[bugfix] html escape special characters in text instead of totally removing them (#719)

* remove minify dependency

* tidy up some tests

* remove pre + postformat funcs

* rework sanitization + formatting

* update tests

* add some more markdown tests
This commit is contained in:
tobi
2022-07-19 15:21:17 +02:00
committed by GitHub
parent 098dbe6ff4
commit c84384e660
51 changed files with 129 additions and 7419 deletions

View File

@ -71,16 +71,16 @@ type LinkTestSuite struct {
func (suite *LinkTestSuite) TestParseSimple() {
f := suite.formatter.FromPlain(context.Background(), simple, nil, nil)
assert.Equal(suite.T(), simpleExpected, f)
suite.Equal(simpleExpected, f)
}
func (suite *LinkTestSuite) TestParseURLsFromText1() {
urls := text.FindLinks(text1)
assert.Equal(suite.T(), "https://example.org/link/to/something#fragment", urls[0].String())
assert.Equal(suite.T(), "http://test.example.org?q=bahhhhhhhhhhhh", urls[1].String())
assert.Equal(suite.T(), "https://another.link.example.org/with/a/pretty/long/path/at/the/end/of/it", urls[2].String())
assert.Equal(suite.T(), "https://example.orghttps://google.com", urls[3].String())
suite.Equal("https://example.org/link/to/something#fragment", urls[0].String())
suite.Equal("http://test.example.org?q=bahhhhhhhhhhhh", urls[1].String())
suite.Equal("https://another.link.example.org/with/a/pretty/long/path/at/the/end/of/it", urls[2].String())
suite.Equal("https://example.orghttps://google.com", urls[3].String())
}
func (suite *LinkTestSuite) TestParseURLsFromText2() {
@ -99,7 +99,7 @@ func (suite *LinkTestSuite) TestParseURLsFromText3() {
func (suite *LinkTestSuite) TestReplaceLinksFromText1() {
replaced := suite.formatter.ReplaceLinks(context.Background(), text1)
assert.Equal(suite.T(), `
suite.Equal(`
This is a text with some links in it. Here's link number one: <a href="https://example.org/link/to/something#fragment" rel="noopener">example.org/link/to/something#fragment</a>
Here's link number two: <a href="http://test.example.org?q=bahhhhhhhhhhhh" rel="noopener">test.example.org?q=bahhhhhhhhhhhh</a>
@ -114,7 +114,7 @@ really.cool.website <-- this one shouldn't be parsed as a link because it doesn'
func (suite *LinkTestSuite) TestReplaceLinksFromText2() {
replaced := suite.formatter.ReplaceLinks(context.Background(), text2)
assert.Equal(suite.T(), `
suite.Equal(`
this is one link: <a href="https://example.org" rel="noopener">example.org</a>
this is the same link again: <a href="https://example.org" rel="noopener">example.org</a>
@ -126,14 +126,14 @@ these should be deduplicated
func (suite *LinkTestSuite) TestReplaceLinksFromText3() {
// we know mailto links won't be replaced with hrefs -- we only accept https and http
replaced := suite.formatter.ReplaceLinks(context.Background(), text3)
assert.Equal(suite.T(), `
suite.Equal(`
here's a mailto link: mailto:whatever@test.org
`, replaced)
}
func (suite *LinkTestSuite) TestReplaceLinksFromText4() {
replaced := suite.formatter.ReplaceLinks(context.Background(), text4)
assert.Equal(suite.T(), `
suite.Equal(`
two similar links:
<a href="https://example.org" rel="noopener">example.org</a>
@ -145,7 +145,7 @@ two similar links:
func (suite *LinkTestSuite) TestReplaceLinksFromText5() {
// we know this one doesn't work properly, which is why html should always be sanitized before being passed into the ReplaceLinks function
replaced := suite.formatter.ReplaceLinks(context.Background(), text5)
assert.Equal(suite.T(), `
suite.Equal(`
what happens when we already have a link within an href?
<a href="<a href="https://example.org" rel="noopener">example.org</a>"><a href="https://example.org" rel="noopener">example.org</a></a>