region_extractor 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +17 -0
- data/Rakefile +46 -0
- data/VERSION +1 -0
- data/lib/region_extractor.rb +55 -0
- data/lib/region_extractor/point.rb +16 -0
- data/lib/region_extractor/region.rb +23 -0
- data/region_extractor.gemspec +60 -0
- data/spec/region_extractor_spec.rb +94 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +9 -0
- metadata +103 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Andrew Carpenter
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
= region_extractor
|
2
|
+
|
3
|
+
Description goes here.
|
4
|
+
|
5
|
+
== Note on Patches/Pull Requests
|
6
|
+
|
7
|
+
* Fork the project.
|
8
|
+
* Make your feature addition or bug fix.
|
9
|
+
* Add tests for it. This is important so I don't break it in a
|
10
|
+
future version unintentionally.
|
11
|
+
* Commit, do not mess with rakefile, version, or history.
|
12
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
13
|
+
* Send me a pull request. Bonus points for topic branches.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2010 Andrew Carpenter. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "region_extractor"
|
8
|
+
gem.summary = %Q{Extract geographic regions from plain text}
|
9
|
+
gem.description = %Q{Attempts to extract geographic regions mentioned in txt/html documents.}
|
10
|
+
gem.email = "andrew.main@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/andrewcarpenter/region_extractor"
|
12
|
+
gem.authors = ["Andrew Carpenter"]
|
13
|
+
gem.add_development_dependency "rspec", ">= 1.2.9"
|
14
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
15
|
+
gem.add_dependency('proj4rb', '>= 0.3.1')
|
16
|
+
end
|
17
|
+
Jeweler::GemcutterTasks.new
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'spec/rake/spectask'
|
23
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
24
|
+
spec.libs << 'lib' << 'spec'
|
25
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
26
|
+
end
|
27
|
+
|
28
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
29
|
+
spec.libs << 'lib' << 'spec'
|
30
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
31
|
+
spec.rcov = true
|
32
|
+
end
|
33
|
+
|
34
|
+
task :spec => :check_dependencies
|
35
|
+
|
36
|
+
task :default => :spec
|
37
|
+
|
38
|
+
require 'rake/rdoctask'
|
39
|
+
Rake::RDocTask.new do |rdoc|
|
40
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
41
|
+
|
42
|
+
rdoc.rdoc_dir = 'rdoc'
|
43
|
+
rdoc.title = "region_extractor #{version}"
|
44
|
+
rdoc.rdoc_files.include('README*')
|
45
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
46
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.1
|
@@ -0,0 +1,55 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'proj4'
|
3
|
+
|
4
|
+
require "region_extractor/region"
|
5
|
+
require "region_extractor/point"
|
6
|
+
|
7
|
+
class RegionExtractor
|
8
|
+
attr_accessor :regions, :resulting_text
|
9
|
+
|
10
|
+
def initialize(text, ®ion_transformer)
|
11
|
+
@text = text || ''
|
12
|
+
@regions = []
|
13
|
+
@resulting_text = text
|
14
|
+
@region_transformer = region_transformer
|
15
|
+
extract!
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
|
20
|
+
def extract!
|
21
|
+
@resulting_text = @text.gsub(/(?:excluding land bound by )?(?:\d{6,7}\s*,\s*\d{6,7};\s*){2,}\d{6,7}\s*,\s*\d{6,7}/) do |region_string|
|
22
|
+
match = @text.match(/UTM [z|Z]one (\d+)/)
|
23
|
+
zone = match ? match[1] : ''
|
24
|
+
|
25
|
+
points = region_string.sub(/^excluding land bound by /,'').split(/\s*;\s*/).map do |c|
|
26
|
+
x , y = c.split(/\s*,\s*/)
|
27
|
+
Point.new(x.to_i,y.to_i)
|
28
|
+
end
|
29
|
+
|
30
|
+
region = Region.new(:points => points, :zone => zone)
|
31
|
+
if region_string =~ /^excluding/
|
32
|
+
prior_region = @regions.last
|
33
|
+
prior_region.add_hole(region)
|
34
|
+
|
35
|
+
region_string # don't modify the document
|
36
|
+
else
|
37
|
+
@regions << region
|
38
|
+
|
39
|
+
if @region_transformer
|
40
|
+
@region_transformer.call(region_string, region, @regions.size-1)
|
41
|
+
else
|
42
|
+
nil
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
# extractor = RegionExtractor.new("507093, 4879404; 507095, 4879401") do |region, i|
|
50
|
+
# "<div id=\"map_#{i}\"></div>"
|
51
|
+
#
|
52
|
+
# end
|
53
|
+
#
|
54
|
+
# extractor.regions
|
55
|
+
# extractor.resulting_text
|
@@ -0,0 +1,16 @@
|
|
1
|
+
class RegionExtractor
|
2
|
+
include Proj4
|
3
|
+
class Point
|
4
|
+
attr_accessor :x, :y
|
5
|
+
|
6
|
+
def initialize(x,y)
|
7
|
+
@x = x
|
8
|
+
@y = y
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.tranform_point(point, origin_projection, destination_projection)
|
12
|
+
output = origin_projection.transform(destination_projection, point)
|
13
|
+
Point.new(output.x * Proj4::RAD_TO_DEG, output.y * Proj4::RAD_TO_DEG)
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
class RegionExtractor
|
2
|
+
class Region
|
3
|
+
attr_accessor :points, :zone, :holes
|
4
|
+
def initialize(options = {})
|
5
|
+
@points = options[:points]
|
6
|
+
@zone = options[:zone]
|
7
|
+
@projection = Proj4::Projection.new( :proj => 'utm', :datum => "NAD83", :zone => @zone)
|
8
|
+
@holes = []
|
9
|
+
end
|
10
|
+
|
11
|
+
def transformed_points(output_projection = Proj4::Projection.new( :proj => 'latlong', :datum => 'WGS84' ))
|
12
|
+
@points.map{|p| Point.tranform_point(p, @projection, output_projection) }
|
13
|
+
end
|
14
|
+
|
15
|
+
def coordinates(output_projection = Proj4::Projection.new( :proj => 'latlong', :datum => 'WGS84' ))
|
16
|
+
transformed_points(output_projection).map{|p|"#{p.x},#{p.y},0.000000"}.join("\n")
|
17
|
+
end
|
18
|
+
|
19
|
+
def add_hole(region)
|
20
|
+
@holes << region
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,60 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{region_extractor}
|
8
|
+
s.version = "0.0.1"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Andrew Carpenter"]
|
12
|
+
s.date = %q{2010-06-12}
|
13
|
+
s.description = %q{Attempts to extract geographic regions mentioned in txt/html documents.}
|
14
|
+
s.email = %q{andrew.main@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"lib/region_extractor.rb",
|
27
|
+
"lib/region_extractor/point.rb",
|
28
|
+
"lib/region_extractor/region.rb",
|
29
|
+
"region_extractor.gemspec",
|
30
|
+
"spec/region_extractor_spec.rb",
|
31
|
+
"spec/spec.opts",
|
32
|
+
"spec/spec_helper.rb"
|
33
|
+
]
|
34
|
+
s.homepage = %q{http://github.com/andrewcarpenter/region_extractor}
|
35
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
36
|
+
s.require_paths = ["lib"]
|
37
|
+
s.rubygems_version = %q{1.3.6}
|
38
|
+
s.summary = %q{Extract geographic regions from plain text}
|
39
|
+
s.test_files = [
|
40
|
+
"spec/region_extractor_spec.rb",
|
41
|
+
"spec/spec_helper.rb"
|
42
|
+
]
|
43
|
+
|
44
|
+
if s.respond_to? :specification_version then
|
45
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
46
|
+
s.specification_version = 3
|
47
|
+
|
48
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
49
|
+
s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
|
50
|
+
s.add_runtime_dependency(%q<proj4rb>, [">= 0.3.1"])
|
51
|
+
else
|
52
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
53
|
+
s.add_dependency(%q<proj4rb>, [">= 0.3.1"])
|
54
|
+
end
|
55
|
+
else
|
56
|
+
s.add_dependency(%q<rspec>, [">= 1.2.9"])
|
57
|
+
s.add_dependency(%q<proj4rb>, [">= 0.3.1"])
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
@@ -0,0 +1,94 @@
|
|
1
|
+
require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
|
2
|
+
describe "RegionExtractor" do
|
3
|
+
context "parsing text" do
|
4
|
+
context "with no regions present" do
|
5
|
+
before(:each) do
|
6
|
+
@texts = [
|
7
|
+
"",
|
8
|
+
"The brown cow.",
|
9
|
+
"10/15/1982",
|
10
|
+
"Portland, OR 97266; telephone 503-231-6179; facsimile 503-231-6195",
|
11
|
+
"<p>Optimal Oregon chub habitat provides 1 square meter (11 square feet) of aquatic surface area per adult, at depths between 0.5 m (1.6 ft) to 2 m (6.6 ft) (Scheerer 2008b).</p>"
|
12
|
+
]
|
13
|
+
end
|
14
|
+
|
15
|
+
it "returns no regions" do
|
16
|
+
@texts.each do |text|
|
17
|
+
RegionExtractor.new(text).regions.should == []
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
it "does not modify the text" do
|
22
|
+
@texts.each do |text|
|
23
|
+
RegionExtractor.new(text).resulting_text.should == text
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
context "with one simple region" do
|
29
|
+
before(:each) do
|
30
|
+
@extractor = RegionExtractor.new("Land bounded by the following UTM Zone 10, NAD83 coordinates (E,N): 557923, 4838857; 557919, 4838854; 557919, 4838854;")
|
31
|
+
end
|
32
|
+
|
33
|
+
it "finds the correct number of regions" do
|
34
|
+
@extractor.regions.size.should == 1
|
35
|
+
end
|
36
|
+
|
37
|
+
it "the region has the correct number of points" do
|
38
|
+
@extractor.regions.first.points.size.should == 3
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should determine the correct zone" do
|
42
|
+
@extractor.regions.first.zone.should == "10"
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
46
|
+
|
47
|
+
context "with more complex regions" do
|
48
|
+
before(:each) do
|
49
|
+
@extractor = RegionExtractor.new("<p>Unit 1A consists of boundary points with the following coordinates in UTM Zone 4, with the units in meters, using North American Datum of 1983 (Nad83):</p>
|
50
|
+
<p>(A) 451377, 2420941; 451318, 2421296; 451365, 2421383; 451432, 2421109; 451596, 2421040; 451959, 2421072.</p><p>(ii) Follow the approximate coordinates: 457583, 2422071; 457631, 2422040; 457702, 2421952; 457543, 2421778; 457490, 2421812; 457400, 2421778; 457352, 2421693; 457380, 2421601.</p>")
|
51
|
+
end
|
52
|
+
|
53
|
+
it "finds the correct number of regions" do
|
54
|
+
@extractor.regions.size.should == 2
|
55
|
+
end
|
56
|
+
|
57
|
+
it "the regions have the correct number of points" do
|
58
|
+
@extractor.regions[0].points.size.should == 6
|
59
|
+
@extractor.regions[1].points.size.should == 8
|
60
|
+
end
|
61
|
+
|
62
|
+
it "should determine the correct zone" do
|
63
|
+
@extractor.regions[0].zone.should == "4"
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
context "with regions to exclude" do
|
68
|
+
before(:each) do
|
69
|
+
@extractor = RegionExtractor.new("<p>UTM zone 4 451377, 2420941; 451318, 2421296; 451365, 2421383; 451432, 2421109 excluding land bound by 457490, 2421812; 457400, 2421778; 457352, 2421693") do |str, region, i|
|
70
|
+
"#{str}[POST]"
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
it "should find the right number of regions" do
|
75
|
+
@extractor.regions.size.should == 1
|
76
|
+
end
|
77
|
+
|
78
|
+
it "should not overwrite the exclude" do
|
79
|
+
@extractor.resulting_text.should == "<p>UTM zone 4 451377, 2420941; 451318, 2421296; 451365, 2421383; 451432, 2421109[POST] excluding land bound by 457490, 2421812; 457400, 2421778; 457352, 2421693"
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
context "with a block" do
|
84
|
+
it "puts a replacement in for each region" do
|
85
|
+
extractor = RegionExtractor.new("UTM Zone 10 557923, 4838857; 557919, 4838854; 557919, 4838854. Then 457631, 2421540; 457678, 2421675; 457766, 2421821; 457637, 2421453.") do |str, region, i|
|
86
|
+
"#{str}[i=#{i}; points=#{region.points.size}]"
|
87
|
+
end
|
88
|
+
extractor.resulting_text.should == "UTM Zone 10 557923, 4838857; 557919, 4838854; 557919, 4838854[i=0; points=3]. Then 457631, 2421540; 457678, 2421675; 457766, 2421821; 457637, 2421453[i=1; points=4]."
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
# (ii) Starting on the coastline at approximately coordinates of: 458997, 2422152; follow: 458345, 2422341; 458686, 2422405; 458786, 2422373;458934, 2422253; 459001, 2422151; 458997, 2422152; 457589, 2420990; 457575, 2420975; 457511, 2420984; 457631, 2421127; 457738, 2421168; 457900, 2421206; 458023, 2421343; 458023, 2421417; 457895, 2421435; 457803, 2421394; 457686, 2421405; 457637, 2421453; 457631, 2421540; 457678, 2421675; 457766, 2421821; 457908, 2421944; 458069, 2421867; 458216, 2421849; 458244, 2421886; 458253, 2421996; 458235, 2422079; 458299, 2422272; 458345, 2422341; 457589, 2420990; to approximately: 457590, 2420991 (coastline); follow coastline to the approximate coordinates of: 458494, 2421794; then follow: 458494, 2421795; 458495, 2421795; 458502, 2421802, 458492, 2421904; 458483, 2421987; 458566, 2422060; 458559, 2422190; 458630, 2422263; 458718, 2422262; 458805, 2422159; 458777, 2422115; 458686, 2422119; 458658, 2422060; 458667, 2421987; 458702, 2421920; to the coastline, approximately at: 458702, 2421919; follow coastline to beginning point: 458997, 2422152.
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--color
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,103 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: region_extractor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
version: 0.0.1
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Andrew Carpenter
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-06-12 00:00:00 -07:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rspec
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 1
|
29
|
+
- 2
|
30
|
+
- 9
|
31
|
+
version: 1.2.9
|
32
|
+
type: :development
|
33
|
+
version_requirements: *id001
|
34
|
+
- !ruby/object:Gem::Dependency
|
35
|
+
name: proj4rb
|
36
|
+
prerelease: false
|
37
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
segments:
|
42
|
+
- 0
|
43
|
+
- 3
|
44
|
+
- 1
|
45
|
+
version: 0.3.1
|
46
|
+
type: :runtime
|
47
|
+
version_requirements: *id002
|
48
|
+
description: Attempts to extract geographic regions mentioned in txt/html documents.
|
49
|
+
email: andrew.main@gmail.com
|
50
|
+
executables: []
|
51
|
+
|
52
|
+
extensions: []
|
53
|
+
|
54
|
+
extra_rdoc_files:
|
55
|
+
- LICENSE
|
56
|
+
- README.rdoc
|
57
|
+
files:
|
58
|
+
- .document
|
59
|
+
- .gitignore
|
60
|
+
- LICENSE
|
61
|
+
- README.rdoc
|
62
|
+
- Rakefile
|
63
|
+
- VERSION
|
64
|
+
- lib/region_extractor.rb
|
65
|
+
- lib/region_extractor/point.rb
|
66
|
+
- lib/region_extractor/region.rb
|
67
|
+
- region_extractor.gemspec
|
68
|
+
- spec/region_extractor_spec.rb
|
69
|
+
- spec/spec.opts
|
70
|
+
- spec/spec_helper.rb
|
71
|
+
has_rdoc: true
|
72
|
+
homepage: http://github.com/andrewcarpenter/region_extractor
|
73
|
+
licenses: []
|
74
|
+
|
75
|
+
post_install_message:
|
76
|
+
rdoc_options:
|
77
|
+
- --charset=UTF-8
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
segments:
|
85
|
+
- 0
|
86
|
+
version: "0"
|
87
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - ">="
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
segments:
|
92
|
+
- 0
|
93
|
+
version: "0"
|
94
|
+
requirements: []
|
95
|
+
|
96
|
+
rubyforge_project:
|
97
|
+
rubygems_version: 1.3.6
|
98
|
+
signing_key:
|
99
|
+
specification_version: 3
|
100
|
+
summary: Extract geographic regions from plain text
|
101
|
+
test_files:
|
102
|
+
- spec/region_extractor_spec.rb
|
103
|
+
- spec/spec_helper.rb
|