author | František Kučera <franta-hg@frantovo.cz> |
Tue, 30 Jul 2019 23:56:30 +0200 | |
branch | v_0 |
changeset 14 | 3b26c2918eae |
parent 8 | 14e14a5db027 |
child 15 | 177321664baf |
permissions | -rw-r--r-- |
0 | 1 |
/** |
2 |
* Relational pipes |
|
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
3 |
* Copyright © 2019 František Kučera (Frantovo.cz, GlobalCode.info) |
0 | 4 |
* |
5 |
* This program is free software: you can redistribute it and/or modify |
|
6 |
* it under the terms of the GNU General Public License as published by |
|
7 |
* the Free Software Foundation, either version 3 of the License, or |
|
8 |
* (at your option) any later version. |
|
9 |
* |
|
10 |
* This program is distributed in the hope that it will be useful, |
|
11 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
12 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
13 |
* GNU General Public License for more details. |
|
14 |
* |
|
15 |
* You should have received a copy of the GNU General Public License |
|
16 |
* along with this program. If not, see <http://www.gnu.org/licenses/>. |
|
17 |
*/ |
|
18 |
#pragma once |
|
19 |
||
20 |
#include <cstdlib> |
|
21 |
#include <iostream> |
|
22 |
#include <string> |
|
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
23 |
#include <sstream> |
0 | 24 |
#include <vector> |
25 |
#include <algorithm> |
|
26 |
||
1
9aed8c2ea97d
add Xerces-C++ dependency
František Kučera <franta-hg@frantovo.cz>
parents:
0
diff
changeset
|
27 |
#include <xercesc/sax2/SAX2XMLReader.hpp> |
9aed8c2ea97d
add Xerces-C++ dependency
František Kučera <franta-hg@frantovo.cz>
parents:
0
diff
changeset
|
28 |
#include <xercesc/sax2/XMLReaderFactory.hpp> |
9aed8c2ea97d
add Xerces-C++ dependency
František Kučera <franta-hg@frantovo.cz>
parents:
0
diff
changeset
|
29 |
#include <xercesc/sax2/DefaultHandler.hpp> |
5
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
30 |
#include <xercesc/sax2/Attributes.hpp> |
1
9aed8c2ea97d
add Xerces-C++ dependency
František Kučera <franta-hg@frantovo.cz>
parents:
0
diff
changeset
|
31 |
#include <xercesc/util/XMLString.hpp> |
9aed8c2ea97d
add Xerces-C++ dependency
František Kučera <franta-hg@frantovo.cz>
parents:
0
diff
changeset
|
32 |
|
0 | 33 |
#include <relpipe/writer/typedefs.h> |
34 |
||
2
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
35 |
#include "StreamInputSource.h" |
6
be83e0f457a8
move string conversion method to a separate class + report SAX exception details if any
František Kučera <franta-hg@frantovo.cz>
parents:
5
diff
changeset
|
36 |
#include "XercesStringConvertor.h" |
2
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
37 |
|
0 | 38 |
namespace relpipe { |
39 |
namespace in { |
|
40 |
namespace xml { |
|
41 |
||
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
42 |
using namespace relpipe::writer; |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
43 |
using namespace xercesc; |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
44 |
|
0 | 45 |
class XMLCommand { |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
46 |
private: |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
47 |
|
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
48 |
class RelpipeSaxHandler : public xercesc::DefaultHandler { |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
49 |
private: |
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
50 |
const wstring XMLNS = L"tag:globalcode.info,2018:relpipe"; |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
51 |
unique_ptr<RelationalWriter> writer; |
6
be83e0f457a8
move string conversion method to a separate class + report SAX exception details if any
František Kučera <franta-hg@frantovo.cz>
parents:
5
diff
changeset
|
52 |
XercesStringConvertor xConvertor; |
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
53 |
wstring currentRelationName; |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
54 |
vector<AttributeMetadata> currentAttributes; |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
55 |
wstringstream currentValue; |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
56 |
|
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
57 |
void resetCurrentValue() { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
58 |
currentValue.str(L""); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
59 |
currentValue.clear(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
60 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
61 |
|
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
62 |
string_t getAttributeName(const Attributes& attrs, string_t uri, string_t localname) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
63 |
// TODO: less string conversions, better performance |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
64 |
XMLCh* xUri = xConvertor.toXercesString(uri); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
65 |
XMLCh* xLocalName = xConvertor.toXercesString(localname); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
66 |
string_t value = xConvertor.toString(attrs.getValue(xUri, xLocalName)); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
67 |
XMLString::release(&xUri); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
68 |
XMLString::release(&xLocalName); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
69 |
return value; |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
70 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
71 |
|
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
72 |
void startElement(const string_t uri, const string_t localname, const string_t qname, const Attributes& attrs) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
73 |
if (uri == XMLNS) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
74 |
if (localname == L"name") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
75 |
resetCurrentValue(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
76 |
} else if (localname == L"attributes-metadata") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
77 |
currentAttributes.clear(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
78 |
} else if (localname == L"attribute-metadata") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
79 |
AttributeMetadata am; |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
80 |
am.attributeName = getAttributeName(attrs, L"", L"name"); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
81 |
am.typeId = writer->toTypeId(getAttributeName(attrs, L"", L"type")); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
82 |
currentAttributes.push_back(am); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
83 |
} else if (localname == L"attribute") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
84 |
resetCurrentValue(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
85 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
86 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
87 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
88 |
|
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
89 |
void endElement(const string_t uri, const string_t localname, const string_t qname) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
90 |
if (uri == XMLNS) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
91 |
if (localname == L"name") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
92 |
currentRelationName = currentValue.str(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
93 |
} else if (localname == L"attributes-metadata") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
94 |
writer->startRelation(currentRelationName, currentAttributes, true); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
95 |
} else if (localname == L"attribute") { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
96 |
writer->writeAttribute(currentValue.str()); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
97 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
98 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
99 |
} |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
100 |
|
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
101 |
void characters(const string_t chars) { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
102 |
currentValue << chars.c_str(); |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
103 |
} |
5
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
104 |
|
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
105 |
public: |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
106 |
|
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
107 |
RelpipeSaxHandler(std::ostream& output) : DefaultHandler(), writer(Factory::create(output)) { |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
108 |
} |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
109 |
|
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
110 |
virtual ~RelpipeSaxHandler() { |
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
111 |
|
4
1363ec0879ca
report SAX events in a single relation
František Kučera <franta-hg@frantovo.cz>
parents:
3
diff
changeset
|
112 |
} |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
113 |
|
4
1363ec0879ca
report SAX events in a single relation
František Kučera <franta-hg@frantovo.cz>
parents:
3
diff
changeset
|
114 |
void startElement(const XMLCh * const uri, const XMLCh * const localname, const XMLCh * const qname, const Attributes& attrs) override { |
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
115 |
startElement(xConvertor.toString(uri), xConvertor.toString(localname), xConvertor.toString(qname), attrs); |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
116 |
} |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
117 |
|
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
118 |
void endElement(const XMLCh * const uri, const XMLCh * const localname, const XMLCh * const qname) override { |
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
119 |
endElement(xConvertor.toString(uri), xConvertor.toString(localname), xConvertor.toString(qname)); |
4
1363ec0879ca
report SAX events in a single relation
František Kučera <franta-hg@frantovo.cz>
parents:
3
diff
changeset
|
120 |
} |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
121 |
|
4
1363ec0879ca
report SAX events in a single relation
František Kučera <franta-hg@frantovo.cz>
parents:
3
diff
changeset
|
122 |
void characters(const XMLCh * const chars, const XMLSize_t length) override { |
8
14e14a5db027
lossless bidirectional XML conversion of relational data
František Kučera <franta-hg@frantovo.cz>
parents:
7
diff
changeset
|
123 |
characters(xConvertor.toString(chars)); |
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
124 |
} |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
125 |
|
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
126 |
}; |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
127 |
|
0 | 128 |
public: |
129 |
||
130 |
void process(std::istream& input, std::ostream& output) { |
|
2
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
131 |
XMLPlatformUtils::Initialize(); |
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
132 |
unique_ptr<SAX2XMLReader> parser(XMLReaderFactory::createXMLReader()); |
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
133 |
parser->setFeature(XMLUni::fgSAX2CoreValidation, true); |
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
134 |
parser->setFeature(XMLUni::fgSAX2CoreNameSpaces, true); |
5
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
135 |
// TODO: optional unbuffered mode for more fluent output? |
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
136 |
// http://xerces.apache.org/xerces-c/program-sax2-3.html#SAX2Features |
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
137 |
// parser->setProperty(XMLUni::fgXercesLowWaterMark, ...); |
e5cf88ce91ac
generic XML parser for arbitrary documents that generates a relation containing the SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
4
diff
changeset
|
138 |
// parser->setInputBufferSize(...); |
2
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
139 |
|
3
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
140 |
RelpipeSaxHandler saxHandler(output); |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
141 |
parser->setContentHandler(&saxHandler); |
4b566dee1a57
generate random relation on SAX events
František Kučera <franta-hg@frantovo.cz>
parents:
2
diff
changeset
|
142 |
parser->setErrorHandler(&saxHandler); |
2
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
143 |
|
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
144 |
StreamInputSource inputSource(input); |
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
145 |
|
3ab78bf63467
read XML from istream using Xerces (just parse/validate, no processing yet)
František Kučera <franta-hg@frantovo.cz>
parents:
1
diff
changeset
|
146 |
parser->parse(inputSource); |
0 | 147 |
} |
148 |
}; |
|
149 |
||
150 |
} |
|
151 |
} |
|
152 |
} |