//===-- HTMLLogger.cpp ----------------------------------------------------===//
//
// 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 the HTML logger. Given a directory dir/, we write
// dir/0.html for the first analysis, etc.
// These files contain a visualization that allows inspecting the CFG and the
// state of the analysis at each point.
// Static assets (HTMLLogger.js, HTMLLogger.css) and SVG graphs etc are embedded
// so each output file is self-contained.
//
// VIEWS
//
// The timeline and function view are always shown. These allow selecting basic
// blocks, statements within them, and processing iterations (BBs are visited
// multiple times when e.g. loops are involved).
// These are written directly into the HTML body.
//
// There are also listings of particular basic blocks, and dumps of the state
// at particular analysis points (i.e. BB2 iteration 3 statement 2).
// These are only shown when the relevant BB/analysis point is *selected*.
//
// DATA AND TEMPLATES
//
// The HTML proper is mostly static.
// The analysis data is in a JSON object HTMLLoggerData which is embedded as
// a \n";
writeCode();
writeCFG();
*OS << "\n";
*OS << llvm::StringRef(HTMLLogger_html).split("").second;
}
void enterBlock(const CFGBlock &B, bool PostVisit) override {
llvm::SmallVector &BIter = BlockIters[&B];
unsigned IterNum = BIter.size() + 1;
BIter.push_back(Iters.size());
Iters.push_back({&B, IterNum, PostVisit, /*Converged=*/false});
ElementIndex = 0;
}
void enterElement(const CFGElement &E) override {
++ElementIndex;
}
static std::string blockID(unsigned Block) {
return llvm::formatv("B{0}", Block);
}
static std::string eltID(unsigned Block, unsigned Element) {
return llvm::formatv("B{0}.{1}", Block, Element);
}
static std::string iterID(unsigned Block, unsigned Iter) {
return llvm::formatv("B{0}:{1}", Block, Iter);
}
static std::string elementIterID(unsigned Block, unsigned Iter,
unsigned Element) {
return llvm::formatv("B{0}:{1}_B{0}.{2}", Block, Iter, Element);
}
// Write the analysis state associated with a particular analysis point.
// FIXME: this dump is fairly opaque. We should show:
// - values associated with the current Stmt
// - values associated with its children
// - meaningful names for values
// - which boolean values are implied true/false by the flow condition
void recordState(TypeErasedDataflowAnalysisState &State) override {
unsigned Block = Iters.back().Block->getBlockID();
unsigned Iter = Iters.back().Iter;
bool PostVisit = Iters.back().PostVisit;
JOS->attributeObject(elementIterID(Block, Iter, ElementIndex), [&] {
JOS->attribute("block", blockID(Block));
JOS->attribute("iter", Iter);
JOS->attribute("post_visit", PostVisit);
JOS->attribute("element", ElementIndex);
// If this state immediately follows an Expr, show its built-in model.
if (ElementIndex > 0) {
auto S =
Iters.back().Block->Elements[ElementIndex - 1].getAs();
if (const Expr *E = S ? llvm::dyn_cast(S->getStmt()) : nullptr) {
if (E->isPRValue()) {
if (auto *V = State.Env.getValue(*E))
JOS->attributeObject(
"value", [&] { ModelDumper(*JOS, State.Env).dump(*V); });
} else {
if (auto *Loc = State.Env.getStorageLocation(*E))
JOS->attributeObject(
"value", [&] { ModelDumper(*JOS, State.Env).dump(*Loc); });
}
}
}
if (!ContextLogs.empty()) {
JOS->attribute("logs", ContextLogs);
ContextLogs.clear();
}
{
std::string BuiltinLattice;
llvm::raw_string_ostream BuiltinLatticeS(BuiltinLattice);
State.Env.dump(BuiltinLatticeS);
JOS->attribute("builtinLattice", BuiltinLattice);
}
});
}
void blockConverged() override { Iters.back().Converged = true; }
void logText(llvm::StringRef S) override {
ContextLogs.append(S.begin(), S.end());
ContextLogs.push_back('\n');
}
private:
// Write the CFG block details.
// Currently this is just the list of elements in execution order.
// FIXME: an AST dump would be a useful view, too.
void writeBlock(const CFGBlock &B, llvm::ArrayRef ItersForB) {
JOS->attributeObject(blockID(B.getBlockID()), [&] {
JOS->attributeArray("iters", [&] {
for (size_t IterIdx : ItersForB) {
const Iteration &Iter = Iters[IterIdx];
JOS->object([&] {
JOS->attribute("iter", Iter.Iter);
JOS->attribute("post_visit", Iter.PostVisit);
JOS->attribute("converged", Iter.Converged);
});
}
});
JOS->attributeArray("elements", [&] {
for (const auto &Elt : B.Elements) {
std::string Dump;
llvm::raw_string_ostream DumpS(Dump);
Elt.dumpToStream(DumpS);
JOS->value(Dump);
}
});
});
}
// Write the code of function being examined.
// We want to overlay the code with s that mark which BB particular
// tokens are associated with, and even which BB element (so that clicking
// can select the right element).
void writeCode() {
const auto &AST = CFG->getDecl().getASTContext();
bool Invalid = false;
// Extract the source code from the original file.
// Pretty-printing from the AST would probably be nicer (no macros or
// indentation to worry about), but we need the boundaries of particular
// AST nodes and the printer doesn't provide this.
auto Range = clang::Lexer::makeFileCharRange(
CharSourceRange::getTokenRange(CFG->getDecl().getSourceRange()),
AST.getSourceManager(), AST.getLangOpts());
if (Range.isInvalid())
return;
llvm::StringRef Code = clang::Lexer::getSourceText(
Range, AST.getSourceManager(), AST.getLangOpts(), &Invalid);
if (Invalid)
return;
// TokenInfo stores the BB and set of elements that a token is part of.
struct TokenInfo {
enum : unsigned { Missing = static_cast(-1) };
// The basic block this is part of.
// This is the BB of the stmt with the smallest containing range.
unsigned BB = Missing;
unsigned BBPriority = 0;
// The most specific stmt this is part of (smallest range).
unsigned Elt = Missing;
unsigned EltPriority = 0;
// All stmts this is part of.
SmallVector Elts;
// Mark this token as being part of BB.Elt.
// RangeLen is the character length of the element's range, used to
// distinguish inner vs outer statements.
// For example in `a==0`, token "a" is part of the stmts "a" and "a==0".
// However "a" has a smaller range, so is more specific. Clicking on the
// token "a" should select the stmt "a".
void assign(unsigned BB, unsigned Elt, unsigned RangeLen) {
// A worse BB (larger range) => ignore.
if (this->BB != Missing && BB != this->BB && BBPriority <= RangeLen)
return;
if (BB != this->BB) {
this->BB = BB;
Elts.clear();
BBPriority = RangeLen;
}
BBPriority = std::min(BBPriority, RangeLen);
Elts.push_back(Elt);
if (this->Elt == Missing || EltPriority > RangeLen)
this->Elt = Elt;
}
bool operator==(const TokenInfo &Other) const {
return std::tie(BB, Elt, Elts) ==
std::tie(Other.BB, Other.Elt, Other.Elts);
}
// Write the attributes for the on this token.
void write(llvm::raw_ostream &OS) const {
OS << "class='c";
if (BB != Missing)
OS << " " << blockID(BB);
for (unsigned Elt : Elts)
OS << " " << eltID(BB, Elt);
OS << "'";
if (Elt != Missing)
OS << " data-elt='" << eltID(BB, Elt) << "'";
if (BB != Missing)
OS << " data-bb='" << blockID(BB) << "'";
}
};
// Construct one TokenInfo per character in a flat array.
// This is inefficient (chars in a token all have the same info) but simple.
std::vector State(Code.size());
for (const auto *Block : CFG->getCFG()) {
unsigned EltIndex = 0;
for (const auto& Elt : *Block) {
++EltIndex;
if (const auto S = Elt.getAs()) {
auto EltRange = clang::Lexer::makeFileCharRange(
CharSourceRange::getTokenRange(S->getStmt()->getSourceRange()),
AST.getSourceManager(), AST.getLangOpts());
if (EltRange.isInvalid())
continue;
if (EltRange.getBegin() < Range.getBegin() ||
EltRange.getEnd() >= Range.getEnd() ||
EltRange.getEnd() < Range.getBegin() ||
EltRange.getEnd() >= Range.getEnd())
continue;
unsigned Off = EltRange.getBegin().getRawEncoding() -
Range.getBegin().getRawEncoding();
unsigned Len = EltRange.getEnd().getRawEncoding() -
EltRange.getBegin().getRawEncoding();
for (unsigned I = 0; I < Len; ++I)
State[Off + I].assign(Block->getBlockID(), EltIndex, Len);
}
}
}
// Finally, write the code with the correct s.
unsigned Line =
AST.getSourceManager().getSpellingLineNumber(Range.getBegin());
*OS << "\n";
*OS << "";
llvm::printHTMLEscaped(
llvm::sys::path::filename(
AST.getSourceManager().getFilename(Range.getBegin())),
*OS);
*OS << "";
*OS << "";
for (unsigned I = 0; I < Code.size(); ++I) {
// Don't actually write a around each character, only break spans
// when the TokenInfo changes.
bool NeedOpen = I == 0 || !(State[I] == State[I-1]);
bool NeedClose = I + 1 == Code.size() || !(State[I] == State[I + 1]);
if (NeedOpen) {
*OS << "";
}
if (Code[I] == '\n')
*OS << "\n";
else
llvm::printHTMLEscaped(Code.substr(I, 1), *OS);
if (NeedClose) *OS << "";
}
*OS << "\n";
*OS << "";
}
// Write the CFG diagram, a graph of basic blocks.
// Laying out graphs is hard, so we construct a graphviz description and shell
// out to `dot` to turn it into an SVG.
void writeCFG() {
*OS << "\n";
if (auto SVG = renderSVG(buildCFGDot(CFG->getCFG())))
*OS << *SVG;
else
*OS << "Can't draw CFG: " << toString(SVG.takeError());
*OS << "\n";
}
// Produce a graphviz description of a CFG.
static std::string buildCFGDot(const clang::CFG &CFG) {
std::string Graph;
llvm::raw_string_ostream GraphS(Graph);
// Graphviz likes to add unhelpful tooltips everywhere, " " suppresses.
GraphS << R"(digraph {
tooltip=" "
node[class=bb, shape=square, fontname="sans-serif", tooltip=" "]
edge[tooltip = " "]
)";
for (unsigned I = 0; I < CFG.getNumBlockIDs(); ++I)
GraphS << " " << blockID(I) << " [id=" << blockID(I) << "]\n";
for (const auto *Block : CFG) {
for (const auto &Succ : Block->succs()) {
if (Succ.getReachableBlock())
GraphS << " " << blockID(Block->getBlockID()) << " -> "
<< blockID(Succ.getReachableBlock()->getBlockID()) << "\n";
}
}
GraphS << "}\n";
return Graph;
}
};
// Nothing interesting here, just subprocess/temp-file plumbing.
llvm::Expected renderSVG(llvm::StringRef DotGraph) {
std::string DotPath;
if (const auto *FromEnv = ::getenv("GRAPHVIZ_DOT"))
DotPath = FromEnv;
else {
auto FromPath = llvm::sys::findProgramByName("dot");
if (!FromPath)
return llvm::createStringError(FromPath.getError(),
"'dot' not found on PATH");
DotPath = FromPath.get();
}
// Create input and output files for `dot` subprocess.
// (We create the output file as empty, to reserve the temp filename).
llvm::SmallString<256> Input, Output;
int InputFD;
if (auto EC = llvm::sys::fs::createTemporaryFile("analysis", ".dot", InputFD,
Input))
return llvm::createStringError(EC, "failed to create `dot` temp input");
llvm::raw_fd_ostream(InputFD, /*shouldClose=*/true) << DotGraph;
auto DeleteInput =
llvm::make_scope_exit([&] { llvm::sys::fs::remove(Input); });
if (auto EC = llvm::sys::fs::createTemporaryFile("analysis", ".svg", Output))
return llvm::createStringError(EC, "failed to create `dot` temp output");
auto DeleteOutput =
llvm::make_scope_exit([&] { llvm::sys::fs::remove(Output); });
std::vector> Redirects = {
Input, Output,
/*stderr=*/std::nullopt};
std::string ErrMsg;
int Code = llvm::sys::ExecuteAndWait(
DotPath, {"dot", "-Tsvg"}, /*Env=*/std::nullopt, Redirects,
/*SecondsToWait=*/0, /*MemoryLimit=*/0, &ErrMsg);
if (!ErrMsg.empty())
return llvm::createStringError(llvm::inconvertibleErrorCode(),
"'dot' failed: " + ErrMsg);
if (Code != 0)
return llvm::createStringError(llvm::inconvertibleErrorCode(),
"'dot' failed (" + llvm::Twine(Code) + ")");
auto Buf = llvm::MemoryBuffer::getFile(Output);
if (!Buf)
return llvm::createStringError(Buf.getError(), "Can't read `dot` output");
// Output has prefix we don't want. Skip to