SARIFDiagnostic.cpp

Go to the documentation of this file.

//===--------- SARIFDiagnostic.cpp - SARIF Diagnostic Formatting ----------===//
//
// 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
//
//===----------------------------------------------------------------------===//
 
#include "clang/Frontend/SARIFDiagnostic.h"
#include "clang/Basic/CharInfo.h"
#include "clang/Basic/DiagnosticOptions.h"
#include "clang/Basic/FileManager.h"
#include "clang/Basic/Sarif.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Lex/Lexer.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/Locale.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <string>
 
namespace clang {
 
SARIFDiagnostic::SARIFDiagnostic(raw_ostream &OS, const LangOptions &LangOpts,
                                 DiagnosticOptions *DiagOpts,
                                 SarifDocumentWriter *Writer)
    : DiagnosticRenderer(LangOpts, DiagOpts), Writer(Writer) {}
 
// FIXME(llvm-project/issues/57323): Refactor Diagnostic classes.
void SARIFDiagnostic::emitDiagnosticMessage(
    FullSourceLoc Loc, PresumedLoc PLoc, DiagnosticsEngine::Level Level,
    StringRef Message, ArrayRef<clang::CharSourceRange> Ranges,
    DiagOrStoredDiag D) {
 
  const auto *Diag = D.dyn_cast<const Diagnostic *>();
 
  if (!Diag)
    return;
 
  SarifRule Rule = SarifRule::create().setRuleId(std::to_string(Diag->getID()));
 
  Rule = addDiagnosticLevelToRule(Rule, Level);
 
  unsigned RuleIdx = Writer->createRule(Rule);
 
  SarifResult Result =
      SarifResult::create(RuleIdx).setDiagnosticMessage(Message);
 
  if (Loc.isValid())
    Result = addLocationToResult(Result, Loc, PLoc, Ranges, *Diag);
 
  Writer->appendResult(Result);
}
 
SarifResult SARIFDiagnostic::addLocationToResult(
    SarifResult Result, FullSourceLoc Loc, PresumedLoc PLoc,
    ArrayRef<CharSourceRange> Ranges, const Diagnostic &Diag) {
  SmallVector<CharSourceRange> Locations = {};
 
  if (PLoc.isInvalid()) {
    // At least add the file name if available:
    FileID FID = Loc.getFileID();
    if (FID.isValid()) {
      if (OptionalFileEntryRef FE = Loc.getFileEntryRef()) {
        emitFilename(FE->getName(), Loc.getManager());
        // FIXME(llvm-project/issues/57366): File-only locations
      }
    }
    return Result;
  }
 
  FileID CaretFileID = Loc.getExpansionLoc().getFileID();
 
  for (const CharSourceRange Range : Ranges) {
    // Ignore invalid ranges.
    if (Range.isInvalid())
      continue;
 
    auto &SM = Loc.getManager();
    SourceLocation B = SM.getExpansionLoc(Range.getBegin());
    CharSourceRange ERange = SM.getExpansionRange(Range.getEnd());
    SourceLocation E = ERange.getEnd();
    bool IsTokenRange = ERange.isTokenRange();
 
    std::pair<FileID, unsigned> BInfo = SM.getDecomposedLoc(B);
    std::pair<FileID, unsigned> EInfo = SM.getDecomposedLoc(E);
 
    // If the start or end of the range is in another file, just discard
    // it.
    if (BInfo.first != CaretFileID || EInfo.first != CaretFileID)
      continue;
 
    // Add in the length of the token, so that we cover multi-char
    // tokens.
    unsigned TokSize = 0;
    if (IsTokenRange)
      TokSize = Lexer::MeasureTokenLength(E, SM, LangOpts);
 
    FullSourceLoc BF(B, SM), EF(E, SM);
    SourceLocation BeginLoc = SM.translateLineCol(
        BF.getFileID(), BF.getLineNumber(), BF.getColumnNumber());
    SourceLocation EndLoc = SM.translateLineCol(
        EF.getFileID(), EF.getLineNumber(), EF.getColumnNumber() + TokSize);
 
    Locations.push_back(
        CharSourceRange{SourceRange{BeginLoc, EndLoc}, /* ITR = */ false});
    // FIXME: Additional ranges should use presumed location in both
    // Text and SARIF diagnostics.
  }
 
  auto &SM = Loc.getManager();
  auto FID = PLoc.getFileID();
  // Visual Studio 2010 or earlier expects column number to be off by one.
  unsigned int ColNo = (LangOpts.MSCompatibilityVersion &&
                        !LangOpts.isCompatibleWithMSVC(LangOptions::MSVC2012))
                           ? PLoc.getColumn() - 1
                           : PLoc.getColumn();
  SourceLocation DiagLoc = SM.translateLineCol(FID, PLoc.getLine(), ColNo);
 
  // FIXME(llvm-project/issues/57366): Properly process #line directives.
  Locations.push_back(
      CharSourceRange{SourceRange{DiagLoc, DiagLoc}, /* ITR = */ false});
 
  return Result.setLocations(Locations);
}
 
SarifRule
SARIFDiagnostic::addDiagnosticLevelToRule(SarifRule Rule,
                                          DiagnosticsEngine::Level Level) {
  auto Config = SarifReportingConfiguration::create();
 
  switch (Level) {
  case DiagnosticsEngine::Note:
    Config = Config.setLevel(SarifResultLevel::Note);
    break;
  case DiagnosticsEngine::Remark: