llvm-project/clang/lib/StaticAnalyzer/Core/HTMLDiagnostics.cpp

566 lines
17 KiB
C++
Raw Normal View History

//===--- HTMLDiagnostics.cpp - HTML Diagnostics for Paths ----*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the HTMLDiagnostics object.
//
//===----------------------------------------------------------------------===//
#include "clang/StaticAnalyzer/Core/PathDiagnosticConsumers.h"
#include "clang/StaticAnalyzer/Core/BugReporter/PathDiagnostic.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/Decl.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Basic/FileManager.h"
#include "clang/Rewrite/Rewriter.h"
#include "clang/Rewrite/HTMLRewrite.h"
#include "clang/Lex/Lexer.h"
#include "clang/Lex/Preprocessor.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Support/Path.h"
using namespace clang;
using namespace ento;
//===----------------------------------------------------------------------===//
// Boilerplate.
//===----------------------------------------------------------------------===//
namespace {
class HTMLDiagnostics : public PathDiagnosticConsumer {
llvm::sys::Path Directory, FilePrefix;
bool createdDir, noDir;
const Preprocessor &PP;
public:
HTMLDiagnostics(const std::string& prefix, const Preprocessor &pp);
virtual ~HTMLDiagnostics() { FlushDiagnostics(NULL); }
virtual void FlushDiagnosticsImpl(std::vector<const PathDiagnostic *> &Diags,
FilesMade *filesMade);
virtual StringRef getName() const {
return "HTMLDiagnostics";
}
unsigned ProcessMacroPiece(raw_ostream &os,
const PathDiagnosticMacroPiece& P,
unsigned num);
void HandlePiece(Rewriter& R, FileID BugFileID,
const PathDiagnosticPiece& P, unsigned num, unsigned max);
Introduce code modification hints into the diagnostics system. When we know how to recover from an error, we can attach a hint to the diagnostic that states how to modify the code, which can be one of: - Insert some new code (a text string) at a particular source location - Remove the code within a given range - Replace the code within a given range with some new code (a text string) Right now, we use these hints to annotate diagnostic information. For example, if one uses the '>>' in a template argument in C++98, as in this code: template<int I> class B { }; B<1000 >> 2> *b1; we'll warn that the behavior will change in C++0x. The fix is to insert parenthese, so we use code insertion annotations to illustrate where the parentheses go: test.cpp:10:10: warning: use of right-shift operator ('>>') in template argument will require parentheses in C++0x B<1000 >> 2> *b1; ^ ( ) Use of these annotations is partially implemented for HTML diagnostics, but it's not (yet) producing valid HTML, which may be related to PR2386, so it has been #if 0'd out. In this future, we could consider hooking this mechanism up to the rewriter to actually try to fix these problems during compilation (or, after a compilation whose only errors have fixes). For now, however, I suggest that we use these code modification hints whenever we can, so that we get better diagnostics now and will have better coverage when we find better ways to use this information. This also fixes PR3410 by placing the complaint about missing tokens just after the previous token (rather than at the location of the next token). llvm-svn: 65570
2009-02-27 05:00:50 +08:00
void HighlightRange(Rewriter& R, FileID BugFileID, SourceRange Range,
const char *HighlightStart = "<span class=\"mrange\">",
const char *HighlightEnd = "</span>");
void ReportDiag(const PathDiagnostic& D,
FilesMade *filesMade);
};
} // end anonymous namespace
HTMLDiagnostics::HTMLDiagnostics(const std::string& prefix,
const Preprocessor &pp)
: Directory(prefix), FilePrefix(prefix), createdDir(false), noDir(false),
PP(pp) {
// All html files begin with "report"
FilePrefix.appendComponent("report");
}
void ento::createHTMLDiagnosticConsumer(PathDiagnosticConsumers &C,
const std::string& prefix,
const Preprocessor &PP) {
C.push_back(new HTMLDiagnostics(prefix, PP));
}
//===----------------------------------------------------------------------===//
// Report processing.
//===----------------------------------------------------------------------===//
void HTMLDiagnostics::FlushDiagnosticsImpl(
std::vector<const PathDiagnostic *> &Diags,
FilesMade *filesMade) {
for (std::vector<const PathDiagnostic *>::iterator it = Diags.begin(),
et = Diags.end(); it != et; ++it) {
ReportDiag(**it, filesMade);
}
}
void HTMLDiagnostics::ReportDiag(const PathDiagnostic& D,
FilesMade *filesMade) {
// Create the HTML directory if it is missing.
if (!createdDir) {
createdDir = true;
std::string ErrorMsg;
Directory.createDirectoryOnDisk(true, &ErrorMsg);
bool IsDirectory;
if (llvm::sys::fs::is_directory(Directory.str(), IsDirectory) ||
!IsDirectory) {
llvm::errs() << "warning: could not create directory '"
<< Directory.str() << "'\n"
<< "reason: " << ErrorMsg << '\n';
noDir = true;
return;
}
}
if (noDir)
return;
// First flatten out the entire path to make it easier to use.
PathPieces path = D.path.flatten(/*ShouldFlattenMacros=*/false);
// The path as already been prechecked that all parts of the path are
// from the same file and that it is non-empty.
const SourceManager &SMgr = (*path.begin())->getLocation().getManager();
assert(!path.empty());
FileID FID =
(*path.begin())->getLocation().asLocation().getExpansionLoc().getFileID();
assert(!FID.isInvalid());
// Create a new rewriter to generate HTML.
Rewriter R(const_cast<SourceManager&>(SMgr), PP.getLangOpts());
// Process the path.
unsigned n = path.size();
unsigned max = n;
for (PathPieces::const_reverse_iterator I = path.rbegin(),
E = path.rend();
I != E; ++I, --n)
HandlePiece(R, FID, **I, n, max);
// Add line numbers, header, footer, etc.
// unsigned FID = R.getSourceMgr().getMainFileID();
html::EscapeText(R, FID);
html::AddLineNumbers(R, FID);
// If we have a preprocessor, relex the file and syntax highlight.
// We might not have a preprocessor if we come from a deserialized AST file,
// for example.
html::SyntaxHighlight(R, FID, PP);
html::HighlightMacros(R, FID, PP);
// Get the full directory name of the analyzed file.
const FileEntry* Entry = SMgr.getFileEntryForID(FID);
// This is a cludge; basically we want to append either the full
// working directory if we have no directory information. This is
// a work in progress.
std::string DirName = "";
if (llvm::sys::path::is_relative(Entry->getName())) {
llvm::sys::Path P = llvm::sys::Path::GetCurrentDirectory();
DirName = P.str() + "/";
}
// Add the name of the file as an <h1> tag.
{
std::string s;
llvm::raw_string_ostream os(s);
os << "<!-- REPORTHEADER -->\n"
<< "<h3>Bug Summary</h3>\n<table class=\"simpletable\">\n"
"<tr><td class=\"rowname\">File:</td><td>"
<< html::EscapeText(DirName)
<< html::EscapeText(Entry->getName())
<< "</td></tr>\n<tr><td class=\"rowname\">Location:</td><td>"
"<a href=\"#EndPath\">line "
<< (*path.rbegin())->getLocation().asLocation().getExpansionLineNumber()
<< ", column "
<< (*path.rbegin())->getLocation().asLocation().getExpansionColumnNumber()
<< "</a></td></tr>\n"
"<tr><td class=\"rowname\">Description:</td><td>"
<< D.getVerboseDescription() << "</td></tr>\n";
// Output any other meta data.
for (PathDiagnostic::meta_iterator I=D.meta_begin(), E=D.meta_end();
I!=E; ++I) {
os << "<tr><td></td><td>" << html::EscapeText(*I) << "</td></tr>\n";
}
os << "</table>\n<!-- REPORTSUMMARYEXTRA -->\n"
"<h3>Annotated Source Code</h3>\n";
R.InsertTextBefore(SMgr.getLocForStartOfFile(FID), os.str());
}
// Embed meta-data tags.
{
std::string s;
llvm::raw_string_ostream os(s);
StringRef BugDesc = D.getVerboseDescription();
if (!BugDesc.empty())
os << "\n<!-- BUGDESC " << BugDesc << " -->\n";
StringRef BugType = D.getBugType();
if (!BugType.empty())
os << "\n<!-- BUGTYPE " << BugType << " -->\n";
StringRef BugCategory = D.getCategory();
if (!BugCategory.empty())
os << "\n<!-- BUGCATEGORY " << BugCategory << " -->\n";
os << "\n<!-- BUGFILE " << DirName << Entry->getName() << " -->\n";
os << "\n<!-- BUGLINE "
<< path.back()->getLocation().asLocation().getExpansionLineNumber()
<< " -->\n";
os << "\n<!-- BUGPATHLENGTH " << path.size() << " -->\n";
// Mark the end of the tags.
os << "\n<!-- BUGMETAEND -->\n";
// Insert the text.
R.InsertTextBefore(SMgr.getLocForStartOfFile(FID), os.str());
}
// Add CSS, header, and footer.
html::AddHeaderFooterInternalBuiltinCSS(R, FID, Entry->getName());
// Get the rewrite buffer.
const RewriteBuffer *Buf = R.getRewriteBufferFor(FID);
if (!Buf) {
llvm::errs() << "warning: no diagnostics generated for main file.\n";
return;
}
// Create a path for the target HTML file.
llvm::sys::Path F(FilePrefix);
F.makeUnique(false, NULL);
// Rename the file with an HTML extension.
llvm::sys::Path H(F);
H.appendSuffix("html");
F.renamePathOnDisk(H, NULL);
std::string ErrorMsg;
llvm::raw_fd_ostream os(H.c_str(), ErrorMsg);
if (!ErrorMsg.empty()) {
llvm::errs() << "warning: could not create file '" << F.str()
<< "'\n";
return;
}
if (filesMade) {
filesMade->addDiagnostic(D, getName(), llvm::sys::path::filename(H.str()));
}
// Emit the HTML to disk.
for (RewriteBuffer::iterator I = Buf->begin(), E = Buf->end(); I!=E; ++I)
os << *I;
}
void HTMLDiagnostics::HandlePiece(Rewriter& R, FileID BugFileID,
const PathDiagnosticPiece& P,
unsigned num, unsigned max) {
// For now, just draw a box above the line in question, and emit the
// warning.
FullSourceLoc Pos = P.getLocation().asLocation();
if (!Pos.isValid())
return;
SourceManager &SM = R.getSourceMgr();
assert(&Pos.getManager() == &SM && "SourceManagers are different!");
std::pair<FileID, unsigned> LPosInfo = SM.getDecomposedExpansionLoc(Pos);
if (LPosInfo.first != BugFileID)
return;
const llvm::MemoryBuffer *Buf = SM.getBuffer(LPosInfo.first);
const char* FileStart = Buf->getBufferStart();
// Compute the column number. Rewind from the current position to the start
// of the line.
unsigned ColNo = SM.getColumnNumber(LPosInfo.first, LPosInfo.second);
const char *TokInstantiationPtr =Pos.getExpansionLoc().getCharacterData();
const char *LineStart = TokInstantiationPtr-ColNo;
// Compute LineEnd.
const char *LineEnd = TokInstantiationPtr;
const char* FileEnd = Buf->getBufferEnd();
while (*LineEnd != '\n' && LineEnd != FileEnd)
++LineEnd;
// Compute the margin offset by counting tabs and non-tabs.
unsigned PosNo = 0;
for (const char* c = LineStart; c != TokInstantiationPtr; ++c)
PosNo += *c == '\t' ? 8 : 1;
// Create the html for the message.
const char *Kind = 0;
switch (P.getKind()) {
case PathDiagnosticPiece::Call:
llvm_unreachable("Calls should already be handled");
case PathDiagnosticPiece::Event: Kind = "Event"; break;
case PathDiagnosticPiece::ControlFlow: Kind = "Control"; break;
// Setting Kind to "Control" is intentional.
case PathDiagnosticPiece::Macro: Kind = "Control"; break;
}
std::string sbuf;
llvm::raw_string_ostream os(sbuf);
os << "\n<tr><td class=\"num\"></td><td class=\"line\"><div id=\"";
if (num == max)
os << "EndPath";
else
os << "Path" << num;
os << "\" class=\"msg";
if (Kind)
os << " msg" << Kind;
os << "\" style=\"margin-left:" << PosNo << "ex";
// Output a maximum size.
if (!isa<PathDiagnosticMacroPiece>(P)) {
// Get the string and determining its maximum substring.
const std::string& Msg = P.getString();
unsigned max_token = 0;
unsigned cnt = 0;
unsigned len = Msg.size();
for (std::string::const_iterator I=Msg.begin(), E=Msg.end(); I!=E; ++I)
switch (*I) {
default:
++cnt;
continue;
case ' ':
case '\t':
case '\n':
if (cnt > max_token) max_token = cnt;
cnt = 0;
}
if (cnt > max_token)
max_token = cnt;
// Determine the approximate size of the message bubble in em.
unsigned em;
const unsigned max_line = 120;
if (max_token >= max_line)
em = max_token / 2;
else {
unsigned characters = max_line;
unsigned lines = len / max_line;
if (lines > 0) {
for (; characters > max_token; --characters)
if (len / characters > lines) {
++characters;
break;
}
}
em = characters / 2;
}
if (em < max_line/2)
os << "; max-width:" << em << "em";
}
else
os << "; max-width:100em";
os << "\">";
if (max > 1) {
os << "<table class=\"msgT\"><tr><td valign=\"top\">";
os << "<div class=\"PathIndex";
if (Kind) os << " PathIndex" << Kind;
os << "\">" << num << "</div>";
if (num > 1) {
os << "</td><td><div class=\"PathNav\"><a href=\"#Path"
<< (num - 1)
<< "\" title=\"Previous event ("
<< (num - 1)
<< ")\">&#x2190;</a></div></td>";
}
os << "</td><td>";
}
if (const PathDiagnosticMacroPiece *MP =
dyn_cast<PathDiagnosticMacroPiece>(&P)) {
os << "Within the expansion of the macro '";
// Get the name of the macro by relexing it.
{
FullSourceLoc L = MP->getLocation().asLocation().getExpansionLoc();
assert(L.isFileID());
StringRef BufferInfo = L.getBufferData();
std::pair<FileID, unsigned> LocInfo = L.getDecomposedLoc();
const char* MacroName = LocInfo.second + BufferInfo.data();
Lexer rawLexer(SM.getLocForStartOfFile(LocInfo.first), PP.getLangOpts(),
BufferInfo.begin(), MacroName, BufferInfo.end());
Token TheTok;
rawLexer.LexFromRawLexer(TheTok);
for (unsigned i = 0, n = TheTok.getLength(); i < n; ++i)
os << MacroName[i];
}
os << "':\n";
if (max > 1) {
os << "</td>";
if (num < max) {
os << "<td><div class=\"PathNav\"><a href=\"#";
if (num == max - 1)
os << "EndPath";
else
os << "Path" << (num + 1);
os << "\" title=\"Next event ("
<< (num + 1)
<< ")\">&#x2192;</a></div></td>";
}
os << "</tr></table>";
}
// Within a macro piece. Write out each event.
ProcessMacroPiece(os, *MP, 0);
}
else {
os << html::EscapeText(P.getString());
if (max > 1) {
os << "</td>";
if (num < max) {
os << "<td><div class=\"PathNav\"><a href=\"#";
if (num == max - 1)
os << "EndPath";
else
os << "Path" << (num + 1);
os << "\" title=\"Next event ("
<< (num + 1)
<< ")\">&#x2192;</a></div></td>";
}
os << "</tr></table>";
}
}
os << "</div></td></tr>";
// Insert the new html.
unsigned DisplayPos = LineEnd - FileStart;
SourceLocation Loc =
SM.getLocForStartOfFile(LPosInfo.first).getLocWithOffset(DisplayPos);
R.InsertTextBefore(Loc, os.str());
// Now highlight the ranges.
ArrayRef<SourceRange> Ranges = P.getRanges();
for (ArrayRef<SourceRange>::iterator I = Ranges.begin(),
E = Ranges.end(); I != E; ++I) {
HighlightRange(R, LPosInfo.first, *I);
}
}
static void EmitAlphaCounter(raw_ostream &os, unsigned n) {
2010-03-13 19:34:41 +08:00
unsigned x = n % ('z' - 'a');
n /= 'z' - 'a';
2010-03-13 19:34:41 +08:00
if (n > 0)
EmitAlphaCounter(os, n);
2010-03-13 19:34:41 +08:00
os << char('a' + x);
}
unsigned HTMLDiagnostics::ProcessMacroPiece(raw_ostream &os,
const PathDiagnosticMacroPiece& P,
unsigned num) {
for (PathPieces::const_iterator I = P.subPieces.begin(), E=P.subPieces.end();
I!=E; ++I) {
if (const PathDiagnosticMacroPiece *MP =
dyn_cast<PathDiagnosticMacroPiece>(*I)) {
num = ProcessMacroPiece(os, *MP, num);
continue;
}
if (PathDiagnosticEventPiece *EP = dyn_cast<PathDiagnosticEventPiece>(*I)) {
os << "<div class=\"msg msgEvent\" style=\"width:94%; "
"margin-left:5px\">"
"<table class=\"msgT\"><tr>"
"<td valign=\"top\"><div class=\"PathIndex PathIndexEvent\">";
EmitAlphaCounter(os, num++);
os << "</div></td><td valign=\"top\">"
<< html::EscapeText(EP->getString())
<< "</td></tr></table></div>\n";
}
}
return num;
}
void HTMLDiagnostics::HighlightRange(Rewriter& R, FileID BugFileID,
Introduce code modification hints into the diagnostics system. When we know how to recover from an error, we can attach a hint to the diagnostic that states how to modify the code, which can be one of: - Insert some new code (a text string) at a particular source location - Remove the code within a given range - Replace the code within a given range with some new code (a text string) Right now, we use these hints to annotate diagnostic information. For example, if one uses the '>>' in a template argument in C++98, as in this code: template<int I> class B { }; B<1000 >> 2> *b1; we'll warn that the behavior will change in C++0x. The fix is to insert parenthese, so we use code insertion annotations to illustrate where the parentheses go: test.cpp:10:10: warning: use of right-shift operator ('>>') in template argument will require parentheses in C++0x B<1000 >> 2> *b1; ^ ( ) Use of these annotations is partially implemented for HTML diagnostics, but it's not (yet) producing valid HTML, which may be related to PR2386, so it has been #if 0'd out. In this future, we could consider hooking this mechanism up to the rewriter to actually try to fix these problems during compilation (or, after a compilation whose only errors have fixes). For now, however, I suggest that we use these code modification hints whenever we can, so that we get better diagnostics now and will have better coverage when we find better ways to use this information. This also fixes PR3410 by placing the complaint about missing tokens just after the previous token (rather than at the location of the next token). llvm-svn: 65570
2009-02-27 05:00:50 +08:00
SourceRange Range,
const char *HighlightStart,
const char *HighlightEnd) {
SourceManager &SM = R.getSourceMgr();
const LangOptions &LangOpts = R.getLangOpts();
SourceLocation InstantiationStart = SM.getExpansionLoc(Range.getBegin());
unsigned StartLineNo = SM.getExpansionLineNumber(InstantiationStart);
SourceLocation InstantiationEnd = SM.getExpansionLoc(Range.getEnd());
unsigned EndLineNo = SM.getExpansionLineNumber(InstantiationEnd);
if (EndLineNo < StartLineNo)
return;
if (SM.getFileID(InstantiationStart) != BugFileID ||
SM.getFileID(InstantiationEnd) != BugFileID)
return;
// Compute the column number of the end.
unsigned EndColNo = SM.getExpansionColumnNumber(InstantiationEnd);
unsigned OldEndColNo = EndColNo;
if (EndColNo) {
// Add in the length of the token, so that we cover multi-char tokens.
EndColNo += Lexer::MeasureTokenLength(Range.getEnd(), SM, LangOpts)-1;
}
// Highlight the range. Make the span tag the outermost tag for the
// selected range.
SourceLocation E =
InstantiationEnd.getLocWithOffset(EndColNo - OldEndColNo);
Introduce code modification hints into the diagnostics system. When we know how to recover from an error, we can attach a hint to the diagnostic that states how to modify the code, which can be one of: - Insert some new code (a text string) at a particular source location - Remove the code within a given range - Replace the code within a given range with some new code (a text string) Right now, we use these hints to annotate diagnostic information. For example, if one uses the '>>' in a template argument in C++98, as in this code: template<int I> class B { }; B<1000 >> 2> *b1; we'll warn that the behavior will change in C++0x. The fix is to insert parenthese, so we use code insertion annotations to illustrate where the parentheses go: test.cpp:10:10: warning: use of right-shift operator ('>>') in template argument will require parentheses in C++0x B<1000 >> 2> *b1; ^ ( ) Use of these annotations is partially implemented for HTML diagnostics, but it's not (yet) producing valid HTML, which may be related to PR2386, so it has been #if 0'd out. In this future, we could consider hooking this mechanism up to the rewriter to actually try to fix these problems during compilation (or, after a compilation whose only errors have fixes). For now, however, I suggest that we use these code modification hints whenever we can, so that we get better diagnostics now and will have better coverage when we find better ways to use this information. This also fixes PR3410 by placing the complaint about missing tokens just after the previous token (rather than at the location of the next token). llvm-svn: 65570
2009-02-27 05:00:50 +08:00
html::HighlightRange(R, InstantiationStart, E, HighlightStart, HighlightEnd);
}