author | František Kučera <franta-hg@frantovo.cz> |
Sun, 31 Oct 2021 17:30:40 +0100 | |
branch | v_0 |
changeset 33 | c9a158da6c32 |
parent 32 | e72546725c77 |
permissions | -rw-r--r-- |
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
1 |
/** |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
2 |
* Relational pipes |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
3 |
* Copyright © 2019 František Kučera (Frantovo.cz, GlobalCode.info) |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
4 |
* |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
5 |
* This program is free software: you can redistribute it and/or modify |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
6 |
* it under the terms of the GNU General Public License as published by |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
7 |
* the Free Software Foundation, version 3 of the License. |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
8 |
* |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
9 |
* This program is distributed in the hope that it will be useful, |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
10 |
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
11 |
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
12 |
* GNU General Public License for more details. |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
13 |
* |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
14 |
* You should have received a copy of the GNU General Public License |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
15 |
* along with this program. If not, see <http://www.gnu.org/licenses/>. |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
16 |
*/ |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
17 |
#pragma once |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
18 |
|
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
19 |
#include <stdexcept> |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
20 |
#include <libxml++-2.6/libxml++/libxml++.h> |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
21 |
|
29
06aaad12c207
configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents:
28
diff
changeset
|
22 |
#include "lib/uri.h" |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
23 |
#include "lib/INIReader.h" |
28
0e7c57d48d1e
configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents:
27
diff
changeset
|
24 |
#include "lib/BasicUnescapingProcessor.h" |
0e7c57d48d1e
configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents:
27
diff
changeset
|
25 |
#include "lib/BackspaceUnescapingProcessor.h" |
0e7c57d48d1e
configurable unescaping processors
František Kučera <franta-hg@frantovo.cz>
parents:
27
diff
changeset
|
26 |
#include "lib/JavaPropertiesUnescapingProcessor.h" |
29
06aaad12c207
configurable dialects: in separate classes
František Kučera <franta-hg@frantovo.cz>
parents:
28
diff
changeset
|
27 |
#include "lib/JavaPropertiesDialect.h" |
33
c9a158da6c32
java-manifest-mf dialect for parsing MANIFEST.MF files (import shared code from relpipe-in-ini)
František Kučera <franta-hg@frantovo.cz>
parents:
32
diff
changeset
|
28 |
#include "lib/JavaManifestMFDialect.h" |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
29 |
#include "lib/XMLNameCodec.h" |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
30 |
|
26 | 31 |
using namespace relpipe::in::ini::lib; |
32 |
||
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
33 |
namespace relpipe { |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
34 |
namespace in { |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
35 |
namespace xmltable { |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
36 |
|
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
37 |
class HierarchicalINIContentHandler : public INIContentHandler { |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
38 |
private: |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
39 |
xmlpp::DomParser* domParser; |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
40 |
XMLNameCodec nameCodec; |
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
41 |
xmlpp::Element* currentSection = nullptr; |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
42 |
|
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
43 |
enum class TreeStyle { |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
44 |
Standard, |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
45 |
Literal, |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
46 |
}; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
47 |
|
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
48 |
TreeStyle parseTreeStyle(const std::string& name) { |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
49 |
if (name == "standard") return TreeStyle::Standard; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
50 |
else if (name == "literal") return TreeStyle::Literal; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
51 |
else throw std::invalid_argument(std::string("Unknown tree style: ") + name); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
52 |
} |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
53 |
|
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
54 |
TreeStyle treeStyle = TreeStyle::Literal; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
55 |
|
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
56 |
std::string rootName = "ini"; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
57 |
bool enableLineNumbers = true; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
58 |
bool enableEventNumbers = true; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
59 |
bool enableSubKeys = true; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
60 |
bool enableComments = true; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
61 |
bool enableWhitespace = true; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
62 |
|
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
63 |
/** |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
64 |
* TODO: use a common method |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
65 |
*/ |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
66 |
bool parseBoolean(const std::string& value) { |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
67 |
if (value == "true") return true; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
68 |
else if (value == "false") return false; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
69 |
else throw std::invalid_argument(std::string("Unable to parse boolean value: ") + value + " (expecting true or false)"); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
70 |
} |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
71 |
|
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
72 |
bool treeWithNamespaces = false; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
73 |
|
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
74 |
public: |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
75 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
76 |
HierarchicalINIContentHandler(xmlpp::DomParser* domParser) : domParser(domParser) { |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
77 |
} |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
78 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
79 |
virtual ~HierarchicalINIContentHandler() { |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
80 |
} |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
81 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
82 |
void startDocument() override { |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
83 |
if (currentSection) throw std::out_of_range("Lunatic INI parser send us multiple documents."); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
84 |
currentSection = domParser->get_document()->create_root_node(rootName, treeWithNamespaces ? xml::XMLNS : ""); |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
85 |
}; |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
86 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
87 |
void endDocument() override { |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
88 |
}; |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
89 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
90 |
void startSection(const SectionStartEvent& event) override { |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
91 |
currentSection = currentSection->add_child(treeStyle == TreeStyle::Literal ? nameCodec.encode(event.name) : "section"); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
92 |
if (treeStyle == TreeStyle::Literal) currentSection->set_attribute("type", "section"); |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
93 |
currentSection->set_attribute("name", event.name); |
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
94 |
if (event.comment.size()) currentSection->set_attribute("comment", event.comment); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
95 |
if (event.lineNumber >= 0 && enableLineNumbers) currentSection->set_attribute("line-number", std::to_string(event.lineNumber)); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
96 |
if (event.eventNumber >= 0 && enableEventNumbers) currentSection->set_attribute("event-number", std::to_string(event.eventNumber)); |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
97 |
}; |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
98 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
99 |
void endSection() override { |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
100 |
currentSection = currentSection->get_parent(); |
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
101 |
if (currentSection == nullptr) throw std::out_of_range("Lunatic INI parser tried to end a section without starting it before."); |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
102 |
}; |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
103 |
|
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
104 |
void entry(const EntryEvent& event) override { |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
105 |
xmlpp::Element* entry = currentSection->add_child(treeStyle == TreeStyle::Literal ? nameCodec.encode(event.fullKey) : "entry"); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
106 |
if (treeStyle == TreeStyle::Literal) entry->set_attribute("type", "entry"); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
107 |
entry->set_attribute("key", enableSubKeys ? event.key : event.fullKey); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
108 |
if (enableSubKeys)entry->set_attribute("full-key", event.fullKey); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
109 |
if (event.subKey.size() && enableSubKeys) entry->set_attribute("sub-key", event.subKey); |
19
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
110 |
if (event.comment.size()) entry->set_attribute("comment", event.comment); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
111 |
if (event.lineNumber >= 0 && enableLineNumbers) entry->set_attribute("line-number", std::to_string(event.lineNumber)); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
112 |
if (event.eventNumber >= 0 && enableEventNumbers) entry->set_attribute("event-number", std::to_string(event.eventNumber)); |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
113 |
entry->add_child_text(event.value); |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
114 |
}; |
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
115 |
|
19
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
116 |
void comment(const CommentEvent& event) override { |
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
117 |
xmlpp::Element* comment = currentSection->add_child("comment"); |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
118 |
if (treeStyle == TreeStyle::Literal) comment->set_attribute("type", "comment"); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
119 |
if (event.lineNumber >= 0 && enableLineNumbers) comment->set_attribute("line-number", std::to_string(event.lineNumber)); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
120 |
if (event.eventNumber >= 0 && enableEventNumbers) comment->set_attribute("event-number", std::to_string(event.eventNumber)); |
19
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
121 |
comment->add_child_text(event.comment); |
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
122 |
} |
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
123 |
|
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
124 |
void whitespace(const WhitespaceEvent& event) override { |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
125 |
xmlpp::Element* whitespace = currentSection->add_child("whitespace"); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
126 |
if (treeStyle == TreeStyle::Literal) whitespace->set_attribute("type", "whitespace"); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
127 |
if (event.lineNumber >= 0 && enableLineNumbers) whitespace->set_attribute("line-number", std::to_string(event.lineNumber)); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
128 |
if (event.eventNumber >= 0 && enableEventNumbers) whitespace->set_attribute("event-number", std::to_string(event.eventNumber)); |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
129 |
whitespace->add_child_text(event.whitespace); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
130 |
} |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
131 |
|
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
132 |
bool setOption(const std::string& uri, const std::string& value) { |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
133 |
if (uri == xml::TreeWithNamespaces) treeWithNamespaces = parseBoolean(value); |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
134 |
else if (uri == xml::TreeStyle) treeStyle = parseTreeStyle(value); |
32
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
135 |
else if (uri == xml::RootName) rootName = value; |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
136 |
else if (uri == xml::EnableWhitespace) enableWhitespace = parseBoolean(value); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
137 |
else if (uri == xml::EnableComments) enableComments = parseBoolean(value); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
138 |
else if (uri == xml::EnableSubKeys) enableSubKeys = parseBoolean(value); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
139 |
else if (uri == xml::EnableLineNumbers) enableLineNumbers = parseBoolean(value); |
e72546725c77
add --parser-option root-name, enable-comments, enable-whitespace, enable-line-numbers, enable-event-numbers, enable-sub-keys
František Kučera <franta-hg@frantovo.cz>
parents:
31
diff
changeset
|
140 |
else if (uri == xml::EnableEventNumbers) enableEventNumbers = parseBoolean(value); |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
141 |
else return false; |
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
142 |
return true; |
19
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
143 |
} |
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
144 |
|
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
145 |
}; |
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
146 |
|
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
147 |
// TODO: support also other styles/mappings e.g. <section/> and <entry/> with INI names only in the XML attributes (and thus without @type="section|entry") |
19
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
148 |
// or map INI comments and whitespace to native XML comments and text nodes (but there will be no metadata like line/event numbers) |
90f2b8ca32bf
improved support for comments and whitespace
František Kučera <franta-hg@frantovo.cz>
parents:
18
diff
changeset
|
149 |
// TODO: optional namespaces (xmlns) |
18
45c06bdf9045
produce hierarchical structure of INI sections and entries
František Kučera <franta-hg@frantovo.cz>
parents:
17
diff
changeset
|
150 |
|
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
151 |
class XMLDocumentConstructor { |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
152 |
private: |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
153 |
std::istream* input = nullptr; |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
154 |
xmlpp::DomParser* parser = nullptr; |
30
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
155 |
std::shared_ptr<INIReader> reader; |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
156 |
std::shared_ptr<HierarchicalINIContentHandler> handler; |
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
157 |
public: |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
158 |
|
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
159 |
XMLDocumentConstructor(std::istream* input, xmlpp::DomParser* parser) : input(input), parser(parser) { |
30
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
160 |
reader.reset(INIReader::create(*input)); |
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
161 |
reader->addUnescapingProcessor(std::make_shared<BasicUnescapingProcessor>(), unescaping::Basic, true); |
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
162 |
reader->addUnescapingProcessor(std::make_shared<JavaPropertiesUnescapingProcessor>(), unescaping::JavaProperties, false); |
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
163 |
reader->addUnescapingProcessor(std::make_shared<BackspaceUnescapingProcessor>(), unescaping::Backspace, true); |
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
164 |
reader->addDialect(std::make_shared<JavaPropertiesDialect>(), dialect::JavaProperties, false); |
33
c9a158da6c32
java-manifest-mf dialect for parsing MANIFEST.MF files (import shared code from relpipe-in-ini)
František Kučera <franta-hg@frantovo.cz>
parents:
32
diff
changeset
|
165 |
reader->addDialect(std::make_shared<JavaManifestMFDialect>(), dialect::JavaManifestMF, false); |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
166 |
handler = std::make_shared<HierarchicalINIContentHandler>(parser); |
30
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
167 |
} |
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
168 |
|
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
169 |
void setOption(const std::string& uri, const std::string& value) { |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
170 |
if (handler->setOption(uri, value)) return; |
30
f686bdaeb9e0
add --parser-option
František Kučera <franta-hg@frantovo.cz>
parents:
29
diff
changeset
|
171 |
reader->setOption(uri, value); |
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
172 |
} |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
173 |
|
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
174 |
void process() { |
31
c6527b45fbc2
add --parser-option tree-style standard|literal --parser-option tree-with-namespaces true|false
František Kučera <franta-hg@frantovo.cz>
parents:
30
diff
changeset
|
175 |
reader->addHandler(handler.get()); |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
176 |
reader->process(); |
14
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
177 |
} |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
178 |
}; |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
179 |
|
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
180 |
} |
5be268bc4c69
separate the „std::istream to DOM“ phase
František Kučera <franta-hg@frantovo.cz>
parents:
diff
changeset
|
181 |
} |
17
786977554fc3
dump raw INI parser events
František Kučera <franta-hg@frantovo.cz>
parents:
14
diff
changeset
|
182 |
} |