Use the new StringTableBuilder in yaml2elf

[hans]

Summary

Please take a look.

[silvas]

LGTM. I'm still not too fond of having those weird "finalize()" calls which change the behavior of the class, but as long as there are asserts guarding misuse it should be fine.

[hans]

Thanks! Committed r207694.

test/Object/yaml2obj-elf-rel.yaml

Symbols:
   Weak:
     - Name: weak1
 
 # CHECK:        Section {
 # CHECK-NEXT:     Index: 0
 # CHECK:        }
 # CHECK:        Section {
 # CHECK-NEXT:     Index: 1
-# CHECK-NEXT:     Name: .text (1)
+# CHECK-NEXT:     Name: .text (16)
 # CHECK:        }
 # CHECK-NEXT:   Section {
 # CHECK-NEXT:     Index: 2
-# CHECK-NEXT:     Name: .rel.text (7)
+# CHECK-NEXT:     Name: .rel.text (1)
 # CHECK-NEXT:     Type: SHT_REL (0x9)
 # CHECK-NEXT:     Flags [ (0x0)
 # CHECK-NEXT:     ]
 # CHECK-NEXT:     Address: 0x0
 # CHECK-NEXT:     Offset: 0x160
 # CHECK-NEXT:     Size: 24
 # CHECK-NEXT:     Link: 4
 # CHECK-NEXT:     Info: 1
 # CHECK-NEXT:     AddressAlignment: 4
 # CHECK-NEXT:     EntrySize: 8
 # CHECK-NEXT:   }
 # CHECK-NEXT:   Section {
 # CHECK-NEXT:     Index: 3
-# CHECK-NEXT:     Name: .rela.text (17)
+# CHECK-NEXT:     Name: .rela.text (11)
 # CHECK-NEXT:     Type: SHT_RELA (0x4)
 # CHECK-NEXT:     Flags [ (0x0)
 # CHECK-NEXT:     ]
 # CHECK-NEXT:     Address: 0x0
 # CHECK-NEXT:     Offset: 0x180
 # CHECK-NEXT:     Size: 36
 # CHECK-NEXT:     Link: 4
 # CHECK-NEXT:     Info: 1
 # CHECK-NEXT:     AddressAlignment: 4
 # CHECK-NEXT:     EntrySize: 12
 # CHECK-NEXT:   }
 # CHECK-NEXT:   Section {
 # CHECK-NEXT:     Index: 4
-# CHECK-NEXT:     Name: .symtab (28)
+# CHECK-NEXT:     Name: .symtab (40)
 # CHECK:        }
 # CHECK-NEXT:   Section {
 # CHECK-NEXT:     Index: 5
-# CHECK-NEXT:     Name: .strtab (36)
+# CHECK-NEXT:     Name: .strtab (32)
 # CHECK:        }
 # CHECK:        Relocations [
 # CHECK-NEXT:     Section (2) .rel.text {
 # CHECK-NEXT:       0x1 R_MIPS_32 glob1 0x0
 # CHECK-NEXT:       0x1 R_MIPS_CALL16 glob2 0x0
 # CHECK-NEXT:       0x2 R_MIPS_LO16 loc1 0x0
 # CHECK-NEXT:     }
 # CHECK-NEXT:     Section (3) .rela.text {
 # CHECK-NEXT:       0x1 R_MIPS_32 glob1 0x1
 # CHECK-NEXT:       0x1 R_MIPS_CALL16 glob2 0x2
 # CHECK-NEXT:       0x2 R_MIPS_LO16 loc1 0x3
 # CHECK-NEXT:     }
 # CHECK-NEXT:   ]

test/Object/yaml2obj-elf-section-basic.yaml

 # Check that Link != 0.
 # CHECK:          Link: {{[1-9][0-9]*}}
 # CHECK:          AddressAlignment: 2
 # CHECK:          SectionData (
 # CHECK-NEXT:       0000: EBFE
 # CHECK-NEXT:     )
 #
 # CHECK:        Section {
-# CHECK:          Name: .symtab (7)
+# CHECK:          Name: .symtab (25)
 # CHECK:          Type: SHT_SYMTAB (0x2)
 # CHECK:        }
 # CHECK:        Section {
-# CHECK:          Name: .strtab (15)
+# CHECK:          Name: .strtab (17)
 # CHECK:          Type: SHT_STRTAB (0x3)
 # CHECK:        }
 # CHECK:        Section {
-# CHECK:          Name: .shstrtab (23)
+# CHECK:          Name: .shstrtab (7)
 # CHECK:          Type: SHT_STRTAB (0x3)
 # CHECK:        }

tools/yaml2obj/yaml2elf.cpp

 /// \brief The ELF component of yaml2obj.
 ///
 //===----------------------------------------------------------------------===//
 
 #include "yaml2obj.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/Object/ELFYAML.h"
+#include "llvm/Object/StringTableBuilder.h"
 #include "llvm/Support/ELF.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/YAMLTraits.h"
 #include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
-// There is similar code in yaml2coff, but with some slight COFF-specific
-// variations like different initial state. Might be able to deduplicate
-// some day, but also want to make sure that the Mach-O use case is served.
-//
-// This class has a deliberately small interface, since a lot of
-// implementation variation is possible.
-//
-// TODO: Use the StringTable builder from lib/Object instead, since it
-// will deduplicate suffixes.
-namespace {
-class StringTableBuilder {
-  /// \brief Indices of strings currently present in `Buf`.
-  StringMap<unsigned> StringIndices;
-  /// \brief The contents of the string table as we build it.
-  std::string Buf;
-public:
-  StringTableBuilder() {
-    Buf.push_back('\0');
-  }
-  /// \returns Index of string in string table.
-  unsigned addString(StringRef S) {
-    StringMapEntry<unsigned> &Entry = StringIndices.GetOrCreateValue(S);
-    unsigned &I = Entry.getValue();
-    if (I != 0)
-      return I;
-    I = Buf.size();
-    Buf.append(S.begin(), S.end());
-    Buf.push_back('\0');
-    return I;
-  }
-  size_t size() const {
-    return Buf.size();
-  }
-  void writeToStream(raw_ostream &OS) {
-    OS.write(Buf.data(), Buf.size());
-  }
-};
-} // end anonymous namespace
-
 // This class is used to build up a contiguous binary blob while keeping
 // track of an offset in the output (which notionally begins at
 // `InitialOffset`).
 namespace {
 class ContiguousBlobAccumulator {
   const uint64_t InitialOffset;
   SmallVector<char, 128> Buf;
   raw_svector_ostream OS;

 bool ELFState<ELFT>::initSectionHeaders(std::vector<Elf_Shdr> &SHeaders,
                                         ContiguousBlobAccumulator &CBA) {
   // Ensure SHN_UNDEF entry is present. An all-zero section header is a
   // valid SHN_UNDEF entry since SHT_NULL == 0.
   Elf_Shdr SHeader;
   zero(SHeader);
   SHeaders.push_back(SHeader);
 
+  for (const auto &Sec : Doc.Sections)
+    DotShStrtab.add(Sec->Name);
+  DotShStrtab.finalize();
+
   for (const auto &Sec : Doc.Sections) {
     zero(SHeader);
-    SHeader.sh_name = DotShStrtab.addString(Sec->Name);
+    SHeader.sh_name = DotShStrtab.getOffset(Sec->Name);
     SHeader.sh_type = Sec->Type;
     SHeader.sh_flags = Sec->Flags;
     SHeader.sh_addr = Sec->Address;
     SHeader.sh_addralign = Sec->AddressAlign;
 
     if (!Sec->Link.empty()) {
       unsigned Index;
       if (SN2I.lookup(Sec->Link, Index)) {
bool ELFState<ELFT>::initSectionHeaders(std::vector<Elf_Shdr> &SHeaders,
   }
   return true;
 }
 
 template <class ELFT>
 void ELFState<ELFT>::initSymtabSectionHeader(Elf_Shdr &SHeader,
                                              ContiguousBlobAccumulator &CBA) {
   zero(SHeader);
-  SHeader.sh_name = DotShStrtab.addString(StringRef(".symtab"));
+  SHeader.sh_name = DotShStrtab.getOffset(".symtab");
   SHeader.sh_type = ELF::SHT_SYMTAB;
   SHeader.sh_link = getDotStrTabSecNo();
   // One greater than symbol table index of the last local symbol.
   SHeader.sh_info = Doc.Symbols.Local.size() + 1;
   SHeader.sh_entsize = sizeof(Elf_Sym);
 
   std::vector<Elf_Sym> Syms;
   {
     // Ensure STN_UNDEF is present
     Elf_Sym Sym;
     zero(Sym);
     Syms.push_back(Sym);
   }
+
+  // Add symbol names to .strtab.
+  for (const auto &Sym : Doc.Symbols.Local)
+    DotStrtab.add(Sym.Name);
+  for (const auto &Sym : Doc.Symbols.Global)
+    DotStrtab.add(Sym.Name);
+  for (const auto &Sym : Doc.Symbols.Weak)
+    DotStrtab.add(Sym.Name);
+  DotStrtab.finalize();
+
   addSymbols(Doc.Symbols.Local, Syms, ELF::STB_LOCAL);
   addSymbols(Doc.Symbols.Global, Syms, ELF::STB_GLOBAL);
   addSymbols(Doc.Symbols.Weak, Syms, ELF::STB_WEAK);
 
   writeArrayData(CBA.getOSAndAlignedOffset(SHeader.sh_offset),
                  makeArrayRef(Syms));
   SHeader.sh_size = arrayDataSize(makeArrayRef(Syms));
 }
 
 template <class ELFT>
 void ELFState<ELFT>::initStrtabSectionHeader(Elf_Shdr &SHeader, StringRef Name,
                                              StringTableBuilder &STB,
                                              ContiguousBlobAccumulator &CBA) {
   zero(SHeader);
-  SHeader.sh_name = DotShStrtab.addString(Name);
+  SHeader.sh_name = DotShStrtab.getOffset(Name);
   SHeader.sh_type = ELF::SHT_STRTAB;
-  STB.writeToStream(CBA.getOSAndAlignedOffset(SHeader.sh_offset));
-  SHeader.sh_size = STB.size();
+  CBA.getOSAndAlignedOffset(SHeader.sh_offset) << STB.data();
+  SHeader.sh_size = STB.data().size();
   SHeader.sh_addralign = 1;
 }
 
 template <class ELFT>
 void ELFState<ELFT>::addSymbols(const std::vector<ELFYAML::Symbol> &Symbols,
                                 std::vector<Elf_Sym> &Syms,
                                 unsigned SymbolBinding) {
   for (const auto &Sym : Symbols) {
     Elf_Sym Symbol;
     zero(Symbol);
     if (!Sym.Name.empty())
-      Symbol.st_name = DotStrtab.addString(Sym.Name);
+      Symbol.st_name = DotStrtab.getOffset(Sym.Name);
     Symbol.setBindingAndType(SymbolBinding, Sym.Type);
     if (!Sym.Section.empty()) {
       unsigned Index;
       if (SN2I.lookup(Sym.Section, Index)) {
         errs() << "error: Unknown section referenced: '" << Sym.Section
                << "' by YAML symbol " << Sym.Name << ".\n";
         exit(1);
       }
int ELFState<ELFT>::writeELF(raw_ostream &OS, const ELFYAML::Object &Doc) {
   // TODO: Program headers.
 
   // XXX: This offset is tightly coupled with the order that we write
   // things to `OS`.
   const size_t SectionContentBeginOffset =
       Header.e_ehsize + Header.e_shentsize * Header.e_shnum;
   ContiguousBlobAccumulator CBA(SectionContentBeginOffset);
 
+  // Doc might not contain .symtab, .strtab and .shstrtab sections,
+  // but we will emit them, so make sure to add them to ShStrTabSHeader.
+  State.DotShStrtab.add(".symtab");
+  State.DotShStrtab.add(".strtab");
+  State.DotShStrtab.add(".shstrtab");
+
   std::vector<Elf_Shdr> SHeaders;
   if(!State.initSectionHeaders(SHeaders, CBA))
     return 1;
 
   // .symtab section.
   Elf_Shdr SymtabSHeader;
   State.initSymtabSectionHeader(SymtabSHeader, CBA);
   SHeaders.push_back(SymtabSHeader);