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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314
|
//===-- MsgPackDocument.cpp - MsgPack Document --------------------------*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// This file implements a class that exposes a simple in-memory representation
/// of a document of MsgPack objects, that can be read from MsgPack, written to
/// MsgPack, and inspected and modified in memory. This is intended to be a
/// lighter-weight (in terms of memory allocations) replacement for
/// MsgPackTypes.
///
//===----------------------------------------------------------------------===//
#include "llvm/BinaryFormat/MsgPackDocument.h"
#include "llvm/BinaryFormat/MsgPackWriter.h"
using namespace llvm;
using namespace msgpack;
// Convert this DocNode into an empty array.
void DocNode::convertToArray() { *this = getDocument()->getArrayNode(); }
// Convert this DocNode into an empty map.
void DocNode::convertToMap() { *this = getDocument()->getMapNode(); }
/// Find the key in the MapDocNode.
DocNode::MapTy::iterator MapDocNode::find(StringRef S) {
return find(getDocument()->getNode(S));
}
/// Member access for MapDocNode. The string data must remain valid for the
/// lifetime of the Document.
DocNode &MapDocNode::operator[](StringRef S) {
return (*this)[getDocument()->getNode(S)];
}
/// Member access for MapDocNode.
DocNode &MapDocNode::operator[](DocNode Key) {
assert(!Key.isEmpty());
DocNode &N = (*Map)[Key];
if (N.isEmpty()) {
// Ensure a new element has its KindAndDoc initialized.
N = getDocument()->getEmptyNode();
}
return N;
}
/// Member access for MapDocNode for integer key.
DocNode &MapDocNode::operator[](int Key) {
return (*this)[getDocument()->getNode(Key)];
}
DocNode &MapDocNode::operator[](unsigned Key) {
return (*this)[getDocument()->getNode(Key)];
}
DocNode &MapDocNode::operator[](int64_t Key) {
return (*this)[getDocument()->getNode(Key)];
}
DocNode &MapDocNode::operator[](uint64_t Key) {
return (*this)[getDocument()->getNode(Key)];
}
/// Array element access. This extends the array if necessary.
DocNode &ArrayDocNode::operator[](size_t Index) {
if (size() <= Index) {
// Ensure new elements have their KindAndDoc initialized.
Array->resize(Index + 1, getDocument()->getEmptyNode());
}
return (*Array)[Index];
}
// Convenience assignment operators. This only works if the destination
// DocNode has an associated Document, i.e. it was not constructed using the
// default constructor. The string one does not copy, so the string must
// remain valid for the lifetime of the Document. Use fromString to avoid
// that restriction.
DocNode &DocNode::operator=(StringRef Val) {
*this = getDocument()->getNode(Val);
return *this;
}
DocNode &DocNode::operator=(bool Val) {
*this = getDocument()->getNode(Val);
return *this;
}
DocNode &DocNode::operator=(int Val) {
*this = getDocument()->getNode(Val);
return *this;
}
DocNode &DocNode::operator=(unsigned Val) {
*this = getDocument()->getNode(Val);
return *this;
}
DocNode &DocNode::operator=(int64_t Val) {
*this = getDocument()->getNode(Val);
return *this;
}
DocNode &DocNode::operator=(uint64_t Val) {
*this = getDocument()->getNode(Val);
return *this;
}
// A level in the document reading stack.
struct StackLevel {
StackLevel(DocNode Node, size_t StartIndex, size_t Length,
DocNode *MapEntry = nullptr)
: Node(Node), Index(StartIndex), End(StartIndex + Length),
MapEntry(MapEntry) {}
DocNode Node;
size_t Index;
size_t End;
// Points to map entry when we have just processed a map key.
DocNode *MapEntry;
DocNode MapKey;
};
// Read a document from a binary msgpack blob, merging into anything already in
// the Document.
// The blob data must remain valid for the lifetime of this Document (because a
// string object in the document contains a StringRef into the original blob).
// If Multi, then this sets root to an array and adds top-level objects to it.
// If !Multi, then it only reads a single top-level object, even if there are
// more, and sets root to that.
// Returns false if failed due to illegal format or merge error.
bool Document::readFromBlob(
StringRef Blob, bool Multi,
function_ref<int(DocNode *DestNode, DocNode SrcNode, DocNode MapKey)>
Merger) {
msgpack::Reader MPReader(Blob);
SmallVector<StackLevel, 4> Stack;
if (Multi) {
// Create the array for multiple top-level objects.
Root = getArrayNode();
Stack.push_back(StackLevel(Root, 0, (size_t)-1));
}
do {
// On to next element (or key if doing a map key next).
// Read the value.
Object Obj;
if (!MPReader.read(Obj)) {
if (Multi && Stack.size() == 1) {
// OK to finish here as we've just done a top-level element with Multi
break;
}
return false; // Finished too early
}
// Convert it into a DocNode.
DocNode Node;
switch (Obj.Kind) {
case Type::Nil:
Node = getNode();
break;
case Type::Int:
Node = getNode(Obj.Int);
break;
case Type::UInt:
Node = getNode(Obj.UInt);
break;
case Type::Boolean:
Node = getNode(Obj.Bool);
break;
case Type::Float:
Node = getNode(Obj.Float);
break;
case Type::String:
Node = getNode(Obj.Raw);
break;
case Type::Map:
Node = getMapNode();
break;
case Type::Array:
Node = getArrayNode();
break;
default:
return false; // Raw and Extension not supported
}
// Store it.
DocNode *DestNode = nullptr;
if (Stack.empty())
DestNode = &Root;
else if (Stack.back().Node.getKind() == Type::Array) {
// Reading an array entry.
auto &Array = Stack.back().Node.getArray();
DestNode = &Array[Stack.back().Index++];
} else {
auto &Map = Stack.back().Node.getMap();
if (!Stack.back().MapEntry) {
// Reading a map key.
Stack.back().MapKey = Node;
Stack.back().MapEntry = &Map[Node];
continue;
}
// Reading the value for the map key read in the last iteration.
DestNode = Stack.back().MapEntry;
Stack.back().MapEntry = nullptr;
++Stack.back().Index;
}
int MergeResult = 0;
if (!DestNode->isEmpty()) {
// In a merge, there is already a value at this position. Call the
// callback to attempt to resolve the conflict. The resolution must result
// in an array or map if Node is an array or map respectively.
DocNode MapKey = !Stack.empty() && !Stack.back().MapKey.isEmpty()
? Stack.back().MapKey
: getNode();
MergeResult = Merger(DestNode, Node, MapKey);
if (MergeResult < 0)
return false; // Merge conflict resolution failed
assert(!((Node.isMap() && !DestNode->isMap()) ||
(Node.isArray() && !DestNode->isArray())));
} else
*DestNode = Node;
// See if we're starting a new array or map.
switch (DestNode->getKind()) {
case msgpack::Type::Array:
case msgpack::Type::Map:
Stack.push_back(StackLevel(*DestNode, MergeResult, Obj.Length, nullptr));
break;
default:
break;
}
// Pop finished stack levels.
while (!Stack.empty()) {
if (Stack.back().MapEntry)
break;
if (Stack.back().Index != Stack.back().End)
break;
Stack.pop_back();
}
} while (!Stack.empty());
return true;
}
struct WriterStackLevel {
DocNode Node;
DocNode::MapTy::iterator MapIt;
DocNode::ArrayTy::iterator ArrayIt;
bool OnKey;
};
/// Write a MsgPack document to a binary MsgPack blob.
void Document::writeToBlob(std::string &Blob) {
Blob.clear();
raw_string_ostream OS(Blob);
msgpack::Writer MPWriter(OS);
SmallVector<WriterStackLevel, 4> Stack;
DocNode Node = getRoot();
for (;;) {
switch (Node.getKind()) {
case Type::Array:
MPWriter.writeArraySize(Node.getArray().size());
Stack.push_back(
{Node, DocNode::MapTy::iterator(), Node.getArray().begin(), false});
break;
case Type::Map:
MPWriter.writeMapSize(Node.getMap().size());
Stack.push_back(
{Node, Node.getMap().begin(), DocNode::ArrayTy::iterator(), true});
break;
case Type::Nil:
MPWriter.writeNil();
break;
case Type::Boolean:
MPWriter.write(Node.getBool());
break;
case Type::Int:
MPWriter.write(Node.getInt());
break;
case Type::UInt:
MPWriter.write(Node.getUInt());
break;
case Type::String:
MPWriter.write(Node.getString());
break;
case Type::Empty:
llvm_unreachable("unhandled empty msgpack node");
default:
llvm_unreachable("unhandled msgpack object kind");
}
// Pop finished stack levels.
while (!Stack.empty()) {
if (Stack.back().Node.getKind() == Type::Map) {
if (Stack.back().MapIt != Stack.back().Node.getMap().end())
break;
} else {
if (Stack.back().ArrayIt != Stack.back().Node.getArray().end())
break;
}
Stack.pop_back();
}
if (Stack.empty())
break;
// Get the next value.
if (Stack.back().Node.getKind() == Type::Map) {
if (Stack.back().OnKey) {
// Do the key of a key,value pair in a map.
Node = Stack.back().MapIt->first;
Stack.back().OnKey = false;
} else {
Node = Stack.back().MapIt->second;
++Stack.back().MapIt;
Stack.back().OnKey = true;
}
} else {
Node = *Stack.back().ArrayIt;
++Stack.back().ArrayIt;
}
}
}
|