Class: Zlib::GzipReader

Inherits:
GzipFile show all
Includes:
Enumerable
Defined in:
zlib.c,
zlib.c

Overview

Zlib::GzipReader is the class for reading a gzipped file. GzipReader should be used an IO, or -IO-like, object.

Zlib::GzipReader.open('hoge.gz') {|gz|
  print gz.read
}

File.open('hoge.gz') do |f|
  gz = Zlib::GzipReader.new(f)
  print gz.read
  gz.close
end

Method Catalogue

The following methods in Zlib::GzipReader are just like their counterparts in IO, but they raise Zlib::Error or Zlib::GzipFile::Error exception if an error was found in the gzip file.

  • #each

  • #each_line

  • #each_byte

  • #gets

  • #getc

  • #lineno

  • #lineno=

  • #read

  • #readchar

  • #readline

  • #readlines

  • #ungetc

Be careful of the footer of the gzip file. A gzip file has the checksum of pre-compressed data in its footer. GzipReader checks all uncompressed data against that checksum at the following cases, and if it fails, raises Zlib::GzipFile::NoFooter, Zlib::GzipFile::CRCError, or Zlib::GzipFile::LengthError exception.

  • When an reading request is received beyond the end of file (the end of compressed data). That is, when Zlib::GzipReader#read, Zlib::GzipReader#gets, or some other methods for reading returns nil.

  • When Zlib::GzipFile#close method is called after the object reaches the end of file.

  • When Zlib::GzipReader#unused method is called after the object reaches the end of file.

The rest of the methods are adequately described in their own documentation.

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from GzipFile

#close, #closed?, #comment, #crc, #finish, #level, #mtime, #orig_name, #os_code, #sync, #sync=, #to_io, wrap

Constructor Details

#initialize ⇒ Object

call-seq:

Zlib::GzipReader.new(io, options = {})

Creates a GzipReader object associated with io. The GzipReader object reads gzipped data from io, and parses/decompresses it. The io must have a read method that behaves same as the IO#read.

The options hash may be used to set the encoding of the data. :external_encoding, :internal_encoding and :encoding may be set as in IO::new.

If the gzip file header is incorrect, raises an Zlib::GzipFile::Error exception.



3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
 
# File 'zlib.c', line 3673

static VALUE
rb_gzreader_initialize(int argc, VALUE *argv, VALUE obj)
{
    VALUE io, opt = Qnil;
    struct gzfile *gz;
    int err;

    Data_Get_Struct(obj, struct gzfile, gz);
    rb_scan_args(argc, argv, "1:", &io, &opt);

    /* this is undocumented feature of zlib */
    err = inflateInit2(&gz->z.stream, -MAX_WBITS);
    if (err != Z_OK) {
	raise_zlib_error(err, gz->z.stream.msg);
    }
    gz->io = io;
    ZSTREAM_READY(&gz->z);
    gzfile_read_header(gz);
    rb_gzfile_ecopts(gz, opt);

    if (rb_respond_to(io, id_path)) {
	gz->path = rb_funcall(gz->io, id_path, 0);
	rb_define_singleton_method(obj, "path", rb_gzfile_path, 0);
    }

    return obj;
}

Class Method Details

.open ⇒ Object

call-seq: Zlib::GzipReader.open(filename) {|gz| … }

Opens a file specified by filename as a gzipped file, and returns a GzipReader object associated with that file. Further details of this method are in Zlib::GzipReader.new and ZLib::GzipFile.wrap.



3650
3651
3652
3653
3654
 
# File 'zlib.c', line 3650

static VALUE
rb_gzreader_s_open(int argc, VALUE *argv, VALUE klass)
{
    return gzfile_s_open(argc, argv, klass, "rb");
}

Instance Method Details

#bytes ⇒ Object

This is a deprecated alias for each_byte.



3887
3888
3889
3890
3891
3892
3893
3894
 
# File 'zlib.c', line 3887

static VALUE
rb_gzreader_bytes(VALUE obj)
{
    rb_warn("Zlib::GzipReader#bytes is deprecated; use #each_byte instead");
    if (!rb_block_given_p())
	return rb_enumeratorize(obj, ID2SYM(rb_intern("each_byte")), 0, 0);
    return rb_gzreader_each_byte(obj);
}

#each ⇒ Object

See Zlib::GzipReader documentation for a description.



4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
 
# File 'zlib.c', line 4149

static VALUE
rb_gzreader_each(int argc, VALUE *argv, VALUE obj)
{
    VALUE str;

    RETURN_ENUMERATOR(obj, 0, 0);

    while (!NIL_P(str = gzreader_gets(argc, argv, obj))) {
	rb_yield(str);
    }
    return obj;
}

#each_byte ⇒ Object

See Zlib::GzipReader documentation for a description.



3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
 
# File 'zlib.c', line 3869

static VALUE
rb_gzreader_each_byte(VALUE obj)
{
    VALUE c;

    RETURN_ENUMERATOR(obj, 0, 0);

    while (!NIL_P(c = rb_gzreader_getbyte(obj))) {
	rb_yield(c);
    }
    return Qnil;
}

#each_char ⇒ Object

See Zlib::GzipReader documentation for a description.



3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
 
# File 'zlib.c', line 3851

static VALUE
rb_gzreader_each_char(VALUE obj)
{
    VALUE c;

    RETURN_ENUMERATOR(obj, 0, 0);

    while (!NIL_P(c = rb_gzreader_getc(obj))) {
	rb_yield(c);
    }
    return Qnil;
}

#each_line ⇒ Object

See Zlib::GzipReader documentation for a description.



4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
 
# File 'zlib.c', line 4149

static VALUE
rb_gzreader_each(int argc, VALUE *argv, VALUE obj)
{
    VALUE str;

    RETURN_ENUMERATOR(obj, 0, 0);

    while (!NIL_P(str = gzreader_gets(argc, argv, obj))) {
	rb_yield(str);
    }
    return obj;
}

#eof ⇒ Object

Returns true or false whether the stream has reached the end.



3303
3304
3305
3306
3307
3308
 
# File 'zlib.c', line 3303

static VALUE
rb_gzfile_eof_p(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    return GZFILE_IS_FINISHED(gz) ? Qtrue : Qfalse;
}

#eof? ⇒ Boolean

Returns true or false whether the stream has reached the end.

Returns:

  • (Boolean) 


3303
3304
3305
3306
3307
3308
 
# File 'zlib.c', line 3303

static VALUE
rb_gzfile_eof_p(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    return GZFILE_IS_FINISHED(gz) ? Qtrue : Qfalse;
}

#getbyte ⇒ Object

See Zlib::GzipReader documentation for a description.



3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
 
# File 'zlib.c', line 3817

static VALUE
rb_gzreader_getbyte(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    VALUE dst;

    dst = gzfile_read(gz, 1);
    if (!NIL_P(dst)) {
	dst = INT2FIX((unsigned int)(RSTRING_PTR(dst)[0]) & 0xff);
    }
    return dst;
}

#getc ⇒ Object

See Zlib::GzipReader documentation for a description.



3788
3789
3790
3791
3792
3793
3794
 
# File 'zlib.c', line 3788

static VALUE
rb_gzreader_getc(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);

    return gzfile_getc(gz);
}

#gets ⇒ Object

See Zlib::GzipReader documentation for a description.



4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
 
# File 'zlib.c', line 4117

static VALUE
rb_gzreader_gets(int argc, VALUE *argv, VALUE obj)
{
    VALUE dst;
    dst = gzreader_gets(argc, argv, obj);
    if (!NIL_P(dst)) {
	rb_lastline_set(dst);
    }
    return dst;
}

#lineno ⇒ Object

The line number of the last row read from this file.



3156
3157
3158
3159
3160
 
# File 'zlib.c', line 3156

static VALUE
rb_gzfile_lineno(VALUE obj)
{
    return INT2NUM(get_gzfile(obj)->lineno);
}

#lineno= ⇒ Object

Specify line number of the last row read from this file.



3167
3168
3169
3170
3171
3172
3173
 
# File 'zlib.c', line 3167

static VALUE
rb_gzfile_set_lineno(VALUE obj, VALUE lineno)
{
    struct gzfile *gz = get_gzfile(obj);
    gz->lineno = NUM2INT(lineno);
    return lineno;
}

#lines ⇒ Object

This is a deprecated alias for each_line.



4167
4168
4169
4170
4171
4172
4173
4174
 
# File 'zlib.c', line 4167

static VALUE
rb_gzreader_lines(int argc, VALUE *argv, VALUE obj)
{
    rb_warn("Zlib::GzipReader#lines is deprecated; use #each_line instead");
    if (!rb_block_given_p())
	return rb_enumeratorize(obj, ID2SYM(rb_intern("each_line")), argc, argv);
    return rb_gzreader_each(argc, argv, obj);
}

#pos ⇒ Object

Total number of output bytes output so far.



3361
3362
3363
3364
3365
3366
 
# File 'zlib.c', line 3361

static VALUE
rb_gzfile_total_out(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    return rb_uint2inum(gz->z.stream.total_out - gz->z.buf_filled);
}

#read ⇒ Object

See Zlib::GzipReader documentation for a description.



3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
 
# File 'zlib.c', line 3734

static VALUE
rb_gzreader_read(int argc, VALUE *argv, VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    VALUE vlen;
    long len;

    rb_scan_args(argc, argv, "01", &vlen);
    if (NIL_P(vlen)) {
	return gzfile_read_all(gz);
    }

    len = NUM2INT(vlen);
    if (len < 0) {
	rb_raise(rb_eArgError, "negative length %ld given", len);
    }
    return gzfile_read(gz, len);
}

#readbyte ⇒ Object

See Zlib::GzipReader documentation for a description.



3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
 
# File 'zlib.c', line 3835

static VALUE
rb_gzreader_readbyte(VALUE obj)
{
    VALUE dst;
    dst = rb_gzreader_getbyte(obj);
    if (NIL_P(dst)) {
	rb_raise(rb_eEOFError, "end of file reached");
    }
    return dst;
}

#readchar ⇒ Object

See Zlib::GzipReader documentation for a description.



3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
 
# File 'zlib.c', line 3801

static VALUE
rb_gzreader_readchar(VALUE obj)
{
    VALUE dst;
    dst = rb_gzreader_getc(obj);
    if (NIL_P(dst)) {
	rb_raise(rb_eEOFError, "end of file reached");
    }
    return dst;
}

#readline ⇒ Object

See Zlib::GzipReader documentation for a description.



4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
 
# File 'zlib.c', line 4133

static VALUE
rb_gzreader_readline(int argc, VALUE *argv, VALUE obj)
{
    VALUE dst;
    dst = rb_gzreader_gets(argc, argv, obj);
    if (NIL_P(dst)) {
	rb_raise(rb_eEOFError, "end of file reached");
    }
    return dst;
}

#readlines ⇒ Object

See Zlib::GzipReader documentation for a description.



4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
 
# File 'zlib.c', line 4181

static VALUE
rb_gzreader_readlines(int argc, VALUE *argv, VALUE obj)
{
    VALUE str, dst;
    dst = rb_ary_new();
    while (!NIL_P(str = gzreader_gets(argc, argv, obj))) {
	rb_ary_push(dst, str);
    }
    return dst;
}

#readpartial ⇒ Object

call-seq:

   gzipreader.readpartial(maxlen [, outbuf]) => string, outbuf

Reads at most <i>maxlen</i> bytes from the gziped stream but
it blocks only if <em>gzipreader</em> has no data immediately available.
If the optional <i>outbuf</i> argument is present,
it must reference a String, which will receive the data.
It raises <code>EOFError</code> on end of file.



3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
 
# File 'zlib.c', line 3765

static VALUE
rb_gzreader_readpartial(int argc, VALUE *argv, VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    VALUE vlen, outbuf;
    long len;

    rb_scan_args(argc, argv, "11", &vlen, &outbuf);

    len = NUM2INT(vlen);
    if (len < 0) {
	rb_raise(rb_eArgError, "negative length %ld given", len);
    }
    if (!NIL_P(outbuf))
        Check_Type(outbuf, T_STRING);
    return gzfile_readpartial(gz, len, outbuf);
}

#rewind ⇒ Object

Resets the position of the file pointer to the point created the GzipReader object. The associated IO object needs to respond to the seek method.



3707
3708
3709
3710
3711
3712
3713
 
# File 'zlib.c', line 3707

static VALUE
rb_gzreader_rewind(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    gzfile_reader_rewind(gz);
    return INT2FIX(0);
}

#tell ⇒ Object

Total number of output bytes output so far.



3361
3362
3363
3364
3365
3366
 
# File 'zlib.c', line 3361

static VALUE
rb_gzfile_total_out(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    return rb_uint2inum(gz->z.stream.total_out - gz->z.buf_filled);
}

#ungetbyte ⇒ Object

See Zlib::GzipReader documentation for a description.



3922
3923
3924
3925
3926
3927
3928
 
# File 'zlib.c', line 3922

static VALUE
rb_gzreader_ungetbyte(VALUE obj, VALUE ch)
{
    struct gzfile *gz = get_gzfile(obj);
    gzfile_ungetbyte(gz, NUM2CHR(ch));
    return Qnil;
}

#ungetc ⇒ Object

See Zlib::GzipReader documentation for a description.



3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
 
# File 'zlib.c', line 3901

static VALUE
rb_gzreader_ungetc(VALUE obj, VALUE s)
{
    struct gzfile *gz;

    if (FIXNUM_P(s))
	return rb_gzreader_ungetbyte(obj, s);
    gz = get_gzfile(obj);
    StringValue(s);
    if (gz->enc2 && gz->enc2 != rb_ascii8bit_encoding()) {
	s = rb_str_conv_enc(s, rb_enc_get(s), gz->enc2);
    }
    gzfile_ungets(gz, (const Bytef*)RSTRING_PTR(s), RSTRING_LEN(s));
    return Qnil;
}

#unused ⇒ Object

Returns the rest of the data which had read for parsing gzip format, or nil if the whole gzip file is not parsed yet.



3721
3722
3723
3724
3725
3726
3727
 
# File 'zlib.c', line 3721

static VALUE
rb_gzreader_unused(VALUE obj)
{
    struct gzfile *gz;
    Data_Get_Struct(obj, struct gzfile, gz);
    return gzfile_reader_get_unused(gz);
}