moved all directories to src subdirectory

src/space/spaceparser.h

@@ -0,0 +1,376 @@
+/*
+ * This file is a part of PikoTools
+ * and is distributed under the (new) BSD licence.
+ * Author: Tomasz Sowa <t.sowa@ttmath.org>
+ */
+
+/* 
+ * Copyright (c) 2012-2021, 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 SpaceParser
+{
+public:
+
+
+	/*
+		ctor -- setting default values (SetDefault() method)
+	*/
+	SpaceParser();
+
+
+	/*
+		setting the root space
+	*/
+	void SetSpace(Space * pspace);
+	void SetSpace(Space & pspace);
+
+
+	/*
+		setting options of the parser to the default values 
+		utf8 etc.
+	*/
+	void SetDefault();
+
+
+	/*
+		status of parsing
+	*/
+	enum Status { ok, cant_open_file, syntax_error, no_space };
+
+
+	/*
+		the last status of parsing, set by Parse() methods
+	*/
+	Status status;
+
+
+
+
+	/*
+		how many objects were skipped
+		used in parsing tables when create_table_as_space is false
+	*/
+	size_t skipped;
+
+
+	/*
+		main methods used to parse a JSON file
+		file_name is the path to a file
+	*/
+	Status ParseJSONFile(const char * file_name);
+	Status ParseJSONFile(const std::string & file_name);
+	Status ParseJSONFile(const wchar_t * file_name);
+	Status ParseJSONFile(const std::wstring & file_name);
+
+
+	/*
+		main methods used to parse a Space file
+		file_name is the path to a file
+	*/
+	Status ParseSpaceFile(const char * file_name);
+	Status ParseSpaceFile(const std::string & file_name);
+	Status ParseSpaceFile(const wchar_t * file_name);
+	Status ParseSpaceFile(const std::wstring & file_name);
+
+
+	/*
+		main methods used to parse
+		str - input string (either 8bit ascii or UTF-8 -- see UTF8() method)
+	*/
+	Status ParseJSON(const char * str);
+	Status ParseJSON(const std::string & str);
+
+	/*
+		main methods used to parse
+		here input string is always in unicode (wide characters)
+	*/
+	Status ParseJSON(const wchar_t * str);
+	Status ParseJSON(const std::wstring & str);
+
+
+
+	Status ParseSpace(const char * str);
+	Status ParseSpace(const std::string & str);
+	Status ParseSpace(const wchar_t * str);
+	Status ParseSpace(const std::wstring & str);
+
+
+
+	/*
+	 * add two args Parse method
+	 * Status Parse(const char * str, Space & output_space);
+	 *
+	 */
+
+
+	/*
+		if true then empty values and lists, e.g:
+			option = 
+			option2 = ()
+		will be omitted (not inserted to 'table')
+		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
+		default true
+
+		the internal storage for strings is std::wstring so if you call UTF8(false) then
+		the characters of input string will be simple static_cast<> from char to wchar_t
+	*/
+	// rename to use_utf8(bool)
+	void UTF8(bool utf);
+
+
+	/*
+	 *
+	 * returns a number of a last parsed line
+	 * can be used to obtain the line in which there was a syntax error
+	 *
+	 */
+	int get_last_parsed_line();
+
+
+private:
+
+
+	/*
+		current space set by SetSpace();
+	*/
+	Space * root_space;
+
+
+	/*
+		a number of a line in which there is a syntax_error
+	*/
+	int line;
+
+	/*
+		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;
+
+
+	/*
+		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
+
+		may it would be better to make a pointer?
+		if we parse only a string then there is no sense to have such an object
+	*/
+	std::ifstream file;
+
+
+	/*
+		if true then empty lists, e.g:
+			option = 
+			option2 = ()
+		will be omitted (not inserted to 'table')
+		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 parsing_space is false then it means we are parsing JSON format
+	 *
+	 *
+	 */
+	bool parsing_space;
+
+
+
+	// new
+	void ParseRootSpace();
+	void Parse(Space * space, bool is_object_value, bool is_table_value);
+	void ParseSpace(Space * space);
+	void ParseTable(Space * space);
+
+	void ParseKeyValuePairs(Space * space);
+	void ParseValuesList(Space * space);
+
+	void ReadKey();
+
+	void ParseTextValue(Space * space);
+	void ParseIntegerValue(Space * space);
+	void ParseFloatingPointValue(Space * space);
+
+
+	bool is_alfa_numeric_char(int c);
+
+	void ReadTokenUntilDelimiter(std::wstring & token, int delimiter1, int delimiter2);
+	void ReadAlfaNumericToken(std::wstring & token);
+	void ReadStringValue(std::wstring & token, bool is_object_value, bool is_table_value);
+
+
+	bool is_integer_token();
+	bool is_floating_point_token();
+
+	void ReadSpaceFieldToken(std::wstring & token);
+	void ReadTokenQuoted(std::wstring & token);
+	void ReadMultilineTokenQuoted(std::wstring & token);
+
+
+
+	int  ReadUTF8Char();
+	int  ReadASCIIChar();
+	int  ReadCharFromWcharString();
+	int  ReadCharFromUTF8String();
+	int  ReadCharFromAsciiString();
+	int  ReadCharNoEscape();
+	int  ReadChar();
+	bool IsWhite(int c);
+	void SkipLine();
+	void SkipWhite();
+	void TrimLastWhite(std::wstring & s);
+	//void Trim(std::wstring & s);
+	bool IsHexDigit(wchar_t c);
+	int  HexToInt(wchar_t c);
+	void ReadUnicodeCodePoint();
+
+};
+
+
+
+
+} // namespace
+
+
+#endif