removed: old SpaceParser

pull/4/head
Tomasz Sowa 2 years ago
parent 6e169f7650
commit 961a02ab39

@ -1,678 +0,0 @@
/*
* This file is a part of PikoTools
* and is distributed under the (new) BSD licence.
* Author: Tomasz Sowa <t.sowa@ttmath.org>
*/
/*
* Copyright (c) 2008-2017, 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 "spaceparser.h"
#include "utf8/utf8.h"
namespace PT
{
#ifdef nonexisting_value
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 = ',';
skip_empty = false;
use_escape_char = true;
input_as_utf8 = true;
}
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, std::ios_base::binary | std::ios_base::in);
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;
reading_commentary = false;
ReadChar();
SkipWhiteLines();
ParseLoop();
if( status == ok && space != root_space )
{
// last closing ')' characters are missing (closing a space)
status = syntax_error;
}
token.clear();
key.clear();
value.clear();
}
void SpaceParser::ParseLoop()
{
while( status == ok && lastc != -1 )
{
if( lastc == list_end )
{
SpaceEnds();
}
else
{
ReadKey();
SkipWhite();
if( lastc == list_start )
{
SpaceStarts();
}
else
if( lastc == separator )
{
ReadValue();
AddKeyValuePair();
}
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(); // skipping closing space character ')'
SkipWhite();
}
}
void SpaceParser::SpaceStarts()
{
Space * new_space = new Space();
space->spaces.push_back(new_space);
new_space->parent = space;
new_space->name = key;
space = new_space;
ReadChar(); // skipping space starts character ')'
}
/*
those white characters here should be the same as in space.h
*/
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;
}
/*
skip_lines is default false
*/
void SpaceParser::SkipWhite(bool skip_lines)
{
while( IsWhite(lastc) || lastc == commentary || (skip_lines && lastc=='\n'))
{
if( lastc == commentary )
SkipComment();
else
ReadChar();
}
}
void SpaceParser::SkipWhiteLines()
{
SkipWhite(true);
}
/*
do not skip the last \n character
*/
void SpaceParser::SkipLine()
{
while( lastc != -1 && lastc != '\n' )
ReadChar();
}
/*
do not skip the last \n character
*/
void SpaceParser::SkipComment()
{
reading_commentary = true;
SkipLine();
reading_commentary = false;
}
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::DeleteFromTable(const std::wstring & var)
{
Space::Table::iterator i = space->table.find(var);
if( i != space->table.end() )
space->table.erase(i);
}
void SpaceParser::ReadTokenQuoted()
{
ReadChar(); // skipping the first quotation mark
while( lastc != -1 && (char_was_escaped || lastc != '"') )
{
token += static_cast<wchar_t>(lastc);
ReadChar();
}
if( !char_was_escaped && lastc == '"' )
ReadChar(); // skipping the last quotation mark
else
status = syntax_error;
}
void SpaceParser::ReadTokenSingle(bool white_delimit, bool new_line_delimit, int delimit1, int delimit2)
{
while( true )
{
if( lastc == commentary )
SkipComment();
if( lastc == -1 ||
(!char_was_escaped &&
(
lastc == list_end ||
(white_delimit && IsWhite(lastc)) ||
(new_line_delimit && lastc == '\n') ||
(delimit1 != -1 && lastc == delimit1) ||
(delimit2 != -1 && lastc == delimit2)
) ) )
{
break;
}
token += static_cast<wchar_t>(lastc);
ReadChar();
}
Trim(token);
}
void SpaceParser::ReadToken(bool white_delimit, bool new_line_delimit, int delimit1, int delimit2)
{
token.clear();
SkipWhite();
if( !char_was_escaped && lastc == '"' )
ReadTokenQuoted();
else
ReadTokenSingle(white_delimit, new_line_delimit, delimit1, delimit2);
}
void SpaceParser::ReadKey()
{
ReadToken(false, true, separator, list_start);
key = token;
SkipWhite();
}
void SpaceParser::ReadValueList()
{
ReadChar(); // skipping the first list character ')'
SkipWhiteLines();
while( lastc != -1 && lastc != list_end )
{
ReadToken(true, true, list_delimiter, list_end);
value.push_back(token);
SkipWhiteLines();
if( lastc == list_delimiter )
{
ReadChar();
SkipWhiteLines();
}
}
if( lastc == list_end )
{
ReadChar(); // skipping the last list character ')'
SkipWhite();
}
else
{
status = syntax_error; // missing one ')'
}
}
void SpaceParser::ReadValueSingle()
{
SkipWhite();
ReadToken(false, true, -1, -1);
value.push_back(token);
SkipWhite();
}
void SpaceParser::ReadValue()
{
ReadChar(); // skipping separator '='
value.clear();
SkipWhite();
if( lastc == list_start )
ReadValueList();
else
ReadValueSingle();
SkipWhiteLines();
}
void SpaceParser::AddKeyValuePair()
{
if( value.empty() && skip_empty )
{
DeleteFromTable(key);
return;
}
space->table[key] = value;
}
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::ReadCharNoEscape()
{
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();
}
}
}
int SpaceParser::ReadChar()
{
char_was_escaped = false;
ReadCharNoEscape();
if( !reading_commentary && use_escape_char && lastc == '\\' )
{
char_was_escaped = true;
ReadCharNoEscape();
switch(lastc)
{
case '0': lastc = 0; break;
case 't': lastc = '\t'; break;
case 'r': lastc = '\r'; break;
case 'n': lastc = '\n'; break;
// in other cases we return the last character
}
}
return lastc;
}
#endif
} // namespace

@ -1,328 +0,0 @@
/*
* This file is a part of PikoTools
* and is distributed under the (new) BSD licence.
* Author: Tomasz Sowa <t.sowa@ttmath.org>
*/
/*
* Copyright (c) 2010-2017, 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_confparser_spaceparser
#define headerfile_picotools_confparser_spaceparser
#include <fstream>
#include "space.h"
namespace PT
{
#ifdef nonexisting_value
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;
/*
a number of a line in which there is a syntax_error
*/
int line;
/*
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 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
so "some \t t\"ext" will produce "some t t"ext"
default: true
special characters:
\0 - 0 (zero code point)
\t - tabulator (9 code point)
\r - carriage return (13 code point)
\n - a new line character (10 code point)
in other cases we return the last character so \Z gives Z and \\ gives one \
escape character are not used in commentaries
so you can write:
# this is my comment \n but this was not a new line
*/
void UseEscapeChar(bool escape);
/*
if true then the input file or string (char* or std::string) is treated as UTF-8
default: true
*/
void UTF8(bool utf);
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;
/*
commentary char, default: '#'
*/
int commentary;
/*
list starting character, default: '('
*/
int list_start;
/*
list ending character, default: ')'
*/
int list_end;
/*
list delimiter, default: ','
*/
int list_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 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;
/*
true if we are reading the commentary (#)
this is to avoid parsing escape characters in the commentary
*/
bool reading_commentary;
std::string afile_name;
void Parse();
void ParseLoop();
void SpaceEnds();
void SpaceStarts();
void DeleteFromTable(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 ReadValueList();
void ReadValueSingle();
void ReadValue();
void AddKeyValuePair();
int ReadUTF8Char();
int ReadASCIIChar();
int ReadCharFromWcharString();
int ReadCharFromUTF8String();
int ReadCharFromAsciiString();
int ReadCharNoEscape();
int ReadChar();
bool IsWhite(int c);
void SkipWhite(bool skip_lines = false);
void SkipWhiteLines();
void SkipLine();
void SkipComment();
void Trim(std::wstring & s);
};
#endif
} // namespace
#endif
Loading…
Cancel
Save