Merge branch 'feature/imports' into develop

README.rst

@@ -131,7 +131,7 @@ If you'd like to contribute, simply fork `the repository`_, commit your changes
 
 Roadmap
 -------
-- Import datasets from CSV, JSON, YAML
+- Import datasets from CSV.
 - Release CLI Interface
 - Auto-detect import format
 - Add possible other exports (SQL?)

tablib/core.py

@@ -1,9 +1,8 @@
 # -*- coding: utf-8 -*-
 
-""" Tablib - Core Library
+""" Tablib - core.
 """
 
-
 import csv
 import cStringIO
 
@@ -11,6 +10,8 @@ import simplejson as json
 import xlwt
 import yaml
 
+from tablib.formats import formats
+
 
 __title__ = 'tablib'
 __version__ = '0.7.1'
@@ -24,9 +25,6 @@ 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
 
@@ -40,6 +38,7 @@ class Dataset(object):
 		except KeyError:
 			self.title = None
 
+		self._register_formats()
 
 	def __len__(self):
 		return self.height
@@ -71,6 +70,20 @@ 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."""
@@ -105,6 +118,7 @@ class Dataset(object):
 
 		return data
 
+	
 	@property
 	def height(self):
 		"""Returns the height of the Dataset."""
@@ -121,7 +135,8 @@ class Dataset(object):
 				return len(self.headers)
 			except TypeError:
 				return 0
-	
+
+
 	@property
 	def headers(self):
 		"""Headers property."""
@@ -146,42 +161,21 @@ 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."""
-
-		workb = xlwt.Workbook(encoding='utf8')
-		works = workb.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):
-				works.write(i, j, col)
-
-		stream = cStringIO.StringIO()
-		workb.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):
@@ -214,6 +208,12 @@ class Dataset(object):
 			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):
@@ -223,14 +223,35 @@ class Databook(object):
 
 	def __init__(self, sets=[]):
 		self._datasets = sets
+		self._register_formats()
 
 
 	def __repr__(self):
-		return '<databook object>'
+		try:
+			return '<%s databook>' % (self.title.lower())
+		except AttributeError:
+			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:
@@ -253,40 +274,6 @@ class Databook(object):
 		"""The number of the Datasets within DataBook."""
 		return len(self._datasets)
 
-	@property
-	def xls(self):
-		"""Returns XLS representation of DataBook."""
-
-
-		workb = xlwt.Workbook(encoding='utf8')
-
-		for i, dset in enumerate(self._datasets):
-			works = workb.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):
-					works.write(i, j, col)
-
-
-		stream = cStringIO.StringIO()
-		workb.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())
-
 
 
 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 = (csv, json, xls, yaml)

tablib/formats/_csv.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+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)

tablib/formats/_json.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+
+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)

tablib/formats/_xls.py

@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+
+import xlwt
+import cStringIO
+
+
+title = 'xls'
+extentions = ('xls',)
+
+
+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')
+
+	for i, row in enumerate(dataset._package(dicts=False)):
+		for j, col in enumerate(row):
+			ws.write(i, j, col)
+
+	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))
+
+		#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()

tablib/formats/_yaml.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+
+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)

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)
@@ -181,6 +183,101 @@ 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_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()