tests/html_parser.cc

Commits

b966b2a517365074e5c381dbdea05b3221dc0198 e840f1eeb0ae26af69e1ae146ea9938e28e9f1af e4e05418a640eaed08cd1ec7cd8644eb1dbcca50 4e01ba8ad2c3361fa4be3d896288020948b58b5e aae562ac1350480e4889aabb35899f776c5b59e9 6c3ae0e31eb0893f20e3872117f92cc6b9a942af 350e7d88bb2feb9db00c6e032cc6623f215b7adf 95e6c70d23e99ffcf70e5bbe12503496e5d8f232 e188783659b9bc3b9993a647e93ed110e7f41db6 5e4c38ff3c212cdd9881427ef3f8c2706539a190 e50ea9e1356a74af18fdd171337ef9dc931e1f4e 8f2e83556d12aaebe8e8597ea6923804b0eb7a43 1627c585128af263181053ab2cf1a4cdcd14ee21 def3513f75b325464ad88a33c741c4ca80572b77 a21501590980a905fa9b902897d700a42a08b7f0 56074a6bfe4498d092f3a227297c8c20e2bb962c d9cf1485b7ae0614130494f0e73237921323b9a1 80f04b134ae32ad8a9d526007b33dd02f6600f05 23d6c65f9368d3c622a55a3068a6b2f1efa0c8d4 09c195df02536b6a796bd648fce9669397b96109 f2b5c8202fbc904e2ed78260e3fdbd55164799d2 4bfba076120f389994fc46a98e8b7a2622314400 e36ac5417e10ee9b9f94f340e1ccf28afc5705ea d00dc89a86dd7e2fcfd4618bc3a1c8cfba9e3c3d d9eef16adaf292f3748db5fb5aa98463de10d712 18ff2ec1bfc1cf9fcd17c1acb05c3b41f8f0ed83 9e7fd2980d723437ea621b78d395fa72ca3f4922

Diff

#include <catch_amalgamated.hpp>
#include "../include/grim.h"
#include "../include/parser.h" 
#include <string>
#include <fstream>

void checkNode(Node* node, std::string tagName, unsigned long children, std::string id, std::vector<std::string> classes, std::unordered_map<std::string, std::string> attributes, std::string note = "") {
	INFO("=========================");
	INFO("TAG: "+tagName);
	INFO("NOTE: "+note+"\n");
	INFO("HTML:\n"+node->print());

REQUIRE(node->getTagName() == tagName);
	REQUIRE(node->children.size() == children);
	REQUIRE(node->getId() == id);

size_t i = 0;
	for (auto c : node->classList.values()) {
		REQUIRE(c == classes[i]);
		i++;
	}

for (auto pair : attributes) {
		REQUIRE(node->getAttribute(pair.first) == pair.second);
	}
}

TEST_CASE( "parseStream can parse various types of HTML strings", "[html]" ) {
	SECTION("Parses a simple HTML document") {
		std::string html = "<!DOCTYPE html>"
			"<html>"
				"<head>"
					"<title>This is a simple test</title>"
					"<link rel=\"stylesheet\" href=\'/style.css\'/>"
				"</head>"
				"<body>"
					"<p id=\"paragraph\" class=\"class1 class2\">This is some text for a simple test</p>"
				"</body>"
			"</html>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Simple HTML Document") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "html", 2, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "head", 2, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "title", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "text", 0, "", {}, {{"innerText","This is a simple test"}}, "First innerText check");

current = current->parent->parent->children[1].get();
		checkNode(current, "link", 0, "", {}, {{"rel","stylesheet"}, {"href","/style.css"}}
				, "Check attribute parsing with different quote types. Also check self closing tags");

current = current->parent->parent->children[1].get();
		checkNode(current, "body", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "p", 1, "paragraph", {"class1", "class2"}, {{}}, "Checks for id and class parsing");

current = current->children[0].get();
		checkNode(current, "text", 0, "", {}, {{"innerText","This is some text for a simple test"}}, "Second innerText check");
	}

SECTION("Inline comment") {
		std::string html = "<div>"
					""
				   "</div>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Inline comment") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "div", 0, "", {}, {{}});
	}

SECTION("Multi line comment") {
		std::string html = "<div>"
					""
				   "</div>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Multiline comment") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "div", 0, "", {}, {{}});
	}

SECTION("Multi line comment with html") {
		std::string html = "<div>"
					""
				   "</div>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Multiline comment with HTML") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "div", 0, "", {}, {{}});
	}

SECTION("Style tag parsing (with HTML in the content prop)") {
		std::string html = "<style>"
					"body > h1 {"
						"margin-left: calc(100% / 50px);"
						"background: url(https://example.com/image.png);"
						"content: \"<h1>hi</h1>\";"
					"}"
				   "</style>"
				   "<h1>test</h1>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Style tag parsing (with HTML in the content prop)") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "style", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "text", 0, "", {}, {{"innerText", "body > h1 {"
						"margin-left: calc(100% / 50px);"
						"background: url(https://example.com/image.png);"
						"content: \"<h1>hi</h1>\";"
					"}"}});
		current = document->children[1].get();
		checkNode(current, "h1", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "text", 0, "", {}, {{"innerText", "test"}});
	}

SECTION("Script tag prematurly closing a pre tag") {
		std::string html = "<pre>"
					"<script>console.log(\"</pre>\");</script>"
				"</pre>";

std::stringstream ss(html);
		std::unique_ptr<Node> document = parseStream(ss);

BENCHMARK("Script tag prematurly closing a pre tag") {
			return parseStream(ss);
		};

// Ensure the only child of root is html
		Node* current = document->children[0].get();

checkNode(current, "pre", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "script", 1, "", {}, {{}});

current = current->children[0].get();
		checkNode(current, "text", 0, "", {}, {{"innerText", "console.log(\"</pre>\");"}});
	}

SECTION("Textarea with script tag inside") {
		std::string html = "<textarea>"
					"<script>console.log(\"</pre>\");</script>"
				"

"; std::stringstream ss(html); std::unique_ptr document = parseStream(ss); BENCHMARK("Textarea with script tag inside") { return parseStream(ss); }; // Ensure the only child of root is html Node* current = document->children[0].get(); checkNode(current, "textarea", 1, "", {}, {{}}); current = current->children[0].get(); checkNode(current, "text", 0, "", {}, {{"innerText",""}}); } }