package org.jsoup.nodes;
import org.jsoup.Jsoup;
import org.jsoup.TextUtil;
import org.jsoup.integration.ParseTest;
import org.jsoup.nodes.Document.OutputSettings;
import org.jsoup.nodes.Document.OutputSettings.Syntax;
import org.jsoup.parser.ParseSettings;
import org.jsoup.parser.Parser;
import org.jsoup.select.Elements;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import java.io.*;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.util.List;
import static org.junit.jupiter.api.Assertions.*;
/**
Tests for Document.
@author Jonathan Hedley, jonathan@hedley.net */
public class DocumentTest {
private static final String charsetUtf8 = "UTF-8";
private static final String charsetIso8859 = "ISO-8859-1";
@Test public void setTextPreservesDocumentStructure() {
Document doc = Jsoup.parse("Hello
");
doc.text("Replaced");
assertEquals("Replaced", doc.text());
assertEquals("Replaced", doc.body().text());
assertEquals(1, doc.select("head").size());
}
@Test public void testTitles() {
Document noTitle = Jsoup.parse("Hello
");
Document withTitle = Jsoup.parse("FirstIgnoreHello
");
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(" Hello\nthere \n now \n");
assertEquals("Hello there now", normaliseTitle.title());
}
@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().name());
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 testXhtmlReferences() {
Document doc = Jsoup.parse("< > & " ' ×");
doc.outputSettings().escapeMode(Entities.EscapeMode.xhtml);
assertEquals("< > & \" ' ×", doc.body().html());
}
@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><p>two</noscript></head><body><p>three</p><p>four</p></body></html>", TextUtil.stripNewlines(doc.html()));
}
@Test public void accessorsWillNormalizeStructure() {
Document doc = new Document("");
assertEquals("", doc.html());
Element body = doc.body();
assertEquals("body", body.tagName());
Element head = doc.head();
assertEquals("head", head.tagName());
assertEquals("<html><head></head><body></body></html>", TextUtil.stripNewlines(doc.html()));
}
@Test public void accessorsAreCaseInsensitive() {
Parser parser = Parser.htmlParser().settings(ParseSettings.preserveCase);
Document doc = parser.parseInput("<!DOCTYPE html><HTML><HEAD><TITLE>SHOUTYHELLO