bson 4.1.1 → 5.2.0

data/spec/spec_tests/common_driver_spec.rb

@@ -0,0 +1,84 @@
+# rubocop:todo all
+require 'spec_helper'
+require 'runners/common_driver'
+
+describe 'Driver common bson tests' do
+
+  specs = DRIVER_COMMON_BSON_TESTS.map { |file| BSON::CommonDriver::Spec.new(file) }
+
+  specs.each do |spec|
+
+    context(spec.description) do
+
+      spec.valid_tests.each do |test|
+
+        context(test.description << ' - ' << test.string) do
+
+          it 'decodes the subject and displays as the correct string' do
+            expect(test.object.to_s).to eq(test.expected_to_string)
+          end
+
+          it 'encodes the decoded object correctly (roundtrips)' do
+            expect(test.reencoded_hex).to eq(test.subject.upcase)
+          end
+
+          it 'creates the correct object from extended json', if: test.from_ext_json? do
+            expect(test.from_json_string).to eq(test.object)
+          end
+
+          it 'serializes to a string', if: test.to_ext_json? do
+            expect(test.document_as_extended_json).to eq(test.ext_json)
+          end
+
+          it 'creates the correct extended json document from the decoded object', if: test.to_ext_json? do
+            expect(test.document_as_extended_json).to eq(test.ext_json)
+          end
+
+          it 'parses the string value to the same value as the decoded document', if: test.from_string? do
+            expect(BSON::Decimal128.new(test.string)).to eq(test.object)
+          end
+
+          it 'parses the #to_s (match_string) value to the same value as the decoded document', if: test.match_string do
+            expect(BSON::Decimal128.new(test.match_string)).to eq(test.object)
+          end
+
+          it 'creates the correct object from a non canonical string and then prints to the correct string', if: test.match_string do
+            expect(BSON::Decimal128.new(test.string).to_s).to eq(test.match_string)
+          end
+
+          it 'can be converted to a native type' do
+            expect(test.native_type_conversion).to be_a(test.native_type)
+          end
+        end
+      end
+
+      spec.invalid_tests.each do |test|
+
+        context(test.description << " - " << test.subject ) do
+
+          let(:error) do
+            ex = nil
+            begin
+              test.parse_invalid_string
+            rescue => e
+              ex = e
+            end
+            ex
+          end
+
+          let(:valid_errors) do
+            [
+              BSON::Error::InvalidDecimal128String,
+              BSON::Error::InvalidDecimal128Range,
+              BSON::Error::UnrepresentablePrecision,
+            ]
+          end
+
+          it 'raises an exception when parsing' do
+            expect(error.class).to satisfy { |e| valid_errors.include?(e) }
+          end
+        end
+      end
+    end
+  end
+end

data/spec/spec_tests/corpus_legacy_spec.rb

@@ -0,0 +1,72 @@
+# rubocop:todo all
+require 'spec_helper'
+require 'runners/corpus_legacy'
+
+describe 'Driver BSON Corpus Legacy spec tests' do
+
+  BSON_CORPUS_LEGACY_TESTS.each do |path|
+    basename = File.basename(path)
+    # All of the tests in the failures subdir are failing apparently
+    #basename = path.sub(/.*corpus-tests\//, '')
+
+    spec = BSON::CorpusLegacy::Spec.new(path)
+
+    context("(#{basename}): #{spec.description}") do
+
+      spec.valid_tests.each do |test|
+
+        context("VALID CASE: #{test.description}") do
+
+          it 'roundtrips the given bson correctly' do
+            expect(test.reencoded_bson).to eq(test.correct_bson)
+          end
+
+          context 'when the canonical bson is roundtripped', if: test.test_canonical_bson? do
+
+            it 'encodes the canonical bson correctly' do
+              expect(test.reencoded_canonical_bson).to eq(test.correct_bson)
+            end
+          end
+
+          context 'when the document can be represented as extended json', if: test.test_extjson? do
+
+            it 'decodes from the given bson, then encodes the document as extended json correctly' do
+              expect(test.extjson_from_bson).to eq(test.correct_extjson)
+              expect(test.extjson_from_bson[test.test_key]).to eq(test.correct_extjson[test.test_key])
+            end
+
+            it 'decodes from extended json, then encodes the document as extended json correctly' do
+              expect(test.extjson_from_encoded_extjson).to eq(test.correct_extjson)
+              expect(test.extjson_from_encoded_extjson[test.test_key]).to eq(test.correct_extjson[test.test_key])
+            end
+
+            context 'when the canonical bson can be represented as extended json', if: (test.test_canonical_bson? && test.test_extjson?) do
+
+              it 'encodes the canonical bson correctly as extended json' do
+                expect(test.extjson_from_canonical_bson).to eq(test.correct_extjson)
+                expect(test.extjson_from_canonical_bson[test.test_key]).to eq(test.correct_extjson[test.test_key])
+              end
+            end
+          end
+        end
+      end
+
+      spec.invalid_tests.each do |test|
+
+        context("INVALID CASE: #{test.description}") do
+
+          let(:error) do
+            begin; test.reencoded_bson; false; rescue => e; e; end
+          end
+
+          it 'raises an error' do
+            skip 'This test case does not raise and error but should' unless error
+            expect do
+              test.reencoded_bson
+            end.to raise_error(error.class)
+          end
+        end
+      end
+    end
+  end
+end

data/spec/spec_tests/corpus_spec.rb

@@ -0,0 +1,134 @@
+# rubocop:todo all
+require 'spec_helper'
+require 'runners/corpus'
+
+describe 'BSON Corpus spec tests' do
+
+  BSON_CORPUS_TESTS.each do |path|
+    basename = File.basename(path)
+    # All of the tests in the failures subdir are failing apparently
+    #basename = path.sub(/.*corpus-tests\//, '')
+
+    spec = BSON::Corpus::Spec.new(path)
+
+    context("(#{basename}): #{spec.description}") do
+
+      spec.valid_tests&.each do |test|
+
+        context("valid: #{test.description}") do
+
+          let(:decoded_canonical_bson) do
+            BSON::Document.from_bson(BSON::ByteBuffer.new(test.canonical_bson), mode: :bson)
+          end
+
+          it 'round-trips canonical bson' do
+            decoded_canonical_bson.to_bson.to_s.should == test.canonical_bson
+          end
+
+=begin
+          it 'converts bson to canonical extended json' do
+            pending
+            raise NotImplementedError
+          end
+=end
+
+          it 'converts bson to canonical extended json' do
+            decoded_canonical_bson.as_extended_json.should == test.canonical_extjson_doc
+          end
+
+          if test.relaxed_extjson
+            it 'converts bson to relaxed extended json' do
+              decoded_canonical_bson.as_extended_json(mode: :relaxed).should == test.relaxed_extjson_doc
+            end
+
+            let(:parsed_relaxed_extjson) do
+              BSON::ExtJSON.parse_obj(test.relaxed_extjson_doc, mode: :bson)
+            end
+
+            let(:round_tripped_relaxed_extjson) do
+              parsed_relaxed_extjson.as_extended_json(mode: :relaxed)
+            end
+
+            # Relaxed extended json may parse into something other than the
+            # canonical bson. For example, relaxed extjson representation for
+            # a small int64 is a number that would serialize to an int32.
+            # But round-tripping extended json back to extjson should produce
+            # the same representation we started with.
+            it 'round-trips relaxed extended json' do
+              round_tripped_relaxed_extjson.should == test.relaxed_extjson_doc
+            end
+          end
+
+          if test.degenerate_bson
+
+            let(:decoded_degenerate_bson) do
+              BSON::Document.from_bson(BSON::ByteBuffer.new(test.degenerate_bson), mode: :relaxed)
+            end
+
+            it 'round-trips degenerate bson to canonical bson' do
+              decoded_degenerate_bson.to_bson.to_s.should == test.canonical_bson
+            end
+          end
+
+          let(:parsed_canonical_extjson) do
+            BSON::ExtJSON.parse_obj(test.canonical_extjson_doc, mode: :bson)
+          end
+
+          unless test.lossy?
+            it 'converts canonical extended json to bson' do
+              parsed_canonical_extjson.to_bson.to_s.should == test.canonical_bson
+            end
+          end
+
+        end
+      end
+
+      spec.decode_error_tests&.each do |test|
+
+        context("decode error: #{test.description}") do
+
+          let(:decoded_bson) do
+            BSON::Document.from_bson(BSON::ByteBuffer.new(test.bson), mode: :bson)
+          end
+
+          # Until bson-ruby gets an exception hierarchy, we can only rescue
+          # the basic Exception here.
+          # https://jira.mongodb.org/browse/RUBY-1806
+          it 'raises an exception' do
+            expect do
+              decoded_bson
+            end.to raise_error(Exception)
+          end
+        end
+      end
+
+      spec.parse_error_tests&.each do |test|
+
+        context("parse error: #{test.description}") do
+
+          # As per:
+          #   https://github.com/mongodb/specifications/blob/e7ee829329400786e01279b4f37d4e440d1e9cfa/source/bson-corpus/bson-corpus.rst#decimal128-type-0x13
+          #
+          # Values under test must be parsed in a type-specific manner.
+          let(:parsed_value) do
+            case spec.bson_type
+            when BSON::Decimal128::BSON_TYPE
+              BSON::Decimal128.new(test.string)
+            else
+              BSON::ExtJSON.parse(test.string, mode: :bson)
+            end
+          end
+
+          # Until bson-ruby gets an exception hierarchy, we can only rescue
+          # the basic Exception here.
+          # https://jira.mongodb.org/browse/RUBY-1806
+          it 'raises an exception' do
+            expect do
+              parsed_value
+            end.to raise_error(Exception)
+          end
+        end
+      end
+    end
+  end
+end

data/spec/spec_tests/data/binary_vector/README.md

@@ -0,0 +1,61 @@
+# Testing Binary subtype 9: Vector
+
+The JSON files in this directory tree are platform-independent tests that drivers can use to prove their conformance to
+the specification.
+
+These tests focus on the roundtrip of the list of numbers as input/output, along with their data type and byte padding.
+
+Additional tests exist in `bson_corpus/tests/binary.json` but do not sufficiently test the end-to-end process of Vector
+to BSON. For this reason, drivers must create a bespoke test runner for the vector subtype.
+
+## Format
+
+The test data corpus consists of a JSON file for each data type (dtype). Each file contains a number of test cases,
+under the top-level key "tests". Each test case pertains to a single vector. The keys provide the specification of the
+vector. Valid cases also include the Canonical BSON format of a document {test_key: binary}. The "test_key" is common,
+and specified at the top level.
+
+#### Top level keys
+
+Each JSON file contains three top-level keys.
+
+- `description`: human-readable description of what is in the file
+- `test_key`: name used for key when encoding/decoding a BSON document containing the single BSON Binary for the test
+    case. Applies to *every* case.
+- `tests`: array of test case objects, each of which have the following keys. Valid cases will also contain additional
+    binary and json encoding values.
+
+#### Keys of individual tests cases
+
+- `description`: string describing the test.
+- `valid`: boolean indicating if the vector, dtype, and padding should be considered a valid input.
+- `vector`: (required if valid is true) list of numbers
+- `dtype_hex`: string defining the data type in hex (e.g. "0x10", "0x27")
+- `dtype_alias`: (optional) string defining the data dtype, perhaps as Enum.
+- `padding`: (optional) integer for byte padding. Defaults to 0.
+- `canonical_bson`: (required if valid is true) an (uppercase) big-endian hex representation of a BSON byte string.
+
+## Required tests
+
+#### To prove correct in a valid case (`valid: true`), one MUST
+
+- encode a document from the numeric values, dtype, and padding, along with the "test_key", and assert this matches the
+    canonical_bson string.
+- decode the canonical_bson into its binary form, and then assert that the numeric values, dtype, and padding all match
+    those provided in the JSON.
+
+Note: For floating point number types, exact numerical matches may not be possible. Drivers that natively support the
+floating-point type being tested (e.g., when testing float32 vector values in a driver that natively supports float32),
+MUST assert that the input float array is the same after encoding and decoding.
+
+#### To prove correct in an invalid case (`valid:false`), one MUST
+
+- if the vector field is present, raise an exception when attempting to encode a document from the numeric values,
+    dtype, and padding.
+- if the canonical_bson field is present, raise an exception when attempting to deserialize it into the corresponding
+    numeric values, as the field contains corrupted data.
+
+## FAQ
+
+- What MongoDB Server version does this apply to?
+    - Files in the "specifications" repository have no version scheme. They are not tied to a MongoDB server version.

data/spec/spec_tests/data/binary_vector/float32.json

@@ -0,0 +1,65 @@
+{
+  "description": "Tests of Binary subtype 9, Vectors, with dtype FLOAT32",
+  "test_key": "vector",
+  "tests": [
+    {
+      "description": "Simple Vector FLOAT32",
+      "valid": true,
+      "vector": [127.0, 7.0],
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "padding": 0,
+      "canonical_bson": "1C00000005766563746F72000A0000000927000000FE420000E04000"
+    },
+    {
+      "description": "Vector with decimals and negative value FLOAT32",
+      "valid": true,
+      "vector": [127.7, -7.7],
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "padding": 0,
+      "canonical_bson": "1C00000005766563746F72000A0000000927006666FF426666F6C000"
+    },
+    {
+      "description": "Empty Vector FLOAT32",
+      "valid": true,
+      "vector": [],
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "padding": 0,
+      "canonical_bson": "1400000005766563746F72000200000009270000"
+    },
+    {
+      "description": "Infinity Vector FLOAT32",
+      "valid": true,
+      "vector": [{"$numberDouble": "-Infinity"}, 0.0, {"$numberDouble": "Infinity"} ],
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "padding": 0,
+      "canonical_bson": "2000000005766563746F72000E000000092700000080FF000000000000807F00"
+    },
+    {
+      "description": "FLOAT32 with padding",
+      "valid": false,
+      "vector": [127.0, 7.0],
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "padding": 3,
+      "canonical_bson": "1C00000005766563746F72000A0000000927030000FE420000E04000"
+    },
+    {
+      "description": "Insufficient vector data with 3 bytes FLOAT32",
+      "valid": false,
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "canonical_bson": "1700000005766563746F7200050000000927002A2A2A00"
+    },
+    {
+      "description": "Insufficient vector data with 5 bytes FLOAT32",
+      "valid": false,
+      "dtype_hex": "0x27",
+      "dtype_alias": "FLOAT32",
+      "canonical_bson": "1900000005766563746F7200070000000927002A2A2A2A2A00"
+    }
+  ]
+}

data/spec/spec_tests/data/binary_vector/int8.json

@@ -0,0 +1,57 @@
+{
+  "description": "Tests of Binary subtype 9, Vectors, with dtype INT8",
+  "test_key": "vector",
+  "tests": [
+    {
+      "description": "Simple Vector INT8",
+      "valid": true,
+      "vector": [127, 7],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 0,
+      "canonical_bson": "1600000005766563746F7200040000000903007F0700"
+    },
+    {
+      "description": "Empty Vector INT8",
+      "valid": true,
+      "vector": [],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 0,
+      "canonical_bson": "1400000005766563746F72000200000009030000"
+    },
+    {
+      "description": "Overflow Vector INT8",
+      "valid": false,
+      "vector": [128],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 0
+    },
+    {
+      "description": "Underflow Vector INT8",
+      "valid": false,
+      "vector": [-129],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 0
+    },
+    {
+      "description": "INT8 with padding",
+      "valid": false,
+      "vector": [127, 7],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 3,
+      "canonical_bson": "1600000005766563746F7200040000000903037F0700"
+    },
+    {
+      "description": "INT8 with float inputs",
+      "valid": false,
+      "vector": [127.77, 7.77],
+      "dtype_hex": "0x03",
+      "dtype_alias": "INT8",
+      "padding": 0
+    }
+  ]
+}

data/spec/spec_tests/data/binary_vector/packed_bit.json

@@ -0,0 +1,83 @@
+{
+  "description": "Tests of Binary subtype 9, Vectors, with dtype PACKED_BIT",
+  "test_key": "vector",
+  "tests": [
+    {
+      "description": "Padding specified with no vector data PACKED_BIT",
+      "valid": false,
+      "vector": [],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 1,
+      "canonical_bson": "1400000005766563746F72000200000009100100"
+    },
+    {
+      "description": "Simple Vector PACKED_BIT",
+      "valid": true,
+      "vector": [127, 7],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 0,
+      "canonical_bson": "1600000005766563746F7200040000000910007F0700"
+    },
+    {
+      "description": "Empty Vector PACKED_BIT",
+      "valid": true,
+      "vector": [],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 0,
+      "canonical_bson": "1400000005766563746F72000200000009100000"
+    },
+    {
+      "description": "PACKED_BIT with padding",
+      "valid": true,
+      "vector": [127, 7],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 3,
+      "canonical_bson": "1600000005766563746F7200040000000910037F0700"
+    },
+    {
+      "description": "Overflow Vector PACKED_BIT",
+      "valid": false,
+      "vector": [256],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 0
+    },
+    {
+      "description": "Underflow Vector PACKED_BIT",
+      "valid": false,
+      "vector": [-1],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 0
+    },
+    {
+      "description": "Vector with float values PACKED_BIT",
+      "valid": false,
+      "vector": [127.5],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 0
+    },
+    {
+      "description": "Exceeding maximum padding PACKED_BIT",
+      "valid": false,
+      "vector": [1],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": 8,
+      "canonical_bson": "1500000005766563746F7200030000000910080100"
+    },
+    {
+      "description": "Negative padding PACKED_BIT",
+      "valid": false,
+      "vector": [1],
+      "dtype_hex": "0x10",
+      "dtype_alias": "PACKED_BIT",
+      "padding": -1
+    }
+  ]
+}

data/spec/spec_tests/data/corpus/README.md

@@ -0,0 +1,15 @@
+There are the following deliberate changes made to the corpus tests in Ruby:
+
+1. In double.js, Ruby appears to offer less precision than the spec tests
+demand:
+
+    irb(main):001:0> -1.23456789012345677E+18
+    => -1.2345678901234568e+18
+
+Because of this, -1.23456789012345677E+18 was changed to -1.2345678901234568e+18.
+The "e" was lowercased as well. Both the precision reduction and the lowercasing
+of "e" changes are also present in the Python driver, which appears to be
+affected by the same precision limitation.
+
+2. In datetime.js, the millisecond component of iso8601 serialization of
+timestamps is always present, even if it is zero.

data/spec/spec_tests/data/corpus/array.json

@@ -0,0 +1,49 @@
+{
+    "description": "Array",
+    "bson_type": "0x04",
+    "test_key": "a",
+    "valid": [
+        {
+            "description": "Empty",
+            "canonical_bson": "0D000000046100050000000000",
+            "canonical_extjson": "{\"a\" : []}"
+        },
+        {
+            "description": "Single Element Array",
+            "canonical_bson": "140000000461000C0000001030000A0000000000",
+            "canonical_extjson": "{\"a\" : [{\"$numberInt\": \"10\"}]}"
+        },
+        {
+            "description": "Single Element Array with index set incorrectly to empty string",
+            "degenerate_bson": "130000000461000B00000010000A0000000000",
+            "canonical_bson": "140000000461000C0000001030000A0000000000",
+            "canonical_extjson": "{\"a\" : [{\"$numberInt\": \"10\"}]}"
+        },
+        {
+            "description": "Single Element Array with index set incorrectly to ab",
+            "degenerate_bson": "150000000461000D000000106162000A0000000000",
+            "canonical_bson": "140000000461000C0000001030000A0000000000",
+            "canonical_extjson": "{\"a\" : [{\"$numberInt\": \"10\"}]}"
+        },
+        {
+            "description": "Multi Element Array with duplicate indexes",
+            "degenerate_bson": "1b000000046100130000001030000a000000103000140000000000",
+            "canonical_bson": "1b000000046100130000001030000a000000103100140000000000",
+            "canonical_extjson": "{\"a\" : [{\"$numberInt\": \"10\"}, {\"$numberInt\": \"20\"}]}"
+        }
+    ],
+    "decodeErrors": [
+        {
+            "description": "Array length too long: eats outer terminator",
+            "bson": "140000000461000D0000001030000A0000000000"
+        },
+        {
+            "description": "Array length too short: leaks terminator",
+            "bson": "140000000461000B0000001030000A0000000000"
+        },
+        {
+            "description": "Invalid Array: bad string length in field",
+            "bson": "1A00000004666F6F00100000000230000500000062617A000000"
+        }
+    ]
+}