2Text(input)
sanitized, _ := html2text.FromString(input)
return sanitized
}

func safeRequest(url string) *http.Response {
Expand Down
19 changes: 19 additions & 0 deletions web_test.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
package main

import (
"testing"
)

func TestSanitize(t *testing.T) {
unsanitizedComment := "Uncrewed, yes. <a href=\"https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Boeing_Orbital_Flight_Test_2\" rel=\"nofollow\">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Boeing_Orbital_Flight_Test_2</a>"

expectedComment := "Uncrewed, yes. https://en.wikipedia.org/wiki/Boeing_Orbital_Flight_Test_2"

// call sanitize
sanitizedComment := sanitize(unsanitizedComment)

// check if sanitized comment is equal to expected comment
if sanitizedComment != expectedComment {
t.Errorf("Expected %q, got %q", expectedComment, sanitizedComment)
}
}

0 comments on commit f59c80d

Please sign in to comment.