src/lib/BackspaceUnescapingProcessor.h
author František Kučera <franta-hg@frantovo.cz>
Sat, 28 Nov 2020 21:09:18 +0100
branchv_0
changeset 29 06aaad12c207
parent 28 0e7c57d48d1e
permissions -rw-r--r--
configurable dialects: in separate classes
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
26
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     1
/**
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     2
 * Relational pipes
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     3
 * Copyright © 2020 František Kučera (Frantovo.cz, GlobalCode.info)
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     4
 *
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     5
 * This program is free software: you can redistribute it and/or modify
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     6
 * it under the terms of the GNU General Public License as published by
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     7
 * the Free Software Foundation, version 3 of the License.
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     8
 *
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     9
 * This program is distributed in the hope that it will be useful,
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    10
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    11
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    12
 * GNU General Public License for more details.
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    13
 *
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    14
 * You should have received a copy of the GNU General Public License
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    15
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    16
 */
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    17
#pragma once
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    18
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    19
#include <sstream>
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    20
28
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    21
#include "UnescapingProcessor.h"
26
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    22
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    23
using namespace std;
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    24
using namespace relpipe::writer;
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    25
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    26
namespace relpipe {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    27
namespace in {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    28
namespace ini {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    29
namespace lib {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    30
28
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    31
class BackspaceUnescapingProcessor : public UnescapingProcessor {
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    32
private:
29
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    33
	/**
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    34
	 * By default it is set to true, thus no unrecognized escape sequences may left after this stage.
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    35
	 * Setting this to false is dangerous and may lead to errors and ambiguous behavior.
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    36
	 * It should be used only as a last resort.
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    37
	 * Because both "\\ \xxx" and "\ \xxx" will be converted to "\ \xxx" and the information will be lost.
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    38
	 * So, it is usually better to keep the "\" escaped as "\\" and process both the escaped backspaces and unrecognized escape sequences later.
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    39
	 */
06aaad12c207 configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents: 28
diff changeset
    40
28
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    41
	const bool lastEscaphingPhase = true;
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    42
public:
26
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    43
28
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    44
	std::string unescape(const std::string& s, const TextType type) override {
26
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    45
		std::stringstream result;
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    46
		for (int i = 0, length = s.size(); i < length; i++) {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    47
			char ch = s[i];
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    48
			if (i + 1 < length && ch == ESC) {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    49
				ch = s[i + 1];
28
0e7c57d48d1e configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents: 26
diff changeset
    50
				if (ch == ESC) put(result, ESC, i); // unescape \\ to \.
26
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    51
				else if (lastEscaphingPhase) throw std::logic_error(std::string("Unsupported escape sequence: ") + ch);
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    52
				else result.put(ESC); // keep the escape sequence for later unescaping phase
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    53
			} else if (ch == ESC) {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    54
				throw std::logic_error(std::string("Missing escape sequence")); // this should not happen
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    55
			} else {
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    56
				result.put(ch);
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    57
			}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    58
		}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    59
		return result.str();
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    60
	}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    61
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    62
};
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    63
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    64
}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    65
}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    66
}
80e129ec3408 new INI parser
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    67
}