-//===- ReadArchive.cpp - Code to read LLVM bytecode from .a files ---------===//
+//===- ArchiveReader.cpp - Code to read LLVM bytecode from .a files -------===//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file was developed by the LLVM research group and is distributed under
+// the University of Illinois Open Source License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
//
// This file implements the ReadArchiveFile interface, which allows a linker to
// read all of the LLVM bytecode files contained in a .a file. This file
// understands the standard system .a file format. This can only handle the .a
-// variant prevelant on linux systems so far, but may be extended. See
+// variant prevalent on Linux systems so far, but may be extended. See
// information in this source file for more information:
// http://sources.redhat.com/cgi-bin/cvsweb.cgi/src/bfd/archive.c?cvsroot=src
//
#include "llvm/Bytecode/Reader.h"
#include "llvm/Module.h"
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <fcntl.h>
+#include "Support/FileUtilities.h"
+#include "Config/sys/mman.h"
+#include "Config/fcntl.h"
+#include <cstdlib>
+using namespace llvm;
namespace {
struct ar_hdr {
UserObject, // A user .o/.bc file
Unknown, // Unknown file, just ignore it
SVR4LongFilename, // a "//" section used for long file names
+ ArchiveSymbolTable, // Symbol table produced by ranlib.
};
}
-
-// getObjectType - Determine the type of object that this header represents.
-// This is capable of parsing the variety of special sections used for various
-// purposes.
-static enum ObjectType getObjectType(ar_hdr *H, unsigned Size) {
+/// getObjectType - Determine the type of object that this header represents.
+/// This is capable of parsing the variety of special sections used for various
+/// purposes.
+///
+static enum ObjectType getObjectType(ar_hdr *H, unsigned char *MemberData,
+ unsigned Size) {
// Check for sections with special names...
+ if (!memcmp(H->name, "__.SYMDEF ", 16))
+ return ArchiveSymbolTable;
+ if (!memcmp(H->name, "__.SYMDEF SORTED", 16))
+ return ArchiveSymbolTable;
if (!memcmp(H->name, "// ", 16))
return SVR4LongFilename;
// Check to see if it looks like an llvm object file...
- if (Size >= 4 && !memcmp(H+1, "llvm", 4))
+ if (Size >= 4 && !memcmp(MemberData, "llvm", 4))
return UserObject;
return Unknown;
}
-
static inline bool Error(std::string *ErrorStr, const char *Message) {
if (ErrorStr) *ErrorStr = Message;
return true;
}
-static bool ParseLongFilenameSection(unsigned char *Buffer, unsigned Size,
- std::vector<std::string> &LongFilenames,
- std::string *S) {
- if (!LongFilenames.empty())
- return Error(S, "archive file contains multiple long filename entries");
-
- while (Size) {
- // Long filename entries are newline delimited to keep the archive readable.
- unsigned char *Ptr = (unsigned char*)memchr(Buffer, '\n', Size);
- if (Ptr == 0)
- return Error(S, "archive long filename entry doesn't end with newline!");
- assert(*Ptr == '\n');
-
- if (Ptr == Buffer) break; // Last entry contains just a newline.
-
- unsigned char *End = Ptr;
- if (End[-1] == '/') --End; // Remove trailing / from name
-
- LongFilenames.push_back(std::string(Buffer, End));
- Size -= Ptr-Buffer+1;
- Buffer = Ptr+1;
- }
-
+static bool ParseSymbolTableSection(unsigned char *Buffer, unsigned Size,
+ std::string *S) {
+ // Currently not supported (succeeds without doing anything)
return false;
}
-
-static bool ReadArchiveBuffer(unsigned char *Buffer, unsigned Length,
+static bool ReadArchiveBuffer(const std::string &ArchiveName,
+ unsigned char *Buffer, unsigned Length,
std::vector<Module*> &Objects,
std::string *ErrorStr) {
if (Length < 8 || memcmp(Buffer, "!<arch>\n", 8))
return Error(ErrorStr, "signature incorrect for an archive file!");
Buffer += 8; Length -= 8; // Skip the magic string.
- std::vector<std::string> LongFilenames;
+ std::vector<char> LongFilenames;
while (Length >= sizeof(ar_hdr)) {
ar_hdr *Hdr = (ar_hdr*)Buffer;
- unsigned Size = atoi(Hdr->size);
- if (Size+sizeof(ar_hdr) > Length)
+ unsigned SizeFromHeader = atoi(Hdr->size);
+ if (SizeFromHeader + sizeof(ar_hdr) > Length)
return Error(ErrorStr, "invalid record length in archive file!");
- switch (getObjectType(Hdr, Size)) {
+ unsigned char *MemberData = Buffer + sizeof(ar_hdr);
+ unsigned MemberSize = SizeFromHeader;
+ // Get name of archive member.
+ char *startp = Hdr->name;
+ char *endp = (char *) memchr (startp, '/', sizeof(ar_hdr));
+ if (memcmp (Hdr->name, "#1/", 3) == 0) {
+ // 4.4BSD/MacOSX long filenames are abbreviated as "#1/L", where L is an
+ // ASCII-coded decimal number representing the length of the name buffer,
+ // which is prepended to the archive member's contents.
+ unsigned NameLength = atoi (&Hdr->name[3]);
+ startp = (char *) MemberData;
+ endp = startp + NameLength;
+ MemberData += NameLength;
+ MemberSize -= NameLength;
+ } else if (startp == endp && isdigit (Hdr->name[1])) {
+ // SVR4 long filenames are abbreviated as "/I", where I is
+ // an ASCII-coded decimal index into the LongFilenames vector.
+ unsigned NameIndex = atoi (&Hdr->name[1]);
+ assert (LongFilenames.size () > NameIndex
+ && "SVR4-style long filename for archive member not found");
+ startp = &LongFilenames[NameIndex];
+ endp = strchr (startp, '/');
+ }
+ if (!endp) {
+ // 4.4BSD/MacOSX *short* filenames are not guaranteed to have a
+ // terminator. Start at the end of the field and backtrack over spaces.
+ endp = startp + sizeof(Hdr->name);
+ while (endp[-1] == ' ')
+ --endp;
+ }
+ std::string MemberName (startp, endp);
+ std::string FullMemberName = ArchiveName + "(" + MemberName + ")";
+
+ switch (getObjectType(Hdr, MemberData, MemberSize)) {
case SVR4LongFilename:
// If this is a long filename section, read all of the file names into the
// LongFilenames vector.
- //
- if (ParseLongFilenameSection(Buffer+sizeof(ar_hdr), Size,
- LongFilenames, ErrorStr))
- return true;
+ LongFilenames.assign (MemberData, MemberData + MemberSize);
break;
case UserObject: {
- Module *M = ParseBytecodeBuffer(Buffer+sizeof(ar_hdr), Size, ErrorStr);
+ Module *M = ParseBytecodeBuffer(MemberData, MemberSize,
+ FullMemberName, ErrorStr);
if (!M) return true;
Objects.push_back(M);
break;
}
- case Unknown:
- std::cerr << "ReadArchiveBuffer: WARNING: Skipping unknown file: ";
- std::cerr << std::string(Hdr->name, Hdr->name+sizeof(Hdr->name+1)) <<"\n";
+ case ArchiveSymbolTable:
+ if (ParseSymbolTableSection(MemberData, MemberSize, ErrorStr))
+ return true;
+ break;
+ default:
+ std::cerr << "ReadArchiveBuffer: WARNING: Skipping unknown file: "
+ << FullMemberName << "\n";
break; // Just ignore unknown files.
}
- // Round Size up to an even number...
- Size = (Size+1)/2*2;
- Buffer += sizeof(ar_hdr)+Size; // Move to the next entry
- Length -= sizeof(ar_hdr)+Size;
+ // Round SizeFromHeader up to an even number...
+ SizeFromHeader = (SizeFromHeader+1)/2*2;
+ Buffer += sizeof(ar_hdr)+SizeFromHeader; // Move to the next entry
+ Length -= sizeof(ar_hdr)+SizeFromHeader;
}
return Length != 0;
}
-// ReadArchiveFile - Read bytecode files from the specfied .a file, returning
+// ReadArchiveFile - Read bytecode files from the specified .a file, returning
// true on error, or false on success. This does not support reading files from
// standard input.
//
-bool ReadArchiveFile(const std::string &Filename, std::vector<Module*> &Objects,
- std::string *ErrorStr) {
+bool llvm::ReadArchiveFile(const std::string &Filename,
+ std::vector<Module*> &Objects,std::string *ErrorStr){
+ int Length = getFileSize(Filename);
+ if (Length == -1)
+ return Error(ErrorStr, "Error getting file length!");
+
int FD = open(Filename.c_str(), O_RDONLY);
if (FD == -1)
return Error(ErrorStr, "Error opening file!");
- // Stat the file to get its length...
- struct stat StatBuf;
- if (fstat(FD, &StatBuf) == -1 || StatBuf.st_size == 0)
- return Error(ErrorStr, "Error stat'ing file!");
-
// mmap in the file all at once...
- int Length = StatBuf.st_size;
unsigned char *Buffer = (unsigned char*)mmap(0, Length, PROT_READ,
MAP_PRIVATE, FD, 0);
if (Buffer == (unsigned char*)MAP_FAILED)
return Error(ErrorStr, "Error mmapping file!");
// Parse the archive files we mmap'ped in
- bool Result = ReadArchiveBuffer(Buffer, Length, Objects, ErrorStr);
+ bool Result = ReadArchiveBuffer(Filename, Buffer, Length, Objects, ErrorStr);
// Unmmap the archive...
munmap((char*)Buffer, Length);