src/AttributeFinder.h
author František Kučera <franta-hg@frantovo.cz>
Sun, 25 Apr 2021 18:47:57 +0200
branchv_0
changeset 89 25a11859975b
parent 32 bccda5688d71
permissions -rw-r--r--
streamlet examples: QR: rename qr to qr-decode + simplify Makefile
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     1
/**
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     2
 * Relational pipes
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     3
 * Copyright © 2019 František Kučera (Frantovo.cz, GlobalCode.info)
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     4
 *
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     5
 * This program is free software: you can redistribute it and/or modify
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     6
 * it under the terms of the GNU General Public License as published by
24
4353cd19a6b5 fix license version: GNU GPLv3
František Kučera <franta-hg@frantovo.cz>
parents: 9
diff changeset
     7
 * the Free Software Foundation, version 3 of the License.
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     8
 *
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
     9
 * This program is distributed in the hope that it will be useful,
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    10
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    11
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    12
 * GNU General Public License for more details.
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    13
 *
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    14
 * You should have received a copy of the GNU General Public License
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    15
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    16
 */
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    17
#pragma once
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    18
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    19
#include <vector>
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    20
#include <filesystem>
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    21
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    22
#include <relpipe/writer/typedefs.h>
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    23
#include <relpipe/writer/AttributeMetadata.h>
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    24
#include <relpipe/writer/RelationalWriter.h>
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    25
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    26
#include "RequestedField.h"
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    27
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    28
namespace relpipe {
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    29
namespace in {
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    30
namespace filesystem {
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    31
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    32
namespace fs = std::filesystem;
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    33
using namespace relpipe::writer;
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    34
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    35
class AttributeFinder {
8
eb1ecb37c6b7 interpret empty string as current directory (e.g. result of: find -printf '%P\0')
František Kučera <franta-hg@frantovo.cz>
parents: 4
diff changeset
    36
protected:
eb1ecb37c6b7 interpret empty string as current directory (e.g. result of: find -printf '%P\0')
František Kučera <franta-hg@frantovo.cz>
parents: 4
diff changeset
    37
	fs::path currentFile;
eb1ecb37c6b7 interpret empty string as current directory (e.g. result of: find -printf '%P\0')
František Kučera <franta-hg@frantovo.cz>
parents: 4
diff changeset
    38
	string currentFileRaw;
9
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    39
	bool currentFileExists;
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    40
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    41
	/**
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    42
	 * Writes field attribute(s). The attribute count must match with count of AttributeMetadata returned in toMetadata().
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    43
	 * @param writer
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    44
	 * @param field
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    45
	 */
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    46
	virtual void writeFieldOfExistingFile(RelationalWriter* writer, const string_t& relationName, const RequestedField& field) = 0;
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    47
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    48
	/**
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    49
	 * Writes empty attribute(s) in case of non-existent file or an error. 
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    50
	 * The attribute count must match with count of AttributeMetadata returned in toMetadata().
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    51
	 * @param writer
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    52
	 * @param field
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    53
	 */
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    54
	virtual void writeEmptyField(RelationalWriter* writer, const string_t& relationName, const RequestedField& field) {
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    55
		// TODO: better handling of null values (when null values are supported by the format specification)
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    56
		for (AttributeMetadata m : toMetadata(writer, relationName, field)) {
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    57
			switch (m.typeId) {
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    58
				case TypeId::BOOLEAN:
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    59
					writer->writeAttribute(L"false");
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    60
					break;
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    61
				case TypeId::INTEGER:
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    62
					writer->writeAttribute(L"0");
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    63
					break;
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    64
				case TypeId::STRING:
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    65
					writer->writeAttribute(L"");
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    66
					break;
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    67
				default:
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    68
					throw RelpipeWriterException(L"Unsupported attribute type in writeEmptyField().");
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    69
			}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    70
		}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    71
	}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
    72
9
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    73
public:
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    74
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    75
	/**
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    76
	 * Single requested fields might generate multiple attributes in the relation.
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    77
	 * But usually it is 1:1.
29
6f15f18d2abf field group --exec, replaces --script and --hash, starts reusable sub-program that returns set of attributes for all records during its runtime
František Kučera <franta-hg@frantovo.cz>
parents: 24
diff changeset
    78
	 * @param writer can be used for TypeId coversion from string_t
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    79
	 * @param relationName default one or set by the user
9
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    80
	 * @param field requested field from the user (usually from CLI arguments)
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    81
	 * @return attribute metadata to be used in the RelationalWriter.startRelation()
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    82
	 */
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    83
	virtual vector<AttributeMetadata> toMetadata(RelationalWriter* writer, const string_t& relationName, const RequestedField& field) = 0;
9
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    84
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    85
	/**
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    86
	 * Writing of the record for current file is starting.
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    87
	 * Following writeField() calls are related to this file.
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    88
	 * @param file path to the file
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    89
	 * @param fileRaw raw file name as it was on the input
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    90
	 */
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    91
	virtual void startFile(const fs::path& file, const string& fileRaw, bool exists) {
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    92
		currentFile = file;
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    93
		currentFileRaw = fileRaw;
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    94
		currentFileExists = exists;
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    95
	}
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
    96
32
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    97
	virtual void writeField(RelationalWriter* writer, const string_t& relationName, const RequestedField& field) {
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    98
		if (currentFileExists) writeFieldOfExistingFile(writer, relationName, field);
bccda5688d71 propagate the relation name to the finders and streamlets
František Kučera <franta-hg@frantovo.cz>
parents: 29
diff changeset
    99
		else writeEmptyField(writer, relationName, field);
9
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   100
	}
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   101
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   102
	/**
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   103
	 * Writing of the record for current file is finished. All resources linked to this file should be released.
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   104
	 */
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   105
	virtual void endFile() {
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   106
		currentFile.clear();
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   107
		currentFileRaw.clear();
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   108
	}
b4f29fb16159 process also links to non-existent files and non-readable links
František Kučera <franta-hg@frantovo.cz>
parents: 8
diff changeset
   109
4
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   110
	virtual ~AttributeFinder() {
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   111
	}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   112
};
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   113
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   114
}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   115
}
d44ed75822e7 modular design
František Kučera <franta-hg@frantovo.cz>
parents:
diff changeset
   116
}