treat 0.1.4 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +4 -4
- data/TODO +21 -54
- data/lib/economist/half_cocked_basel.txt +16 -0
- data/lib/economist/hose_and_dry.doc +0 -0
- data/lib/economist/hungarys_troubles.abw +70 -0
- data/lib/economist/republican_nomination.pdf +0 -0
- data/lib/economist/saving_the_euro.odt +0 -0
- data/lib/economist/to_infinity_and_beyond.txt +15 -0
- data/lib/economist/zero_sum.html +91 -0
- data/lib/treat.rb +58 -72
- data/lib/treat/buildable.rb +59 -15
- data/lib/treat/categories.rb +26 -14
- data/lib/treat/category.rb +2 -2
- data/lib/treat/delegatable.rb +65 -48
- data/lib/treat/doable.rb +44 -0
- data/lib/treat/entities.rb +34 -14
- data/lib/treat/entities/collection.rb +2 -0
- data/lib/treat/entities/document.rb +3 -2
- data/lib/treat/entities/entity.rb +105 -90
- data/lib/treat/entities/phrases.rb +17 -0
- data/lib/treat/entities/tokens.rb +28 -13
- data/lib/treat/entities/zones.rb +20 -0
- data/lib/treat/extractors.rb +49 -11
- data/lib/treat/extractors/coreferences/stanford.rb +68 -0
- data/lib/treat/extractors/date/chronic.rb +32 -0
- data/lib/treat/extractors/date/ruby.rb +25 -0
- data/lib/treat/extractors/keywords/tf_idf.rb +26 -0
- data/lib/treat/extractors/keywords/{topics_frequency.rb → topics_tf_idf.rb} +15 -7
- data/lib/treat/{detectors/language/language_detector.rb → extractors/language/language_extractor.rb} +5 -2
- data/lib/treat/extractors/language/what_language.rb +49 -0
- data/lib/treat/extractors/named_entity_tag/stanford.rb +53 -0
- data/lib/treat/extractors/roles/naive.rb +73 -0
- data/lib/treat/extractors/statistics/frequency_in.rb +6 -13
- data/lib/treat/extractors/statistics/{position_in_parent.rb → position_in.rb} +1 -1
- data/lib/treat/extractors/statistics/tf_idf.rb +89 -21
- data/lib/treat/extractors/statistics/transition_matrix.rb +11 -11
- data/lib/treat/extractors/statistics/transition_probability.rb +4 -4
- data/lib/treat/extractors/time/nickel.rb +30 -12
- data/lib/treat/extractors/topic_words/lda.rb +9 -9
- data/lib/treat/extractors/topics/reuters.rb +14 -15
- data/lib/treat/extractors/topics/reuters/region.xml +1 -0
- data/lib/treat/features.rb +7 -0
- data/lib/treat/formatters/readers/abw.rb +6 -1
- data/lib/treat/formatters/readers/autoselect.rb +5 -6
- data/lib/treat/formatters/readers/doc.rb +3 -1
- data/lib/treat/formatters/readers/html.rb +1 -1
- data/lib/treat/formatters/readers/image.rb +43 -0
- data/lib/treat/formatters/readers/odt.rb +1 -2
- data/lib/treat/formatters/readers/pdf.rb +9 -1
- data/lib/treat/formatters/readers/xml.rb +40 -0
- data/lib/treat/formatters/serializers/xml.rb +50 -14
- data/lib/treat/formatters/serializers/yaml.rb +7 -2
- data/lib/treat/formatters/unserializers/xml.rb +33 -7
- data/lib/treat/formatters/visualizers/dot.rb +90 -20
- data/lib/treat/formatters/visualizers/short_value.rb +2 -2
- data/lib/treat/formatters/visualizers/standoff.rb +2 -2
- data/lib/treat/formatters/visualizers/tree.rb +1 -1
- data/lib/treat/formatters/visualizers/txt.rb +13 -4
- data/lib/treat/group.rb +16 -10
- data/lib/treat/helpers/linguistics_loader.rb +18 -0
- data/lib/treat/inflectors.rb +10 -0
- data/lib/treat/inflectors/cardinal_words/linguistics.rb +3 -3
- data/lib/treat/inflectors/conjugations/linguistics.rb +5 -12
- data/lib/treat/inflectors/declensions/english.rb +319 -0
- data/lib/treat/inflectors/declensions/linguistics.rb +12 -11
- data/lib/treat/inflectors/ordinal_words/linguistics.rb +3 -3
- data/lib/treat/install.rb +59 -0
- data/lib/treat/kernel.rb +18 -8
- data/lib/treat/languages.rb +18 -11
- data/lib/treat/languages/arabic.rb +4 -2
- data/lib/treat/languages/chinese.rb +6 -2
- data/lib/treat/languages/dutch.rb +16 -0
- data/lib/treat/languages/english.rb +47 -19
- data/lib/treat/languages/french.rb +8 -5
- data/lib/treat/languages/german.rb +9 -6
- data/lib/treat/languages/greek.rb +16 -0
- data/lib/treat/languages/italian.rb +6 -3
- data/lib/treat/languages/polish.rb +16 -0
- data/lib/treat/languages/portuguese.rb +16 -0
- data/lib/treat/languages/russian.rb +16 -0
- data/lib/treat/languages/spanish.rb +16 -0
- data/lib/treat/languages/swedish.rb +16 -0
- data/lib/treat/languages/tags.rb +377 -0
- data/lib/treat/lexicalizers.rb +34 -23
- data/lib/treat/lexicalizers/category/from_tag.rb +17 -10
- data/lib/treat/lexicalizers/linkages/naive.rb +51 -51
- data/lib/treat/lexicalizers/synsets/wordnet.rb +5 -1
- data/lib/treat/lexicalizers/tag/brill.rb +35 -40
- data/lib/treat/lexicalizers/tag/lingua.rb +19 -14
- data/lib/treat/lexicalizers/tag/stanford.rb +59 -68
- data/lib/treat/lexicalizers/tag/tagger.rb +29 -0
- data/lib/treat/processors.rb +8 -8
- data/lib/treat/processors/chunkers/txt.rb +4 -4
- data/lib/treat/processors/parsers/enju.rb +114 -99
- data/lib/treat/processors/parsers/stanford.rb +109 -41
- data/lib/treat/processors/segmenters/punkt.rb +17 -18
- data/lib/treat/processors/segmenters/punkt/dutch.yaml +9716 -0
- data/lib/treat/processors/segmenters/punkt/english.yaml +10340 -0
- data/lib/treat/processors/segmenters/punkt/french.yaml +43159 -0
- data/lib/treat/processors/segmenters/punkt/german.yaml +9572 -0
- data/lib/treat/processors/segmenters/punkt/greek.yaml +6050 -0
- data/lib/treat/processors/segmenters/punkt/italian.yaml +14748 -0
- data/lib/treat/processors/segmenters/punkt/polish.yaml +9751 -0
- data/lib/treat/processors/segmenters/punkt/portuguese.yaml +13662 -0
- data/lib/treat/processors/segmenters/punkt/russian.yaml +4237 -0
- data/lib/treat/processors/segmenters/punkt/spanish.yaml +24034 -0
- data/lib/treat/processors/segmenters/punkt/swedish.yaml +10001 -0
- data/lib/treat/processors/segmenters/stanford.rb +38 -37
- data/lib/treat/processors/segmenters/tactful.rb +5 -4
- data/lib/treat/processors/tokenizers/macintyre.rb +7 -6
- data/lib/treat/processors/tokenizers/multilingual.rb +2 -3
- data/lib/treat/processors/tokenizers/perl.rb +2 -2
- data/lib/treat/processors/tokenizers/punkt.rb +6 -2
- data/lib/treat/processors/tokenizers/stanford.rb +25 -24
- data/lib/treat/processors/tokenizers/tactful.rb +1 -2
- data/lib/treat/proxies.rb +2 -35
- data/lib/treat/registrable.rb +17 -22
- data/lib/treat/sugar.rb +11 -11
- data/lib/treat/tree.rb +27 -17
- data/lib/treat/viewable.rb +29 -0
- data/lib/treat/visitable.rb +1 -1
- data/test/tc_entity.rb +56 -49
- data/test/tc_extractors.rb +41 -18
- data/test/tc_formatters.rb +7 -8
- data/test/tc_inflectors.rb +19 -24
- data/test/tc_lexicalizers.rb +12 -19
- data/test/tc_processors.rb +26 -12
- data/test/tc_resources.rb +2 -7
- data/test/tc_treat.rb +20 -22
- data/test/tc_tree.rb +4 -4
- data/test/tests.rb +3 -5
- data/test/texts.rb +13 -14
- data/tmp/INFO +1 -0
- metadata +78 -158
- data/bin/INFO +0 -1
- data/examples/benchmark.rb +0 -81
- data/examples/keywords.rb +0 -148
- data/lib/treat/detectors.rb +0 -31
- data/lib/treat/detectors/encoding/r_chardet19.rb +0 -27
- data/lib/treat/detectors/format/file.rb +0 -36
- data/lib/treat/detectors/language/what_language.rb +0 -29
- data/lib/treat/entities/constituents.rb +0 -15
- data/lib/treat/entities/sentence.rb +0 -8
- data/lib/treat/extractors/named_entity/abner.rb +0 -20
- data/lib/treat/extractors/named_entity/stanford.rb +0 -174
- data/lib/treat/extractors/statistics/frequency_of.rb +0 -15
- data/lib/treat/extractors/time/chronic.rb +0 -20
- data/lib/treat/extractors/time/native.rb +0 -18
- data/lib/treat/formatters/readers/gocr.rb +0 -26
- data/lib/treat/formatters/readers/ocropus.rb +0 -31
- data/lib/treat/formatters/visualizers/html.rb +0 -13
- data/lib/treat/formatters/visualizers/inspect.rb +0 -20
- data/lib/treat/inflectors/declensions/en.rb +0 -18
- data/lib/treat/languages/categories.rb +0 -5
- data/lib/treat/languages/english/categories.rb +0 -23
- data/lib/treat/languages/english/tags.rb +0 -352
- data/lib/treat/languages/xinhua.rb +0 -12
- data/lib/treat/lexicalizers/synsets/rita_wn.rb +0 -23
- data/lib/treat/string.rb +0 -5
- data/test/tc_detectors.rb +0 -26
@@ -4,8 +4,10 @@ module Treat
|
|
4
4
|
class Doc
|
5
5
|
def self.read(document, options = {})
|
6
6
|
f = `antiword #{document.file}`
|
7
|
+
f.gsub!("\n\n", '#keep#')
|
8
|
+
f.gsub!("\n", ' ')
|
9
|
+
f.gsub!('#keep#', "\n\n")
|
7
10
|
document << Treat::Entities::Entity.from_string(f)
|
8
|
-
document
|
9
11
|
end
|
10
12
|
end
|
11
13
|
end
|
@@ -7,7 +7,7 @@ module Treat
|
|
7
7
|
# Require Hpricot.
|
8
8
|
silence_warnings { require 'hpricot' }
|
9
9
|
# By default, backup the HTML text while cleaning.
|
10
|
-
DefaultOptions = { clean
|
10
|
+
DefaultOptions = { :clean => true, :backup => false }
|
11
11
|
# Read the HTML document and strip it of its markup.
|
12
12
|
#
|
13
13
|
# Options:
|
@@ -0,0 +1,43 @@
|
|
1
|
+
module Treat
|
2
|
+
module Formatters
|
3
|
+
module Readers
|
4
|
+
# This class is a wrapper for the Google Ocropus
|
5
|
+
# optical character recognition (OCR) engine.
|
6
|
+
#
|
7
|
+
# "OCRopus(tm) is a state-of-the-art document
|
8
|
+
# analysis and OCR system, featuring pluggable
|
9
|
+
# layout analysis, pluggable character recognition,
|
10
|
+
# statistical natural language modeling, and multi-
|
11
|
+
# lingual capabilities."
|
12
|
+
#
|
13
|
+
# Original paper:
|
14
|
+
# Breuel, Thomas M. The Ocropus Open Source OCR System.
|
15
|
+
# DFKI and U. Kaiserslautern, Germany.
|
16
|
+
class Image
|
17
|
+
# Read a file using the Google Ocropus reader.
|
18
|
+
#
|
19
|
+
# Options:
|
20
|
+
# - (Boolean) :silent => whether to silence Ocropus.
|
21
|
+
def self.read(document, options = {})
|
22
|
+
read = lambda do |doc|
|
23
|
+
create_temp_dir do |tmp|
|
24
|
+
`ocropus book2pages #{tmp}/out #{doc.file}`
|
25
|
+
`ocropus pages2lines #{tmp}/out`
|
26
|
+
`ocropus lines2fsts #{tmp}/out`
|
27
|
+
`ocropus buildhtml #{tmp}/out > #{tmp}/output.html`
|
28
|
+
f = document.file
|
29
|
+
doc.remove_all!
|
30
|
+
doc.set :file, "#{tmp}/output.html"
|
31
|
+
doc.read(:html)
|
32
|
+
doc.set :file, f
|
33
|
+
end
|
34
|
+
end
|
35
|
+
options[:silent] ?
|
36
|
+
silence_stdout { read.call(document) } :
|
37
|
+
read.call(document)
|
38
|
+
document
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
@@ -17,7 +17,6 @@ module Treat
|
|
17
17
|
raise "Couldn't unzip dot file #{document.file}!" unless f
|
18
18
|
xml_h = OOXmlHandler.new
|
19
19
|
REXML::Document.parse_stream(f, xml_h)
|
20
|
-
puts xml_h.plain_text
|
21
20
|
document << Treat::Entities::Entity.from_string(xml_h.plain_text)
|
22
21
|
document
|
23
22
|
end
|
@@ -39,7 +38,7 @@ module Treat
|
|
39
38
|
s = s.strip
|
40
39
|
if s.length > 0
|
41
40
|
@plain_text << s
|
42
|
-
@plain_text << "\n"
|
41
|
+
@plain_text << "\n\n"
|
43
42
|
end
|
44
43
|
end
|
45
44
|
end
|
@@ -1,3 +1,4 @@
|
|
1
|
+
# encoding: utf-8
|
1
2
|
module Treat
|
2
3
|
module Formatters
|
3
4
|
module Readers
|
@@ -10,7 +11,14 @@ module Treat
|
|
10
11
|
def self.read(document, options = {})
|
11
12
|
create_temp_file(:txt) do |tmp|
|
12
13
|
`pdftotext #{document.file} #{tmp} `.strip
|
13
|
-
|
14
|
+
f = File.read(tmp)
|
15
|
+
f.gsub!("\t\r ", '')
|
16
|
+
f.gsub!('-‐', '-')
|
17
|
+
f.gsub!("\n\n", '#keep#')
|
18
|
+
f.gsub!("\n", ' ')
|
19
|
+
f.gsub!(" ", ' ')
|
20
|
+
f.gsub!('#keep#', "\n\n")
|
21
|
+
document << Treat::Entities::Entity.from_string(f)
|
14
22
|
end
|
15
23
|
document
|
16
24
|
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
module Treat
|
2
|
+
module Formatters
|
3
|
+
module Readers
|
4
|
+
class XML
|
5
|
+
require 'stanford-core-nlp'
|
6
|
+
require 'cgi'
|
7
|
+
# By default, backup the XML text while cleaning.
|
8
|
+
DefaultOptions = { :clean => true, :backup => false }
|
9
|
+
@@xml_cleaner = nil
|
10
|
+
# Read the XML document and strip it of its markup.
|
11
|
+
# Also splits the text into sentences and tokenizes it?
|
12
|
+
#
|
13
|
+
# Options:
|
14
|
+
#
|
15
|
+
# - (Boolean) :clean => whether to strip XML markup.
|
16
|
+
# - (Boolean) :backup => whether to backup the XML
|
17
|
+
# markup while cleaning.
|
18
|
+
def self.read(document, options = {})
|
19
|
+
options = DefaultOptions.merge(options)
|
20
|
+
document << Treat::Entities::Entity.from_string(File.read(document.file))
|
21
|
+
if options[:clean]
|
22
|
+
@@xml_cleaner ||= StanfordCoreNLP.load(:tokenize, :ssplit, :cleanxml)
|
23
|
+
document.each do |zone|
|
24
|
+
text = StanfordCoreNLP::Text.new(zone.to_s)
|
25
|
+
@@xml_cleaner.annotate(text)
|
26
|
+
sentences = []
|
27
|
+
text.get(:sentences) do |sentence|
|
28
|
+
sentences << Treat::Entities::Sentence.from_string(sentence.to_s)
|
29
|
+
end
|
30
|
+
val = sentences.join(' ')
|
31
|
+
zone.set :xml_value, CGI.escapeHTML(text.to_s) if options[:backup]
|
32
|
+
zone.value = val
|
33
|
+
end
|
34
|
+
end
|
35
|
+
document
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -6,44 +6,80 @@ module Treat
|
|
6
6
|
# Reauire the Nokogiri XML parser.
|
7
7
|
require 'nokogiri'
|
8
8
|
# Serialize an entity tree in XML format.
|
9
|
+
#
|
10
|
+
# Options:
|
11
|
+
# - (String) :file => a file to write to.
|
9
12
|
def self.serialize(entity, options = {})
|
10
|
-
options = {:indent => 0} if options[:indent].nil?
|
13
|
+
options = options.merge({:indent => 0}) if options[:indent].nil?
|
14
|
+
indent = options[:indent]
|
11
15
|
if options[:indent] == 0
|
12
|
-
|
13
|
-
string = "<?xml version=\"1.0\" encoding=\"
|
16
|
+
enc = entity.to_s.encoding.to_s.downcase
|
17
|
+
string = "<?xml version=\"1.0\" encoding=\"#{enc}\" standalone=\"no\" ?>\n<treat>"
|
14
18
|
else
|
15
19
|
string = ''
|
16
20
|
end
|
17
21
|
spaces = ''
|
18
22
|
options[:indent].times { spaces << ' ' }
|
19
|
-
attributes = ''
|
23
|
+
attributes = " id='#{entity.id}' "
|
20
24
|
if !entity.features.nil? && entity.features.size != 0
|
21
|
-
attributes
|
25
|
+
attributes << ' '
|
22
26
|
entity.features.each_pair do |feature, value|
|
23
27
|
if value.is_a? Entities::Entity
|
24
28
|
attributes << "#{feature}='#{value.id}' "
|
25
29
|
else
|
26
|
-
attributes << "#{feature}='#{value}' "
|
30
|
+
attributes << "#{feature}='#{escape(value)}' "
|
27
31
|
end
|
28
32
|
end
|
29
|
-
|
30
|
-
|
33
|
+
attributes << "dependencies='"
|
34
|
+
a = []
|
35
|
+
entity.dependencies.each do |dependency|
|
36
|
+
a << ("{target: #{dependency.target}, type: #{dependency.type}, " +
|
37
|
+
"directed: #{dependency.directed}, " +
|
38
|
+
"direction: #{dependency.direction}}" )
|
31
39
|
end
|
40
|
+
# Structs.
|
41
|
+
attributes << a.join('--') + "'"
|
32
42
|
end
|
33
43
|
tag = entity.class.to_s.split('::')[-1].downcase
|
34
|
-
|
44
|
+
unless entity.is_a?(Treat::Entities::Token)
|
45
|
+
string += "\n"
|
46
|
+
end
|
47
|
+
string += "#{spaces}<#{tag}#{attributes}>"
|
35
48
|
if entity.has_children?
|
36
49
|
options[:indent] += 1
|
37
|
-
entity.children.each do |child|
|
38
|
-
string =
|
50
|
+
entity.children.each do |child|
|
51
|
+
string =
|
52
|
+
string +
|
53
|
+
serialize(child, options)
|
39
54
|
end
|
40
55
|
options[:indent] -= 1
|
41
56
|
else
|
42
|
-
string = string + "
|
57
|
+
string = string + "#{escape(entity.value)}"
|
58
|
+
end
|
59
|
+
unless entity.is_a?(Treat::Entities::Token)
|
60
|
+
string += "\n#{spaces}"
|
43
61
|
end
|
44
|
-
string
|
62
|
+
string += "</#{tag}>\n"
|
63
|
+
if indent == 0
|
64
|
+
string += "\n</treat>"
|
65
|
+
if options[:file]
|
66
|
+
File.open(options[:file], 'w') { |f| f.write(string) }
|
67
|
+
end
|
68
|
+
# puts string
|
69
|
+
end
|
70
|
+
string
|
71
|
+
end
|
72
|
+
|
73
|
+
def self.escape(input)
|
74
|
+
result = input.to_s.dup
|
75
|
+
result.gsub!("&", "&")
|
76
|
+
result.gsub!("<", "<")
|
77
|
+
result.gsub!(">", ">")
|
78
|
+
result.gsub!("'", "'")
|
79
|
+
result.gsub!("\"", """)
|
80
|
+
result
|
45
81
|
end
|
46
82
|
end
|
47
83
|
end
|
48
84
|
end
|
49
|
-
end
|
85
|
+
end
|
@@ -7,9 +7,14 @@ module Treat
|
|
7
7
|
class YAML
|
8
8
|
# Serialize an entity in YAML format.
|
9
9
|
#
|
10
|
-
# Options:
|
10
|
+
# Options:
|
11
|
+
# - (String) :file => a file to write to.
|
11
12
|
def self.serialize(entity, options = {})
|
12
|
-
::Psych.dump(entity)
|
13
|
+
yaml = ::Psych.dump(entity)
|
14
|
+
if options[:file]
|
15
|
+
File.open(options[:file], 'w') { |f| f.write(yaml) }
|
16
|
+
end
|
17
|
+
yaml
|
13
18
|
end
|
14
19
|
end
|
15
20
|
end
|
@@ -11,6 +11,8 @@ module Treat
|
|
11
11
|
def self.unserialize(document, options = {})
|
12
12
|
# Read in the XML file.
|
13
13
|
xml = File.read(document.file)
|
14
|
+
xml.gsub!('<treat>', '')
|
15
|
+
xml.gsub!('</treat>', '')
|
14
16
|
xml_reader = Nokogiri::XML::Reader.from_memory(xml)
|
15
17
|
current_element = nil
|
16
18
|
previous_depth = 0
|
@@ -33,13 +35,33 @@ module Treat
|
|
33
35
|
end
|
34
36
|
|
35
37
|
id = nil; value = ''
|
36
|
-
attributes = {}
|
37
|
-
|
38
|
+
attributes = {}
|
39
|
+
dependencies = []
|
40
|
+
unless xml_reader.attributes.size == 0
|
38
41
|
xml_reader.attributes.each_pair do |k,v|
|
39
42
|
if k == 'id'
|
40
|
-
id = v
|
41
|
-
elsif k == '
|
42
|
-
|
43
|
+
id = v.to_i
|
44
|
+
elsif k == 'dependencies'
|
45
|
+
a = v.split('--')
|
46
|
+
a.each do |b|
|
47
|
+
c = b.split(';')
|
48
|
+
c.each do |dep|
|
49
|
+
vals = []
|
50
|
+
dep.split(',').each do |name_val|
|
51
|
+
name_val = name_val[0..-2] if name_val[-1] == '}'
|
52
|
+
d = name_val.split(':')[1]
|
53
|
+
vals << d.strip if d
|
54
|
+
end
|
55
|
+
|
56
|
+
target, type, directed, direction = *vals
|
57
|
+
dependencies << [
|
58
|
+
target.to_i,
|
59
|
+
type,
|
60
|
+
(directed == 'true' ? true : false),
|
61
|
+
direction.to_i
|
62
|
+
]
|
63
|
+
end
|
64
|
+
end
|
43
65
|
elsif k == 'value'
|
44
66
|
value = v
|
45
67
|
else
|
@@ -60,9 +82,13 @@ module Treat
|
|
60
82
|
end
|
61
83
|
current_element.features = attributes
|
62
84
|
current_element.features = attributes
|
63
|
-
|
85
|
+
dependencies.each do |dependency|
|
86
|
+
target, type, directed, direction = *dependency
|
87
|
+
current_element.link(target, type, directed, direction)
|
88
|
+
end
|
64
89
|
else
|
65
|
-
current_value = xml_reader.value
|
90
|
+
current_value = xml_reader.value ?
|
91
|
+
xml_reader.value.strip : ''
|
66
92
|
if current_value && current_value != ''
|
67
93
|
current_element.value = current_value
|
68
94
|
current_element.register_token(current_element)
|
@@ -2,7 +2,16 @@ module Treat
|
|
2
2
|
module Formatters
|
3
3
|
module Visualizers
|
4
4
|
class Dot
|
5
|
-
|
5
|
+
require 'date'
|
6
|
+
DefaultOptions = {
|
7
|
+
:colors => {},
|
8
|
+
:features => :all,
|
9
|
+
:file => nil,
|
10
|
+
:remove_types => [],
|
11
|
+
:remove_features => [],
|
12
|
+
:colors => nil,
|
13
|
+
:first => true # For internal purposes only.
|
14
|
+
}
|
6
15
|
# Create the top-most graph structure
|
7
16
|
# and delegate the creation of the graph
|
8
17
|
# nodes to to_dot.
|
@@ -11,53 +20,114 @@ module Treat
|
|
11
20
|
string = "graph {"
|
12
21
|
string << self.to_dot(entity, options)
|
13
22
|
string << "\n}"
|
23
|
+
if options[:file]
|
24
|
+
File.open(options[:file], 'w') { |f| f.write(string) }
|
25
|
+
end
|
26
|
+
string
|
14
27
|
end
|
15
28
|
# dot -Tpdf test4.dot > test4.pdf
|
16
29
|
def self.to_dot(entity, options)
|
30
|
+
# Filter out specified types.
|
31
|
+
match_types = lambda do |t1, t2s|
|
32
|
+
f = false
|
33
|
+
t2s.each { |t2| f = true if Treat::Entities.match_types[t1][t2] }
|
34
|
+
f
|
35
|
+
end
|
36
|
+
return '' if match_types.call(entity.type, options[:remove_types])
|
17
37
|
# Id
|
18
38
|
string = ''
|
19
39
|
label = ''
|
40
|
+
sv = entity.short_value.inspect[1..-2]
|
20
41
|
string = "\n#{entity.id} ["
|
21
|
-
#
|
22
|
-
|
23
|
-
label = entity.to_s
|
24
|
-
else
|
25
|
-
label = entity.type.to_s.capitalize + " "
|
26
|
-
if entity.is_leaf?
|
27
|
-
label = entity.short_value.gsub(' [...]', " [...] \\n")
|
28
|
-
end
|
29
|
-
end
|
42
|
+
label = "#{entity.type.to_s.capitalize}\\n\\\"#{sv}\\\""
|
43
|
+
label.gsub!(' [...]', " [...] \\n")
|
30
44
|
# Features
|
31
45
|
if entity.has_features?
|
32
46
|
unless options[:features] == :none
|
33
47
|
label << "\\n"
|
34
48
|
entity.features.each do |feature, value|
|
49
|
+
next if options[:remove_features].include?(feature)
|
35
50
|
if options[:features] == :all ||
|
36
51
|
options[:features].include?(feature)
|
37
52
|
if value.is_a?(Treat::Entities::Entity)
|
38
|
-
label << "\\n#{feature}
|
53
|
+
label << "\\n#{feature}: \\\"*#{value.id}\\\""
|
54
|
+
elsif value.is_a?(Struct)
|
55
|
+
label << "\\n#{feature}: \\n\{ "
|
56
|
+
value.members.each do |member|
|
57
|
+
v = value.send(member)
|
58
|
+
v = v.to_s if v.is_a?(DateTime)
|
59
|
+
v = "*#{v.id}" if v.is_a?(Treat::Entities::Entity)
|
60
|
+
v = v ? v.inspect : ' -- '
|
61
|
+
v.gsub!('[', '\[')
|
62
|
+
v.gsub!('{', '\}')
|
63
|
+
v.gsub!(']', '\]')
|
64
|
+
v.gsub!('}', '\}')
|
65
|
+
v.gsub!('"', '\"')
|
66
|
+
label << "#{member}: #{v},\\n"
|
67
|
+
end
|
68
|
+
label = label[0..-4] unless label[-2] == '{'
|
69
|
+
label << "\},"
|
70
|
+
elsif value.is_a?(Hash)
|
71
|
+
label << "\\n#{feature}: \\n\{ "
|
72
|
+
value.each do |k,v|
|
73
|
+
v = v ? v.inspect : ' -- '
|
74
|
+
v.gsub!('[', '\[')
|
75
|
+
v.gsub!('{', '\}')
|
76
|
+
v.gsub!(']', '\]')
|
77
|
+
v.gsub!('}', '\}')
|
78
|
+
v.gsub!('"', '\"')
|
79
|
+
label << "#{k}: #{v},\\n"
|
80
|
+
end
|
81
|
+
label = label[0..-4] unless label[-2] == '{'
|
82
|
+
label << "\},"
|
83
|
+
elsif value.is_a?(Array)
|
84
|
+
label << "\\n#{feature}: \\n\[ "
|
85
|
+
value.each do |e|
|
86
|
+
e = "*#{e.id}" if e.is_a?(Treat::Entities::Entity)
|
87
|
+
label << "#{e},\\n"
|
88
|
+
end
|
89
|
+
label = label[0..-4] unless label[-2] == '['
|
90
|
+
label << " \]"
|
39
91
|
else
|
40
|
-
label << "\\n#{feature}
|
92
|
+
label << "\\n#{feature}: \\\"#{value}\\\""
|
41
93
|
end
|
42
94
|
end
|
43
95
|
end
|
44
96
|
end
|
45
97
|
end
|
98
|
+
color = nil
|
99
|
+
if options[:colors]
|
100
|
+
options[:colors].each do |col, lambda|
|
101
|
+
color = col.to_s if lambda.call(entity)
|
102
|
+
break if color
|
103
|
+
end
|
104
|
+
end
|
46
105
|
label = label[0..-2] if label[-1] == ','
|
47
|
-
string << "label=\"#{label}\"]"
|
106
|
+
string << "label=\"#{label}\",color=\"#{color.to_s}\"]"
|
107
|
+
string.gsub!('\\\\""]', '\\""]')
|
108
|
+
string.gsub('\"\""]', '\""]')
|
48
109
|
# Parent-child relationships.
|
49
110
|
if entity.has_parent?
|
50
|
-
|
111
|
+
unless options[:first] == true
|
112
|
+
string << "\n#{entity.parent.id} -- #{entity.id};"
|
113
|
+
end
|
51
114
|
end
|
52
|
-
#
|
53
|
-
if entity.
|
54
|
-
entity.
|
55
|
-
|
56
|
-
|
57
|
-
|
115
|
+
# Dependencies.
|
116
|
+
if entity.has_dependencies?
|
117
|
+
entity.dependencies.each do |dependency|
|
118
|
+
dir = ''
|
119
|
+
if dependency.directed == true
|
120
|
+
dir = dependency.direction == 1 ? 'forward' : 'back'
|
121
|
+
dir = ",dir=#{dir}"
|
122
|
+
else
|
123
|
+
dir = ",dir=both"
|
124
|
+
end
|
125
|
+
string << "\n#{entity.id} -- #{dependency.target}"
|
126
|
+
string << "[label=#{dependency.type}#{dir}]"
|
58
127
|
end
|
59
128
|
end
|
60
129
|
# Recurse.
|
130
|
+
options[:first] = false
|
61
131
|
if entity.has_children?
|
62
132
|
entity.each do |child|
|
63
133
|
string << self.to_dot(child, options)
|