datapipeline 2.0.0: Gem aus dem Projekt etl herausgelöst

2026-10-08 15:30:02 +02:00
commit cce7b03ca9
56 changed files with 5205 additions and 0 deletions
@@ -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