Merge branch 'release/0.8.3'

Bolden headers and Separators.

AUTHORS

@@ -10,4 +10,5 @@ Development Lead
 Patches and Suggestions
 ```````````````````````
 
-- A Lucky Someone
+- Luke Lee
+- Josh Ourisman

HISTORY.rst

@@ -1,6 +1,30 @@
 History
 =======
 
+0.8.3 (2010-10-04)
+------------------
+
+* Ability to append new column passing a callable 
+  as the value that will be applied to every row.
+
+
+0.8.2 (2010-10-04)
+------------------
+* Added alignment wrapping to written cells.
+* Added separator support to XLS.
+
+0.8.1 (2010-09-28)
+------------------
+* Packaging Fix
+
+
+0.8.0 (2010-09-25)
+------------------
+* New format plugin system!
+* Imports! ELEGANT Imports!
+* Tests. Lots of tests.
+
+
 0.7.1 (2010-09-20)
 ------------------
 

README.rst

@@ -15,15 +15,27 @@ Tablib is a format-agnostic tabular dataset library, written in Python.
 
 Output formats supported:
 
-- Excel
-- JSON
-- YAML
-- CSV
+- Excel (Sets + Books)
+- JSON (Sets + Books)
+- YAML (Sets + Books)
+- CSV (Sets)
 
-At this time, Tablib supports the **export** of it's powerful Dataset object instances into any of the above formats. Import is underway.
+Import formats supported:
+
+- JSON (Sets + Books)
+- YAML (Sets + Books)
+- CSV (Sets)
 
 Note that tablib *purposefully* excludes XML support. It always will.
 
+Overview
+--------
+
+`tablib.Dataset()`
+	A Dataset is a table of tabular data. It may or may not have a header row. They can be build and maniuplated as raw Python datatypes (Lists of tuples|dictonaries). Datasets can be imported from JSON, YAML, and CSV; they can be exported to Excel (XLS), JSON, YAML, and CSV.
+	
+`tablib.Databook()`
+	A Databook is a set of Datasets. The most common form of a Databook is an Excel file with multiple spreadsheets. Databooks can be imported from JSON and YAML; they can be exported to Excel (XLS), JSON, and YAML.
 
 Usage
 -----
@@ -64,6 +76,9 @@ Easily delete rows: ::
 
     >>> del data[1]
 
+Exports
+-------
+
 Drumroll please...........
 
 JSON! 
@@ -109,8 +124,41 @@ EXCEL!
 	>>> open('people.xls', 'wb').write(data.xls)
 
 It's that easy.
+
+Imports!
+--------
+
+JSON
+++++
+
+::
+
+	>>> data.json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
+	>>> print data[0]
+	('John', 'Adams', 90)
+
+
+YAML
+++++
+::
+
+	>>> data.yaml = '- {age: 90, first_name: John, last_name: Adams}'
+	>>> print data[0]
+	('John', 'Adams', 90)
+
+CSV
++++
+::
+
+	>>> data.yaml = 'age, first_name, last_name\n90, John, Adams'
+	>>> print data[0]
+	('John', 'Adams', 90)
 	
-    
+	>>> print data.yaml
+	- {age: 90, first_name: John, last_name: Adams}
+	
+
+
 Installation
 ------------
 
@@ -131,13 +179,10 @@ If you'd like to contribute, simply fork `the repository`_, commit your changes
 
 Roadmap
 -------
-- Import datasets from CSV, JSON, YAML
 - Release CLI Interface
 - Auto-detect import format
 - Add possible other exports (SQL?)
-- Possibly plugin-ify format architecture
 - Ability to assign types to rows (set, regex=, &c.)
-- Plugin support
 
 .. _`the repository`: http://github.com/kennethreitz/tablib
 .. _AUTHORS: http://github.com/kennethreitz/tablib/blob/master/AUTHORS

setup.py

@@ -11,21 +11,20 @@ def publish():
 	"""Publish to PyPi"""
 	os.system("python setup.py sdist upload")
 
-
 if sys.argv[-1] == "publish":
 	publish()
 	sys.exit()
 
 setup(
 	name='tablib',
-	version='0.7.1',
+	version='0.8.3',
 	description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)',
 	long_description=open('README.rst').read() + '\n\n' +
 	                 open('HISTORY.rst').read(),
 	author='Kenneth Reitz',
 	author_email='me@kennethreitz.com',
 	url='http://github.com/kennethreitz/tablib',
-	packages=['tablib'],
+	packages=['tablib', 'tablib.formats'],
 	install_requires=['xlwt', 'simplejson', 'PyYAML'],
 	license='MIT',
 	classifiers=(

tabbed

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+Tabbed -- CLI for Tablib
+Copyright (c) 2010 Kenneth Reitz. MIT License.
+"""
+
+import tablib.cli
+
+
+if __name__ == '__main__':
+	
+	tablib.cli.start()

tablib/__init__.py

@@ -1 +1,8 @@
-from core import *
+""" Tablib.
+"""
+
+from tablib.core import (
+	Databook, Dataset, detect, import_set, 
+	InvalidDatasetType, InvalidDimensions, UnsupportedFormat
+)
+

tablib/cli.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+""" Tabbed CLI Inteface Application
+"""
+
+import io
+import sys
+
+import argue
+
+import tablib
+from helpers import Struct, piped
+
+
+
+FORMATS = [fmt.title for fmt in tablib.formats.FORMATS]
+
+opts = []
+
+opts.append(('v', 'version', False, 'Report tabbed version'))
+
+for format in FORMATS:
+	opts.append(('', format, False, 'Output to %s' % (format.upper())))
+
+
+
+@argue.command(options=opts, usage='[FILE] [--FORMAT | FILE]')
+def start(in_file=None, out_file=None, **opts):
+	"""Covertly convert dataset formats"""
+	
+	opts = Struct(**opts)
+	
+	if opts.version:
+		print('Tabbed, Ver. %s' % tablib.core.__version__)
+		sys.exit(0)
+	
+	stdin = piped()
+	
+	if stdin:
+		data = tablib.import_set(stdin)
+	
+	elif in_file:
+		
+		try:
+			in_stream =- io.open(in_file, 'r').read()
+		except Exception, e:
+			print(' %s cannot be read.' % in_file)
+			sys.exit(65)
+		
+		try:
+			tablib.import_set(in_stream)
+		except Exception, e:
+			raise e
+			print('Import format not supported.')
+			sys.exit(65)
+	else:
+		print('Please provide input.')
+		sys.exit(65)
+		
+
+	_formats_sum = sum(opts[f] for f in FORMATS)
+	
+	# Multiple output formats given
+	if _formats_sum > 1:
+		print('Please specify a single output format.')
+		sys.exit(64)
+		
+	# No output formats given
+	elif _formats_sum < 1:
+		print('Please specify an output format.')
+		sys.exit(64)
+	
+	
+	# fetch options.formats list
+	# if sum(()) > 1
+	# log only one data format please
+	# if sum of formats == 0, specity format
+	
+	# look for filename
+	
+	# print opts.__dict__
+	# print in_file
+	# print out_file

tablib/core.py

@@ -1,28 +1,14 @@
 # -*- coding: utf-8 -*-
 
-# _____         ______  ______        _________
-# __  /_______ ____  /_ ___  /_ _____ ______  /
-# _  __/_  __ `/__  __ \__  __ \_  _ \_  __  / 
-# / /_  / /_/ / _  /_/ /_  /_/ //  __// /_/ /  
-# \__/  \__,_/  /_.___/ /_.___/ \___/ \__,_/   
+""" Tablib - Core Library.
+"""
+
+from tablib.formats import FORMATS as formats
 
 
-import csv
-import cStringIO
-import random
-
-import simplejson as json
-import xlwt
-import yaml
-
-from helpers import *
-
-
-# __all__ = ['Dataset', 'DataBook']
-
-__name__ = 'tablib'
-__version__ = '0.7.1'
-__build__ = 0x000701
+__title__ = 'tablib'
+__version__ = '0.8.3'
+__build__ = 0x000803
 __author__ = 'Kenneth Reitz'
 __license__ = 'MIT'
 __copyright__ = 'Copyright 2010 Kenneth Reitz'
@@ -32,23 +18,25 @@ class Dataset(object):
 	"""Epic Tabular-Dataset object. """
 
 	def __init__(self, *args, **kwargs):
-		self._data = None
-		self._saved_file = None
-		self._saved_format = None
 		self._data = list(args)
 		self.__headers = None
+		
+		# ('title', index) tuples
+		self._separators = []
 
 		try:
 			self.headers = kwargs['headers']
-		except KeyError, why:
+		except KeyError:
 			self.headers = None
 
 		try:
 			self.title = kwargs['title']
-		except KeyError, why:
+		except KeyError:
 			self.title = None
 
+		self._register_formats()
 
+		
 	def __len__(self):
 		return self.height
 
@@ -79,6 +67,20 @@ class Dataset(object):
 		except AttributeError:
 			return '<dataset object>'
 
+	
+	@classmethod
+	def _register_formats(cls):
+		"""Adds format properties."""
+		for fmt in formats:
+			try:
+				try:
+					setattr(cls, fmt.title, property(fmt.export_set, fmt.import_set))
+				except AttributeError:
+					setattr(cls, fmt.title, property(fmt.export_set))
+					
+			except AttributeError:
+				pass
+
 
 	def _validate(self, row=None, col=None, safety=False):
 		"""Assures size of every row in dataset is of proper proportions."""
@@ -113,6 +115,7 @@ class Dataset(object):
 
 		return data
 
+	
 	@property
 	def height(self):
 		"""Returns the height of the Dataset."""
@@ -124,12 +127,13 @@ class Dataset(object):
 		"""Returns the width of the Dataset."""
 		try:
 			return len(self._data[0])
-		except IndexError, why:
+		except IndexError:
 			try:
 				return len(self.headers)
-			except TypeError, e:
+			except TypeError:
 				return 0
-	
+
+
 	@property
 	def headers(self):
 		"""Headers property."""
@@ -143,7 +147,7 @@ class Dataset(object):
 		if collection:
 			try:
 				self.__headers = list(collection)
-			except TypeError, why:
+			except TypeError:
 				raise TypeError
 		else:
 			self.__headers = None
@@ -154,50 +158,38 @@ class Dataset(object):
 		"""Returns python dict of Dataset."""
 		return self._package()
 
-
-	@property
-	def json(self):
-		"""Returns JSON representation of Dataset."""
-		return json.dumps(self.dict)
-
-	@property
-	def yaml(self):
-		"""Returns YAML representation of Dataset."""
-		return yaml.dump(self.dict)
-
-	@property
-	def csv(self):
-		"""Returns CSV representation of Dataset."""
-		stream = cStringIO.StringIO()
-		_csv = csv.writer(stream)
-
-		for row in self._package(dicts=False):
-			_csv.writerow(row)
-
-		return stream.getvalue()
-
-	@property
-	def xls(self):
-		"""Returns XLS representation of Dataset."""
-
-		wb = xlwt.Workbook(encoding='utf8')
-		ws = wb.add_sheet(self.title if self.title else 'Tabbed Dataset')
-
-		for i, row in enumerate(self._package(dicts=False)):
-			for j, col in enumerate(row):
-				ws.write(i, j, col)
-
-		stream = cStringIO.StringIO()
-		wb.save(stream)
-		return stream.getvalue()
+	
+	@dict.setter
+	def dict(self, pickle):
+		"""Returns python dict of Dataset."""
+		if not len(pickle):
+			return
+		if isinstance(pickle[0], list):
+			for row in pickle:
+				self.append(row)
+		elif isinstance(pickle[0], dict):
+			self.headers = pickle[0].keys()
+			for row in pickle:
+				self.append(row.values())
+		else:
+			raise UnsupportedFormat
 
 
 	def append(self, row=None, col=None):
 		"""Adds a row to the end of Dataset"""
-		if row:
+		if row is not None:
 			self._validate(row)
 			self._data.append(tuple(row))
-		elif col:
+		elif col is not None:
+			col = list(col)
+			if self.headers:
+				header = [col.pop(0)]
+			else:
+				header = []
+			if len(col) == 1 and callable(col[0]):
+				col = map(col[0], self._data)
+			col = tuple(header + col)
+				
 			self._validate(col=col)
 
 			if self.headers:
@@ -215,13 +207,38 @@ class Dataset(object):
 				self._data = [tuple([row]) for row in col]
 
 
-	def insert(self, i, row=None, col=None):
+	def insert_separator(self, index, text='-'):
+		"""Adds a separator to Dataset at given index."""
+
+		sep = (index, text)
+		self._separators.append(sep)
+
+
+	def append_separator(self, text='-'):
+		"""Adds a separator to Dataset."""
+
+		# change offsets if headers are or aren't defined
+		if not self.headers:
+			index = self.height if self.height else 0
+		else:
+			index = (self.height + 1) if self.height else 1
+
+		self.insert_separator(index, text)
+
+
+	def insert(self, i, row=None):
 		"""Inserts a row at given position in Dataset"""
 		if row:
 			self._validate(row)
 			self._data.insert(i, tuple(row))
 		elif col:
 			pass
+			
+	
+	def wipe(self):
+		"""Erases all data from Dataset."""
+		self._data = list()
+		self.__headers = None
 
 
 class Databook(object):
@@ -231,6 +248,7 @@ class Databook(object):
 
 	def __init__(self, sets=[]):
 		self._datasets = sets
+		self._register_formats()
 
 
 	def __repr__(self):
@@ -240,15 +258,35 @@ class Databook(object):
 			return '<databook object>'
 
 
+	def wipe(self):
+		"""Wipe book clean."""
+		self._datasets = []
+
+		
+	@classmethod
+	def _register_formats(cls):
+		"""Adds format properties."""
+		for fmt in formats:
+			try:
+				try:
+					setattr(cls, fmt.title, property(fmt.export_book, fmt.import_book))
+				except AttributeError:
+					setattr(cls, fmt.title, property(fmt.export_book))
+					
+			except AttributeError:
+				pass
+
+
 	def add_sheet(self, dataset):
-		"""Add given dataset ."""
+		"""Adds given dataset."""
 		if type(dataset) is Dataset:
 			self._datasets.append(dataset)
 		else:
 			raise InvalidDatasetType
-
+		
 
 	def _package(self):
+		"""Packages Databook for delivery."""
 		collector = []
 		for dset in self._datasets:
 			collector.append(dict(
@@ -263,40 +301,29 @@ class Databook(object):
 		"""The number of the Datasets within DataBook."""
 		return len(self._datasets)
 
-	@property
-	def xls(self):
-		"""Returns XLS representation of DataBook."""
 
+def detect(stream):
+	"""Return (format, stream) of given stream."""
+	for fmt in formats:
+		try:
+			if fmt.detect(stream):
+				return (fmt, stream) 
+		except AttributeError:
+			pass 
+	return (None, stream)
+	
+	
+def import_set(stream):
+	"""Return dataset of given stream."""
+	(format, stream) = detect(stream)
 
-		wb = xlwt.Workbook(encoding='utf8')
-
-		for i, dset in enumerate(self._datasets):
-			ws = wb.add_sheet(dset.title if dset.title else 'Sheet%s' % (i))
-
-			#for row in self._package(dicts=False):
-			for i, row in enumerate(dset._package(dicts=False)):
-				for j, col in enumerate(row):
-					ws.write(i, j, col)
-
-
-		stream = cStringIO.StringIO()
-		wb.save(stream)
-		return stream.getvalue()
-
-
-	@property
-	def json(self):
-		"""Returns JSON representation of Databook."""
-
-		return json.dumps(self._package())
-
-
-	@property
-	def yaml(self):
-		"""Returns YAML representation of Databook."""
-
-		return yaml.dump(self._package())
-
+	try:
+		data = Dataset()
+		format.import_set(data, stream)
+		return data
+		
+	except AttributeError, e:
+		return None
 
 
 class InvalidDatasetType(Exception):

tablib/formats/__init__.py

@@ -0,0 +1,11 @@
+# -*- coding: utf-8 -*-
+
+""" Tablib - formats
+"""
+
+import _csv as csv
+import _json as json
+import _xls as xls
+import _yaml as yaml
+
+FORMATS = (json, xls, yaml, csv)

tablib/formats/_csv.py

@@ -0,0 +1,51 @@
+# -*- coding: utf-8 -*-
+
+""" Tablib - CSV Support.
+"""
+
+import cStringIO
+import csv
+import os
+
+import simplejson as json
+
+import tablib
+
+
+title = 'csv'
+extentions = ('csv',)
+
+
+
+def export_set(dataset):
+	"""Returns CSV representation of Dataset."""
+	stream = cStringIO.StringIO()
+	_csv = csv.writer(stream)
+
+	for row in dataset._package(dicts=False):
+		_csv.writerow(row)
+
+	return stream.getvalue()
+
+
+def import_set(dset, in_stream, headers=True):
+	"""Returns dataset from CSV stream."""
+
+	dset.wipe()
+
+	rows = csv.reader(in_stream.split())
+	for i, row in enumerate(rows):
+
+		if (i == 0) and (headers):
+			dset.headers = row
+		else:
+			dset.append(row)
+
+
+def detect(stream):
+	"""Returns True if given stream is valid CSV."""
+	try:
+		rows = dialect = csv.Sniffer().sniff(stream)
+		return True
+	except csv.Error:
+		return False

tablib/formats/_json.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+""" Tablib - JSON Support
+"""
+
+import simplejson as json
+import tablib.core
+
+title = 'json'
+extentions = ('json', 'jsn')
+
+
+def export_set(dataset):
+	"""Returns JSON representation of Dataset."""
+	return json.dumps(dataset.dict)
+
+
+def export_book(databook):
+	"""Returns JSON representation of Databook."""
+	return json.dumps(databook._package())
+	
+
+def import_set(dset, in_stream):
+	"""Returns dataset from JSON stream."""
+	
+	dset.wipe()
+	dset.dict = json.loads(in_stream)
+
+
+def import_book(dbook, in_stream):
+	"""Returns databook from JSON stream."""
+
+	dbook.wipe()
+	for sheet in json.loads(in_stream):
+		data = tablib.core.Dataset()
+		data.title = sheet['title']
+		data.dict = sheet['data']
+		dbook.add_sheet(data)
+
+
+def detect(stream):
+	"""Returns True if given stream is valid JSON."""
+	try:
+		json.loads(stream)
+		return True
+	except json.decoder.JSONDecodeError:
+		return False

tablib/formats/_xls.py

@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+
+""" Tablib - XLS Support.
+"""
+
+import xlwt
+import cStringIO
+
+
+title = 'xls'
+extentions = ('xls',)
+wrap = xlwt.easyxf("alignment: wrap on")
+bold = xlwt.easyxf("font: bold on")
+
+def export_set(dataset):
+	"""Returns XLS representation of Dataset."""
+
+	wb = xlwt.Workbook(encoding='utf8')
+	ws = wb.add_sheet(dataset.title if dataset.title else 'Tabbed Dataset')
+
+	dset_sheet(dataset, ws)
+	
+	stream = cStringIO.StringIO()
+	wb.save(stream)
+	return stream.getvalue()
+
+
+def export_book(databook):
+	"""Returns XLS representation of DataBook."""
+
+	wb = xlwt.Workbook(encoding='utf8')
+
+	for i, dset in enumerate(databook._datasets):
+		ws = wb.add_sheet(dset.title if dset.title else 'Sheet%s' % (i))
+
+		dset_sheet(dset, ws)
+
+
+	stream = cStringIO.StringIO()
+	wb.save(stream)
+	return stream.getvalue()
+
+
+def dset_sheet(dataset, ws):
+	"""Completes given worksheet from given Dataset."""
+	_package = dataset._package(dicts=False)
+
+	for i, sep in enumerate(dataset._separators):
+		_offset = i
+		_package.insert((sep[0] + _offset), (sep[1],))
+
+	for i, row in enumerate(_package):
+		for j, col in enumerate(row):
+
+			# bold headers
+			if (i == 0) and dataset.headers:
+				ws.write(i, j, col, bold)
+
+			# bold separators
+			elif len(row) < dataset.width:
+				ws.write(i, j, col, bold)
+
+			# wrap the rest
+			else:
+				ws.write(i, j, col, wrap)
+
+	

tablib/formats/_yaml.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+
+""" Tablib - YAML Support.
+"""
+
+import yaml
+import tablib
+
+
+
+title = 'yaml'
+extentions = ('yaml', 'yml')
+
+
+
+def export_set(dataset):
+	"""Returns YAML representation of Dataset."""
+	return yaml.dump(dataset.dict)
+
+
+def export_book(databook):
+	"""Returns YAML representation of Databook."""
+	return yaml.dump(databook._package())
+
+
+def import_set(dset, in_stream):
+	"""Returns dataset from YAML stream."""
+
+	dset.wipe()
+	dset.dict = yaml.load(in_stream)
+
+
+def import_book(dbook, in_stream):
+	"""Returns databook from YAML stream."""
+
+	dbook.wipe()
+
+	for sheet in yaml.load(in_stream):
+		data = tablib.core.Dataset()
+		data.title = sheet['title']
+		data.dict = sheet['data']
+		dbook.add_sheet(data)
+		
+def detect(stream):
+	"""Returns True if given stream is valid YAML."""
+	try:
+		_yaml = yaml.load(stream)
+		if isinstance(_yaml, (list, tuple, dict)):
+			return True
+		else:
+			return False
+	except yaml.parser.ParserError:
+		return False

tablib/helpers.py

@@ -1,5 +1,8 @@
 # -*- coding: utf-8 -*-
 
+""" Tablib - General Helpers.
+"""
+
 import sys
 
 
@@ -12,6 +15,19 @@ class Struct(object):
 	def __getitem__(self, key):
 		return getattr(self, key, None)
 
+	def dictionary(self):
+		"""Returns dictionary representation of object."""
+		return self.__dict__
+
+	def items(self):
+		"""Returns items within object."""
+		return self.__dict__.items()
+
+	def keys(self):
+		"""Returns keys within object."""
+		return self.__dict__.keys()
+
+
 
 def piped():
 	"""Returns piped input via stdin, else False."""

test_tablib.py

@@ -13,8 +13,10 @@ class TablibTestCase(unittest.TestCase):
 
 	def setUp(self):
 		"""Create simple data set with headers."""
-		global data
+
+		global data, book
 		data = tablib.Dataset()
+		book = tablib.Databook()
 
 		self.headers = ('first_name', 'last_name', 'gpa')
 		self.john = ('John', 'Adams', 90)
@@ -100,6 +102,13 @@ class TablibTestCase(unittest.TestCase):
 
 		self.assertRaises(tablib.InvalidDimensions, data.append, col=new_col)
 
+	def test_add_callable_column(self):
+		"""Verify adding column with values specified as callable."""
+		new_col = ['first_again', lambda x: x[0]]
+		self.founders.append(col=new_col)
+
+		self.assertTrue(map(lambda x: x[0] == x[-1], self.founders))
+
 
 	def test_header_slicing(self):
 		"""Verify slicing by headers."""
@@ -181,6 +190,153 @@ class TablibTestCase(unittest.TestCase):
 		data.csv
 		data.xls
 
+ 
+	def test_book_export_no_exceptions(self):
+		"""Test that varoius exports don't error out."""
+
+		book = tablib.Databook()
+		book.add_sheet(data)
+
+		book.json
+		book.yaml
+		book.xls
+
+
+	def test_json_import_set(self):
+		"""Generate and import JSON set serialization."""
+		data.append(self.john)
+		data.append(self.george)
+		data.headers = self.headers
+
+		_json = data.json
+
+		data.json = _json
+
+		self.assertEqual(_json, data.json)
+
+
+	def test_json_import_book(self):
+		"""Generate and import JSON book serialization."""
+		data.append(self.john)
+		data.append(self.george)
+		data.headers = self.headers
+
+		book.add_sheet(data)
+		_json = book.json
+
+		book.json = _json
+
+		self.assertEqual(_json, book.json)
+
+
+	def test_yaml_import_set(self):
+		"""Generate and import YAML set serialization."""
+		data.append(self.john)
+		data.append(self.george)
+		data.headers = self.headers
+
+		_yaml = data.yaml
+
+		data.yaml = _yaml
+
+		self.assertEqual(_yaml, data.yaml)
+
+		
+	def test_yaml_import_book(self):
+		"""Generate and import YAML book serialization."""
+		data.append(self.john)
+		data.append(self.george)
+		data.headers = self.headers
+
+		book.add_sheet(data)
+		_yaml = book.yaml
+
+		book.yaml = _yaml
+
+		self.assertEqual(_yaml, book.yaml)
+		
+
+	def test_csv_import_set(self):
+		"""Generate and import CSV set serialization."""
+		data.append(self.john)
+		data.append(self.george)
+		data.headers = self.headers
+
+		_csv = data.csv
+
+		data.csv = _csv
+
+		self.assertEqual(_csv, data.csv)
+
+	def test_csv_format_detect(self):
+		"""Test CSV format detection."""
+		
+		_csv = (
+			'1,2,3\n'
+			'4,5,6\n'
+			'7,8,9\n'
+		)
+		_bunk = (
+			'¡¡¡¡¡¡¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+		
+		self.assertTrue(tablib.formats.csv.detect(_csv))
+		self.assertFalse(tablib.formats.csv.detect(_bunk))
+
+	def test_json_format_detect(self):
+		"""Test JSON format detection."""
+
+		_json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
+		_bunk = (
+			'¡¡¡¡¡¡¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+
+		self.assertTrue(tablib.formats.json.detect(_json))
+		self.assertFalse(tablib.formats.json.detect(_bunk))
+
+
+	def test_yaml_format_detect(self):
+		"""Test YAML format detection."""
+
+		_yaml = '- {age: 90, first_name: John, last_name: Adams}'
+		_bunk = (
+			'¡¡¡¡¡¡---///\n\n\n¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+
+		self.assertTrue(tablib.formats.yaml.detect(_yaml))
+		self.assertFalse(tablib.formats.yaml.detect(_bunk))
+
+
+	def test_auto_format_detect(self):
+		"""Test auto format detection."""
+
+		_yaml = '- {age: 90, first_name: John, last_name: Adams}'
+		_json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
+		_csv = '1,2,3\n4,5,6\n7,8,9\n'
+		_bunk = '¡¡¡¡¡¡---///\n\n\n¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+
+		self.assertEqual(tablib.detect(_yaml)[0], tablib.formats.yaml)
+		self.assertEqual(tablib.detect(_csv)[0], tablib.formats.csv)
+		self.assertEqual(tablib.detect(_json)[0], tablib.formats.json)
+		self.assertEqual(tablib.detect(_bunk)[0], None)
+
+
+	def test_wipe(self):
+		"""Purge a dataset."""
+		
+		new_row = (1, 2, 3)
+		data.append(new_row)
+
+		# Verify width/data
+		self.assertTrue(data.width == len(new_row))
+		self.assertTrue(data[0] == new_row)
+		
+		data.wipe()
+		new_row = (1, 2, 3, 4)
+		data.append(new_row)
+		self.assertTrue(data.width == len(new_row))
+		self.assertTrue(data[0] == new_row)
 	
+		
 if __name__ == '__main__':
 	unittest.main()