SourceMgr.h revision 341825 
1//===- SourceMgr.h - Manager for Source Buffers & Diagnostics ---*- C++ -*-===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This file declares the SMDiagnostic and SourceMgr classes.  This
11// provides a simple substrate for diagnostics, #include handling, and other low
12// level things for simple parsers.
13//
14//===----------------------------------------------------------------------===//
15
16#ifndef LLVM_SUPPORT_SOURCEMGR_H
17#define LLVM_SUPPORT_SOURCEMGR_H
18
19#include "llvm/ADT/ArrayRef.h"
20#include "llvm/ADT/None.h"
21#include "llvm/ADT/PointerUnion.h"
22#include "llvm/ADT/SmallVector.h"
23#include "llvm/ADT/StringRef.h"
24#include "llvm/ADT/Twine.h"
25#include "llvm/Support/MemoryBuffer.h"
26#include "llvm/Support/SMLoc.h"
27#include <algorithm>
28#include <cassert>
29#include <memory>
30#include <string>
31#include <utility>
32#include <vector>
33
34namespace llvm {
35
36class raw_ostream;
37class SMDiagnostic;
38class SMFixIt;
39
40/// This owns the files read by a parser, handles include stacks,
41/// and handles diagnostic wrangling.
42class SourceMgr {
43public:
44  enum DiagKind {
45    DK_Error,
46    DK_Warning,
47    DK_Remark,
48    DK_Note,
49  };
50
51  /// Clients that want to handle their own diagnostics in a custom way can
52  /// register a function pointer+context as a diagnostic handler.
53  /// It gets called each time PrintMessage is invoked.
54  using DiagHandlerTy = void (*)(const SMDiagnostic &, void *Context);
55
56private:
57  struct SrcBuffer {
58    /// The memory buffer for the file.
59    std::unique_ptr<MemoryBuffer> Buffer;
60
61    /// Helper type for OffsetCache below: since we're storing many offsets
62    /// into relatively small files (often smaller than 2^8 or 2^16 bytes),
63    /// we select the offset vector element type dynamically based on the
64    /// size of Buffer.
65    using VariableSizeOffsets = PointerUnion4<std::vector<uint8_t> *,
66                                              std::vector<uint16_t> *,
67                                              std::vector<uint32_t> *,
68                                              std::vector<uint64_t> *>;
69
70    /// Vector of offsets into Buffer at which there are line-endings
71    /// (lazily populated). Once populated, the '\n' that marks the end of
72    /// line number N from [1..] is at Buffer[OffsetCache[N-1]]. Since
73    /// these offsets are in sorted (ascending) order, they can be
74    /// binary-searched for the first one after any given offset (eg. an
75    /// offset corresponding to a particular SMLoc).
76    mutable VariableSizeOffsets OffsetCache;
77
78    /// Populate \c OffsetCache and look up a given \p Ptr in it, assuming
79    /// it points somewhere into \c Buffer. The static type parameter \p T
80    /// must be an unsigned integer type from uint{8,16,32,64}_t large
81    /// enough to store offsets inside \c Buffer.
82    template<typename T>
83    unsigned getLineNumber(const char *Ptr) const;
84
85    /// This is the location of the parent include, or null if at the top level.
86    SMLoc IncludeLoc;
87
88    SrcBuffer() = default;
89    SrcBuffer(SrcBuffer &&);
90    SrcBuffer(const SrcBuffer &) = delete;
91    SrcBuffer &operator=(const SrcBuffer &) = delete;
92    ~SrcBuffer();
93  };
94
95  /// This is all of the buffers that we are reading from.
96  std::vector<SrcBuffer> Buffers;
97
98  // This is the list of directories we should search for include files in.
99  std::vector<std::string> IncludeDirectories;
100
101  DiagHandlerTy DiagHandler = nullptr;
102  void *DiagContext = nullptr;
103
104  bool isValidBufferID(unsigned i) const { return i && i <= Buffers.size(); }
105
106public:
107  SourceMgr() = default;
108  SourceMgr(const SourceMgr &) = delete;
109  SourceMgr &operator=(const SourceMgr &) = delete;
110  ~SourceMgr() = default;
111
112  void setIncludeDirs(const std::vector<std::string> &Dirs) {
113    IncludeDirectories = Dirs;
114  }
115
116  /// Specify a diagnostic handler to be invoked every time PrintMessage is
117  /// called. \p Ctx is passed into the handler when it is invoked.
118  void setDiagHandler(DiagHandlerTy DH, void *Ctx = nullptr) {
119    DiagHandler = DH;
120    DiagContext = Ctx;
121  }
122
123  DiagHandlerTy getDiagHandler() const { return DiagHandler; }
124  void *getDiagContext() const { return DiagContext; }
125
126  const SrcBuffer &getBufferInfo(unsigned i) const {
127    assert(isValidBufferID(i));
128    return Buffers[i - 1];
129  }
130
131  const MemoryBuffer *getMemoryBuffer(unsigned i) const {
132    assert(isValidBufferID(i));
133    return Buffers[i - 1].Buffer.get();
134  }
135
136  unsigned getNumBuffers() const {
137    return Buffers.size();
138  }
139
140  unsigned getMainFileID() const {
141    assert(getNumBuffers());
142    return 1;
143  }
144
145  SMLoc getParentIncludeLoc(unsigned i) const {
146    assert(isValidBufferID(i));
147    return Buffers[i - 1].IncludeLoc;
148  }
149
150  /// Add a new source buffer to this source manager. This takes ownership of
151  /// the memory buffer.
152  unsigned AddNewSourceBuffer(std::unique_ptr<MemoryBuffer> F,
153                              SMLoc IncludeLoc) {
154    SrcBuffer NB;
155    NB.Buffer = std::move(F);
156    NB.IncludeLoc = IncludeLoc;
157    Buffers.push_back(std::move(NB));
158    return Buffers.size();
159  }
160
161  /// Search for a file with the specified name in the current directory or in
162  /// one of the IncludeDirs.
163  ///
164  /// If no file is found, this returns 0, otherwise it returns the buffer ID
165  /// of the stacked file. The full path to the included file can be found in
166  /// \p IncludedFile.
167  unsigned AddIncludeFile(const std::string &Filename, SMLoc IncludeLoc,
168                          std::string &IncludedFile);
169
170  /// Return the ID of the buffer containing the specified location.
171  ///
172  /// 0 is returned if the buffer is not found.
173  unsigned FindBufferContainingLoc(SMLoc Loc) const;
174
175  /// Find the line number for the specified location in the specified file.
176  /// This is not a fast method.
177  unsigned FindLineNumber(SMLoc Loc, unsigned BufferID = 0) const {
178    return getLineAndColumn(Loc, BufferID).first;
179  }
180
181  /// Find the line and column number for the specified location in the
182  /// specified file. This is not a fast method.
183  std::pair<unsigned, unsigned> getLineAndColumn(SMLoc Loc,
184                                                 unsigned BufferID = 0) const;
185
186  /// Emit a message about the specified location with the specified string.
187  ///
188  /// \param ShowColors Display colored messages if output is a terminal and
189  /// the default error handler is used.
190  void PrintMessage(raw_ostream &OS, SMLoc Loc, DiagKind Kind,
191                    const Twine &Msg,
192                    ArrayRef<SMRange> Ranges = None,
193                    ArrayRef<SMFixIt> FixIts = None,
194                    bool ShowColors = true) const;
195
196  /// Emits a diagnostic to llvm::errs().
197  void PrintMessage(SMLoc Loc, DiagKind Kind, const Twine &Msg,
198                    ArrayRef<SMRange> Ranges = None,
199                    ArrayRef<SMFixIt> FixIts = None,
200                    bool ShowColors = true) const;
201
202  /// Emits a manually-constructed diagnostic to the given output stream.
203  ///
204  /// \param ShowColors Display colored messages if output is a terminal and
205  /// the default error handler is used.
206  void PrintMessage(raw_ostream &OS, const SMDiagnostic &Diagnostic,
207                    bool ShowColors = true) const;
208
209  /// Return an SMDiagnostic at the specified location with the specified
210  /// string.
211  ///
212  /// \param Msg If non-null, the kind of message (e.g., "error") which is
213  /// prefixed to the message.
214  SMDiagnostic GetMessage(SMLoc Loc, DiagKind Kind, const Twine &Msg,
215                          ArrayRef<SMRange> Ranges = None,
216                          ArrayRef<SMFixIt> FixIts = None) const;
217
218  /// Prints the names of included files and the line of the file they were
219  /// included from. A diagnostic handler can use this before printing its
220  /// custom formatted message.
221  ///
222  /// \param IncludeLoc The location of the include.
223  /// \param OS the raw_ostream to print on.
224  void PrintIncludeStack(SMLoc IncludeLoc, raw_ostream &OS) const;
225};
226
227/// Represents a single fixit, a replacement of one range of text with another.
228class SMFixIt {
229  SMRange Range;
230
231  std::string Text;
232
233public:
234  // FIXME: Twine.str() is not very efficient.
235  SMFixIt(SMLoc Loc, const Twine &Insertion)
236    : Range(Loc, Loc), Text(Insertion.str()) {
237    assert(Loc.isValid());
238  }
239
240  // FIXME: Twine.str() is not very efficient.
241  SMFixIt(SMRange R, const Twine &Replacement)
242    : Range(R), Text(Replacement.str()) {
243    assert(R.isValid());
244  }
245
246  StringRef getText() const { return Text; }
247  SMRange getRange() const { return Range; }
248
249  bool operator<(const SMFixIt &Other) const {
250    if (Range.Start.getPointer() != Other.Range.Start.getPointer())
251      return Range.Start.getPointer() < Other.Range.Start.getPointer();
252    if (Range.End.getPointer() != Other.Range.End.getPointer())
253      return Range.End.getPointer() < Other.Range.End.getPointer();
254    return Text < Other.Text;
255  }
256};
257
258/// Instances of this class encapsulate one diagnostic report, allowing
259/// printing to a raw_ostream as a caret diagnostic.
260class SMDiagnostic {
261  const SourceMgr *SM = nullptr;
262  SMLoc Loc;
263  std::string Filename;
264  int LineNo = 0;
265  int ColumnNo = 0;
266  SourceMgr::DiagKind Kind = SourceMgr::DK_Error;
267  std::string Message, LineContents;
268  std::vector<std::pair<unsigned, unsigned>> Ranges;
269  SmallVector<SMFixIt, 4> FixIts;
270
271public:
272  // Null diagnostic.
273  SMDiagnostic() = default;
274  // Diagnostic with no location (e.g. file not found, command line arg error).
275  SMDiagnostic(StringRef filename, SourceMgr::DiagKind Knd, StringRef Msg)
276    : Filename(filename), LineNo(-1), ColumnNo(-1), Kind(Knd), Message(Msg) {}
277
278  // Diagnostic with a location.
279  SMDiagnostic(const SourceMgr &sm, SMLoc L, StringRef FN,
280               int Line, int Col, SourceMgr::DiagKind Kind,
281               StringRef Msg, StringRef LineStr,
282               ArrayRef<std::pair<unsigned,unsigned>> Ranges,
283               ArrayRef<SMFixIt> FixIts = None);
284
285  const SourceMgr *getSourceMgr() const { return SM; }
286  SMLoc getLoc() const { return Loc; }
287  StringRef getFilename() const { return Filename; }
288  int getLineNo() const { return LineNo; }
289  int getColumnNo() const { return ColumnNo; }
290  SourceMgr::DiagKind getKind() const { return Kind; }
291  StringRef getMessage() const { return Message; }
292  StringRef getLineContents() const { return LineContents; }
293  ArrayRef<std::pair<unsigned, unsigned>> getRanges() const { return Ranges; }
294
295  void addFixIt(const SMFixIt &Hint) {
296    FixIts.push_back(Hint);
297  }
298
299  ArrayRef<SMFixIt> getFixIts() const {
300    return FixIts;
301  }
302
303  void print(const char *ProgName, raw_ostream &S, bool ShowColors = true,
304             bool ShowKindLabel = true) const;
305};
306
307} // end namespace llvm
308
309#endif // LLVM_SUPPORT_SOURCEMGR_H
310