Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

HtmlState: restore FormattedMode if still in pre after char ref #1414

Merged
merged 4 commits into from
Nov 23, 2021
Merged

HtmlState: restore FormattedMode if still in pre after char ref #1414

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
906ced9
HtmlState: restore FormattedMode if still in pre
stroborobo Nov 19, 2021
978a362
HtmlState: restore code element treated as formatted, fixup test
stroborobo Nov 20, 2021
3ecc424
HtmlState: move from FormattedMode to HasFormattedParent bool
stroborobo Nov 23, 2021
0ac87b2
HtmlState: fixup test to expect Environment.NewLine
stroborobo Nov 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions src/Html/HtmlParser.fs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,14 +334,11 @@ module internal HtmlParser =
x.Tokens := result :: !x.Tokens

member x.IsFormattedTag
with get() =
match x.CurrentTagName() with
| "pre" | "code" -> true
| _ -> false
with get() = x.CurrentTagName().ToLower() = "pre"

member x.IsScriptTag
with get() =
match x.CurrentTagName().Trim().ToLower() with
match x.CurrentTagName().ToLower() with
| "script" | "style" -> true
| _ -> false

Expand Down Expand Up @@ -386,7 +383,9 @@ module internal HtmlParser =
| DocTypeMode -> DocType content
| CDATAMode -> CData (content.Replace("<![CDATA[", "").Replace("]]>", ""))
x.Content := CharList.Empty
x.InsertionMode := DefaultMode
x.InsertionMode :=
if x.IsFormattedTag then FormattedMode
else DefaultMode
match result with
| Text t when String.IsNullOrEmpty(t) -> ()
| _ -> x.Tokens := result :: !x.Tokens
Expand Down
17 changes: 9 additions & 8 deletions tests/FSharp.Data.Tests/HtmlParser.fs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -805,15 +805,16 @@ let ``Can parse pre blocks``() =
result |> should equal [ "\r\n This code should be indented and\r\n have line feeds in it" ]

[<Test>]
let ``Can parse code blocks``() =
let html = "<code>\r\n let f a b = a * b\r\n f 5 6 |> should equal 30</code>"
let ``Can parse pre blocks with char refs``() =
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This removes the code blocks test - could you add that test back as well?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sure, it would test for invalid behavior though since code is an inline element. Should I restore the behavior for code anyways and open another issue for elements nested in pre?

let html = "<pre>let hello who =\r\n &quot;hello&quot; + who</pre>"

let result =
(HtmlDocument.Parse html)
|> HtmlDocument.descendantsNamed true [ "code" ]
|> Seq.map (HtmlNode.innerText)
|> Seq.toList
result |> should equal [ "\r\n let f a b = a * b\r\n f 5 6 |> should equal 30" ]
|> HtmlDocument.descendantsNamed true [ "pre" ]
|> Seq.head
|> HtmlNode.innerText
let expected = "let hello who =\r\n \"hello\" + who"
result |> should equal expected

[<Test>]
let ``Can parse national rail mobile site correctly``() =
Expand Down Expand Up @@ -911,9 +912,9 @@ let ``Parsing non-html content doesn't cause an infinite loop - Github-1264``()
[<Test; Timeout(2000)>]
let ``Can handle incomplete tags at end of file without creating an infinite loop``() =
let result = HtmlDocument.Parse """<html><head></head></html"""
let expected =
let expected =
HtmlDocument.New
[ HtmlNode.NewElement
("html",
[ HtmlNode.NewElement("head")])]
result |> should equal expected
result |> should equal expected