pdf-extract 0.0.8 → 0.0.9
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.
- data/data/reference.model +110 -131
- data/lib/analysis/sections.rb +2 -1
- data/lib/language.rb +31 -16
- data/lib/references/references.rb +2 -0
- data/lib/references/score.rb +1 -1
- metadata +18 -14
- data/bin/config.json +0 -4
- data/bin/fac_v19n11_s5.mask.pdf +0 -0
- data/bin/margins.mask.pdf +0 -0
- data/bin/one-column.mask.pdf +69 -24080
- data/bin/s002040050107_Arch_Toxicol_1994_68_8.mask.pdf +0 -0
- data/bin/s6.mask.pdf +0 -0
- data/bin/some3.mask.pdf +0 -0
- data/bin/some5.mask.pdf +0 -0
- data/bin/some6.mask.pdf +0 -0
- data/bin/two-column.mask.pdf +0 -0
- data/lib/#language.rb# +0 -66
|
File without changes
|
data/bin/s6.mask.pdf
DELETED
|
Binary file
|
data/bin/some3.mask.pdf
DELETED
|
Binary file
|
data/bin/some5.mask.pdf
DELETED
|
Binary file
|
data/bin/some6.mask.pdf
DELETED
|
Binary file
|
data/bin/two-column.mask.pdf
DELETED
|
Binary file
|
data/lib/#language.rb#
DELETED
|
@@ -1,66 +0,0 @@
|
|
|
1
|
-
require_relative "names"
|
|
2
|
-
|
|
3
|
-
module PdfExtract::Language
|
|
4
|
-
|
|
5
|
-
def self.transliterate s
|
|
6
|
-
s = s.gsub "\ufb01", "fi"
|
|
7
|
-
s = s.gsub "\ufb02", "fl"
|
|
8
|
-
s = s.gsub "\ufb03", "ffi"
|
|
9
|
-
s = s.gsub "\ufb04", "ffl"
|
|
10
|
-
s = s.gsub "\ufb06", "st"
|
|
11
|
-
s = s.gsub "\u2018", "'"
|
|
12
|
-
s = s.gsub "\u2019", "'"
|
|
13
|
-
s = s.gsub "\u2013", "-"
|
|
14
|
-
s = s.gsub "\u2014", "-"
|
|
15
|
-
s = s.gsub "\u201c", "\""
|
|
16
|
-
s = s.gsub "\u201d", "\""
|
|
17
|
-
s = s.gsub "\u25af", "("
|
|
18
|
-
s = s.gsub "\u00b4", ""
|
|
19
|
-
s = s.gsub "\u00b1", "-"
|
|
20
|
-
|
|
21
|
-
s = s.gsub /\s+/, " "
|
|
22
|
-
end
|
|
23
|
-
|
|
24
|
-
def self.letter_ratio s
|
|
25
|
-
s.count("A-Z0-9\-[],.\"'()") / s.length.to_f
|
|
26
|
-
end
|
|
27
|
-
|
|
28
|
-
# TODO Ignore caps in middle of words
|
|
29
|
-
def self.cap_ratio s
|
|
30
|
-
sentence_end = true
|
|
31
|
-
cap_count = 0
|
|
32
|
-
|
|
33
|
-
s.each_char do |c|
|
|
34
|
-
if c =~ /\./
|
|
35
|
-
sentence_end = true
|
|
36
|
-
elsif c =~ /[A-Z]/
|
|
37
|
-
cap_count = cap_count + 1 unless sentence_end
|
|
38
|
-
sentence_end = false
|
|
39
|
-
elsif c =~ /[^\s]/
|
|
40
|
-
sentence_end = false
|
|
41
|
-
end
|
|
42
|
-
end
|
|
43
|
-
|
|
44
|
-
cap_count / s.split.length.to_f
|
|
45
|
-
end
|
|
46
|
-
|
|
47
|
-
def self.year_ratio s
|
|
48
|
-
words = s.split
|
|
49
|
-
|
|
50
|
-
year_words = words.map do |word|
|
|
51
|
-
word =~ /[^\d]\d{4}[^\d]/
|
|
52
|
-
end
|
|
53
|
-
|
|
54
|
-
year_words.reject { |year_word| not year_word }.length / words.length.to_f
|
|
55
|
-
end
|
|
56
|
-
|
|
57
|
-
def self.name_ratio content
|
|
58
|
-
PdfExtract::Names.detect_names(content)[:name_frequency]
|
|
59
|
-
end
|
|
60
|
-
|
|
61
|
-
def self.word_count s
|
|
62
|
-
s.split.count
|
|
63
|
-
end
|
|
64
|
-
|
|
65
|
-
end
|
|
66
|
-
|