From c8d3e421391520af45d8e0f60a884fee139652a0 Mon Sep 17 00:00:00 2001 From: Harrison Healey Date: Tue, 24 Jul 2018 10:40:01 -0400 Subject: MM-11451 Added autolinking to Markdown parser (#9151) * MM-11451 Added autolinking to Markdown parser * Added missing headers * Added mailto and tel links --- utils/markdown/autolink_test.go | 617 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 617 insertions(+) create mode 100644 utils/markdown/autolink_test.go (limited to 'utils/markdown/autolink_test.go') diff --git a/utils/markdown/autolink_test.go b/utils/markdown/autolink_test.go new file mode 100644 index 000000000..d0ea53fa4 --- /dev/null +++ b/utils/markdown/autolink_test.go @@ -0,0 +1,617 @@ +// Copyright (c) 2017-present Mattermost, Inc. All Rights Reserved. +// See License.txt for license information. + +package markdown + +import ( + "testing" + + "github.com/stretchr/testify/assert" +) + +func TestParseURLAutolink(t *testing.T) { + testCases := []struct { + Description string + Input string + Position int + Expected string + }{ + { + Description: "no link", + Input: "This is an :emoji:", + Position: 11, + Expected: "", + }, + { + Description: "no link 2", + Input: "These are two things: apple and orange", + Position: 20, + Expected: "", + }, + { + Description: "link with http", + Input: "http://example.com and some text", + Position: 4, + Expected: "http://example.com", + }, + { + Description: "link with https", + Input: "https://example.com and some text", + Position: 5, + Expected: "https://example.com", + }, + { + Description: "link with ftp", + Input: "ftp://example.com and some text", + Position: 3, + Expected: "ftp://example.com", + }, + { + Description: "link with a path", + Input: "https://example.com/abcd and some text", + Position: 5, + Expected: "https://example.com/abcd", + }, + { + Description: "link with parameters", + Input: "ftp://example.com/abcd?foo=bar and some text", + Position: 3, + Expected: "ftp://example.com/abcd?foo=bar", + }, + { + Description: "link, not at start", + Input: "This is https://example.com and some text", + Position: 13, + Expected: "https://example.com", + }, + { + Description: "link with a path, not at start", + Input: "This is also http://www.example.com/abcd and some text", + Position: 17, + Expected: "http://www.example.com/abcd", + }, + { + Description: "link with parameters, not at start", + Input: "These are https://www.example.com/abcd?foo=bar and some text", + Position: 15, + Expected: "https://www.example.com/abcd?foo=bar", + }, + { + Description: "link with trailing characters", + Input: "This is ftp://www.example.com??", + Position: 11, + Expected: "ftp://www.example.com", + }, + { + Description: "multiple links", + Input: "This is https://example.com/abcd and ftp://www.example.com/1234", + Position: 13, + Expected: "https://example.com/abcd", + }, + { + Description: "second of multiple links", + Input: "This is https://example.com/abcd and ftp://www.example.com/1234", + Position: 40, + Expected: "ftp://www.example.com/1234", + }, + { + Description: "link with brackets", + Input: "Go to ftp://www.example.com/my/page_(disambiguation) and some text", + Position: 9, + Expected: "ftp://www.example.com/my/page_(disambiguation)", + }, + { + Description: "link in brackets", + Input: "(https://www.example.com/foo/bar)", + Position: 6, + Expected: "https://www.example.com/foo/bar", + }, + { + Description: "link in underscores", + Input: "_http://www.example.com_", + Position: 5, + Expected: "http://www.example.com", + }, + { + Description: "link in asterisks", + Input: "This is **ftp://example.com**", + Position: 13, + Expected: "ftp://example.com", + }, + { + Description: "link in strikethrough", + Input: "Those were ~~https://example.com~~", + Position: 18, + Expected: "https://example.com", + }, + { + Description: "link with angle brackets", + Input: "We use http://example.com", + Position: 14, + Expected: "http://example.com", + }, + } + + for _, testCase := range testCases { + t.Run(testCase.Description, func(t *testing.T) { + assert.Equal(t, testCase.Expected, parseURLAutolink(testCase.Input, testCase.Position)) + }) + } +} + +func TestParseWWWAutolink(t *testing.T) { + testCases := []struct { + Description string + Input string + Position int + Expected string + }{ + { + Description: "no link", + Input: "This is some text", + Position: 0, + Expected: "", + }, + { + Description: "link", + Input: "www.example.com and some text", + Position: 0, + Expected: "www.example.com", + }, + { + Description: "link with a path", + Input: "www.example.com/abcd and some text", + Position: 0, + Expected: "www.example.com/abcd", + }, + { + Description: "link with parameters", + Input: "www.example.com/abcd?foo=bar and some text", + Position: 0, + Expected: "www.example.com/abcd?foo=bar", + }, + { + Description: "link, not at start", + Input: "This is www.example.com and some text", + Position: 8, + Expected: "www.example.com", + }, + { + Description: "link with a path, not at start", + Input: "This is also www.example.com/abcd and some text", + Position: 13, + Expected: "www.example.com/abcd", + }, + { + Description: "link with parameters, not at start", + Input: "These are www.example.com/abcd?foo=bar and some text", + Position: 10, + Expected: "www.example.com/abcd?foo=bar", + }, + { + Description: "link with trailing characters", + Input: "This is www.example.com??", + Position: 8, + Expected: "www.example.com", + }, + { + Description: "link after current position", + Input: "This is some text and www.example.com", + Position: 0, + Expected: "", + }, + { + Description: "multiple links", + Input: "This is www.example.com/abcd and www.example.com/1234", + Position: 8, + Expected: "www.example.com/abcd", + }, + { + Description: "multiple links 2", + Input: "This is www.example.com/abcd and www.example.com/1234", + Position: 33, + Expected: "www.example.com/1234", + }, + { + Description: "link with brackets", + Input: "Go to www.example.com/my/page_(disambiguation) and some text", + Position: 6, + Expected: "www.example.com/my/page_(disambiguation)", + }, + { + Description: "link following other letters", + Input: "aaawww.example.com and some text", + Position: 3, + Expected: "", + }, + { + Description: "link in brackets", + Input: "(www.example.com)", + Position: 1, + Expected: "www.example.com", + }, + { + Description: "link in underscores", + Input: "_www.example.com_", + Position: 1, + Expected: "www.example.com", + }, + { + Description: "link in asterisks", + Input: "This is **www.example.com**", + Position: 10, + Expected: "www.example.com", + }, + { + Description: "link in strikethrough", + Input: "Those were ~~www.example.com~~", + Position: 13, + Expected: "www.example.com", + }, + { + Description: "using www1", + Input: "Our backup site is at www1.example.com/foo", + Position: 22, + Expected: "www1.example.com/foo", + }, + { + Description: "link with angle brackets", + Input: "We use www2.example.com", + Position: 10, + Expected: "www2.example.com", + }, + } + + for _, testCase := range testCases { + t.Run(testCase.Description, func(t *testing.T) { + assert.Equal(t, testCase.Expected, parseWWWAutolink(testCase.Input, testCase.Position)) + }) + } +} + +func TestTrimTrailingCharactersFromLink(t *testing.T) { + testCases := []struct { + Input string + Expected string + }{ + { + Input: "http://www.example.com", + Expected: "http://www.example.com", + }, + { + Input: "http://www.example.com/abcd", + Expected: "http://www.example.com/abcd", + }, + { + Input: "http://www.example.com/abcd/", + Expected: "http://www.example.com/abcd/", + }, + { + Input: "http://www.example.com/1234", + Expected: "http://www.example.com/1234", + }, + { + Input: "http://www.example.com/abcd?foo=bar", + Expected: "http://www.example.com/abcd?foo=bar", + }, + { + Input: "http://www.example.com/abcd#heading", + Expected: "http://www.example.com/abcd#heading", + }, + { + Input: "http://www.example.com.", + Expected: "http://www.example.com", + }, + { + Input: "http://www.example.com,", + Expected: "http://www.example.com", + }, + { + Input: "http://www.example.com?", + Expected: "http://www.example.com", + }, + { + Input: "http://www.example.com)", + Expected: "http://www.example.com", + }, + { + Input: "http://www.example.com", + Expected: "http://www.example.com", + }, + { + Input: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation)", + Expected: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation)", + }, + { + Input: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation", + Expected: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation", + }, + { + Input: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation))", + Expected: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation)", + }, + { + Input: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation)_(disambiguation)", + Expected: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation)_(disambiguation)", + }, + { + Input: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation_(disambiguation))", + Expected: "https://en.wikipedia.org/wiki/Dolphin_(disambiguation_(disambiguation))", + }, + { + Input: "http://www.example.com"", + Expected: "http://www.example.com", + }, + } + + for _, testCase := range testCases { + t.Run(testCase.Input, func(t *testing.T) { + assert.Equal(t, testCase.Expected, trimTrailingCharactersFromLink(testCase.Input)) + }) + } +} + +func TestAutolinking(t *testing.T) { + // These tests are adapted from https://github.com/mattermost/commonmark.js/test/mattermost.txt. + // It is missing tests for: + // 1. Links surrounded by emphasis (emphasis not implemented on the server) + // 2. IPv6 addresses (not implemented on the server or by GitHub) + // 3. Custom URL schemes (not implemented) + + for name, tc := range map[string]struct { + Markdown string + ExpectedHTML string + }{ + "valid-link-1": { + Markdown: `http://example.com`, + ExpectedHTML: `

http://example.com

`, + }, + "valid-link-2": { + Markdown: `https://example.com`, + ExpectedHTML: `

https://example.com

`, + }, + "valid-link-3": { + Markdown: `ftp://example.com`, + ExpectedHTML: `

ftp://example.com

`, + }, + // "valid-link-4": { + // Markdown: `ts3server://example.com?port=9001`, + // ExpectedHTML: `

ts3server://example.com?port=9001

`, + // }, + "valid-link-5": { + Markdown: `www.example.com`, + ExpectedHTML: `

www.example.com

`, + }, + "valid-link-6": { + Markdown: `www.example.com/index`, + ExpectedHTML: `

www.example.com/index

`, + }, + "valid-link-7": { + Markdown: `www.example.com/index.html`, + ExpectedHTML: `

www.example.com/index.html

`, + }, + "valid-link-8": { + Markdown: `http://example.com/index/sub`, + ExpectedHTML: `

http://example.com/index/sub

`, + }, + "valid-link-9": { + Markdown: `www1.example.com`, + ExpectedHTML: `

www1.example.com

`, + }, + "valid-link-10": { + Markdown: `https://en.wikipedia.org/wiki/URLs#Syntax`, + ExpectedHTML: `

https://en.wikipedia.org/wiki/URLs#Syntax

`, + }, + "valid-link-11": { + Markdown: `https://groups.google.com/forum/#!msg`, + ExpectedHTML: `

https://groups.google.com/forum/#!msg

`, + }, + "valid-link-12": { + Markdown: `www.example.com/index?params=1`, + ExpectedHTML: `

www.example.com/index?params=1

`, + }, + "valid-link-13": { + Markdown: `www.example.com/index?params=1&other=2`, + ExpectedHTML: `

www.example.com/index?params=1&other=2

`, + }, + "valid-link-14": { + Markdown: `www.example.com/index?params=1;other=2`, + ExpectedHTML: `

www.example.com/index?params=1;other=2

`, + }, + "valid-link-15": { + Markdown: `http://www.example.com/_/page`, + ExpectedHTML: `

http://www.example.com/_/page

`, + }, + "valid-link-16": { + Markdown: `https://en.wikipedia.org/wiki/🐬`, + ExpectedHTML: `

https://en.wikipedia.org/wiki/🐬

`, + }, + "valid-link-17": { + Markdown: `http://βœͺdf.ws/1234`, + ExpectedHTML: `

http://βœͺdf.ws/1234

`, + }, + "valid-link-18": { + Markdown: `https://groups.google.com/forum/#!msg`, + ExpectedHTML: `

https://groups.google.com/forum/#!msg

`, + }, + "valid-link-19": { + Markdown: `https://ΠΏΡ€ΠΈΠΌΠ΅Ρ€.срб/ΠΏΡ€ΠΈΠΌΠ΅Ρ€-26/`, + ExpectedHTML: `

https://ΠΏΡ€ΠΈΠΌΠ΅Ρ€.срб/ΠΏΡ€ΠΈΠΌΠ΅Ρ€-26/

`, + }, + "valid-link-20": { + Markdown: `mailto://test@example.com`, + ExpectedHTML: `

mailto://test@example.com

`, + }, + "valid-link-21": { + Markdown: `tel://555-123-4567`, + ExpectedHTML: `

tel://555-123-4567

`, + }, + + "ip-address-1": { + Markdown: `http://127.0.0.1`, + ExpectedHTML: `

http://127.0.0.1

`, + }, + "ip-address-2": { + Markdown: `http://192.168.1.1:4040`, + ExpectedHTML: `

http://192.168.1.1:4040

`, + }, + "ip-address-3": { + Markdown: `http://username:password@127.0.0.1`, + ExpectedHTML: `

http://username:password@127.0.0.1

`, + }, + "ip-address-4": { + Markdown: `http://username:password@[2001:0:5ef5:79fb:303a:62d5:3312:ff42]:80`, + ExpectedHTML: `

http://username:password@[2001:0:5ef5:79fb:303a:62d5:3312:ff42]:80

`, + }, + + "link-with-brackets-1": { + Markdown: `https://en.wikipedia.org/wiki/Rendering_(computer_graphics)`, + ExpectedHTML: `

https://en.wikipedia.org/wiki/Rendering_(computer_graphics)

`, + }, + "link-with-brackets-2": { + Markdown: `http://example.com/more_(than)_one_(parens)`, + ExpectedHTML: `

http://example.com/more_(than)_one_(parens)

`, + }, + "link-with-brackets-3": { + Markdown: `http://example.com/(something)?after=parens`, + ExpectedHTML: `

http://example.com/(something)?after=parens

`, + }, + "link-with-brackets-4": { + Markdown: `http://foo.com/unicode_(βœͺ)_in_parens`, + ExpectedHTML: `

http://foo.com/unicode_(βœͺ)_in_parens

`, + }, + + "inside-another-link-1": { + Markdown: `[www.example.com](https://example.com)`, + ExpectedHTML: `

www.example.com

`, + }, + "inside-another-link-2": { + Markdown: `[http://www.example.com](https://example.com)`, + ExpectedHTML: `

http://www.example.com

`, + }, + + "link-in-sentence-1": { + Markdown: `(http://example.com)`, + ExpectedHTML: `

(http://example.com)

`, + }, + "link-in-sentence-2": { + Markdown: `(see http://example.com)`, + ExpectedHTML: `

(see http://example.com)

`, + }, + "link-in-sentence-3": { + Markdown: `(http://example.com watch this)`, + ExpectedHTML: `

(http://example.com watch this)

`, + }, + "link-in-sentence-4": { + Markdown: `This is a sentence with a http://example.com in it.`, + ExpectedHTML: `

This is a sentence with a http://example.com in it.

`, + }, + "link-in-sentence-5": { + Markdown: `This is a sentence with a [link](http://example.com) in it.`, + ExpectedHTML: `

This is a sentence with a link in it.

`, + }, + "link-in-sentence-6": { + Markdown: `This is a sentence with a http://example.com/_/underscore in it.`, + ExpectedHTML: `

This is a sentence with a http://example.com/_/underscore in it.

`, + }, + "link-in-sentence-7": { + Markdown: `This is a sentence with a link (http://example.com) in it.`, + ExpectedHTML: `

This is a sentence with a link (http://example.com) in it.

`, + }, + "link-in-sentence-8": { + Markdown: `This is a sentence with a (https://en.wikipedia.org/wiki/Rendering_(computer_graphics)) in it.`, + ExpectedHTML: `

This is a sentence with a (https://en.wikipedia.org/wiki/Rendering_(computer_graphics)) in it.

`, + }, + "link-in-sentence-9": { + Markdown: `This is a sentence with a http://192.168.1.1:4040 in it.`, + ExpectedHTML: `

This is a sentence with a http://192.168.1.1:4040 in it.

`, + }, + "link-in-sentence-10": { + Markdown: `This is a link to http://example.com.`, + ExpectedHTML: `

This is a link to http://example.com.

`, + }, + "link-in-sentence-11": { + Markdown: `This is a link to http://example.com*`, + ExpectedHTML: `

This is a link to http://example.com*

`, + }, + "link-in-sentence-12": { + Markdown: `This is a link to http://example.com_`, + ExpectedHTML: `

This is a link to http://example.com_

`, + }, + "link-in-sentence-13": { + Markdown: `This is a link containing http://example.com/something?with,commas,in,url, but not at the end`, + ExpectedHTML: `

This is a link containing http://example.com/something?with,commas,in,url, but not at the end

`, + }, + "link-in-sentence-14": { + Markdown: `This is a question about a link http://example.com?`, + ExpectedHTML: `

This is a question about a link http://example.com?

`, + }, + + "plt-7250-link-with-trailing-periods-1": { + Markdown: `http://example.com.`, + ExpectedHTML: `

http://example.com.

`, + }, + "plt-7250-link-with-trailing-periods-2": { + Markdown: `http://example.com...`, + ExpectedHTML: `

http://example.com...

`, + }, + "plt-7250-link-with-trailing-periods-3": { + Markdown: `http://example.com/foo.`, + ExpectedHTML: `

http://example.com/foo.

`, + }, + "plt-7250-link-with-trailing-periods-4": { + Markdown: `http://example.com/foo...`, + ExpectedHTML: `

http://example.com/foo...

`, + }, + "plt-7250-link-with-trailing-periods-5": { + Markdown: `http://example.com/foo.bar`, + ExpectedHTML: `

http://example.com/foo.bar

`, + }, + "plt-7250-link-with-trailing-periods-6": { + Markdown: `http://example.com/foo...bar`, + ExpectedHTML: `

http://example.com/foo...bar

`, + }, + + "rn-319-www-link-as-part-of-word-1": { + Markdown: `testwww.example.com`, + ExpectedHTML: `

testwww.example.com

`, + }, + + "mm-10180-link-containing-period-followed-by-non-letter-1": { + Markdown: `https://example.com/123.+Pagetitle`, + ExpectedHTML: `

https://example.com/123.+Pagetitle

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-2": { + Markdown: `https://example.com/123.?Pagetitle`, + ExpectedHTML: `

https://example.com/123.?Pagetitle

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-3": { + Markdown: `https://example.com/123.-Pagetitle`, + ExpectedHTML: `

https://example.com/123.-Pagetitle

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-4": { + Markdown: `https://example.com/123._Pagetitle`, + ExpectedHTML: `

https://example.com/123._Pagetitle

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-5": { + Markdown: `https://example.com/123.+`, + ExpectedHTML: `

https://example.com/123.+

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-6": { + Markdown: `https://example.com/123.?`, + ExpectedHTML: `

https://example.com/123.?

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-7": { + Markdown: `https://example.com/123.-`, + ExpectedHTML: `

https://example.com/123.-

`, + }, + "mm-10180-link-containing-period-followed-by-non-letter-8": { + Markdown: `https://example.com/123._`, + ExpectedHTML: `

https://example.com/123._

`, + }, + } { + t.Run(name, func(t *testing.T) { + assert.Equal(t, tc.ExpectedHTML, RenderHTML(tc.Markdown)) + }) + } +} -- cgit v1.2.3-1-g7c22