src/NullByteHandler.h
author František Kučera <franta-hg@frantovo.cz>
Sat, 23 Apr 2022 11:52:41 +0200
branchv_0
changeset 25 58de33c1af03
parent 24 d698d34baf9b
permissions -rw-r--r--
do not stop at null byte 0x00; replace them with configurable string (default '^@')
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     1
/**
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     2
 * Relational pipes
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     3
 * Copyright © 2018 František Kučera (Frantovo.cz, GlobalCode.info)
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     4
 *
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     5
 * This program is free software: you can redistribute it and/or modify
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     6
 * it under the terms of the GNU General Public License as published by
15
638f581903d0 fix license version: GNU GPLv3
František Kučera <franta-hg@frantovo.cz>
parents: 11
diff changeset
     7
 * the Free Software Foundation, version 3 of the License.
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     8
 *
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     9
 * This program is distributed in the hope that it will be useful,
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    10
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    11
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    12
 * GNU General Public License for more details.
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    13
 *
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    14
 * You should have received a copy of the GNU General Public License
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    15
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    16
 */
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    17
#pragma once
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    18
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    19
#include <memory>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    20
#include <string>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    21
#include <vector>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    22
#include <iostream>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    23
#include <sstream>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    24
#include <locale>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    25
#include <codecvt>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    26
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    27
#include <relpipe/reader/typedefs.h>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    28
#include <relpipe/reader/TypeId.h>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    29
#include <relpipe/reader/handlers/RelationalReaderStringHandler.h>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    30
#include <relpipe/reader/handlers/AttributeMetadata.h>
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    31
25
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    32
#include "Configuration.h"
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    33
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    34
namespace relpipe {
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    35
namespace out {
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    36
namespace nullbyte {
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    37
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    38
using namespace relpipe;
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    39
using namespace relpipe::reader;
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    40
using namespace relpipe::reader::handlers;
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    41
11
7c92942ac1e8 fix typo: Hadler → Handler
František Kučera <franta-hg@frantovo.cz>
parents: 4
diff changeset
    42
class NullByteHandler : public RelationalReaderStringHandler {
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    43
private:
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    44
	std::ostream& output;
25
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    45
	std::wstring_convert<std::codecvt_utf8<wchar_t>> convertor; // TODO: support also other encodings?
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    46
	Configuration configuration;
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    47
	std::string nullByteReplacement;
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    48
public:
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    49
25
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    50
	NullByteHandler(Configuration configuration, std::ostream& output) : configuration(configuration), output(output), nullByteReplacement(convertor.to_bytes(configuration.nullByteReplacement)) {
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    51
	}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    52
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    53
	void startRelation(string_t name, std::vector<AttributeMetadata> attributes) override {
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    54
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    55
	}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    56
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    57
	void attribute(const string_t& value) override {
23
b717a552e63f do not stop at null byte 0x00; replace them with '@' I
František Kučera <franta-hg@frantovo.cz>
parents: 15
diff changeset
    58
		const std::string octets = convertor.to_bytes(value);
24
d698d34baf9b do not stop at null byte 0x00; replace them with '@' II
František Kučera <franta-hg@frantovo.cz>
parents: 23
diff changeset
    59
		for (char ch : octets) {
d698d34baf9b do not stop at null byte 0x00; replace them with '@' II
František Kučera <franta-hg@frantovo.cz>
parents: 23
diff changeset
    60
			if (ch) output.put(ch);
25
58de33c1af03 do not stop at null byte 0x00; replace them with configurable string (default '^@')
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    61
			else output << nullByteReplacement;
24
d698d34baf9b do not stop at null byte 0x00; replace them with '@' II
František Kučera <franta-hg@frantovo.cz>
parents: 23
diff changeset
    62
		}
4
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    63
		output.put(0);
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    64
	}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    65
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    66
	void endOfPipe() {
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    67
		output.flush();
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    68
	}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    69
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    70
};
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    71
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    72
}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    73
}
12ffbdbb3574 NullByteHandler: produces \0-separated values
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    74
}