[clang] 7b6fe71 - Refactor StaticAnalyzer to use `clang::SarifDocumentWriter`
Aaron Ballman via cfe-commits
cfe-commits at lists.llvm.org
Thu Nov 17 11:48:44 PST 2022
Author: Vaibhav Yenamandra
Date: 2022-11-17T14:47:02-05:00
New Revision: 7b6fe711b210a90cbb8facfe5343a0f999de5a0c
URL: https://github.com/llvm/llvm-project/commit/7b6fe711b210a90cbb8facfe5343a0f999de5a0c
DIFF: https://github.com/llvm/llvm-project/commit/7b6fe711b210a90cbb8facfe5343a0f999de5a0c.diff
LOG: Refactor StaticAnalyzer to use `clang::SarifDocumentWriter`
Refactor StaticAnalyzer to use clang::SarifDocumentWriter for
serializing sarif diagnostics.
Uses clang::SarifDocumentWriter to generate SARIF output in the
StaticAnalyzer.
Various bugfixes are also made to clang::SarifDocumentWriter.
Summary of changes:
clang/lib/Basic/Sarif.cpp:
* Fix bug in adjustColumnPos introduced from prev move, it now uses
FullSourceLoc::getDecomposedExpansionLoc which provides the correct
location (in the presence of macros) instead of
FullSourceLoc::getDecomposedLoc.
* Fix createTextRegion so that it handles caret ranges correctly,
this should bring it to parity with the previous implementation.
clang/test/Analysis/diagnostics/Inputs/expected-sarif:
* Update the schema URL to the offical website
* Add the emitted defaultConfiguration sections to all rules
* Annotate results with the "level" property
clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp:
* Update SarifDiagnostics class to hold a clang::SarifDocumentWriter
that it uses to convert diagnostics to SARIF.
Added:
Modified:
clang/include/clang/Basic/SourceLocation.h
clang/lib/Basic/Sarif.cpp
clang/lib/Basic/SourceLocation.cpp
clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp
clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-diagnostics-taint-test.c.sarif
clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-multi-diagnostic-test.c.sarif
clang/test/Frontend/sarif-diagnostics.cpp
clang/unittests/Basic/SarifTest.cpp
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/SourceLocation.h b/clang/include/clang/Basic/SourceLocation.h
index 4451523bc9450..c709c1102834b 100644
--- a/clang/include/clang/Basic/SourceLocation.h
+++ b/clang/include/clang/Basic/SourceLocation.h
@@ -398,6 +398,12 @@ class FullSourceLoc : public SourceLocation {
unsigned getExpansionLineNumber(bool *Invalid = nullptr) const;
unsigned getExpansionColumnNumber(bool *Invalid = nullptr) const;
+ /// Decompose the underlying \c SourceLocation into a raw (FileID + Offset)
+ /// pair, after walking through all expansion records.
+ ///
+ /// \see SourceManager::getDecomposedExpansionLoc
+ std::pair<FileID, unsigned> getDecomposedExpansionLoc() const;
+
unsigned getSpellingLineNumber(bool *Invalid = nullptr) const;
unsigned getSpellingColumnNumber(bool *Invalid = nullptr) const;
diff --git a/clang/lib/Basic/Sarif.cpp b/clang/lib/Basic/Sarif.cpp
index 73be86b57df77..b3bee674225d2 100644
--- a/clang/lib/Basic/Sarif.cpp
+++ b/clang/lib/Basic/Sarif.cpp
@@ -118,7 +118,7 @@ static unsigned int adjustColumnPos(FullSourceLoc Loc,
unsigned int TokenLen = 0) {
assert(!Loc.isInvalid() && "invalid Loc when adjusting column position");
- std::pair<FileID, unsigned> LocInfo = Loc.getDecomposedLoc();
+ std::pair<FileID, unsigned> LocInfo = Loc.getDecomposedExpansionLoc();
Optional<MemoryBufferRef> Buf =
Loc.getManager().getBufferOrNone(LocInfo.first);
assert(Buf && "got an invalid buffer for the location's file");
@@ -149,13 +149,16 @@ json::Object createMessage(StringRef Text) {
/// \pre CharSourceRange must be a token range
static json::Object createTextRegion(const SourceManager &SM,
const CharSourceRange &R) {
- FullSourceLoc FirstTokenLoc{R.getBegin(), SM};
- FullSourceLoc LastTokenLoc{R.getEnd(), SM};
- json::Object Region{{"startLine", FirstTokenLoc.getExpansionLineNumber()},
- {"startColumn", adjustColumnPos(FirstTokenLoc)},
- {"endColumn", adjustColumnPos(LastTokenLoc)}};
- if (FirstTokenLoc != LastTokenLoc) {
- Region["endLine"] = LastTokenLoc.getExpansionLineNumber();
+ FullSourceLoc BeginCharLoc{R.getBegin(), SM};
+ FullSourceLoc EndCharLoc{R.getEnd(), SM};
+ json::Object Region{{"startLine", BeginCharLoc.getExpansionLineNumber()},
+ {"startColumn", adjustColumnPos(BeginCharLoc)}};
+
+ if (BeginCharLoc == EndCharLoc) {
+ Region["endColumn"] = adjustColumnPos(BeginCharLoc);
+ } else {
+ Region["endLine"] = EndCharLoc.getExpansionLineNumber();
+ Region["endColumn"] = adjustColumnPos(EndCharLoc);
}
return Region;
}
@@ -232,8 +235,10 @@ SarifDocumentWriter::createPhysicalLocation(const CharSourceRange &R) {
}
assert(I != CurrentArtifacts.end() && "Failed to insert new artifact");
const SarifArtifactLocation &Location = I->second.Location;
- uint32_t Idx = Location.Index.value();
- return json::Object{{{"artifactLocation", json::Object{{{"index", Idx}}}},
+ json::Object ArtifactLocationObject{{"uri", Location.URI}};
+ if (Location.Index.has_value())
+ ArtifactLocationObject["index"] = Location.Index.value();
+ return json::Object{{{"artifactLocation", std::move(ArtifactLocationObject)},
{"region", createTextRegion(SourceMgr, R)}}};
}
diff --git a/clang/lib/Basic/SourceLocation.cpp b/clang/lib/Basic/SourceLocation.cpp
index f9ecd52e5f27b..772f2e612f074 100644
--- a/clang/lib/Basic/SourceLocation.cpp
+++ b/clang/lib/Basic/SourceLocation.cpp
@@ -166,6 +166,10 @@ FullSourceLoc FullSourceLoc::getExpansionLoc() const {
return FullSourceLoc(SrcMgr->getExpansionLoc(*this), *SrcMgr);
}
+std::pair<FileID, unsigned> FullSourceLoc::getDecomposedExpansionLoc() const {
+ return SrcMgr->getDecomposedExpansionLoc(*this);
+}
+
FullSourceLoc FullSourceLoc::getSpellingLoc() const {
assert(isValid());
return FullSourceLoc(SrcMgr->getSpellingLoc(*this), *SrcMgr);
diff --git a/clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp b/clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp
index ad31107925929..fab520098f13e 100644
--- a/clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp
+++ b/clang/lib/StaticAnalyzer/Core/SarifDiagnostics.cpp
@@ -13,6 +13,8 @@
#include "clang/Analysis/MacroExpansionContext.h"
#include "clang/Analysis/PathDiagnostic.h"
#include "clang/Basic/FileManager.h"
+#include "clang/Basic/Sarif.h"
+#include "clang/Basic/SourceManager.h"
#include "clang/Basic/Version.h"
#include "clang/Lex/Preprocessor.h"
#include "clang/StaticAnalyzer/Core/PathDiagnosticConsumers.h"
@@ -30,10 +32,12 @@ namespace {
class SarifDiagnostics : public PathDiagnosticConsumer {
std::string OutputFile;
const LangOptions &LO;
+ SarifDocumentWriter SarifWriter;
public:
- SarifDiagnostics(const std::string &Output, const LangOptions &LO)
- : OutputFile(Output), LO(LO) {}
+ SarifDiagnostics(const std::string &Output, const LangOptions &LO,
+ const SourceManager &SM)
+ : OutputFile(Output), LO(LO), SarifWriter(SM) {}
~SarifDiagnostics() override = default;
void FlushDiagnosticsImpl(std::vector<const PathDiagnostic *> &Diags,
@@ -56,250 +60,12 @@ void ento::createSarifDiagnosticConsumer(
if (Output.empty())
return;
- C.push_back(new SarifDiagnostics(Output, PP.getLangOpts()));
+ C.push_back(
+ new SarifDiagnostics(Output, PP.getLangOpts(), PP.getSourceManager()));
createTextMinimalPathDiagnosticConsumer(std::move(DiagOpts), C, Output, PP,
CTU, MacroExpansions);
}
-static StringRef getFileName(const FileEntry &FE) {
- StringRef Filename = FE.tryGetRealPathName();
- if (Filename.empty())
- Filename = FE.getName();
- return Filename;
-}
-
-static std::string percentEncodeURICharacter(char C) {
- // RFC 3986 claims alpha, numeric, and this handful of
- // characters are not reserved for the path component and
- // should be written out directly. Otherwise, percent
- // encode the character and write that out instead of the
- // reserved character.
- if (llvm::isAlnum(C) ||
- StringRef::npos != StringRef("-._~:@!$&'()*+,;=").find(C))
- return std::string(&C, 1);
- return "%" + llvm::toHex(StringRef(&C, 1));
-}
-
-static std::string fileNameToURI(StringRef Filename) {
- llvm::SmallString<32> Ret = StringRef("file://");
-
- // Get the root name to see if it has a URI authority.
- StringRef Root = sys::path::root_name(Filename);
- if (Root.startswith("//")) {
- // There is an authority, so add it to the URI.
- Ret += Root.drop_front(2).str();
- } else if (!Root.empty()) {
- // There is no authority, so end the component and add the root to the URI.
- Ret += Twine("/" + Root).str();
- }
-
- auto Iter = sys::path::begin(Filename), End = sys::path::end(Filename);
- assert(Iter != End && "Expected there to be a non-root path component.");
- // Add the rest of the path components, encoding any reserved characters;
- // we skip past the first path component, as it was handled it above.
- for (StringRef Component : llvm::make_range(++Iter, End)) {
- // For reasons unknown to me, we may get a backslash with Windows native
- // paths for the initial backslash following the drive component, which
- // we need to ignore as a URI path part.
- if (Component == "\\")
- continue;
-
- // Add the separator between the previous path part and the one being
- // currently processed.
- Ret += "/";
-
- // URI encode the part.
- for (char C : Component) {
- Ret += percentEncodeURICharacter(C);
- }
- }
-
- return std::string(Ret);
-}
-
-static json::Object createArtifactLocation(const FileEntry &FE) {
- return json::Object{{"uri", fileNameToURI(getFileName(FE))}};
-}
-
-static json::Object createArtifact(const FileEntry &FE) {
- return json::Object{{"location", createArtifactLocation(FE)},
- {"roles", json::Array{"resultFile"}},
- {"length", FE.getSize()},
- {"mimeType", "text/plain"}};
-}
-
-static json::Object createArtifactLocation(const FileEntry &FE,
- json::Array &Artifacts) {
- std::string FileURI = fileNameToURI(getFileName(FE));
-
- // See if the Artifacts array contains this URI already. If it does not,
- // create a new artifact object to add to the array.
- auto I = llvm::find_if(Artifacts, [&](const json::Value &File) {
- if (const json::Object *Obj = File.getAsObject()) {
- if (const json::Object *FileLoc = Obj->getObject("location")) {
- Optional<StringRef> URI = FileLoc->getString("uri");
- return URI && URI->equals(FileURI);
- }
- }
- return false;
- });
-
- // Calculate the index within the artifact array so it can be stored in
- // the JSON object.
- auto Index = static_cast<unsigned>(std::distance(Artifacts.begin(), I));
- if (I == Artifacts.end())
- Artifacts.push_back(createArtifact(FE));
-
- return json::Object{{"uri", FileURI}, {"index", Index}};
-}
-
-static unsigned int adjustColumnPos(const SourceManager &SM, SourceLocation Loc,
- unsigned int TokenLen = 0) {
- assert(!Loc.isInvalid() && "invalid Loc when adjusting column position");
-
- std::pair<FileID, unsigned> LocInfo = SM.getDecomposedExpansionLoc(Loc);
- assert(LocInfo.second > SM.getExpansionColumnNumber(Loc) &&
- "position in file is before column number?");
-
- Optional<MemoryBufferRef> Buf = SM.getBufferOrNone(LocInfo.first);
- assert(Buf && "got an invalid buffer for the location's file");
- assert(Buf->getBufferSize() >= (LocInfo.second + TokenLen) &&
- "token extends past end of buffer?");
-
- // Adjust the offset to be the start of the line, since we'll be counting
- // Unicode characters from there until our column offset.
- unsigned int Off = LocInfo.second - (SM.getExpansionColumnNumber(Loc) - 1);
- unsigned int Ret = 1;
- while (Off < (LocInfo.second + TokenLen)) {
- Off += getNumBytesForUTF8(Buf->getBuffer()[Off]);
- Ret++;
- }
-
- return Ret;
-}
-
-static json::Object createTextRegion(const LangOptions &LO, SourceRange R,
- const SourceManager &SM) {
- json::Object Region{
- {"startLine", SM.getExpansionLineNumber(R.getBegin())},
- {"startColumn", adjustColumnPos(SM, R.getBegin())},
- };
- if (R.getBegin() == R.getEnd()) {
- Region["endColumn"] = adjustColumnPos(SM, R.getBegin());
- } else {
- Region["endLine"] = SM.getExpansionLineNumber(R.getEnd());
- Region["endColumn"] = adjustColumnPos(
- SM, R.getEnd(),
- Lexer::MeasureTokenLength(R.getEnd(), SM, LO));
- }
- return Region;
-}
-
-static json::Object createPhysicalLocation(const LangOptions &LO,
- SourceRange R, const FileEntry &FE,
- const SourceManager &SMgr,
- json::Array &Artifacts) {
- return json::Object{
- {{"artifactLocation", createArtifactLocation(FE, Artifacts)},
- {"region", createTextRegion(LO, R, SMgr)}}};
-}
-
-enum class Importance { Important, Essential, Unimportant };
-
-static StringRef importanceToStr(Importance I) {
- switch (I) {
- case Importance::Important:
- return "important";
- case Importance::Essential:
- return "essential";
- case Importance::Unimportant:
- return "unimportant";
- }
- llvm_unreachable("Fully covered switch is not so fully covered");
-}
-
-static json::Object createThreadFlowLocation(json::Object &&Location,
- Importance I) {
- return json::Object{{"location", std::move(Location)},
- {"importance", importanceToStr(I)}};
-}
-
-static json::Object createMessage(StringRef Text) {
- return json::Object{{"text", Text.str()}};
-}
-
-static json::Object createLocation(json::Object &&PhysicalLocation,
- StringRef Message = "") {
- json::Object Ret{{"physicalLocation", std::move(PhysicalLocation)}};
- if (!Message.empty())
- Ret.insert({"message", createMessage(Message)});
- return Ret;
-}
-
-static Importance calculateImportance(const PathDiagnosticPiece &Piece) {
- switch (Piece.getKind()) {
- case PathDiagnosticPiece::Call:
- case PathDiagnosticPiece::Macro:
- case PathDiagnosticPiece::Note:
- case PathDiagnosticPiece::PopUp:
- // FIXME: What should be reported here?
- break;
- case PathDiagnosticPiece::Event:
- return Piece.getTagStr() == "ConditionBRVisitor" ? Importance::Important
- : Importance::Essential;
- case PathDiagnosticPiece::ControlFlow:
- return Importance::Unimportant;
- }
- return Importance::Unimportant;
-}
-
-static json::Object createThreadFlow(const LangOptions &LO,
- const PathPieces &Pieces,
- json::Array &Artifacts) {
- const SourceManager &SMgr = Pieces.front()->getLocation().getManager();
- json::Array Locations;
- for (const auto &Piece : Pieces) {
- const PathDiagnosticLocation &P = Piece->getLocation();
- Locations.push_back(createThreadFlowLocation(
- createLocation(createPhysicalLocation(
- LO, P.asRange(),
- *P.asLocation().getExpansionLoc().getFileEntry(),
- SMgr, Artifacts),
- Piece->getString()),
- calculateImportance(*Piece)));
- }
- return json::Object{{"locations", std::move(Locations)}};
-}
-
-static json::Object createCodeFlow(const LangOptions &LO,
- const PathPieces &Pieces,
- json::Array &Artifacts) {
- return json::Object{
- {"threadFlows", json::Array{createThreadFlow(LO, Pieces, Artifacts)}}};
-}
-
-static json::Object createResult(const LangOptions &LO,
- const PathDiagnostic &Diag,
- json::Array &Artifacts,
- const StringMap<unsigned> &RuleMapping) {
- const PathPieces &Path = Diag.path.flatten(false);
- const SourceManager &SMgr = Path.front()->getLocation().getManager();
-
- auto Iter = RuleMapping.find(Diag.getCheckerName());
- assert(Iter != RuleMapping.end() && "Rule ID is not in the array index map?");
-
- return json::Object{
- {"message", createMessage(Diag.getVerboseDescription())},
- {"codeFlows", json::Array{createCodeFlow(LO, Path, Artifacts)}},
- {"locations",
- json::Array{createLocation(createPhysicalLocation(
- LO, Diag.getLocation().asRange(),
- *Diag.getLocation().asLocation().getExpansionLoc().getFileEntry(),
- SMgr, Artifacts))}},
- {"ruleIndex", Iter->getValue()},
- {"ruleId", Diag.getCheckerName()}};
-}
-
static StringRef getRuleDescription(StringRef CheckName) {
return llvm::StringSwitch<StringRef>(CheckName)
#define GET_CHECKERS
@@ -322,60 +88,99 @@ static StringRef getRuleHelpURIStr(StringRef CheckName) {
;
}
-static json::Object createRule(const PathDiagnostic &Diag) {
- StringRef CheckName = Diag.getCheckerName();
- json::Object Ret{
- {"fullDescription", createMessage(getRuleDescription(CheckName))},
- {"name", CheckName},
- {"id", CheckName}};
-
- std::string RuleURI = std::string(getRuleHelpURIStr(CheckName));
- if (!RuleURI.empty())
- Ret["helpUri"] = RuleURI;
-
- return Ret;
+static ThreadFlowImportance
+calculateImportance(const PathDiagnosticPiece &Piece) {
+ switch (Piece.getKind()) {
+ case PathDiagnosticPiece::Call:
+ case PathDiagnosticPiece::Macro:
+ case PathDiagnosticPiece::Note:
+ case PathDiagnosticPiece::PopUp:
+ // FIXME: What should be reported here?
+ break;
+ case PathDiagnosticPiece::Event:
+ return Piece.getTagStr() == "ConditionBRVisitor"
+ ? ThreadFlowImportance::Important
+ : ThreadFlowImportance::Essential;
+ case PathDiagnosticPiece::ControlFlow:
+ return ThreadFlowImportance::Unimportant;
+ }
+ return ThreadFlowImportance::Unimportant;
+}
+
+/// Accepts a SourceRange corresponding to a pair of the first and last tokens
+/// and converts to a Character granular CharSourceRange.
+static CharSourceRange convertTokenRangeToCharRange(const SourceRange &R,
+ const SourceManager &SM,
+ const LangOptions &LO) {
+ // Caret diagnostics have the first and last locations pointed at the same
+ // location, return these as-is.
+ if (R.getBegin() == R.getEnd())
+ return CharSourceRange::getCharRange(R);
+
+ SourceLocation BeginCharLoc = R.getBegin();
+ // For token ranges, the raw end SLoc points at the first character of the
+ // last token in the range. This must be moved to one past the end of the
+ // last character using the lexer.
+ SourceLocation EndCharLoc =
+ Lexer::getLocForEndOfToken(R.getEnd(), /* Offset = */ 0, SM, LO);
+ return CharSourceRange::getCharRange(BeginCharLoc, EndCharLoc);
+}
+
+static SmallVector<ThreadFlow, 8> createThreadFlows(const PathDiagnostic *Diag,
+ const LangOptions &LO) {
+ SmallVector<ThreadFlow, 8> Flows;
+ const PathPieces &Pieces = Diag->path.flatten(false);
+ for (const auto &Piece : Pieces) {
+ auto Range = convertTokenRangeToCharRange(
+ Piece->getLocation().asRange(), Piece->getLocation().getManager(), LO);
+ auto Flow = ThreadFlow::create()
+ .setImportance(calculateImportance(*Piece))
+ .setRange(Range)
+ .setMessage(Piece->getString());
+ Flows.push_back(Flow);
+ }
+ return Flows;
}
-static json::Array createRules(std::vector<const PathDiagnostic *> &Diags,
- StringMap<unsigned> &RuleMapping) {
- json::Array Rules;
+static StringMap<uint32_t>
+createRuleMapping(const std::vector<const PathDiagnostic *> &Diags,
+ SarifDocumentWriter &SarifWriter) {
+ StringMap<uint32_t> RuleMapping;
llvm::StringSet<> Seen;
for (const PathDiagnostic *D : Diags) {
- StringRef RuleID = D->getCheckerName();
- std::pair<llvm::StringSet<>::iterator, bool> P = Seen.insert(RuleID);
+ StringRef CheckName = D->getCheckerName();
+ std::pair<llvm::StringSet<>::iterator, bool> P = Seen.insert(CheckName);
if (P.second) {
- RuleMapping[RuleID] = Rules.size(); // Maps RuleID to an Array Index.
- Rules.push_back(createRule(*D));
+ auto Rule = SarifRule::create()
+ .setName(CheckName)
+ .setRuleId(CheckName)
+ .setDescription(getRuleDescription(CheckName))
+ .setHelpURI(getRuleHelpURIStr(CheckName));
+ size_t RuleIdx = SarifWriter.createRule(Rule);
+ RuleMapping[CheckName] = RuleIdx;
}
}
-
- return Rules;
+ return RuleMapping;
}
-static json::Object createTool(std::vector<const PathDiagnostic *> &Diags,
- StringMap<unsigned> &RuleMapping) {
- return json::Object{
- {"driver", json::Object{{"name", "clang"},
- {"fullName", "clang static analyzer"},
- {"language", "en-US"},
- {"version", getClangFullVersion()},
- {"rules", createRules(Diags, RuleMapping)}}}};
-}
-
-static json::Object createRun(const LangOptions &LO,
- std::vector<const PathDiagnostic *> &Diags) {
- json::Array Results, Artifacts;
- StringMap<unsigned> RuleMapping;
- json::Object Tool = createTool(Diags, RuleMapping);
+static SarifResult createResult(const PathDiagnostic *Diag,
+ const StringMap<uint32_t> &RuleMapping,
+ const LangOptions &LO) {
- for (const PathDiagnostic *D : Diags)
- Results.push_back(createResult(LO, *D, Artifacts, RuleMapping));
+ StringRef CheckName = Diag->getCheckerName();
+ uint32_t RuleIdx = RuleMapping.lookup(CheckName);
+ auto Range = convertTokenRangeToCharRange(
+ Diag->getLocation().asRange(), Diag->getLocation().getManager(), LO);
- return json::Object{{"tool", std::move(Tool)},
- {"results", std::move(Results)},
- {"artifacts", std::move(Artifacts)},
- {"columnKind", "unicodeCodePoints"}};
+ SmallVector<ThreadFlow, 8> Flows = createThreadFlows(Diag, LO);
+ auto Result = SarifResult::create(RuleIdx)
+ .setRuleId(CheckName)
+ .setDiagnosticMessage(Diag->getVerboseDescription())
+ .setDiagnosticLevel(SarifResultLevel::Warning)
+ .setLocations({Range})
+ .setThreadFlows(Flows);
+ return Result;
}
void SarifDiagnostics::FlushDiagnosticsImpl(
@@ -391,10 +196,14 @@ void SarifDiagnostics::FlushDiagnosticsImpl(
llvm::errs() << "warning: could not create file: " << EC.message() << '\n';
return;
}
- json::Object Sarif{
- {"$schema",
- "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json"},
- {"version", "2.1.0"},
- {"runs", json::Array{createRun(LO, Diags)}}};
- OS << llvm::formatv("{0:2}\n", json::Value(std::move(Sarif)));
+
+ std::string ToolVersion = getClangFullVersion();
+ SarifWriter.createRun("clang", "clang static analyzer", ToolVersion);
+ StringMap<uint32_t> RuleMapping = createRuleMapping(Diags, SarifWriter);
+ for (const PathDiagnostic *D : Diags) {
+ SarifResult Result = createResult(D, RuleMapping, LO);
+ SarifWriter.appendResult(Result);
+ }
+ auto Document = SarifWriter.createDocument();
+ OS << llvm::formatv("{0:2}\n", json::Value(std::move(Document)));
}
diff --git a/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-diagnostics-taint-test.c.sarif b/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-diagnostics-taint-test.c.sarif
index 2deb1bd90c259..0ac96cacbed19 100644
--- a/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-diagnostics-taint-test.c.sarif
+++ b/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-diagnostics-taint-test.c.sarif
@@ -1,11 +1,12 @@
{
- "$schema": "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json",
+ "$schema": "https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json",
"runs": [
{
"artifacts": [
{
"length": 434,
"location": {
+ "index": 0,
},
"mimeType": "text/plain",
"roles": [
@@ -64,6 +65,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -89,10 +91,16 @@
"tool": {
"driver": {
"fullName": "clang static analyzer",
+ "informationUri": "https://clang.llvm.org/docs/UsersManual.html",
"language": "en-US",
"name": "clang",
"rules": [
{
+ "defaultConfiguration": {
+ "enabled": true,
+ "level": "warning",
+ "rank": -1
+ },
"fullDescription": {
"text": "Mark tainted symbols as such."
},
diff --git a/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-multi-diagnostic-test.c.sarif b/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-multi-diagnostic-test.c.sarif
index 9005a3654ad0e..ae49ad6604cb2 100644
--- a/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-multi-diagnostic-test.c.sarif
+++ b/clang/test/Analysis/diagnostics/Inputs/expected-sarif/sarif-multi-diagnostic-test.c.sarif
@@ -1,11 +1,12 @@
{
- "$schema": "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json",
+ "$schema": "https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json",
"runs": [
{
"artifacts": [
{
"length": 1081,
"location": {
+ "index": 0,
},
"mimeType": "text/plain",
"roles": [
@@ -64,6 +65,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -153,6 +155,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -240,6 +243,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -345,6 +349,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -413,6 +418,7 @@
]
}
],
+ "level": "warning",
"locations": [
{
"physicalLocation": {
@@ -437,10 +443,16 @@
"tool": {
"driver": {
"fullName": "clang static analyzer",
+ "informationUri": "https://clang.llvm.org/docs/UsersManual.html",
"language": "en-US",
"name": "clang",
"rules": [
{
+ "defaultConfiguration": {
+ "enabled": true,
+ "level": "warning",
+ "rank": -1
+ },
"fullDescription": {
"text": "Mark tainted symbols as such."
},
@@ -448,6 +460,11 @@
"name": "debug.TaintTest"
},
{
+ "defaultConfiguration": {
+ "enabled": true,
+ "level": "warning",
+ "rank": -1
+ },
"fullDescription": {
"text": "Check for logical errors for function calls and Objective-C message expressions (e.g., uninitialized arguments, null function pointers)"
},
@@ -456,6 +473,11 @@
"name": "core.CallAndMessage"
},
{
+ "defaultConfiguration": {
+ "enabled": true,
+ "level": "warning",
+ "rank": -1
+ },
"fullDescription": {
"text": "Check for division by zero"
},
@@ -464,6 +486,11 @@
"name": "core.DivideZero"
},
{
+ "defaultConfiguration": {
+ "enabled": true,
+ "level": "warning",
+ "rank": -1
+ },
"fullDescription": {
"text": "Check for memory leaks, double free, and use-after-free problems. Traces memory managed by malloc()/free()."
},
diff --git a/clang/test/Frontend/sarif-diagnostics.cpp b/clang/test/Frontend/sarif-diagnostics.cpp
index 9e390285b30dd..3a35131cdb004 100644
--- a/clang/test/Frontend/sarif-diagnostics.cpp
+++ b/clang/test/Frontend/sarif-diagnostics.cpp
@@ -33,25 +33,25 @@ void f1(t1 x, t1 y) {
// CHECK: ,"location":{"index":0,"uri":"file://
// Omit filepath to llvm project directory
// CHECK: clang/test/Frontend/sarif-diagnostics.cpp"},"mimeType":"text/plain","roles":["resultFile"]}],"columnKind":"unicodeCodePoints","results":
-// CHECK: [{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":
+// CHECK: [{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
// CHECK: {"endColumn":1,"startColumn":1,"startLine":12}}}],"message":{"text":"'main' must return 'int'"},"ruleId":"{{[0-9]+}}","ruleIndex":0},
-// CHECK: {"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":
+// CHECK: {"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
// CHECK: {"endColumn":11,"startColumn":11,"startLine":13}}}],"message":{"text":"use of undeclared identifier
// CHECK: 'hello'"},"ruleId":"{{[0-9]+}}","ruleIndex":1},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":
-// CHECK: {"index":0},"region":{"endColumn":17,"startColumn":17,"startLine":15}}}],"message":{"text":"invalid digit 'a' in decimal
+// CHECK: {"index":0,"uri":"file://{{.+}}"},"region":{"endColumn":17,"startColumn":17,"startLine":15}}}],"message":{"text":"invalid digit 'a' in decimal
// CHECK: constant"},"ruleId":"{{[0-9]+}}","ruleIndex":2},{"level":"warning","locations":[{"physicalLocation":{"artifactLocation":
-// CHECK: {"index":0},"region":{"endColumn":5,"startColumn":5,"startLine":19}}}],"message":{"text":"misleading indentation; statement is not part
+// CHECK: {"index":0,"uri":"file://{{.+}}"},"region":{"endColumn":5,"startColumn":5,"startLine":19}}}],"message":{"text":"misleading indentation; statement is not part
// CHECK: of the previous 'if'"},"ruleId":"{{[0-9]+}}","ruleIndex":3},{"level":"note","locations":[{"physicalLocation":{"artifactLocation":
-// CHECK: {"index":0},"region":{"endColumn":3,"startColumn":3,"startLine":17}}}],"message":{"text":"previous statement is
+// CHECK: {"index":0,"uri":"file://{{.+}}"},"region":{"endColumn":3,"startColumn":3,"startLine":17}}}],"message":{"text":"previous statement is
// CHECK: here"},"ruleId":"{{[0-9]+}}","ruleIndex":4},{"level":"warning","locations":[{"physicalLocation":{"artifactLocation":
-// CHECK: {"index":0},"region":{"endColumn":10,"startColumn":10,"startLine":18}}}],"message":{"text":"unused variable
-// CHECK: 'Yes'"},"ruleId":"{{[0-9]+}}","ruleIndex":5},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":
+// CHECK: {"index":0,"uri":"file://{{.+}}"},"region":{"endColumn":10,"startColumn":10,"startLine":18}}}],"message":{"text":"unused variable
+// CHECK: 'Yes'"},"ruleId":"{{[0-9]+}}","ruleIndex":5},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
// CHECK: {"endColumn":12,"startColumn":12,"startLine":21}}}],"message":{"text":"use of undeclared identifier
-// CHECK: 'hi'"},"ruleId":"{{[0-9]+}}","ruleIndex":6},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":
+// CHECK: 'hi'"},"ruleId":"{{[0-9]+}}","ruleIndex":6},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
// CHECK: {"endColumn":1,"startColumn":1,"startLine":23}}}],"message":{"text":"extraneous closing brace
-// CHECK: ('}')"},"ruleId":"{{[0-9]+}}","ruleIndex":7},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":
-// CHECK: {"endColumn":6,"endLine":27,"startColumn":5,"startLine":27}}},{"physicalLocation":{"artifactLocation":{"index":0},"region":
-// CHECK: {"endColumn":10,"endLine":27,"startColumn":9,"startLine":27}}},{"physicalLocation":{"artifactLocation":{"index":0},"region":
+// CHECK: ('}')"},"ruleId":"{{[0-9]+}}","ruleIndex":7},{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
+// CHECK: {"endColumn":6,"endLine":27,"startColumn":5,"startLine":27}}},{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
+// CHECK: {"endColumn":10,"endLine":27,"startColumn":9,"startLine":27}}},{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file://
// CHECK: {"endColumn":7,"startColumn":7,"startLine":27}}}],"message":{"text":"invalid operands to binary expression ('t1' and
// CHECK: 't1')"},"ruleId":"{{[0-9]+}}","ruleIndex":8}],"tool":{"driver":{"fullName":"","informationUri":"https://clang.llvm.org/docs/
// CHECK: UsersManual.html","language":"en-US","name":"clang","rules":[{"defaultConfiguration":
diff --git a/clang/unittests/Basic/SarifTest.cpp b/clang/unittests/Basic/SarifTest.cpp
index fb68f4a4b99b8..9bbed582f50b6 100644
--- a/clang/unittests/Basic/SarifTest.cpp
+++ b/clang/unittests/Basic/SarifTest.cpp
@@ -292,7 +292,7 @@ TEST_F(SarifDocumentWriterTest, checkSerializingResultsWithCustomRuleConfig) {
TEST_F(SarifDocumentWriterTest, checkSerializingArtifacts) {
// GIVEN:
const std::string ExpectedOutput =
- R"({"$schema":"https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json","runs":[{"artifacts":[{"length":40,"location":{"index":0,"uri":"file:///main.cpp"},"mimeType":"text/plain","roles":["resultFile"]}],"columnKind":"unicodeCodePoints","results":[{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":{"endColumn":14,"startColumn":14,"startLine":3}}}],"message":{"text":"expected ';' after top level declarator"},"ruleId":"clang.unittest","ruleIndex":0}],"tool":{"driver":{"fullName":"sarif test runner","informationUri":"https://clang.llvm.org/docs/UsersManual.html","language":"en-US","name":"sarif test","rules":[{"defaultConfiguration":{"enabled":true,"level":"warning","rank":-1},"fullDescription":{"text":"Example rule created during unit tests"},"id":"clang.unittest","name":"clang unit test"}],"version":"1.0.0"}}}],"version":"2.1.0"})";
+ R"({"$schema":"https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json","runs":[{"artifacts":[{"length":40,"location":{"index":0,"uri":"file:///main.cpp"},"mimeType":"text/plain","roles":["resultFile"]}],"columnKind":"unicodeCodePoints","results":[{"level":"error","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file:///main.cpp"},"region":{"endColumn":14,"startColumn":14,"startLine":3}}}],"message":{"text":"expected ';' after top level declarator"},"ruleId":"clang.unittest","ruleIndex":0}],"tool":{"driver":{"fullName":"sarif test runner","informationUri":"https://clang.llvm.org/docs/UsersManual.html","language":"en-US","name":"sarif test","rules":[{"defaultConfiguration":{"enabled":true,"level":"warning","rank":-1},"fullDescription":{"text":"Example rule created during unit tests"},"id":"clang.unittest","name":"clang unit test"}],"version":"1.0.0"}}}],"version":"2.1.0"})";
SarifDocumentWriter Writer{SourceMgr};
const SarifRule &Rule =
@@ -332,7 +332,7 @@ TEST_F(SarifDocumentWriterTest, checkSerializingArtifacts) {
TEST_F(SarifDocumentWriterTest, checkSerializingCodeflows) {
// GIVEN:
const std::string ExpectedOutput =
- R"({"$schema":"https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json","runs":[{"artifacts":[{"length":27,"location":{"index":1,"uri":"file:///test-header-1.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":30,"location":{"index":2,"uri":"file:///test-header-2.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":28,"location":{"index":3,"uri":"file:///test-header-3.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":41,"location":{"index":0,"uri":"file:///main.cpp"},"mimeType":"text/plain","roles":["resultFile"]}],"columnKind":"unicodeCodePoints","results":[{"codeFlows":[{"threadFlows":[{"locations":[{"importance":"essential","location":{"message":{"text":"Message #1"},"physicalLocation":{"artifactLocation":{"index":1},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}},{"importance":"important","location":{"message":{"text":"Message #2"},"physicalLocation":{"artifactLocation":{"index":2},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}},{"importance":"unimportant","location":{"message":{"text":"Message #3"},"physicalLocation":{"artifactLocation":{"index":3},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}}]}]}],"level":"warning","locations":[{"physicalLocation":{"artifactLocation":{"index":0},"region":{"endColumn":8,"endLine":2,"startColumn":5,"startLine":2}}}],"message":{"text":"Redefinition of 'foo'"},"ruleId":"clang.unittest","ruleIndex":0}],"tool":{"driver":{"fullName":"sarif test runner","informationUri":"https://clang.llvm.org/docs/UsersManual.html","language":"en-US","name":"sarif test","rules":[{"defaultConfiguration":{"enabled":true,"level":"warning","rank":-1},"fullDescription":{"text":"Example rule created during unit tests"},"id":"clang.unittest","name":"clang unit test"}],"version":"1.0.0"}}}],"version":"2.1.0"})";
+ R"({"$schema":"https://docs.oasis-open.org/sarif/sarif/v2.1.0/cos02/schemas/sarif-schema-2.1.0.json","runs":[{"artifacts":[{"length":27,"location":{"index":1,"uri":"file:///test-header-1.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":30,"location":{"index":2,"uri":"file:///test-header-2.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":28,"location":{"index":3,"uri":"file:///test-header-3.h"},"mimeType":"text/plain","roles":["resultFile"]},{"length":41,"location":{"index":0,"uri":"file:///main.cpp"},"mimeType":"text/plain","roles":["resultFile"]}],"columnKind":"unicodeCodePoints","results":[{"codeFlows":[{"threadFlows":[{"locations":[{"importance":"essential","location":{"message":{"text":"Message #1"},"physicalLocation":{"artifactLocation":{"index":1,"uri":"file:///test-header-1.h"},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}},{"importance":"important","location":{"message":{"text":"Message #2"},"physicalLocation":{"artifactLocation":{"index":2,"uri":"file:///test-header-2.h"},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}},{"importance":"unimportant","location":{"message":{"text":"Message #3"},"physicalLocation":{"artifactLocation":{"index":3,"uri":"file:///test-header-3.h"},"region":{"endColumn":8,"endLine":2,"startColumn":1,"startLine":1}}}}]}]}],"level":"warning","locations":[{"physicalLocation":{"artifactLocation":{"index":0,"uri":"file:///main.cpp"},"region":{"endColumn":8,"endLine":2,"startColumn":5,"startLine":2}}}],"message":{"text":"Redefinition of 'foo'"},"ruleId":"clang.unittest","ruleIndex":0}],"tool":{"driver":{"fullName":"sarif test runner","informationUri":"https://clang.llvm.org/docs/UsersManual.html","language":"en-US","name":"sarif test","rules":[{"defaultConfiguration":{"enabled":true,"level":"warning","rank":-1},"fullDescription":{"text":"Example rule created during unit tests"},"id":"clang.unittest","name":"clang unit test"}],"version":"1.0.0"}}}],"version":"2.1.0"})";
const char *SourceText = "int foo = 0;\n"
"int foo = 1;\n"
More information about the cfe-commits
mailing list