public void TestReadFlatFile_SchemaProvided_TypesUsed()
{
const string text = @"123,Bob,12/31/2012,3.14159";
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = new DataTable();
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"))
.AddColumn(new DoubleColumn("avg"));
IParser parser = new SeparatedValueParser(stream, schema);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
DataRow row = table.Rows[0];
object[] expected = new object[] { 123, "Bob", new DateTime(2012, 12, 31), 3.14159 };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void TestReadFlatFile_ClearsSchemaAndData()
{
// fill the table with some existing columns, constraints and data
DataTable table = new DataTable();
DataColumn column = table.Columns.Add("blah", typeof(int));
table.Columns.Add("bleh", typeof(string));
table.Constraints.Add("PK_blah", column, true);
DataRow row = table.Rows.Add(new object[] { 123, "dopey" });
row.AcceptChanges();
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
IParser parser = new SeparatedValueParser(stream, options);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
row = table.Rows[0];
object[] expected = new object[] { "123", "Bob", "12/31/2012", "3.14159" };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void TestReadFlatFile_ExtractsSchema_PopulatesTable()
{
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = new DataTable();
IParser parser = new SeparatedValueParser(stream, options);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
DataRow row = table.Rows[0];
object[] expected = new object[] { "123", "Bob", "12/31/2012", "3.14159" };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void TestReadFlatFile_ClearsSchemaAndData()
{
// fill the table with some existing columns, constraints and data
DataTable table = new DataTable();
DataColumn column = table.Columns.Add("blah", typeof(int));
table.Columns.Add("bleh", typeof(string));
table.Constraints.Add("PK_blah", column, true);
DataRow row = table.Rows.Add(new object[] { 123, "dopey" });
row.AcceptChanges();
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
IParser parser = new SeparatedValueParser(stream, options);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
row = table.Rows[0];
object[] expected = new object[] { "123", "Bob", "12/31/2012", "3.14159" };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void TestRead_GetValuesWithoutReading_Throws()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
parser.GetValues();
}
public void TestReadFlatFile_DataTableNull_Throws()
{
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = null;
IParser parser = new SeparatedValueParser(stream, options);
DataTableExtensions.ReadFlatFile(table, parser);
}
public void TestRead_ValuesAfterEndOfFile_Throws()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
canRead = parser.Read();
Assert.IsFalse(canRead, "We should have reached the end of the file.");
parser.GetValues();
}
public void TestGetSchema_NotExtracted_Throws()
{
string text = "a,b,c";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = false
};
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
parser.GetSchema();
}
public void TestGetSchema_SchemaProvided_WrongNumberOfColumns_Throws()
{
const string text = @"123,Bob";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema);
parser.Read();
}
public void TestGetSchema_FirstRecordSchema_WrongNumberOfColumns_Throws()
{
const string text = @"id,name,created
123,Bob,1/19/2013,Hello";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
parser.Read();
}
public void TestRead_MultipleCallsToValues_ReturnsSameValues()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
string[] expected = new string[] { "a", "b", "c" };
object[] actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The wrong values were parsed.");
actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The same values were not returned multiple times.");
}
public void TestRead_SingleRecord_ReturnsTrueOnce()
{
const string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
string[] expected = new string[] { "a", "b", "c" };
object[] actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The wrong values were parsed.");
canRead = parser.Read();
Assert.IsFalse(canRead, "No more records should have been read.");
}
public void TestReadFlatFile_DataTableNull_Throws()
{
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = null;
IParser parser = new SeparatedValueParser(stream, options);
DataTableExtensions.ReadFlatFile(table, parser);
}
public void TestGetSchema_Extracted_ReturnsColumnNames()
{
string text = "a,b,c";
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
Schema schema = parser.GetSchema();
Assert.IsTrue(schema.ColumnDefinitions.All(d => d is StringColumn), "Not all of the columns were treated as strings.");
string[] actual = schema.ColumnDefinitions.Select(d => d.ColumnName).ToArray();
string[] expected = new string[] { "a", "b", "c" };
CollectionAssert.AreEqual(expected, actual, "The schema was not extracted as expected.");
}
public void TestGetSchema_SchemaProvided_ParsesValues()
{
const string text = @"123,Bob,1/19/2013";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema);
Assert.IsTrue(parser.Read(), "The first record was skipped.");
object[] actual = parser.GetValues();
object[] expected = new object[] { 123, "Bob", new DateTime(2013, 1, 19) };
CollectionAssert.AreEqual(expected, actual, "The values were not parsed as expected.");
}
public void TestGetSchema_SchemaProvided_FirstRecordSchema_SkipsFirstRecord()
{
const string text = @"id,name,created";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema, options);
Schema actual = parser.GetSchema();
Assert.AreSame(schema, actual, "The schema was passed did not take priority.");
Assert.IsFalse(parser.Read(), "The schema record was not skipped.");
}
public void ShouldCreateCustomerFromCsv()
{
Schema schema = new Schema().AddColumn<string>("name").AddColumn<DateTime>("modified").AddColumn<int>("visits");
Mapper<Customer> mapper = new Mapper<Customer>().Map(c => c.Name).To("name").Map(c => c.LastModified).To("modified").Map(c => c.Visits).To("visits");
const string data = @"name,modified,visits
bob,12/31/2012,108";
Stream stream = new MemoryStream(Encoding.Default.GetBytes(data));
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
SeparatedValueParser parser = new SeparatedValueParser(stream, schema, options);
FlatFileReader reader = new FlatFileReader(parser);
IEnumerable<Customer> customers = mapper.Extract(reader);
Assert.AreEqual(1, customers.Count(), "The wrong number of records were mapped.");
Assert.AreEqual("bob", customers.First().Name, "The customer name was not parsed correctly.");
Assert.AreEqual(new DateTime(2012, 12, 31), customers.First().LastModified, "The customer modified date was not parsed correctly.");
Assert.AreEqual(108, customers.First().Visits, "The customer visits was not parsed correctly.");
}
public void TestReadFlatFile_ExtractsSchema_PopulatesTable()
{
const string text = @"id,name,created,avg
123,Bob,12/31/2012,3.14159";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = new DataTable();
IParser parser = new SeparatedValueParser(stream, options);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
DataRow row = table.Rows[0];
object[] expected = new object[] { "123", "Bob", "12/31/2012", "3.14159" };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void ShouldCreateCustomerFromCsv()
{
Schema schema = new Schema().AddColumn <string>("name").AddColumn <DateTime>("modified").AddColumn <int>("visits");
Mapper <Customer> mapper = new Mapper <Customer>().Map(c => c.Name).To("name").Map(c => c.LastModified).To("modified").Map(c => c.Visits).To("visits");
const string data = @"name,modified,visits
bob,12/31/2012,108";
Stream stream = new MemoryStream(Encoding.Default.GetBytes(data));
SeparatedValueParserOptions options = new SeparatedValueParserOptions()
{
IsFirstRecordSchema = true
};
SeparatedValueParser parser = new SeparatedValueParser(stream, schema, options);
FlatFileReader reader = new FlatFileReader(parser);
IEnumerable <Customer> customers = mapper.Extract(reader);
Assert.AreEqual(1, customers.Count(), "The wrong number of records were mapped.");
Assert.AreEqual("bob", customers.First().Name, "The customer name was not parsed correctly.");
Assert.AreEqual(new DateTime(2012, 12, 31), customers.First().LastModified, "The customer modified date was not parsed correctly.");
Assert.AreEqual(108, customers.First().Visits, "The customer visits was not parsed correctly.");
}
public void TestGetSchema_FirstRecordSchema_WrongNumberOfColumns_Throws()
{
const string text = @"id,name,created
123,Bob,1/19/2013,Hello";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
parser.Read();
}
public void TestGetSchema_NotExtracted_Throws()
{
string text = "a,b,c";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = false };
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
parser.GetSchema();
}
public void TestGetSchema_SchemaProvided_FirstRecordSchema_SkipsFirstRecord()
{
const string text = @"id,name,created";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema, options);
Schema actual = parser.GetSchema();
Assert.AreSame(schema, actual, "The schema was passed did not take priority.");
Assert.IsFalse(parser.Read(), "The schema record was not skipped.");
}
public void TestGetSchema_SchemaProvided_ParsesValues()
{
const string text = @"123,Bob,1/19/2013";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema);
Assert.IsTrue(parser.Read(), "The first record was skipped.");
object[] actual = parser.GetValues();
object[] expected = new object[] { 123, "Bob", new DateTime(2013, 1, 19) };
CollectionAssert.AreEqual(expected, actual, "The values were not parsed as expected.");
}
public void TestGetSchema_SchemaProvided_WrongNumberOfColumns_Throws()
{
const string text = @"123,Bob";
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"));
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), schema);
parser.Read();
}
public void TestRead_GetValuesWithoutReading_Throws()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
parser.GetValues();
}
public void TestRead_MultipleCallsToValues_ReturnsSameValues()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
string[] expected = new string[] { "a", "b", "c" };
object[] actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The wrong values were parsed.");
actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The same values were not returned multiple times.");
}
public void TestRead_SingleRecord_ReturnsTrueOnce()
{
const string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
string[] expected = new string[] { "a", "b", "c" };
object[] actual = parser.GetValues();
CollectionAssert.AreEqual(expected, actual, "The wrong values were parsed.");
canRead = parser.Read();
Assert.IsFalse(canRead, "No more records should have been read.");
}
public void TestRead_ValuesAfterEndOfFile_Throws()
{
string text = "a,b,c";
SeparatedValueParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)));
bool canRead = parser.Read();
Assert.IsTrue(canRead, "Could not read the record.");
canRead = parser.Read();
Assert.IsFalse(canRead, "We should have reached the end of the file.");
parser.GetValues();
}
public void TestReadFlatFile_SchemaProvided_TypesUsed()
{
const string text = @"123,Bob,12/31/2012,3.14159";
Stream stream = new MemoryStream(Encoding.Default.GetBytes(text));
DataTable table = new DataTable();
Schema schema = new Schema();
schema.AddColumn(new Int32Column("id"))
.AddColumn(new StringColumn("name"))
.AddColumn(new DateTimeColumn("created"))
.AddColumn(new DoubleColumn("avg"));
IParser parser = new SeparatedValueParser(stream, schema);
table.ReadFlatFile(parser);
Assert.AreEqual(4, table.Columns.Count, "The wrong number of columns were extracted.");
Assert.IsTrue(table.Columns.Contains("id"), "The ID column was not extracted.");
Assert.IsTrue(table.Columns.Contains("name"), "The name column was not extracted.");
Assert.IsTrue(table.Columns.Contains("created"), "The created column was not extracted.");
Assert.IsTrue(table.Columns.Contains("avg"), "The AVG column was not extracted.");
Assert.AreEqual(1, table.Rows.Count, "Not all of the records were extracted.");
DataRow row = table.Rows[0];
object[] expected = new object[] { 123, "Bob", new DateTime(2012, 12, 31), 3.14159 };
object[] values = row.ItemArray;
CollectionAssert.AreEqual(expected, values, "The wrong values were extracted");
}
public void TestGetSchema_Extracted_ReturnsColumnNames()
{
string text = "a,b,c";
SeparatedValueParserOptions options = new SeparatedValueParserOptions() { IsFirstRecordSchema = true };
IParser parser = new SeparatedValueParser(new MemoryStream(Encoding.Default.GetBytes(text)), options);
Schema schema = parser.GetSchema();
Assert.IsTrue(schema.ColumnDefinitions.All(d => d is StringColumn), "Not all of the columns were treated as strings.");
string[] actual = schema.ColumnDefinitions.Select(d => d.ColumnName).ToArray();
string[] expected = new string[] { "a", "b", "c" };
CollectionAssert.AreEqual(expected, actual, "The schema was not extracted as expected.");
}
