factbook 1.1.1 → 2.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/{HISTORY.md → CHANGELOG.md} +3 -3
- data/Manifest.txt +1 -58
- data/README.md +50 -575
- data/Rakefile +29 -33
- data/lib/factbook.rb +8 -75
- metadata +20 -114
- data/data/attributes.yml +0 -337
- data/data/categories.csv +0 -164
- data/data/codes.csv +0 -262
- data/data/codesxref.csv +0 -280
- data/data/comparisons.csv +0 -75
- data/lib/factbook/almanac.rb +0 -72
- data/lib/factbook/attributes.rb +0 -74
- data/lib/factbook/builder.rb +0 -214
- data/lib/factbook/builder_item.rb +0 -92
- data/lib/factbook/builder_json.rb +0 -79
- data/lib/factbook/codes.rb +0 -119
- data/lib/factbook/comparisons.rb +0 -50
- data/lib/factbook/counter.rb +0 -48
- data/lib/factbook/db/importer.rb +0 -92
- data/lib/factbook/db/models.rb +0 -11
- data/lib/factbook/db/schema.rb +0 -36
- data/lib/factbook/normalize.rb +0 -43
- data/lib/factbook/page.rb +0 -185
- data/lib/factbook/page_info.rb +0 -12
- data/lib/factbook/reader_json.rb +0 -51
- data/lib/factbook/sanitizer.rb +0 -207
- data/lib/factbook/sect.rb +0 -29
- data/lib/factbook/subsect.rb +0 -18
- data/lib/factbook/table.rb +0 -52
- data/lib/factbook/utils.rb +0 -85
- data/lib/factbook/utils_info.rb +0 -102
- data/lib/factbook/version.rb +0 -22
- data/script/almanac.rb +0 -48
- data/script/attributes.rb +0 -34
- data/script/build.rb +0 -28
- data/script/counter.rb +0 -145
- data/script/json.rb +0 -18
- data/script/testbr.rb +0 -33
- data/script/testcodes.rb +0 -11
- data/test/data/au.html +0 -579
- data/test/data/au.yml +0 -8
- data/test/data/be.html +0 -596
- data/test/data/be.yml +0 -8
- data/test/data/json/au.json +0 -892
- data/test/data/src/au.html +0 -2006
- data/test/data/src/be.html +0 -2011
- data/test/helper.rb +0 -11
- data/test/test_attribs.rb +0 -82
- data/test/test_attribs_def.rb +0 -20
- data/test/test_builder.rb +0 -35
- data/test/test_codes.rb +0 -76
- data/test/test_comparisons.rb +0 -19
- data/test/test_convert.rb +0 -30
- data/test/test_counter.rb +0 -31
- data/test/test_fields.rb +0 -52
- data/test/test_importer.rb +0 -55
- data/test/test_item_builder.rb +0 -99
- data/test/test_json.rb +0 -44
- data/test/test_json_builder.rb +0 -25
- data/test/test_normalize.rb +0 -23
- data/test/test_page.rb +0 -38
- data/test/test_sanitizer.rb +0 -35
data/test/test_json.rb
DELETED
@@ -1,44 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_json.rb
|
6
|
-
|
7
|
-
|
8
|
-
require 'helper'
|
9
|
-
|
10
|
-
|
11
|
-
class TestJson < MiniTest::Test
|
12
|
-
|
13
|
-
|
14
|
-
def test_json
|
15
|
-
Dir.mkdir( 'tmp' ) unless Dir.exists?( 'tmp' )
|
16
|
-
|
17
|
-
codes = [ 'au',
|
18
|
-
'be',
|
19
|
-
#'br',
|
20
|
-
#'mx',
|
21
|
-
#'ls',
|
22
|
-
#'vt',
|
23
|
-
#'ee',
|
24
|
-
#'xx'
|
25
|
-
]
|
26
|
-
|
27
|
-
codes.each do |code|
|
28
|
-
|
29
|
-
html = File.read( "#{Factbook.root}/test/data/src/#{code}.html" )
|
30
|
-
page = Factbook::Page.new( code, html: html )
|
31
|
-
|
32
|
-
h = page.data
|
33
|
-
pp h
|
34
|
-
|
35
|
-
### save to json
|
36
|
-
puts "saving a copy to #{code}.json for debugging"
|
37
|
-
File.open( "tmp/#{code}.json", 'w' ) do |f|
|
38
|
-
f.write JSON.pretty_generate( h )
|
39
|
-
## f.write page.to_json
|
40
|
-
end
|
41
|
-
end
|
42
|
-
end
|
43
|
-
|
44
|
-
end # class TestJson
|
data/test/test_json_builder.rb
DELETED
@@ -1,25 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_json_builder.rb
|
6
|
-
|
7
|
-
|
8
|
-
require 'helper'
|
9
|
-
|
10
|
-
|
11
|
-
class TestJsonBuilder < MiniTest::Test
|
12
|
-
|
13
|
-
def test_read
|
14
|
-
code = 'au'
|
15
|
-
b = Factbook::JsonBuilder.from_file( "#{Factbook.root}/test/data/json/#{code}.json" )
|
16
|
-
|
17
|
-
assert_equal 10, b.sects.size
|
18
|
-
assert_equal 1, b.sects[0].subsects.size ## e.g. Introduction/Background
|
19
|
-
assert_equal 'Central Europe, north of Italy and Slovenia', b.json['Geography']['Location']['text']
|
20
|
-
|
21
|
-
assert true ## assume everthing ok
|
22
|
-
end
|
23
|
-
|
24
|
-
end # class TestJsonBuilder
|
25
|
-
|
data/test/test_normalize.rb
DELETED
@@ -1,23 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_normalize.rb
|
6
|
-
|
7
|
-
|
8
|
-
require 'helper'
|
9
|
-
|
10
|
-
|
11
|
-
class TestNormalizer < MiniTest::Test
|
12
|
-
|
13
|
-
include Factbook::NormalizeHelper
|
14
|
-
|
15
|
-
def test_normalize
|
16
|
-
assert_equal 'border countries', normalize_category( 'border countries:' )
|
17
|
-
assert_equal 'border countries', normalize_category( 'border countries: ' )
|
18
|
-
assert_equal 'border countries', normalize_category( 'border countries (8):' )
|
19
|
-
assert_equal 'border countries', normalize_category( 'border countries (10): ' )
|
20
|
-
end
|
21
|
-
|
22
|
-
end # class TestNormalizer
|
23
|
-
|
data/test/test_page.rb
DELETED
@@ -1,38 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_page.rb
|
6
|
-
|
7
|
-
|
8
|
-
require 'helper'
|
9
|
-
|
10
|
-
|
11
|
-
class TestPage < MiniTest::Test
|
12
|
-
|
13
|
-
|
14
|
-
def test_sects
|
15
|
-
pages = [
|
16
|
-
[ 'au', 10 ],
|
17
|
-
[ 'be', 10 ],
|
18
|
-
# [ 'br', 10 ],
|
19
|
-
# [ 'ee', 10 ],
|
20
|
-
# [ 'mx', 10 ],
|
21
|
-
# [ 'xx', 10 ],
|
22
|
-
# [ 'ls', 9 ],
|
23
|
-
# [ 'vt', 8 ],
|
24
|
-
]
|
25
|
-
|
26
|
-
pages.each do |rec|
|
27
|
-
code = rec[0]
|
28
|
-
sects_size = rec[1]
|
29
|
-
|
30
|
-
html = File.read( "#{Factbook.root}/test/data/src/#{code}.html" )
|
31
|
-
page = Factbook::Page.new( code, html: html )
|
32
|
-
|
33
|
-
assert_equal sects_size, page.sects.size
|
34
|
-
end
|
35
|
-
end
|
36
|
-
|
37
|
-
|
38
|
-
end # class TestPage
|
data/test/test_sanitizer.rb
DELETED
@@ -1,35 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
|
3
|
-
###
|
4
|
-
# to run use
|
5
|
-
# ruby -I ./lib -I ./test test/test_sanitizer.rb
|
6
|
-
|
7
|
-
|
8
|
-
require 'helper'
|
9
|
-
|
10
|
-
|
11
|
-
class TestSanitizer < MiniTest::Test
|
12
|
-
|
13
|
-
def test_sanitize
|
14
|
-
|
15
|
-
['au','be'].each do |cc|
|
16
|
-
## use/fix: ASCII-8BIT (e.g.keep as is) -???
|
17
|
-
html_ascii = File.read( "#{Factbook.root}/test/data/src/#{cc}.html" ) ## fix/todo: use ASCII8BIT/binary reader ??
|
18
|
-
|
19
|
-
html, info, errors = Factbook::Sanitizer.new.sanitize( html_ascii )
|
20
|
-
|
21
|
-
File.open( "./tmp/#{cc}.profile.html", 'w' ) do |f|
|
22
|
-
f.write "** info:\n"
|
23
|
-
f.write info.inspect + "\n\n"
|
24
|
-
f.write "** errors:\n"
|
25
|
-
f.write errors.inspect + "\n\n"
|
26
|
-
f.write "** html:\n"
|
27
|
-
f.write html
|
28
|
-
end
|
29
|
-
end
|
30
|
-
|
31
|
-
assert true ## assume everthing ok
|
32
|
-
end
|
33
|
-
|
34
|
-
end # class TestSanitizer
|
35
|
-
|