bzip2-ruby 0.2.6 → 0.2.7
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +8 -0
- data/.yardopts +1 -0
- data/CHANGELOG.rdoc +70 -1
- data/Gemfile +3 -0
- data/Gemfile.lock +26 -0
- data/README.rdoc +44 -3
- data/Rakefile +2 -19
- data/bzip2-ruby.gemspec +14 -48
- data/ext/bzip2.c +1012 -823
- data/ext/extconf.rb +4 -1
- data/lib/bzip2-ruby.rb +1 -0
- data/lib/bzip2.rb +10 -2
- data/lib/bzip2/internals.rb +13 -0
- data/lib/bzip2/reader.rb +27 -0
- data/lib/bzip2/version.rb +3 -0
- data/lib/bzip2/writer.rb +63 -0
- data/spec/reader_spec.rb +118 -214
- data/spec/spec_helper.rb +9 -1
- data/spec/writer_spec.rb +64 -74
- metadata +50 -17
- data/VERSION.yml +0 -4
- data/tasks/extconf.rake +0 -13
- data/tasks/extconf/bz2.rake +0 -43
data/ext/extconf.rb
CHANGED
@@ -3,6 +3,9 @@ require 'mkmf'
|
|
3
3
|
dir_config('bz2')
|
4
4
|
have_header('bzlib.h')
|
5
5
|
|
6
|
+
$CFLAGS << ' -Wall -funroll-loops '
|
7
|
+
# $CFLAGS << ' -O0 -ggdb -Wextra'
|
8
|
+
|
6
9
|
if have_library("bz2", "BZ2_bzWriteOpen")
|
7
10
|
if enable_config("shared", true)
|
8
11
|
$static = nil
|
@@ -12,7 +15,7 @@ if have_library("bz2", "BZ2_bzWriteOpen")
|
|
12
15
|
$CFLAGS << ' -DRUBY_19_COMPATIBILITY'
|
13
16
|
end
|
14
17
|
|
15
|
-
create_makefile(
|
18
|
+
create_makefile('bzip2_ext')
|
16
19
|
else
|
17
20
|
puts "libbz2 not found, maybe try manually specifying --with-bz2-dir to find it?"
|
18
21
|
end
|
data/lib/bzip2-ruby.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'bzip2'
|
data/lib/bzip2.rb
CHANGED
@@ -1,5 +1,13 @@
|
|
1
1
|
require 'bzip2_ext'
|
2
|
+
require 'bzip2/version'
|
2
3
|
|
4
|
+
# This is the base module for the +bzip2-ruby+ gem. Beneath it are the classes
|
5
|
+
# for writing and reading data from bzip2 compressed and uncompressed streams.
|
6
|
+
#
|
7
|
+
# For example usage, see the Bzip2::Reader or Bzip2::Writer or the
|
8
|
+
# {README}[link:docs/file/README.rdoc]
|
9
|
+
#
|
10
|
+
# @see Bzip2::Writer
|
11
|
+
# @see Bzip2::Reader
|
3
12
|
module Bzip2
|
4
|
-
|
5
|
-
end
|
13
|
+
end
|
data/lib/bzip2/reader.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# This file is mostly here for documentation purposes, do not require this
|
2
|
+
|
3
|
+
#
|
4
|
+
module Bzip2
|
5
|
+
# Bzip2::Reader is meant to read streams of bz2 compressed bytes. It behaves
|
6
|
+
# like an IO object with many similar methods. It also includes the Enumerable
|
7
|
+
# module and each element is a 'line' in the stream.
|
8
|
+
#
|
9
|
+
# It can both decompress files:
|
10
|
+
#
|
11
|
+
# reader = Bzip2::Reader.open('file')
|
12
|
+
# puts reader.read
|
13
|
+
#
|
14
|
+
# reader = Bzip2::Reader.new File.open('file')
|
15
|
+
# put reader.gets
|
16
|
+
#
|
17
|
+
# And it may just decompress raw strings
|
18
|
+
#
|
19
|
+
# reader = Bzip2::Reader.new compressed_string
|
20
|
+
# reader = Bzip2::Reader.new Bzip2.compress('compress-me')
|
21
|
+
class Reader
|
22
|
+
alias :each_line :each
|
23
|
+
alias :closed :closed?
|
24
|
+
alias :eoz :eoz?
|
25
|
+
alias :eof :eof?
|
26
|
+
end
|
27
|
+
end
|
data/lib/bzip2/writer.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
# This file is mostly here for documentation purposes, do not require this
|
2
|
+
|
3
|
+
#
|
4
|
+
module Bzip2
|
5
|
+
# A Bzip2::Writer represents a stream which compresses data written to it.
|
6
|
+
# It can be constructed with another IO object (a File) which data can be
|
7
|
+
# written to. Otherwise, data is all stored internally as a string and can
|
8
|
+
# be retrieved via the Bzip2::Writer#flush method
|
9
|
+
#
|
10
|
+
# It can both write to files:
|
11
|
+
#
|
12
|
+
# writer = Bzip2::Writer.open('file')
|
13
|
+
# writer << data
|
14
|
+
# writer.close
|
15
|
+
#
|
16
|
+
# Bzip2::Writer.open('file'){ |f| f << data }
|
17
|
+
#
|
18
|
+
# writer = Bzip2::Writer.new File.open('file')
|
19
|
+
#
|
20
|
+
# And output data as a string
|
21
|
+
#
|
22
|
+
# writer = Bzip2::Writer.new
|
23
|
+
# writer << data
|
24
|
+
# writer.flush # => data compressed via bz2
|
25
|
+
#
|
26
|
+
# @see Bzip2::Writer#initialize The initialize method for examples
|
27
|
+
class Writer
|
28
|
+
|
29
|
+
alias :finish :flush
|
30
|
+
|
31
|
+
# Append some data to this buffer, returning the buffer so this method can
|
32
|
+
# be chained
|
33
|
+
#
|
34
|
+
# writer = Bzip2::Writer.new
|
35
|
+
# writer << 'asdf' << 1 << obj << 'a'
|
36
|
+
# writer.flush
|
37
|
+
#
|
38
|
+
# @param [#to_s] data anything responding to #to_s
|
39
|
+
# @see IO#<<
|
40
|
+
def << data
|
41
|
+
end
|
42
|
+
|
43
|
+
# Adds a number of strings to this buffer. A newline is also inserted into
|
44
|
+
# the buffer after each object
|
45
|
+
# @see IO#puts
|
46
|
+
def puts *objs
|
47
|
+
end
|
48
|
+
|
49
|
+
# Similar to Bzip2::Writer#puts except a newline is not appended after each
|
50
|
+
# object appended to this buffer
|
51
|
+
#
|
52
|
+
# @see IO#print
|
53
|
+
def print *objs
|
54
|
+
end
|
55
|
+
|
56
|
+
# Prints data to this buffer with the specified format.
|
57
|
+
#
|
58
|
+
# @see Kernel#sprintf
|
59
|
+
def printf format, *ojbs
|
60
|
+
end
|
61
|
+
|
62
|
+
end
|
63
|
+
end
|
data/spec/reader_spec.rb
CHANGED
@@ -1,9 +1,8 @@
|
|
1
1
|
# encoding: UTF-8
|
2
|
-
require
|
2
|
+
require 'spec_helper'
|
3
3
|
|
4
|
-
describe
|
5
|
-
before(:
|
6
|
-
@sample = "08: This is a line\n"
|
4
|
+
describe Bzip2::Writer do
|
5
|
+
before(:each) do
|
7
6
|
@file = "_10lines_"
|
8
7
|
@data = [
|
9
8
|
"00: This is a line\n",
|
@@ -15,343 +14,248 @@ describe "Bzip2::Writer" do
|
|
15
14
|
"06: This is a line\n",
|
16
15
|
"07: This is a line\n",
|
17
16
|
"08: This is a line\n",
|
18
|
-
"09: This is a line\n"
|
17
|
+
"09: This is a line\n"
|
19
18
|
]
|
20
19
|
|
21
20
|
open("|bzip2 > #{@file}", "w") do |f|
|
22
21
|
@data.each { |l| f.puts l }
|
23
22
|
end
|
24
23
|
end
|
25
|
-
|
26
|
-
after(:
|
27
|
-
File.
|
24
|
+
|
25
|
+
after(:each) do
|
26
|
+
File.delete(@file) if File.exists?(@file)
|
28
27
|
end
|
29
28
|
|
30
|
-
it "
|
31
|
-
|
32
|
-
Bzip2::Reader.foreach(@file)
|
33
|
-
|
34
|
-
count.should == num
|
35
|
-
count += 1
|
36
|
-
end
|
37
|
-
@data.size.should == count
|
29
|
+
it "iterate over each line of the file via the foreach method" do
|
30
|
+
lines = []
|
31
|
+
Bzip2::Reader.foreach(@file){ |line| lines << line }
|
32
|
+
lines.should == @data
|
38
33
|
|
39
|
-
|
34
|
+
lines.clear
|
40
35
|
Bzip2::Reader.foreach(@file, nil) do |file|
|
41
|
-
file.split(/\n/).each
|
42
|
-
num = line[0..1].to_i
|
43
|
-
count.should == num
|
44
|
-
count += 1
|
45
|
-
end
|
36
|
+
file.split(/\n/).each{ |line| lines << line + "\n" }
|
46
37
|
end
|
47
|
-
|
38
|
+
lines.should == @data
|
48
39
|
|
49
40
|
count = 0
|
50
41
|
Bzip2::Reader.foreach(@file, ' ') do |thing|
|
51
42
|
count += 1
|
52
43
|
end
|
53
|
-
|
44
|
+
count.should == 41
|
54
45
|
end
|
55
|
-
|
56
|
-
it "
|
46
|
+
|
47
|
+
it "returns an array of the lines read via #readlines" do
|
57
48
|
lines = Bzip2::Reader.readlines(@file)
|
58
|
-
|
49
|
+
lines.should == @data
|
59
50
|
|
60
51
|
lines = Bzip2::Reader.readlines(@file, nil)
|
61
|
-
|
62
|
-
(@sample.length * @data.size).should == lines[0].size
|
52
|
+
lines.should == [@data.join]
|
63
53
|
end
|
64
54
|
|
65
|
-
it "
|
55
|
+
it "track when the stream has been closed" do
|
66
56
|
f = Bzip2::Reader.open(@file)
|
67
|
-
f.
|
57
|
+
f.should_not be_closed
|
68
58
|
f.close
|
69
|
-
f.
|
59
|
+
f.should be_closed
|
70
60
|
end
|
71
61
|
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
count += 1
|
62
|
+
shared_examples_for 'a line iterator' do |method|
|
63
|
+
it "iterates over the lines when using #each" do
|
64
|
+
Bzip2::Reader.open(@file) do |file|
|
65
|
+
list = []
|
66
|
+
file.send(method){ |l| list << l }
|
67
|
+
list.should == @data
|
79
68
|
end
|
80
|
-
@data.size.should == count
|
81
|
-
end
|
82
69
|
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
contents.split(/\n/).each do |line|
|
87
|
-
num = line[0..1].to_i
|
88
|
-
count.should == num
|
89
|
-
count += 1
|
70
|
+
Bzip2::Reader.open(@file) do |file|
|
71
|
+
file.send(method, nil) do |contents|
|
72
|
+
contents.should == @data.join
|
90
73
|
end
|
91
74
|
end
|
92
|
-
end
|
93
|
-
@data.size.should == count
|
94
75
|
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
76
|
+
count = 0
|
77
|
+
Bzip2::Reader.open(@file) do |file|
|
78
|
+
file.send(method, ' ') do |thing|
|
79
|
+
count += 1
|
80
|
+
end
|
99
81
|
end
|
82
|
+
41.should == count
|
100
83
|
end
|
101
|
-
41.should == count
|
102
84
|
end
|
103
85
|
|
104
|
-
|
105
|
-
|
106
|
-
data = @data.join
|
86
|
+
it_should_behave_like 'a line iterator', :each
|
87
|
+
it_should_behave_like 'a line iterator', :each_line
|
107
88
|
|
108
|
-
|
109
|
-
|
110
|
-
data.getbyte(count).should == b
|
111
|
-
count += 1
|
112
|
-
end
|
113
|
-
end
|
114
|
-
(@sample.length * @data.size).should == count
|
115
|
-
end
|
89
|
+
it "iterates over the decompressed bytes via #each_byte" do
|
90
|
+
bytes = @data.join.bytes.to_a
|
116
91
|
|
117
|
-
it "should test_f_each_line" do
|
118
|
-
count = 0
|
119
92
|
Bzip2::Reader.open(@file) do |file|
|
120
|
-
file.
|
121
|
-
|
122
|
-
count.should == num
|
123
|
-
count += 1
|
124
|
-
end
|
125
|
-
@data.size.should == count
|
126
|
-
end
|
127
|
-
|
128
|
-
count = 0
|
129
|
-
Bzip2::Reader.open(@file) do |file|
|
130
|
-
file.each_line(nil) do |contents|
|
131
|
-
contents.split(/\n/).each do |line|
|
132
|
-
num = line[0..1].to_i
|
133
|
-
count.should == num
|
134
|
-
count += 1
|
135
|
-
end
|
93
|
+
file.each_byte do |b|
|
94
|
+
b.should == bytes.shift
|
136
95
|
end
|
137
96
|
end
|
138
|
-
@data.size.should == count
|
139
97
|
|
140
|
-
|
141
|
-
Bzip2::Reader.open(@file) do |file|
|
142
|
-
file.each_line(' ') do |thing|
|
143
|
-
count += 1
|
144
|
-
end
|
145
|
-
end
|
146
|
-
41.should == count
|
98
|
+
bytes.size.should == 0
|
147
99
|
end
|
148
100
|
|
149
|
-
it "
|
101
|
+
it "keeps track of when eof has been reached" do
|
150
102
|
Bzip2::Reader.open(@file) do |file|
|
151
103
|
@data.size.times do
|
152
|
-
|
153
|
-
(!file.eof?).should be_true
|
104
|
+
file.should_not be_eof
|
154
105
|
file.gets
|
155
106
|
end
|
156
|
-
|
157
|
-
file.
|
107
|
+
|
108
|
+
file.should be_eof
|
158
109
|
end
|
159
110
|
end
|
160
111
|
|
161
|
-
it "
|
162
|
-
|
163
|
-
data = @data.join
|
112
|
+
it "gets only one byte at a time via getc and doesn't raise an exception" do
|
113
|
+
bytes = @data.join.bytes.to_a
|
164
114
|
|
165
115
|
Bzip2::Reader.open(@file) do |file|
|
166
|
-
while
|
167
|
-
|
168
|
-
count += 1
|
116
|
+
while ch = file.getc
|
117
|
+
ch.should == bytes.shift
|
169
118
|
end
|
119
|
+
|
170
120
|
file.getc.should be_nil
|
171
121
|
end
|
172
|
-
|
122
|
+
|
123
|
+
bytes.size.should == 0
|
173
124
|
end
|
174
125
|
|
175
|
-
it "
|
176
|
-
count = 0
|
126
|
+
it "reads an entire line via gets" do
|
177
127
|
Bzip2::Reader.open(@file) do |file|
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
count += 1
|
128
|
+
lines = []
|
129
|
+
while line = file.gets
|
130
|
+
lines << line
|
182
131
|
end
|
132
|
+
lines.should == @data
|
133
|
+
|
183
134
|
file.gets.should be_nil
|
184
|
-
@data.size.should == count
|
185
135
|
end
|
186
136
|
|
187
|
-
count = 0
|
188
137
|
Bzip2::Reader.open(@file) do |file|
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
count.should == num
|
193
|
-
count += 1
|
138
|
+
lines = []
|
139
|
+
while line = file.gets("line\n")
|
140
|
+
lines << line
|
194
141
|
end
|
142
|
+
lines.should == @data
|
143
|
+
|
195
144
|
file.gets.should be_nil
|
196
|
-
@data.size.should == count
|
197
145
|
end
|
198
146
|
|
199
|
-
|
147
|
+
lines = ''
|
200
148
|
Bzip2::Reader.open(@file) do |file|
|
201
|
-
while
|
202
|
-
|
203
|
-
num = line[0..1].to_i
|
204
|
-
count.should == num
|
205
|
-
count += 1
|
206
|
-
end
|
149
|
+
while contents = file.gets(nil)
|
150
|
+
lines << contents
|
207
151
|
end
|
208
152
|
end
|
209
|
-
|
153
|
+
lines.should == @data.join
|
210
154
|
|
211
155
|
count = 0
|
212
156
|
Bzip2::Reader.open(@file) do |file|
|
213
|
-
|
214
|
-
count += 1
|
215
|
-
end
|
157
|
+
count += 1 while file.gets(' ')
|
216
158
|
end
|
217
159
|
41.should == count
|
218
160
|
end
|
219
161
|
|
220
|
-
it "
|
162
|
+
it "reads the entire file or a specified length when using #read" do
|
221
163
|
Bzip2::Reader.open(@file) do |file|
|
222
|
-
|
223
|
-
(@sample.length * @data.size).should == content.length
|
224
|
-
count = 0
|
225
|
-
content.split(/\n/).each do |line|
|
226
|
-
num = line[0..1].to_i
|
227
|
-
count.should == num
|
228
|
-
count += 1
|
229
|
-
end
|
164
|
+
file.read.should == @data.join
|
230
165
|
end
|
231
166
|
|
232
167
|
Bzip2::Reader.open(@file) do |file|
|
233
|
-
"00: This is "
|
234
|
-
"a line\n01: T"
|
168
|
+
file.read(12).should == "00: This is "
|
169
|
+
file.read(12).should == "a line\n01: T"
|
235
170
|
end
|
236
171
|
end
|
237
172
|
|
238
|
-
it "
|
173
|
+
it "reads one character and returns the byte value of the character read" do
|
239
174
|
count = 0
|
240
175
|
data = @data.join
|
241
176
|
Bzip2::Reader.open(@file) do |file|
|
242
|
-
|
243
|
-
|
244
|
-
data.getbyte(count).should == ch
|
245
|
-
count += 1
|
177
|
+
@data.join.bytes do |byte|
|
178
|
+
file.readchar.should == byte
|
246
179
|
end
|
180
|
+
|
247
181
|
lambda { file.readchar }.should raise_error(Bzip2::EOZError)
|
248
182
|
end
|
249
183
|
end
|
250
184
|
|
251
|
-
it "
|
185
|
+
it "reads one line at a time and raises and exception when no more" do
|
252
186
|
count = 0
|
253
187
|
Bzip2::Reader.open(@file) do |file|
|
188
|
+
lines = []
|
254
189
|
@data.size.times do |count|
|
255
|
-
|
256
|
-
num = line[0..1].to_i
|
257
|
-
count.should == num
|
258
|
-
count += 1
|
190
|
+
lines << file.readline
|
259
191
|
end
|
192
|
+
|
193
|
+
lines.should == @data
|
260
194
|
lambda { file.readline }.should raise_error(Bzip2::EOZError)
|
261
195
|
end
|
262
196
|
|
263
|
-
count = 0
|
264
197
|
Bzip2::Reader.open(@file) do |file|
|
265
|
-
|
266
|
-
|
267
|
-
num = line[0..1].to_i
|
268
|
-
count.should == num
|
269
|
-
count += 1
|
270
|
-
end
|
198
|
+
file.readline(nil).should == @data.join
|
199
|
+
|
271
200
|
lambda { file.readline }.should raise_error(Bzip2::EOZError)
|
272
201
|
end
|
273
|
-
@data.size.should == count
|
274
202
|
|
275
|
-
count = 0
|
276
203
|
Bzip2::Reader.open(@file) do |file|
|
277
|
-
41.times
|
278
|
-
thing = file.readline(' ')
|
279
|
-
count += 1
|
280
|
-
end
|
204
|
+
41.times { |count| file.readline(' ') }
|
281
205
|
lambda { file.readline }.should raise_error(Bzip2::EOZError)
|
282
206
|
end
|
283
207
|
end
|
284
208
|
|
285
|
-
it "
|
209
|
+
it "returns an array of lines in the file" do
|
286
210
|
Bzip2::Reader.open(@file) do |file|
|
287
|
-
|
288
|
-
@data.size.should == lines.size
|
211
|
+
file.readlines.should == @data
|
289
212
|
end
|
290
213
|
|
291
214
|
Bzip2::Reader.open(@file) do |file|
|
292
|
-
|
293
|
-
1.should == lines.size
|
294
|
-
(@sample.length * @data.size).should == lines[0].size
|
215
|
+
file.readlines(nil).should == [@data.join]
|
295
216
|
end
|
296
217
|
end
|
297
218
|
|
298
|
-
|
299
|
-
# Bzip2::Reader.open(@file) do |file|
|
300
|
-
# ?0.getbyte(0).should == file.getc
|
301
|
-
# ?0.getbyte(0).should == file.getc
|
302
|
-
# ?:.getbyte(0).should == file.getc
|
303
|
-
# ?\s.getbyte(0).should == file.getc
|
304
|
-
# file.ungetc(?:.to_i).should be_nil
|
305
|
-
# ?:.getbyte(0).should == file.getc
|
306
|
-
# 1 while file.getc
|
307
|
-
# file.ungetc(?A).should be_nil
|
308
|
-
# ?A.should == file.getc
|
309
|
-
# end
|
310
|
-
# end
|
311
|
-
|
312
|
-
it "should test_f_ungets" do
|
313
|
-
count = 0
|
219
|
+
it "rewinds the stream when #ungetc is called and returns that byte next" do
|
314
220
|
Bzip2::Reader.open(@file) do |file|
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
221
|
+
'0'.bytes.first.should == file.getc
|
222
|
+
'0'.bytes.first.should == file.getc
|
223
|
+
':'.bytes.first.should == file.getc
|
224
|
+
' '.bytes.first.should == file.getc
|
225
|
+
|
226
|
+
file.ungetc(':'.bytes.first).should be_nil
|
227
|
+
':'.bytes.first.should == file.getc
|
228
|
+
|
229
|
+
file.read
|
230
|
+
|
231
|
+
file.ungetc('A'.bytes.first).should be_nil
|
232
|
+
'A'.bytes.first.should == file.getc
|
320
233
|
end
|
321
234
|
end
|
322
235
|
|
323
|
-
it "
|
324
|
-
|
325
|
-
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
num = line[0..1].to_i
|
330
|
-
count.should == num
|
331
|
-
count += 1
|
236
|
+
it "rewinds the stream when #ungets is called" do
|
237
|
+
Bzip2::Reader.open(@file) do |file|
|
238
|
+
@data[0].should == file.gets
|
239
|
+
1.should == file.lineno
|
240
|
+
file.ungets(@data[0]).should be_nil
|
241
|
+
@data[0].should == file.gets
|
332
242
|
end
|
333
|
-
|
334
|
-
file.close
|
243
|
+
end
|
335
244
|
|
336
|
-
|
245
|
+
it "reads entire lines via readline and throws an exception when there is" do
|
246
|
+
string = File.read(@file)
|
337
247
|
file = Bzip2::Reader.new(string)
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
count.should == num
|
342
|
-
count += 1
|
248
|
+
lines = []
|
249
|
+
@data.size.times do |count|
|
250
|
+
lines << file.readline
|
343
251
|
end
|
252
|
+
lines.should == @data
|
344
253
|
lambda { file.readline }.should raise_error(Bzip2::EOZError)
|
345
|
-
@data.size.should == count
|
346
254
|
file.close
|
347
255
|
|
348
|
-
count = 0
|
349
256
|
file = Bzip2::Reader.new(string)
|
350
|
-
|
351
|
-
thing = file.readline(' ')
|
352
|
-
count += 1
|
353
|
-
end
|
257
|
+
file.readline(nil).should == @data.join
|
354
258
|
lambda { file.readline }.should raise_error(Bzip2::EOZError)
|
355
259
|
file.close
|
356
260
|
end
|
357
|
-
end
|
261
|
+
end
|