esri_shapefile 0.0.1

data/lib/esri_shapefile/models/shapes/polygon_m.rb

@@ -0,0 +1,52 @@
+require 'esri_shapefile/byte_model'
+
+module EsriShapefile
+  module Shapes
+    #
+    # A PolygonM consists of a number of rings. A ring is a closed,
+    # non-self-intersecting loop. A PolygonZ may contain multiple outer rings.
+    # The rings of a PolygonZ are referred to as its parts.
+    #
+    # The PolygonM structure is identical to the PolyLineM structure
+    #
+    class PolygonM
+      extend EsriShapefile::ByteModel
+
+      field :shape_type, position: 0,  type: :integer, byte_order: :little
+      field :x_min,      position: 4,  type: :double,  byte_order: :little
+      field :y_min,      position: 12, type: :double,  byte_order: :little
+      field :x_max,      position: 20, type: :double,  byte_order: :little
+      field :y_max,      position: 28, type: :double,  byte_order: :little
+
+      # The number of parts in the PolyLine
+      field :num_parts,  position: 36, type: :integer, byte_order: :little
+
+      # The total number of points for all parts.
+      field :num_points, position: 40, type: :integer, byte_order: :little
+
+      # An array of length num_parts. Stores, for each PolyLine, the index of
+      # its first point in the points array. Array indexes are with respect to 0.
+      field :parts,      position: 44, type: :integer, byte_order: :little, number: :num_parts
+
+      # An array of length NumPoints. The points for each part in the PolyLine
+      # are stored end to end. The points for Part 2 follow the points for
+      # Part 1, and so on. The parts array holds the array index of the starting
+      # point for each part. There is no delimiter in the points array between parts.
+      field :points,     position: :x, type: :point,   byte_order: :little, number: :num_points
+
+      # The minimum measure for the PolyLineZ
+      field :m_min,      position: :z,         type: :double,  byte_order: :little
+
+      # The maximum measure for the PolyLineZ
+      field :m_max,      position: :z_plus_8,  type: :double,  byte_order: :little
+
+      # An array of length num_points. The measures for each part in the
+      # PolyLineZ are stored end to end. The measures for Part 2 follow the
+      # measures for Part 1, and so on. The parts array holds the array index of
+      # the starting measure for each part. There is no delimited in the measure
+      # array between parts.
+      field :m_array,    position: :z_plus_16, type: :double,  byte_order: :little,  number: :num_points
+    end
+  end
+end
+

data/lib/esri_shapefile/models/shapes/polygon_z.rb

@@ -0,0 +1,65 @@
+require 'esri_shapefile/byte_model'
+
+module EsriShapefile
+  module Shapes
+    #
+    # A PolygonZ consists of a number of rings. A ring is a closed,
+    # non-self-intersecting loop. A PolygonZ may contain multiple outer rings.
+    # The rings of a PolygonZ are referred to as its parts.
+    #
+    # The PolygonZ structure is identical to the PolyLineZ structure
+    #
+    class PolygonZ
+      extend EsriShapefile::ByteModel
+
+      field :shape_type, position: 0,  type: :integer, byte_order: :little
+      field :x_min,      position: 4,  type: :double,  byte_order: :little
+      field :y_min,      position: 12, type: :double,  byte_order: :little
+      field :x_max,      position: 20, type: :double,  byte_order: :little
+      field :y_max,      position: 28, type: :double,  byte_order: :little
+
+      # The number of parts in the PolyLine
+      field :num_parts,  position: 36, type: :integer, byte_order: :little
+
+      # The total number of points for all parts.
+      field :num_points, position: 40, type: :integer, byte_order: :little
+
+      # An array of length num_parts. Stores, for each PolyLine, the index of
+      # its first point in the points array. Array indexes are with respect to 0.
+      field :parts,      position: 44, type: :integer, byte_order: :little, number: :num_parts
+
+      # An array of length NumPoints. The points for each part in the PolyLine
+      # are stored end to end. The points for Part 2 follow the points for
+      # Part 1, and so on. The parts array holds the array index of the starting
+      # point for each part. There is no delimiter in the points array between parts.
+      field :points,     position: :x, type: :point,   byte_order: :little, number: :num_points
+
+      # The minimum Z value for the PolyLineZ
+      field :z_min,      position: :y,         type: :double,  byte_order: :little
+
+      # The maximum Z value for the PoliyLineZ
+      field :z_max,      position: :y_plus_8,  type: :double,  byte_order: :little
+
+      # An array of length num_points. the Z values for each part in the
+      # PolyLineZ are stored end to end. The Z values for Part 2 follow the Z
+      # values for Part 1, and so on. The parts array holds the array index of
+      # the starting point for each part. There is no delimited in the Z array
+      # between parts.
+      field :z_array,    position: :y_plus_16, type: :double,  byte_order: :little,  number: :num_points
+
+      # The minimum measure for the PolyLineZ
+      field :m_min,      position: :z,         type: :double,  byte_order: :little
+
+      # The maximum measure for the PolyLineZ
+      field :m_max,      position: :z_plus_8,  type: :double,  byte_order: :little
+
+      # An array of length num_points. The measures for each part in the
+      # PolyLineZ are stored end to end. The measures for Part 2 follow the
+      # measures for Part 1, and so on. The parts array holds the array index of
+      # the starting measure for each part. There is no delimited in the measure
+      # array between parts.
+      field :m_array,    position: :z_plus_16, type: :double,  byte_order: :little,  number: :num_points
+    end
+  end
+end
+

data/lib/esri_shapefile/models/shapes.rb

@@ -0,0 +1,33 @@
+module EsriShapefile
+  module Shapes
+
+    # Shape types not specified below (2, 4, 6, etc., and up to 33) are
+    # reserved for future use
+    SHAPES = {
+      0  => Shapes::Null,
+      1  => Shapes::Point,
+      3  => Shapes::PolyLine,
+      5  => Shapes::Polygon,
+      8  => Shapes::MultiPoint,
+      11 => Shapes::PointZ,
+      13 => Shapes::PolyLineZ,
+      15 => Shapes::PolygonZ,
+      18 => Shapes::MultiPointZ,
+      21 => Shapes::PointM,
+      23 => Shapes::PolyLineM,
+      25 => Shapes::PolygonM,
+      28 => Shapes::MultiPointM,
+      31 => Shapes::MultiPatch,
+    }
+
+    def self.find_by_type(shape_type)
+      SHAPES.fetch(shape_type)
+    end
+
+    def self.find_by_bytes(bytes)
+      shape_type = bytes.unpack('l<').first
+      find_by_type(shape_type)
+    end
+
+  end
+end

data/lib/esri_shapefile/reader.rb

@@ -0,0 +1,44 @@
+module EsriShapefile
+  class Reader
+
+    MAIN_FILE_HEADER_BYTESIZE = 100
+    RECORD_HEADER_BYTESIZE = 8
+
+    attr_reader :main_file_header
+
+    def initialize(path_to_shapefile)
+      @path_to_shapefile = path_to_shapefile
+      @main_file_header = parse_main_file_header
+    end
+
+    def each_record
+      File.open(@path_to_shapefile) do |file|
+        file.pos = MAIN_FILE_HEADER_BYTESIZE
+
+        (0..Float::INFINITY).lazy.reduce(file.pos) do |current_offset, number|
+          break if current_offset >= main_file_header.file_length_bytes
+
+          record_header_bytes = file.read(RECORD_HEADER_BYTESIZE)
+          record_header = RecordHeader.from_bytes(record_header_bytes)
+
+          shape_bytes = file.read(record_header.content_length_bytes)
+          shape_class = Shapes.find_by_bytes(shape_bytes)
+          shape = shape_class.from_bytes(shape_bytes)
+
+          yield record_header, shape
+
+          file.pos
+        end
+      end
+    end
+
+    private
+
+    def parse_main_file_header
+      main_file_header_bytes = File.binread(@path_to_shapefile, 100, 0)
+      MainFileHeader.from_bytes(main_file_header_bytes)
+    end
+
+  end
+end
+

data/lib/esri_shapefile/version.rb

@@ -0,0 +1,3 @@
+module EsriShapefile
+  VERSION = "0.0.1"
+end

data/lib/esri_shapefile.rb

@@ -0,0 +1,29 @@
+require "esri_shapefile/version"
+require "esri_shapefile/byte_model"
+require "esri_shapefile/byte_model/field"
+
+require "esri_shapefile/models/shapes/null"
+require "esri_shapefile/models/shapes/point"
+require "esri_shapefile/models/shapes/point_m"
+require "esri_shapefile/models/shapes/point_z"
+require "esri_shapefile/models/shapes/multi_point"
+require "esri_shapefile/models/shapes/multi_point_m"
+require "esri_shapefile/models/shapes/multi_point_z"
+require "esri_shapefile/models/shapes/poly_line"
+require "esri_shapefile/models/shapes/poly_line_m"
+require "esri_shapefile/models/shapes/poly_line_z"
+require "esri_shapefile/models/shapes/polygon"
+require "esri_shapefile/models/shapes/polygon_m"
+require "esri_shapefile/models/shapes/polygon_z"
+require "esri_shapefile/models/shapes/multi_patch"
+require "esri_shapefile/models/shapes"
+
+require "esri_shapefile/models/main_file_header"
+require "esri_shapefile/models/record_header"
+
+require "esri_shapefile/reader"
+
+module EsriShapefile
+  # Your code goes here...
+end
+

data/spec/esri_shapefile/field_spec.rb

@@ -0,0 +1,95 @@
+require 'spec_helper'
+
+module EsriShapefile
+  module ByteModel
+    describe Field do
+
+      describe "type" do
+        describe "integer" do
+          it "has a bytesize of 4" do
+            integer_field = Field.new(:integer_field, type: :integer, byte_order: :little, position: 0)
+            expect(integer_field.bytesize).to eql(4)
+          end
+
+          it "correctly identifies the unpack format for the little byte order" do
+            integer_field = Field.new(:integer_field, type: :integer, byte_order: :little, position: 0)
+            expect(integer_field.unpack_format).to eql('l<1')
+          end
+
+          it "correctly identifies the unpack format for the big byte order" do
+            integer_field = Field.new(:integer_field, type: :integer, byte_order: :big, position: 0)
+            expect(integer_field.unpack_format).to eql('l>1')
+          end
+        end
+
+        describe "double" do
+          it "has a bytesize of 8" do
+            integer_field = Field.new(:integer_field, type: :double, byte_order: :little, position: 0)
+            expect(integer_field.bytesize).to eql(8)
+          end
+
+          it "correctly identifies the unpack format for the little byte order" do
+            integer_field = Field.new(:integer_field, type: :double, byte_order: :little, position: 0)
+            expect(integer_field.unpack_format).to eql('E1')
+          end
+
+          it "correctly identifies the unpack format for the big byte order" do
+            integer_field = Field.new(:integer_field, type: :double, byte_order: :big, position: 0)
+            expect(integer_field.unpack_format).to eql('G1')
+          end
+        end
+
+        describe "point" do
+          it "has a bytesize of 16" do
+            integer_field = Field.new(:integer_field, type: :point, byte_order: :little, position: 0)
+            expect(integer_field.bytesize).to eql(16)
+          end
+
+          it "correctly identifies the unpack format for the little byte order" do
+            integer_field = Field.new(:integer_field, type: :point, byte_order: :little, position: 0)
+            expect(integer_field.unpack_format).to eql('E2')
+          end
+
+          it "correctly identifies the unpack format for the big byte order" do
+            integer_field = Field.new(:integer_field, type: :point, byte_order: :big, position: 0)
+            expect(integer_field.unpack_format).to eql('G2')
+          end
+        end
+      end
+
+      describe "list" do
+        it "is a list when a number is provided" do
+          field = Field.new(:field, number: 0, type: :point, byte_order: :big, position: 0)
+          expect(field).to be_a_list
+        end
+
+        it "is NOT a list when a number is NOT provided" do
+          field = Field.new(:field, type: :point, byte_order: :big, position: 0)
+          expect(field).to_not be_a_list
+        end
+      end
+
+      describe "number attribute" do
+        it "is optional" do
+          field = Field.new(:field_without_number, type: :double, byte_order: :little, position: 0)
+          expect(field.number).to eql(1)
+          expect(field).to_not be_number_depends_on_field
+        end
+
+        it "can be an integer" do
+          field = Field.new(:field_with_number, number: 42, type: :double, byte_order: :little, position: 0)
+          expect(field.number).to eql(42)
+          expect(field).to_not be_number_depends_on_field
+        end
+
+        it "can depend upon the value of another field" do
+          field = Field.new(:field_with_depended_number, number: :num_foo, type: :double, byte_order: :little, position: 0)
+          expect(field.number).to eql(:num_foo)
+          expect(field).to be_number_depends_on_field
+        end
+      end
+
+    end
+  end
+
+end

data/spec/esri_shapefile/model_spec.rb

@@ -0,0 +1,26 @@
+require 'spec_helper'
+
+describe EsriShapefile::ByteModel do
+
+  describe "declaring fields" do
+    let(:example_model) do
+      Class.new do
+        extend EsriShapefile::ByteModel
+        field :foo, position: 0, type: :integer, byte_order: :little
+      end
+    end
+
+    it "allows them to be accessed" do
+      model = example_model.new
+      model.foo = "Bar"
+
+      expect(model.foo).to eql("Bar")
+    end
+
+    it "adds them to the list of fields" do
+      expect(example_model.fields.size).to eql(1)
+      expect(example_model.fields.first.name).to eql(:foo)
+    end
+  end
+end
+

data/spec/esri_shapefile/models/main_file_header_spec.rb

@@ -0,0 +1,72 @@
+require 'spec_helper'
+
+module EsriShapefile
+  describe MainFileHeader do
+
+    let(:main_file_header_bytes) do
+      bytes = "\x00\x00'\n\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"
+      bytes << "\x00\x00\x00\x00\x00\x00\x00\x01|\xD2t\xE8\x03\x00\x00\x05\x00"
+      bytes << "\x00\x00\xFA\xD6`\x02\xB7df\xC0\x80\xEC\xBCA?\xE92@\x12\x9A\xE3N"
+      bytes << "\xE9xf@\xF2\xB4\x02\xD3\xE8\xD8Q@\x00\x00\x00\x00\x00\x00\x00\x00"
+      bytes << "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"
+      bytes << "\x00\x00\x00\x00\x00\x00\x00\x00"
+      bytes
+    end
+
+    describe "from_bytes" do
+      let(:main_file_header) do
+        MainFileHeader.from_bytes(main_file_header_bytes)
+      end
+
+      it "sets the file code" do
+        expect(main_file_header.file_code).to eql(9994)
+      end
+
+      it "sets the file length" do
+        expect(main_file_header.file_length).to eql(24957556)
+      end
+
+      it "sets the version" do
+        expect(main_file_header.version).to eql(1000)
+      end
+
+      it "sets the shape type" do
+        expect(main_file_header.shape_type).to eql(5)
+      end
+
+      it "sets the x_min" do
+        expect(main_file_header.x_min).to eql(-179.1473400012399)
+      end
+
+      it "sets the y_min" do
+        expect(main_file_header.y_min).to eql(18.911121472000104)
+      end
+
+      it "sets the x_max" do
+        expect(main_file_header.x_max).to eql(179.7784800000523)
+      end
+
+      it "sets the y_max" do
+        expect(main_file_header.y_max).to eql(71.38921046509111)
+      end
+
+      it "sets the z_min" do
+        expect(main_file_header.z_min).to eql(0.0)
+      end
+
+      it "sets the z_max" do
+        expect(main_file_header.z_min).to eql(0.0)
+      end
+
+      it "sets the m_min" do
+        expect(main_file_header.m_min).to eql(0.0)
+      end
+
+      it "sets the m_max" do
+        expect(main_file_header.m_max).to eql(0.0)
+      end
+    end
+
+  end
+end
+

data/spec/esri_shapefile/models/record_header_spec.rb

@@ -0,0 +1,26 @@
+require 'spec_helper'
+
+module EsriShapefile
+  describe RecordHeader do
+
+    let(:record_header_bytes) do
+      "\x00\x00\x00\x01\x00\x00\x00\x04"
+    end
+
+    describe "from_bytes" do
+      let(:record_header) do
+        RecordHeader.from_bytes(record_header_bytes)
+      end
+
+      it "sets the record number" do
+        expect(record_header.record_number).to eql(1)
+      end
+
+      it "sets the content length" do
+        expect(record_header.content_length).to eql(4)
+      end
+    end
+
+  end
+end
+

data/spec/esri_shapefile/models/shapes/point_spec.rb

@@ -0,0 +1,24 @@
+module EsriShapefile
+  module Shapes
+    describe Point do
+
+      describe "from_bytes" do
+        let(:point_bytes) { [1, 42, 57].pack('l<EE') }
+        let(:point) { Point.from_bytes(point_bytes) }
+
+        it "sets the shape_type" do
+          expect(point.shape_type).to eql(1)
+        end
+
+        it "sets the x coordinate" do
+          expect(point.x).to eql(42.0)
+        end
+
+        it "sets the y coordinate" do
+          expect(point.y).to eql(57.0)
+        end
+      end
+    end
+  end
+end
+

data/spec/spec_helper.rb

@@ -0,0 +1,105 @@
+require 'esri_shapefile'
+
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+  # This option will default to `:apply_to_host_groups` in RSpec 4 (and will
+  # have no way to turn it off -- the option exists only for backwards
+  # compatibility in RSpec 3). It causes shared context metadata to be
+  # inherited by the metadata hash of host groups and examples, rather than
+  # triggering implicit auto-inclusion in groups with matching metadata.
+  config.shared_context_metadata_behavior = :apply_to_host_groups
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # This allows you to limit a spec run to individual examples or groups
+  # you care about by tagging them with `:focus` metadata. When nothing
+  # is tagged with `:focus`, all examples get run. RSpec also provides
+  # aliases for `it`, `describe`, and `context` that include `:focus`
+  # metadata: `fit`, `fdescribe` and `fcontext`, respectively.
+  config.filter_run_when_matching :focus
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://rspec.info/blog/2012/06/rspecs-new-expectation-syntax/
+  #   - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://rspec.info/blog/2014/05/notable-changes-in-rspec-3/#zero-monkey-patching-mode
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end