@Test
public void testNormalisesStructure() {
Document doc =
Jsoup.parse(
"<html><head><script>one</script><noscript><p>two</p></noscript></head><body><p>three</p></body><p>four</p></html>");
assertEquals(
"<html><head><script>one</script><noscript></noscript></head><body><p>two</p><p>three</p><p>four</p></body></html>",
TextUtil.stripNewlines(doc.html()));
}
@Test
public void testOutputEncoding() {
Document doc = Jsoup.parse("<p title=π>π & < > </p>");
// default is utf-8
assertEquals("<p title=\"π\">π & < > </p>", doc.body().html());
assertEquals("UTF-8", doc.outputSettings().charset().displayName());
doc.outputSettings().charset("ascii");
assertEquals(Entities.EscapeMode.base, doc.outputSettings().escapeMode());
assertEquals("<p title=\"π\">π & < > </p>", doc.body().html());
doc.outputSettings().escapeMode(Entities.EscapeMode.extended);
assertEquals("<p title=\"π\">π & < > </p>", doc.body().html());
}
@Test
public void testClone() {
Document doc = Jsoup.parse("<title>Hello</title> <p>One<p>Two");
Document clone = doc.clone();
assertEquals(
"<html><head><title>Hello</title> </head><body><p>One</p><p>Two</p></body></html>",
TextUtil.stripNewlines(clone.html()));
clone.title("Hello there");
clone.select("p").first().text("One more").attr("id", "1");
assertEquals(
"<html><head><title>Hello there</title> </head><body><p id=\"1\">One more</p><p>Two</p></body></html>",
TextUtil.stripNewlines(clone.html()));
assertEquals(
"<html><head><title>Hello</title> </head><body><p>One</p><p>Two</p></body></html>",
TextUtil.stripNewlines(doc.html()));
}
@Test
public void testClonesDeclarations() {
Document doc = Jsoup.parse("<!DOCTYPE html><html><head><title>Doctype test");
Document clone = doc.clone();
assertEquals(doc.html(), clone.html());
assertEquals(
"<!DOCTYPE html><html><head><title>Doctype test</title></head><body></body></html>",
TextUtil.stripNewlines(clone.html()));
}
@Test
public void testXhtmlReferences() {
Document doc = Jsoup.parse("< > & " ' ×");
doc.outputSettings().escapeMode(Entities.EscapeMode.xhtml);
assertEquals("< > & " ' ×", doc.body().html());
}
@Test
public void testTitles() {
Document noTitle = Jsoup.parse("<p>Hello</p>");
Document withTitle = Jsoup.parse("<title>First</title><title>Ignore</title><p>Hello</p>");
assertEquals("", noTitle.title());
noTitle.title("Hello");
assertEquals("Hello", noTitle.title());
assertEquals("Hello", noTitle.select("title").first().text());
assertEquals("First", withTitle.title());
withTitle.title("Hello");
assertEquals("Hello", withTitle.title());
assertEquals("Hello", withTitle.select("title").first().text());
Document normaliseTitle = Jsoup.parse("<title> Hello\nthere \n now \n");
assertEquals("Hello there now", normaliseTitle.title());
}
@Test
public void setTextPreservesDocumentStructure() {
Document doc = Jsoup.parse("<p>Hello</p>");
doc.text("Replaced");
assertEquals("Replaced", doc.text());
assertEquals("Replaced", doc.body().text());
assertEquals(1, doc.select("head").size());
}