scribe/spec/classes/markup_converter_spec.cr
Edward Loveall 7d0bc37efd
Fix markup errors caused by UTF-16/8 differences
Medium uses UTF-16 character offsets (likely to make it easier to parse
in JavaScript) but Crystal uses UTF-8. Converting strings to UTF-16 to
do offset calculation then back to UFT-8 fixes some markup bugs.

---

Medium calculates markup offsets using UTF-16 encoding. Some characters
like Emoji are count as multiple bytes which affects those offsets. For
example in UTF-16 💸 is worth two bytes, but Crystal strings only count
it as one. This is a problem for markup generation because it can
offset the markup and even cause out-of-range errors.

Take the following example:

💸💸!

Imagine that `!` was bold but the emoji isn't. For Crystal, this starts
at char index 2, end at char index 3. Medium's markup will say markup
goes from character 4 to 5. In a 3 character string like this, trying
to access character range 4...5 is an error because 5 is already out of
bounds.

My theory is that this is meant to be compatible with JavaScript's
string length calculations, as Medium is primarily a platform built for
the web:

```js
"a".length // 1
"💸".length // 2
"👩‍❤️‍💋‍👩".length // 11
```

To get these same numbers in Crystal strings must be converted to
UTF-16:

```crystal
"a".to_utf16.size # 1
"💸".to_utf16.size # 2
"👩‍❤️‍💋‍👩".to_utf16.size # 11
```

The MarkupConverter now converts text into UFT-16 byte arrays on
initialization. Once it's figured out the range of bytes needed for
each piece of markup, it converts it back into UTF-8 strings.
2022-01-30 11:53:22 -05:00

211 lines
5.2 KiB
Crystal

require "../spec_helper"
include Nodes
describe MarkupConverter do
describe "#convert" do
it "returns just text with no markups" do
markups = [] of PostResponse::Markup
result = MarkupConverter.convert(text: "Hello, world", markups: markups)
result.should eq([Text.new(content: "Hello, world")])
end
it "returns text with multiple markups" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": null,
"type": "STRONG",
"href": null,
"start": 0,
"end": 6,
"rel": null,
"anchorType": null
},
{
"title": null,
"type": "EM",
"href": null,
"start": 11,
"end": 21,
"rel": null,
"anchorType": null
}
]
JSON
result = MarkupConverter.convert(text: "strong and emphasized only", markups: markups)
result.should eq([
Strong.new(children: [Text.new(content: "strong")] of Child),
Text.new(content: " and "),
Emphasis.new(children: [Text.new(content: "emphasized")] of Child),
Text.new(content: " only"),
])
end
it "returns text with a code markup" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": null,
"type": "CODE",
"href": null,
"start": 7,
"end": 11,
"rel": null,
"anchorType": null
}
]
JSON
result = MarkupConverter.convert(text: "inline code", markups: markups)
result.should eq([
Text.new(content: "inline "),
Code.new(children: [Text.new(content: "code")] of Child),
])
end
it "renders an A-LINK markup" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": "",
"type": "A",
"href": "https://example.com",
"start": 7,
"end": 11,
"rel": "",
"anchorType": "LINK"
}
]
JSON
result = MarkupConverter.convert(text: "I am a Link", markups: markups)
result.should eq([
Text.new("I am a "),
Anchor.new(children: [Text.new("Link")] of Child, href: "https://example.com"),
])
end
it "renders an A-USER markup" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": null,
"type": "A",
"href": null,
"userId": "abc123",
"start": 3,
"end": 10,
"rel": null,
"anchorType": "USER"
}
]
JSON
result = MarkupConverter.convert(text: "Hi Dr Nick!", markups: markups)
result.should eq([
Text.new("Hi "),
UserAnchor.new(children: [Text.new("Dr Nick")] of Child, user_id: "abc123"),
Text.new("!"),
])
end
it "renders overlapping markups" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": null,
"type": "STRONG",
"href": null,
"userId": null,
"start": 7,
"end": 15,
"rel": null,
"anchorType": null
},
{
"title": null,
"type": "EM",
"href": null,
"userId": null,
"start": 0,
"end": 10,
"rel": null,
"anchorType": null
}
]
JSON
result = MarkupConverter.convert(text: "Italic and bold", markups: markups)
result.should eq([
Emphasis.new(children: [Text.new("Italic ")] of Child),
Emphasis.new(children: [
Strong.new(children: [Text.new("and")] of Child),
] of Child),
Strong.new(children: [Text.new(" bold")] of Child),
])
end
it "handles offsets from unicode text" do
markup = PostResponse::Markup.new(
type: PostResponse::MarkupType::STRONG,
start: 5,
end: 6
)
result = MarkupConverter.convert(text: "💸💸 <", markups: [markup])
result.should eq([
Text.new("💸💸 "),
Strong.new(children: [Text.new("<")] of Child),
])
end
end
describe "#wrap_in_markups" do
it "returns text wrapped in multiple markups" do
markups = Array(PostResponse::Markup).from_json <<-JSON
[
{
"title": null,
"type": "STRONG",
"href": null,
"start": 0,
"end": 17,
"rel": null,
"anchorType": null
},
{
"title": null,
"type": "A",
"href": null,
"userId": "abc123",
"start": 13,
"end": 17,
"rel": null,
"anchorType": "USER"
}
]
JSON
converter = MarkupConverter.new(text: "it's ya boi, jack", markups: markups)
result = converter.wrap_in_markups("jack", markups)
result.should eq([
UserAnchor.new(children: [
Strong.new([
Text.new("jack"),
] of Child),
] of Child, user_id: "abc123"),
])
end
end
end