anystyle 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/HISTORY.md +78 -0
- data/LICENSE +27 -0
- data/README.md +103 -0
- data/lib/anystyle.rb +71 -0
- data/lib/anystyle/dictionary.rb +132 -0
- data/lib/anystyle/dictionary/gdbm.rb +52 -0
- data/lib/anystyle/dictionary/lmdb.rb +67 -0
- data/lib/anystyle/dictionary/marshal.rb +27 -0
- data/lib/anystyle/dictionary/redis.rb +55 -0
- data/lib/anystyle/document.rb +264 -0
- data/lib/anystyle/errors.rb +14 -0
- data/lib/anystyle/feature.rb +27 -0
- data/lib/anystyle/feature/affix.rb +43 -0
- data/lib/anystyle/feature/brackets.rb +32 -0
- data/lib/anystyle/feature/canonical.rb +13 -0
- data/lib/anystyle/feature/caps.rb +20 -0
- data/lib/anystyle/feature/category.rb +70 -0
- data/lib/anystyle/feature/dictionary.rb +16 -0
- data/lib/anystyle/feature/indent.rb +16 -0
- data/lib/anystyle/feature/keyword.rb +52 -0
- data/lib/anystyle/feature/line.rb +39 -0
- data/lib/anystyle/feature/locator.rb +18 -0
- data/lib/anystyle/feature/number.rb +39 -0
- data/lib/anystyle/feature/position.rb +28 -0
- data/lib/anystyle/feature/punctuation.rb +22 -0
- data/lib/anystyle/feature/quotes.rb +20 -0
- data/lib/anystyle/feature/ref.rb +21 -0
- data/lib/anystyle/feature/terminal.rb +19 -0
- data/lib/anystyle/feature/words.rb +74 -0
- data/lib/anystyle/finder.rb +94 -0
- data/lib/anystyle/format/bibtex.rb +63 -0
- data/lib/anystyle/format/csl.rb +28 -0
- data/lib/anystyle/normalizer.rb +65 -0
- data/lib/anystyle/normalizer/brackets.rb +13 -0
- data/lib/anystyle/normalizer/container.rb +13 -0
- data/lib/anystyle/normalizer/date.rb +109 -0
- data/lib/anystyle/normalizer/edition.rb +16 -0
- data/lib/anystyle/normalizer/journal.rb +14 -0
- data/lib/anystyle/normalizer/locale.rb +30 -0
- data/lib/anystyle/normalizer/location.rb +24 -0
- data/lib/anystyle/normalizer/locator.rb +22 -0
- data/lib/anystyle/normalizer/names.rb +88 -0
- data/lib/anystyle/normalizer/page.rb +29 -0
- data/lib/anystyle/normalizer/publisher.rb +18 -0
- data/lib/anystyle/normalizer/pubmed.rb +18 -0
- data/lib/anystyle/normalizer/punctuation.rb +23 -0
- data/lib/anystyle/normalizer/quotes.rb +14 -0
- data/lib/anystyle/normalizer/type.rb +54 -0
- data/lib/anystyle/normalizer/volume.rb +26 -0
- data/lib/anystyle/parser.rb +199 -0
- data/lib/anystyle/support.rb +4 -0
- data/lib/anystyle/support/finder.mod +3234 -0
- data/lib/anystyle/support/finder.txt +75 -0
- data/lib/anystyle/support/parser.mod +15025 -0
- data/lib/anystyle/support/parser.txt +75 -0
- data/lib/anystyle/utils.rb +70 -0
- data/lib/anystyle/version.rb +3 -0
- data/res/finder/bb132pr2055.ttx +6803 -0
- data/res/finder/bb550sh8053.ttx +18660 -0
- data/res/finder/bb599nz4341.ttx +2957 -0
- data/res/finder/bb725rt6501.ttx +15276 -0
- data/res/finder/bc605xz1554.ttx +18815 -0
- data/res/finder/bd040gx5718.ttx +4271 -0
- data/res/finder/bd413nt2715.ttx +4956 -0
- data/res/finder/bd466fq0394.ttx +6100 -0
- data/res/finder/bf668vw2021.ttx +3578 -0
- data/res/finder/bg495cx0468.ttx +7267 -0
- data/res/finder/bg599vt3743.ttx +6752 -0
- data/res/finder/bg608dx2253.ttx +4094 -0
- data/res/finder/bh410qk3771.ttx +8785 -0
- data/res/finder/bh989ww6442.ttx +17204 -0
- data/res/finder/bj581pc8202.ttx +2719 -0
- data/res/parser/bad.xml +5199 -0
- data/res/parser/core.xml +7924 -0
- data/res/parser/gold.xml +2707 -0
- data/res/parser/good.xml +34281 -0
- data/res/parser/stanford-books.xml +2280 -0
- data/res/parser/stanford-diss.xml +726 -0
- data/res/parser/stanford-theses.xml +4684 -0
- data/res/parser/ugly.xml +33246 -0
- metadata +195 -0
@@ -0,0 +1,67 @@
|
|
1
|
+
module AnyStyle
|
2
|
+
require 'lmdb'
|
3
|
+
|
4
|
+
class Dictionary
|
5
|
+
class LMDB < Dictionary
|
6
|
+
@defaults = {
|
7
|
+
path: File.expand_path('../data', __FILE__),
|
8
|
+
mapsize: 1 << 22,
|
9
|
+
writemap: true,
|
10
|
+
mapasync: true
|
11
|
+
}
|
12
|
+
|
13
|
+
attr_reader :env
|
14
|
+
|
15
|
+
def initialize(options = {})
|
16
|
+
super(self.class.defaults.merge(options))
|
17
|
+
end
|
18
|
+
|
19
|
+
def open
|
20
|
+
unless open?
|
21
|
+
@env = ::LMDB.new(path, lmdb_options)
|
22
|
+
@db = @env.database create: true
|
23
|
+
end
|
24
|
+
|
25
|
+
self
|
26
|
+
ensure
|
27
|
+
populate! if empty?
|
28
|
+
end
|
29
|
+
|
30
|
+
def close
|
31
|
+
env.close if open?
|
32
|
+
end
|
33
|
+
|
34
|
+
def open?
|
35
|
+
!db.nil?
|
36
|
+
end
|
37
|
+
|
38
|
+
def empty?
|
39
|
+
open? and db.size == 0
|
40
|
+
end
|
41
|
+
|
42
|
+
def truncate
|
43
|
+
close
|
44
|
+
%w{ data.mdb lock.mdb }.each do |mdb|
|
45
|
+
mdb = File.join(path, mdb)
|
46
|
+
File.unlink(mdb) if File.exists?(mdb)
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
def get(key)
|
51
|
+
db[key.to_s].to_i
|
52
|
+
end
|
53
|
+
|
54
|
+
def put(key, value)
|
55
|
+
db[key.to_s] = value.to_i.to_s
|
56
|
+
end
|
57
|
+
|
58
|
+
def path
|
59
|
+
options[:path]
|
60
|
+
end
|
61
|
+
|
62
|
+
def lmdb_options
|
63
|
+
options.reject { |k| [:path, :source].include?(k) }
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module AnyStyle
|
2
|
+
class Dictionary
|
3
|
+
class Marshal < Dictionary
|
4
|
+
@defaults = {
|
5
|
+
path: File.expand_path('../../data/dict.marshal', __FILE__)
|
6
|
+
}
|
7
|
+
|
8
|
+
def initialize(options = {})
|
9
|
+
super(self.class.defaults.merge(options))
|
10
|
+
end
|
11
|
+
|
12
|
+
def open
|
13
|
+
if File.exists?(options[:path])
|
14
|
+
@db = ::Marshal.load(File.open(options[:path]))
|
15
|
+
else
|
16
|
+
@db = {}
|
17
|
+
end
|
18
|
+
self
|
19
|
+
ensure
|
20
|
+
if empty?
|
21
|
+
populate!
|
22
|
+
::Marshal.dump(db, File.open(options[:path], 'wb'))
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
module AnyStyle
|
2
|
+
require 'redis'
|
3
|
+
maybe_require 'redis/namespace'
|
4
|
+
|
5
|
+
class Dictionary
|
6
|
+
class Redis < Dictionary
|
7
|
+
@defaults = {
|
8
|
+
namespace: 'anystyle',
|
9
|
+
port: 6379
|
10
|
+
}
|
11
|
+
|
12
|
+
def initialize(options = {})
|
13
|
+
super(self.class.defaults.merge(options))
|
14
|
+
end
|
15
|
+
|
16
|
+
def open
|
17
|
+
unless open?
|
18
|
+
@db = ::Redis.new(options)
|
19
|
+
|
20
|
+
unless namespace.nil? or not defined?(::Redis::Namespace)
|
21
|
+
@db = ::Redis::Namespace.new namespace, redis: @db
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
self
|
26
|
+
ensure
|
27
|
+
populate! if empty?
|
28
|
+
end
|
29
|
+
|
30
|
+
def close
|
31
|
+
db.close
|
32
|
+
end
|
33
|
+
|
34
|
+
def open?
|
35
|
+
not db.nil?
|
36
|
+
end
|
37
|
+
|
38
|
+
def empty?
|
39
|
+
open? and db.dbsize == 0
|
40
|
+
end
|
41
|
+
|
42
|
+
def get(key)
|
43
|
+
db[key.to_s].to_i
|
44
|
+
end
|
45
|
+
|
46
|
+
def put(key, value)
|
47
|
+
db[key.to_s] = value.to_i
|
48
|
+
end
|
49
|
+
|
50
|
+
def namespace
|
51
|
+
options[:namespace]
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,264 @@
|
|
1
|
+
module AnyStyle
|
2
|
+
class Document < Wapiti::Sequence
|
3
|
+
class << self
|
4
|
+
include PdfUtils
|
5
|
+
|
6
|
+
def parse(string, delimiter: /\r?\n/, tagged: false)
|
7
|
+
current_label = ''
|
8
|
+
new(string.split(delimiter).map { |line|
|
9
|
+
if tagged
|
10
|
+
label, line = line.split(/\s*\| /, 2)
|
11
|
+
current_label = label unless label.empty?
|
12
|
+
end
|
13
|
+
Wapiti::Token.new line, label: current_label.to_s
|
14
|
+
})
|
15
|
+
end
|
16
|
+
|
17
|
+
def open(path, format: File.extname(path), tagged: false, layout: true, **opts)
|
18
|
+
raise ArgumentError,
|
19
|
+
"cannot open tainted path: '#{path}'" if path.tainted?
|
20
|
+
raise ArgumentError,
|
21
|
+
"document not found: '#{path}'" unless File.exist?(path)
|
22
|
+
|
23
|
+
path = File.absolute_path(path)
|
24
|
+
|
25
|
+
case format.downcase
|
26
|
+
when '.pdf'
|
27
|
+
meta = pdf_meta path if opts[:parse_meta]
|
28
|
+
info = pdf_info path if opts[:parse_info]
|
29
|
+
input = pdf_to_text path, layout: layout
|
30
|
+
when '.ttx'
|
31
|
+
tagged = true
|
32
|
+
input = File.read(path, encoding: 'utf-8')
|
33
|
+
when '.txt'
|
34
|
+
input = File.read(path, encoding: 'utf-8')
|
35
|
+
end
|
36
|
+
|
37
|
+
doc = parse input, tagged: tagged
|
38
|
+
doc.path = path
|
39
|
+
doc.meta = meta
|
40
|
+
doc.info = info
|
41
|
+
doc
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
include StringUtils
|
46
|
+
|
47
|
+
attr_accessor :meta, :info, :path, :pages, :tokens
|
48
|
+
alias_method :lines, :tokens
|
49
|
+
|
50
|
+
def pages
|
51
|
+
@pages ||= Page.parse(lines)
|
52
|
+
end
|
53
|
+
|
54
|
+
def each
|
55
|
+
if block_given?
|
56
|
+
pages.each.with_index do |page, pn|
|
57
|
+
page.lines.each.with_index do |line, ln|
|
58
|
+
yield line, ln, page, pn
|
59
|
+
end
|
60
|
+
end
|
61
|
+
self
|
62
|
+
else
|
63
|
+
to_enum
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
def each_section
|
68
|
+
if block_given?
|
69
|
+
current = []
|
70
|
+
lines.each do |ln|
|
71
|
+
case ln.label
|
72
|
+
when 'title'
|
73
|
+
unless current.empty?
|
74
|
+
yield current
|
75
|
+
current = []
|
76
|
+
end
|
77
|
+
when 'ref', 'text'
|
78
|
+
current << ln
|
79
|
+
else
|
80
|
+
# ignore
|
81
|
+
end
|
82
|
+
end
|
83
|
+
unless current.empty?
|
84
|
+
yield current
|
85
|
+
end
|
86
|
+
self
|
87
|
+
else
|
88
|
+
to_enum
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
def label(other)
|
93
|
+
doc = dup
|
94
|
+
doc.tokens = lines.map.with_index { |line, idx|
|
95
|
+
Wapiti::Token.new line.value,
|
96
|
+
label: other[idx].label.to_s,
|
97
|
+
observations: other[idx].observations.dup
|
98
|
+
}
|
99
|
+
doc
|
100
|
+
end
|
101
|
+
|
102
|
+
def to_s(delimiter: "\n", encode: false, tagged: false, **opts)
|
103
|
+
if tagged
|
104
|
+
prev_label = nil
|
105
|
+
lines.map { |ln|
|
106
|
+
label = (ln.label == prev_label) ? '' : ln.label
|
107
|
+
prev_label = ln.label
|
108
|
+
'%.14s| %s' % ["#{label} ", ln.value]
|
109
|
+
}.join(delimiter)
|
110
|
+
else
|
111
|
+
super(delimiter: delimiter, encode: encode, tagged: tagged, expanded: false, **opts)
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
115
|
+
def to_a(encode: true, **opts)
|
116
|
+
super(encode: encode, **opts)
|
117
|
+
end
|
118
|
+
|
119
|
+
def to_h(**opts)
|
120
|
+
{
|
121
|
+
info: info,
|
122
|
+
meta: meta,
|
123
|
+
sections: sections(**opts),
|
124
|
+
title: title(**opts),
|
125
|
+
references: references(**opts)
|
126
|
+
}
|
127
|
+
end
|
128
|
+
|
129
|
+
def references(**opts)
|
130
|
+
bib, current, delta, indent = [], nil, 0, 0
|
131
|
+
|
132
|
+
lines.each do |ln|
|
133
|
+
case ln.label
|
134
|
+
when 'ref'
|
135
|
+
val = display_chars(ln.value).rstrip
|
136
|
+
idt = val[/^\s*/].length
|
137
|
+
val.lstrip!
|
138
|
+
|
139
|
+
if current.nil?
|
140
|
+
current, delta, indent = val, 0, idt
|
141
|
+
else
|
142
|
+
if join_refs?(current, val, delta, idt - indent)
|
143
|
+
current = join_refs(current, val)
|
144
|
+
else
|
145
|
+
bib << current
|
146
|
+
current, delta, indent = val, 0, idt
|
147
|
+
end
|
148
|
+
end
|
149
|
+
else
|
150
|
+
unless current.nil?
|
151
|
+
if delta > 15 || %w{ blank meta }.include?(ln.label)
|
152
|
+
delta += 1
|
153
|
+
else
|
154
|
+
bib << current
|
155
|
+
current, delta, indent = nil, 0, idt
|
156
|
+
end
|
157
|
+
end
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
unless current.nil?
|
162
|
+
bib << current
|
163
|
+
end
|
164
|
+
|
165
|
+
bib
|
166
|
+
end
|
167
|
+
|
168
|
+
def join_refs?(a, b, delta = 0, indent = 0)
|
169
|
+
pro = [
|
170
|
+
indent > 0,
|
171
|
+
delta == 0,
|
172
|
+
b.length < 50,
|
173
|
+
a.length < 65,
|
174
|
+
a.match?(/[,;:&\p{Pd}]$/),
|
175
|
+
b.match?(/^\p{Ll}/) || a.match?(/\p{L}$/) && b.match?(/^\p{L}/)
|
176
|
+
].count(true)
|
177
|
+
|
178
|
+
con = [
|
179
|
+
indent < 0,
|
180
|
+
delta > 8,
|
181
|
+
a.match?(/\.\]$/),
|
182
|
+
a.length > 500,
|
183
|
+
(b.length - a.length) > 12,
|
184
|
+
b.match?(/^(\p{Pd}\p{Pd}|\p{Lu}\p{Ll}+, \p{Lu}\.|\[\d)/)
|
185
|
+
].count(true)
|
186
|
+
|
187
|
+
(pro - con) > 1
|
188
|
+
end
|
189
|
+
|
190
|
+
def join_refs(a, b)
|
191
|
+
if a[-1] == '-'
|
192
|
+
if b =~ /^\p{Ll}/
|
193
|
+
"#{a[0...-1]}#{b}"
|
194
|
+
else
|
195
|
+
"#{a}#{b}"
|
196
|
+
end
|
197
|
+
else
|
198
|
+
"#{a} #{b}"
|
199
|
+
end
|
200
|
+
end
|
201
|
+
|
202
|
+
def sections(delimiter: "\n", **opts)
|
203
|
+
[]
|
204
|
+
end
|
205
|
+
|
206
|
+
def title(delimiter: " ", **opts)
|
207
|
+
lines.drop_while { |ln|
|
208
|
+
ln.label != 'title'
|
209
|
+
}.take_while { |ln|
|
210
|
+
ln.label == 'title'
|
211
|
+
}.map(&:value).join(delimiter)
|
212
|
+
end
|
213
|
+
|
214
|
+
def inspect
|
215
|
+
"#<AnyStyle::Document lines={#{size}}>"
|
216
|
+
end
|
217
|
+
|
218
|
+
|
219
|
+
class Page
|
220
|
+
extend StringUtils
|
221
|
+
|
222
|
+
class << self
|
223
|
+
def parse(lines)
|
224
|
+
pages, current, width = [], [], 0
|
225
|
+
|
226
|
+
lines.each do |line|
|
227
|
+
if page_break?(line.value)
|
228
|
+
unless current.empty?
|
229
|
+
pages << new(current, width: width)
|
230
|
+
end
|
231
|
+
|
232
|
+
current = [line]
|
233
|
+
width = display_width(line.value)
|
234
|
+
else
|
235
|
+
current << line
|
236
|
+
width = [width, display_width(line.value)].max
|
237
|
+
end
|
238
|
+
end
|
239
|
+
|
240
|
+
unless current.empty?
|
241
|
+
pages << new(current, width: width)
|
242
|
+
end
|
243
|
+
|
244
|
+
pages
|
245
|
+
end
|
246
|
+
end
|
247
|
+
|
248
|
+
attr_accessor :lines, :width
|
249
|
+
|
250
|
+
def initialize(lines = [], width: 0)
|
251
|
+
@lines = lines
|
252
|
+
@width = width
|
253
|
+
end
|
254
|
+
|
255
|
+
def size
|
256
|
+
lines.size
|
257
|
+
end
|
258
|
+
|
259
|
+
def inspect
|
260
|
+
"#<AnyStyle::Document::Page size={#{size}} width={#{width}}>"
|
261
|
+
end
|
262
|
+
end
|
263
|
+
end
|
264
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module AnyStyle
|
2
|
+
class Feature
|
3
|
+
include StringUtils
|
4
|
+
|
5
|
+
attr_reader :precision
|
6
|
+
|
7
|
+
def initialize(precision: 10, **opts)
|
8
|
+
@precision = precision
|
9
|
+
end
|
10
|
+
|
11
|
+
def observe(token, **opts)
|
12
|
+
raise NotImplementedError
|
13
|
+
end
|
14
|
+
|
15
|
+
def next(idx, seq)
|
16
|
+
sequence[idx + 1]
|
17
|
+
end
|
18
|
+
|
19
|
+
def prev(idx, seq)
|
20
|
+
idx == 0 ? nil : seq[idx - 1]
|
21
|
+
end
|
22
|
+
|
23
|
+
def ratio(x, y)
|
24
|
+
(y > 0) ? ((x.to_f / y) * precision).round : 0
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|