Class: Zlib::GzipReader

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

Overview

Zlib::GzipReader is the class for reading a gzipped file. GzipReader should be used as 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(*args) ⇒ 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.



3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
 
# File 'ext/zlib/zlib.c', line 3915

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

    TypedData_Get_Struct(obj, struct gzfile, &gzfile_data_type, 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, Qnil);
    rb_gzfile_ecopts(gz, opt);

    if (rb_respond_to(io, id_path)) {
	/* File#path may raise IOError in case when a path is unavailable */
	rb_rescue2(gzfile_initialize_path_partial, obj, NULL, Qnil, rb_eIOError, (VALUE)0);
    }

    return obj;
}

Class Method Details

.open(*args) ⇒ 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.



3838
3839
3840
3841
3842
 
# File 'ext/zlib/zlib.c', line 3838

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

.zcat(*args) ⇒ Object

call-seq:

Zlib::GzipReader.zcat(io, options = {}, &block) => nil
Zlib::GzipReader.zcat(io, options = {}) => string

Decompresses all gzip data in the io, handling multiple gzip streams until the end of the io. There should not be any non-gzip data after the gzip streams.

If a block is given, it is yielded strings of uncompressed data, and the method returns nil. If a block is not given, the method returns the concatenation of all uncompressed data in all gzip streams.



3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
 
# File 'ext/zlib/zlib.c', line 3860

static VALUE
rb_gzreader_s_zcat(int argc, VALUE *argv, VALUE klass)
{
    VALUE io, unused, obj, buf=0, tmpbuf;
    long pos;

    rb_check_arity(argc, 1, 2);
    io = argv[0];

    do {
        obj = rb_funcallv(klass, rb_intern("new"), argc, argv);
        if (rb_block_given_p()) {
           rb_gzreader_each(0, 0, obj);
        }
        else {
            if (!buf) {
                buf = rb_str_new(0, 0);
            }
            tmpbuf = gzfile_read_all(get_gzfile(obj));
            rb_str_cat(buf, RSTRING_PTR(tmpbuf), RSTRING_LEN(tmpbuf));
        }

        rb_gzreader_read(0, 0, obj);
        pos = NUM2LONG(rb_funcall(io, rb_intern("pos"), 0));
        unused = rb_gzreader_unused(obj);
        rb_gzfile_finish(obj);
        if (!NIL_P(unused)) {
            pos -= NUM2LONG(rb_funcall(unused, rb_intern("length"), 0));
            rb_funcall(io, rb_intern("pos="), 1, LONG2NUM(pos));
        }
    } while (pos < NUM2LONG(rb_funcall(io, rb_intern("size"), 0)));

    if (rb_block_given_p()) {
        return Qnil;
    }
    return buf;
}

Instance Method Details

#each(*args) ⇒ Object

See Zlib::GzipReader documentation for a description.



4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
 
# File 'ext/zlib/zlib.c', line 4385

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.



4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
 
# File 'ext/zlib/zlib.c', line 4111

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.



4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
 
# File 'ext/zlib/zlib.c', line 4093

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(*args) ⇒ Object

See Zlib::GzipReader documentation for a description.



4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
 
# File 'ext/zlib/zlib.c', line 4385

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.



3468
3469
3470
3471
3472
3473
 
# File 'ext/zlib/zlib.c', line 3468

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) 


3468
3469
3470
3471
3472
3473
 
# File 'ext/zlib/zlib.c', line 3468

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

#external_encoding ⇒ Object

See Zlib::GzipReader documentation for a description.



4419
4420
4421
4422
4423
 
# File 'ext/zlib/zlib.c', line 4419

static VALUE
rb_gzreader_external_encoding(VALUE self)
{
    return rb_enc_from_encoding(get_gzfile(self)->enc);
}

#getbyte ⇒ Object

See Zlib::GzipReader documentation for a description.



4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
 
# File 'ext/zlib/zlib.c', line 4059

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.



4030
4031
4032
4033
4034
4035
4036
 
# File 'ext/zlib/zlib.c', line 4030

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

    return gzfile_getc(gz);
}

#gets(*args) ⇒ Object

See Zlib::GzipReader documentation for a description. However, note that this method can return nil even if #eof? returns false, unlike the behavior of File#gets.



4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
 
# File 'ext/zlib/zlib.c', line 4353

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.



3307
3308
3309
3310
3311
 
# File 'ext/zlib/zlib.c', line 3307

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

#lineno=(lineno) ⇒ Object

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



3318
3319
3320
3321
3322
3323
3324
 
# File 'ext/zlib/zlib.c', line 3318

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

#pos ⇒ Object

Total number of output bytes output so far.



3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
 
# File 'ext/zlib/zlib.c', line 3526

static VALUE
rb_gzfile_total_out(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    uLong total_out = gz->z.stream.total_out;
    long buf_filled = ZSTREAM_BUF_FILLED(&gz->z);

    if (total_out >= (uLong)buf_filled) {
        return rb_uint2inum(total_out - buf_filled);
    } else {
        return LONG2FIX(-(buf_filled - (long)total_out));
    }
}

#read(*args) ⇒ Object

See Zlib::GzipReader documentation for a description.



3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
 
# File 'ext/zlib/zlib.c', line 3976

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.



4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
 
# File 'ext/zlib/zlib.c', line 4077

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.



4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
 
# File 'ext/zlib/zlib.c', line 4043

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(*args) ⇒ Object

See Zlib::GzipReader documentation for a description.



4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
 
# File 'ext/zlib/zlib.c', line 4369

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(*args) ⇒ Object

See Zlib::GzipReader documentation for a description.



4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
 
# File 'ext/zlib/zlib.c', line 4403

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(*args) ⇒ 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.



4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
 
# File 'ext/zlib/zlib.c', line 4007

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.



3949
3950
3951
3952
3953
3954
3955
 
# File 'ext/zlib/zlib.c', line 3949

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.



3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
 
# File 'ext/zlib/zlib.c', line 3526

static VALUE
rb_gzfile_total_out(VALUE obj)
{
    struct gzfile *gz = get_gzfile(obj);
    uLong total_out = gz->z.stream.total_out;
    long buf_filled = ZSTREAM_BUF_FILLED(&gz->z);

    if (total_out >= (uLong)buf_filled) {
        return rb_uint2inum(total_out - buf_filled);
    } else {
        return LONG2FIX(-(buf_filled - (long)total_out));
    }
}

#ungetbyte(ch) ⇒ Object

See Zlib::GzipReader documentation for a description.



4151
4152
4153
4154
4155
4156
4157
 
# File 'ext/zlib/zlib.c', line 4151

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

#ungetc(s) ⇒ Object

See Zlib::GzipReader documentation for a description.



4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
 
# File 'ext/zlib/zlib.c', line 4129

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));
    RB_GC_GUARD(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.



3963
3964
3965
3966
3967
3968
3969
 
# File 'ext/zlib/zlib.c', line 3963

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