From e2cc2530fc6d54ebc975c01a4ff887ce12f0a736 Mon Sep 17 00:00:00 2001 From: Pavel Aharoni Date: Wed, 29 Mar 2017 13:35:45 +0300 Subject: [SDC-6] sdc-distribution-client 1707 rebasing Change-Id: I322a05fd79beb6ba4fee4d32afffecf531b86e98 Signed-off-by: Pavel Aharoni --- .../unicodecsv-0.14.1-py2.7.egg/EGG-INFO/PKG-INFO | 48 ++ .../EGG-INFO/SOURCES.txt | 12 + .../EGG-INFO/dependency_links.txt | 1 + .../EGG-INFO/not-zip-safe | 1 + .../EGG-INFO/top_level.txt | 1 + .../unicodecsv/__init__.py | 11 + .../unicodecsv-0.14.1-py2.7.egg/unicodecsv/py2.py | 223 +++++ .../unicodecsv-0.14.1-py2.7.egg/unicodecsv/py3.py | 95 +++ .../unicodecsv-0.14.1-py2.7.egg/unicodecsv/test.py | 919 +++++++++++++++++++++ 9 files changed, 1311 insertions(+) create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/PKG-INFO create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/SOURCES.txt create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/dependency_links.txt create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/not-zip-safe create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/top_level.txt create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/__init__.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py2.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py3.py create mode 100644 jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/test.py (limited to 'jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg') diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/PKG-INFO b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/PKG-INFO new file mode 100644 index 0000000..2fc3a20 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/PKG-INFO @@ -0,0 +1,48 @@ +Metadata-Version: 1.1 +Name: unicodecsv +Version: 0.14.1 +Summary: Python2's stdlib csv module is nice, but it doesn't support unicode. This module is a drop-in replacement which *does*. +Home-page: https://github.com/jdunck/python-unicodecsv +Author: Jeremy Dunck +Author-email: jdunck@gmail.com +License: BSD License +Description: unicodecsv + ========== + + The unicodecsv is a drop-in replacement for Python 2.7's csv module which supports unicode strings without a hassle. Supported versions are python 2.7, 3.3, 3.4, 3.5, and pypy 2.4.0. + + More fully + ---------- + + Python 2's csv module doesn't easily deal with unicode strings, leading to the dreaded "'ascii' codec can't encode characters in position ..." exception. + + You can work around it by encoding everything just before calling write (or just after read), but why not add support to the serializer? + + .. code-block:: pycon + + >>> import unicodecsv as csv + >>> from io import BytesIO + >>> f = BytesIO() + >>> w = csv.writer(f, encoding='utf-8') + >>> _ = w.writerow((u'é', u'ñ')) + >>> _ = f.seek(0) + >>> r = csv.reader(f, encoding='utf-8') + >>> next(r) == [u'é', u'ñ'] + True + + Note that unicodecsv expects a bytestream, not unicode -- so there's no need to use `codecs.open` or similar wrappers. Plain `open(..., 'rb')` will do. + + (Version 0.14.0 dropped support for python 2.6, but 0.14.1 added it back. See c0b7655248c4249 for the mistaken, breaking change.) + +Platform: UNKNOWN +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: BSD License +Classifier: Natural Language :: English +Classifier: Programming Language :: Python :: 2.6 +Classifier: Programming Language :: Python :: 2.7 +Classifier: Programming Language :: Python :: 3.3 +Classifier: Programming Language :: Python :: 3.4 +Classifier: Programming Language :: Python :: 3.5 +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Programming Language :: Python :: Implementation :: CPython diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/SOURCES.txt b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/SOURCES.txt new file mode 100644 index 0000000..bb7ea0b --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/SOURCES.txt @@ -0,0 +1,12 @@ +MANIFEST.in +README.rst +setup.cfg +setup.py +unicodecsv/__init__.py +unicodecsv/py2.py +unicodecsv/py3.py +unicodecsv/test.py +unicodecsv.egg-info/PKG-INFO +unicodecsv.egg-info/SOURCES.txt +unicodecsv.egg-info/dependency_links.txt +unicodecsv.egg-info/top_level.txt \ No newline at end of file diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/dependency_links.txt b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/dependency_links.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/not-zip-safe b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/not-zip-safe new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/not-zip-safe @@ -0,0 +1 @@ + diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/top_level.txt b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/top_level.txt new file mode 100644 index 0000000..fee1540 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/EGG-INFO/top_level.txt @@ -0,0 +1 @@ +unicodecsv diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/__init__.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/__init__.py new file mode 100644 index 0000000..270bdee --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/__init__.py @@ -0,0 +1,11 @@ +# -*- coding: utf-8 -*- +# http://semver.org/ +import sys + +if sys.version_info >= (3, 0): + from unicodecsv.py3 import * +else: + from unicodecsv.py2 import * + +VERSION = (0, 14, 1) +__version__ = ".".join(map(str, VERSION)) diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py2.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py2.py new file mode 100644 index 0000000..f436397 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py2.py @@ -0,0 +1,223 @@ +# -*- coding: utf-8 -*- +import csv +import numbers + +from itertools import izip + +pass_throughs = [ + 'register_dialect', + 'unregister_dialect', + 'get_dialect', + 'list_dialects', + 'field_size_limit', + 'Dialect', + 'excel', + 'excel_tab', + 'Sniffer', + 'QUOTE_ALL', + 'QUOTE_MINIMAL', + 'QUOTE_NONNUMERIC', + 'QUOTE_NONE', + 'Error' +] +__all__ = [ + 'reader', + 'writer', + 'DictReader', + 'DictWriter', +] + pass_throughs + +for prop in pass_throughs: + globals()[prop] = getattr(csv, prop) + + +def _stringify(s, encoding, errors): + if s is None: + return '' + if isinstance(s, unicode): + return s.encode(encoding, errors) + elif isinstance(s, numbers.Number): + pass # let csv.QUOTE_NONNUMERIC do its thing. + elif not isinstance(s, str): + s = str(s) + return s + + +def _stringify_list(l, encoding, errors='strict'): + try: + return [_stringify(s, encoding, errors) for s in iter(l)] + except TypeError as e: + raise csv.Error(str(e)) + + +def _unicodify(s, encoding): + if s is None: + return None + if isinstance(s, (unicode, int, float)): + return s + elif isinstance(s, str): + return s.decode(encoding) + return s + + +class UnicodeWriter(object): + """ + >>> import unicodecsv + >>> from cStringIO import StringIO + >>> f = StringIO() + >>> w = unicodecsv.writer(f, encoding='utf-8') + >>> w.writerow((u'é', u'ñ')) + >>> f.seek(0) + >>> r = unicodecsv.reader(f, encoding='utf-8') + >>> row = r.next() + >>> row[0] == u'é' + True + >>> row[1] == u'ñ' + True + """ + def __init__(self, f, dialect=csv.excel, encoding='utf-8', errors='strict', + *args, **kwds): + self.encoding = encoding + self.writer = csv.writer(f, dialect, *args, **kwds) + self.encoding_errors = errors + + def writerow(self, row): + return self.writer.writerow( + _stringify_list(row, self.encoding, self.encoding_errors)) + + def writerows(self, rows): + for row in rows: + self.writerow(row) + + @property + def dialect(self): + return self.writer.dialect +writer = UnicodeWriter + + +class UnicodeReader(object): + def __init__(self, f, dialect=None, encoding='utf-8', errors='strict', + **kwds): + + format_params = ['delimiter', 'doublequote', 'escapechar', + 'lineterminator', 'quotechar', 'quoting', + 'skipinitialspace'] + + if dialect is None: + if not any([kwd_name in format_params + for kwd_name in kwds.keys()]): + dialect = csv.excel + self.reader = csv.reader(f, dialect, **kwds) + self.encoding = encoding + self.encoding_errors = errors + self._parse_numerics = bool( + self.dialect.quoting & csv.QUOTE_NONNUMERIC) + + def next(self): + row = self.reader.next() + encoding = self.encoding + encoding_errors = self.encoding_errors + unicode_ = unicode + if self._parse_numerics: + float_ = float + return [(value if isinstance(value, float_) else + unicode_(value, encoding, encoding_errors)) + for value in row] + else: + return [unicode_(value, encoding, encoding_errors) + for value in row] + + def __iter__(self): + return self + + @property + def dialect(self): + return self.reader.dialect + + @property + def line_num(self): + return self.reader.line_num +reader = UnicodeReader + + +class DictWriter(csv.DictWriter): + """ + >>> from cStringIO import StringIO + >>> f = StringIO() + >>> w = DictWriter(f, ['a', u'ñ', 'b'], restval=u'î') + >>> w.writerow({'a':'1', u'ñ':'2'}) + >>> w.writerow({'a':'1', u'ñ':'2', 'b':u'ø'}) + >>> w.writerow({'a':u'é', u'ñ':'2'}) + >>> f.seek(0) + >>> r = DictReader(f, fieldnames=['a', u'ñ'], restkey='r') + >>> r.next() == {'a': u'1', u'ñ':'2', 'r': [u'î']} + True + >>> r.next() == {'a': u'1', u'ñ':'2', 'r': [u'\xc3\xb8']} + True + >>> r.next() == {'a': u'\xc3\xa9', u'ñ':'2', 'r': [u'\xc3\xae']} + True + """ + def __init__(self, csvfile, fieldnames, restval='', + extrasaction='raise', dialect='excel', encoding='utf-8', + errors='strict', *args, **kwds): + self.encoding = encoding + csv.DictWriter.__init__(self, csvfile, fieldnames, restval, + extrasaction, dialect, *args, **kwds) + self.writer = UnicodeWriter(csvfile, dialect, encoding=encoding, + errors=errors, *args, **kwds) + self.encoding_errors = errors + + def writeheader(self): + header = dict(zip(self.fieldnames, self.fieldnames)) + self.writerow(header) + + +class DictReader(csv.DictReader): + """ + >>> from cStringIO import StringIO + >>> f = StringIO() + >>> w = DictWriter(f, fieldnames=['name', 'place']) + >>> w.writerow({'name': 'Cary Grant', 'place': 'hollywood'}) + >>> w.writerow({'name': 'Nathan Brillstone', 'place': u'øLand'}) + >>> w.writerow({'name': u'Will ø. Unicoder', 'place': u'éSpandland'}) + >>> f.seek(0) + >>> r = DictReader(f, fieldnames=['name', 'place']) + >>> print r.next() == {'name': 'Cary Grant', 'place': 'hollywood'} + True + >>> print r.next() == {'name': 'Nathan Brillstone', 'place': u'øLand'} + True + >>> print r.next() == {'name': u'Will ø. Unicoder', 'place': u'éSpandland'} + True + """ + def __init__(self, csvfile, fieldnames=None, restkey=None, restval=None, + dialect='excel', encoding='utf-8', errors='strict', *args, + **kwds): + if fieldnames is not None: + fieldnames = _stringify_list(fieldnames, encoding) + csv.DictReader.__init__(self, csvfile, fieldnames, restkey, restval, + dialect, *args, **kwds) + self.reader = UnicodeReader(csvfile, dialect, encoding=encoding, + errors=errors, *args, **kwds) + if fieldnames is None and not hasattr(csv.DictReader, 'fieldnames'): + # Python 2.5 fieldnames workaround. + # See http://bugs.python.org/issue3436 + reader = UnicodeReader(csvfile, dialect, encoding=encoding, + *args, **kwds) + self.fieldnames = _stringify_list(reader.next(), reader.encoding) + + if self.fieldnames is not None: + self.unicode_fieldnames = [_unicodify(f, encoding) for f in + self.fieldnames] + else: + self.unicode_fieldnames = [] + + self.unicode_restkey = _unicodify(restkey, encoding) + + def next(self): + row = csv.DictReader.next(self) + result = dict((uni_key, row[str_key]) for (str_key, uni_key) in + izip(self.fieldnames, self.unicode_fieldnames)) + rest = row.get(self.restkey) + if rest: + result[self.unicode_restkey] = rest + return result diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py3.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py3.py new file mode 100644 index 0000000..13a8bf7 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/py3.py @@ -0,0 +1,95 @@ +# -*- coding: utf-8 -*- +import csv +from csv import * + + +class _UnicodeWriteWrapper(object): + """Simple write() wrapper that converts unicode to bytes.""" + + def __init__(self, binary, encoding, errors): + self.binary = binary + self.encoding = encoding + self.errors = errors + + def write(self, string): + return self.binary.write(string.encode(self.encoding, self.errors)) + + +class UnicodeWriter(object): + def __init__(self, f, dialect=csv.excel, encoding='utf-8', errors='strict', + *args, **kwds): + if f is None: + raise TypeError + + f = _UnicodeWriteWrapper(f, encoding=encoding, errors=errors) + self.writer = csv.writer(f, dialect, *args, **kwds) + + def writerow(self, row): + return self.writer.writerow(row) + + def writerows(self, rows): + return self.writer.writerows(rows) + + @property + def dialect(self): + return self.writer.dialect + + +class UnicodeReader(object): + def __init__(self, f, dialect=None, encoding='utf-8', errors='strict', + **kwds): + + format_params = ['delimiter', 'doublequote', 'escapechar', + 'lineterminator', 'quotechar', 'quoting', + 'skipinitialspace'] + + if dialect is None: + if not any([kwd_name in format_params + for kwd_name in kwds.keys()]): + dialect = csv.excel + + f = (bs.decode(encoding, errors=errors) for bs in f) + self.reader = csv.reader(f, dialect, **kwds) + + def __next__(self): + return self.reader.__next__() + + def __iter__(self): + return self + + @property + def dialect(self): + return self.reader.dialect + + @property + def line_num(self): + return self.reader.line_num + + +writer = UnicodeWriter +reader = UnicodeReader + + +class DictWriter(csv.DictWriter): + def __init__(self, csvfile, fieldnames, restval='', + extrasaction='raise', dialect='excel', encoding='utf-8', + errors='strict', *args, **kwds): + super().__init__(csvfile, fieldnames, restval, + extrasaction, dialect, *args, **kwds) + self.writer = UnicodeWriter(csvfile, dialect, encoding=encoding, + errors=errors, *args, **kwds) + self.encoding_errors = errors + + def writeheader(self): + header = dict(zip(self.fieldnames, self.fieldnames)) + self.writerow(header) + + +class DictReader(csv.DictReader): + def __init__(self, csvfile, fieldnames=None, restkey=None, restval=None, + dialect='excel', encoding='utf-8', errors='strict', *args, + **kwds): + csv.DictReader.__init__(self, csvfile, fieldnames, restkey, restval, + dialect, *args, **kwds) + self.reader = UnicodeReader(csvfile, dialect, encoding=encoding, + errors=errors, *args, **kwds) diff --git a/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/test.py b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/test.py new file mode 100644 index 0000000..f3d0377 --- /dev/null +++ b/jython-tosca-parser/src/main/resources/Lib/site-packages/unicodecsv-0.14.1-py2.7.egg/unicodecsv/test.py @@ -0,0 +1,919 @@ +# -*- coding: utf-8 -*- +# Copyright (C) 2001,2002 Python Software Foundation +# csv package unit tests + +import array +import decimal +import os +import string +import sys +import tempfile +import unittest2 as unittest +from codecs import EncodedFile +from io import BytesIO + +import unicodecsv as csv + +try: + # Python 2 + chr = unichr +except: + pass + + +# pypy and cpython differ under which exception is raised under some +# circumstances e.g. whether a module is written in C or not. +py_compat_exc = (TypeError, AttributeError) + + +class Test_Csv(unittest.TestCase): + """ + Test the underlying C csv parser in ways that are not appropriate + from the high level interface. Further tests of this nature are done + in TestDialectRegistry. + """ + def _test_arg_valid(self, ctor, arg): + self.assertRaises(py_compat_exc, ctor) + self.assertRaises(py_compat_exc, ctor, None) + self.assertRaises(py_compat_exc, ctor, arg, bad_attr=0) + self.assertRaises(py_compat_exc, ctor, arg, delimiter=0) + self.assertRaises(py_compat_exc, ctor, arg, delimiter='XX') + self.assertRaises(csv.Error, ctor, arg, 'foo') + self.assertRaises(py_compat_exc, ctor, arg, delimiter=None) + self.assertRaises(py_compat_exc, ctor, arg, delimiter=1) + self.assertRaises(py_compat_exc, ctor, arg, quotechar=1) + self.assertRaises(py_compat_exc, ctor, arg, lineterminator=None) + self.assertRaises(py_compat_exc, ctor, arg, lineterminator=1) + self.assertRaises(py_compat_exc, ctor, arg, quoting=None) + self.assertRaises(py_compat_exc, ctor, arg, + quoting=csv.QUOTE_ALL, quotechar='') + self.assertRaises(py_compat_exc, ctor, arg, + quoting=csv.QUOTE_ALL, quotechar=None) + + def test_reader_arg_valid(self): + self._test_arg_valid(csv.reader, []) + + def test_writer_arg_valid(self): + self._test_arg_valid(csv.writer, BytesIO()) + + def _test_default_attrs(self, ctor, *args): + obj = ctor(*args) + # Check defaults + self.assertEqual(obj.dialect.delimiter, ',') + self.assertEqual(obj.dialect.doublequote, True) + self.assertEqual(obj.dialect.escapechar, None) + self.assertEqual(obj.dialect.lineterminator, "\r\n") + self.assertEqual(obj.dialect.quotechar, '"') + self.assertEqual(obj.dialect.quoting, csv.QUOTE_MINIMAL) + self.assertEqual(obj.dialect.skipinitialspace, False) + self.assertEqual(obj.dialect.strict, False) + # Try deleting or changing attributes (they are read-only) + self.assertRaises(py_compat_exc, delattr, + obj.dialect, 'delimiter') + self.assertRaises(py_compat_exc, setattr, + obj.dialect, 'delimiter', ':') + self.assertRaises(py_compat_exc, delattr, + obj.dialect, 'quoting') + self.assertRaises(py_compat_exc, setattr, + obj.dialect, 'quoting', None) + + def test_reader_attrs(self): + self._test_default_attrs(csv.reader, []) + + def test_writer_attrs(self): + self._test_default_attrs(csv.writer, BytesIO()) + + def _test_kw_attrs(self, ctor, *args): + # Now try with alternate options + kwargs = dict(delimiter=':', doublequote=False, escapechar='\\', + lineterminator='\r', quotechar='*', + quoting=csv.QUOTE_NONE, skipinitialspace=True, + strict=True) + obj = ctor(*args, **kwargs) + self.assertEqual(obj.dialect.delimiter, ':') + self.assertEqual(obj.dialect.doublequote, False) + self.assertEqual(obj.dialect.escapechar, '\\') + self.assertEqual(obj.dialect.lineterminator, "\r") + self.assertEqual(obj.dialect.quotechar, '*') + self.assertEqual(obj.dialect.quoting, csv.QUOTE_NONE) + self.assertEqual(obj.dialect.skipinitialspace, True) + self.assertEqual(obj.dialect.strict, True) + + def test_reader_kw_attrs(self): + self._test_kw_attrs(csv.reader, []) + + def test_writer_kw_attrs(self): + self._test_kw_attrs(csv.writer, BytesIO()) + + def _test_dialect_attrs(self, ctor, *args): + # Now try with dialect-derived options + class dialect: + delimiter = '-' + doublequote = False + escapechar = '^' + lineterminator = '$' + quotechar = '#' + quoting = csv.QUOTE_ALL + skipinitialspace = True + strict = False + args = args + (dialect,) + obj = ctor(*args) + self.assertEqual(obj.dialect.delimiter, '-') + self.assertEqual(obj.dialect.doublequote, False) + self.assertEqual(obj.dialect.escapechar, '^') + self.assertEqual(obj.dialect.lineterminator, "$") + self.assertEqual(obj.dialect.quotechar, '#') + self.assertEqual(obj.dialect.quoting, csv.QUOTE_ALL) + self.assertEqual(obj.dialect.skipinitialspace, True) + self.assertEqual(obj.dialect.strict, False) + + def test_reader_dialect_attrs(self): + self._test_dialect_attrs(csv.reader, []) + + def test_writer_dialect_attrs(self): + self._test_dialect_attrs(csv.writer, BytesIO()) + + def _write_test(self, fields, expect, **kwargs): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, **kwargs) + writer.writerow(fields) + fileobj.seek(0) + self.assertEqual(fileobj.read(), + expect + writer.dialect.lineterminator.encode('utf-8')) + finally: + fileobj.close() + os.unlink(name) + + def test_write_arg_valid(self): + import sys + pypy3 = hasattr(sys, 'pypy_version_info') and sys.version_info.major == 3 + + self.assertRaises(TypeError if pypy3 else csv.Error, self._write_test, None, '') + self._write_test((), b'') + self._write_test([None], b'""') + self.assertRaises(csv.Error, self._write_test, + [None], None, quoting=csv.QUOTE_NONE) + + # Check that exceptions are passed up the chain + class BadList: + def __len__(self): + return 10 + + def __getitem__(self, i): + if i > 2: + raise IOError + + self.assertRaises(IOError, self._write_test, BadList(), '') + + class BadItem: + def __str__(self): + raise IOError + + self.assertRaises(IOError, self._write_test, [BadItem()], '') + + def test_write_bigfield(self): + # This exercises the buffer realloc functionality + bigstring = 'X' * 50000 + self._write_test([bigstring, bigstring], + b','.join([bigstring.encode('utf-8')] * 2)) + + def test_write_quoting(self): + self._write_test(['a', 1, 'p,q'], b'a,1,"p,q"') + self.assertRaises(csv.Error, + self._write_test, + ['a', 1, 'p,q'], b'a,1,p,q', + quoting=csv.QUOTE_NONE) + self._write_test(['a', 1, 'p,q'], b'a,1,"p,q"', + quoting=csv.QUOTE_MINIMAL) + self._write_test(['a', 1, 'p,q'], b'"a",1,"p,q"', + quoting=csv.QUOTE_NONNUMERIC) + self._write_test(['a', 1, 'p,q'], b'"a","1","p,q"', + quoting=csv.QUOTE_ALL) + self._write_test(['a\nb', 1], b'"a\nb","1"', + quoting=csv.QUOTE_ALL) + + def test_write_decimal(self): + self._write_test(['a', decimal.Decimal("1.1"), 'p,q'], b'"a",1.1,"p,q"', + quoting=csv.QUOTE_NONNUMERIC) + + def test_write_escape(self): + self._write_test(['a', 1, 'p,q'], b'a,1,"p,q"', + escapechar='\\') + self.assertRaises(csv.Error, + self._write_test, + ['a', 1, 'p,"q"'], b'a,1,"p,\\"q\\""', + escapechar=None, doublequote=False) + self._write_test(['a', 1, 'p,"q"'], b'a,1,"p,\\"q\\""', + escapechar='\\', doublequote=False) + self._write_test(['"'], b'""""', + escapechar='\\', quoting=csv.QUOTE_MINIMAL) + self._write_test(['"'], b'\\"', + escapechar='\\', quoting=csv.QUOTE_MINIMAL, + doublequote=False) + self._write_test(['"'], b'\\"', + escapechar='\\', quoting=csv.QUOTE_NONE) + self._write_test(['a', 1, 'p,q'], b'a,1,p\\,q', + escapechar='\\', quoting=csv.QUOTE_NONE) + + def test_writerows(self): + class BrokenFile: + def write(self, buf): + raise IOError + + writer = csv.writer(BrokenFile()) + self.assertRaises(IOError, writer.writerows, [['a']]) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj) + self.assertRaises(TypeError, writer.writerows, None) + writer.writerows([['a', 'b'], ['c', 'd']]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"a,b\r\nc,d\r\n") + finally: + fileobj.close() + os.unlink(name) + + def _read_test(self, input, expect, **kwargs): + reader = csv.reader(input, **kwargs) + result = list(reader) + self.assertEqual(result, expect) + + def test_read_oddinputs(self): + self._read_test([], []) + self._read_test([b''], [[]]) + self.assertRaises(csv.Error, self._read_test, + [b'"ab"c'], None, strict=1) + # cannot handle null bytes for the moment + self.assertRaises(csv.Error, self._read_test, + [b'ab\0c'], None, strict=1) + self._read_test([b'"ab"c'], [['abc']], doublequote=0) + + def test_read_eol(self): + self._read_test([b'a,b'], [['a', 'b']]) + self._read_test([b'a,b\n'], [['a', 'b']]) + self._read_test([b'a,b\r\n'], [['a', 'b']]) + self._read_test([b'a,b\r'], [['a', 'b']]) + self.assertRaises(csv.Error, self._read_test, [b'a,b\rc,d'], []) + self.assertRaises(csv.Error, self._read_test, [b'a,b\nc,d'], []) + self.assertRaises(csv.Error, self._read_test, [b'a,b\r\nc,d'], []) + + def test_read_escape(self): + self._read_test([b'a,\\b,c'], [['a', 'b', 'c']], escapechar='\\') + self._read_test([b'a,b\\,c'], [['a', 'b,c']], escapechar='\\') + self._read_test([b'a,"b\\,c"'], [['a', 'b,c']], escapechar='\\') + self._read_test([b'a,"b,\\c"'], [['a', 'b,c']], escapechar='\\') + self._read_test([b'a,"b,c\\""'], [['a', 'b,c"']], escapechar='\\') + self._read_test([b'a,"b,c"\\'], [['a', 'b,c\\']], escapechar='\\') + + def test_read_quoting(self): + self._read_test([b'1,",3,",5'], [['1', ',3,', '5']]) + self._read_test([b'1,",3,",5'], [['1', '"', '3', '"', '5']], + quotechar=None, escapechar='\\') + self._read_test([b'1,",3,",5'], [['1', '"', '3', '"', '5']], + quoting=csv.QUOTE_NONE, escapechar='\\') + # will this fail where locale uses comma for decimals? + self._read_test([b',3,"5",7.3, 9'], [['', 3, '5', 7.3, 9]], + quoting=csv.QUOTE_NONNUMERIC) + self._read_test([b'"a\nb", 7'], [['a\nb', ' 7']]) + self.assertRaises(ValueError, self._read_test, + [b'abc,3'], [[]], + quoting=csv.QUOTE_NONNUMERIC) + + def test_read_linenum(self): + for r in (csv.reader([b'line,1', b'line,2', b'line,3']), + csv.DictReader([b'line,1', b'line,2', b'line,3'], + fieldnames=['a', 'b', 'c'])): + self.assertEqual(r.line_num, 0) + next(r) + self.assertEqual(r.line_num, 1) + next(r) + self.assertEqual(r.line_num, 2) + next(r) + self.assertEqual(r.line_num, 3) + self.assertRaises(StopIteration, next, r) + self.assertEqual(r.line_num, 3) + + def test_roundtrip_quoteed_newlines(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj) + self.assertRaises(TypeError, writer.writerows, None) + rows = [['a\nb', 'b'], ['c', 'x\r\nd']] + writer.writerows(rows) + fileobj.seek(0) + for i, row in enumerate(csv.reader(fileobj)): + self.assertEqual(row, rows[i]) + finally: + fileobj.close() + os.unlink(name) + + +class TestDialectRegistry(unittest.TestCase): + def test_registry_badargs(self): + self.assertRaises(TypeError, csv.list_dialects, None) + self.assertRaises(TypeError, csv.get_dialect) + self.assertRaises(csv.Error, csv.get_dialect, None) + self.assertRaises(csv.Error, csv.get_dialect, "nonesuch") + self.assertRaises(TypeError, csv.unregister_dialect) + self.assertRaises(csv.Error, csv.unregister_dialect, None) + self.assertRaises(csv.Error, csv.unregister_dialect, "nonesuch") + self.assertRaises(TypeError, csv.register_dialect, None) + self.assertRaises(TypeError, csv.register_dialect, None, None) + self.assertRaises(TypeError, csv.register_dialect, "nonesuch", 0, 0) + self.assertRaises(TypeError, csv.register_dialect, "nonesuch", + badargument=None) + self.assertRaises(TypeError, csv.register_dialect, "nonesuch", + quoting=None) + self.assertRaises(TypeError, csv.register_dialect, []) + + def test_registry(self): + class myexceltsv(csv.excel): + delimiter = "\t" + name = "myexceltsv" + expected_dialects = csv.list_dialects() + [name] + expected_dialects.sort() + csv.register_dialect(name, myexceltsv) + try: + self.assertEqual(csv.get_dialect(name).delimiter, '\t') + got_dialects = csv.list_dialects() + got_dialects.sort() + self.assertEqual(expected_dialects, got_dialects) + finally: + csv.unregister_dialect(name) + + def test_register_kwargs(self): + name = 'fedcba' + csv.register_dialect(name, delimiter=';') + try: + self.assertNotEqual(csv.get_dialect(name).delimiter, '\t') + self.assertEqual(list(csv.reader([b'X;Y;Z'], name)), [[u'X', u'Y', u'Z']]) + finally: + csv.unregister_dialect(name) + + def test_incomplete_dialect(self): + class myexceltsv(csv.Dialect): + delimiter = "\t" + self.assertRaises(csv.Error, myexceltsv) + + def test_space_dialect(self): + class space(csv.excel): + delimiter = " " + quoting = csv.QUOTE_NONE + escapechar = "\\" + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"abc def\nc1ccccc1 benzene\n") + fileobj.seek(0) + rdr = csv.reader(fileobj, dialect=space()) + self.assertEqual(next(rdr), ["abc", "def"]) + self.assertEqual(next(rdr), ["c1ccccc1", "benzene"]) + finally: + fileobj.close() + os.unlink(name) + + def test_dialect_apply(self): + class testA(csv.excel): + delimiter = "\t" + + class testB(csv.excel): + delimiter = ":" + + class testC(csv.excel): + delimiter = "|" + + csv.register_dialect('testC', testC) + try: + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj) + writer.writerow([1, 2, 3]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"1,2,3\r\n") + finally: + fileobj.close() + os.unlink(name) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, testA) + writer.writerow([1, 2, 3]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"1\t2\t3\r\n") + finally: + fileobj.close() + os.unlink(name) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect=testB()) + writer.writerow([1, 2, 3]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"1:2:3\r\n") + finally: + fileobj.close() + os.unlink(name) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect='testC') + writer.writerow([1, 2, 3]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"1|2|3\r\n") + finally: + fileobj.close() + os.unlink(name) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect=testA, delimiter=';') + writer.writerow([1, 2, 3]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), b"1;2;3\r\n") + finally: + fileobj.close() + os.unlink(name) + + finally: + csv.unregister_dialect('testC') + + def test_bad_dialect(self): + # Unknown parameter + self.assertRaises(TypeError, csv.reader, [], bad_attr=0) + # Bad values + self.assertRaises(TypeError, csv.reader, [], delimiter=None) + self.assertRaises(TypeError, csv.reader, [], quoting=-1) + self.assertRaises(TypeError, csv.reader, [], quoting=100) + + +class TestCsvBase(unittest.TestCase): + def readerAssertEqual(self, input, expected_result): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(input) + fileobj.seek(0) + reader = csv.reader(fileobj, dialect=self.dialect) + fields = list(reader) + self.assertEqual(fields, expected_result) + finally: + fileobj.close() + os.unlink(name) + + def writerAssertEqual(self, input, expected_result): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect=self.dialect) + writer.writerows(input) + fileobj.seek(0) + self.assertEqual(fileobj.read(), expected_result) + finally: + fileobj.close() + os.unlink(name) + + +class TestDialectExcel(TestCsvBase): + dialect = 'excel' + + def test_single(self): + self.readerAssertEqual(b'abc', [['abc']]) + + def test_simple(self): + self.readerAssertEqual(b'1,2,3,4,5', [['1', '2', '3', '4', '5']]) + + def test_blankline(self): + self.readerAssertEqual(b'', []) + + def test_empty_fields(self): + self.readerAssertEqual(b',', [['', '']]) + + def test_singlequoted(self): + self.readerAssertEqual(b'""', [['']]) + + def test_singlequoted_left_empty(self): + self.readerAssertEqual(b'"",', [['', '']]) + + def test_singlequoted_right_empty(self): + self.readerAssertEqual(b',""', [['', '']]) + + def test_single_quoted_quote(self): + self.readerAssertEqual(b'""""', [['"']]) + + def test_quoted_quotes(self): + self.readerAssertEqual(b'""""""', [['""']]) + + def test_inline_quote(self): + self.readerAssertEqual(b'a""b', [['a""b']]) + + def test_inline_quotes(self): + self.readerAssertEqual(b'a"b"c', [['a"b"c']]) + + def test_quotes_and_more(self): + # Excel would never write a field containing '"a"b', but when + # reading one, it will return 'ab'. + self.readerAssertEqual(b'"a"b', [['ab']]) + + def test_lone_quote(self): + self.readerAssertEqual(b'a"b', [['a"b']]) + + def test_quote_and_quote(self): + # Excel would never write a field containing '"a" "b"', but when + # reading one, it will return 'a "b"'. + self.readerAssertEqual(b'"a" "b"', [['a "b"']]) + + def test_space_and_quote(self): + self.readerAssertEqual(b' "a"', [[' "a"']]) + + def test_quoted(self): + self.readerAssertEqual(b'1,2,3,"I think, therefore I am",5,6', + [['1', '2', '3', + 'I think, therefore I am', + '5', '6']]) + + def test_quoted_quote(self): + value = b'1,2,3,"""I see,"" said the blind man","as he picked up his hammer and saw"' + self.readerAssertEqual(value, + [['1', '2', '3', + '"I see," said the blind man', + 'as he picked up his hammer and saw']]) + + def test_quoted_nl(self): + input = b'''\ +1,2,3,"""I see,"" +said the blind man","as he picked up his +hammer and saw" +9,8,7,6''' + self.readerAssertEqual(input, + [['1', '2', '3', + '"I see,"\nsaid the blind man', + 'as he picked up his\nhammer and saw'], + ['9', '8', '7', '6']]) + + def test_dubious_quote(self): + self.readerAssertEqual(b'12,12,1",', [['12', '12', '1"', '']]) + + def test_null(self): + self.writerAssertEqual([], b'') + + def test_single_writer(self): + self.writerAssertEqual([['abc']], b'abc\r\n') + + def test_simple_writer(self): + self.writerAssertEqual([[1, 2, 'abc', 3, 4]], + b'1,2,abc,3,4\r\n') + + def test_quotes(self): + self.writerAssertEqual([[1, 2, 'a"bc"', 3, 4]], + b'1,2,"a""bc""",3,4\r\n') + + def test_quote_fieldsep(self): + self.writerAssertEqual([['abc,def']], + b'"abc,def"\r\n') + + def test_newlines(self): + self.writerAssertEqual([[1, 2, 'a\nbc', 3, 4]], + b'1,2,"a\nbc",3,4\r\n') + + +class EscapedExcel(csv.excel): + quoting = csv.QUOTE_NONE + escapechar = '\\' + + +class TestEscapedExcel(TestCsvBase): + dialect = EscapedExcel() + + def test_escape_fieldsep(self): + self.writerAssertEqual([['abc,def']], b'abc\\,def\r\n') + + def test_read_escape_fieldsep(self): + self.readerAssertEqual(b'abc\\,def\r\n', [['abc,def']]) + + +class QuotedEscapedExcel(csv.excel): + quoting = csv.QUOTE_NONNUMERIC + escapechar = '\\' + + +class TestQuotedEscapedExcel(TestCsvBase): + dialect = QuotedEscapedExcel() + + def test_write_escape_fieldsep(self): + self.writerAssertEqual([['abc,def']], b'"abc,def"\r\n') + + def test_read_escape_fieldsep(self): + self.readerAssertEqual(b'"abc\\,def"\r\n', [['abc,def']]) + + +class TestDictFields(unittest.TestCase): + # "long" means the row is longer than the number of fieldnames + # "short" means there are fewer elements in the row than fieldnames + def test_write_simple_dict(self): + fd, name = tempfile.mkstemp() + fileobj = open(name, 'w+b') + try: + writer = csv.DictWriter(fileobj, fieldnames=["f1", "f2", "f3"]) + writer.writeheader() + fileobj.seek(0) + self.assertEqual(fileobj.readline(), b"f1,f2,f3\r\n") + writer.writerow({"f1": 10, "f3": "abc"}) + fileobj.seek(0) + fileobj.readline() # header + self.assertEqual(fileobj.read(), b"10,,abc\r\n") + finally: + fileobj.close() + os.unlink(name) + + def test_write_unicode_header_dict(self): + fd, name = tempfile.mkstemp() + fileobj = open(name, 'w+b') + try: + writer = csv.DictWriter(fileobj, fieldnames=[u"ñ", u"ö"]) + writer.writeheader() + fileobj.seek(0) + self.assertEqual(fileobj.readline().decode('utf-8'), u"ñ,ö\r\n") + finally: + fileobj.close() + os.unlink(name) + + def test_write_no_fields(self): + fileobj = BytesIO() + self.assertRaises(TypeError, csv.DictWriter, fileobj) + + def test_read_dict_fields(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"1,2,abc\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj, + fieldnames=["f1", "f2", "f3"]) + self.assertEqual(next(reader), + {"f1": '1', "f2": '2', "f3": 'abc'}) + finally: + fileobj.close() + os.unlink(name) + + def test_read_dict_no_fieldnames(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"f1,f2,f3\r\n1,2,abc\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj) + self.assertEqual(reader.fieldnames, + ["f1", "f2", "f3"]) + self.assertEqual(next(reader), + {"f1": '1', "f2": '2', "f3": 'abc'}) + finally: + fileobj.close() + os.unlink(name) + + # Two test cases to make sure existing ways of implicitly setting + # fieldnames continue to work. Both arise from discussion in issue3436. + def test_read_dict_fieldnames_from_file(self): + fd, name = tempfile.mkstemp() + f = os.fdopen(fd, "w+b") + try: + f.write(b"f1,f2,f3\r\n1,2,abc\r\n") + f.seek(0) + reader = csv.DictReader(f, fieldnames=next(csv.reader(f))) + self.assertEqual(reader.fieldnames, + ["f1", "f2", "f3"]) + self.assertEqual(next(reader), + {"f1": '1', "f2": '2', "f3": 'abc'}) + finally: + f.close() + os.unlink(name) + + def test_read_dict_fieldnames_chain(self): + import itertools + fd, name = tempfile.mkstemp() + f = os.fdopen(fd, "w+b") + try: + f.write(b"f1,f2,f3\r\n1,2,abc\r\n") + f.seek(0) + reader = csv.DictReader(f) + first = next(reader) + for row in itertools.chain([first], reader): + self.assertEqual(reader.fieldnames, ["f1", "f2", "f3"]) + self.assertEqual(row, {"f1": '1', "f2": '2', "f3": 'abc'}) + finally: + f.close() + os.unlink(name) + + def test_read_long(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"1,2,abc,4,5,6\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj, + fieldnames=["f1", "f2"]) + self.assertEqual(next(reader), {"f1": '1', "f2": '2', + None: ["abc", "4", "5", "6"]}) + finally: + fileobj.close() + os.unlink(name) + + def test_read_long_with_rest(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"1,2,abc,4,5,6\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj, + fieldnames=["f1", "f2"], restkey="_rest") + self.assertEqual(next(reader), {"f1": '1', "f2": '2', + "_rest": ["abc", "4", "5", "6"]}) + finally: + fileobj.close() + os.unlink(name) + + def test_read_long_with_rest_no_fieldnames(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"f1,f2\r\n1,2,abc,4,5,6\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj, restkey="_rest") + self.assertEqual(reader.fieldnames, ["f1", "f2"]) + self.assertEqual(next(reader), {"f1": '1', "f2": '2', + "_rest": ["abc", "4", "5", "6"]}) + finally: + fileobj.close() + os.unlink(name) + + def test_read_short(self): + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + fileobj.write(b"1,2,abc,4,5,6\r\n1,2,abc\r\n") + fileobj.seek(0) + reader = csv.DictReader(fileobj, + fieldnames="1 2 3 4 5 6".split(), + restval="DEFAULT") + self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc', + "4": '4', "5": '5', "6": '6'}) + self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc', + "4": 'DEFAULT', "5": 'DEFAULT', + "6": 'DEFAULT'}) + finally: + fileobj.close() + os.unlink(name) + + def test_read_multi(self): + sample = [ + b'2147483648,43.0e12,17,abc,def\r\n', + b'147483648,43.0e2,17,abc,def\r\n', + b'47483648,43.0,170,abc,def\r\n' + ] + + reader = csv.DictReader(sample, + fieldnames="i1 float i2 s1 s2".split()) + self.assertEqual(next(reader), {"i1": '2147483648', + "float": '43.0e12', + "i2": '17', + "s1": 'abc', + "s2": 'def'}) + + def test_read_with_blanks(self): + reader = csv.DictReader([b"1,2,abc,4,5,6\r\n", b"\r\n", + b"1,2,abc,4,5,6\r\n"], + fieldnames="1 2 3 4 5 6".split()) + self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc', + "4": '4', "5": '5', "6": '6'}) + self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc', + "4": '4', "5": '5', "6": '6'}) + + def test_read_semi_sep(self): + reader = csv.DictReader([b"1;2;abc;4;5;6\r\n"], + fieldnames="1 2 3 4 5 6".split(), + delimiter=';') + self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc', + "4": '4', "5": '5', "6": '6'}) + + def test_empty_file(self): + csv.DictReader(BytesIO()) + +class TestArrayWrites(unittest.TestCase): + def test_int_write(self): + contents = [(20-i) for i in range(20)] + a = array.array('i', contents) + + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect="excel") + writer.writerow(a) + expected = b",".join([str(i).encode('utf-8') for i in a])+b"\r\n" + fileobj.seek(0) + self.assertEqual(fileobj.read(), expected) + finally: + fileobj.close() + os.unlink(name) + + def test_double_write(self): + contents = [(20-i)*0.1 for i in range(20)] + a = array.array('d', contents) + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect="excel") + writer.writerow(a) + float_repr = str + if sys.version_info >= (2, 7, 3): + float_repr = repr + expected = b",".join([float_repr(i).encode('utf-8') for i in a])+b"\r\n" + fileobj.seek(0) + self.assertEqual(fileobj.read(), expected) + finally: + fileobj.close() + os.unlink(name) + + def test_float_write(self): + contents = [(20-i)*0.1 for i in range(20)] + a = array.array('f', contents) + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect="excel") + writer.writerow(a) + float_repr = str + if sys.version_info >= (2, 7, 3): + float_repr = repr + expected = b",".join([float_repr(i).encode('utf-8') for i in a])+b"\r\n" + fileobj.seek(0) + self.assertEqual(fileobj.read(), expected) + finally: + fileobj.close() + os.unlink(name) + + def test_char_write(self): + a = string.ascii_letters + fd, name = tempfile.mkstemp() + fileobj = os.fdopen(fd, "w+b") + try: + writer = csv.writer(fileobj, dialect="excel") + writer.writerow(a) + expected = ",".join(a).encode('utf-8')+b"\r\n" + fileobj.seek(0) + self.assertEqual(fileobj.read(), expected) + finally: + fileobj.close() + os.unlink(name) + + +class TestUnicode(unittest.TestCase): + def test_unicode_read(self): + f = EncodedFile(BytesIO((u"Martin von Löwis," + u"Marc André Lemburg," + u"Guido van Rossum," + u"François Pinard\r\n").encode('iso-8859-1')), + data_encoding='iso-8859-1') + reader = csv.reader(f, encoding='iso-8859-1') + self.assertEqual(list(reader), [[u"Martin von Löwis", + u"Marc André Lemburg", + u"Guido van Rossum", + u"François Pinard"]]) + + +class TestUnicodeErrors(unittest.TestCase): + def test_encode_error(self): + fd = BytesIO() + writer = csv.writer(fd, encoding='cp1252', errors='xmlcharrefreplace') + writer.writerow(['hello', chr(2603)]) + self.assertEqual(fd.getvalue(), b'hello,ਫ\r\n') + + def test_encode_error_dictwriter(self): + fd = BytesIO() + dw = csv.DictWriter(fd, ['col1'], + encoding='cp1252', errors='xmlcharrefreplace') + dw.writerow({'col1': chr(2604)}) + self.assertEqual(fd.getvalue(), b'ਬ\r\n') + + def test_decode_error(self): + """Make sure the specified error-handling mode is obeyed on readers.""" + file = EncodedFile(BytesIO(u'Löwis,2,3'.encode('iso-8859-1')), + data_encoding='iso-8859-1') + reader = csv.reader(file, encoding='ascii', errors='ignore') + self.assertEqual(list(reader)[0][0], 'Lwis') + + def test_decode_error_dictreader(self): + """Make sure the error-handling mode is obeyed on DictReaders.""" + file = EncodedFile(BytesIO(u'name,height,weight\nLöwis,2,3'.encode('iso-8859-1')), + data_encoding='iso-8859-1') + reader = csv.DictReader(file, encoding='ascii', errors='ignore') + self.assertEqual(list(reader)[0]['name'], 'Lwis') -- cgit 1.2.3-korg