File: todoextractor.cpp

package info (click to toggle)
kdevelop 4%3A5.3.1-3
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 52,544 kB
  • sloc: cpp: 254,897; python: 3,380; sh: 1,271; ansic: 657; xml: 221; php: 95; makefile: 36; lisp: 13; sed: 12
file content (216 lines) | stat: -rw-r--r-- 6,813 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
/*
 * Copyright 2014 Kevin Funk <kfunk@kde.org>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; either version 2 of
 * the License or (at your option) version 3 or any later version
 * accepted by the membership of KDE e.V. (or its successor approved
 * by the membership of KDE e.V.), which shall act as a proxy
 * defined in Section 14 of version 3 of the license.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 */

#include "todoextractor.h"

#include "../util/clangtypes.h"

#include <language/duchain/problem.h>
#include <language/duchain/stringhelpers.h>
#include <language/editor/documentrange.h>
#include <interfaces/icore.h>
#include <interfaces/ilanguagecontroller.h>
#include <interfaces/icompletionsettings.h>

#include <QStringList>
#include <QDir>

#include <algorithm>
#include <limits>

using namespace KDevelop;

namespace {

inline int findEndOfLineOrEnd(const QString& str, int from = 0)
{
    const int index = str.indexOf(QLatin1Char('\n'), from);
    return (index == -1 ? str.length() : index);
}

inline int findBeginningOfLineOrStart(const QString& str, int from = 0)
{
    const int index = str.lastIndexOf(QLatin1Char('\n'), from);
    return (index == -1 ? 0 : index+1);
}

inline int findEndOfCommentOrEnd(const QString& str, int from = 0)
{
    const int index = str.indexOf(QLatin1String("*/"), from);
    return (index == -1 ? str.length() : index);
}

/**
 * @brief Class for parsing to-do items out of a given comment string
 *
 * Make sure this class is very performant as it will be used for every comment string
 * throughout the code base.
 *
 * So: No unnecessary deep-copies of strings if possible!
 */
class CommentTodoParser
{
public:
    struct Result {
        /// Description of the problem
        QString description;
        /// Range within the comment
        KTextEditor::Range localRange;
    };

    CommentTodoParser(const QString& str, const QStringList& markerWords)
        : m_str(str)
        , m_todoMarkerWords(markerWords)
    {
        skipUntilMarkerWord();
    }

    QVector<Result> results() const
    {
        return m_results;
    }

private:
    void skipUntilMarkerWord()
    {
        // in the most-cases, we won't find a to-do item
        // make sure this case is sufficiently fast

        // for each to-do marker, scan the comment text
        foreach (const QString& todoMarker, m_todoMarkerWords) {
            int offset = m_str.indexOf(todoMarker, m_offset);
            if (offset != -1) {
                m_offset = offset;
                parseTodoMarker();
            }
        }
    }

    void skipUntilNewline()
    {
        m_offset = findEndOfLineOrEnd(m_str, m_offset);
    }

    void parseTodoMarker()
    {
        // okay, we've found something
        // m_offset points to the start of the to-do item
        const int lineStart = findBeginningOfLineOrStart(m_str, m_offset);
        const int lineEnd = findEndOfLineOrEnd(m_str, m_offset);
        Q_ASSERT(lineStart <= m_offset);
        Q_ASSERT(lineEnd > m_offset);

        QString text = m_str.mid(m_offset, lineEnd - m_offset);
        Q_ASSERT(!text.contains(QLatin1Char('\n')));

        // there's nothing to be stripped on the left side, hence ignore that
        text.chop(text.length() - findEndOfCommentOrEnd(text));
        text = text.trimmed(); // remove additional whitespace from the end

        // check at what line within the comment we are by just counting the newlines until now
        const int line = std::count(m_str.constBegin(), m_str.constBegin() + m_offset, QLatin1Char('\n'));
        KTextEditor::Cursor start = {line, m_offset - lineStart};
        KTextEditor::Cursor end = {line, start.column() + text.length()};
        m_results << Result{text, {start, end}};

        skipUntilNewline();
        skipUntilMarkerWord();
    }

    inline bool atEnd() const
    {
        return m_offset < m_str.length();
    }

private:
    const QString m_str;
    const QStringList m_todoMarkerWords;

    int m_offset = 0;

    QVector<Result> m_results;
};

}

Q_DECLARE_TYPEINFO(CommentTodoParser::Result, Q_MOVABLE_TYPE);

TodoExtractor::TodoExtractor(CXTranslationUnit unit, CXFile file)
    : m_unit(unit)
    , m_file(file)
    , m_todoMarkerWords(KDevelop::ICore::self()->languageController()->completionSettings()->todoMarkerWords())
{
    extractTodos();
}

void TodoExtractor::extractTodos()
{
    using uintLimits = std::numeric_limits<uint>;

    auto start = clang_getLocation(m_unit, m_file, 1, 1);
    auto end = clang_getLocation(m_unit, m_file, uintLimits::max(), uintLimits::max());

    auto range = clang_getRange(start, end);

    IndexedString path(QDir(ClangString(clang_getFileName(m_file)).toString()).canonicalPath());

    if(clang_Range_isNull(range)){
        return;
    }

    const ClangTokens tokens(m_unit, range);
    for (CXToken token : tokens) {
        CXTokenKind tokenKind = clang_getTokenKind(token);
        if (tokenKind != CXToken_Comment) {
            continue;
        }

        CXString tokenSpelling = clang_getTokenSpelling(m_unit, token);
        auto tokenRange = ClangRange(clang_getTokenExtent(m_unit, token)).toRange();
        const QString text = ClangString(tokenSpelling).toString();

        CommentTodoParser parser(text, m_todoMarkerWords);
        const auto parserResults = parser.results();
        m_problems.reserve(m_problems.size() + parserResults.size());
        for (const CommentTodoParser::Result& result : parserResults) {
            ProblemPointer problem(new Problem);
            problem->setDescription(result.description);
            problem->setSeverity(IProblem::Hint);
            problem->setSource(IProblem::ToDo);

            // move the local range to the correct location
            // note: localRange is the range *within* the comment only
            auto localRange = result.localRange;
            KTextEditor::Range todoRange{
                tokenRange.start().line() + localRange.start().line(),
                localRange.start().column(),
                tokenRange.start().line() + localRange.end().line(),
                localRange.end().column()};
            problem->setFinalLocation({path, todoRange});
            m_problems << problem;
        }
    }
}

QList< ProblemPointer > TodoExtractor::problems() const
{
    return m_problems;
}