Handle P4 special characters

p4-fusion/branch_set.cc

@@ -10,16 +10,6 @@
 static const std::string EMPTY_STRING = "";
 static const std::array<std::string, 2> INVALID_BRANCH_PATH { EMPTY_STRING, EMPTY_STRING };
 
-std::vector<std::string> BranchedFileGroup::GetRelativeFileNames()
-{
-	std::vector<std::string> ret;
-	for (auto& fileData : files)
-	{
-		ret.push_back(fileData.GetRelativePath());
-	}
-	return ret;
-}
-
 ChangedFileGroups::ChangedFileGroups()
     : totalFileCount(0)
 {
@@ -295,7 +285,7 @@ std::unique_ptr<ChangedFileGroups> BranchSet::ParseAffectedFiles(const std::vect
 
 			// It's a valid destination to a branch.
 			// Make sure the relative path is set.
-			fileData.SetRelativePath(branchPath[1]);
+			fileData.SetRelativeDepotPath(branchPath[1]);
 
 			bool needsHandling = true;
 			if (fileData.IsIntegrated())
@@ -326,7 +316,7 @@ std::unique_ptr<ChangedFileGroups> BranchSet::ParseAffectedFiles(const std::vect
 		{
 			// It's a non-branching setup.
 			// Make sure the relative path is set.
-			fileData.SetRelativePath(relativeDepotPath);
+			fileData.SetRelativeDepotPath(relativeDepotPath);
 			branchMap.addTarget(EMPTY_STRING, fileData);
 		}
 	}

p4-fusion/branch_set.h

@@ -1,101 +1,98 @@
-/*
- * Copyright (c) 2022 Salesforce, Inc.
- * All rights reserved.
- * SPDX-License-Identifier: BSD-3-Clause
- * For full license text, see the LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
- */
-#pragma once
-
-#include <string>
-#include <vector>
-#include <array>
-#include <memory>
-#include <stdexcept>
-
-#include "commands/file_map.h"
-#include "commands/file_data.h"
-#include "commands/stream_result.h"
-#include "utils/std_helpers.h"
-
-struct BranchedFileGroup
-{
-	// If a BranchedFiles collection hasSource == true,
-	// then all files in this collection MUST be a merge
-	// from the given source branch to the target branch.
-	// These branch names will be the Git branch names.
-	std::string sourceBranch;
-	std::string targetBranch;
-	bool hasSource;
-	std::vector<FileData> files;
-
-	// Get all the relative file names from each of the file data.
-	std::vector<std::string> GetRelativeFileNames();
-};
-
-struct ChangedFileGroups
-{
-private:
-	ChangedFileGroups();
-
-public:
-	std::vector<BranchedFileGroup> branchedFileGroups;
-	int totalFileCount;
-
-	// When all the file groups have finished being used,
-	// only then can we safely clear out the data.
-	void Clear();
-
-	ChangedFileGroups(std::vector<BranchedFileGroup>& groups, int totalFileCount);
-
-	static std::unique_ptr<ChangedFileGroups> Empty() { return std::unique_ptr<ChangedFileGroups>(new ChangedFileGroups); };
-};
-
-struct Branch
-{
-public:
-	const std::string depotBranchPath;
-	const std::string gitAlias;
-
-	Branch(const std::string& branch, const std::string& alias);
-
-	// splitBranchPath If the relativeDepotPath matches, returns {branch alias, branch file path}.
-	//   Otherwise, returns {"", ""}
-	std::array<std::string, 2> SplitBranchPath(const std::string& relativeDepotPath) const;
-};
-
-// A singular view on the branches and a base view (acts as a filter to trim down affected files).
-// Maps a changed file state to a list of resulting branches and affected files.
-struct BranchSet
-{
-private:
-	// Technically, these should all be const.
-	const bool m_includeBinaries;
-	std::string m_basePath;
-	const std::vector<Branch> m_branches;
-	const std::vector<StreamResult::MappingData> m_mappings;
-	const std::vector<StreamResult::MappingData> m_exclusions;
-	FileMap m_view;
-
-	// stripBasePath remove the base path from the depot path, or "" if not in the base path.
-	std::string stripBasePath(const std::string& depotPath) const;
-
-	// splitBranchPath extract the branch name and path under the branch (no leading '/' on the path)
-	//    relativeDepotPath - already stripped from running stripBasePath.
-	std::array<std::string, 2> splitBranchPath(const std::string& relativeDepotPath) const;
-
-public:
-	BranchSet(std::vector<std::string>& clientViewMapping, const std::string& baseDepotPath, const std::vector<std::string>& branches, const std::vector<StreamResult::MappingData>& mappings, const std::vector<StreamResult::MappingData>& exclusions, const bool includeBinaries);
-
-	// HasMergeableBranch is there a branch model that requires integration history?
-	bool HasMergeableBranch() const { return !m_branches.empty(); };
-
-	int Count() const { return m_branches.size(); };
-
-	// ParseAffectedFiles create collections of merges and commits.
-	// Breaks up the files into those that are within the view, with each item in the
-	// list is its own target Git branch.
-	// This also has the side-effect of populating the relative path value in the file data.
-	//   ... the FileData object is copied, but it's underlying shared data is shared.  So, this
-	//       breaks the const.
-	std::unique_ptr<ChangedFileGroups> ParseAffectedFiles(const std::vector<FileData>& cl) const;
-};
+/*
+ * Copyright (c) 2022 Salesforce, Inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see the LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ */
+#pragma once
+
+#include <string>
+#include <vector>
+#include <array>
+#include <memory>
+#include <stdexcept>
+
+#include "commands/file_map.h"
+#include "commands/file_data.h"
+#include "commands/stream_result.h"
+#include "utils/std_helpers.h"
+
+struct BranchedFileGroup
+{
+	// If a BranchedFiles collection hasSource == true,
+	// then all files in this collection MUST be a merge
+	// from the given source branch to the target branch.
+	// These branch names will be the Git branch names.
+	std::string sourceBranch;
+	std::string targetBranch;
+	bool hasSource;
+	std::vector<FileData> files;
+};
+
+struct ChangedFileGroups
+{
+private:
+	ChangedFileGroups();
+
+public:
+	std::vector<BranchedFileGroup> branchedFileGroups;
+	int totalFileCount;
+
+	// When all the file groups have finished being used,
+	// only then can we safely clear out the data.
+	void Clear();
+
+	ChangedFileGroups(std::vector<BranchedFileGroup>& groups, int totalFileCount);
+
+	static std::unique_ptr<ChangedFileGroups> Empty() { return std::unique_ptr<ChangedFileGroups>(new ChangedFileGroups); };
+};
+
+struct Branch
+{
+public:
+	const std::string depotBranchPath;
+	const std::string gitAlias;
+
+	Branch(const std::string& branch, const std::string& alias);
+
+	// splitBranchPath If the relativeDepotPath matches, returns {branch alias, branch file path}.
+	//   Otherwise, returns {"", ""}
+	std::array<std::string, 2> SplitBranchPath(const std::string& relativeDepotPath) const;
+};
+
+// A singular view on the branches and a base view (acts as a filter to trim down affected files).
+// Maps a changed file state to a list of resulting branches and affected files.
+struct BranchSet
+{
+private:
+	// Technically, these should all be const.
+	const bool m_includeBinaries;
+	std::string m_basePath;
+	const std::vector<Branch> m_branches;
+	const std::vector<StreamResult::MappingData> m_mappings;
+	const std::vector<StreamResult::MappingData> m_exclusions;
+	FileMap m_view;
+
+	// stripBasePath remove the base path from the depot path, or "" if not in the base path.
+	std::string stripBasePath(const std::string& depotPath) const;
+
+	// splitBranchPath extract the branch name and path under the branch (no leading '/' on the path)
+	//    relativeDepotPath - already stripped from running stripBasePath.
+	std::array<std::string, 2> splitBranchPath(const std::string& relativeDepotPath) const;
+
+public:
+	BranchSet(std::vector<std::string>& clientViewMapping, const std::string& baseDepotPath, const std::vector<std::string>& branches, const std::vector<StreamResult::MappingData>& mappings, const std::vector<StreamResult::MappingData>& exclusions, const bool includeBinaries);
+
+	// HasMergeableBranch is there a branch model that requires integration history?
+	bool HasMergeableBranch() const { return !m_branches.empty(); };
+
+	int Count() const { return m_branches.size(); };
+
+	// ParseAffectedFiles create collections of merges and commits.
+	// Breaks up the files into those that are within the view, with each item in the
+	// list is its own target Git branch.
+	// This also has the side-effect of populating the relative path value in the file data.
+	//   ... the FileData object is copied, but it's underlying shared data is shared.  So, this
+	//       breaks the const.
+	std::unique_ptr<ChangedFileGroups> ParseAffectedFiles(const std::vector<FileData>& cl) const;
+};

p4-fusion/commands/file_data.cc

@@ -76,7 +76,7 @@ void FileData::SetPendingDownload()
 	}
 }
 
-void FileData::SetRelativePath(std::string& relativePath)
+void FileData::SetRelativeDepotPath(const std::string& relativePath)
 {
 	m_data->relativePath = relativePath;
 }

p4-fusion/commands/file_data.h

@@ -76,7 +76,7 @@ struct FileData
 	FileData& operator=(FileData& other);
 
 	void SetFromDepotFile(const std::string& fromDepotFile, const std::string& fromRevision);
-	void SetRelativePath(std::string& relativePath);
+	void SetRelativeDepotPath(const std::string& relativePath);
 	void SetFakeIntegrationDeleteAction() { m_data->SetAction(FAKE_INTEGRATION_DELETE_ACTION_NAME); };
 
 	// moves the argument's data into this file data structure.
@@ -88,7 +88,7 @@ struct FileData
 	const std::string& GetDepotFile() const { return m_data->depotFile; };
 	const std::string& GetRevision() const { return m_data->revision; };
 	const FileAction GetAction() const { return m_data->actionCategory; };
-	const std::string& GetRelativePath() const { return m_data->relativePath; };
+	const std::string& GetRelativeDepotPath() const { return m_data->relativePath; };
 	const std::vector<char>& GetContents() const { return m_data->contents; };
 	bool IsDeleted() const { return m_data->isDeleted; };
 	bool IsIntegrated() const { return m_data->isIntegrated; };

p4-fusion/main.cc

@@ -15,6 +15,7 @@
 #include "utils/std_helpers.h"
 #include "utils/timer.h"
 #include "utils/arguments.h"
+#include "utils/p4_helpers.h"
 
 #include "thread_pool.h"
 #include "p4_api.h"
@@ -390,13 +391,14 @@ int Main(int argc, char** argv)
 
 			for (auto& file : branchGroup.files)
 			{
+				const std::string unescapedPath = P4Unescape(file.GetRelativeDepotPath());
 				if (file.IsDeleted())
 				{
-					git.RemoveFileFromIndex(file.GetRelativePath());
+					git.RemoveFileFromIndex(unescapedPath);
 				}
 				else
 				{
-					git.AddFileToIndex(file.GetRelativePath(), file.GetContents(), file.IsExecutable());
+					git.AddFileToIndex(unescapedPath, file.GetContents(), file.IsExecutable());
 				}
 
 				// No use for keeping the contents in memory once it has been added

p4-fusion/utils/p4_helpers.cc

@@ -0,0 +1,19 @@
+/*
+ * Copyright (c) 2022 Salesforce, Inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see the LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ */
+#include "p4_helpers.h"
+
+#include "std_helpers.h"
+
+std::string P4Unescape(std::string p4path)
+{
+	STDHelpers::ReplaceAll(p4path, "%40", "@");
+	STDHelpers::ReplaceAll(p4path, "%23", "#");
+	STDHelpers::ReplaceAll(p4path, "%2A", "*");
+	// Replace %25 last to avoid interfering with other escape sequences
+	STDHelpers::ReplaceAll(p4path, "%25", "%");
+	return p4path;
+}

p4-fusion/utils/p4_helpers.h

@@ -0,0 +1,11 @@
+/*
+ * Copyright (c) 2022 Salesforce, Inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see the LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ */
+#pragma once
+
+#include <string>
+
+std::string P4Unescape(std::string p4path);

p4-fusion/utils/std_helpers.cc

@@ -67,6 +67,25 @@ void STDHelpers::StripSurrounding(std::string& source, const char c)
 	}
 }
 
+std::string STDHelpers::ToLower(const std::string& source)
+{
+	std::string result = source;
+	std::transform(result.begin(), result.end(), result.begin(), ::tolower);
+	return result;
+}
+
+void STDHelpers::ReplaceAll(std::string& str, const std::string& find, const std::string& replace)
+{
+	std::string::size_type pos;
+	std::string::size_type startPos = 0;
+
+	while ((pos = str.find(find, startPos)) != std::string::npos)
+	{
+		str.replace(pos, find.length(), replace);
+		startPos = pos + replace.length();
+	}
+}
+
 std::array<std::string, 2> STDHelpers::SplitAt(const std::string& source, const char c, const size_t startAt)
 {
 	size_t pos = source.find(c, startAt);