pdf-extract 0.0.1 → 0.0.2
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/bin/s6.mask.pdf +0 -0
- data/lib/analysis/columns.rb +3 -0
- data/lib/font_metrics.rb +3 -0
- metadata +4 -3
data/bin/s6.mask.pdf
ADDED
Binary file
|
data/lib/analysis/columns.rb
CHANGED
@@ -47,6 +47,9 @@ module PdfExtract
|
|
47
47
|
y = body[:y] + (body[:height] * i * step)
|
48
48
|
column_ranges << columns_at(y, body_regions)
|
49
49
|
end
|
50
|
+
|
51
|
+
# Discard those with a coverage of 0.
|
52
|
+
column_ranges.reject! { |r| r.covered.zero? }
|
50
53
|
|
51
54
|
# Discard those with more than x columns. They've probably hit a table.
|
52
55
|
column_ranges.reject! { |r| r.count > pdf.settings[:max_column_count] }
|
data/lib/font_metrics.rb
CHANGED
metadata
CHANGED
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 0
|
8
|
-
-
|
9
|
-
version: 0.0.
|
8
|
+
- 2
|
9
|
+
version: 0.0.2
|
10
10
|
platform: ruby
|
11
11
|
authors:
|
12
12
|
- Karl Jonathan Ward
|
@@ -14,7 +14,7 @@ autorequire:
|
|
14
14
|
bindir: bin
|
15
15
|
cert_chain: []
|
16
16
|
|
17
|
-
date: 2011-10-
|
17
|
+
date: 2011-10-24 00:00:00 +01:00
|
18
18
|
default_executable:
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
@@ -140,6 +140,7 @@ files:
|
|
140
140
|
- bin/one-column.mask.pdf
|
141
141
|
- bin/pdf-extract
|
142
142
|
- bin/s002040050107_Arch_Toxicol_1994_68_8.mask.pdf
|
143
|
+
- bin/s6.mask.pdf
|
143
144
|
- bin/some3.mask.pdf
|
144
145
|
- bin/some5.mask.pdf
|
145
146
|
- bin/some6.mask.pdf
|