documented (a766a939) · Commits · jan.koester / libhtmlpp

src/html.cpp

+52 −0

Original line number	Diff line number	Diff line
		/**
		* @file html.cpp
		* @brief Definitions for libhtmlpp HTML element types and utilities.
		* @date 2025-10-30
		*
		* This file is part of libhtmlpp and provides HTML parsing, DOM-like element
		* types, serialization helpers, and encoding utilities.
		*/
		/*******************************************************************************
		* Copyright (c) 2021, Jan Koester jan.koester@gmx.net
		* All rights reserved.
		@@ -43,6 +51,10 @@
		#define HTMLTAG_TERMINATE '/'
		#define HTMLTAG_CLOSE '>'
		#define HTMLTAG_COMMENT '!'
		/**
		* @namespace libhtmlpp
		* @brief Core namespace for the libhtmlpp HTML parsing and printing library.
		*/

		namespace libhtmlpp {

		@@ -374,6 +386,10 @@ void libhtmlpp::HtmlString::_buildtreenode(
		start = start->nextel.get();
		}
		}
		/**
		* @brief Tokenizes the buffer and constructs the intermediate DocElements list,
		* then converts it into a tree stored in @_rootEl.
		*/

		void libhtmlpp::HtmlString::_buildTree() {
		DocElements *lastEl = nullptr;
		@@ -527,11 +543,23 @@ void libhtmlpp::HtmlString::_buildTree() {

		_buildtreenode(firstEl.get(),nullptr,_rootEl);
		}
		/**
		* @brief Streams an HtmlString to an output stream using its underlying string.
		* @param os Output stream.
		* @param p HtmlString to stream.
		* @return Reference to @p os.
		*/

		std::ostream& operator<<(std::ostream& os, const libhtmlpp::HtmlString& p) {
		os << p.str();
		return os;
		}
		/**
		* @brief Extracts tag name and attributes from a token vector into an HtmlElement.
		* @param in Token buffer containing a single open tag.
		* @param out Destination HtmlElement to populate.
		* @throws HTMLException if no tag could be determined.
		*/

		void libhtmlpp::HtmlString::_serialelize(std::vector<char> in, libhtmlpp::HtmlElement *out) {
		size_t st=0,et=0;
		@@ -1241,6 +1269,12 @@ libhtmlpp::HtmlPage::HtmlPage(){

		libhtmlpp::HtmlPage::~HtmlPage(){
		}
		/**
		* @brief Loads an HTML file from disk into a given HtmlElement root.
		* @param html Output root element to populate.
		* @param path Filesystem path to the HTML file.
		* @throws HTMLException if the file cannot be opened or parsed.
		*/

		void libhtmlpp::HtmlPage::loadFile(libhtmlpp::HtmlElement &html,const std::string& path){
		std::string data;
		@@ -1264,6 +1298,12 @@ void libhtmlpp::HtmlPage::loadFile(libhtmlpp::HtmlElement &html,const std::strin
		_CheckHeader(data);
		loadString(html,data);
		}
		/**
		* @brief Parses an HTML source string and copies the result into @p html.
		* @param html Output root element to populate.
		* @param src Input HTML source.
		* @throws HTMLException on malformed input.
		*/

		void libhtmlpp::HtmlPage::loadString(libhtmlpp::HtmlElement &html,const std::string &src){
		HtmlString buf=src;
		@@ -1285,6 +1325,12 @@ void loadString(libhtmlpp::HtmlElement &html,const libhtmlpp::HtmlString *node){
		libhtmlpp::HtmlString buf=*node;
		html=(libhtmlpp::HtmlElement&)buf.parse();
		}
		/**
		* @brief Serializes an HtmlElement subtree and writes it to a file.
		* @param html Element to serialize.
		* @param path Destination file path.
		* @throws HTMLException on I/O errors.
		*/

		void libhtmlpp::HtmlPage::saveFile(libhtmlpp::HtmlElement &html,const std::string& path){
		HtmlString data;
		@@ -1389,6 +1435,12 @@ void libhtmlpp::HtmlPage::_CheckHeader(const HtmlString &page){
		_Html5=!html4;

		}
		/**
		* @brief Serializes an element (and its subtree) into an HtmlString (definition).
		* @param element Root element to print.
		* @param output Output buffer to append serialized HTML to.
		* @param formated If true, pretty-prints the output with line breaks/indentation.
		*/

		void libhtmlpp::print(const Element &element, HtmlString &output,bool formated) {

src/html.h

+63 −0

Original line number	Diff line number	Diff line
		/**
		* @file html.h
		* @brief Public declarations for libhtmlpp HTML element types and utilities.
		* @date 2025-10-30
		*
		* This file is part of libhtmlpp and provides HTML parsing, DOM-like element
		* types, serialization helpers, and encoding utilities.
		*/
		/*******************************************************************************
		Copyright (c) 2014, Jan Koester jan.koester@gmx.net
		All rights reserved.
		@@ -34,10 +42,23 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
		#include <memory>

		#pragma once
		/**
		* @namespace libhtmlpp
		* @brief Core namespace for the libhtmlpp HTML parsing and printing library.
		*/

		namespace libhtmlpp {
		/**
		* @brief Internal helper frame used while building the tree during parsing.
		*/
		class DocElements;
		/**
		* @brief Concrete element representing a generic HTML tag with attributes and child/next links.
		*/
		class HtmlElement;
		/**
		* @brief Mutable string buffer for HTML input/output with parsing facilities.
		*/
		class HtmlString;

		enum ElementType{
		@@ -47,6 +68,9 @@ namespace libhtmlpp {
		ScriptEL=3,
		SvgEL=4
		};
		/**
		* @brief Abstract base class for all nodes in the HTML tree. Provides linkage and common operations.
		*/

		class Element {
		public:
		@@ -140,6 +164,9 @@ namespace libhtmlpp {
		friend void print(const Element& element, HtmlString &output,bool formated);
		friend void _copy(libhtmlpp::Element dest,const libhtmlpp::Element src);
		};
		/**
		* @brief Leaf node representing plain text content of an HTML document.
		*/

		class TextElement : public Element {
		public:
		@@ -161,6 +188,9 @@ namespace libhtmlpp {
		friend void print(const Element& element, HtmlString &output,bool formated);
		friend void _copy(libhtmlpp::Element dest,const libhtmlpp::Element src);
		};
		/**
		* @brief Leaf node representing an HTML comment (<!-- -->).
		*/

		class CommentElement : public Element{
		public:
		@@ -181,6 +211,9 @@ namespace libhtmlpp {
		friend void print(const Element& element, HtmlString &output,bool formated);
		friend void _copy(libhtmlpp::Element dest,const libhtmlpp::Element src);
		};
		/**
		* @brief Element representing a <script> tag and its text content.
		*/

		class ScriptElement : public HtmlElement{
		public:
		@@ -210,6 +243,9 @@ namespace libhtmlpp {
		friend void print(const Element& element, HtmlString &output,bool formated);
		friend void _copy(libhtmlpp::Element dest,const libhtmlpp::Element src);
		};
		/**
		* @brief Element representing an embedded <svg> tag and its attributes/content.
		*/

		class SvgElement : public HtmlElement{
		public:
		@@ -239,6 +275,13 @@ namespace libhtmlpp {
		friend void print(const Element& element, HtmlString &output,bool formated);
		friend void _copy(libhtmlpp::Element dest,const libhtmlpp::Element src);
		};
		/**
		* @brief Serializes an element (and its subtree) into an HtmlString.
		* @param element Root element to print.
		* @param output Output buffer to append serialized HTML to.
		* @param formated If true, pretty-prints the output with line breaks/indentation.
		*/


		void print(const Element& element, HtmlString &output,bool formated=false);

		@@ -284,6 +327,11 @@ namespace libhtmlpp {
		const std::vector<char>& data() const;
		const std::string str() const;
		const char *c_str() const;
		/**
		* @brief Parses the current buffer into a DOM-like tree and returns the root element.
		* @return Reference to the root Element stored internally.
		* @throws HTMLException on malformed input.
		*/

		libhtmlpp::Element &parse();

		@@ -296,9 +344,24 @@ namespace libhtmlpp {
		friend void HtmlEncode(const std::string &input,HtmlString *output);
		friend class HtmlPage;
		};
		/**
		* @brief Encodes special HTML characters in a string and appends to an HtmlString.
		* @param input Plain input string.
		* @param output Destination HtmlString that receives encoded characters.
		*/


		void HtmlEncode(const std::string &input,HtmlString *output);
		/**
		* @brief Encodes special HTML characters in a string and writes into std::string.
		* @param input Plain input string.
		* @param output Receives encoded HTML string.
		*/

		void HtmlEncode(const std::string &input,std::string &output);
		/**
		* @brief High level loader/saver for HTML documents (files and strings).
		*/

		class HtmlPage {
		public: