added: JSONToSpaceParser -- a parser for JSON format to Space structure

added: SpaceToJSON -- a serializer from Space structure to JSON (not finished yet)



git-svn-id: svn://ttmath.org/publicrep/pikotools/trunk@427 e52654a7-88a9-db11-a3e9-0013d4bc506e

space/jsontospaceparser.h

@@ -0,0 +1,380 @@
+/*
+ * This file is a part of PikoTools
+ * and is distributed under the (new) BSD licence.
+ * Author: Tomasz Sowa <t.sowa@ttmath.org>
+ */
+
+/* 
+ * Copyright (c) 2012, Tomasz Sowa
+ * All rights reserved.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * 
+ *  * Redistributions of source code must retain the above copyright notice,
+ *    this list of conditions and the following disclaimer.
+ *    
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ *    
+ *  * Neither the name Tomasz Sowa nor the names of contributors to this
+ *    project may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ * THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef headerfile_picotools_space_jsonspaceparser
+#define headerfile_picotools_space_jsonspaceparser
+
+#include <fstream>
+#include "space.h"
+
+
+
+namespace PT
+{
+
+
+
+class JSONToSpaceParser
+{
+public:
+
+
+	/*
+		ctor -- setting default values (SetDefault() method)
+	*/
+	JSONToSpaceParser();
+
+
+	/*
+		setting the root space
+	*/
+	void SetSpace(Space * pspace);
+	void SetSpace(Space & pspace);
+
+
+	/*
+		setting options of the parser to the default values 
+		utf8, split single etc.
+	*/
+	void SetDefault();
+
+
+	/*
+		status of parsing
+	*/
+	enum Status { ok, cant_open_file, syntax_error, max_nested_spaces_exceeded, no_space };
+
+
+	/*
+		the last status of parsing, set by Parse() methods
+	*/
+	Status status;
+
+
+	/*
+		a number of a line in which there is a syntax_error
+	*/
+	int line;
+
+
+	/*
+		how many objects were skipped
+		used in parsing tables when create_table_as_space is false
+	*/
+	size_t skipped;
+
+
+	/*
+		main methods used to parse
+		file_name is the path to a file
+	*/
+	Status Parse(const char * file_name);
+	Status Parse(const std::string & file_name);
+	Status Parse(const wchar_t * file_name);
+	Status Parse(const std::wstring & file_name);
+
+
+	/*
+		main methods used to parse
+		str - input string (either 8bit ascii or UTF-8 -- see UTF8() method)
+	*/
+	Status ParseString(const char * str);
+	Status ParseString(const std::string & str);
+
+
+	/*
+		main methods used to parse
+		here input string is always in unicode (wide characters)
+	*/
+	Status ParseString(const wchar_t * str);
+	Status ParseString(const std::wstring & str);
+
+
+	/*
+		if your list consists of only one item, e.g:
+			option1 = value 1
+			option2 = "value 2"
+			option3 = ( "value 3" )
+		then if you call SplitSingle(true) then such values will be stored in 
+		'table_single' instead of 'table' map
+		default: false
+	*/
+	void SplitSingle(bool split);
+
+
+	/*
+		if true then empty values and lists, e.g:
+			option = 
+			option2 = ()
+		will be omitted (not inserted to 'table' or 'table_single')
+		default: false	
+	*/
+	void SkipEmpty(bool skip);
+
+
+	/*
+		'\' character is used to escape other characters in a quoted string
+		so "some \t t\"ext" will produce "some t t"ext"
+		default: true
+	*/
+	void UseEscapeChar(bool escape);
+
+
+	/*
+		if true then the input file or string (char* or std::string) is treated as UTF-8
+	*/
+	void UTF8(bool utf);
+
+
+	/*
+
+		default: true
+	*/
+	void CreateTableAsSpace(bool create_table_as_space_);
+
+private:
+
+
+	/*
+		current space set by SetSpace();
+	*/
+	Space * root_space;
+
+
+	/*
+		a space in which we are now
+	*/
+	Space * space;
+
+
+	/*
+		true if Parse() method was called
+		false if ParseString() was called
+	*/
+	bool reading_from_file;
+
+
+	/*
+		pointers to the current character
+		if ParseString() is in used
+	*/
+	const char    * pchar_ascii;
+	const wchar_t * pchar_unicode;
+
+
+	/*
+		true if ParseString(wchar_t *) or ParseString(std::wstring&) was called
+	*/
+	bool reading_from_wchar_string;
+
+
+	/*
+		last read token
+	*/
+	std::wstring token;
+
+
+	/*
+		last read key
+	*/
+	std::wstring key;
+
+
+	/*
+		last read list
+	*/
+	Space::Value value;
+
+
+	/*
+		separator between a variable and a value, default: '='
+	*/
+	int separator;	
+
+
+	/*
+		space starting character, default: '{'
+	*/
+	int space_start;
+
+
+	/*
+		space ending character, default: '}'
+	*/
+	int space_end;
+
+
+	/*
+		table starting character, default: '['
+	*/
+	int table_start;
+
+
+	/*
+		table ending character, default: ']'
+	*/
+	int table_end;
+
+
+	/*
+		option delimiter, default: ','
+	*/
+	int option_delimiter;
+
+
+	/*
+		last read char
+		or -1 if the end
+	*/
+	int lastc;
+
+
+	/*
+		true if the lastc was escaped (with a backslash)
+		we have to know if the last sequence was \" or just "
+	*/
+	bool char_was_escaped;
+
+
+	/*
+		current file
+	*/
+	std::ifstream file;
+
+
+	/*
+		if true then lists with one item will be put into 'table_single' table
+		default: false
+	*/
+	bool split_single;
+
+
+	/*
+		if true then empty lists, e.g:
+			option = 
+			option2 = ()
+		will be omitted (not inserted to 'table' or 'table_single')
+		default: false	
+	*/
+	bool skip_empty;
+
+
+	/*
+		input file is in UTF-8
+		default: true
+	*/
+	bool input_as_utf8;
+
+
+	/*
+		if true you can use an escape character '\' in quoted values
+	*/
+	bool use_escape_char;
+
+
+	/*
+		if false we only allow the tables to consists of text items (numeric, boolean too)
+		objects are not allowed then
+		default: true
+	*/
+	bool create_table_as_space;
+
+
+	/*
+
+	*/
+	size_t current_nested_level;
+
+
+	/*
+
+		default: 1000;
+	*/
+	size_t max_nested_level;
+
+
+	std::string afile_name;
+
+	void Parse();
+	void ParseSpace(bool has_space_name, bool insert_new_space = true);
+	void ParseTextTable();
+	void ParseObjectsTable(bool has_key);
+	void ParseTable(bool has_key);
+	void ParseKeyValuePairs();
+
+	void SkipText();
+	void SkipObjectOrTable(int start_char, int end_char);
+	void SkipTable();
+	void SkipObject();
+
+	void SpaceEnds(bool skip_space_char = true);
+	void SpaceStarts(bool has_space_name, bool skip_space_char = true);
+
+	void DeleteFromTable(const std::wstring & var);
+	void DeleteFromTableSingle(const std::wstring & var);
+
+	void ReadTokenQuoted();
+	void ReadTokenSingle(bool white_delimit, bool new_line_delimit, int delimit1, int delimit2);
+	void ReadToken(bool white_delimit, bool new_line_delimit, int delimit1, int delimit2);
+	void ReadKey();
+	void ReadValue(bool skip_object_or_table = false,
+					bool add_space_for_text_value = false,
+					bool has_key = false,
+					bool auto_add_text_value = false);
+
+	void AddKeyValuePair();
+	int  ReadUTF8Char();
+	int  ReadASCIIChar();
+	int  ReadCharFromWcharString();
+	int  ReadCharFromUTF8String();
+	int  ReadCharFromAsciiString();
+	int  ReadCharNoEscape();
+	int  ReadChar();
+	bool IsWhite(int c);
+	void SkipWhite();
+	void Trim(std::wstring & s);
+	bool IsHexDigit(wchar_t c);
+	int  HexToInt(wchar_t c);
+	void ReadUnicodeCodePoint();
+
+};
+
+
+} // namespace
+
+
+#endif