diff --git a/docs/formats/HTML.md b/docs/formats/HTML.md index ca11ab13..bbbbb14f 100644 --- a/docs/formats/HTML.md +++ b/docs/formats/HTML.md @@ -342,18 +342,18 @@ The element names are case-sensitive when using the XML parser. ###### Input ```HTML - - - Hello world! - - -

Hello world

- - + + + Hallo world + + + + + ``` -https://sparql-anything.cc/examples/simple.html +https://sparql-anything.cc/examples/simple.xml ###### Query @@ -363,7 +363,7 @@ CONSTRUCT ?s ?p ?o . } WHERE - { SERVICE + { SERVICE { ?s ?p ?o } } @@ -386,13 +386,18 @@ WHERE @prefix xsd: . @prefix xyz: . -[ rdf:type , fx:root ; - rdf:_1 [ rdf:type ; - rdf:_1 "Hallo world" - ] ; - rdf:_2 [ rdf:type ; - "0.1" - ] +[ rdf:type , fx:root ; + rdf:_1 [ rdf:type ; + rdf:_1 "Hallo world" ; + whatwg:innerHTML "Hallo world" ; + whatwg:innerText "Hallo world" + ] ; + rdf:_2 [ rdf:type ; + "0.1" + ] ; + xhtml:xmlns:xx "http://www.example.org" ; + whatwg:innerHTML "\n\tHallo world\n\t\n" ; + whatwg:innerText "Hallo world" ] . ``` diff --git a/docs/formats/Metadata.md b/docs/formats/Metadata.md index 3786575a..91237edb 100644 --- a/docs/formats/Metadata.md +++ b/docs/formats/Metadata.md @@ -122,7 +122,7 @@ WHERE "f/7.1" ; - "Fri Feb 23 15:47:25 +00:00 2024" ; + "Fri Feb 23 15:53:44 +00:00 2024" ; "Canon_40D.jpg" ; diff --git a/formats/HTML.md b/formats/HTML.md index ca11ab13..bbbbb14f 100644 --- a/formats/HTML.md +++ b/formats/HTML.md @@ -342,18 +342,18 @@ The element names are case-sensitive when using the XML parser. ###### Input ```HTML - - - Hello world! - - -

Hello world

- - + + + Hallo world + + + + + ``` -https://sparql-anything.cc/examples/simple.html +https://sparql-anything.cc/examples/simple.xml ###### Query @@ -363,7 +363,7 @@ CONSTRUCT ?s ?p ?o . } WHERE - { SERVICE + { SERVICE { ?s ?p ?o } } @@ -386,13 +386,18 @@ WHERE @prefix xsd: . @prefix xyz: . -[ rdf:type , fx:root ; - rdf:_1 [ rdf:type ; - rdf:_1 "Hallo world" - ] ; - rdf:_2 [ rdf:type ; - "0.1" - ] +[ rdf:type , fx:root ; + rdf:_1 [ rdf:type ; + rdf:_1 "Hallo world" ; + whatwg:innerHTML "Hallo world" ; + whatwg:innerText "Hallo world" + ] ; + rdf:_2 [ rdf:type ; + "0.1" + ] ; + xhtml:xmlns:xx "http://www.example.org" ; + whatwg:innerHTML "\n\tHallo world\n\t\n" ; + whatwg:innerText "Hallo world" ] . ``` diff --git a/formats/Metadata.md b/formats/Metadata.md index 3786575a..91237edb 100644 --- a/formats/Metadata.md +++ b/formats/Metadata.md @@ -122,7 +122,7 @@ WHERE "f/7.1" ; - "Fri Feb 23 15:47:25 +00:00 2024" ; + "Fri Feb 23 15:53:44 +00:00 2024" ; "Canon_40D.jpg" ; diff --git a/sparql-anything-html/src/main/java/io/github/sparqlanything/html/HTMLTriplifier.java b/sparql-anything-html/src/main/java/io/github/sparqlanything/html/HTMLTriplifier.java index 35ff5f52..623fabe5 100644 --- a/sparql-anything-html/src/main/java/io/github/sparqlanything/html/HTMLTriplifier.java +++ b/sparql-anything-html/src/main/java/io/github/sparqlanything/html/HTMLTriplifier.java @@ -66,7 +66,7 @@ public class HTMLTriplifier implements Triplifier { @Option(description = "It tells the triplifier to use the specified browser to navigate to the page to obtain HTML. By default a browser is not used. The use of a browser has some dependencies -- see [BROWSER](https://github.com/SPARQL-Anything/sparql.anything/blob/v1.0-DEV/BROWSER.md) and [justin2004's blogpost](https://github.com/justin2004/weblog/tree/master/scraping_with_sparql).", validValues = "chromium|webkit|firefox") public static final IRIArgument PROPERTY_BROWSER = new IRIArgument("html.browser"); - @Example(resource = "https://sparql-anything.cc/examples/simple.html", description = "The element names are case-sensitive when using the XML parser.", query = "CONSTRUCT {?s ?p ?o} WHERE { SERVICE { ?s ?p ?o } }") + @Example(resource = "https://sparql-anything.cc/examples/simple.xml", description = "The element names are case-sensitive when using the XML parser.", query = "CONSTRUCT {?s ?p ?o} WHERE { SERVICE { ?s ?p ?o } }") @Option(description = "It tells the triplifier to use the specified JSoup parser (default: html).", validValues = "xml html") public static final IRIArgument PROPERTY_PARSER = new IRIArgument("html.parser", "html"); private enum ParamParser {