diff --git a/HISTORY.rst b/HISTORY.rst index 5d2ba1e..7852f75 100644 --- a/HISTORY.rst +++ b/HISTORY.rst @@ -1,6 +1,11 @@ History ======= +0.6.3 (2010-09-14) +------------------ +* Added Dataset.append() support for columns. + + 0.6.2 (2010-09-13) ------------------ * Fixed Dataset.append() error on empty dataset. diff --git a/README.rst b/README.rst index 3e9e09f..32d477f 100644 --- a/README.rst +++ b/README.rst @@ -31,11 +31,11 @@ Usage Populate fresh data files: :: - headers = ('first_name', 'last_name', 'gpa') + headers = ('first_name', 'last_name') data = [ - ('John', 'Adams', 90), - ('George', 'Washington', 67) + ('John', 'Adams'), + ('George', 'Washington') ] data = tablib.Dataset(*data, headers=headers) @@ -43,7 +43,11 @@ Populate fresh data files: :: Intelligently add new rows: :: - >>> data.append(('Henry', 'Ford', 83)) + >>> data.append(('Henry', 'Ford')) + +Intelligently add new columns: :: + + >>> data.append(col=('age', 90, 67, 83)) Slice rows: :: @@ -122,7 +126,7 @@ Or, if you absolutely must: :: Contribute ---------- -If you'd like to contribute, simply fork `the repository`_, commit your changes, and send a pull request. Make sure you add yourself to AUTHORS_. +If you'd like to contribute, simply fork `the repository`_, commit your changes to the **develop** branch (or branch off of it), and send a pull request. Make sure you add yourself to AUTHORS_. Roadmap @@ -133,6 +137,7 @@ Roadmap - 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 diff --git a/setup.py b/setup.py index 5670078..02c84d3 100644 --- a/setup.py +++ b/setup.py @@ -18,7 +18,7 @@ if sys.argv[-1] == "publish": setup( name='tablib', - version='0.6.2', + version='0.6.3', description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)', long_description=open('README.rst').read() + '\n\n' + open('HISTORY.rst').read(), diff --git a/tablib/core.py b/tablib/core.py index ac61315..658fd10 100644 --- a/tablib/core.py +++ b/tablib/core.py @@ -21,8 +21,8 @@ from helpers import * # __all__ = ['Dataset', 'DataBook'] __name__ = 'tablib' -__version__ = '0.6.2' -__build__ = 0x000602 +__version__ = '0.6.3' +__build__ = 0x000603 __author__ = 'Kenneth Reitz' __license__ = 'MIT' __copyright__ = 'Copyright 2010 Kenneth Reitz' @@ -54,7 +54,7 @@ class Dataset(object): def __getitem__(self, key): - if is_string(key): + if isinstance(key, basestring): if key in self.headers: pos = self.headers.index(key) # get 'key' index from each data return [row[pos] for row in self._data] @@ -80,10 +80,15 @@ class Dataset(object): return '' - def _validate(self, row=None, safety=False): + def _validate(self, row=None, col=None, safety=False): """Assures size of every row in dataset is of proper proportions.""" if row: is_valid = (len(row) == self.width) if self.width else True + elif col: + if self.headers: + is_valid = (len(col) - 1) == self.height + else: + is_valid = (len(col) == self.height) if self.height else True else: is_valid = all((len(x)== self.width for x in self._data)) @@ -130,17 +135,27 @@ class Dataset(object): """Headers property.""" return self.__headers + @headers.setter def headers(self, collection): """Validating headers setter.""" self._validate(collection) - self.__headers = collection - + if collection: + try: + self.__headers = list(collection) + except TypeError, why: + raise TypeError + else: + self.__headers = None + + + @property def dict(self): """Returns python dict of Dataset.""" return self._package() + @property def json(self): """Returns JSON representation of Dataset.""" @@ -180,16 +195,36 @@ class Dataset(object): return stream.getvalue() - def append(self, row): + def append(self, row=None, col=None): """Adds a row to the end of Dataset""" - self._validate(row) - self._data.append(tuple(row)) + if row: + self._validate(row) + self._data.append(tuple(row)) + elif col: + self._validate(col=col) + + if self.headers: + # pop the first item off, add to headers + self.headers.append(col[0]) + col = col[1:] + + if self.height and self.width: + + for i, row in enumerate(self._data): + _row = list(row) + _row.append(col[i]) + self._data[i] = tuple(_row) + else: + self._data = [tuple([row]) for row in col] - def index(self, i, row): + def insert(self, i, row=None, col=None): """Inserts a row at given position in Dataset""" - self._validate(row) - self._data.insert(i, tuple(row)) + if row: + self._validate(row) + self._data.insert(i, tuple(row)) + elif col: + pass class DataBook(object): @@ -200,12 +235,14 @@ class DataBook(object): def __init__(self, sets=[]): self._datasets = sets + def __repr__(self): try: return '<%s databook>' % (self.title.lower()) except AttributeError: return '' + def add_sheet(self, dataset): """Add given dataset .""" if type(dataset) is Dataset: @@ -213,6 +250,7 @@ class DataBook(object): else: raise InvalidDatasetType + def _package(self): collector = [] for dset in self._datasets: @@ -222,6 +260,7 @@ class DataBook(object): )) return collector + @property def size(self): """The number of the Datasets within DataBook.""" @@ -235,8 +274,8 @@ class DataBook(object): stream = cStringIO.StringIO() wb = xlwt.Workbook() - for dset in self._datasets: - ws = wb.add_sheet(dset.title if dset.title else 'Tabbed Dataset %s' % (int(random.random() * 100000000))) + 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)): @@ -246,24 +285,29 @@ class DataBook(object): 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()) - + + class InvalidDatasetType(Exception): "Only Datasets can be added to a DataBook" + class InvalidDimensions(Exception): "Invalid size" + class UnsupportedFormat(NotImplementedError): "Format is not supported" diff --git a/tablib/helpers.py b/tablib/helpers.py index a12c4dd..0a91e56 100644 --- a/tablib/helpers.py +++ b/tablib/helpers.py @@ -10,16 +10,12 @@ class Struct(object): self.__dict__.update(entries) def __getitem__(self, key): - return getattr(self, key) + return getattr(self, key, None) def piped(): - """Returns piped input via stdin, else False""" + """Returns piped input via stdin, else False.""" with sys.stdin as stdin: + # TTY is only way to detect if stdin contains data return stdin.read() if not stdin.isatty() else None - -def is_string(obj): - """Tests if an object is a string""" - - return True if type(obj).__name__ == 'str' else False \ No newline at end of file diff --git a/test_tablib.py b/test_tablib.py index 3111206..ad7bcd9 100644 --- a/test_tablib.py +++ b/test_tablib.py @@ -13,6 +13,9 @@ class TablibTestCase(unittest.TestCase): def setUp(self): """Create simple data set with headers""" + global data + data = tablib.Dataset() + headers = ('first_name', 'last_name', 'gpa') self.john = ('John', 'Adams', 90) self.george = ('George', 'Washington', 67) @@ -29,9 +32,7 @@ class TablibTestCase(unittest.TestCase): def test_empty_append(self): """Verify append() correctly adds tuple with no headers""" - data = tablib.Dataset() - - new_row = (1, 2, 3) + new_row = (1,2,3) data.append(new_row) # Verify width/data @@ -42,13 +43,63 @@ class TablibTestCase(unittest.TestCase): """Verify append() correctly detects mismatch of number of headers and data """ - data = tablib.Dataset() - data.headers = ['first', 'second'] new_row = (1, 2, 3, 4) self.assertRaises(tablib.InvalidDimensions, data.append, new_row) + + def test_add_column(self): + # No Headers + + data.append(['kenneth']) + data.append(['bessie']) + + new_col = ['reitz', 'monke'] + + data.append(col=new_col) + + self.assertEquals(data[0], ('kenneth', 'reitz')) + self.assertEquals(data.width, 2) + + # With Headers + data.headers = ('fname', 'lname') + new_col = ['age', 21, 22] + data.append(col=new_col) + + self.assertEquals(data[new_col[0]], new_col[1:]) + + def test_add_column_no_data_no_headers(self): + + # no headers + + new_col = ('reitz', 'monke') + + data.append(col=new_col) + + self.assertEquals(data[0], tuple([new_col[0]])) + self.assertEquals(data.width, 1) + self.assertEquals(data.height, len(new_col)) + + def test_add_column_no_data_with_headers(self): + + # no headers + + data.headers = ('first', 'last') + + new_col = ('age',) + data.append(col=new_col) + + self.assertEquals(len(data.headers), 3) + self.assertEquals(data.width, 3) + + new_col = ('foo', 'bar') + + self.assertRaises(tablib.InvalidDimensions, data.append, col=new_col) + + def tuple_check(self): + data.append(col=(1,2,3)) + def test_header_slicing(self): """Verify slicing by headers""" @@ -75,8 +126,6 @@ class TablibTestCase(unittest.TestCase): self.assertEqual(self.founders[1:3], [self.george, self.tom]) self.assertEqual(self.founders[2:], [self.tom]) - # def test_adding_header with (self): - - + if __name__ == '__main__': unittest.main()