added a base class for parsers: BaseParser (convert/baseparser.h|cpp)

there are methods for reading from string/files there
  those methods were moved from SpaceParser and CSVParser
fixed: CSVParser didn't set input_as_utf8 flag
htmlparserlistener
Tomasz Sowa 2 years ago
parent 2a3f43c5c3
commit 7ce07c57f5

@ -8,6 +8,9 @@
./convert/double.o: convert/inttostr.h utf8/utf8.h textstream/stream.h
./convert/double.o: utf8/utf8_templates.h utf8/utf8_private.h date/date.h
./convert/double.o: membuffer/membuffer.h textstream/types.h
./convert/baseparser.o: ./convert/baseparser.h utf8/utf8.h
./convert/baseparser.o: textstream/stream.h utf8/utf8_templates.h
./convert/baseparser.o: utf8/utf8_private.h
./date/date.o: ./date/date.h convert/inttostr.h
./log/filelog.o: ./log/filelog.h textstream/textstream.h textstream/stream.h
./log/filelog.o: space/space.h textstream/types.h convert/inttostr.h
@ -29,14 +32,15 @@
./space/spaceparser.o: ./space/spaceparser.h ./space/space.h
./space/spaceparser.o: textstream/types.h convert/inttostr.h utf8/utf8.h
./space/spaceparser.o: textstream/stream.h utf8/utf8_templates.h
./space/spaceparser.o: utf8/utf8_private.h convert/strtoint.h
./space/spaceparser.o: ./convert/text.h ./convert/misc.h
./space/spaceparser.o: utf8/utf8_private.h convert/baseparser.h
./space/spaceparser.o: convert/strtoint.h ./convert/text.h ./convert/misc.h
./utf8/utf8.o: ./utf8/utf8.h textstream/stream.h utf8/utf8_templates.h
./utf8/utf8.o: utf8/utf8_private.h
./utf8/utf8_private.o: utf8/utf8_private.h
./csv/csvparser.o: ./csv/csvparser.h space/space.h textstream/types.h
./csv/csvparser.o: convert/inttostr.h utf8/utf8.h textstream/stream.h
./csv/csvparser.o: utf8/utf8_templates.h utf8/utf8_private.h
./csv/csvparser.o: convert/baseparser.h
./mainoptions/mainoptionsparser.o: ./mainoptions/mainoptionsparser.h
./mainoptions/mainoptionsparser.o: space/space.h textstream/types.h
./mainoptions/mainoptionsparser.o: convert/inttostr.h utf8/utf8.h

@ -0,0 +1,188 @@
/*
* This file is a part of PikoTools
* and is distributed under the (new) BSD licence.
* Author: Tomasz Sowa <t.sowa@ttmath.org>
*/
/*
* Copyright (c) 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.
*/
#include "baseparser.h"
#include "utf8/utf8.h"
namespace pt
{
BaseParser::BaseParser()
{
clear();
}
void BaseParser::clear()
{
line = 0;
reading_from_file = false;
pchar_ascii = nullptr;
pchar_unicode = nullptr;
reading_from_wchar_string = false;
lastc = -1;
input_as_utf8 = true;
}
int BaseParser::read_utf8_char()
{
int c;
bool correct;
lastc = -1;
do
{
utf8_to_int(file, c, correct);
if( !file )
return lastc;
}
while( !correct );
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int BaseParser::read_ascii_char()
{
lastc = file.get();
if( lastc == '\n' )
++line;
return lastc;
}
int BaseParser::read_char_from_wchar_string()
{
if( *pchar_unicode == 0 )
lastc = -1;
else
lastc = *(pchar_unicode++);
if( lastc == '\n' )
++line;
return lastc;
}
int BaseParser::read_char_from_utf8_string()
{
int c;
bool correct;
lastc = -1;
do
{
size_t len = utf8_to_int(pchar_ascii, c, correct);
pchar_ascii += len;
}
while( *pchar_ascii && !correct );
if( correct )
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int BaseParser::read_char_from_ascii_string()
{
if( *pchar_ascii == 0 )
lastc = -1;
else
lastc = *(pchar_ascii++);
if( lastc == '\n' )
++line;
return lastc;
}
int BaseParser::read_char_no_escape()
{
if( reading_from_file )
{
if( input_as_utf8 )
return read_utf8_char();
else
return read_ascii_char();
}
else
{
if( reading_from_wchar_string )
{
return read_char_from_wchar_string();
}
else
{
if( input_as_utf8 )
return read_char_from_utf8_string();
else
return read_char_from_ascii_string();
}
}
}
int BaseParser::read_char()
{
return read_char_no_escape();
}
}

@ -0,0 +1,120 @@
/*
* This file is a part of PikoTools
* and is distributed under the (new) BSD licence.
* Author: Tomasz Sowa <t.sowa@ttmath.org>
*/
/*
* Copyright (c) 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_convert_baseparser
#define headerfile_picotools_convert_baseparser
#include <string>
#include <fstream>
namespace pt
{
class BaseParser
{
protected:
BaseParser();
void clear();
int read_utf8_char();
int read_ascii_char();
int read_char_from_wchar_string();
int read_char_from_utf8_string();
int read_char_from_ascii_string();
int read_char_no_escape();
int read_char();
/*
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 char
or -1 if the end
*/
int lastc;
/*
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;
/*
input file is in UTF-8
default: true
*/
bool input_as_utf8;
};
}
#endif

@ -44,6 +44,11 @@ namespace pt
{
CSVParser::CSVParser()
{
input_as_utf8 = true;
}
CSVParser::Status CSVParser::parse_file(const char * file_name, Space & out_space)
@ -285,132 +290,6 @@ bool CSVParser::read_non_quoted_value_to(std::wstring & value)
int CSVParser::read_utf8_char()
{
int c;
bool correct;
lastc = -1;
do
{
utf8_to_int(file, c, correct);
if( !file )
return lastc;
}
while( !correct );
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int CSVParser::read_ascii_char()
{
lastc = file.get();
if( lastc == '\n' )
++line;
return lastc;
}
int CSVParser::read_char_from_wchar_string()
{
if( *pchar_unicode == 0 )
lastc = -1;
else
lastc = *(pchar_unicode++);
if( lastc == '\n' )
++line;
return lastc;
}
int CSVParser::read_char_from_utf8_string()
{
int c;
bool correct;
lastc = -1;
do
{
size_t len = utf8_to_int(pchar_ascii, c, correct);
pchar_ascii += len;
}
while( *pchar_ascii && !correct );
if( correct )
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int CSVParser::read_char_from_ascii_string()
{
if( *pchar_ascii == 0 )
lastc = -1;
else
lastc = *(pchar_ascii++);
if( lastc == '\n' )
++line;
return lastc;
}
int CSVParser::read_char_no_escape()
{
if( reading_from_file )
{
if( input_as_utf8 )
return read_utf8_char();
else
return read_ascii_char();
}
else
{
if( reading_from_wchar_string )
{
return read_char_from_wchar_string();
}
else
{
if( input_as_utf8 )
return read_char_from_utf8_string();
else
return read_char_from_ascii_string();
}
}
}
int CSVParser::read_char()
{
return read_char_no_escape();
}
}

@ -38,9 +38,11 @@
#ifndef headerfile_picotools_csv_csvparser
#define headerfile_picotools_csv_csvparser
#include "space/space.h"
#include <string>
#include <fstream>
#include "space/space.h"
#include "convert/baseparser.h"
namespace pt
@ -51,10 +53,12 @@ namespace pt
* https://datatracker.ietf.org/doc/html/rfc4180
*
*/
class CSVParser
class CSVParser : public BaseParser
{
public:
CSVParser();
enum Status
{
ok,
@ -85,53 +89,6 @@ protected:
Space * space;
/*
true if parse_file() method was called
false if parse() was called
*/
bool reading_from_file;
/*
true if parse(wchar_t *) or parse(std::wstring&) was called
*/
bool reading_from_wchar_string;
/*
pointers to the current character
if parse() is being used
*/
const char * pchar_ascii;
const wchar_t * pchar_unicode;
/*
last read char
or -1 if the end
*/
int lastc;
/*
a number of a line in which there is a syntax_error
*/
int line;
/*
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;
/*
input file is in UTF-8
default: true
*/
bool input_as_utf8;
void parse();
@ -142,19 +99,6 @@ protected:
bool read_non_quoted_value_to(std::wstring & value);
/*
* copied from SpaceParser
* may it would be better to have a class with those methods and inherit from it?
*/
int read_utf8_char();
int read_ascii_char();
int read_char_from_wchar_string();
int read_char_from_utf8_string();
int read_char_from_ascii_string();
int read_char_no_escape();
int read_char();
};
}

@ -891,122 +891,6 @@ void SpaceParser::read_key()
int SpaceParser::read_utf8_char()
{
int c;
bool correct;
lastc = -1;
do
{
utf8_to_int(file, c, correct);
if( !file )
return lastc;
}
while( !correct );
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int SpaceParser::read_ascii_char()
{
lastc = file.get();
if( lastc == '\n' )
++line;
return lastc;
}
int SpaceParser::read_char_from_wchar_string()
{
if( *pchar_unicode == 0 )
lastc = -1;
else
lastc = *(pchar_unicode++);
if( lastc == '\n' )
++line;
return lastc;
}
int SpaceParser::read_char_from_utf8_string()
{
int c;
bool correct;
lastc = -1;
do
{
size_t len = utf8_to_int(pchar_ascii, c, correct);
pchar_ascii += len;
}
while( *pchar_ascii && !correct );
if( correct )
lastc = c;
if( lastc == '\n' )
++line;
return lastc;
}
int SpaceParser::read_char_from_ascii_string()
{
if( *pchar_ascii == 0 )
lastc = -1;
else
lastc = *(pchar_ascii++);
if( lastc == '\n' )
++line;
return lastc;
}
int SpaceParser::read_char_no_escape()
{
if( reading_from_file )
{
if( input_as_utf8 )
return read_utf8_char();
else
return read_ascii_char();
}
else
{
if( reading_from_wchar_string )
{
return read_char_from_wchar_string();
}
else
{
if( input_as_utf8 )
return read_char_from_utf8_string();
else
return read_char_from_ascii_string();
}
}
}
bool SpaceParser::is_hex_digit(wchar_t c)
{

@ -40,6 +40,7 @@
#include <fstream>
#include "space.h"
#include "convert/baseparser.h"
@ -49,7 +50,7 @@ namespace pt
class SpaceParser
class SpaceParser : public BaseParser
{
public:
@ -154,32 +155,6 @@ private:
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
*/
@ -222,13 +197,6 @@ private:
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 "
@ -236,22 +204,6 @@ private:
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;
/*
input file is in UTF-8
default: true
*/
bool input_as_utf8;
/*
* if parsing_space is false then it means we are parsing JSON format
*
@ -287,12 +239,6 @@ private:
void read_token_quoted(std::wstring & token);
void read_multiline_token_quoted(std::wstring & token);
int read_utf8_char();
int read_ascii_char();
int read_char_from_wchar_string();
int read_char_from_utf8_string();
int read_char_from_ascii_string();
int read_char_no_escape();
int read_char();
bool is_white(int c);
void skip_line();

@ -13,7 +13,8 @@
./csvparser.o: csvparser.h ../src/csv/csvparser.h ../src/space/space.h
./csvparser.o: ../src/textstream/types.h ../src/convert/inttostr.h
./csvparser.o: ../src/utf8/utf8.h ../src/textstream/stream.h
./csvparser.o: ../src/utf8/utf8_templates.h ../src/utf8/utf8_private.h test.h
./csvparser.o: ../src/utf8/utf8_templates.h ../src/utf8/utf8_private.h
./csvparser.o: ../src/convert/baseparser.h test.h
./main.o: convert.h mainoptionsparser.h csvparser.h
./test.o: test.h
./mainoptionsparser.o: mainoptionsparser.h test.h

Loading…
Cancel
Save