Chapter 27 deals with iostreams and all their subcomponents and extensions. All kinds of fun stuff.
So you want to copy a file quickly and easily, and most important, completely portably. And since this is C++, you have an open ifstream (call it IN) and an open ofstream (call it OUT):
   #include <fstream>
   std::ifstream  IN ("input_file");
   std::ofstream  OUT ("output_file"); 
   Here's the easiest way to get it completely wrong:
OUT << IN;
For those of you who don't already know why this doesn't work (probably from having done it before), I invite you to quickly create a simple text file called "input_file" containing the sentence
      The quick brown fox jumped over the lazy dog.
   surrounded by blank lines. Code it up and try it. The contents of "output_file" may surprise you.
Seriously, go do it. Get surprised, then come back. It's worth it.
The thing to remember is that the basic_[io]stream classes
      handle formatting, nothing else.  In particular, they break up on
      whitespace.  The actual reading, writing, and storing of data is
      handled by the basic_streambuf family.  Fortunately, the
      operator<< is overloaded to take an ostream and
      a pointer-to-streambuf, in order to help with just this kind of
      "dump the data verbatim" situation.
   
Why a pointer to streambuf and not just a streambuf?  Well,
      the [io]streams hold pointers (or references, depending on the
      implementation) to their buffers, not the actual
      buffers.  This allows polymorphic behavior on the part of the buffers
      as well as the streams themselves.  The pointer is easily retrieved
      using the rdbuf() member function.  Therefore, the easiest
      way to copy the file is:
   
OUT << IN.rdbuf();
So what was happening with OUT<<IN? Undefined behavior, since that particular << isn't defined by the Standard. I have seen instances where it is implemented, but the character extraction process removes all the whitespace, leaving you with no blank lines and only "Thequickbrownfox...". With libraries that do not define that operator, IN (or one of IN's member pointers) sometimes gets converted to a void*, and the output file then contains a perfect text representation of a hexidecimal address (quite a big surprise). Others don't compile at all.
Also note that none of this is specific to o*f*streams. The operators shown above are all defined in the parent basic_ostream class and are therefore available with all possible descendents.
Return to top of page or to the FAQ.
First, are you sure that you understand buffering? Particularly the fact that C++ may not, in fact, have anything to do with it?
The rules for buffering can be a little odd, but they aren't any different from those of C. (Maybe that's why they can be a bit odd.) Many people think that writing a newline to an output stream automatically flushes the output buffer. This is true only when the output stream is, in fact, a terminal and not a file or some other device -- and that may not even be true since C++ says nothing about files nor terminals. All of that is system-dependent. (The "newline-buffer-flushing only occurring on terminals" thing is mostly true on Unix systems, though.)
Some people also believe that sending endl down an
      output stream only writes a newline.  This is incorrect; after a
      newline is written, the buffer is also flushed.  Perhaps this
      is the effect you want when writing to a screen -- get the text
      out as soon as possible, etc -- but the buffering is largely
      wasted when doing this to a file:
   
output << "a line of text" << endl; output << some_data_variable << endl; output << "another line of text" << endl;
The proper thing to do in this case to just write the data out and let the libraries and the system worry about the buffering. If you need a newline, just write a newline:
   output << "a line of text\n"
          << some_data_variable << '\n'
          << "another line of text\n"; 
   I have also joined the output statements into a single statement. You could make the code prettier by moving the single newline to the start of the quoted text on the last line, for example.
If you do need to flush the buffer above, you can send an
      endl if you also need a newline, or just flush the buffer
      yourself:
   
output << ...... << flush; // can use std::flush manipulator output.flush(); // or call a member fn
On the other hand, there are times when writing to a file should be like writing to standard error; no buffering should be done because the data needs to appear quickly (a prime example is a log file for security-related information). The way to do this is just to turn off the buffering before any I/O operations at all have been done (note that opening counts as an I/O operation):
   std::ofstream    os;
   std::ifstream    is;
   int   i;
   os.rdbuf()->pubsetbuf(0,0);
   is.rdbuf()->pubsetbuf(0,0);
   os.open("/foo/bar/baz");
   is.open("/qux/quux/quuux");
   ...
   os << "this data is written immediately\n";
   is >> i;   // and this will probably cause a disk read 
   Since all aspects of buffering are handled by a streambuf-derived
      member, it is necessary to get at that member with rdbuf().
      Then the public version of setbuf can be called.  The 
      arguments are the same as those for the Standard C I/O Library
      function (a buffer area followed by its size).
   
A great deal of this is implementation-dependent.  For example,
      streambuf does not specify any actions for its own 
      setbuf()-ish functions; the classes derived from
      streambuf each define behavior that "makes 
      sense" for that class:  an argument of (0,0) turns off buffering
      for filebuf but does nothing at all for its siblings
      stringbuf and strstreambuf, and specifying
      anything other than (0,0) has varying effects.
      User-defined classes derived from streambuf can
      do whatever they want.  (For filebuf and arguments for
      (p,s) other than zeros, libstdc++ does what you'd expect:
      the first s bytes of p are used as a buffer,
      which you must allocate and deallocate.)
   
A last reminder: there are usually more buffers involved than just those at the language/library level. Kernel buffers, disk buffers, and the like will also have an effect. Inspecting and changing those are system-dependent.
Return to top of page or to the FAQ.
The first and most important thing to remember about binary I/O is
      that opening a file with ios::binary is not, repeat
      not, the only thing you have to do.  It is not a silver
      bullet, and will not allow you to use the <</>>
      operators of the normal fstreams to do binary I/O.
   
Sorry. Them's the breaks.
This isn't going to try and be a complete tutorial on reading and writing binary files (because "binary" covers a lot of ground), but we will try and clear up a couple of misconceptions and common errors.
First, ios::binary has exactly one defined effect, no more
      and no less.  Normal text mode has to be concerned with the newline
      characters, and the runtime system will translate between (for
      example) '\n' and the appropriate end-of-line sequence (LF on Unix,
      CRLF on DOS, CR on Macintosh, etc).  (There are other things that
      normal mode does, but that's the most obvious.)  Opening a file in
      binary mode disables this conversion, so reading a CRLF sequence
      under Windows won't accidentally get mapped to a '\n' character, etc.
      Binary mode is not supposed to suddenly give you a bitstream, and
      if it is doing so in your program then you've discovered a bug in
      your vendor's compiler (or some other part of the C++ implementation,
      possibly the runtime system).
   
Second, using << to write and >> to
      read isn't going to work with the standard file stream classes, even
      if you use skipws during reading.  Why not?  Because 
      ifstream and ofstream exist for the purpose of formatting,
      not reading and writing.  Their job is to interpret the data into
      text characters, and that's exactly what you don't want to happen
      during binary I/O.
   
Third, using the get() and put()/write() member
      functions still aren't guaranteed to help you.  These are
      "unformatted" I/O functions, but still character-based.
      (This may or may not be what you want, see below.)
   
Notice how all the problems here are due to the inappropriate use of formatting functions and classes to perform something which requires that formatting not be done? There are a seemingly infinite number of solutions, and a few are listed here:
mmap()
          the file and copy the structure."  Well, this is easy to
          make work, and easy to break, and is pretty equivalent to
          using ::read() and ::write() directly, and
          makes no use of the iostream library at all...
      How to go about using streambufs is a bit beyond the scope of this document (at least for now), but while streambufs go a long way, they still leave a couple of things up to you, the programmer. As an example, byte ordering is completely between you and the operating system, and you have to handle it yourself.
Deriving a streambuf or filebuf
      class from the standard ones, one that is specific to your data
      types (or an abstraction thereof) is probably a good idea, and
      lots of examples exist in journals and on Usenet.  Using the
      standard filebufs directly (either by declaring your own or by
      using the pointer returned from an fstream's rdbuf())
      is certainly feasible as well.
   
One area that causes problems is trying to do bit-by-bit operations
      with filebufs.  C++ is no different from C in this respect:  I/O
      must be done at the byte level.  If you're trying to read or write
      a few bits at a time, you're going about it the wrong way.  You
      must read/write an integral number of bytes and then process the
      bytes.  (For example, the streambuf functions take and return
      variables of type int_type.)
   
Another area of problems is opening text files in binary mode. Generally, binary mode is intended for binary files, and opening text files in binary mode means that you now have to deal with all of those end-of-line and end-of-file problems that we mentioned before. An instructive thread from comp.lang.c++.moderated delved off into this topic starting more or less at this article and continuing to the end of the thread. (You'll have to sort through some flames every couple of paragraphs, but the points made are good ones.)
Stringstreams (defined in the header <sstream>)
      are in this author's opinion one of the coolest things since
      sliced time.  An example of their use is in the Received Wisdom
      section for Chapter 21 (Strings),
       describing how to
      format strings.
   
The quick definition is:  they are siblings of ifstream and ofstream,
      and they do for std::string what their siblings do for
      files.  All that work you put into writing << and
      >> functions for your classes now pays off
      again!  Need to format a string before passing the string
      to a function?  Send your stuff via << to an
      ostringstream.  You've read a string as input and need to parse it?
      Initialize an istringstream with that string, and then pull pieces
      out of it with >>.  Have a stringstream and need to
      get a copy of the string inside?  Just call the str()
      member function.
   
This only works if you've written your
      <</>> functions correctly, though,
      and correctly means that they take istreams and ostreams as
      parameters, not ifstreams and ofstreams.  If they
      take the latter, then your I/O operators will work fine with
      file streams, but with nothing else -- including stringstreams.
   
If you are a user of the strstream classes, you need to update
      your code.  You don't have to explicitly append ends to
      terminate the C-style character array, you don't have to mess with
      "freezing" functions, and you don't have to manage the
      memory yourself.  The strstreams have been officially deprecated,
      which means that 1) future revisions of the C++ Standard won't
      support them, and 2) if you use them, people will laugh at you.
   
Creating your own stream buffers for I/O can be remarkably easy. If you are interested in doing so, we highly recommend two very excellent books: Standard C++ IOStreams and Locales by Langer and Kreft, ISBN 0-201-18395-1, and The C++ Standard Library by Nicolai Josuttis, ISBN 0-201-37926-0. Both are published by Addison-Wesley, who isn't paying us a cent for saying that, honest.
Here is a simple example, io/outbuf1, from the Josuttis text. It transforms everything sent through it to uppercase. This version assumes many things about the nature of the character type being used (for more information, read the books or the newsgroups):
    #include <iostream>
    #include <streambuf>
    #include <locale>
    #include <cstdio>
    class outbuf : public std::streambuf
    {
      protected:
	/* central output function
	 * - print characters in uppercase mode
	 */
	virtual int_type overflow (int_type c) {
	    if (c != EOF) {
		// convert lowercase to uppercase
		c = std::toupper(static_cast<char>(c),getloc());
		// and write the character to the standard output
		if (putchar(c) == EOF) {
		    return EOF;
		}
	    }
	    return c;
	}
    };
    int main()
    {
	// create special output buffer
	outbuf ob;
	// initialize output stream with that output buffer
	std::ostream out(&ob);
	out << "31 hexadecimal: "
	    << std::hex << 31 << std::endl;
	return 0;
    }
   
   Try it yourself!  More examples can be found in 3.1.x code, in
      include/ext/*_filebuf.h, and on
      Dietmar
      Kühl's IOStreams page.
   
Towards the beginning of February 2001, the subject of "binary" I/O was brought up in a couple of places at the same time. One notable place was Usenet, where James Kanze and Dietmar Kühl separately posted articles on why attempting generic binary I/O was not a good idea. (Here are copies of Kanze's article and Kühl's article.)
Briefly, the problems of byte ordering and type sizes mean that
      the unformatted functions like ostream::put() and
      istream::get() cannot safely be used to communicate
      between arbitrary programs, or across a network, or from one
      invocation of a program to another invocation of the same program
      on a different platform, etc.
   
The entire Usenet thread is instructive, and took place under the subject heading "binary iostreams" on both comp.std.c++ and comp.lang.c++.moderated in parallel. Also in that thread, Dietmar Kühl mentioned that he had written a pair of stream classes that would read and write XDR, which is a good step towards a portable binary format.
It sounds like a flame on C, but it isn't. Really. Calm down. I'm just saying it to get your attention.
Because the C++ library includes the C library, both C-style and C++-style I/O have to work at the same time. For example:
     #include <iostream>
     #include <cstdio>
     std::cout << "Hel";
     std::printf ("lo, worl");
     std::cout << "d!\n";
   
   This must do what you think it does.
Alert members of the audience will immediately notice that buffering is going to make a hash of the output unless special steps are taken.
The special steps taken by libstdc++, at least for version 3.0,
      involve doing very little buffering for the standard streams, leaving
      most of the buffering to the underlying C library.  (This kind of
      thing is tricky to get right.)
      The upside is that correctness is ensured.  The downside is that
      writing through cout can quite easily lead to awful
      performance when the C++ I/O library is layered on top of the C I/O
      library (as it is for 3.0 by default).  Some patches have been applied
      which improve the situation for 3.1.
   
However, the C and C++ standard streams only need to be kept in sync when both libraries' facilities are in use. If your program only uses C++ I/O, then there's no need to sync with the C streams. The right thing to do in this case is to call
     #include any of the I/O headers such as ios, iostream, etc
     std::ios::sync_with_stdio(false);
   
   You must do this before performing any I/O via the C++ stream objects.
      Once you call this, the C++ streams will operate independently of the
      (unused) C streams.  For GCC 3.x, this means that cout and
      company will become fully buffered on their own.
   
Note, by the way, that the synchronization requirement only applies to
      the standard streams (cin, cout,
      cerr,
      clog, and their wide-character counterparts).  File stream
      objects that you declare yourself have no such requirement and are fully
      buffered.
   
I'll assume that you have already read the general notes on library threads, and the notes on threaded container access (you might not think of an I/O stream as a container, but the points made there also hold here). If you have not read them, please do so first.
This gets a bit tricky. Please read carefully, and bear with me.
As described here, a wrapper
      type called __basic_file provides our abstraction layer
      for the std::filebuf classes.  Nearly all decisions dealing
      with actual input and output must be made in __basic_file.
   
A generic locking mechanism is somewhat in place at the filebuf layer, but is not used in the current code. Providing locking at any higher level is akin to providing locking within containers, and is not done for the same reasons (see the links above).
The __basic_file type is simply a collection of small wrappers around
      the C stdio layer (again, see the link under Structure).  We do no
      locking ourselves, but simply pass through to calls to fopen,
      fwrite, and so forth.
   
So, for 3.0, the question of "is multithreading safe for I/O" must be answered with, "is your platform's C library threadsafe for I/O?" Some are by default, some are not; many offer multiple implementations of the C library with varying tradeoffs of threadsafety and efficiency. You, the programmer, are always required to take care with multiple threads.
(As an example, the POSIX standard requires that C stdio FILE*
       operations are atomic.  POSIX-conforming C libraries (e.g, on Solaris
       and GNU/Linux) have an internal mutex to serialize operations on
       FILE*s.  However, you still need to not do stupid things like calling
       fclose(fs) in one thread followed by an access of
       fs in another.)
   
So, if your platform's C library is threadsafe, then your
      fstream I/O operations will be threadsafe at the lowest
      level.  For higher-level operations, such as manipulating the data
      contained in the stream formatting classes (e.g., setting up callbacks
      inside an std::ofstream), you need to guard such accesses
      like any other critical shared resource.
   
As already mentioned here, a second choice is available for I/O implementations: libio. This is disabled by default, and in fact will not currently work due to other issues. It will be revisited, however.
The libio code is a subset of the guts of the GNU libc (glibc) I/O
      implementation.  When libio is in use, the __basic_file
      type is basically derived from FILE.  (The real situation is more
      complex than that... it's derived from an internal type used to
      implement FILE.  See libio/libioP.h to see scary things done with
      vtbls.)  The result is that there is no "layer" of C stdio
      to go through; the filebuf makes calls directly into the same
      functions used to implement fread, fwrite,
      and so forth, using internal data structures.  (And when I say
      "makes calls directly," I mean the function is literally
      replaced by a jump into an internal function.  Fast but frightening.
      *grin*)
   
Also, the libio internal locks are used. This requires pulling in large chunks of glibc, such as a pthreads implementation, and is one of the issues preventing widespread use of libio as the libstdc++ cstdio implementation.
But we plan to make this work, at least as an option if not a future default. Platforms running a copy of glibc with a recent-enough version will see calls from libstdc++ directly into the glibc already installed. For other platforms, a copy of the libio subsection will be built and included in libstdc++.
Don't forget that other cstdio implemenations are possible. You could easily write one to perform your own forms of locking, to solve your "interesting" problems.
To minimize the time you have to wait on the compiler, it's good to only include the headers you really need. Many people simply include <iostream> when they don't need to -- and that can penalize your runtime as well. Here are some tips on which header to use for which situations, starting with the simplest.
<iosfwd> should be included whenever you simply need the name of an I/O-related class, such as "ofstream" or "basic_streambuf". Like the name implies, these are forward declarations. (A word to all you fellow old school programmers: trying to forward declare classes like "class istream;" won't work. Look in the iosfwd header if you'd like to know why.) For example,
    #include <iosfwd>
    class MyClass
    {
        ....
        std::ifstream   input_file;
    };
    extern std::ostream& operator<< (std::ostream&, MyClass&);
   
   <ios> declares the base classes for the entire I/O stream hierarchy, std::ios_base and std::basic_ios<charT>, the counting types std::streamoff and std::streamsize, the file positioning type std::fpos, and the various manipulators like std::hex, std::fixed, std::noshowbase, and so forth.
The ios_base class is what holds the format flags, the state flags, and the functions which change them (setf(), width(), precision(), etc). You can also store extra data and register callback functions through ios_base, but that has been historically underused. Anything which doesn't depend on the type of characters stored is consolidated here.
The template class basic_ios is the highest template class in the hierarchy; it is the first one depending on the character type, and holds all general state associated with that type: the pointer to the polymorphic stream buffer, the facet information, etc.
<streambuf> declares the template class basic_streambuf, and two standard instantiations, streambuf and wstreambuf. If you need to work with the vastly useful and capable stream buffer classes, e.g., to create a new form of storage transport, this header is the one to include.
<istream>/<ostream> are the headers to include when you are using the >>/<< interface, or any of the other abstract stream formatting functions. For example,
    #include <istream>
    std::ostream& operator<< (std::ostream& os, MyClass& c)
    {
       return os << c.data1() << c.data2();
    }
   
   The std::istream and std::ostream classes are the abstract parents of the various concrete implementations. If you are only using the interfaces, then you only need to use the appropriate interface header.
<iomanip> provides "extractors and inserters
      that alter information maintained by class ios_base and its dervied
      classes," such as std::setprecision and std::setw.  If you need
      to write expressions like os << setw(3); or
      is >> setbase(8);, you must include <iomanip>.
   
<sstream>/<fstream> declare the six stringstream and fstream classes. As they are the standard concrete descendants of istream and ostream, you will already know about them.
Finally, <iostream> provides the eight standard global objects (cin, cout, etc). To do this correctly, this header also provides the contents of the <istream> and <ostream> headers, but nothing else. The contents of this header look like
    #include <ostream>
    #include <istream>
    namespace std
    {
        extern istream cin;
        extern ostream cout;
        ....
        // this is explained below
        static ios_base::Init __foo;    // not its real name
    }
   
   Now, the runtime penalty mentioned previously: the global objects must be initialized before any of your own code uses them; this is guaranteed by the standard. Like any other global object, they must be initialized once and only once. This is typically done with a construct like the one above, and the nested class ios_base::Init is specified in the standard for just this reason.
How does it work? Because the header is included before any of your code, the __foo object is constructed before any of your objects. (Global objects are built in the order in which they are declared, and destroyed in reverse order.) The first time the constructor runs, the eight stream objects are set up.
The static keyword means that each object file compiled
      from a source file containing <iostream> will have its own
      private copy of __foo.  There is no specified order
      of construction across object files (it's one of those pesky NP
      problems that make life so interesting), so one copy in each object
      file means that the stream objects are guaranteed to be set up before
      any of your code which uses them could run, thereby meeting the
      requirements of the standard.
   
The penalty, of course, is that after the first copy of __foo is constructed, all the others are just wasted processor time. The time spent is merely for an increment-and-test inside a function call, but over several dozen or hundreds of object files, that time can add up. (It's not in a tight loop, either.)
The lesson? Only include <iostream> when you need to use one of the standard objects in that source file; you'll pay less startup time. Only include the header files you need to in general; your compile times will go down when there's less parsing work to do.
The v2 library included non-standard extensions to construct
      std::filebufs from C stdio types such as
      FILE*s and POSIX file descriptors.
      Today the recommended way to use stdio types with libstdc++-v3
      IOStreams is via the stdio_filebuf class (see below),
      but earlier releases provided slightly different mechanisms.
   
filebufs have another ctor with this signature:
         basic_filebuf(__c_file_type*, ios_base::openmode, int_type);
         __c_file_type*      F   
              // the __c_file_type typedef usually boils down to stdio's FILE
          ios_base::openmode  M   
              // same as all the other uses of openmode
          int_type            B   
              // buffer size, defaults to BUFSIZ if not specified
          fdopen().
     filebufs bring
         back an old extension:  the fd() member function.  The
         integer returned from this function can be used for whatever file
         descriptors can be used for on your platform.  Naturally, the
         library cannot track what you do on your own with a file descriptor,
         so if you perform any I/O directly, don't expect the library to be
         aware of it.
     filebuf constructor and
         the fd() function were removed from the standard
         filebuf.  Instead, <ext/stdio_filebuf.h> contains
         a derived class called
         __gnu_cxx::stdio_filebuf.
         This class can be constructed from a C FILE* or a file
         descriptor, and provides the fd() function.
     If you want to access a filebufs file descriptor to
      implement file locking (e.g. using the fcntl() system
      call) then you might be interested in Henry Suter's
      RWLock
      class.
   
See license.html for copying conditions. Comments and suggestions are welcome, and may be sent to the libstdc++ mailing list.