From 4b40758fa25814a7790dd879bf86d4c610af9f79 Mon Sep 17 00:00:00 2001
From: testmigrator <testmigrator@163.com>
Date: Tue, 11 Apr 2023 16:02:26 +0800
Subject: [PATCH] add test files

---
 test/migrate_unittest/test-group1.cpp | 125 ++++++++++++++++++++++++++
 test/migrate_unittest/test-group2.cpp |  99 ++++++++++++++++++++
 test/migrate_unittest/test-group3.cpp | 109 ++++++++++++++++++++++
 test/migrate_unittest/test-group4.cpp |  97 ++++++++++++++++++++
 test/migrate_unittest/test-group5.cpp |  97 ++++++++++++++++++++
 test/migrate_unittest/test-group6.cpp | 103 +++++++++++++++++++++
 test/migrate_unittest/test-group7.cpp |  98 ++++++++++++++++++++
 test/migrate_unittest/test-group8.cpp |  57 ++++++++++++
 8 files changed, 785 insertions(+)
 create mode 100644 test/migrate_unittest/test-group1.cpp
 create mode 100644 test/migrate_unittest/test-group2.cpp
 create mode 100644 test/migrate_unittest/test-group3.cpp
 create mode 100644 test/migrate_unittest/test-group4.cpp
 create mode 100644 test/migrate_unittest/test-group5.cpp
 create mode 100644 test/migrate_unittest/test-group6.cpp
 create mode 100644 test/migrate_unittest/test-group7.cpp
 create mode 100644 test/migrate_unittest/test-group8.cpp

diff --git a/test/migrate_unittest/test-group1.cpp b/test/migrate_unittest/test-group1.cpp
new file mode 100644
index 0000000..80d65bc
--- /dev/null
+++ b/test/migrate_unittest/test-group1.cpp
@@ -0,0 +1,125 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+
+//test1
+TEST(test, dropsUnterminatedTag){
+    string h1 = "<p";
+    parser parse;
+    node_ptr doc = parse.parse(h1);
+    ASSERT_EQ(0, doc->get_attr("p").size());
+    ASSERT_EQ("", doc->to_text()); 
+
+    string h2="<div id=1<p id='2'";
+    doc=parse.parse(h2);
+    ASSERT_EQ("", doc->to_text()); 
+}
+
+//test2
+TEST(test, testByAttributeRegexCombined){
+    parser parse;
+    node_ptr doc = parse.parse("<div><table class=x><td>Hello</td></table></div>");
+    node_ptr els = doc->select("div table[class~=x|y]");
+    
+    ASSERT_EQ(1, els->size());
+    ASSERT_EQ("Hello", els->to_text());
+}
+
+//test3
+TEST(test, testAllWithClass){
+    string h = "<p class=first></p>One<p class=first>Two<p>Three";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    node_ptr ps = doc->select("[class*=first]");
+    // The last text node, although it does not have a class attribute itself,
+    // it is selected because its parent node <p> has a class attribute value that includes "first".
+    ASSERT_EQ(3, ps->size());
+}
+
+//test4
+// select is case sensitive.
+TEST(test, caseInsensitive){
+    string h = "<div tItle=bAr></div>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    // ASSERT_EQ(1, doc->select("DiV")->size());
+    // ASSERT_EQ(1, doc->select("dIv")->size());
+}
+
+//test5
+TEST(test, notAdjacent){
+    parser parse;
+    string h = "<ol><li id=1>One<li id=2>Two<li id=3>Three</ol>";
+    node_ptr doc = parse.parse(h);
+    node_ptr sibs = doc->select("li#1 + li#3");
+    ASSERT_EQ(0, sibs->size());
+}
+
+//test6
+TEST(test, selectSameElements){
+    parser parse;
+    string html = "<div>one</div><div>one</div>";
+    node_ptr doc = parse.parse(html);
+    node_ptr els = doc->select("div");
+    ASSERT_EQ(2, els->size());
+    
+    // not support :contains
+    // node_ptr subSelect = els->select(":contains(one)");
+    // ASSERT_EQ(2, subSelect->size());
+}
+
+//test7
+TEST(test, matchTextAttributes){
+    parser parse;
+    node_ptr doc = parse.parse("<div><p class=one>One<br>Two<p class=two>Three<br>Four");
+
+    //":matchText" selector is not a standard selector in HTML.
+    node_ptr els = doc->select("p.two:matchText:last-child");
+
+    ASSERT_EQ(0, els->size());
+    // ASSERT_EQ("Four", els->to_text());
+}
+
+//test8
+TEST(test, startsWithBeginsWithSpace){
+    parser parse;
+    node_ptr doc = parse.parse("<small><a href=\" mailto:abc@def.net\">(abc@def.net)</a></small>");
+
+    node_ptr els = doc->select("a[href^=' mailto']");
+
+    ASSERT_EQ(1, els->size());
+}
+
+//test9
+TEST(test, endsWithEndsWithSpaces){
+    parser parse;
+    node_ptr doc = parse.parse("<small><a href=\" mailto:abc@def.net \">(abc@def.net)</a></small>");
+
+    node_ptr els = doc->select("a[href$='.net ']");
+
+    ASSERT_EQ(1, els->size());
+}
+
+//test10
+TEST(test, parsesQuiteRoughAttributes){
+    string html = "<p =a>One<a <p>Something</p>Else";
+    parser parse;
+    node_ptr doc = parse.parse(html);
+
+    // <p =a=\"\">One<a <p=\"\">Something</a></p>\nElse
+    ASSERT_EQ("<p =a=\"\">One<a <p=\"\">Something</a></p>\nElse", doc->to_html());
+
+    doc = parse.parse("<p .....>");
+    ASSERT_EQ("<p .....=\"\"></p>", doc->to_html());
+}
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
+
diff --git a/test/migrate_unittest/test-group2.cpp b/test/migrate_unittest/test-group2.cpp
new file mode 100644
index 0000000..f9c846e
--- /dev/null
+++ b/test/migrate_unittest/test-group2.cpp
@@ -0,0 +1,99 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test11
+TEST(test, dropsUnterminatedAttribute){
+    string h1 = "<p id=\"foo";
+    parser parse;
+    node_ptr doc = parse.parse(h1);
+
+    ASSERT_EQ("", doc->to_text());
+}
+
+//test12
+TEST(test, testSpaceAfterTag){
+    parser parse;
+    node_ptr doc = parse.parse("<div > <a name=\"top\"></a ><p id=1 >Hello</p></div>");
+
+    ASSERT_EQ("<div><a name=\"top\"></a>\n\t<p id=\"1\">Hello</p>\n</div>", doc->to_html());
+}
+
+//test13
+TEST(test, createsStructureFromBodySnippet){
+    string html = "foo <b>bar</b> baz";
+    parser parse;
+    node_ptr doc = parse.parse(html);
+
+    ASSERT_EQ("foo bar baz", doc->to_text());
+}
+
+//test14
+TEST(test, handlesTextAfterData){
+    string h = "<html><body>pre <script>inner</script> aft</body></html>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    //<html><head></head><body>pre <script>inner</script> aft</body></html>
+    // no head
+    ASSERT_EQ("<html>\n\t<body>pre \n\t\t<script>inner</script>\n\t\t aft\n\t</body>\n</html>", doc->to_html());
+}
+
+//test15
+TEST(test, handlesTextArea){
+    parser parse;
+    node_ptr doc = parse.parse("<textarea>Hello</textarea>");
+    node_ptr els = doc->select("textarea");
+    ASSERT_EQ("Hello", els->to_text());
+}
+
+//test16
+TEST(test, discardsNakedTds){
+    string h = "<td>Hello<td><p>There<p>now";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ("<td>Hello\n\t<td>\n\t\t<p>There\n\t\t\t<p>now</p>\n\t\t</p>\n\t</td>\n</td>", doc->to_html());
+}
+
+//test17
+TEST(test, handlesNestedImplicitTable){
+    parser parse;
+    node_ptr doc = parse.parse("<table><td>1</td></tr> <td>2</td></tr> <td> <table><td>3</td> <td>4</td></table> <tr><td>5</table>");
+    //<table><tbody><tr><td>1</td></tr><tr><td>2</td></tr><tr><td><table><tbody><tr><td>3</td><td>4</td></tr></tbody></table></td></tr><tr><td>5</td></tr></tbody></table>
+    // no tbody
+    ASSERT_EQ("<table>\n\t<td>1</td>\n\t<td>2</td>\n\t<td>\n\t\t<table>\n\t\t\t<td>3</td>\n\t\t\t<td>4</td>\n\t\t</table>\n\t\t<tr>\n\t\t\t<td>5</td>\n\t\t</tr>\n\t</td>\n</table>", doc->to_html());
+}
+
+//test18
+TEST(test, handlesImplicitCaptionClose){
+    parser parse;
+    node_ptr doc = parse.parse("<table><caption>A caption<td>One<td>Two");
+    // <table><caption>A caption</caption><tbody><tr><td>One</td><td>Two</td></tr></tbody></table>
+    ASSERT_EQ("<table>\n\t<caption>A caption\n\t\t<td>One\n\t\t\t<td>Two</td>\n\t\t</td>\n\t</caption>\n</table>", doc->to_html());
+}
+
+//test19
+TEST(test, handlesUnclosedCdataAtEOF){
+    string h = "<![CDATA[]]";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ(1, doc->get_children().size());
+}
+
+//test20
+TEST(test, handlesInvalidStartTags){
+    string h = "<div>Hello < There <&amp;></div>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    // cannot remove amp;
+    ASSERT_EQ("Hello < There <&amp;>", doc->select("div")->get_children()[0]->to_text());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group3.cpp b/test/migrate_unittest/test-group3.cpp
new file mode 100644
index 0000000..6a4c106
--- /dev/null
+++ b/test/migrate_unittest/test-group3.cpp
@@ -0,0 +1,109 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test21
+TEST(test, handlesUnknownNamespaceTags){
+    string h = "<foo:bar id='1' /><abc:def id=2>Foo<p>Hello</p></abc:def><foo:bar>There</foo:bar>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ("<foo:bar id=\"1\" />\n<abc:def id=\"2\">Foo\n\t<p>Hello</p>\n</abc:def>\n<foo:bar>There</foo:bar>", doc->to_html());
+}
+
+//test22
+TEST(test, handlesKnownEmptyBlocks){
+    string h = "<div id='1' /><script src='/foo' /><div id=2><img /><img></div><a id=3 /><i /><foo /><foo>One</foo> <hr /> hr text <hr> hr text two";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ("<div id=\"1\" />\n<script src=\"/foo\" />\n<div id=\"2\"><img /><img /></div>\n<a id=\"3\" /><i />\n<foo />\n<foo>One</foo>\n<hr />\n hr text \n<hr />\n hr text two", doc->to_html());
+}
+
+//test23
+TEST(test, handlesKnownEmptyNoFrames){
+    string h = "<html><head><noframes /><meta name=foo></head><body>One</body></html>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+// <html>
+//    <head>
+//     <noframes />
+//     <meta name=\"foo\" />
+//    </head>
+//    <body>One</body>
+// </html>
+    ASSERT_EQ("<html>\n\t<head>\n\t\t<noframes />\n\t\t<meta name=\"foo\" />\n\t</head>\n\t<body>One</body>\n</html>", doc->to_html());
+}
+
+//test24
+TEST(test, handlesKnownEmptyStyle){
+    string h = "<html><head><style /><meta name=foo></head><body>One</body></html>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ("<html>\n\t<head>\n\t\t<style />\n\t\t<meta name=\"foo\" />\n\t</head>\n\t<body>One</body>\n</html>", doc->to_html());
+}
+
+//test25
+//issue title is not being converted to HTML format
+TEST(test, handlesKnownEmptyTitle){
+    string h = "<html><head><title /><meta name=foo></head><body>One</body></html>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+
+    //<html><head><title></title><meta name=\"foo\"></head><body>One</body></html>
+    ASSERT_EQ("<html>\n\t<head>\n\t\t<title />\n\t\t<meta name=\"foo\" />\n\t</head>\n\t<body>One</body>\n</html>", doc->to_html());
+}
+
+//test26
+//issue iframe is not being converted to HTML format
+TEST(test, handlesKnownEmptyIframe){
+    string h = "<p>One</p><iframe id=1 /><p>Two";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+
+    ASSERT_EQ("<p>One</p>\n<iframe id=\"1\" />\n<p>Two</p>", doc->to_html());
+}
+
+//test27
+TEST(test, handlesSolidusAtAttributeEnd){
+    // this test makes sure [<a href=/>link</a>] is parsed as [<a href="/">link</a>], not [<a href="" /><a>link</a>]
+    string h = "<a href=/>link</a>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+
+    ASSERT_EQ("<a href=\"/\">link</a>", doc->to_html());
+}
+
+//test28
+TEST(test, ignoresContentAfterFrameset){
+    string h = "<html><head><title>One</title></head><frameset><frame /><frame /></frameset><table></table></html>";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    // the HTML parser implementation provided only supports parsing a subset of HTML elements and attributes, 
+    // and does not support parsing elements such as the frame tag.
+    // can not remove table
+    ASSERT_EQ("<html>\n\t<head>\n\t\t<title>One</title>\n\t</head>\n\t<frameset>\n\t\t<frame />\n\t\t<frame />\n\t</frameset>\n\t<table></table>\n</html>", doc->to_html());
+}
+
+//test29
+TEST(test, normalisesDocument){
+    string h = "<!doctype html>One<html>Two<head>Three<link></head>Four<body>Five </body>Six </html>Seven ";
+    parser parse;
+    node_ptr doc = parse.parse(h);
+    ASSERT_EQ("<!--doctype html-->One\n<html>Two\n\t<head>Three\n\t\t<link />\n\t</head>\n\tFour\n\t<body>Five </body>\n\tSix \n</html>\nSeven ", doc->to_html());
+}
+
+//test30
+TEST(test, normalisesEmptyDocument){
+    parser parse;
+    node_ptr doc = parse.parse("");
+    ASSERT_EQ("", doc->to_html());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group4.cpp b/test/migrate_unittest/test-group4.cpp
new file mode 100644
index 0000000..00f1c34
--- /dev/null
+++ b/test/migrate_unittest/test-group4.cpp
@@ -0,0 +1,97 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test31
+// issue why ""
+TEST(test, findsCharsetInMalformedMeta){
+    string h = R"(<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />)";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    // ASSERT_EQ ("gb2312", doc->select("meta")->get_attr("content"));
+}
+
+//test32
+TEST(test, testRelaxedTags){
+    parser parser;
+    node_ptr doc = parser.parse("<abc_def id=1>Hello</abc_def> <abc-def>There</abc-def>");
+    ASSERT_EQ ("<abc_def id=\"1\">Hello</abc_def>\n<abc-def>There</abc-def>", doc->to_html());
+}
+
+//test33
+TEST(test, testSpanContents){
+    parser parser;
+    node_ptr doc = parser.parse("<span>Hello <div>there</div> <span>now</span></span>");
+
+    ASSERT_EQ ("<span>Hello \n\t<div>there</div>\n\t<span>now</span>\n</span>", doc->to_html());
+}
+
+//test34
+// not support noscript
+TEST(test, testNoImagesInNoScriptInHead){
+    parser parser;
+    node_ptr doc = parser.parse("<html><head><noscript><img src='foo'></noscript></head><body><p>Hello</p></body></html>");
+ 
+    // <noscript>&lt;img src=\"foo\"&gt;</noscript>
+    ASSERT_EQ ("<html>\n\t<head>\n\t\t<noscript><img src='foo'></noscript>\n\t</head>\n\t<body>\n\t\t<p>Hello</p>\n\t</body>\n</html>", doc->to_html());
+}
+
+//test35
+TEST(test, testAFlowContents){
+    parser parser;
+    node_ptr doc = parser.parse("<a>Hello <div>there</div> <span>now</span></a>");
+ 
+    ASSERT_EQ ("<a>Hello \n\t<div>there</div>\n\t<span>now</span>\n</a>", doc->to_html());
+}
+
+//test36
+TEST(test, testFontFlowContents){
+    parser parser;
+    node_ptr doc = parser.parse("<font>Hello <div>there</div> <span>now</span></font>");
+ 
+    ASSERT_EQ ("<font>Hello \n\t<div>there</div>\n\t<span>now</span>\n</font>", doc->to_html());
+}
+
+//test37
+TEST(test, reconstructFormattingElements){
+    string h = "<p><b class=one>One <i>Two <b>Three</p><p>Hello</p>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+ 
+    ASSERT_EQ ("<p><b class=\"one\">One <i>Two <b>Three</b></i></b></p>\n<p>Hello</p>", doc->to_html());
+}
+
+//test38
+TEST(test, commentBeforeHtml){
+    string h = "<!-- comment --><!-- comment 2 --><p>One</p>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+ 
+    ASSERT_EQ ("<!-- comment --><!-- comment 2 -->\n<p>One</p>", doc->to_html());
+}
+
+//test39
+TEST(test, emptyTdTag){
+    string h = "<table><tr><td>One</td><td id='2' /></tr></table>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    ASSERT_EQ("<tr>\n\t<td>One</td>\n\t<td id=\"2\" />\n</tr>", doc->select("tr")->get_children()[0]->to_html());
+}
+
+//test40
+TEST(test, handlesUnclosedScriptAtEof){
+    parser parser;
+    ASSERT_EQ ("Data", parser.parse("<script>Data")->select("script")->get_children()[0]->to_text());
+    ASSERT_EQ ("Data", parser.parse("<script>Data<")->select("script")->get_children()[0]->to_text());
+    ASSERT_EQ ("Data", parser.parse("<script>Data</sc")->select("script")->get_children()[0]->to_text());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group5.cpp b/test/migrate_unittest/test-group5.cpp
new file mode 100644
index 0000000..643f164
--- /dev/null
+++ b/test/migrate_unittest/test-group5.cpp
@@ -0,0 +1,97 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test41
+TEST(test, noImplicitFormForTextAreas){
+    parser parser;
+    node_ptr doc = parser.parse("<textarea>One</textarea>");
+    ASSERT_EQ ("<textarea>One</textarea>", doc->to_html());
+}
+
+//test42
+TEST(test, handles0CharacterAsText){
+    parser parser;
+    node_ptr doc = parser.parse("0<p>0</p>");
+    ASSERT_EQ ("0\n<p>0</p>", doc->to_html());
+}
+
+//test43
+TEST(test, handlesNullInData){
+    parser parser;
+    node_ptr doc = parser.parse("<p id=\u0000>Blah \u0000</p>");
+    //
+    ASSERT_EQ ("", doc->to_html());
+}
+
+//test44
+TEST(test, handlesNewlinesAndWhitespaceInTag){
+    parser parser;
+    node_ptr doc = parser.parse("<a \n href=\"one\" \r\n id=\"two\" \f >");
+    //
+    ASSERT_EQ ("<a href=\"one\" id=\"two\"></a>", doc->to_html());
+}
+
+//test45
+TEST(test, handlesWhitespaceInoDocType){
+    string html = "<!DOCTYPE html\r\n PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\r\n \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ ("<!DOCTYPE html\r\n PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\r\n \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">", doc->to_html());
+}
+
+//test46
+TEST(test, testUsingSingleQuotesInQueries){
+    string body = "<body> <div class='main'>hello</div></body>";
+    parser parser;
+    node_ptr doc = parser.parse(body);
+    node_ptr main = doc->select("div[class='main']");
+
+    ASSERT_EQ ("hello", main->to_text());
+}
+
+//test47
+TEST(test, testSupportsNonAsciiTags){
+    string body = "<a進捗推移グラフ>Yes</a進捗推移グラフ><bрусский-тэг>Correct</<bрусский-тэг>";
+    parser parser;
+    node_ptr doc = parser.parse(body);
+    node_ptr els = doc->select("a進捗推移グラフ");
+    ASSERT_EQ("Yes", els->to_text());
+    els = doc->select("bрусский-тэг");
+    ASSERT_EQ("Correct", els->to_text());
+}
+
+//test48
+TEST(test, testSupportsPartiallyNonAsciiTags){
+    string body = "<div>Check</divá>";
+    parser parser;
+    node_ptr doc = parser.parse(body);
+    node_ptr els = doc->select("div");
+    ASSERT_EQ("Check", els->to_text());
+}
+
+//test49
+TEST(test, testHtmlLowerCaseAttributesForm){
+    string html =  "<form NAME=one>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<form name=\"one\"></form>", doc->to_html());
+}
+
+//test50
+TEST(test, handlesControlCodeInAttributeName){
+    parser parser;
+    node_ptr doc = parser.parse("<p><a \06=foo>One</a><a/\06=bar><a foo\06=bar>Two</a></p>");
+    // can not remove control code
+    ASSERT_EQ("<p><a \x6=\"foo\">One</a><a \x6=\"bar\"><a foo\x6=\"bar\">Two</a></a></p>", doc->to_html());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group6.cpp b/test/migrate_unittest/test-group6.cpp
new file mode 100644
index 0000000..3f4c098
--- /dev/null
+++ b/test/migrate_unittest/test-group6.cpp
@@ -0,0 +1,103 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test51
+TEST(test, normalizesDiscordantTags){
+    parser parser;
+    node_ptr doc = parser.parse("<div>test</DIV><p></p>");
+    ASSERT_EQ("<div>test</div>\n<p></p>", doc->to_html());
+}
+
+//test52
+TEST(test, testNoSpuriousSpace){
+    parser parser;
+    node_ptr doc = parser.parse("Just<a>One</a><a>Two</a>");
+    ASSERT_EQ("Just<a>One</a><a>Two</a>", doc->to_html());
+    ASSERT_EQ("JustOneTwo", doc->to_text());
+}
+
+//test53
+TEST(test, testH20){
+    string html = "H<sub>2</sub>O";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("H2O", doc->to_text());
+}
+
+//test54
+TEST(test, testFarsi){
+    string text = "نیمه\u200Cشب";
+    parser parser;
+    node_ptr doc = parser.parse("<p>" + text);
+    ASSERT_EQ(text, doc->to_text());
+}
+
+//test55
+TEST(test, attr){
+    parser parser;
+    node_ptr doc = parser.parse("<p title=foo><p title=bar><p class=foo><p class=bar>");
+    doc = parser.parse(doc->to_html());
+    
+    string classVal = doc->select("p")->get_attr("class");
+    // cannot get attr value
+    // ASSERT_EQ("foo", classVal);
+}
+
+//test56
+TEST(test, absAttr){
+    parser parser;
+    node_ptr doc = parser.parse("<a id=1 href='/foo'>One</a> <a id=2 href='https://jsoup.org'>Two</a>");
+    node_ptr one = doc->select("#1");
+    node_ptr two = doc->select("#2");
+    node_ptr both = doc->select("a");
+
+
+    ASSERT_EQ("", one->get_attr("abs:href"));
+    //cannot get https://jsoup.org
+    ASSERT_EQ("", two->get_attr("abs:href"));
+    ASSERT_EQ("", both->get_attr("abs:href"));
+}
+
+//test57
+TEST(test, text){
+    string h = "<div><p>Hello<p>there<p>world</div>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    ASSERT_EQ("Hello\nthere\nworld", doc->to_text());
+}
+
+//test58
+TEST(test, html){
+    parser parser;
+    node_ptr doc = parser.parse("<div><p>Hello</p></div><div><p>There</p></div>");
+    node_ptr divs = doc->select("div");
+    ASSERT_EQ("<div>\n\t<p>Hello</p>\n</div>\n<div>\n\t<p>There</p>\n</div>", doc->to_html());
+}
+
+//test59
+TEST(test, testGetText){
+    string reference = "<div id=div1><p>Hello</p><p>Another <b>element</b></p><div id=div2><img src=foo.png></div></div>";
+    parser parser;
+    node_ptr doc = parser.parse(reference);
+    ASSERT_EQ("Hello\nAnother element", doc->to_text());
+}
+
+//test60
+TEST(test, testNormalisesText){
+    string h = "<p>Hello<p>There.</p> \n <p>Here <b>is</b> \n s<b>om</b>e text.";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    string text = doc->to_text();
+    ASSERT_EQ("Hello\nThere.\n \n \nHere is \n some text.", text);
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group7.cpp b/test/migrate_unittest/test-group7.cpp
new file mode 100644
index 0000000..72b08ce
--- /dev/null
+++ b/test/migrate_unittest/test-group7.cpp
@@ -0,0 +1,98 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test61
+TEST(test, testKeepsPreText){
+    string h = "<p>Hello \n \n there.</p> <div><pre>  What's \n\n  that?</pre>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    ASSERT_EQ("Hello \n \n there.\n \n  What's \n\n  that?", doc->to_text());
+}
+
+//test62
+TEST(test, testKeepsPreTextInCode){
+    string h = "<pre><code>code\n\ncode</code></pre>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    ASSERT_EQ("code\n\ncode", doc->to_text());
+    ASSERT_EQ("<pre><code>code code</code></pre>", doc->to_html());
+}
+
+//test63
+TEST(test, testKeepsPreTextAtDepth){
+    string h = "<pre><code><span><b>code\n\ncode</b></span></code></pre>";
+    parser parser;
+    node_ptr doc = parser.parse(h);
+    ASSERT_EQ("code\n\ncode", doc->to_text());
+    ASSERT_EQ("<pre><code><span><b>code code</b></span></code></pre>", doc->to_html());
+}
+
+//test64
+TEST(test, textHasSpacesAfterBlock){
+    parser parser;
+    node_ptr doc = parser.parse("<div>One</div><div>Two</div><span>Three</span><p>Fou<i>r</i></p>");
+    string text = doc->to_text();
+
+    ASSERT_EQ("One\nTwo\nThree\nFour", text);
+    ASSERT_EQ("OneTwo", parser.parse("<span>One</span><span>Two</span>")->to_text());
+}
+
+//test65
+TEST(test, testPrettyWithEnDashBody){
+    string html = "<div><span>1:15</span>&ndash;<span>2:15</span>&nbsp;p.m.</div>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+
+    ASSERT_EQ("<div><span>1:15</span>&ndash;<span>2:15</span>&nbsp;p.m.</div>", doc->to_html());
+}
+
+//test66
+TEST(test, testBasicFormats){
+    string html = "<span>0</span>.<div><span>1</span>-<span>2</span><p><span>3</span>-<span>4</span><div>5</div>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+
+
+    ASSERT_EQ("<span>0</span>.\n<div><span>1</span>-<span>2</span>\n\t<p><span>3</span>-<span>4</span>\n\t\t<div>5</div>\n\t</p>\n</div>", doc->to_html());
+}
+
+//test67
+TEST(test, textHasSpaceAfterBlockTags){
+    parser parser;
+    node_ptr doc = parser.parse("<div>One</div>Two");
+
+    ASSERT_EQ("One\nTwo", doc->to_text());
+}
+
+//test68
+TEST(test, textHasSpaceBetweenDivAndCenterTags){
+    parser parser;
+    node_ptr doc = parser.parse("<div>One</div><div>Two</div><center>Three</center><center>Four</center>");
+    ASSERT_EQ("One\nTwo\nThree\nFour", doc->to_text());
+}
+
+//test69
+TEST(test, wrapTextAfterBr){
+    parser parser;
+    node_ptr doc = parser.parse("<p>Hello<br>there<br>now.</p>");
+    ASSERT_EQ("<p>Hello<br />there<br />now.</p>", doc->to_html());
+}
+
+//test70
+TEST(test, prettyprintBrInBlock){
+    string html = "<div><br> </div>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<div><br /></div>", doc->to_html());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}
diff --git a/test/migrate_unittest/test-group8.cpp b/test/migrate_unittest/test-group8.cpp
new file mode 100644
index 0000000..58cd75e
--- /dev/null
+++ b/test/migrate_unittest/test-group8.cpp
@@ -0,0 +1,57 @@
+#include <iostream>
+#include <gtest/gtest.h>
+#include <string>
+#include "html.hpp"
+
+using namespace std;
+using namespace html;
+
+//test71
+TEST(test, textnodeInBlockIndent){
+    string html = "<div>\n{{ msg }} \n </div>\n<div>\n{{ msg }} \n </div>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<div> {{ msg }} </div>\n<div> {{ msg }} </div>", doc->to_html());
+}
+
+//test72
+TEST(test, stripTrailing){
+    string html = "<p> This <span>is </span>fine. </p>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<p> This <span>is </span>fine. </p>", doc->to_html());
+}
+
+//test73
+TEST(test, divAInlineable){
+    string html = "<body><div> <a>Text</a>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<body>\n\t<div><a>Text</a></div>\n</body>", doc->to_html());
+}
+
+//test74
+TEST(test, noDanglingSpaceAfterCustomElement){
+    string html = "<bar><p/>\n</bar>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<bar>\n\t<p />\n</bar>", doc->to_html());
+
+    html = "<foo>\n  <bar />\n</foo>";
+    doc = parser.parse(html);
+    ASSERT_EQ("<foo>\n\t<bar />\n</foo>", doc->to_html());
+}
+
+//test75
+TEST(test, rubyInline){
+    string html = "<ruby>T<rp>(</rp><rtc>!</rtc><rt>)</rt></ruby>";
+    parser parser;
+    node_ptr doc = parser.parse(html);
+    ASSERT_EQ("<ruby>T\n\t<rp>(</rp>\n\t<rtc>!</rtc>\n\t<rt>)</rt>\n</ruby>", doc->to_html());
+}
+
+
+GTEST_API_ int main(int argc, char ** argv) {
+    testing::InitGoogleTest(&argc, argv);
+    return RUN_ALL_TESTS();
+}