class Zlib::GzipReader
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.
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.
Public Class Methods
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.
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; }
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.
static VALUE rb_gzreader_s_open(int argc, VALUE *argv, VALUE klass) { return gzfile_s_open(argc, argv, klass, "rb"); }
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.
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), Qnil); 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; }
Public Instance Methods
See Zlib::GzipReader
documentation for a description.
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; }
See Zlib::GzipReader
documentation for a description.
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; }
See Zlib::GzipReader
documentation for a description.
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; }
Returns true
or false
whether the stream has reached the end.
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; }
See Zlib::GzipReader
documentation for a description.
static VALUE rb_gzreader_external_encoding(VALUE self) { return rb_enc_from_encoding(get_gzfile(self)->enc); }
See Zlib::GzipReader
documentation for a description.
static VALUE rb_gzreader_getbyte(VALUE obj) { struct gzfile *gz = get_gzfile(obj); VALUE dst; dst = gzfile_read(gz, 1, Qnil); if (!NIL_P(dst)) { dst = INT2FIX((unsigned int)(RSTRING_PTR(dst)[0]) & 0xff); } return dst; }
See Zlib::GzipReader
documentation for a description.
static VALUE rb_gzreader_getc(VALUE obj) { struct gzfile *gz = get_gzfile(obj); return gzfile_getc(gz); }
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.
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; }
The line number of the last row read from this file.
static VALUE rb_gzfile_lineno(VALUE obj) { return INT2NUM(get_gzfile(obj)->lineno); }
Specify line number of the last row read from this file.
static VALUE rb_gzfile_set_lineno(VALUE obj, VALUE lineno) { struct gzfile *gz = get_gzfile(obj); gz->lineno = NUM2INT(lineno); return lineno; }
Total number of output bytes output so far.
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)); } }
See Zlib::GzipReader
documentation for a description.
static VALUE rb_gzreader_read(int argc, VALUE *argv, VALUE obj) { struct gzfile *gz = get_gzfile(obj); VALUE vlen, outbuf; long len; rb_scan_args(argc, argv, "02", &vlen, &outbuf); if (NIL_P(vlen)) { return gzfile_read_all(gz, outbuf); } len = NUM2INT(vlen); if (len < 0) { rb_raise(rb_eArgError, "negative length %ld given", len); } return gzfile_read(gz, len, outbuf); }
See Zlib::GzipReader
documentation for a description.
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; }
See Zlib::GzipReader
documentation for a description.
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; }
See Zlib::GzipReader
documentation for a description.
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; }
See Zlib::GzipReader
documentation for a description.
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; }
Reads at most maxlen bytes from the gziped stream but it blocks only if gzipreader has no data immediately available. If the optional outbuf argument is present, it must reference a String, which will receive the data. It raises EOFError
on end of file.
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); }
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.
static VALUE rb_gzreader_rewind(VALUE obj) { struct gzfile *gz = get_gzfile(obj); gzfile_reader_rewind(gz); return INT2FIX(0); }
See Zlib::GzipReader
documentation for a description.
static VALUE rb_gzreader_ungetbyte(VALUE obj, VALUE ch) { struct gzfile *gz = get_gzfile(obj); gzfile_ungetbyte(gz, NUM2CHR(ch)); return Qnil; }
See Zlib::GzipReader
documentation for a description.
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; }
Returns the rest of the data which had read for parsing gzip format, or nil
if the whole gzip file is not parsed yet.
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); }