[Lldb-commits] [lldb] r220894 - Start adopting the StringPrinter API. The StringPrinter API is the new blessed way of printing strings that supports escaping non-printables, and has better handling of different UTF encodings

Enrico Granata egranata at apple.com
Wed Oct 29 18:45:40 PDT 2014


Author: enrico
Date: Wed Oct 29 20:45:39 2014
New Revision: 220894

URL: http://llvm.org/viewvc/llvm-project?rev=220894&view=rev
Log:
Start adopting the StringPrinter API. The StringPrinter API is the new blessed way of printing strings that supports escaping non-printables, and has better handling of different UTF encodings

Added:
    lldb/trunk/include/lldb/DataFormatters/StringPrinter.h
    lldb/trunk/source/DataFormatters/StringPrinter.cpp
Modified:
    lldb/trunk/lldb.xcodeproj/project.pbxproj
    lldb/trunk/source/DataFormatters/CXXFormatterFunctions.cpp

Added: lldb/trunk/include/lldb/DataFormatters/StringPrinter.h
URL: http://llvm.org/viewvc/llvm-project/lldb/trunk/include/lldb/DataFormatters/StringPrinter.h?rev=220894&view=auto
==============================================================================
--- lldb/trunk/include/lldb/DataFormatters/StringPrinter.h (added)
+++ lldb/trunk/include/lldb/DataFormatters/StringPrinter.h Wed Oct 29 20:45:39 2014
@@ -0,0 +1,271 @@
+//===-- StringPrinter.h -----------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef liblldb_StringPrinter_h_
+#define liblldb_StringPrinter_h_
+
+#include "lldb/lldb-forward.h"
+
+#include "lldb/Core/DataExtractor.h"
+
+namespace lldb_private {
+    namespace formatters
+    {
+        
+        enum class StringElementType {
+            ASCII,
+            UTF8,
+            UTF16,
+            UTF32
+        };
+        
+        class ReadStringAndDumpToStreamOptions
+        {
+        public:
+            
+            ReadStringAndDumpToStreamOptions () :
+            m_location(0),
+            m_process_sp(),
+            m_stream(NULL),
+            m_prefix_token(0),
+            m_quote('"'),
+            m_source_size(0),
+            m_needs_zero_termination(true),
+            m_escape_non_printables(true)
+            {
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetLocation (uint64_t l)
+            {
+                m_location = l;
+                return *this;
+            }
+            
+            uint64_t
+            GetLocation () const
+            {
+                return m_location;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetProcessSP (lldb::ProcessSP p)
+            {
+                m_process_sp = p;
+                return *this;
+            }
+            
+            lldb::ProcessSP
+            GetProcessSP () const
+            {
+                return m_process_sp;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetStream (Stream* s)
+            {
+                m_stream = s;
+                return *this;
+            }
+            
+            Stream*
+            GetStream () const
+            {
+                return m_stream;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetPrefixToken (char p)
+            {
+                m_prefix_token = p;
+                return *this;
+            }
+            
+            char
+            GetPrefixToken () const
+            {
+                return m_prefix_token;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetQuote (char q)
+            {
+                m_quote = q;
+                return *this;
+            }
+            
+            char
+            GetQuote () const
+            {
+                return m_quote;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetSourceSize (uint32_t s)
+            {
+                m_source_size = s;
+                return *this;
+            }
+            
+            uint32_t
+            GetSourceSize () const
+            {
+                return m_source_size;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetNeedsZeroTermination (bool z)
+            {
+                m_needs_zero_termination = z;
+                return *this;
+            }
+            
+            bool
+            GetNeedsZeroTermination () const
+            {
+                return m_needs_zero_termination;
+            }
+            
+            ReadStringAndDumpToStreamOptions&
+            SetEscapeNonPrintables (bool e)
+            {
+                m_escape_non_printables = e;
+                return *this;
+            }
+            
+            bool
+            GetEscapeNonPrintables () const
+            {
+                return m_escape_non_printables;
+            }
+            
+        private:
+            uint64_t m_location;
+            lldb::ProcessSP m_process_sp;
+            Stream* m_stream;
+            char m_prefix_token;
+            char m_quote;
+            uint32_t m_source_size;
+            bool m_needs_zero_termination;
+            bool m_escape_non_printables;
+        };
+        
+        class ReadBufferAndDumpToStreamOptions
+        {
+        public:
+            
+            ReadBufferAndDumpToStreamOptions () :
+            m_data(),
+            m_stream(NULL),
+            m_prefix_token(0),
+            m_quote('"'),
+            m_source_size(0),
+            m_escape_non_printables(true)
+            {
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetData (DataExtractor d)
+            {
+                m_data = d;
+                return *this;
+            }
+            
+            lldb_private::DataExtractor
+            GetData () const
+            {
+                return m_data;
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetStream (Stream* s)
+            {
+                m_stream = s;
+                return *this;
+            }
+            
+            Stream*
+            GetStream () const
+            {
+                return m_stream;
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetPrefixToken (char p)
+            {
+                m_prefix_token = p;
+                return *this;
+            }
+            
+            char
+            GetPrefixToken () const
+            {
+                return m_prefix_token;
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetQuote (char q)
+            {
+                m_quote = q;
+                return *this;
+            }
+            
+            char
+            GetQuote () const
+            {
+                return m_quote;
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetSourceSize (uint32_t s)
+            {
+                m_source_size = s;
+                return *this;
+            }
+            
+            uint32_t
+            GetSourceSize () const
+            {
+                return m_source_size;
+            }
+            
+            ReadBufferAndDumpToStreamOptions&
+            SetEscapeNonPrintables (bool e)
+            {
+                m_escape_non_printables = e;
+                return *this;
+            }
+            
+            bool
+            GetEscapeNonPrintables () const
+            {
+                return m_escape_non_printables;
+            }
+            
+        private:
+            DataExtractor m_data;
+            Stream* m_stream;
+            char m_prefix_token;
+            char m_quote;
+            uint32_t m_source_size;
+            bool m_escape_non_printables;
+        };
+        
+        template <StringElementType element_type>
+        bool
+        ReadStringAndDumpToStream (ReadStringAndDumpToStreamOptions options);
+        
+        template <StringElementType element_type>
+        bool
+        ReadBufferAndDumpToStream (ReadBufferAndDumpToStreamOptions options);
+        
+    } // namespace formatters
+} // namespace lldb_private
+
+#endif // liblldb_StringPrinter_h_

Modified: lldb/trunk/lldb.xcodeproj/project.pbxproj
URL: http://llvm.org/viewvc/llvm-project/lldb/trunk/lldb.xcodeproj/project.pbxproj?rev=220894&r1=220893&r2=220894&view=diff
==============================================================================
--- lldb/trunk/lldb.xcodeproj/project.pbxproj (original)
+++ lldb/trunk/lldb.xcodeproj/project.pbxproj Wed Oct 29 20:45:39 2014
@@ -699,6 +699,7 @@
 		94E829CA152D33C1006F96A3 /* lldb-platform in Resources */ = {isa = PBXBuildFile; fileRef = 26DC6A101337FE6900FF7998 /* lldb-platform */; };
 		94EA1D5C15E6C9B400D4171A /* PythonDataObjects.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 94EA1D5B15E6C9B400D4171A /* PythonDataObjects.cpp */; };
 		94EA27CE17DE91750070F505 /* LibCxxUnorderedMap.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 94EA27CD17DE91750070F505 /* LibCxxUnorderedMap.cpp */; };
+		94F48F251A01C687005C0EC6 /* StringPrinter.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 94F48F241A01C687005C0EC6 /* StringPrinter.cpp */; };
 		94FA3DE01405D50400833217 /* ValueObjectConstResultChild.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 94FA3DDF1405D50300833217 /* ValueObjectConstResultChild.cpp */; };
 		966C6B7918E6A56A0093F5EC /* libz.dylib in Frameworks */ = {isa = PBXBuildFile; fileRef = 966C6B7818E6A56A0093F5EC /* libz.dylib */; };
 		966C6B7A18E6A56A0093F5EC /* libz.dylib in Frameworks */ = {isa = PBXBuildFile; fileRef = 966C6B7818E6A56A0093F5EC /* libz.dylib */; };
@@ -2077,6 +2078,8 @@
 		94EBAC8313D9EE26009BA64E /* PythonPointer.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = PythonPointer.h; path = include/lldb/Utility/PythonPointer.h; sourceTree = "<group>"; };
 		94ED54A119C8A822007BE2EA /* ThreadSafeDenseMap.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = ThreadSafeDenseMap.h; path = include/lldb/Core/ThreadSafeDenseMap.h; sourceTree = "<group>"; };
 		94EE33F218643C6900CD703B /* FormattersContainer.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = FormattersContainer.h; path = include/lldb/DataFormatters/FormattersContainer.h; sourceTree = "<group>"; };
+		94F48F231A01C679005C0EC6 /* StringPrinter.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = StringPrinter.h; path = include/lldb/DataFormatters/StringPrinter.h; sourceTree = "<group>"; };
+		94F48F241A01C687005C0EC6 /* StringPrinter.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = StringPrinter.cpp; path = source/DataFormatters/StringPrinter.cpp; sourceTree = "<group>"; };
 		94F6C4D119C264C70049D089 /* ProcessStructReader.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = ProcessStructReader.h; path = include/lldb/Utility/ProcessStructReader.h; sourceTree = "<group>"; };
 		94FA3DDD1405D4E500833217 /* ValueObjectConstResultChild.h */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.h; name = ValueObjectConstResultChild.h; path = include/lldb/Core/ValueObjectConstResultChild.h; sourceTree = "<group>"; };
 		94FA3DDF1405D50300833217 /* ValueObjectConstResultChild.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = ValueObjectConstResultChild.cpp; path = source/Core/ValueObjectConstResultChild.cpp; sourceTree = "<group>"; };
@@ -4336,6 +4339,8 @@
 				94D6A0A816CEB55F00833B6E /* NSDictionary.cpp */,
 				9439FB1919EF140C006FD6A4 /* NSIndexPath.cpp */,
 				94D6A0A916CEB55F00833B6E /* NSSet.cpp */,
+				94F48F231A01C679005C0EC6 /* StringPrinter.h */,
+				94F48F241A01C687005C0EC6 /* StringPrinter.cpp */,
 				94CB256816B096F90059775D /* TypeCategory.h */,
 				94CB256416B096F10059775D /* TypeCategory.cpp */,
 				94CB256916B096FA0059775D /* TypeCategoryMap.h */,
@@ -5442,6 +5447,7 @@
 				2698699B15E6CBD0002415FF /* OperatingSystemPython.cpp in Sources */,
 				947A1D641616476B0017C8D1 /* CommandObjectPlugin.cpp in Sources */,
 				262ED0081631FA3A00879631 /* OptionGroupString.cpp in Sources */,
+				94F48F251A01C687005C0EC6 /* StringPrinter.cpp in Sources */,
 				94094C6B163B6F840083A547 /* ValueObjectCast.cpp in Sources */,
 				AF9107EF168570D200DBCD3C /* RegisterContextDarwin_arm64.cpp in Sources */,
 				94CB255B16B069770059775D /* CXXFormatterFunctions.cpp in Sources */,

Modified: lldb/trunk/source/DataFormatters/CXXFormatterFunctions.cpp
URL: http://llvm.org/viewvc/llvm-project/lldb/trunk/source/DataFormatters/CXXFormatterFunctions.cpp?rev=220894&r1=220893&r2=220894&view=diff
==============================================================================
--- lldb/trunk/source/DataFormatters/CXXFormatterFunctions.cpp (original)
+++ lldb/trunk/source/DataFormatters/CXXFormatterFunctions.cpp Wed Oct 29 20:45:39 2014
@@ -10,6 +10,7 @@
 #include "lldb/lldb-python.h"
 
 #include "lldb/DataFormatters/CXXFormatterFunctions.h"
+#include "lldb/DataFormatters/StringPrinter.h"
 
 #include "llvm/Support/ConvertUTF.h"
 
@@ -189,281 +190,6 @@ lldb_private::formatters::CallSelectorOn
     return valobj_sp;
 }
 
-// use this call if you already have an LLDB-side buffer for the data
-template<typename SourceDataType>
-static bool
-DumpUTFBufferToStream (ConversionResult (*ConvertFunction) (const SourceDataType**,
-                                                            const SourceDataType*,
-                                                            UTF8**,
-                                                            UTF8*,
-                                                            ConversionFlags),
-                       DataExtractor& data,
-                       Stream& stream,
-                       char prefix_token = '@',
-                       char quote = '"',
-                       uint32_t sourceSize = 0)
-{
-    if (prefix_token != 0)
-        stream.Printf("%c",prefix_token);
-    if (quote != 0)
-        stream.Printf("%c",quote);
-    if (data.GetByteSize() && data.GetDataStart() && data.GetDataEnd())
-    {
-        const int bufferSPSize = data.GetByteSize();
-        if (sourceSize == 0)
-        {
-            const int origin_encoding = 8*sizeof(SourceDataType);
-            sourceSize = bufferSPSize/(origin_encoding / 4);
-        }
-        
-        SourceDataType *data_ptr = (SourceDataType*)data.GetDataStart();
-        SourceDataType *data_end_ptr = data_ptr + sourceSize;
-        
-        while (data_ptr < data_end_ptr)
-        {
-            if (!*data_ptr)
-            {
-                data_end_ptr = data_ptr;
-                break;
-            }
-            data_ptr++;
-        }
-        
-        data_ptr = (SourceDataType*)data.GetDataStart();
-        
-        lldb::DataBufferSP utf8_data_buffer_sp;
-        UTF8* utf8_data_ptr = nullptr;
-        UTF8* utf8_data_end_ptr = nullptr;
-        
-        if (ConvertFunction)
-        {
-            utf8_data_buffer_sp.reset(new DataBufferHeap(4*bufferSPSize,0));
-            utf8_data_ptr = (UTF8*)utf8_data_buffer_sp->GetBytes();
-            utf8_data_end_ptr = utf8_data_ptr + utf8_data_buffer_sp->GetByteSize();
-            ConvertFunction ( (const SourceDataType**)&data_ptr, data_end_ptr, &utf8_data_ptr, utf8_data_end_ptr, lenientConversion );
-            utf8_data_ptr = (UTF8*)utf8_data_buffer_sp->GetBytes(); // needed because the ConvertFunction will change the value of the data_ptr
-        }
-        else
-        {
-            // just copy the pointers - the cast is necessary to make the compiler happy
-            // but this should only happen if we are reading UTF8 data
-            utf8_data_ptr = (UTF8*)data_ptr;
-            utf8_data_end_ptr = (UTF8*)data_end_ptr;
-        }
-        
-        // since we tend to accept partial data (and even partially malformed data)
-        // we might end up with no NULL terminator before the end_ptr
-        // hence we need to take a slower route and ensure we stay within boundaries
-        for (;utf8_data_ptr != utf8_data_end_ptr; utf8_data_ptr++)
-        {
-            if (!*utf8_data_ptr)
-                break;
-            stream.Printf("%c",*utf8_data_ptr);
-        }
-    }
-    if (quote != 0)
-        stream.Printf("%c",quote);
-    return true;
-}
-
-template<typename SourceDataType>
-class ReadUTFBufferAndDumpToStreamOptions
-{
-public:
-    typedef ConversionResult (*ConvertFunctionType) (const SourceDataType**,
-                                                     const SourceDataType*,
-                                                     UTF8**,
-                                                     UTF8*,
-                                                     ConversionFlags);
-    
-    ReadUTFBufferAndDumpToStreamOptions () :
-    m_conversion_function(NULL),
-    m_location(0),
-    m_process_sp(),
-    m_stream(NULL),
-    m_prefix_token('@'),
-    m_quote('"'),
-    m_source_size(0),
-    m_needs_zero_termination(true)
-    {
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetConversionFunction (ConvertFunctionType f)
-    {
-        m_conversion_function = f;
-        return *this;
-    }
-    
-    ConvertFunctionType
-    GetConversionFunction () const
-    {
-        return m_conversion_function;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetLocation (uint64_t l)
-    {
-        m_location = l;
-        return *this;
-    }
-    
-    uint64_t
-    GetLocation () const
-    {
-        return m_location;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetProcessSP (ProcessSP p)
-    {
-        m_process_sp = p;
-        return *this;
-    }
-    
-    ProcessSP
-    GetProcessSP () const
-    {
-        return m_process_sp;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetStream (Stream* s)
-    {
-        m_stream = s;
-        return *this;
-    }
-    
-    Stream*
-    GetStream () const
-    {
-        return m_stream;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetPrefixToken (char p)
-    {
-        m_prefix_token = p;
-        return *this;
-    }
-    
-    char
-    GetPrefixToken () const
-    {
-        return m_prefix_token;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetQuote (char q)
-    {
-        m_quote = q;
-        return *this;
-    }
-    
-    char
-    GetQuote () const
-    {
-        return m_quote;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetSourceSize (uint32_t s)
-    {
-        m_source_size = s;
-        return *this;
-    }
-    
-    uint32_t
-    GetSourceSize () const
-    {
-        return m_source_size;
-    }
-    
-    ReadUTFBufferAndDumpToStreamOptions&
-    SetNeedsZeroTermination (bool z)
-    {
-        m_needs_zero_termination = z;
-        return *this;
-    }
-    
-    bool
-    GetNeedsZeroTermination () const
-    {
-        return m_needs_zero_termination;
-    }
-    
-private:
-    ConvertFunctionType m_conversion_function;
-    uint64_t m_location;
-    ProcessSP m_process_sp;
-    Stream* m_stream;
-    char m_prefix_token;
-    char m_quote;
-    uint32_t m_source_size;
-    bool m_needs_zero_termination;
-};
-
-template<typename SourceDataType>
-static bool
-ReadUTFBufferAndDumpToStream (const ReadUTFBufferAndDumpToStreamOptions<SourceDataType>& options)
-{
-    if (options.GetLocation() == 0 || options.GetLocation() == LLDB_INVALID_ADDRESS)
-        return false;
-    
-    ProcessSP process_sp(options.GetProcessSP());
-    
-    if (!process_sp)
-        return false;
-
-    const int type_width = sizeof(SourceDataType);
-    const int origin_encoding = 8 * type_width ;
-    if (origin_encoding != 8 && origin_encoding != 16 && origin_encoding != 32)
-        return false;
-    // if not UTF8, I need a conversion function to return proper UTF8
-    if (origin_encoding != 8 && !options.GetConversionFunction())
-        return false;
-    
-    if (!options.GetStream())
-        return false;
-
-    uint32_t sourceSize = options.GetSourceSize();
-    bool needs_zero_terminator = options.GetNeedsZeroTermination();
-    
-    if (!sourceSize)
-    {
-        sourceSize = process_sp->GetTarget().GetMaximumSizeOfStringSummary();
-        needs_zero_terminator = true;
-    }
-    else
-        sourceSize = std::min(sourceSize,process_sp->GetTarget().GetMaximumSizeOfStringSummary());
-    
-    const int bufferSPSize = sourceSize * type_width;
-
-    lldb::DataBufferSP buffer_sp(new DataBufferHeap(bufferSPSize,0));
-    
-    if (!buffer_sp->GetBytes())
-        return false;
-    
-    Error error;
-    char *buffer = reinterpret_cast<char *>(buffer_sp->GetBytes()); 
-
-    size_t data_read = 0;
-    if (needs_zero_terminator)
-        data_read = process_sp->ReadStringFromMemory(options.GetLocation(), buffer, bufferSPSize, error, type_width);
-    else
-        data_read = process_sp->ReadMemoryFromInferior(options.GetLocation(), (char*)buffer_sp->GetBytes(), bufferSPSize, error);
-
-    if (error.Fail() || data_read == 0)
-    {
-        options.GetStream()->Printf("unable to read data");
-        return true;
-    }
-    
-    DataExtractor data(buffer_sp, process_sp->GetByteOrder(), process_sp->GetAddressByteSize());
-    
-    return DumpUTFBufferToStream(options.GetConversionFunction(), data, *options.GetStream(), options.GetPrefixToken(), options.GetQuote(), sourceSize);
-}
-
 bool
 lldb_private::formatters::Char16StringSummaryProvider (ValueObject& valobj, Stream& stream)
 {
@@ -476,14 +202,13 @@ lldb_private::formatters::Char16StringSu
     if (!valobj_addr)
         return false;
     
-    ReadUTFBufferAndDumpToStreamOptions<UTF16> options;
+    ReadStringAndDumpToStreamOptions options;
     options.SetLocation(valobj_addr);
-    options.SetConversionFunction(ConvertUTF16toUTF8);
     options.SetProcessSP(process_sp);
     options.SetStream(&stream);
     options.SetPrefixToken('u');
     
-    if (!ReadUTFBufferAndDumpToStream(options))
+    if (!ReadStringAndDumpToStream<StringElementType::UTF16>(options))
     {
         stream.Printf("Summary Unavailable");
         return true;
@@ -504,14 +229,13 @@ lldb_private::formatters::Char32StringSu
     if (!valobj_addr)
         return false;
     
-    ReadUTFBufferAndDumpToStreamOptions<UTF32> options;
+    ReadStringAndDumpToStreamOptions options;
     options.SetLocation(valobj_addr);
-    options.SetConversionFunction(ConvertUTF32toUTF8);
     options.SetProcessSP(process_sp);
     options.SetStream(&stream);
     options.SetPrefixToken('U');
     
-    if (!ReadUTFBufferAndDumpToStream(options))
+    if (!ReadStringAndDumpToStream<StringElementType::UTF32>(options))
     {
         stream.Printf("Summary Unavailable");
         return true;
@@ -545,45 +269,20 @@ lldb_private::formatters::WCharStringSum
     ClangASTType wchar_clang_type = ClangASTContext::GetBasicType(ast, lldb::eBasicTypeWChar);
     const uint32_t wchar_size = wchar_clang_type.GetBitSize();
 
+    ReadStringAndDumpToStreamOptions options;
+    options.SetLocation(data_addr);
+    options.SetProcessSP(process_sp);
+    options.SetStream(&stream);
+    options.SetPrefixToken('L');
+    
     switch (wchar_size)
     {
         case 8:
-        {
-            // utf 8
-            
-            ReadUTFBufferAndDumpToStreamOptions<UTF8> options;
-            options.SetLocation(data_addr);
-            options.SetConversionFunction(nullptr);
-            options.SetProcessSP(process_sp);
-            options.SetStream(&stream);
-            options.SetPrefixToken('L');
-
-            return ReadUTFBufferAndDumpToStream(options);
-        }
+            return ReadStringAndDumpToStream<StringElementType::UTF8>(options);
         case 16:
-        {
-            // utf 16
-            ReadUTFBufferAndDumpToStreamOptions<UTF16> options;
-            options.SetLocation(data_addr);
-            options.SetConversionFunction(ConvertUTF16toUTF8);
-            options.SetProcessSP(process_sp);
-            options.SetStream(&stream);
-            options.SetPrefixToken('L');
-            
-            return ReadUTFBufferAndDumpToStream(options);
-        }
+            return ReadStringAndDumpToStream<StringElementType::UTF16>(options);
         case 32:
-        {
-            // utf 32
-            ReadUTFBufferAndDumpToStreamOptions<UTF32> options;
-            options.SetLocation(data_addr);
-            options.SetConversionFunction(ConvertUTF32toUTF8);
-            options.SetProcessSP(process_sp);
-            options.SetStream(&stream);
-            options.SetPrefixToken('L');
-            
-            return ReadUTFBufferAndDumpToStream(options);
-        }
+            return ReadStringAndDumpToStream<StringElementType::UTF32>(options);
         default:
             stream.Printf("size for wchar_t is not valid");
             return true;
@@ -606,7 +305,14 @@ lldb_private::formatters::Char16SummaryP
     if (!value.empty())
         stream.Printf("%s ", value.c_str());
 
-    return DumpUTFBufferToStream<UTF16>(ConvertUTF16toUTF8,data,stream, 'u','\'',1);
+    ReadBufferAndDumpToStreamOptions options;
+    options.SetData(data);
+    options.SetStream(&stream);
+    options.SetPrefixToken('u');
+    options.SetQuote('\'');
+    options.SetSourceSize(1);
+    
+    return ReadBufferAndDumpToStream<StringElementType::UTF16>(options);
 }
 
 bool
@@ -624,7 +330,14 @@ lldb_private::formatters::Char32SummaryP
     if (!value.empty())
         stream.Printf("%s ", value.c_str());
     
-    return DumpUTFBufferToStream<UTF32>(ConvertUTF32toUTF8,data,stream, 'U','\'',1);
+    ReadBufferAndDumpToStreamOptions options;
+    options.SetData(data);
+    options.SetStream(&stream);
+    options.SetPrefixToken('U');
+    options.SetQuote('\'');
+    options.SetSourceSize(1);
+    
+    return ReadBufferAndDumpToStream<StringElementType::UTF32>(options);
 }
 
 bool
@@ -637,55 +350,14 @@ lldb_private::formatters::WCharSummaryPr
     if (error.Fail())
         return false;
     
-    clang::ASTContext* ast = valobj.GetClangType().GetASTContext();
-    
-    if (!ast)
-        return false;
-    
-    ClangASTType wchar_clang_type = ClangASTContext::GetBasicType(ast, lldb::eBasicTypeWChar);
-    const uint32_t wchar_size = wchar_clang_type.GetBitSize();
-    std::string value;
+    ReadBufferAndDumpToStreamOptions options;
+    options.SetData(data);
+    options.SetStream(&stream);
+    options.SetPrefixToken('L');
+    options.SetQuote('\'');
+    options.SetSourceSize(1);
     
-    switch (wchar_size)
-    {
-        case 8:
-            // utf 8
-            valobj.GetValueAsCString(lldb::eFormatChar, value);
-            if (!value.empty())
-                stream.Printf("%s ", value.c_str());
-            return DumpUTFBufferToStream<UTF8>(nullptr,
-                                               data,
-                                               stream,
-                                               'L',
-                                               '\'',
-                                               1);
-        case 16:
-            // utf 16
-            valobj.GetValueAsCString(lldb::eFormatUnicode16, value);
-            if (!value.empty())
-                stream.Printf("%s ", value.c_str());
-            return DumpUTFBufferToStream<UTF16>(ConvertUTF16toUTF8,
-                                                data,
-                                                stream,
-                                                'L',
-                                                '\'',
-                                                1);
-        case 32:
-            // utf 32
-            valobj.GetValueAsCString(lldb::eFormatUnicode32, value);
-            if (!value.empty())
-                stream.Printf("%s ", value.c_str());
-            return DumpUTFBufferToStream<UTF32>(ConvertUTF32toUTF8,
-                                                data,
-                                                stream,
-                                                'L',
-                                                '\'',
-                                                1);
-        default:
-            stream.Printf("size for wchar_t is not valid");
-            return true;
-    }
-    return true;
+    return ReadBufferAndDumpToStream<StringElementType::UTF16>(options);
 }
 
 // the field layout in a libc++ string (cap, side, data or data, size, cap)
@@ -1153,8 +825,7 @@ lldb_private::formatters::NSStringSummar
             return false;
         if (has_explicit_length && is_unicode)
         {
-            ReadUTFBufferAndDumpToStreamOptions<UTF16> options;
-            options.SetConversionFunction(ConvertUTF16toUTF8);
+            ReadStringAndDumpToStreamOptions options;
             options.SetLocation(location);
             options.SetProcessSP(process_sp);
             options.SetStream(&stream);
@@ -1162,10 +833,20 @@ lldb_private::formatters::NSStringSummar
             options.SetQuote('"');
             options.SetSourceSize(explicit_length);
             options.SetNeedsZeroTermination(false);
-            return ReadUTFBufferAndDumpToStream (options);
+            return ReadStringAndDumpToStream<StringElementType::UTF16>(options);
         }
         else
-            return ReadAsciiBufferAndDumpToStream(location+1,process_sp,stream, explicit_length);
+        {
+            ReadStringAndDumpToStreamOptions options;
+            options.SetLocation(location+1);
+            options.SetProcessSP(process_sp);
+            options.SetStream(&stream);
+            options.SetPrefixToken('@');
+            options.SetSourceSize(explicit_length);
+            options.SetNeedsZeroTermination(false);
+            
+            return ReadStringAndDumpToStream<StringElementType::ASCII>(options);
+        }
     }
     else if (is_inline && has_explicit_length && !is_unicode && !is_special && !is_mutable)
     {
@@ -1191,8 +872,7 @@ lldb_private::formatters::NSStringSummar
             if (error.Fail())
                 return false;
         }
-        ReadUTFBufferAndDumpToStreamOptions<UTF16> options;
-        options.SetConversionFunction(ConvertUTF16toUTF8);
+        ReadStringAndDumpToStreamOptions options;
         options.SetLocation(location);
         options.SetProcessSP(process_sp);
         options.SetStream(&stream);
@@ -1200,7 +880,7 @@ lldb_private::formatters::NSStringSummar
         options.SetQuote('"');
         options.SetSourceSize(explicit_length);
         options.SetNeedsZeroTermination(has_explicit_length == false);
-        return ReadUTFBufferAndDumpToStream (options);
+        return ReadStringAndDumpToStream<StringElementType::UTF16> (options);
     }
     else if (is_special)
     {
@@ -1208,8 +888,7 @@ lldb_private::formatters::NSStringSummar
         explicit_length = reader.GetField<uint32_t>(ConstString("lengthAndRef")) >> 20;
         lldb::addr_t location = valobj.GetValueAsUnsigned(0) + ptr_size + 4;
         
-        ReadUTFBufferAndDumpToStreamOptions<UTF16> options;
-        options.SetConversionFunction(ConvertUTF16toUTF8);
+        ReadStringAndDumpToStreamOptions options;
         options.SetLocation(location);
         options.SetProcessSP(process_sp);
         options.SetStream(&stream);
@@ -1217,14 +896,20 @@ lldb_private::formatters::NSStringSummar
         options.SetQuote('"');
         options.SetSourceSize(explicit_length);
         options.SetNeedsZeroTermination(has_explicit_length == false);
-        return ReadUTFBufferAndDumpToStream (options);
+        return ReadStringAndDumpToStream<StringElementType::UTF16> (options);
     }
     else if (is_inline)
     {
         uint64_t location = valobj_addr + 2*ptr_size;
         if (!has_explicit_length)
             location++;
-        return ReadAsciiBufferAndDumpToStream(location,process_sp,stream,explicit_length);
+        ReadStringAndDumpToStreamOptions options;
+        options.SetLocation(location);
+        options.SetProcessSP(process_sp);
+        options.SetStream(&stream);
+        options.SetPrefixToken('@');
+        options.SetSourceSize(explicit_length);
+        return ReadStringAndDumpToStream<StringElementType::ASCII>(options);
     }
     else
     {
@@ -1234,7 +919,13 @@ lldb_private::formatters::NSStringSummar
             return false;
         if (has_explicit_length && !has_null)
             explicit_length++; // account for the fact that there is no NULL and we need to have one added
-        return ReadAsciiBufferAndDumpToStream(location,process_sp,stream,explicit_length);
+        ReadStringAndDumpToStreamOptions options;
+        options.SetLocation(location);
+        options.SetProcessSP(process_sp);
+        options.SetPrefixToken('@');
+        options.SetStream(&stream);
+        options.SetSourceSize(explicit_length);
+        return ReadStringAndDumpToStream<StringElementType::ASCII>(options);
     }
 }
 

Added: lldb/trunk/source/DataFormatters/StringPrinter.cpp
URL: http://llvm.org/viewvc/llvm-project/lldb/trunk/source/DataFormatters/StringPrinter.cpp?rev=220894&view=auto
==============================================================================
--- lldb/trunk/source/DataFormatters/StringPrinter.cpp (added)
+++ lldb/trunk/source/DataFormatters/StringPrinter.cpp Wed Oct 29 20:45:39 2014
@@ -0,0 +1,618 @@
+//===-- StringPrinter.cpp ----------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "lldb/DataFormatters/StringPrinter.h"
+
+#include "lldb/Core/DataExtractor.h"
+#include "lldb/Core/Error.h"
+#include "lldb/Target/Process.h"
+#include "lldb/Target/Target.h"
+
+#include "llvm/Support/ConvertUTF.h"
+
+#include <codecvt>
+#include <ctype.h>
+#include <functional>
+#include <locale>
+
+using namespace lldb;
+using namespace lldb_private;
+using namespace lldb_private::formatters;
+
+// I can't use a std::unique_ptr for this because the Deleter is a template argument there
+// and I want the same type to represent both pointers I want to free and pointers I don't need
+// to free - which is what this class essentially is
+// It's very specialized to the needs of this file, and not suggested for general use
+template <typename T = uint8_t, typename U = char, typename S = size_t>
+struct StringPrinterBufferPointer
+{
+public:
+    
+    typedef std::function<void(const T*)> Deleter;
+    
+    StringPrinterBufferPointer (std::nullptr_t ptr) :
+    m_data(nullptr),
+    m_size(0),
+    m_deleter()
+    {}
+    
+    StringPrinterBufferPointer(const T* bytes, S size, Deleter deleter = nullptr) :
+    m_data(bytes),
+    m_size(size),
+    m_deleter(deleter)
+    {}
+    
+    StringPrinterBufferPointer(const U* bytes, S size, Deleter deleter = nullptr) :
+    m_data((T*)bytes),
+    m_size(size),
+    m_deleter(deleter)
+    {}
+    
+    StringPrinterBufferPointer(StringPrinterBufferPointer&& rhs) :
+    m_data(rhs.m_data),
+    m_size(rhs.m_size),
+    m_deleter(rhs.m_deleter)
+    {
+        rhs.m_data = nullptr;
+    }
+    
+    StringPrinterBufferPointer(const StringPrinterBufferPointer& rhs) :
+    m_data(rhs.m_data),
+    m_size(rhs.m_size),
+    m_deleter(rhs.m_deleter)
+    {
+        rhs.m_data = nullptr; // this is why m_data has to be mutable
+    }
+    
+    const T*
+    GetBytes () const
+    {
+        return m_data;
+    }
+    
+    const S
+    GetSize () const
+    {
+        return m_size;
+    }
+    
+    ~StringPrinterBufferPointer ()
+    {
+        if (m_data && m_deleter)
+            m_deleter(m_data);
+        m_data = nullptr;
+    }
+    
+    StringPrinterBufferPointer&
+    operator = (const StringPrinterBufferPointer& rhs)
+    {
+        if (m_data && m_deleter)
+            m_deleter(m_data);
+        m_data = rhs.m_data;
+        m_size = rhs.m_size;
+        m_deleter = rhs.m_deleter;
+        rhs.m_data = nullptr;
+        return *this;
+    }
+    
+private:
+    mutable const T* m_data;
+    size_t m_size;
+    Deleter m_deleter;
+};
+
+// we define this for all values of type but only implement it for those we care about
+// that's good because we get linker errors for any unsupported type
+template <StringElementType type>
+static StringPrinterBufferPointer<>
+GetPrintableImpl(uint8_t* buffer, uint8_t* buffer_end, uint8_t*& next);
+
+// mimic isprint() for Unicode codepoints
+static bool
+isprint(char32_t codepoint)
+{
+    if (codepoint <= 0x1F || codepoint == 0x7F) // C0
+    {
+        return false;
+    }
+    if (codepoint >= 0x80 && codepoint <= 0x9F) // C1
+    {
+        return false;
+    }
+    if (codepoint == 0x2028 || codepoint == 0x2029) // line/paragraph separators
+    {
+        return false;
+    }
+    if (codepoint == 0x200E || codepoint == 0x200F || (codepoint >= 0x202A && codepoint <= 0x202E)) // bidirectional text control
+    {
+        return false;
+    }
+    if (codepoint >= 0xFFF9 && codepoint <= 0xFFFF) // interlinears and generally specials
+    {
+        return false;
+    }
+    return true;
+}
+
+template <>
+StringPrinterBufferPointer<>
+GetPrintableImpl<StringElementType::ASCII> (uint8_t* buffer, uint8_t* buffer_end, uint8_t*& next)
+{
+    StringPrinterBufferPointer<> retval = {nullptr};
+    
+    switch (*buffer)
+    {
+        case '\a':
+            retval = {"\\a",2};
+            break;
+        case '\b':
+            retval = {"\\b",2};
+            break;
+        case '\f':
+            retval = {"\\f",2};
+            break;
+        case '\n':
+            retval = {"\\n",2};
+            break;
+        case '\r':
+            retval = {"\\r",2};
+            break;
+        case '\t':
+            retval = {"\\t",2};
+            break;
+        case '\v':
+            retval = {"\\v",2};
+            break;
+        case '\"':
+            retval = {"\\\"",2};
+            break;
+        case '\\':
+            retval = {"\\\\",2};
+            break;
+        default:
+          if (isprint(*buffer))
+            retval = {buffer,1};
+          else
+          {
+            retval = { new uint8_t[5],4,[] (const uint8_t* c) {delete[] c;} };
+            sprintf((char*)retval.GetBytes(),"\\x%02x",*buffer);
+            break;
+          }
+    }
+    
+    next = buffer + 1;
+    return retval;
+}
+
+static char32_t
+ConvertUTF8ToCodePoint (unsigned char c0, unsigned char c1)
+{
+    return (c0-192)*64+(c1-128);
+}
+static char32_t
+ConvertUTF8ToCodePoint (unsigned char c0, unsigned char c1, unsigned char c2)
+{
+    return (c0-224)*4096+(c1-128)*64+(c2-128);
+}
+static char32_t
+ConvertUTF8ToCodePoint (unsigned char c0, unsigned char c1, unsigned char c2, unsigned char c3)
+{
+    return (c0-240)*262144+(c2-128)*4096+(c2-128)*64+(c3-128);
+}
+
+template <>
+StringPrinterBufferPointer<>
+GetPrintableImpl<StringElementType::UTF8> (uint8_t* buffer, uint8_t* buffer_end, uint8_t*& next)
+{
+    StringPrinterBufferPointer<> retval {nullptr};
+    
+    unsigned utf8_encoded_len = getNumBytesForUTF8(*buffer);
+    
+    if (1+buffer_end-buffer < utf8_encoded_len)
+    {
+        // I don't have enough bytes - print whatever I have left
+        retval = {buffer,static_cast<size_t>(1+buffer_end-buffer)};
+        next = buffer_end+1;
+        return retval;
+    }
+    
+    char32_t codepoint = 0;
+    switch (utf8_encoded_len)
+    {
+        case 1:
+            // this is just an ASCII byte - ask ASCII
+            return GetPrintableImpl<StringElementType::ASCII>(buffer, buffer_end, next);
+        case 2:
+            codepoint = ConvertUTF8ToCodePoint((unsigned char)*buffer, (unsigned char)*(buffer+1));
+            break;
+        case 3:
+            codepoint = ConvertUTF8ToCodePoint((unsigned char)*buffer, (unsigned char)*(buffer+1), (unsigned char)*(buffer+2));
+            break;
+        case 4:
+            codepoint = ConvertUTF8ToCodePoint((unsigned char)*buffer, (unsigned char)*(buffer+1), (unsigned char)*(buffer+2), (unsigned char)*(buffer+3));
+            break;
+        default:
+            // this is probably some bogus non-character thing
+            // just print it as-is and hope to sync up again soon
+            retval = {buffer,1};
+            next = buffer+1;
+            return retval;
+    }
+    
+    if (codepoint)
+    {
+        switch (codepoint)
+        {
+            case '\a':
+                retval = {"\\a",2};
+                break;
+            case '\b':
+                retval = {"\\b",2};
+                break;
+            case '\f':
+                retval = {"\\f",2};
+                break;
+            case '\n':
+                retval = {"\\n",2};
+                break;
+            case '\r':
+                retval = {"\\r",2};
+                break;
+            case '\t':
+                retval = {"\\t",2};
+                break;
+            case '\v':
+                retval = {"\\v",2};
+                break;
+            case '\"':
+                retval = {"\\\"",2};
+                break;
+            case '\\':
+                retval = {"\\\\",2};
+                break;
+            default:
+                if (isprint(codepoint))
+                    retval = {buffer,utf8_encoded_len};
+                else
+                {
+                    retval = { new uint8_t[11],10,[] (const uint8_t* c) {delete[] c;} };
+                    sprintf((char*)retval.GetBytes(),"\\U%08x",codepoint);
+                    break;
+                }
+        }
+        
+        next = buffer + utf8_encoded_len;
+        return retval;
+    }
+    
+    // this should not happen - but just in case.. try to resync at some point
+    retval = {buffer,1};
+    next = buffer+1;
+    return retval;
+}
+
+// Given a sequence of bytes, this function returns:
+// a sequence of bytes to actually print out + a length
+// the following unscanned position of the buffer is in next
+static StringPrinterBufferPointer<>
+GetPrintable(StringElementType type, uint8_t* buffer, uint8_t* buffer_end, uint8_t*& next)
+{
+    if (!buffer)
+        return {nullptr};
+    
+    switch (type)
+    {
+        case StringElementType::ASCII:
+            return GetPrintableImpl<StringElementType::ASCII>(buffer, buffer_end, next);
+        case StringElementType::UTF8:
+            return GetPrintableImpl<StringElementType::UTF8>(buffer, buffer_end, next);
+        default:
+            return {nullptr};
+    }
+}
+
+template <>
+bool
+lldb_private::formatters::ReadStringAndDumpToStream<StringElementType::ASCII> (ReadStringAndDumpToStreamOptions options)
+{
+    assert(options.GetStream() && "need a Stream to print the string to");
+    Error my_error;
+    size_t my_data_read;
+    
+    ProcessSP process_sp(options.GetProcessSP());
+    
+    if (process_sp.get() == nullptr || options.GetLocation() == 0)
+        return false;
+    
+    size_t size;
+    
+    if (options.GetSourceSize() == 0)
+        size = process_sp->GetTarget().GetMaximumSizeOfStringSummary();
+    else
+        size = std::min(options.GetSourceSize(),process_sp->GetTarget().GetMaximumSizeOfStringSummary());
+    
+    lldb::DataBufferSP buffer_sp(new DataBufferHeap(size,0));
+    
+    my_data_read = process_sp->ReadCStringFromMemory(options.GetLocation(), (char*)buffer_sp->GetBytes(), size, my_error);
+    
+    if (my_error.Fail())
+        return false;
+    
+    char prefix_token = options.GetPrefixToken();
+    char quote = options.GetQuote();
+    
+    if (prefix_token != 0)
+        options.GetStream()->Printf("%c%c",prefix_token,quote);
+    else if (quote != 0)
+        options.GetStream()->Printf("%c",quote);
+    
+    uint8_t* data_end = buffer_sp->GetBytes()+buffer_sp->GetByteSize();
+    
+    // since we tend to accept partial data (and even partially malformed data)
+    // we might end up with no NULL terminator before the end_ptr
+    // hence we need to take a slower route and ensure we stay within boundaries
+    for (uint8_t* data = buffer_sp->GetBytes(); *data && (data < data_end);)
+    {
+        if (options.GetEscapeNonPrintables())
+        {
+            uint8_t* next_data = nullptr;
+            auto printable = GetPrintable(StringElementType::ASCII, data, data_end, next_data);
+            auto printable_bytes = printable.GetBytes();
+            auto printable_size = printable.GetSize();
+            if (!printable_bytes || !next_data)
+            {
+                // GetPrintable() failed on us - print one byte in a desperate resync attempt
+                printable_bytes = data;
+                printable_size = 1;
+                next_data = data+1;
+            }
+            for (int c = 0; c < printable_size; c++)
+                options.GetStream()->Printf("%c", *(printable_bytes+c));
+            data = (uint8_t*)next_data;
+        }
+        else
+        {
+            options.GetStream()->Printf("%c",*data);
+            data++;
+        }
+    }
+    
+    if (quote != 0)
+        options.GetStream()->Printf("%c",quote);
+    
+    return true;
+}
+
+// use this call if you already have an LLDB-side buffer for the data
+template<typename SourceDataType>
+static bool
+DumpUTFBufferToStream (ConversionResult (*ConvertFunction) (const SourceDataType**,
+                                                            const SourceDataType*,
+                                                            UTF8**,
+                                                            UTF8*,
+                                                            ConversionFlags),
+                       const DataExtractor& data,
+                       Stream& stream,
+                       char prefix_token,
+                       char quote,
+                       uint32_t sourceSize,
+                       bool escapeNonPrintables)
+{
+    if (prefix_token != 0)
+        stream.Printf("%c",prefix_token);
+    if (quote != 0)
+        stream.Printf("%c",quote);
+    if (data.GetByteSize() && data.GetDataStart() && data.GetDataEnd())
+    {
+        const int bufferSPSize = data.GetByteSize();
+        if (sourceSize == 0)
+        {
+            const int origin_encoding = 8*sizeof(SourceDataType);
+            sourceSize = bufferSPSize/(origin_encoding / 4);
+        }
+        
+        SourceDataType *data_ptr = (SourceDataType*)data.GetDataStart();
+        SourceDataType *data_end_ptr = data_ptr + sourceSize;
+        
+        while (data_ptr < data_end_ptr)
+        {
+            if (!*data_ptr)
+            {
+                data_end_ptr = data_ptr;
+                break;
+            }
+            data_ptr++;
+        }
+        
+        data_ptr = (SourceDataType*)data.GetDataStart();
+        
+        lldb::DataBufferSP utf8_data_buffer_sp;
+        UTF8* utf8_data_ptr = nullptr;
+        UTF8* utf8_data_end_ptr = nullptr;
+        
+        if (ConvertFunction)
+        {
+            utf8_data_buffer_sp.reset(new DataBufferHeap(4*bufferSPSize,0));
+            utf8_data_ptr = (UTF8*)utf8_data_buffer_sp->GetBytes();
+            utf8_data_end_ptr = utf8_data_ptr + utf8_data_buffer_sp->GetByteSize();
+            ConvertFunction ( (const SourceDataType**)&data_ptr, data_end_ptr, &utf8_data_ptr, utf8_data_end_ptr, lenientConversion );
+            utf8_data_ptr = (UTF8*)utf8_data_buffer_sp->GetBytes(); // needed because the ConvertFunction will change the value of the data_ptr
+        }
+        else
+        {
+            // just copy the pointers - the cast is necessary to make the compiler happy
+            // but this should only happen if we are reading UTF8 data
+            utf8_data_ptr = (UTF8*)data_ptr;
+            utf8_data_end_ptr = (UTF8*)data_end_ptr;
+        }
+        
+        // since we tend to accept partial data (and even partially malformed data)
+        // we might end up with no NULL terminator before the end_ptr
+        // hence we need to take a slower route and ensure we stay within boundaries
+        for (;utf8_data_ptr < utf8_data_end_ptr;)
+        {
+            if (!*utf8_data_ptr)
+                break;
+            
+            if (escapeNonPrintables)
+            {
+                uint8_t* next_data = nullptr;
+                auto printable = GetPrintable(StringElementType::UTF8, utf8_data_ptr, utf8_data_end_ptr, next_data);
+                auto printable_bytes = printable.GetBytes();
+                auto printable_size = printable.GetSize();
+                if (!printable_bytes || !next_data)
+                {
+                    // GetPrintable() failed on us - print one byte in a desperate resync attempt
+                    printable_bytes = utf8_data_ptr;
+                    printable_size = 1;
+                    next_data = utf8_data_ptr+1;
+                }
+                for (int c = 0; c < printable_size; c++)
+                    stream.Printf("%c", *(printable_bytes+c));
+                utf8_data_ptr = (uint8_t*)next_data;
+            }
+            else
+            {
+                stream.Printf("%c",*utf8_data_ptr);
+                utf8_data_ptr++;
+            }
+        }
+    }
+    if (quote != 0)
+        stream.Printf("%c",quote);
+    return true;
+}
+
+template<typename SourceDataType>
+static bool
+ReadUTFBufferAndDumpToStream (const ReadStringAndDumpToStreamOptions& options,
+                              ConversionResult (*ConvertFunction) (const SourceDataType**,
+                                                                   const SourceDataType*,
+                                                                   UTF8**,
+                                                                   UTF8*,
+                                                                   ConversionFlags))
+{
+    assert(options.GetStream() && "need a Stream to print the string to");
+
+    if (options.GetLocation() == 0 || options.GetLocation() == LLDB_INVALID_ADDRESS)
+        return false;
+    
+    lldb::ProcessSP process_sp(options.GetProcessSP());
+    
+    if (!process_sp)
+        return false;
+    
+    const int type_width = sizeof(SourceDataType);
+    const int origin_encoding = 8 * type_width ;
+    if (origin_encoding != 8 && origin_encoding != 16 && origin_encoding != 32)
+        return false;
+    // if not UTF8, I need a conversion function to return proper UTF8
+    if (origin_encoding != 8 && !ConvertFunction)
+        return false;
+    
+    if (!options.GetStream())
+        return false;
+    
+    uint32_t sourceSize = options.GetSourceSize();
+    bool needs_zero_terminator = options.GetNeedsZeroTermination();
+    
+    if (!sourceSize)
+    {
+        sourceSize = process_sp->GetTarget().GetMaximumSizeOfStringSummary();
+        needs_zero_terminator = true;
+    }
+    else
+        sourceSize = std::min(sourceSize,process_sp->GetTarget().GetMaximumSizeOfStringSummary());
+    
+    const int bufferSPSize = sourceSize * type_width;
+    
+    lldb::DataBufferSP buffer_sp(new DataBufferHeap(bufferSPSize,0));
+    
+    if (!buffer_sp->GetBytes())
+        return false;
+    
+    Error error;
+    char *buffer = reinterpret_cast<char *>(buffer_sp->GetBytes());
+    
+    size_t data_read = 0;
+    if (needs_zero_terminator)
+        data_read = process_sp->ReadStringFromMemory(options.GetLocation(), buffer, bufferSPSize, error, type_width);
+    else
+        data_read = process_sp->ReadMemoryFromInferior(options.GetLocation(), (char*)buffer_sp->GetBytes(), bufferSPSize, error);
+    
+    if (error.Fail() || data_read == 0)
+    {
+        options.GetStream()->Printf("unable to read data");
+        return true;
+    }
+    
+    DataExtractor data(buffer_sp, process_sp->GetByteOrder(), process_sp->GetAddressByteSize());
+    
+    return DumpUTFBufferToStream(ConvertFunction, data, *options.GetStream(), options.GetPrefixToken(), options.GetQuote(), sourceSize, options.GetEscapeNonPrintables());
+}
+
+template <>
+bool
+lldb_private::formatters::ReadStringAndDumpToStream<StringElementType::UTF8> (ReadStringAndDumpToStreamOptions options)
+{
+    return ReadUTFBufferAndDumpToStream<UTF8>(options,
+                                              nullptr);
+}
+
+template <>
+bool
+lldb_private::formatters::ReadStringAndDumpToStream<StringElementType::UTF16> (ReadStringAndDumpToStreamOptions options)
+{
+    return ReadUTFBufferAndDumpToStream<UTF16>(options,
+                                               ConvertUTF16toUTF8);
+}
+
+template <>
+bool
+lldb_private::formatters::ReadStringAndDumpToStream<StringElementType::UTF32> (ReadStringAndDumpToStreamOptions options)
+{
+    return ReadUTFBufferAndDumpToStream<UTF32>(options,
+                                               ConvertUTF32toUTF8);
+}
+
+template <>
+bool
+lldb_private::formatters::ReadBufferAndDumpToStream<StringElementType::UTF8> (ReadBufferAndDumpToStreamOptions options)
+{
+    assert(options.GetStream() && "need a Stream to print the string to");
+
+    return DumpUTFBufferToStream<UTF8>(nullptr, options.GetData(), *options.GetStream(), options.GetPrefixToken(), options.GetQuote(), options.GetSourceSize(), options.GetEscapeNonPrintables());
+}
+
+template <>
+bool
+lldb_private::formatters::ReadBufferAndDumpToStream<StringElementType::ASCII> (ReadBufferAndDumpToStreamOptions options)
+{
+    // treat ASCII the same as UTF8
+    // FIXME: can we optimize ASCII some more?
+    return ReadBufferAndDumpToStream<StringElementType::UTF8>(options);
+}
+
+template <>
+bool
+lldb_private::formatters::ReadBufferAndDumpToStream<StringElementType::UTF16> (ReadBufferAndDumpToStreamOptions options)
+{
+    assert(options.GetStream() && "need a Stream to print the string to");
+    
+    return DumpUTFBufferToStream(ConvertUTF16toUTF8, options.GetData(), *options.GetStream(), options.GetPrefixToken(), options.GetQuote(), options.GetSourceSize(), options.GetEscapeNonPrintables());
+}
+
+template <>
+bool
+lldb_private::formatters::ReadBufferAndDumpToStream<StringElementType::UTF32> (ReadBufferAndDumpToStreamOptions options)
+{
+    assert(options.GetStream() && "need a Stream to print the string to");
+    
+    return DumpUTFBufferToStream(ConvertUTF32toUTF8, options.GetData(), *options.GetStream(), options.GetPrefixToken(), options.GetQuote(), options.GetSourceSize(), options.GetEscapeNonPrintables());
+}





More information about the lldb-commits mailing list