Resolve JSON-LD @id references, accept schema.org type IRIs, refuse empty durations
Review findings on the Recipe extractor:
- An image or publisher given as an {"@id": ...} reference now resolves to
the node with that @id at a script's top level, in a top-level array or
in an @graph, in any of the page's scripts. An image reference no node
has, or one naming two nodes, is ErrMalformedRecipe; an unresolved
publisher falls through to og:site_name and the host as before.
- @type matches the term or the absolute https:// or http://schema.org IRI,
as a string or in an array, for Recipe, HowToStep and HowToSection.
- A present but empty or blank prepTime, cookTime or totalTime is an invalid
ISO-8601 duration (ErrMalformedRecipe); an absent or null one is still
nil.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -277,6 +277,61 @@ func TestExtractShapes(t *testing.T) {
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "image and publisher resolved by @id within @graph",
|
||||
html: page(`<meta property="og:site_name" content="Not this">`, `{"@context":"https://schema.org","@graph":[
|
||||
{"@type":"Recipe","name":"Stew",
|
||||
"image":{"@id":"https://www.example.com/#primaryimage"},
|
||||
"publisher":{"@id":"https://www.example.com/#organization"}},
|
||||
{"@type":"ImageObject","@id":"https://www.example.com/#primaryimage","url":"/img/stew.jpg","width":1200,"height":800},
|
||||
{"@type":"Organization","@id":"https://www.example.com/#organization","name":"Our Kitchen"}]}`),
|
||||
check: func(t *testing.T, r Recipe) {
|
||||
if r.ImageURL != "https://www.example.com/img/stew.jpg" {
|
||||
t.Errorf("ImageURL = %q", r.ImageURL)
|
||||
}
|
||||
if r.SiteName != "Our Kitchen" {
|
||||
t.Errorf("SiteName = %q", r.SiteName)
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "image @id resolved from another script",
|
||||
html: page("", `{"@type":"Recipe","name":"Stew","image":[{"@id":"#img"}]}`,
|
||||
`{"@type":"ImageObject","@id":"#img","contentUrl":"stew.jpg"}`),
|
||||
check: func(t *testing.T, r Recipe) {
|
||||
if r.ImageURL != "https://www.example.com/recipes/stew/stew.jpg" {
|
||||
t.Errorf("ImageURL = %q", r.ImageURL)
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "absolute schema.org type IRIs",
|
||||
html: page("", `{"@type":"https://schema.org/Recipe","name":"Stew","recipeInstructions":[
|
||||
{"@type":"http://schema.org/HowToStep","text":"one"}]}`),
|
||||
check: func(t *testing.T, r Recipe) {
|
||||
if r.Title != "Stew" || strings.Join(r.Steps, "|") != "one" {
|
||||
t.Errorf("Title = %q, Steps = %q", r.Title, r.Steps)
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "absolute type IRI in a type array",
|
||||
html: page("", `{"@type":["NewsArticle","http://schema.org/Recipe"],"name":"Stew"}`),
|
||||
check: func(t *testing.T, r Recipe) {
|
||||
if r.Title != "Stew" {
|
||||
t.Errorf("Title = %q", r.Title)
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "null duration is absent",
|
||||
html: page("", `{"@type":"Recipe","name":"Stew","prepTime":null,"cookTime":"PT10M"}`),
|
||||
check: func(t *testing.T, r Recipe) {
|
||||
if r.PrepMinutes != nil || r.TotalMinutes != nil || fmtMinutes(r.CookMinutes) != "10" {
|
||||
t.Errorf("prep %s, cook %s, total %s", fmtMinutes(r.PrepMinutes), fmtMinutes(r.CookMinutes), fmtMinutes(r.TotalMinutes))
|
||||
}
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "JSON-LD text inside comments and other scripts is ignored",
|
||||
html: []byte(`<html><head><!-- <script type="application/ld+json">{"@type":"Recipe","name":"Old"}</script> -->` +
|
||||
@@ -313,6 +368,12 @@ func TestExtractErrors(t *testing.T) {
|
||||
{"bad step type", page("", `{"@type":"Recipe","name":"A","recipeInstructions":[{"@type":"Thing"}]}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"step without text", page("", `{"@type":"Recipe","name":"A","recipeInstructions":[{"@type":"HowToStep","name":"x"}]}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"bad image width", page("", `{"@type":"Recipe","name":"A","image":{"url":"a.jpg","width":"wide"}}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"empty prepTime", page("", `{"@type":"Recipe","name":"A","prepTime":""}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"blank cookTime", page("", `{"@type":"Recipe","name":"A","cookTime":" "}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"empty totalTime", page("", `{"@type":"Recipe","name":"A","totalTime":""}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"image @id not on page", page("", `{"@type":"Recipe","name":"A","image":{"@id":"#missing"}}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"image @id on two nodes", page("", `{"@type":"Recipe","name":"A","image":{"@id":"#img"}}`,
|
||||
`{"@id":"#img","url":"a.jpg"}`, `{"@id":"#img","url":"b.jpg"}`), "https://example.com/", ErrMalformedRecipe},
|
||||
{"non-text ingredient", page("", `{"@type":"Recipe","name":"A","recipeIngredient":[{"name":"salt"}]}`), "https://example.com/", ErrMalformedRecipe},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
|
||||
Reference in New Issue
Block a user