Java 类org.jsoup.TextUtil 实例源码

项目：common 文件：ElementTest.java

@Test public void testClone() {
    Document doc = Jsoup.parse("<div><p>One<p><span>Two</div>");

    Element p = doc.select("p").get(1);
    Element clone = p.clone();

    assertNull(clone.parent()); // should be orphaned
    assertEquals(0, clone.siblingIndex);
    assertEquals(1, p.siblingIndex);
    assertNotNull(p.parent());

    clone.append("<span>Three");
    assertEquals("<p><span>Two</span><span>Three</span></p>", TextUtil.stripNewlines(clone.outerHtml()));
    assertEquals("<div><p>One</p><p><span>Two</span></p></div>", TextUtil.stripNewlines(doc.body().html())); // not modified

    doc.body().appendChild(clone); // adopt
    assertNotNull(clone.parent());
    assertEquals("<div><p>One</p><p><span>Two</span></p></div><p><span>Two</span><span>Three</span></p>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Ignore
@Test
public void testSupplyParserToConnection() throws IOException {
    String xmlUrl = "http://direct.infohound.net/tools/jsoup-xml-test.xml";

    // parse with both xml and html parser, ensure different
    Document xmlDoc = Jsoup.connect(xmlUrl).parser(Parser.xmlParser()).get();
    Document htmlDoc = Jsoup.connect(xmlUrl).parser(Parser.htmlParser()).get();
    Document autoXmlDoc = Jsoup.connect(xmlUrl).get(); // check connection auto detects xml, uses xml parser

    assertEquals("<doc><val>One<val>Two</val>Three</val></doc>",
            TextUtil.stripNewlines(xmlDoc.html()));
    assertFalse(htmlDoc.equals(xmlDoc));
    assertEquals(xmlDoc, autoXmlDoc);
    assertEquals(1, htmlDoc.select("head").size()); // html parser normalises
    assertEquals(0, xmlDoc.select("head").size()); // xml parser does not
    assertEquals(0, autoXmlDoc.select("head").size()); // xml parser does not
}

项目：common 文件：TextNodeTest.java

@Test public void testTextBean() {
    Document doc = Jsoup.parse("<p>One <span>two &amp;</span> three &amp;</p>");
    Element p = doc.select("p").first();

    Element span = doc.select("span").first();
    assertEquals("two &", span.text());
    TextNode spanText = (TextNode) span.childNode(0);
    assertEquals("two &", spanText.text());

    TextNode tn = (TextNode) p.childNode(2);
    assertEquals(" three &", tn.text());

    tn.text(" POW!");
    assertEquals("One <span>two &amp;</span> POW!", TextUtil.stripNewlines(p.html()));

    tn.attr("text", "kablam &");
    assertEquals("kablam &", tn.text());
    assertEquals("One <span>two &amp;</span>kablam &amp;", TextUtil.stripNewlines(p.html()));
}

项目：astor 文件：ElementTest.java

@Test
public void testRemoveAfterIndex() {
     Document doc2 = Jsoup.parse(
                "<html><body><div><p>before1</p><p>before2</p><p>XXX</p><p>after1</p><p>after2</p></div></body></html>",
                "");
    Element body = doc2.select("body").first();
    Elements elems = body.select("p:matchesOwn(XXX)");
    Element xElem = elems.first();
    Elements afterX = xElem.parent().getElementsByIndexGreaterThan(xElem.elementSiblingIndex());

    for(Element p : afterX) {
        p.remove();
    }

    assertEquals("<body><div><p>before1</p><p>before2</p><p>XXX</p></div></body>", TextUtil.stripNewlines(body.outerHtml()));
}

项目：astor 文件：TextNodeTest.java

@Test public void testTextBean() {
    Document doc = Jsoup.parse("<p>One <span>two &amp;</span> three &amp;</p>");
    Element p = doc.select("p").first();

    Element span = doc.select("span").first();
    assertEquals("two &", span.text());
    TextNode spanText = (TextNode) span.childNode(0);
    assertEquals("two &", spanText.text());

    TextNode tn = (TextNode) p.childNode(2);
    assertEquals(" three &", tn.text());

    tn.text(" POW!");
    assertEquals("One <span>two &amp;</span> POW!", TextUtil.stripNewlines(p.html()));

    tn.attr("text", "kablam &");
    assertEquals("kablam &", tn.text());
    assertEquals("One <span>two &amp;</span>kablam &amp;", TextUtil.stripNewlines(p.html()));
}

项目：astor 文件：ElementTest.java

@Test public void testClone() {
    Document doc = Jsoup.parse("<div><p>One<p><span>Two</div>");

    Element p = doc.select("p").get(1);
    Element clone = p.clone();

    assertNull(clone.parent()); // should be orphaned
    assertEquals(0, clone.siblingIndex);
    assertEquals(1, p.siblingIndex);
    assertNotNull(p.parent());

    clone.append("<span>Three");
    assertEquals("<p><span>Two</span><span>Three</span></p>", TextUtil.stripNewlines(clone.outerHtml()));
    assertEquals("<div><p>One</p><p><span>Two</span></p></div>", TextUtil.stripNewlines(doc.body().html())); // not modified

    doc.body().appendChild(clone); // adopt
    assertNotNull(clone.parent());
    assertEquals("<div><p>One</p><p><span>Two</span></p></div><p><span>Two</span><span>Three</span></p>", TextUtil.stripNewlines(doc.body().html()));
}

项目：astor 文件：ElementTest.java

@Test
public void testRemoveBeforeIndex() {
    Document doc = Jsoup.parse(
            "<html><body><div><p>before1</p><p>before2</p><p>XXX</p><p>after1</p><p>after2</p></div></body></html>",
            "");
    Element body = doc.select("body").first();
    Elements elems = body.select("p:matchesOwn(XXX)");
    Element xElem = elems.first();
    Elements beforeX = xElem.parent().getElementsByIndexLessThan(xElem.elementSiblingIndex());

    for(Element p : beforeX) {
        p.remove();
    }

    assertEquals("<body><div><p>XXX</p><p>after1</p><p>after2</p></div></body>", TextUtil.stripNewlines(body.outerHtml()));
}

项目：astor 文件：XmlTreeBuilderTest.java

@Ignore
@Test
public void testSupplyParserToConnection() throws IOException {
    String xmlUrl = "http://direct.infohound.net/tools/jsoup-xml-test.xml";

    // parse with both xml and html parser, ensure different
    Document xmlDoc = Jsoup.connect(xmlUrl).parser(Parser.xmlParser()).get();
    Document htmlDoc = Jsoup.connect(xmlUrl).parser(Parser.htmlParser()).get();
    Document autoXmlDoc = Jsoup.connect(xmlUrl).get(); // check connection auto detects xml, uses xml parser

    assertEquals("<doc><val>One<val>Two</val>Three</val></doc>",
            TextUtil.stripNewlines(xmlDoc.html()));
    assertFalse(htmlDoc.equals(xmlDoc));
    assertEquals(xmlDoc, autoXmlDoc);
    assertEquals(1, htmlDoc.select("head").size()); // html parser normalises
    assertEquals(0, xmlDoc.select("head").size()); // xml parser does not
    assertEquals(0, autoXmlDoc.select("head").size()); // xml parser does not
}

项目：common 文件：CleanerTest.java

@Test public void basicBehaviourTest() {
    String h = "<div><p><a href='javascript:sendAllMoney()'>Dodgy</a> <A HREF='HTTP://nice.com'>Nice</a></p><blockquote>Hello</blockquote>";
    String cleanHtml = Jsoup.clean(h, Whitelist.basic());

    assertEquals("<p><a rel=\"nofollow\">Dodgy</a> <a href=\"http://nice.com\" rel=\"nofollow\">Nice</a></p><blockquote>Hello</blockquote>",
            TextUtil.stripNewlines(cleanHtml));
}

项目：common 文件：CleanerTest.java

@Test public void testRemoveEnforcedAttributes() {
    String h = "<div><p><A HREF='HTTP://nice.com'>Nice</a></p><blockquote>Hello</blockquote>";
    String cleanHtml = Jsoup.clean(h, Whitelist.basic().removeEnforcedAttribute("a", "rel"));

    assertEquals("<p><a href=\"http://nice.com\">Nice</a></p><blockquote>Hello</blockquote>",
            TextUtil.stripNewlines(cleanHtml));
}

项目：common 文件：HtmlParserTest.java

@Test public void discardsNakedTds() {
    // jsoup used to make this into an implicit table; but browsers make it into a text run
    String h = "<td>Hello<td><p>There<p>now";
    Document doc = Jsoup.parse(h);
    assertEquals("Hello<p>There</p><p>now</p>", TextUtil.stripNewlines(doc.body().html()));
    // <tbody> is introduced if no implicitly creating table, but allows tr to be directly under table
}

项目：common 文件：HtmlParserTest.java

@Test public void handlesBlocksInDefinitions() {
    // per the spec, dt and dd are inline, but in practise are block
    String h = "<dl><dt><div id=1>Term</div></dt><dd><div id=2>Def</div></dd></dl>";
    Document doc = Jsoup.parse(h);
    assertEquals("dt", doc.select("#1").first().parent().tagName());
    assertEquals("dd", doc.select("#2").first().parent().tagName());
    assertEquals("<dl><dt><div id=\"1\">Term</div></dt><dd><div id=\"2\">Def</div></dd></dl>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：HtmlParserTest.java

@Test public void handlesFrames() {
    String h = "<html><head><script></script><noscript></noscript></head><frameset><frame src=foo></frame><frame src=foo></frameset></html>";
    Document doc = Jsoup.parse(h);
    assertEquals("<html><head><script></script><noscript></noscript></head><frameset><frame src=\"foo\"><frame src=\"foo\"></frameset></html>",
            TextUtil.stripNewlines(doc.html()));
    // no body auto vivification
}

项目：common 文件：HtmlParserTest.java

@Test public void handlesUnexpectedMarkupInTables() {
    // whatwg - tests markers in active formatting (if they didn't work, would get in in table)
    // also tests foster parenting
    String h = "<table><b><tr><td>aaa</td></tr>bbb</table>ccc";
    Document doc = Jsoup.parse(h);
    assertEquals("<b></b><b>bbb</b><table><tbody><tr><td>aaa</td></tr></tbody></table><b>ccc</b>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：HtmlParserTest.java

@Test public void associatedFormControlsWithDisjointForms() {
    // form gets closed, isn't parent of controls
    String html = "<table><tr><form><input type=hidden id=1><td><input type=text id=2></td><tr></table>";
    Document doc = Jsoup.parse(html);
    Element el = doc.select("form").first();

    assertTrue("Is form element", el instanceof FormElement);
    FormElement form = (FormElement) el;
    Elements controls = form.elements();
    assertEquals(2, controls.size());
    assertEquals("1", controls.get(0).id());
    assertEquals("2", controls.get(1).id());

    assertEquals("<table><tbody><tr><form></form><input type=\"hidden\" id=\"1\"><td><input type=\"text\" id=\"2\"></td></tr><tr></tr></tbody></table>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testSimpleXmlParse() {
    String xml = "<doc id=2 href='/bar'>Foo <br /><link>One</link><link>Two</link></doc>";
    XmlTreeBuilder tb = new XmlTreeBuilder();
    Document doc = tb.parse(xml, "http://foo.com/");
    assertEquals("<doc id=\"2\" href=\"/bar\">Foo <br /><link>One</link><link>Two</link></doc>",
            TextUtil.stripNewlines(doc.html()));
    assertEquals(doc.getElementById("2").absUrl("href"), "http://foo.com/bar");
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testPopToClose() {
    // test: </val> closes Two, </bar> ignored
    String xml = "<doc><val>One<val>Two</val></bar>Three</doc>";
    XmlTreeBuilder tb = new XmlTreeBuilder();
    Document doc = tb.parse(xml, "http://foo.com/");
    assertEquals("<doc><val>One<val>Two</val>Three</val></doc>",
            TextUtil.stripNewlines(doc.html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testCommentAndDocType() {
    String xml = "<!DOCTYPE html><!-- a comment -->One <qux />Two";
    XmlTreeBuilder tb = new XmlTreeBuilder();
    Document doc = tb.parse(xml, "http://foo.com/");
    assertEquals("<!DOCTYPE html><!-- a comment -->One <qux />Two",
            TextUtil.stripNewlines(doc.html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testSupplyParserToJsoupClass() {
    String xml = "<doc><val>One<val>Two</val></bar>Three</doc>";
    Document doc = Jsoup.parse(xml, "http://foo.com/", Parser.xmlParser());
    assertEquals("<doc><val>One<val>Two</val>Three</val></doc>",
            TextUtil.stripNewlines(doc.html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testSupplyParserToDataStream() throws IOException, URISyntaxException {
    File xmlFile = new File(XmlTreeBuilder.class.getResource("/htmltests/xml-test.xml").toURI());
    InputStream inStream = new FileInputStream(xmlFile);
    Document doc = Jsoup.parse(inStream, null, "http://foo.com", Parser.xmlParser());
    assertEquals("<doc><val>One<val>Two</val>Three</val></doc>",
            TextUtil.stripNewlines(doc.html()));
}

项目：common 文件：XmlTreeBuilderTest.java

@Test
public void testDetectCharsetEncodingDeclaration() throws IOException, URISyntaxException {
    File xmlFile = new File(XmlTreeBuilder.class.getResource("/htmltests/xml-charset.xml").toURI());
    InputStream inStream = new FileInputStream(xmlFile);
    Document doc = Jsoup.parse(inStream, null, "http://example.com/", Parser.xmlParser());
    assertEquals("ISO-8859-1", doc.charset().name());
    assertEquals("<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?> <data>äöåéü</data>",
        TextUtil.stripNewlines(doc.html()));
}

项目：common 文件：ElementsTest.java

@Test public void setHtml() {
    Document doc = Jsoup.parse("<p>One</p><p>Two</p><p>Three</p>");
    Elements ps = doc.select("p");

    ps.prepend("<b>Bold</b>").append("<i>Ital</i>");
    assertEquals("<p><b>Bold</b>Two<i>Ital</i></p>", TextUtil.stripNewlines(ps.get(1).outerHtml()));

    ps.html("<span>Gone</span>");
    assertEquals("<p><span>Gone</span></p>", TextUtil.stripNewlines(ps.get(1).outerHtml()));
}

项目：common 文件：ElementsTest.java

@Test public void wrapDiv() {
    String h = "<p><b>This</b> is <b>jsoup</b>.</p> <p>How do you like it?</p>";
    Document doc = Jsoup.parse(h);
    doc.select("p").wrap("<div></div>");
    assertEquals("<div><p><b>This</b> is <b>jsoup</b>.</p></div> <div><p>How do you like it?</p></div>",
            TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：DocumentTest.java

@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()));
}

项目：common 文件：DocumentTest.java

@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()));
}

项目：common 文件：ElementTest.java

@Test public void testAddNewElement() {
    Document doc = Jsoup.parse("<div id=1><p>Hello</p></div>");
    Element div = doc.getElementById("1");
    div.appendElement("p").text("there");
    div.appendElement("P").attr("class", "second").text("now");
    assertEquals("<html><head></head><body><div id=\"1\"><p>Hello</p><p>there</p><p class=\"second\">now</p></div></body></html>",
            TextUtil.stripNewlines(doc.html()));

    // check sibling index (with short circuit on reindexChildren):
    Elements ps = doc.select("p");
    for (int i = 0; i < ps.size(); i++) {
        assertEquals(i, ps.get(i).siblingIndex);
    }
}

项目：common 文件：ElementTest.java

@Test public void testAppendRowToTable() {
    Document doc = Jsoup.parse("<table><tr><td>1</td></tr></table>");
    Element table = doc.select("tbody").first();
    table.append("<tr><td>2</td></tr>");

    assertEquals("<table><tbody><tr><td>1</td></tr><tr><td>2</td></tr></tbody></table>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：ElementTest.java

@Test public void testPrependRowToTable() {
    Document doc = Jsoup.parse("<table><tr><td>1</td></tr></table>");
    Element table = doc.select("tbody").first();
    table.prepend("<tr><td>2</td></tr>");

    assertEquals("<table><tbody><tr><td>2</td></tr><tr><td>1</td></tr></tbody></table>", TextUtil.stripNewlines(doc.body().html()));

    // check sibling index (reindexChildren):
    Elements ps = doc.select("tr");
    for (int i = 0; i < ps.size(); i++) {
        assertEquals(i, ps.get(i).siblingIndex);
    }
}

项目：common 文件：ElementTest.java

@Test public void testPrependText() {
    Document doc = Jsoup.parse("<div id=1><p>Hello</p></div>");
    Element div = doc.getElementById("1");
    div.prependText("there & now > ");
    assertEquals("there & now > Hello", div.text());
    assertEquals("there &amp; now &gt; <p>Hello</p>", TextUtil.stripNewlines(div.html()));
}

项目：common 文件：ElementTest.java

@Test public void testAddNewHtml() {
    Document doc = Jsoup.parse("<div id=1><p>Hello</p></div>");
    Element div = doc.getElementById("1");
    div.append("<p>there</p><p>now</p>");
    assertEquals("<p>Hello</p><p>there</p><p>now</p>", TextUtil.stripNewlines(div.html()));

    // check sibling index (no reindexChildren):
    Elements ps = doc.select("p");
    for (int i = 0; i < ps.size(); i++) {
        assertEquals(i, ps.get(i).siblingIndex);
    }
}

项目：common 文件：ElementTest.java

@Test public void testPrependNewHtml() {
    Document doc = Jsoup.parse("<div id=1><p>Hello</p></div>");
    Element div = doc.getElementById("1");
    div.prepend("<p>there</p><p>now</p>");
    assertEquals("<p>there</p><p>now</p><p>Hello</p>", TextUtil.stripNewlines(div.html()));

    // check sibling index (reindexChildren):
    Elements ps = doc.select("p");
    for (int i = 0; i < ps.size(); i++) {
        assertEquals(i, ps.get(i).siblingIndex);
    }
}

项目：common 文件：ElementTest.java

@Test public void testWrap() {
    Document doc = Jsoup.parse("<div><p>Hello</p><p>There</p></div>");
    Element p = doc.select("p").first();
    p.wrap("<div class='head'></div>");
    assertEquals("<div><div class=\"head\"><p>Hello</p></div><p>There</p></div>", TextUtil.stripNewlines(doc.body().html()));

    Element ret = p.wrap("<div><div class=foo></div><p>What?</p></div>");
    assertEquals("<div><div class=\"head\"><div><div class=\"foo\"><p>Hello</p></div><p>What?</p></div></div><p>There</p></div>",
            TextUtil.stripNewlines(doc.body().html()));

    assertEquals(ret, p);
}

项目：common 文件：ElementTest.java

@Test public void before() {
    Document doc = Jsoup.parse("<div><p>Hello</p><p>There</p></div>");
    Element p1 = doc.select("p").first();
    p1.before("<div>one</div><div>two</div>");
    assertEquals("<div><div>one</div><div>two</div><p>Hello</p><p>There</p></div>", TextUtil.stripNewlines(doc.body().html()));

    doc.select("p").last().before("<p>Three</p><!-- four -->");
    assertEquals("<div><div>one</div><div>two</div><p>Hello</p><p>Three</p><!-- four --><p>There</p></div>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：ElementTest.java

@Test public void after() {
    Document doc = Jsoup.parse("<div><p>Hello</p><p>There</p></div>");
    Element p1 = doc.select("p").first();
    p1.after("<div>one</div><div>two</div>");
    assertEquals("<div><p>Hello</p><div>one</div><div>two</div><p>There</p></div>", TextUtil.stripNewlines(doc.body().html()));

    doc.select("p").last().after("<p>Three</p><!-- four -->");
    assertEquals("<div><p>Hello</p><div>one</div><div>two</div><p>There</p><p>Three</p><!-- four --></div>", TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：ElementTest.java

@Test
public void insertChildrenAsCopy() {
    Document doc = Jsoup.parse("<div id=1>Text <p>One</p> Text <p>Two</p></div><div id=2></div>");
    Element div1 = doc.select("div").get(0);
    Element div2 = doc.select("div").get(1);
    Elements ps = doc.select("p").clone();
    ps.first().text("One cloned");
    div2.insertChildren(-1, ps);

    assertEquals(4, div1.childNodeSize()); // not moved -- cloned
    assertEquals(2, div2.childNodeSize());
    assertEquals("<div id=\"1\">Text <p>One</p> Text <p>Two</p></div><div id=\"2\"><p>One cloned</p><p>Two</p></div>",
        TextUtil.stripNewlines(doc.body().html()));
}

项目：common 文件：TextNodeTest.java

@Test public void testSplitAnEmbolden() {
    Document doc = Jsoup.parse("<div>Hello there</div>");
    Element div = doc.select("div").first();
    TextNode tn = (TextNode) div.childNode(0);
    TextNode tail = tn.splitText(6);
    tail.wrap("<b></b>");

    assertEquals("Hello <b>there</b>", TextUtil.stripNewlines(div.html())); // not great that we get \n<b>there there... must correct
}

项目：common 文件：NodeTest.java

@Test public void testRemove() {
    Document doc = Jsoup.parse("<p>One <span>two</span> three</p>");
    Element p = doc.select("p").first();
    p.childNode(0).remove();

    assertEquals("two three", p.text());
    assertEquals("<span>two</span> three", TextUtil.stripNewlines(p.html()));
}

项目：common 文件：NodeTest.java

@Test public void unwrap() {
    Document doc = Jsoup.parse("<div>One <span>Two <b>Three</b></span> Four</div>");
    Element span = doc.select("span").first();
    Node twoText = span.childNode(0);
    Node node = span.unwrap();

    assertEquals("<div>One Two <b>Three</b> Four</div>", TextUtil.stripNewlines(doc.body().html()));
    assertTrue(node instanceof TextNode);
    assertEquals("Two ", ((TextNode) node).text());
    assertEquals(node, twoText);
    assertEquals(node.parent(), doc.select("div").first());
}

项目：common 文件：NodeTest.java

@Test public void unwrapNoChildren() {
    Document doc = Jsoup.parse("<div>One <span></span> Two</div>");
    Element span = doc.select("span").first();
    Node node = span.unwrap();
    assertEquals("<div>One  Two</div>", TextUtil.stripNewlines(doc.body().html()));
    assertTrue(node == null);
}