In Files

  • marshal.c

Marshal

The marshaling library converts collections of Ruby objects into a byte stream, allowing them to be stored outside the currently active script. This data may subsequently be read and the original objects reconstituted. Marshaled data has major and minor version numbers stored along with the object information. In normal use, marshaling can only load data written with the same major version number and an equal or lower minor version number. If Ruby's “verbose'' flag is set (normally using -d, -v, -w, or –verbose) the major and minor numbers must match exactly. Marshal versioning is independent of Ruby's version numbers. You can extract the version by reading the first two bytes of marshaled data.

str = Marshal.dump("thing")
RUBY_VERSION   #=> "1.8.0"
str[0]         #=> 4
str[1]         #=> 8

Some objects cannot be dumped: if the objects to be dumped include bindings, procedure or method objects, instances of class IO, or singleton objects, a TypeError will be raised. If your class has special serialization needs (for example, if you want to serialize in some specific format), or if it contains objects that would otherwise not be serializable, you can implement your own serialization strategy by defining two methods, _dump and _load: The instance method _dump should return a String object containing all the information necessary to reconstitute objects of this class and all referenced objects up to a maximum depth given as an integer parameter (a value of -1 implies that you should disable depth checking). The class method _load should take a String and return an object of this class.

Public Class Methods

dump( obj [, anIO] , limit=--1 ) => anIO click to toggle source

Serializes obj and all descendent objects. If anIO is specified, the serialized data will be written to it, otherwise the data will be returned as a String. If limit is specified, the traversal of subobjects will be limited to that depth. If limit is negative, no checking of depth will be performed.

class Klass
  def initialize(str)
    @str = str
  end
  def sayHello
    @str
  end
end

(produces no output)

o = Klass.new("hello\n")
data = Marshal.dump(o)
obj = Marshal.load(data)
obj.sayHello   #=> "hello\n"
 
               static VALUE
marshal_dump(argc, argv)
    int argc;
    VALUE* argv;
{
    VALUE obj, port, a1, a2;
    int limit = -1;
    struct dump_arg arg;
    struct dump_call_arg c_arg;

    port = Qnil;
    rb_scan_args(argc, argv, "12", &obj, &a1, &a2);
    if (argc == 3) {
        if (!NIL_P(a2)) limit = NUM2INT(a2);
        if (NIL_P(a1)) goto type_error;
        port = a1;
    }
    else if (argc == 2) {
        if (FIXNUM_P(a1)) limit = FIX2INT(a1);
        else if (NIL_P(a1)) goto type_error;
        else port = a1;
    }
    arg.dest = 0;
    arg.symbols = st_init_numtable();
    arg.data    = st_init_numtable();
    arg.taint   = Qfalse;
    arg.str = rb_str_buf_new(0);
    RBASIC(arg.str)->klass = 0;
    arg.wrapper = Data_Wrap_Struct(rb_cData, mark_dump_arg, 0, &arg);
    if (!NIL_P(port)) {
        if (!rb_respond_to(port, s_write)) {
          type_error:
            rb_raise(rb_eTypeError, "instance of IO needed");
        }
        arg.dest = port;
        if (rb_respond_to(port, s_binmode)) {
            rb_funcall2(port, s_binmode, 0, 0);
            check_dump_arg(&arg, s_binmode);
        }
    }
    else {
        port = arg.str;
    }

    c_arg.obj   = obj;
    c_arg.arg   = &arg;
    c_arg.limit = limit;

    w_byte(MARSHAL_MAJOR, &arg);
    w_byte(MARSHAL_MINOR, &arg);

    rb_ensure(dump, (VALUE)&c_arg, dump_ensure, (VALUE)&arg);
    RBASIC(arg.str)->klass = rb_cString;

    return port;
}
            
load( source [, proc] ) => obj click to toggle source

Returns the result of converting the serialized data in source into a Ruby object (possibly with associated subordinate objects). source may be either an instance of IO or an object that responds to to_str. If proc is specified, it will be passed each object as it is deserialized.

 
               static VALUE
marshal_load(argc, argv)
    int argc;
    VALUE *argv;
{
    VALUE port, proc;
    int major, minor;
    VALUE v;
    struct load_arg arg;

    rb_scan_args(argc, argv, "11", &port, &proc);
    v = rb_check_string_type(port);
    if (!NIL_P(v)) {
        arg.taint = OBJ_TAINTED(port); /* original taintedness */
        port = v;
    }
    else if (rb_respond_to(port, s_getc) && rb_respond_to(port, s_read)) {
        if (rb_respond_to(port, s_binmode)) {
            rb_funcall2(port, s_binmode, 0, 0);
        }
        arg.taint = Qtrue;
    }
    else {
        rb_raise(rb_eTypeError, "instance of IO needed");
    }
    arg.src = port;
    arg.offset = 0;
    arg.symbols = st_init_numtable();
    arg.data    = st_init_numtable();
    arg.proc = 0;
    arg.wrapper = Data_Wrap_Struct(rb_cData, mark_load_arg, 0, &arg);

    major = r_byte(&arg);
    minor = r_byte(&arg);
    if (major != MARSHAL_MAJOR || minor > MARSHAL_MINOR) {
        rb_raise(rb_eTypeError, "incompatible marshal file format (can't be read)\n\
\tformat version %d.%d required; %d.%d given",
                 MARSHAL_MAJOR, MARSHAL_MINOR, major, minor);
    }
    if (RTEST(ruby_verbose) && minor != MARSHAL_MINOR) {
        rb_warn("incompatible marshal file format (can be read)\n\
\tformat version %d.%d required; %d.%d given",
                MARSHAL_MAJOR, MARSHAL_MINOR, major, minor);
    }

    if (!NIL_P(proc)) arg.proc = proc;
    v = rb_ensure(load, (VALUE)&arg, load_ensure, (VALUE)&arg);

    return v;
}
            
restore( source [, proc] ) => obj click to toggle source

Returns the result of converting the serialized data in source into a Ruby object (possibly with associated subordinate objects). source may be either an instance of IO or an object that responds to to_str. If proc is specified, it will be passed each object as it is deserialized.

 
               static VALUE
marshal_load(argc, argv)
    int argc;
    VALUE *argv;
{
    VALUE port, proc;
    int major, minor;
    VALUE v;
    struct load_arg arg;

    rb_scan_args(argc, argv, "11", &port, &proc);
    v = rb_check_string_type(port);
    if (!NIL_P(v)) {
        arg.taint = OBJ_TAINTED(port); /* original taintedness */
        port = v;
    }
    else if (rb_respond_to(port, s_getc) && rb_respond_to(port, s_read)) {
        if (rb_respond_to(port, s_binmode)) {
            rb_funcall2(port, s_binmode, 0, 0);
        }
        arg.taint = Qtrue;
    }
    else {
        rb_raise(rb_eTypeError, "instance of IO needed");
    }
    arg.src = port;
    arg.offset = 0;
    arg.symbols = st_init_numtable();
    arg.data    = st_init_numtable();
    arg.proc = 0;
    arg.wrapper = Data_Wrap_Struct(rb_cData, mark_load_arg, 0, &arg);

    major = r_byte(&arg);
    minor = r_byte(&arg);
    if (major != MARSHAL_MAJOR || minor > MARSHAL_MINOR) {
        rb_raise(rb_eTypeError, "incompatible marshal file format (can't be read)\n\
\tformat version %d.%d required; %d.%d given",
                 MARSHAL_MAJOR, MARSHAL_MINOR, major, minor);
    }
    if (RTEST(ruby_verbose) && minor != MARSHAL_MINOR) {
        rb_warn("incompatible marshal file format (can be read)\n\
\tformat version %d.%d required; %d.%d given",
                MARSHAL_MAJOR, MARSHAL_MINOR, major, minor);
    }

    if (!NIL_P(proc)) arg.proc = proc;
    v = rb_ensure(load, (VALUE)&arg, load_ensure, (VALUE)&arg);

    return v;
}