stanford-mods 1.4.0 → 1.5.0
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/lib/stanford-mods.rb +1 -0
- data/lib/stanford-mods/coordinate.rb +81 -0
- data/lib/stanford-mods/geo_spatial.rb +9 -36
- data/lib/stanford-mods/version.rb +1 -1
- data/spec/geo_spatial_spec.rb +14 -38
- data/spec/lib/stanford-mods/coordinate_spec.rb +84 -0
- metadata +5 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: fda4f5ab13e13c81db05b27fd3ca5e5e17be0e1d
|
4
|
+
data.tar.gz: 13a2ee552756a2e700ee102ada1b56b55d5cda82
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 63c3efbf88ea9d76b80182c490cb01c3d6d404858ce7d91f46b1d98c3df284cf8dad19cf6b55eb2185a1779bafd8c750dde4e04cf39e64f6c810cf030cc80359
|
7
|
+
data.tar.gz: 275a160cf3603693e5801f0d5ff530995463c00a5f77625391fc09efaca8b13f0621f5a2e5034de5e1ae9cbb27d7a59fa0dcaf53aac877d057e65e004ecc3627
|
data/lib/stanford-mods.rb
CHANGED
@@ -0,0 +1,81 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
module Stanford
|
3
|
+
module Mods
|
4
|
+
##
|
5
|
+
# Geospatial coordinate parsing
|
6
|
+
class Coordinate
|
7
|
+
attr_reader :value
|
8
|
+
|
9
|
+
def initialize(value)
|
10
|
+
@value = value
|
11
|
+
end
|
12
|
+
|
13
|
+
# Convert the coordinate to a WKT/CQL ENVELOPE representation
|
14
|
+
def as_envelope
|
15
|
+
return unless valid?
|
16
|
+
|
17
|
+
"ENVELOPE(#{bounds[:min_x]}, #{bounds[:max_x]}, #{bounds[:min_y]}, #{bounds[:max_y]})"
|
18
|
+
end
|
19
|
+
|
20
|
+
# Convert the coordinate to a Solr 4.x bbox-format representation
|
21
|
+
def as_bbox
|
22
|
+
return unless valid?
|
23
|
+
|
24
|
+
"#{bounds[:min_x]} #{bounds[:min_y]} #{bounds[:max_x]} #{bounds[:max_y]}"
|
25
|
+
end
|
26
|
+
|
27
|
+
def valid?
|
28
|
+
return false if bounds.empty?
|
29
|
+
|
30
|
+
range_x = -180.0..180.0
|
31
|
+
range_y = -90.0..90.0
|
32
|
+
|
33
|
+
range_x.include?(bounds[:min_x]) &&
|
34
|
+
range_x.include?(bounds[:max_x]) &&
|
35
|
+
range_y.include?(bounds[:min_y]) &&
|
36
|
+
range_y.include?(bounds[:max_y])
|
37
|
+
end
|
38
|
+
|
39
|
+
private
|
40
|
+
|
41
|
+
def bounds
|
42
|
+
@bounds ||= begin
|
43
|
+
matches = coord.match %r{\A(?<lat>[EW].+-+.+)\s*/\s*(?<lng>[NS].+-+.+)\Z}
|
44
|
+
|
45
|
+
if matches
|
46
|
+
min_x, max_x = matches['lat'].split(/-+/).map { |x| coord_to_decimal(x) }.minmax
|
47
|
+
min_y, max_y = matches['lng'].split(/-+/).map { |y| coord_to_decimal(y) }.minmax
|
48
|
+
|
49
|
+
{ min_x: min_x, min_y: min_y, max_x: max_x, max_y: max_y }
|
50
|
+
else
|
51
|
+
{}
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def coord
|
57
|
+
matches = value.match(/^\(?([^)]+)\)?\.?$/)
|
58
|
+
|
59
|
+
if matches
|
60
|
+
matches[1]
|
61
|
+
else
|
62
|
+
value
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
def coord_to_decimal(point)
|
67
|
+
regex = /(?<dir>[NESW])\s*(?<deg>\d+)[°⁰º](?:(?<min>\d+)[ʹ'])?(?:(?<sec>\d+)[ʺ"])?/
|
68
|
+
match = regex.match(point)
|
69
|
+
|
70
|
+
return Float::INFINITY unless match
|
71
|
+
|
72
|
+
dec = match['deg'].to_i
|
73
|
+
dec += match['min'].to_f / 60
|
74
|
+
dec += match['sec'].to_f / 60 / 60
|
75
|
+
dec = -1 * dec if match['dir'] == 'W' || match['dir'] == 'S'
|
76
|
+
|
77
|
+
dec
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
@@ -10,50 +10,23 @@ module Stanford
|
|
10
10
|
Array(@mods_ng_xml.subject.cartographics.coordinates).map(&:text)
|
11
11
|
end
|
12
12
|
|
13
|
-
def
|
13
|
+
def coordinates_as_envelope
|
14
14
|
coordinates.map do |n|
|
15
|
-
|
15
|
+
c = Stanford::Mods::Coordinate.new(n)
|
16
16
|
|
17
|
-
if
|
18
|
-
coord_to_bbox(matches[1])
|
19
|
-
else
|
20
|
-
coord_to_bbox(n)
|
21
|
-
end
|
17
|
+
c.as_envelope if c.valid?
|
22
18
|
end.compact
|
23
19
|
end
|
24
20
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
matches = coord.match %r{\A(?<lat>[EW].+-+.+)\s*/\s*(?<lng>[NS].+-+.+)\Z}
|
29
|
-
return unless matches
|
30
|
-
|
31
|
-
min_x, max_x = matches['lat'].split(/-+/).map { |x| coord_to_decimal(x) }.minmax
|
32
|
-
min_y, max_y = matches['lng'].split(/-+/).map { |y| coord_to_decimal(y) }.minmax
|
33
|
-
|
34
|
-
"#{min_x} #{min_y} #{max_x} #{max_y}" if valid_bbox?(min_x, max_x, min_y, max_y)
|
35
|
-
end
|
36
|
-
|
37
|
-
def coord_to_decimal(point)
|
38
|
-
regex = /(?<dir>[NESW])\s*(?<deg>\d+)[°⁰º](?:(?<min>\d+)[ʹ'])?(?:(?<sec>\d+)[ʺ"])?/
|
39
|
-
match = regex.match(point)
|
40
|
-
|
41
|
-
return Float::INFINITY unless match
|
42
|
-
|
43
|
-
dec = match['deg'].to_i
|
44
|
-
dec += match['min'].to_f / 60
|
45
|
-
dec += match['sec'].to_f / 60 / 60
|
46
|
-
dec = -1 * dec if match['dir'] == 'W' || match['dir'] == 'S'
|
21
|
+
def coordinates_as_bbox
|
22
|
+
coordinates.map do |n|
|
23
|
+
c = Stanford::Mods::Coordinate.new(n)
|
47
24
|
|
48
|
-
|
25
|
+
c.as_bbox if c.valid?
|
26
|
+
end.compact
|
49
27
|
end
|
50
28
|
|
51
|
-
|
52
|
-
range_x = -180.0..180.0
|
53
|
-
range_y = -90.0..90.0
|
54
|
-
|
55
|
-
range_x.include?(min_x) && range_x.include?(max_x) && range_y.include?(min_y) && range_y.include?(max_y)
|
56
|
-
end
|
29
|
+
alias point_bbox coordinates_as_bbox
|
57
30
|
end # class Record
|
58
31
|
end # Module Mods
|
59
32
|
end # Module Stanford
|
data/spec/geo_spatial_spec.rb
CHANGED
@@ -53,7 +53,7 @@ describe "Cartographic coordinates" do
|
|
53
53
|
end
|
54
54
|
end
|
55
55
|
|
56
|
-
|
56
|
+
describe "#coordinates_as_bbox" do
|
57
57
|
it "returns empty array if no coordinates in the mods" do
|
58
58
|
smods_rec.from_str(no_coord)
|
59
59
|
expect(smods_rec.point_bbox).to eq([])
|
@@ -66,44 +66,20 @@ describe "Cartographic coordinates" do
|
|
66
66
|
smods_rec.from_str(with_coords)
|
67
67
|
expect(smods_rec.point_bbox).to eq(["-16.0 -15.0 28.0 13.0"])
|
68
68
|
end
|
69
|
+
end
|
69
70
|
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
[], # N487 is out of bounds for the bounding box
|
83
|
-
%((W 0°-W 0°/S 90°---S 90°)) =>
|
84
|
-
['-0.0 -90.0 -0.0 -90.0'], # one dash, two dashes, three dashes.. what's the difference?
|
85
|
-
%(W 650--W 100/N 700--N 550) =>
|
86
|
-
[] # missing degree character, and all coordinates are out of bounds.
|
87
|
-
}.each do |value, expected|
|
88
|
-
describe 'data mappings' do
|
89
|
-
let(:mods) do
|
90
|
-
<<-EOF
|
91
|
-
<mods xmlns="#{Mods::MODS_NS}">
|
92
|
-
<subject>
|
93
|
-
<cartographics>
|
94
|
-
<coordinates>#{value}</coordinates>
|
95
|
-
</cartographics>
|
96
|
-
</subject>
|
97
|
-
</mods>
|
98
|
-
EOF
|
99
|
-
end
|
100
|
-
|
101
|
-
let(:smods_rec) { Stanford::Mods::Record.new.from_str(mods) }
|
102
|
-
|
103
|
-
it 'maps to the right bounding box' do
|
104
|
-
expect(smods_rec.point_bbox).to eq expected
|
105
|
-
end
|
106
|
-
end
|
71
|
+
describe "#coordinates_as_envelope" do
|
72
|
+
it "returns empty array if no coordinates in the mods" do
|
73
|
+
smods_rec.from_str(no_coord)
|
74
|
+
expect(smods_rec.coordinates_as_envelope).to eq([])
|
75
|
+
end
|
76
|
+
it "returns empty array if bad data is in the mods" do
|
77
|
+
smods_rec.from_str(with_bad_data)
|
78
|
+
expect(smods_rec.coordinates_as_envelope).to eq([])
|
79
|
+
end
|
80
|
+
it "returns decimal representation of latitude and longitude" do
|
81
|
+
smods_rec.from_str(with_coords)
|
82
|
+
expect(smods_rec.coordinates_as_envelope).to eq(["ENVELOPE(-16.0, 28.0, -15.0, 13.0)"])
|
107
83
|
end
|
108
84
|
end
|
109
85
|
end # describe Cartographic coordinates
|
@@ -0,0 +1,84 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
describe Stanford::Mods::Coordinate do
|
5
|
+
describe '#valid' do
|
6
|
+
it 'is valid for well-formed coordinates' do
|
7
|
+
expect(described_class.new('W 123°23ʹ16ʺ--W 122°31ʹ22ʺ/N 39°23ʹ57ʺ--N 38°17ʹ53ʺ')).to be_valid
|
8
|
+
end
|
9
|
+
|
10
|
+
it 'rejects out-of-bounds coordinates' do
|
11
|
+
expect(described_class.new('W80°--E100°/N487°--S42°')).not_to be_valid
|
12
|
+
end
|
13
|
+
|
14
|
+
it 'rejects coordinates without degree symbols' do
|
15
|
+
expect(described_class.new('W 650--W 100/N 700--N 550')).not_to be_valid
|
16
|
+
end
|
17
|
+
|
18
|
+
it 'rejects malformed coordinates' do
|
19
|
+
expect(described_class.new('(E29°--E35/°S12°--S16°).')).not_to be_valid
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
describe '#as_bbox' do
|
24
|
+
it 'is nil for invalid data' do
|
25
|
+
expect(described_class.new('x').as_bbox).to eq nil
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
describe '#as_envelope' do
|
30
|
+
it 'is nil for invalid data' do
|
31
|
+
expect(described_class.new('x').as_envelope).to eq nil
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
context '#as_bbox' do
|
36
|
+
{
|
37
|
+
%((W 123°23ʹ16ʺ--W 122°31ʹ22ʺ/N 39°23ʹ57ʺ--N 38°17ʹ53ʺ)) =>
|
38
|
+
'-123.38777777777779 38.29805555555556 -122.52277777777778 39.399166666666666',
|
39
|
+
%(E 10°03'00"--E 12°58'00"/N 45°00'00"--N 41°46'00") =>
|
40
|
+
'10.05 41.766666666666666 12.966666666666667 45.0',
|
41
|
+
%(E 8°41'-E 12°21'/N 46°04'-N 44°23') =>
|
42
|
+
'8.683333333333334 44.38333333333333 12.35 46.06666666666667',
|
43
|
+
%((E17°--E11°/N14°--N18°).) =>
|
44
|
+
'11.0 14.0 17.0 18.0', # coordinates need to be reordered
|
45
|
+
%((W 170⁰--E 55⁰/N 40⁰--S 36⁰).) =>
|
46
|
+
'-170.0 -36.0 55.0 40.0', # superscript 0 is almost a degree character..
|
47
|
+
%((W 0°-W 0°/S 90°---S 90°)) =>
|
48
|
+
'-0.0 -90.0 -0.0 -90.0' # one dash, two dashes, three dashes.. what's the difference?
|
49
|
+
}.each do |value, expected|
|
50
|
+
describe 'parsing' do
|
51
|
+
let(:subject) { described_class.new(value) }
|
52
|
+
|
53
|
+
it 'transforms into the right bbox' do
|
54
|
+
expect(subject.as_bbox).to eq expected
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
context '#as_envelope' do
|
61
|
+
{
|
62
|
+
%((W 123°23ʹ16ʺ--W 122°31ʹ22ʺ/N 39°23ʹ57ʺ--N 38°17ʹ53ʺ)) =>
|
63
|
+
'ENVELOPE(-123.38777777777779, -122.52277777777778, 38.29805555555556, 39.399166666666666)',
|
64
|
+
%(E 10°03'00"--E 12°58'00"/N 45°00'00"--N 41°46'00") =>
|
65
|
+
'ENVELOPE(10.05, 12.966666666666667, 41.766666666666666, 45.0)',
|
66
|
+
%(E 8°41'-E 12°21'/N 46°04'-N 44°23') =>
|
67
|
+
'ENVELOPE(8.683333333333334, 12.35, 44.38333333333333, 46.06666666666667)',
|
68
|
+
%((E17°--E11°/N14°--N18°).) =>
|
69
|
+
'ENVELOPE(11.0, 17.0, 14.0, 18.0)', # coordinates need to be reordered
|
70
|
+
%((W 170⁰--E 55⁰/N 40⁰--S 36⁰).) =>
|
71
|
+
'ENVELOPE(-170.0, 55.0, -36.0, 40.0)', # superscript 0 is almost a degree character..
|
72
|
+
%((W 0°-W 0°/S 90°---S 90°)) =>
|
73
|
+
'ENVELOPE(-0.0, -0.0, -90.0, -90.0)' # one dash, two dashes, three dashes.. what's the difference?
|
74
|
+
}.each do |value, expected|
|
75
|
+
describe 'parsing' do
|
76
|
+
let(:subject) { described_class.new(value) }
|
77
|
+
|
78
|
+
it 'transforms into the right envelope' do
|
79
|
+
expect(subject.as_envelope).to eq expected
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: stanford-mods
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Naomi Dushay
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2016-01-
|
12
|
+
date: 2016-01-27 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: mods
|
@@ -120,6 +120,7 @@ files:
|
|
120
120
|
- Rakefile
|
121
121
|
- config/mappings_hash.rb
|
122
122
|
- lib/stanford-mods.rb
|
123
|
+
- lib/stanford-mods/coordinate.rb
|
123
124
|
- lib/stanford-mods/date_parsing.rb
|
124
125
|
- lib/stanford-mods/geo_spatial.rb
|
125
126
|
- lib/stanford-mods/name.rb
|
@@ -132,6 +133,7 @@ files:
|
|
132
133
|
- spec/date_parsing_spec.rb
|
133
134
|
- spec/fixtures/spotlight_pub_date_data.rb
|
134
135
|
- spec/geo_spatial_spec.rb
|
136
|
+
- spec/lib/stanford-mods/coordinate_spec.rb
|
135
137
|
- spec/name_spec.rb
|
136
138
|
- spec/origin_info_spec.rb
|
137
139
|
- spec/physical_location_spec.rb
|
@@ -171,6 +173,7 @@ test_files:
|
|
171
173
|
- spec/date_parsing_spec.rb
|
172
174
|
- spec/fixtures/spotlight_pub_date_data.rb
|
173
175
|
- spec/geo_spatial_spec.rb
|
176
|
+
- spec/lib/stanford-mods/coordinate_spec.rb
|
174
177
|
- spec/name_spec.rb
|
175
178
|
- spec/origin_info_spec.rb
|
176
179
|
- spec/physical_location_spec.rb
|