Class: Zlib::GzipReader
- Includes:
- Enumerable
- Defined in:
- zlib.c,
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
-
.open(*args) ⇒ Object
call-seq: Zlib::GzipReader.open(filename) {|gz| … }.
-
.zcat(*args) ⇒ Object
call-seq: Zlib::GzipReader.zcat(io, options = {}, &block) => nil Zlib::GzipReader.zcat(io, options = {}) => string.
Instance Method Summary collapse
-
#each(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#each_byte ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#each_char ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#each_line(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#eof ⇒ Object
Returns
true
orfalse
whether the stream has reached the end. -
#eof? ⇒ Boolean
Returns
true
orfalse
whether the stream has reached the end. -
#external_encoding ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#getbyte ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#getc ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#gets(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#initialize(*args) ⇒ Object
constructor
call-seq: Zlib::GzipReader.new(io, options = {}).
-
#lineno ⇒ Object
The line number of the last row read from this file.
-
#lineno=(lineno) ⇒ Object
Specify line number of the last row read from this file.
-
#pos ⇒ Object
Total number of output bytes output so far.
-
#read(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#readbyte ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#readchar ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#readline(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#readlines(*args) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#readpartial(*args) ⇒ Object
call-seq: gzipreader.readpartial(maxlen [, outbuf]) => string, outbuf.
-
#rewind ⇒ Object
Resets the position of the file pointer to the point created the GzipReader object.
-
#tell ⇒ Object
Total number of output bytes output so far.
-
#ungetbyte(ch) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#ungetc(s) ⇒ Object
See Zlib::GzipReader documentation for a description.
-
#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.
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, = {})
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.
3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 |
# File 'zlib.c', line 3949 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.
3872 3873 3874 3875 3876 |
# File 'zlib.c', line 3872 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, = {}, &block) => nil
Zlib::GzipReader.zcat(io, = {}) => 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.
3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 |
# File 'zlib.c', line 3894 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.
4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 |
# File 'zlib.c', line 4419 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.
4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 |
# File 'zlib.c', line 4145 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.
4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 |
# File 'zlib.c', line 4127 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.
4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 |
# File 'zlib.c', line 4419 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.
3499 3500 3501 3502 3503 3504 3505 3506 3507 |
# File 'zlib.c', line 3499 static VALUE rb_gzfile_eof_p(VALUE obj) { struct gzfile *gz = get_gzfile(obj); while (!ZSTREAM_IS_FINISHED(&gz->z) && ZSTREAM_BUF_FILLED(&gz->z) == 0) { gzfile_read_more(gz, Qnil); } return GZFILE_IS_FINISHED(gz) ? Qtrue : Qfalse; } |
#eof? ⇒ Boolean
Returns true
or false
whether the stream has reached the end.
3499 3500 3501 3502 3503 3504 3505 3506 3507 |
# File 'zlib.c', line 3499 static VALUE rb_gzfile_eof_p(VALUE obj) { struct gzfile *gz = get_gzfile(obj); while (!ZSTREAM_IS_FINISHED(&gz->z) && ZSTREAM_BUF_FILLED(&gz->z) == 0) { gzfile_read_more(gz, Qnil); } return GZFILE_IS_FINISHED(gz) ? Qtrue : Qfalse; } |
#external_encoding ⇒ Object
See Zlib::GzipReader documentation for a description.
4453 4454 4455 4456 4457 |
# File 'zlib.c', line 4453 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.
4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 |
# File 'zlib.c', line 4093 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.
4064 4065 4066 4067 4068 4069 4070 |
# File 'zlib.c', line 4064 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.
4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 |
# File 'zlib.c', line 4387 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.
3338 3339 3340 3341 3342 |
# File 'zlib.c', line 3338 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.
3349 3350 3351 3352 3353 3354 3355 |
# File 'zlib.c', line 3349 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.
3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 |
# File 'zlib.c', line 3560 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.
4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 |
# File 'zlib.c', line 4010 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.
4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 |
# File 'zlib.c', line 4111 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.
4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 |
# File 'zlib.c', line 4077 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.
4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 |
# File 'zlib.c', line 4403 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.
4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 |
# File 'zlib.c', line 4437 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.
4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 |
# File 'zlib.c', line 4041 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.
3983 3984 3985 3986 3987 3988 3989 |
# File 'zlib.c', line 3983 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.
3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 |
# File 'zlib.c', line 3560 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.
4185 4186 4187 4188 4189 4190 4191 |
# File 'zlib.c', line 4185 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.
4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 |
# File 'zlib.c', line 4163 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.
3997 3998 3999 4000 4001 4002 4003 |
# File 'zlib.c', line 3997 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); } |