pikotools/space/spaceparser.cpp

/*
 * This file is a part of PikoTools
 * and is distributed under the (new) BSD licence.
 * Author: Tomasz Sowa <t.sowa@ttmath.org>
 */

/* 
 * Copyright (c) 2008-2012, 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.
 */

#include <cstdlib>
#include <wchar.h>
#include "confparser.h"
#include "utf8/utf8.h"


namespace PT
{



SpaceParser::SpaceParser()
{
	root_space = 0;
	SetDefault();
}


void SpaceParser::SetSpace(Space * pspace)
{
	root_space = pspace;
}


void SpaceParser::SetSpace(Space & pspace)
{
	root_space = &pspace;
}


void SpaceParser::SetDefault()
{
	// you can change this separators to what you want
	// you shoud not use only white characters here (as expected by IsWhite() method)
	// and new line characters ('\n')
	separator       = '=';
	commentary      = '#';
	list_start      = '(';
	list_end        = ')';
	list_delimiter  = ',';
	split_single    = false;
	skip_empty      = false;
	use_escape_char = true;
	input_as_utf8   = false;
}


void SpaceParser::SplitSingle(bool split)
{
	split_single = split;
}


void SpaceParser::SkipEmpty(bool skip)
{
	skip_empty = skip;
}


void SpaceParser::UseEscapeChar(bool escape)
{
	use_escape_char = escape;
}


void SpaceParser::UTF8(bool utf)
{
	input_as_utf8 = utf;
}




SpaceParser::Status SpaceParser::Parse(const char * file_name)
{
	reading_from_file = true;

	file.clear();
	file.open( file_name );
	
	if( file )
	{
		Parse();
		file.close();
	}
	else
	{
		status = cant_open_file;
	}
	
return status;
}



SpaceParser::Status SpaceParser::Parse(const std::string & file_name)
{
	return Parse(file_name.c_str());
}




SpaceParser::Status SpaceParser::Parse(const wchar_t * file_name)
{
	PT::WideToUTF8(file_name, afile_name);
	return Parse(afile_name.c_str());
}



SpaceParser::Status SpaceParser::Parse(const std::wstring & file_name)
{
	return Parse(file_name.c_str());
}



SpaceParser::Status SpaceParser::ParseString(const char * str)
{
	reading_from_file         = false;
	reading_from_wchar_string = false;
	pchar_ascii               = str;
	pchar_unicode             = 0;

	Parse();

return status;
}


SpaceParser::Status SpaceParser::ParseString(const std::string & str)
{
	return ParseString(str.c_str());
}


SpaceParser::Status SpaceParser::ParseString(const wchar_t * str)
{
	reading_from_file         = false;
	reading_from_wchar_string = true;
	pchar_unicode             = str;
	pchar_ascii               = 0;

	Parse();

return status;
}


SpaceParser::Status SpaceParser::ParseString(const std::wstring & str)
{
	return ParseString(str.c_str());
}


void SpaceParser::Parse()
{
	if( !root_space )
	{
		status = no_space;
		return;
	}

	line   = 1;
	status = ok;
	space  = root_space;
	ReadChar();
	SkipWhiteLines();

	ParseLoop();

	if( status == ok && space != root_space )
	{
		// last closing a space characters ')' are missing
		status = syntax_error;
	}
}


void SpaceParser::ParseLoop()
{
	while( status == ok && lastc != -1 )
	{
		if( lastc == list_end )
		{
			SpaceEnds();
		}
		else
		{
			ReadVariable();

			if( lastc == list_start )
			{
				SpaceStarts();
			}
			else
			if( lastc == separator && !variable.empty() )
			{
				ReadAddValue();
			}
			else
			{
				status = syntax_error;
			}
		}

		if( status == ok )
			SkipWhiteLines();
	}
}


void SpaceParser::SpaceEnds()
{
	if( space == root_space )
	{
		// there cannot be a loose list end character in the global space
		status = syntax_error;
	}
	else
	{
		space = space->parent;
		ReadChar();
	}
}


void SpaceParser::SpaceStarts()
{
	Space * new_space = new Space();
	space->spaces.push_back(new_space);
	new_space->parent = space;
	new_space->name   = variable;
	space = new_space;

	ReadChar();
}


void SpaceParser::ReadAddValue()
{
	ReadChar(); // skipping separator '='

	if( ReadValue() )
	{
		AddOption();
	}
	else
	{
		status = syntax_error;
	}
}


bool SpaceParser::IsVariableChar(int c)
{
	if( (c>='a' && c<='z') ||
	    (c>='A' && c<='Z') ||
	    (c>='0' && c<='9') ||
	    c=='.' || c==',' || c=='_' )
		return true;
	
return false;
}


bool SpaceParser::IsWhite(int c)
{
	// dont use '\n' here
	// 13 (\r) is at the end of a line in a dos file \r\n
	// 160 is an unbreakable space
	if( c==' ' || c=='\t' || c==13 || c==160 )
		return true;
		
return false;	
}



void SpaceParser::SkipWhite()
{
	while( IsWhite(lastc) || lastc == commentary )
	{
		if( lastc == commentary )
			SkipLine();
		else
			ReadChar();
	}
}


void SpaceParser::SkipWhiteLines()
{
	while( IsWhite(lastc) || lastc == commentary || lastc=='\n' )
	{
		if( lastc == commentary )
			SkipLine();
		else
			ReadChar();
	}
}


void SpaceParser::SkipLine()
{
	while( lastc != -1 && lastc != '\n' )
		ReadChar();	
}



void SpaceParser::Trim(std::wstring & s)
{
std::wstring::size_type i;
	
	if( s.empty() )
		return;
	
	// looking for white characters at the end
	for(i=s.size()-1 ; i>0 && IsWhite(s[i]) ; --i);
	
	if( i==0 && IsWhite(s[i]) )
	{
		// the whole string has white characters
		s.clear();
		return;
	}
	
	// deleting white characters at the end
	if( i != s.size() - 1 )
		s.erase(i+1, std::wstring::npos);
	
	// looking for white characters at the beginning
	for(i=0 ; i<s.size() && IsWhite(s[i]) ; ++i);
	
	// deleting white characters at the beginning
	if( i != 0 )
		s.erase(0, i);
}





void SpaceParser::AddOption()
{
	if( value.empty() && skip_empty )
	{
		DeleteFromTable(variable);
		DeleteFromTableSingle(variable);
		return;
	}

	if( split_single && value.size() == 1 )
	{
		space->table_single[variable] = value[0];
		DeleteFromTable(variable);
	}
	else
	{
		space->table[variable] = value;
		DeleteFromTableSingle(variable);
	}
}



void SpaceParser::DeleteFromTable(const std::wstring & var)
{
	Space::Table::iterator i = space->table.find(var);

	if( i != space->table.end() )
		space->table.erase(i);
}



void SpaceParser::DeleteFromTableSingle(const std::wstring & var)
{
	Space::TableSingle::iterator i = space->table_single.find(var);

	if( i != space->table_single.end() )
		space->table_single.erase(i);
}



void SpaceParser::ReadVariable()
{
	variable.clear();
	SkipWhite();
	
	while( IsVariableChar(lastc) )
	{
		variable += lastc;
		ReadChar();
	}

	SkipWhite();
}



bool SpaceParser::ReadValue()
{
	value.clear();
	SkipWhite();

	if( lastc == list_start )
		return ReadValueList();
	else
		return ReadValueNoList();
}



bool SpaceParser::ReadValueList()
{
	ReadChar();			// skipping first list character '('
	SkipWhiteLines();	// lists can be split into several lines

	while( lastc != -1 && lastc != list_end )
	{
		if( !ReadValueNoList(true) )
			return false;

		if( lastc == list_delimiter )
			ReadChar();

		SkipWhiteLines();
	}

	if( lastc != list_end )
		return false;

	ReadChar();		// skipping last list character ')'
	SkipWhite();

return true;
}



bool SpaceParser::ReadValueNoList(bool use_list_delimiter)
{
bool res;

	value_item.clear();

	if( lastc == '"' )
	{
		res = ReadValueQuoted(); // quoted value

		if( res )
			value.push_back(value_item);
	}
	else
	{
		res = ReadValueSimple(use_list_delimiter);

		if( res && !value_item.empty() )
			value.push_back(value_item);
	}

return res;
}



bool SpaceParser::ReadValueQuoted()
{
	ReadChar();		// skipping the first quote
	
	// !! IMPROVE ME
	// add some other escaped characters especialy \0 (the serializator is working that way now)

	while( lastc != '"' && lastc != -1 )
	{
		if( use_escape_char && lastc == '\\' )
			ReadChar();
		
		value_item += lastc;
		ReadChar();
	}
	
	if( lastc != '"' )
		return false;
		
	ReadChar();		// skipping the last quote
	SkipWhite();
	
return true;
}



bool SpaceParser::ReadValueSimple(bool use_list_delimiter)
{
	int list_delimiter1 = -1;
	int list_delimiter2 = -1;

	if( use_list_delimiter )
		list_delimiter1 = list_delimiter;

	if( use_list_delimiter || space != root_space )
		list_delimiter2 = list_end;

	while(	lastc!=-1 && lastc!='\n' && lastc!=commentary &&
			lastc!=list_delimiter1 && lastc!=list_delimiter2 )
	{
		value_item += lastc;
		ReadChar();
	}
	
	Trim(value_item);
	SkipWhite();
	
return true;	
}


int SpaceParser::ReadUTF8Char()
{
int c;
bool correct;

	lastc = -1;

	do
	{
		PT::UTF8ToInt(file, c, correct);

		if( !file )
			return lastc;
	}
	while( !correct );

	lastc = c;

	if( lastc == '\n' )
		++line;
	
return lastc;
}



int SpaceParser::ReadASCIIChar()
{
	lastc = file.get();

	if( lastc == '\n' )
		++line;
	
return lastc;
}




int SpaceParser::ReadCharFromWcharString()
{
	if( *pchar_unicode == 0 )
		lastc = -1;
	else
		lastc = *(pchar_unicode++);

	if( lastc == '\n' )
		++line;

return lastc;
}


int SpaceParser::ReadCharFromUTF8String()
{
int c;
bool correct;

	lastc = -1;

	do
	{
		size_t len = PT::UTF8ToInt(pchar_ascii, c, correct);
		pchar_ascii += len;

		if( *pchar_ascii == 0 )
			return lastc;
	}
	while( !correct );

	lastc = c;

	if( lastc == '\n' )
		++line;
	
return lastc;
	
}


int SpaceParser::ReadCharFromAsciiString()
{
	if( *pchar_ascii == 0 )
		lastc = -1;
	else
		lastc = *(pchar_ascii++);

	if( lastc == '\n' )
		++line;

return lastc;
}


int SpaceParser::ReadChar()
{
	if( reading_from_file )
	{
		if( input_as_utf8 )
			return ReadUTF8Char();
		else
			return ReadASCIIChar();
	}
	else
	{
		if( reading_from_wchar_string )
		{
			return ReadCharFromWcharString();
		}
		else
		{
			if( input_as_utf8 )
				return ReadCharFromUTF8String();
			else
				return ReadCharFromAsciiString();
		}
	}
}



} // namespace