datapipeline 2.0.0: Gem aus dem Projekt etl herausgelöst

This commit is contained in:
wkh
2026-10-08 15:30:02 +02:00
commit cce7b03ca9
56 changed files with 5205 additions and 0 deletions
+89
View File
@@ -0,0 +1,89 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
class CsvStorageTest < PipelineTest
include StorageContract
def contract_storage(dir, _purpose) = DataPipeline::CsvStorage.new(file: "#{dir}/data.csv")
def test_read_with_defaults
with_tmpdir do |dir|
File.write("#{dir}/in.csv", "a,b\n1,x\n2,\"\"\n")
assert_equal [{ 'a' => '1', 'b' => 'x' }, { 'a' => '2', 'b' => '' }], DataPipeline::CsvStorage.new(file: "#{dir}/in.csv").read
end
end
def test_read_without_header_uses_columns_or_index
with_tmpdir do |dir|
File.write("#{dir}/in.csv", "1|x\n2|y\n")
csv = { headers: false, col_sep: '|' }
assert_equal [{ 'id' => '1', 'txt' => 'x' }, { 'id' => '2', 'txt' => 'y' }],
DataPipeline::CsvStorage.new(file: "#{dir}/in.csv", columns: %w[id txt], csv:).read
assert_equal({ '0' => '1', '1' => 'x' }, DataPipeline::CsvStorage.new(file: "#{dir}/in.csv", csv:).read.first)
end
end
def test_read_streaming_with_block
with_tmpdir do |dir|
File.write("#{dir}/in.csv", "a\n1\n2\n")
rows = []
DataPipeline::CsvStorage.new(file: "#{dir}/in.csv").read { |row| rows << row }
assert_equal %w[1 2], rows.map { |r| r['a'] }
end
end
def test_defaults_are_merged
options = DataPipeline::CsvStorage.new(file: 'x', csv: { col_sep: ';' }).instance_variable_get(:@options)[:csv]
assert_equal ';', options[:col_sep]
assert options[:headers]
end
def test_file_is_required
error = assert_raises(ArgumentError) { DataPipeline::CsvStorage.new }
assert_includes error.message, 'file'
end
def test_write_without_csv_options
with_tmpdir do |dir|
DataPipeline::CsvStorage.new(file: "#{dir}/o.csv").write([{ 'a' => 1, 'b' => 2 }])
assert_equal "a,b\n1,2\n", File.read("#{dir}/o.csv")
end
end
def test_columns_fix_order_missing_fields_and_key_types
with_tmpdir do |dir|
DataPipeline::CsvStorage.new(file: "#{dir}/o.csv", columns: %w[a b c]).write([{ 'b' => 2, 'a' => 1 }, { c: 3, a: 4 }])
assert_equal "a,b,c\n1,2,\n4,,3\n", File.read("#{dir}/o.csv")
end
end
def test_empty_data
with_tmpdir do |dir|
DataPipeline::CsvStorage.new(file: "#{dir}/a.csv").write([])
DataPipeline::CsvStorage.new(file: "#{dir}/b.csv", columns: %w[a b]).write([])
assert_equal '', File.read("#{dir}/a.csv")
assert_equal "a,b\n", File.read("#{dir}/b.csv")
end
end
def test_write_row_and_close
with_tmpdir do |dir|
csv = DataPipeline::CsvStorage.new(file: "#{dir}/o.csv")
csv.write_row({ 'a' => 1 })
csv.write_row({ 'a' => 2 })
csv.close
assert_equal "a\n1\n2\n", File.read("#{dir}/o.csv")
end
end
# options of the CUDO exports: no header, pipe, no quotes, mixed record types and key types
def test_cudo_format_mixed_record_types
with_tmpdir do |dir|
rows = [{ SATYP: 'FIRC', LFDNR: 0 }, { 'satyp' => 'DOHD', 'belnr' => 'AR1', 'wwert' => nil },
{ 'satyp' => 'DOPS', 'dmbtr' => '1.50' }, { 'SATYPE' => 'LARC', 'SUMME' => '0000000002' }]
DataPipeline::CsvStorage.new(file: "#{dir}/c.ok", csv: { headers: false, col_sep: '|', quote_char: '', encoding: 'utf-8' })
.write(rows)
assert_equal "FIRC|0\nDOHD|AR1|\nDOPS|1.50\nLARC|0000000002\n", File.read("#{dir}/c.ok")
end
end
end
+57
View File
@@ -0,0 +1,57 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
class ExcelStorageTest < PipelineTest
include StorageContract
def contract_storage(dir, _purpose) = DataPipeline::ExcelStorage.new(file: "#{dir}/data.xlsx")
# an empty text is an empty cell in excel
def contract_rows(rows) = rows.map { |row| row.transform_values { |v| v == '' ? nil : v } }
def test_text_stays_text_numbers_and_dates_keep_type
with_tmpdir do |dir|
rows = [{ 'lfdnr' => '0000000001', 'betrag' => 1.5, 'menge' => 3, 'datum' => Date.new(2025, 11, 3), 'text' => '=1+1' }]
DataPipeline::ExcelStorage.new(file: "#{dir}/t.xlsx").write(rows)
row = DataPipeline::ExcelStorage.new(file: "#{dir}/t.xlsx").read.first
assert_equal '0000000001', row['lfdnr']
assert_in_delta 1.5, row['betrag']
assert_equal 3, row['menge'].to_i
assert_equal Date.new(2025, 11, 3), row['datum'].to_date
assert_equal '=1+1', row['text']
end
end
def test_columns_sheet_name_and_symbol_keys
with_tmpdir do |dir|
DataPipeline::ExcelStorage.new(file: "#{dir}/c.xlsx", sheet: 'Buchungen', columns: %w[b a])
.write([{ a: '1', b: '2' }, { 'b' => '4' }])
assert_equal [{ 'b' => '2', 'a' => '1' }, { 'b' => '4', 'a' => nil }],
DataPipeline::ExcelStorage.new(file: "#{dir}/c.xlsx", sheet: 'Buchungen').read
end
end
def test_without_header_and_skip_title_rows
with_tmpdir do |dir|
DataPipeline::ExcelStorage.new(file: "#{dir}/h.xlsx", headers: false).write([{ 'x' => 'Titel' }, { 'x' => 'Kopf' }, { 'x' => 'Wert' }])
assert_equal [{ 'name' => 'Titel' }, { 'name' => 'Kopf' }, { 'name' => 'Wert' }],
DataPipeline::ExcelStorage.new(file: "#{dir}/h.xlsx", headers: false, columns: %w[name]).read
assert_equal [{ 'Kopf' => 'Wert' }], DataPipeline::ExcelStorage.new(file: "#{dir}/h.xlsx", skip: 1).read
end
end
def test_empty_rows_are_skipped_and_short_name
with_tmpdir do |dir|
DataPipeline.new do
logger PipelineHelper::QUIET
read MemoryStorage.new(rows: [{ 'a' => '1' }, { 'a' => nil }, { 'a' => '3' }])
write container(:xlsx, file: "#{dir}/e.xlsx")
end.run
assert_equal [{ 'a' => '1' }, { 'a' => '3' }], DataPipeline::ExcelStorage.new(file: "#{dir}/e.xlsx").read
end
end
def test_file_required
assert_raises(ArgumentError) { DataPipeline::ExcelStorage.new }
end
end
+56
View File
@@ -0,0 +1,56 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
class JsonArrayStorageTest < PipelineTest
include StorageContract
def contract_storage(dir, _purpose) = DataPipeline::JsonStorage.new(file: "#{dir}/data.json")
def test_streamed_array_is_valid_json
with_tmpdir do |dir|
json = DataPipeline::JsonStorage.new(file: "#{dir}/a.json")
json.write_row({ 'a' => 1 })
json.write_row({ 'a' => 2 })
json.close
assert_equal [{ 'a' => 1 }, { 'a' => 2 }], JSON.parse(File.read("#{dir}/a.json"))
end
end
def test_root_path_and_pretty
with_tmpdir do |dir|
File.write("#{dir}/api.json", JSON.generate('data' => { 'items' => [{ 'id' => 1 }] }))
assert_equal [{ 'id' => 1 }], DataPipeline::JsonStorage.new(file: "#{dir}/api.json", root: 'data.items').read
DataPipeline::JsonStorage.new(file: "#{dir}/p.json", pretty: true).write([{ 'a' => 1 }])
assert_includes File.read("#{dir}/p.json"), "\n"
end
end
def test_single_object_is_one_row_and_scalar_raises
with_tmpdir do |dir|
File.write("#{dir}/o.json", '{"a":1}')
assert_equal [{ 'a' => 1 }], DataPipeline::JsonStorage.new(file: "#{dir}/o.json").read
File.write("#{dir}/s.json", '42')
assert_raises(ArgumentError) { DataPipeline::JsonStorage.new(file: "#{dir}/s.json").read }
end
end
def test_options
assert_raises(ArgumentError) { DataPipeline::JsonStorage.new }
assert_raises(ArgumentError) { DataPipeline::JsonStorage.new(file: 'x.json', format: :xml) }
end
end
class JsonLinesStorageTest < PipelineTest
include StorageContract
def contract_storage(dir, _purpose) = DataPipeline::JsonStorage.new(file: "#{dir}/data.ndjson")
def test_format_from_extension_and_blank_lines
with_tmpdir do |dir|
File.write("#{dir}/d.jsonl", "{\"a\":1}\n\n{\"a\":2}\n")
assert_equal [{ 'a' => 1 }, { 'a' => 2 }], DataPipeline::JsonStorage.new(file: "#{dir}/d.jsonl").read
DataPipeline::JsonStorage.new(file: "#{dir}/x.txt", format: :lines).write([{ 'a' => 1 }, { 'a' => 2 }])
assert_equal "{\"a\":1}\n{\"a\":2}\n", File.read("#{dir}/x.txt")
end
end
end
+45
View File
@@ -0,0 +1,45 @@
require_relative '../test_helper'
require 'open3'
# in a fresh process: plugins and their gems are loaded only when used
class LazyLoadingTest < PipelineTest
def loaded_after code
script = <<~RUBY
require 'bundler/setup'
require #{File.join(ROOT, 'lib/datapipeline').inspect}
#{code}
features = $LOADED_FEATURES.join(' ')
puts %w[pg sqlite3 roo caxlsx http].select { |gem| features.match?(%r{/gems/\#{gem}-\\d}) }.join(',')
RUBY
out, err, status = Open3.capture3({ 'BUNDLE_GEMFILE' => File.join(ROOT, 'Gemfile') }, RbConfig.ruby, '-e', script)
assert status.success?, err
out.strip.split(',')
end
def test_nothing_loaded_at_start
assert_empty loaded_after('')
end
def test_json_and_csv_need_no_gem
with_tmpdir do |dir|
code = "DataPipeline.new { logger Logger.new(IO::NULL); read container(:json, file: '#{dir}/x.json').tap { File.write('#{dir}/x.json', '[]') }; write container(:csv, file: '#{dir}/y.csv') }.run"
assert_empty loaded_after(code)
end
end
def test_each_plugin_loads_only_its_gem
with_tmpdir do |dir|
assert_equal %w[sqlite3], loaded_after("DataPipeline::SqliteStorage.new(database: ':memory:').close")
assert_equal %w[caxlsx], loaded_after("DataPipeline::ExcelStorage.new(file: '#{dir}/a.xlsx').write([{ 'a' => 1 }])")
assert_equal %w[roo caxlsx].sort, loaded_after("DataPipeline::ExcelStorage.new(file: '#{dir}/b.xlsx').write([{ 'a' => 1 }]); DataPipeline::ExcelStorage.new(file: '#{dir}/b.xlsx').read").sort
assert_equal %w[http], loaded_after("DataPipeline::RestStorage.new(url: 'http://localhost')")
end
end
def test_missing_gem_message
plugin = Class.new(DataPipeline::StoragePlugin) { def initialize(**) = self.class.require_gem('gibtsnicht_gem') }
Object.const_set(:GibtsNichtStorage, plugin) unless defined?(GibtsNichtStorage)
error = assert_raises(LoadError) { GibtsNichtStorage.new }
assert_includes error.message, "gem 'gibtsnicht_gem'"
end
end
+133
View File
@@ -0,0 +1,133 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
class PostgresStorageTest < PipelineTest
include StorageContract
def with_contract_env
with_pg_database do |db|
pg_exec db, 'create table rows (id text, code text, name text, note text)'
yield db
end
end
def contract_storage db, purpose
purpose == :write ? DataPipeline::PostgresStorage.new(**db, table: 'rows') : DataPipeline::PostgresStorage.new(**db, query: 'select * from rows order by id')
end
def with_table
with_pg_database do |db|
pg_exec db, 'create table t (id int, name text, note text); create schema s; create table s."Mixed Case" ("Col A" text)'
storage = DataPipeline::PostgresStorage.new(**db)
yield db, storage
ensure
storage&.close
end
end
def test_write_rows_with_table_option_quotes_and_null
with_table do |db, pg|
DataPipeline::PostgresStorage.new(**db, table: 't').tap do |w|
w.write([{ 'id' => 1, 'name' => "O'Brien", 'note' => nil }, { id: 2, name: "x'); drop table t; --" }])
w.close
end
assert_equal [{ 'id' => '1', 'name' => "O'Brien", 'note' => nil },
{ 'id' => '2', 'name' => "x'); drop table t; --", 'note' => nil }],
pg.query(query: 'select id, name, note from t order by id')
end
end
def test_write_old_signature_and_schema_quoting
with_table do |_db, pg|
pg.write('t', [{ 'id' => 3 }])
pg.write('s.Mixed Case', [{ 'Col A' => 'v' }])
assert_equal '1', pg.query(query: 'select count(*) from t').first['count']
assert_equal [{ 'Col A' => 'v' }], pg.query(query: 'select * from s."Mixed Case"')
end
end
def test_truncate_before_first_write
with_table do |db, pg|
pg.write('t', [{ 'id' => 1 }, { 'id' => 2 }])
writer = DataPipeline::PostgresStorage.new(**db, table: 't', truncate: true)
writer.write([{ 'id' => 3 }])
writer.write_row({ 'id' => 4 })
writer.close
assert_equal %w[3 4], pg.query(query: 'select id from t order by id').map { |r| r['id'] }
end
end
def test_write_is_one_transaction
with_table do |_db, pg|
assert_raises(PG::Error) { pg.write('t', [{ 'id' => 10 }, { 'id' => 'kein int' }]) }
assert_equal '0', pg.query(query: 'select count(*) from t').first['count']
end
end
def test_write_without_table
with_table do |_db, pg|
assert_includes assert_raises(RuntimeError) { pg.write([{ 'id' => 1 }]) }.message, 'Table'
end
end
def test_query_and_read_with_params
with_table do |db, pg|
pg.write('t', [{ 'id' => 1, 'name' => 'a' }, { 'id' => 2, 'name' => 'b' }, { 'id' => 3 }])
assert_equal [{ 'name' => 'a' }], pg.query(query: 'select name from t where id = $1', params: [1])
reader = DataPipeline::PostgresStorage.new(**db)
reader.set(query: 'select id from t where id > $1 order by id', params: [1])
assert_equal [{ 'id' => '2' }, { 'id' => '3' }], reader.read
reader.close
end
end
def test_typed_and_default_string_values
with_table do |db, pg|
typed = DataPipeline::PostgresStorage.new(**db, typed: true)
row = typed.query(query: 'select 1::int as i, 1.5::float8 as f, current_date as d').first
typed.close
assert_equal 1, row['i']
assert_in_delta 1.5, row['f']
assert_kind_of Date, row['d']
assert_equal '1', pg.query(query: 'select 1::int as i').first['i']
end
end
def test_cursor_read_in_batches
with_pg_database do |db|
pg_exec db, 'create table k as select i as id from generate_series(1, 2500) i'
reader = DataPipeline::PostgresStorage.new(**db, query: "select id from k where id > $1 order by id;\n", params: [500],
fetch_size: 100)
count = 0
reader.read { count += 1 }
reader.close
assert_equal 2000, count
end
end
def test_cursor_rollback_on_error_keeps_connection_usable
with_pg_database do |db|
pg_exec db, 'create table k as select 1 as id'
pg = DataPipeline::PostgresStorage.new(**db, query: 'select id from k')
assert_raises(RuntimeError) { pg.read { raise 'x' } }
assert_equal [{ 'x' => '1' }], pg.query(query: 'select 1 as x')
pg.close
end
end
def test_close_twice
with_pg_database do |db|
pg = DataPipeline::PostgresStorage.new(**db)
pg.close
pg.close
assert pg.instance_variable_get(:@conn).finished?
end
end
def test_connection_error_keeps_cause
skip 'no local postgres' unless PgHelper.available?
error = assert_raises(PG::ConnectionBad) { DataPipeline::PostgresStorage.new(host: 'localhost', port: 1, database: 'x') }
assert_includes error.message, 'Error connection to database:'
end
end
+151
View File
@@ -0,0 +1,151 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
require_relative '../support/test_http_server'
class RestStorageTest < PipelineTest
include StorageContract
# a tiny api: POST /items stores one row or an array, GET /items returns all
def with_contract_env
store = []
server = TestHttpServer.new do |req|
if req[:method] == 'POST'
Array(JSON.parse(req[:body]).then { |b| b.is_a?(Array) ? b : [b] }).each { |row| store << row }
[201, { 'ok' => true }]
else
[200, { 'data' => { 'items' => store } }]
end
end
yield server
ensure
server&.stop
end
def contract_storage(server, _purpose) = DataPipeline::RestStorage.new(url: "#{server.url}/items", root: 'data.items')
# handler: ->(request) { [status, body] }
def server handler
s = TestHttpServer.new(&handler)
yield s
ensure
s&.stop
end
def test_page_param_paging
pages = { '1' => [{ 'id' => 1 }, { 'id' => 2 }], '2' => [{ 'id' => 3 }] }
server(->(req) { [200, pages.fetch(req[:query]['page'], [])] }) do |s|
rows = DataPipeline::RestStorage.new(url: "#{s.url}/kunden", page_param: 'page', params: { 'land' => 'DE' }).read
assert_equal [1, 2, 3], rows.map { |r| r['id'] }
assert_equal %w[1 2 3], s.requests.map { |r| r[:query]['page'] }
assert(s.requests.all? { |r| r[:query]['land'] == 'DE' })
end
end
def test_next_url_paging
base = nil
handler = lambda do |req|
if req[:path] == '/a'
[200, { 'rows' => [{ 'n' => 1 }], 'next' => "#{base}/b" }]
else
[200, { 'rows' => [{ 'n' => 2 }], 'next' => nil }]
end
end
server(handler) do |s|
base = s.url
rows = DataPipeline::RestStorage.new(url: "#{s.url}/a", root: 'rows', next: ->(body) { body['next'] }).read
assert_equal [1, 2], rows.map { |r| r['n'] }
end
end
def test_auth_and_headers
server(->(_req) { [200, []] }) do |s|
DataPipeline::RestStorage.new(url: s.url, auth: 'Bearer geheim', headers: { 'X-Mandant' => '001' }).read
assert_equal 'Bearer geheim', s.requests.first[:headers]['authorization']
assert_equal '001', s.requests.first[:headers]['x-mandant']
end
end
def test_retry_on_503_then_success
calls = 0
server(->(_req) { (calls += 1) < 3 ? [503, 'busy'] : [200, [{ 'ok' => 1 }]] }) do |s|
assert_equal [{ 'ok' => 1 }], DataPipeline::RestStorage.new(url: s.url, retries: 2, retry_wait: 0).read
assert_equal 3, calls
end
end
def test_no_retry_on_404_and_error_message
server(->(_req) { [404, { 'error' => 'nicht da' }] }) do |s|
error = assert_raises(DataPipeline::RestStorage::Error) { DataPipeline::RestStorage.new(url: "#{s.url}/x", retry_wait: 0).read }
assert_includes error.message, 'HTTP 404'
assert_includes error.message, 'nicht da'
assert_equal 1, s.requests.size
end
end
def test_retries_exhausted_and_connection_refused
server(->(_req) { [500, 'kaputt'] }) do |s|
assert_includes assert_raises(DataPipeline::RestStorage::Error) { DataPipeline::RestStorage.new(url: s.url, retries: 1, retry_wait: 0).read }.message, 'HTTP 500'
assert_equal 2, s.requests.size
end
closed = TCPServer.new('127.0.0.1', 0).then { |t| port = t.addr[1]; t.close; port }
assert_raises(DataPipeline::RestStorage::Error) { DataPipeline::RestStorage.new(url: "http://127.0.0.1:#{closed}", retries: 1, retry_wait: 0).read }
end
def test_batch_write_and_write_method
server(->(_req) { [200, ''] }) do |s|
rest = DataPipeline::RestStorage.new(url: "#{s.url}/import", batch_size: 2, write_method: :put)
rest.write([{ 'a' => 1 }, { 'a' => 2 }, { 'a' => 3 }])
assert_equal [[{ 'a' => 1 }, { 'a' => 2 }], [{ 'a' => 3 }]], s.requests.map { |r| JSON.parse(r[:body]) }
assert(s.requests.all? { |r| r[:method] == 'PUT' })
end
end
def test_write_url_per_row
server(->(_req) { [200, ''] }) do |s|
DataPipeline::RestStorage.new(url: s.url, write_method: :put, write_url: ->(row) { "#{s.url}/kunden/#{row['id']}" })
.write([{ 'id' => 7 }, { 'id' => 8 }])
assert_equal %w[/kunden/7 /kunden/8], s.requests.map { |r| r[:path] }
assert_equal({ 'id' => 8 }, JSON.parse(s.requests.last[:body]))
end
assert_raises(ArgumentError) { DataPipeline::RestStorage.new(url: 'http://x', batch_size: 2, write_url: ->(_row) { 'http://x' }) }
end
def test_call_json_status_and_retries
calls = 0
server(->(req) { calls += 1; req[:path] == '/api/fail' ? [503, ''] : [201, { 'echo' => JSON.parse(req[:body]) }] }) do |s|
rest = DataPipeline::RestStorage.new(url: "#{s.url}/api/", retries: 2, retry_wait: 0)
assert_equal({ 'echo' => { 'a' => 1 } }, rest.call(:post, 'person/create', json: { 'a' => 1 }))
assert_equal '/api/person/create', s.requests.last[:path]
calls = 0
error = assert_raises(DataPipeline::RestStorage::Error) { rest.call(:post, 'fail', json: {}, retries: 0) }
assert_equal 503, error.status
assert_equal 1, calls, 'retries: 0 sends once'
end
server(->(_req) { [404, { 'message' => 'weg' }] }) do |s|
assert_equal 404, assert_raises(DataPipeline::RestStorage::Error) { DataPipeline::RestStorage.new(url: s.url).call(:get, 'x') }.status
end
end
def test_ssl_verify_false_context
context = DataPipeline::RestStorage.new(url: 'https://192.168.178.251:50443/pds/rest/api', ssl_verify: false).send(:ssl_context)
assert_equal OpenSSL::SSL::VERIFY_NONE, context.verify_mode
end
def test_query_for_lookup
server(->(req) { [200, [{ 'land' => req[:query]['land'], 'pfad' => req[:path] }]] }) do |s|
names = nil
DataPipeline.new do
api = container :rest, url: "#{s.url}/api/"
names = lookup api, query: '/laender', params: { 'land' => 'DE' }, key: 'land', unique: true
end
assert_equal '/api/laender', names['DE']['pfad']
end
end
def test_not_an_array
server(->(_req) { [200, { 'a' => 1 }] }) do |s|
assert_raises(DataPipeline::RestStorage::Error) { DataPipeline::RestStorage.new(url: s.url).read }
end
end
end
+18
View File
@@ -0,0 +1,18 @@
require_relative '../test_helper'
# no network: only construction and options
class SlackTest < PipelineTest
def test_token_required
token = ENV.delete('SLACK_TOKEN')
assert_raises(ArgumentError) { DataPipeline::Slack.new }
ensure
ENV['SLACK_TOKEN'] = token if token
end
def test_options_per_instance
a = DataPipeline::Slack.new(token: 'x', channel: '#a')
b = DataPipeline::Slack.new(token: 'y')
assert_equal '#a', a.instance_variable_get(:@options)[:channel]
assert_equal '#general', b.instance_variable_get(:@options)[:channel]
end
end
+95
View File
@@ -0,0 +1,95 @@
require_relative '../test_helper'
require_relative '../support/storage_contract'
class SqliteStorageTest < PipelineTest
include StorageContract
def contract_storage dir, purpose
db = "#{dir}/test.sqlite3"
unless File.exist?(db)
DataPipeline::SqliteStorage.new(database: db).tap do |s|
s.query(query: 'create table rows (id text, code text, name text, note text)')
s.close
end
end
purpose == :write ? DataPipeline::SqliteStorage.new(database: db, table: 'rows') : DataPipeline::SqliteStorage.new(database: db, query: 'select * from rows order by id')
end
def memory_db
DataPipeline::SqliteStorage.new(database: ':memory:').tap do |s|
s.query(query: 'create table t (id integer, name text, betrag real, datum text)')
end
end
def test_types_null_and_quotes
db = memory_db
db.write('t', [{ 'id' => 1, 'name' => "O'Brien", 'betrag' => 1.5, 'datum' => Date.new(2025, 11, 3) }, { id: 2, name: nil }])
assert_equal [{ 'id' => 1, 'name' => "O'Brien", 'betrag' => 1.5, 'datum' => '2025-11-03' },
{ 'id' => 2, 'name' => nil, 'betrag' => nil, 'datum' => nil }],
db.query(query: 'select * from t order by id')
db.close
end
def test_positional_and_named_params
db = memory_db
db.write('t', [{ 'id' => 1, 'name' => 'a' }, { 'id' => 2, 'name' => 'b' }])
assert_equal [{ 'name' => 'b' }], db.query(query: 'select name from t where id = ?', params: [2])
assert_equal [{ 'name' => 'a' }], db.query(query: 'select name from t where id = :id', params: { id: 1 })
db.close
end
def test_write_is_one_transaction
db = memory_db
db.query(query: 'create table u (id integer not null)')
assert_raises(SQLite3::Exception) { db.write('u', [{ 'id' => 1 }, { 'id' => nil }]) }
assert_equal 0, db.query(query: 'select count(*) as n from u').first['n']
db.close
end
def test_sql_injection_in_values_and_identifiers
db = memory_db
db.query(query: 'create table "Mixed ""Name""" ("Col A" text)')
db.write('Mixed "Name"', [{ 'Col A' => "x'); drop table t; --" }])
assert_equal [{ 'Col A' => "x'); drop table t; --" }], db.query(query: 'select * from "Mixed ""Name"""')
assert_equal 0, db.query(query: 'select count(*) as n from t').first['n']
db.close
end
def test_create_truncate_and_lazy_open
with_tmpdir do |dir|
path = "#{dir}/neu.sqlite3"
storage = DataPipeline::SqliteStorage.new(database: path, table: 'k', create: true, truncate: true)
refute File.exist?(path), 'opened only on first use'
storage.write([{ 'id' => 1, 'betrag' => 1.5, 'name' => 'a' }, { 'id' => 2, 'betrag' => 2.0, 'name' => 'b' }])
storage.close
again = DataPipeline::SqliteStorage.new(database: path, table: 'k', create: true, truncate: true)
again.write_row({ 'id' => 3, 'betrag' => 3.0, 'name' => 'c' })
assert_equal [{ 'id' => 3, 'betrag' => 3.0, 'name' => 'c' }], again.query(query: 'select * from k')
assert_equal %w[integer real text], again.query(query: 'pragma table_info(k)').map { |c| c['type'].downcase }
again.close
end
end
def test_missing_options
assert_raises(ArgumentError) { DataPipeline::SqliteStorage.new }
db = memory_db
assert_raises(RuntimeError) { db.write([{ 'id' => 1 }]) }
assert_raises(RuntimeError) { db.read }
db.close
end
def test_short_name_and_lookup
with_tmpdir do |dir|
path = "#{dir}/l.sqlite3"
names = nil
DataPipeline.new do
db = container :sqlite3, database: path
db.query(query: 'create table land (code text, name text)')
db.write('land', [{ 'code' => 'DE', 'name' => 'Deutschland' }])
names = lookup db, query: 'select * from land where code like ?', params: ['%'], key: 'code', unique: true
end
assert_equal 'Deutschland', names['DE']['name']
end
end
end