Clang: Filter duplicates in clang query output

Because we can visit headers many times, we get results many times too.

Change-Id: I3bbe7d7a5d01c2580a4569bfe115f14a69edc8a7
Reviewed-by: Tim Jenssen <tim.jenssen@qt.io>

src/tools/clangrefactoringbackend/source/clangquerygatherer.cpp

@@ -34,6 +34,7 @@ ClangQueryGatherer::ClangQueryGatherer(StringCache<Utils::PathString, std::mutex
                                        std::vector<V2::FileContainer> &&unsaved,
                                        Utils::SmallString &&query)
     : m_filePathCache(filePathCache),
+      m_sourceRangeFilter(sources.size()),
       m_sources(std::move(sources)),
       m_unsaved(std::move(unsaved)),
       m_query(std::move(query))
@@ -125,7 +126,7 @@ std::vector<SourceRangesAndDiagnosticsForQueryMessage> ClangQueryGatherer::allCu
     std::vector<SourceRangesAndDiagnosticsForQueryMessage> messages;
 
     for (Future &future : m_sourceFutures)
-        messages.push_back(future.get());
+        messages.push_back(m_sourceRangeFilter.removeDuplicates(future.get()));
 
     return messages;
 }
@@ -135,7 +136,7 @@ std::vector<SourceRangesAndDiagnosticsForQueryMessage> ClangQueryGatherer::finis
     std::vector<SourceRangesAndDiagnosticsForQueryMessage> messages;
 
     for (auto &&future : finishedFutures())
-        messages.push_back(future.get());
+        messages.push_back(m_sourceRangeFilter.removeDuplicates(future.get()));
 
     return messages;
 }

src/tools/clangrefactoringbackend/source/clangquerygatherer.h

@@ -25,6 +25,8 @@
 
 #pragma once
 
+#include "sourcerangefilter.h"
+
 #include <sourcerangesanddiagnosticsforquerymessage.h>
 #include <filecontainerv2.h>
 #include <stringcache.h>
@@ -68,6 +70,7 @@ protected:
 
 private:
     StringCache<Utils::PathString, std::mutex> *m_filePathCache = nullptr;
+    SourceRangeFilter m_sourceRangeFilter;
     std::vector<V2::FileContainer> m_sources;
     std::vector<V2::FileContainer> m_unsaved;
     Utils::SmallString m_query;

src/tools/clangrefactoringbackend/source/clangrefactoringbackend-source.pri

@@ -1,7 +1,8 @@
 INCLUDEPATH += $$PWD
 
 HEADERS += \
-    $$PWD/clangrefactoringbackend_global.h
+    $$PWD/clangrefactoringbackend_global.h \
+    $$PWD/sourcerangefilter.h
 
 !isEmpty(LIBTOOLING_LIBS) {
 SOURCES += \
@@ -33,3 +34,6 @@ HEADERS += \
     $$PWD/locationsourcefilecallbacks.h \
     $$PWD/clangquerygatherer.h
 }
+
+SOURCES += \
+    $$PWD/sourcerangefilter.cpp

src/tools/clangrefactoringbackend/source/refactoringserver.cpp

@@ -115,6 +115,11 @@ bool RefactoringServer::pollTimerIsActive() const
     return m_pollTimer.isActive();
 }
 
+void RefactoringServer::setGathererProcessingSlotCount(uint count)
+{
+    m_gatherer.setProcessingSlotCount(count);
+}
+
 void RefactoringServer::gatherSourceRangesAndDiagnosticsForQueryMessages(
         std::vector<V2::FileContainer> &&sources,
         std::vector<V2::FileContainer> &&unsaved,

src/tools/clangrefactoringbackend/source/refactoringserver.h

@@ -64,6 +64,8 @@ public:
 
     bool pollTimerIsActive() const;
 
+    void setGathererProcessingSlotCount(uint count);
+
 private:
     void gatherSourceRangesAndDiagnosticsForQueryMessages(std::vector<V2::FileContainer> &&sources,
                                                           std::vector<V2::FileContainer> &&unsaved,

src/tools/clangrefactoringbackend/source/sourcerangefilter.cpp

@@ -0,0 +1,59 @@
+/****************************************************************************
+**
+** Copyright (C) 2017 The Qt Company Ltd.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of Qt Creator.
+**
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 3 as published by the Free Software
+** Foundation with exceptions as appearing in the file LICENSE.GPL3-EXCEPT
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-3.0.html.
+**
+****************************************************************************/
+
+#include "sourcerangefilter.h"
+
+#include <algorithm>
+
+namespace ClangBackEnd {
+
+SourceRangeFilter::SourceRangeFilter(std::size_t sourcesCount)
+{
+    m_collectedSourceRanges.reserve(sourcesCount);
+}
+
+SourceRangesAndDiagnosticsForQueryMessage SourceRangeFilter::removeDuplicates(SourceRangesAndDiagnosticsForQueryMessage &&message)
+{
+    removeDuplicates(message.sourceRanges().sourceRangeWithTextContainers());
+
+    return std::move(message);
+}
+
+void SourceRangeFilter::removeDuplicates(SourceRangeWithTextContainers &sourceRanges)
+{
+    auto partitionPoint = std::stable_partition(sourceRanges.begin(),
+                                                sourceRanges.end(),
+                                                [&] (const SourceRangeWithTextContainer &sourceRange) {
+        return m_collectedSourceRanges.find(sourceRange) == m_collectedSourceRanges.end();
+    });
+
+    sourceRanges.erase(partitionPoint, sourceRanges.end());
+
+    std::copy(sourceRanges.begin(),
+              sourceRanges.end(),
+              std::inserter(m_collectedSourceRanges, m_collectedSourceRanges.end()));
+}
+
+} // namespace ClangBackEnd

src/tools/clangrefactoringbackend/source/sourcerangefilter.h

@@ -0,0 +1,47 @@
+/****************************************************************************
+**
+** Copyright (C) 2017 The Qt Company Ltd.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of Qt Creator.
+**
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 3 as published by the Free Software
+** Foundation with exceptions as appearing in the file LICENSE.GPL3-EXCEPT
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-3.0.html.
+**
+****************************************************************************/
+
+#pragma once
+
+#include <unordered_set>
+
+#include <sourcerangesanddiagnosticsforquerymessage.h>
+
+namespace ClangBackEnd {
+
+class SourceRangeFilter
+{
+public:
+    SourceRangeFilter(std::size_t sourcesCount = 0);
+
+    SourceRangesAndDiagnosticsForQueryMessage
+    removeDuplicates(SourceRangesAndDiagnosticsForQueryMessage &&message);
+    void removeDuplicates(SourceRangeWithTextContainers &sourceRanges);
+
+private:
+    std::unordered_set<SourceRangeWithTextContainer> m_collectedSourceRanges;
+};
+
+} // namespace ClangBackEnd