From 8b6e426044251a673ab277ebb88e3b7c0cea9557 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Wed, 12 Jul 2017 19:43:59 -0700
Subject: [PATCH 01/14] Added http(s) basic auth and allow self signed ssl
 certs

---
 pandas/io/common.py            | 71 ++++++++++++++++++++++++++++++++--
 pandas/io/excel.py             | 16 ++++++--
 pandas/io/html.py              | 46 ++++++++++++++++------
 pandas/io/json/json.py         | 12 +++++-
 pandas/io/parsers.py           | 22 +++++++++--
 pandas/tests/io/test_common.py | 11 ++++++
 6 files changed, 155 insertions(+), 23 deletions(-)

diff --git a/pandas/io/common.py b/pandas/io/common.py
index cbfc33dbebb81..247a01026b16f 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -4,6 +4,8 @@
 import csv
 import codecs
 import mmap
+import ssl
+import base64
 from contextlib import contextmanager, closing
 
 from pandas.compat import StringIO, BytesIO, string_types, text_type
@@ -49,7 +51,11 @@
 
 
 if compat.PY3:
-    from urllib.request import urlopen, pathname2url
+    from urllib.request import (urlopen, pathname2url, build_opener,
+                                install_opener,
+                                HTTPPasswordMgrWithDefaultRealm,
+                                HTTPBasicAuthHandler,
+                                HTTPSHandler)
     _urlopen = urlopen
     from urllib.parse import urlparse as parse_url
     from urllib.parse import (uses_relative, uses_netloc, uses_params,
@@ -58,6 +64,7 @@
     from http.client import HTTPException  # noqa
 else:
     from urllib2 import urlopen as _urlopen
+    from urllib2 import Request
     from urllib import urlencode, pathname2url  # noqa
     from urlparse import urlparse as parse_url
     from urlparse import uses_relative, uses_netloc, uses_params, urljoin
@@ -177,7 +184,8 @@ def _stringify_path(filepath_or_buffer):
 
 
 def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
-                           compression=None):
+                           compression=None, username=None,
+                           password=None, verify_ssl=None):
     """
     If the filepath_or_buffer is a url, translate and return the buffer.
     Otherwise passthrough.
@@ -186,7 +194,13 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     ----------
     filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                          or buffer
+            support 'https://username:password@fqdn.com:port/aaa.csv'
     encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
+    compression:
+    username: Authentication username (for https basic auth)
+    password: Authentication password (for https basic auth)
+    verify_ssl: Default True. If False, allow self signed and invalid SSL
+                 certificates for https
 
     Returns
     -------
@@ -195,7 +209,11 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     filepath_or_buffer = _stringify_path(filepath_or_buffer)
 
     if _is_url(filepath_or_buffer):
-        req = _urlopen(filepath_or_buffer)
+        ureq, kwargs = get_urlopen_args(filepath_or_buffer,
+                                        uname=username,
+                                        pwd=password,
+                                        verify_ssl=verify_ssl)
+        req = _urlopen(ureq, **kwargs)
         content_encoding = req.headers.get('Content-Encoding', None)
         if content_encoding == 'gzip':
             # Override compression based on Content-Encoding header
@@ -244,6 +262,53 @@ def file_path_to_url(path):
 }
 
 
+def split_uname_from_url(url_with_uname):
+    o = parse_url(url_with_uname)
+    usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
+    url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
+    return o.username, o.password, url_no_usrpwd
+
+
+def get_urlopen_args(url_with_uname, uname=None, pwd=None, verify_ssl=True):
+    if not uname and not pwd:
+        uname, pwd, url_no_usrpwd = split_uname_from_url(url_with_uname)
+    else:
+        url_no_usrpwd = url_with_uname
+    if compat.PY3:
+        fn = get_urlopen_args_py3
+    else:
+        fn = get_urlopen_args_py2
+    req, kwargs = fn(uname, pwd, url_no_usrpwd, verify_ssl=verify_ssl)
+    return req, kwargs
+
+
+def get_urlopen_args_py2(uname, pwd, url_no_usrpwd, verify_ssl=True):
+    req = Request(url_no_usrpwd)
+    upstr = '{}:{}'.format(uname, pwd)
+    base64string = base64.encodestring(upstr).replace('\n', '')
+    req.add_header("Authorization", "Basic {}".format(base64string))
+    # I hope pandas can support self signed certs too
+    kwargs = {}
+    if verify_ssl not in [None, True]:
+        kwargs['context'] = ssl._create_unverified_context()
+    return req, kwargs
+
+
+def get_urlopen_args_py3(uname, pwd, url_no_usrpwd, verify_ssl=True):
+    passman = HTTPPasswordMgrWithDefaultRealm()
+    passman.add_password(None, url_no_usrpwd, uname, pwd)
+    authhandler = HTTPBasicAuthHandler(passman)
+    if verify_ssl in [None, True]:
+        opener = build_opener(authhandler)
+    else:
+        context = ssl.create_default_context()
+        context.check_hostname = False
+        context.verify_mode = ssl.CERT_NONE
+        opener = build_opener(authhandler, HTTPSHandler(context=context))
+    install_opener(opener)
+    return url_no_usrpwd, {}
+
+
 def _infer_compression(filepath_or_buffer, compression):
     """
     Get the compression method for filepath_or_buffer. If compression='infer',
diff --git a/pandas/io/excel.py b/pandas/io/excel.py
index 5db4603c37be0..3a3e994dce335 100644
--- a/pandas/io/excel.py
+++ b/pandas/io/excel.py
@@ -20,7 +20,7 @@
 from pandas.errors import EmptyDataError
 from pandas.io.common import (_is_url, _urlopen, _validate_header_arg,
                               get_filepath_or_buffer, _NA_VALUES,
-                              _stringify_path)
+                              _stringify_path, get_urlopen_args)
 from pandas.core.indexes.period import Period
 import pandas._libs.json as json
 from pandas.compat import (map, zip, reduce, range, lrange, u, add_metaclass,
@@ -200,7 +200,6 @@ def read_excel(io, sheet_name=0, header=0, skiprows=None, skip_footer=0,
                convert_float=True, converters=None, dtype=None,
                true_values=None, false_values=None, engine=None,
                squeeze=False, **kwds):
-
     # Can't use _deprecate_kwarg since sheetname=None has a special meaning
     if is_integer(sheet_name) and sheet_name == 0 and 'sheetname' in kwds:
         warnings.warn("The `sheetname` keyword is deprecated, use "
@@ -211,7 +210,11 @@ def read_excel(io, sheet_name=0, header=0, skiprows=None, skip_footer=0,
                         "Use just `sheet_name`")
 
     if not isinstance(io, ExcelFile):
-        io = ExcelFile(io, engine=engine)
+        io = ExcelFile(io,
+                       engine=engine,
+                       username=kwds.get('username', None),
+                       password=kwds.get('password', None),
+                       verify_ssl=kwds.get('verify_ssl', None))
 
     return io._parse_excel(
         sheetname=sheet_name, header=header, skiprows=skiprows, names=names,
@@ -259,7 +262,12 @@ def __init__(self, io, **kwds):
         # If io is a url, want to keep the data as bytes so can't pass
         # to get_filepath_or_buffer()
         if _is_url(self._io):
-            io = _urlopen(self._io)
+            verify_ssl = kwds.get('verify_ssl', None)
+            ureq, kwargs = get_urlopen_args(self._io,
+                                            uname=kwds.get('username', None),
+                                            pwd=kwds.get('password', None),
+                                            verify_ssl=verify_ssl)
+            io = _urlopen(ureq, **kwargs)
         elif not isinstance(self.io, (ExcelFile, xlrd.Book)):
             io, _, _ = get_filepath_or_buffer(self._io)
 
diff --git a/pandas/io/html.py b/pandas/io/html.py
index 2613f26ae5f52..3f4e2f2773983 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -15,7 +15,8 @@
 from pandas.core.dtypes.common import is_list_like
 from pandas.errors import EmptyDataError
 from pandas.io.common import (_is_url, urlopen,
-                              parse_url, _validate_header_arg)
+                              parse_url, _validate_header_arg,
+                              get_urlopen_args)
 from pandas.io.parsers import TextParser
 from pandas.compat import (lrange, lmap, u, string_types, iteritems,
                            raise_with_traceback, binary_type)
@@ -116,19 +117,22 @@ def _get_skiprows(skiprows):
                     type(skiprows).__name__)
 
 
-def _read(obj):
+def _read(obj, username=None, password=None, verify_ssl=None):
     """Try to read from a url, file or string.
 
     Parameters
     ----------
     obj : str, unicode, or file-like
-
+    username: username for http basic auth
+    password: password for http basic auth
+    verify_ssl: Default True. Set to False to disable cert verification
     Returns
     -------
     raw_text : str
     """
     if _is_url(obj):
-        with urlopen(obj) as url:
+        ureq, kwargs = get_urlopen_args(obj, username, password, verify_ssl)
+        with urlopen(ureq, **kwargs) as url:
             text = url.read()
     elif hasattr(obj, 'read'):
         text = obj.read()
@@ -187,11 +191,15 @@ class _HtmlFrameParser(object):
     functionality.
     """
 
-    def __init__(self, io, match, attrs, encoding):
+    def __init__(self, io, match, attrs, encoding, username=None,
+                 password=None, verify_ssl=None):
         self.io = io
         self.match = match
         self.attrs = attrs
         self.encoding = encoding
+        self.username = username
+        self.password = password
+        self.verify_ssl = verify_ssl
 
     def parse_tables(self):
         tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
@@ -444,7 +452,8 @@ def _parse_tables(self, doc, match, attrs):
         return result
 
     def _setup_build_doc(self):
-        raw_text = _read(self.io)
+        raw_text = _read(self.io, self.username,
+                         self.password, self.verify_ssl)
         if not raw_text:
             raise ValueError('No text parsed from document: %s' % self.io)
         return raw_text
@@ -731,8 +740,12 @@ def _parse(flavor, io, match, attrs, encoding, **kwargs):
     retained = None
     for flav in flavor:
         parser = _parser_dispatch(flav)
-        p = parser(io, compiled_match, attrs, encoding)
-
+        p = parser(io, compiled_match,
+                   attrs,
+                   encoding,
+                   username=kwargs.get('username', None),
+                   password=kwargs.get('password', None),
+                   verify_ssl=kwargs.get('verify_ssl', None))
         try:
             tables = p.parse_tables()
         except Exception as caught:
@@ -755,7 +768,8 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
               skiprows=None, attrs=None, parse_dates=False,
               tupleize_cols=False, thousands=',', encoding=None,
               decimal='.', converters=None, na_values=None,
-              keep_default_na=True):
+              keep_default_na=True, username=None, password=None,
+              verify_ssl=False):
     r"""Read HTML tables into a ``list`` of ``DataFrame`` objects.
 
     Parameters
@@ -856,7 +870,16 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
 
         .. versionadded:: 0.19.0
 
-    Returns
+    username : str, default None
+        username for HTTP(s) basic auth
+
+    password : str, default None
+        password for HTTP(s) basic auth
+
+    verify_ssl : bool, default True
+        If False, ssl certificate is not verified (allow self signed SSL certs)
+
+        Returns
     -------
     dfs : list of DataFrames
 
@@ -903,4 +926,5 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
                   parse_dates=parse_dates, tupleize_cols=tupleize_cols,
                   thousands=thousands, attrs=attrs, encoding=encoding,
                   decimal=decimal, converters=converters, na_values=na_values,
-                  keep_default_na=keep_default_na)
+                  keep_default_na=keep_default_na, username=username,
+                  password=password, verify_ssl=verify_ssl)
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
index 31907ad586817..823b24ed2bf4a 100644
--- a/pandas/io/json/json.py
+++ b/pandas/io/json/json.py
@@ -174,7 +174,7 @@ def write(self):
 def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
               convert_axes=True, convert_dates=True, keep_default_dates=True,
               numpy=False, precise_float=False, date_unit=None, encoding=None,
-              lines=False):
+              lines=False, username=None, password=None, verify_ssl=None):
     """
     Convert a JSON string to pandas object
 
@@ -263,6 +263,11 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
 
         .. versionadded:: 0.19.0
 
+    username: str, default None. Authentication username for HTTP(s) basic auth
+    passowrd: str, default None. Authentication password for HTTP(s) basic auth
+    verify_ssl: boolean, default None (True).
+                    If false, allow self siged SSL certificates
+
     Returns
     -------
     result : Series or DataFrame, depending on the value of `typ`.
@@ -321,7 +326,10 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
     """
 
     filepath_or_buffer, _, _ = get_filepath_or_buffer(path_or_buf,
-                                                      encoding=encoding)
+                                                      encoding=encoding,
+                                                      username=username,
+                                                      password=password,
+                                                      verify_ssl=verify_ssl)
     if isinstance(filepath_or_buffer, compat.string_types):
         try:
             exists = os.path.exists(filepath_or_buffer)
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
index 343bc7a74fde8..03997a918dd03 100755
--- a/pandas/io/parsers.py
+++ b/pandas/io/parsers.py
@@ -391,9 +391,13 @@ def _read(filepath_or_buffer, kwds):
         kwds['encoding'] = encoding
 
     compression = kwds.get('compression')
+    username = kwds.get('username', None)
+    password = kwds.get('password', None)
+    verify_ssl = kwds.get('verify_ssl', None)
     compression = _infer_compression(filepath_or_buffer, compression)
     filepath_or_buffer, _, compression = get_filepath_or_buffer(
-        filepath_or_buffer, encoding, compression)
+        filepath_or_buffer, encoding, compression, username, password,
+        verify_ssl)
     kwds['compression'] = compression
 
     if kwds.get('date_parser', None) is not None:
@@ -574,7 +578,14 @@ def parser_f(filepath_or_buffer,
                  low_memory=_c_parser_defaults['low_memory'],
                  buffer_lines=None,
                  memory_map=False,
-                 float_precision=None):
+                 float_precision=None,
+
+                 # Basic auth (http/https)
+                 username=None,
+                 password=None,
+
+                 # skip verify self signed SSL certificates
+                 verify_ssl=None):
 
         # Alias sep -> delimiter.
         if delimiter is None:
@@ -654,7 +665,12 @@ def parser_f(filepath_or_buffer,
                     mangle_dupe_cols=mangle_dupe_cols,
                     tupleize_cols=tupleize_cols,
                     infer_datetime_format=infer_datetime_format,
-                    skip_blank_lines=skip_blank_lines)
+                    skip_blank_lines=skip_blank_lines,
+
+                    username=username,
+                    password=password,
+                    verify_ssl=verify_ssl
+                    )
 
         return _read(filepath_or_buffer, kwds)
 
diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
index b527e3c5dc254..9964e41efa9bb 100644
--- a/pandas/tests/io/test_common.py
+++ b/pandas/tests/io/test_common.py
@@ -190,6 +190,17 @@ def test_write_fspath_hdf5(self):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_split_url_extract_uname_pwd(self):
+        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
+                                       'aaa',
+                                       'bbb',
+                                       'https://ccc.com:1010/aaa.txt'
+                                       )]:
+            un, p, u = common.split_uname_from_url(url)
+            assert u == nurl
+            assert un == uname
+            assert p == pwd
+
 
 class TestMMapWrapper(object):
 

From 145c7f4b9f6ff2c1e677432f8134057a7c41d2d4 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Wed, 12 Jul 2017 21:42:13 -0700
Subject: [PATCH 02/14] Change username pwd to auth (username, password)

---
 pandas/io/common.py            | 86 +++++++++++++++++-----------------
 pandas/io/excel.py             |  6 +--
 pandas/io/html.py              | 32 +++++--------
 pandas/io/json/json.py         |  8 ++--
 pandas/io/parsers.py           | 13 ++---
 pandas/tests/io/test_common.py | 11 -----
 6 files changed, 65 insertions(+), 91 deletions(-)

diff --git a/pandas/io/common.py b/pandas/io/common.py
index 247a01026b16f..72387993a740f 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -184,8 +184,8 @@ def _stringify_path(filepath_or_buffer):
 
 
 def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
-                           compression=None, username=None,
-                           password=None, verify_ssl=None):
+                           compression=None, auth=None,
+                           verify_ssl=None):
     """
     If the filepath_or_buffer is a url, translate and return the buffer.
     Otherwise passthrough.
@@ -194,11 +194,10 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     ----------
     filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                          or buffer
-            support 'https://username:password@fqdn.com:port/aaa.csv'
+            supports 'https://username:password@fqdn.com:port/aaa.csv'
     encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
     compression:
-    username: Authentication username (for https basic auth)
-    password: Authentication password (for https basic auth)
+    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
     verify_ssl: Default True. If False, allow self signed and invalid SSL
                  certificates for https
 
@@ -210,8 +209,7 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
 
     if _is_url(filepath_or_buffer):
         ureq, kwargs = get_urlopen_args(filepath_or_buffer,
-                                        uname=username,
-                                        pwd=password,
+                                        auth=auth,
                                         verify_ssl=verify_ssl)
         req = _urlopen(ureq, **kwargs)
         content_encoding = req.headers.get('Content-Encoding', None)
@@ -262,16 +260,45 @@ def file_path_to_url(path):
 }
 
 
-def split_uname_from_url(url_with_uname):
-    o = parse_url(url_with_uname)
-    usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
-    url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
-    return o.username, o.password, url_no_usrpwd
-
-
-def get_urlopen_args(url_with_uname, uname=None, pwd=None, verify_ssl=True):
+def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
+    def split_auth_from_url(url_with_uname):
+        o = parse_url(url_with_uname)
+        usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
+        url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
+        return (o.username, o.password), url_no_usrpwd
+
+    def get_urlopen_args_py2(uname, pwd, url_no_usrpwd, verify_ssl=True):
+        req = Request(url_no_usrpwd)
+        upstr = '{}:{}'.format(uname, pwd)
+        base64string = base64.encodestring(upstr).replace('\n', '')
+        req.add_header("Authorization", "Basic {}".format(base64string))
+        # I hope pandas can support self signed certs too
+        kwargs = {}
+        if verify_ssl not in [None, True]:
+            kwargs['context'] = ssl._create_unverified_context()
+        return req, kwargs
+
+    def get_urlopen_args_py3(uname, pwd, url_no_usrpwd, verify_ssl=True):
+        # not using urllib.request Request for PY3 because
+        # this looks like better code from extensibility purpose
+        passman = HTTPPasswordMgrWithDefaultRealm()
+        passman.add_password(None, url_no_usrpwd, uname, pwd)
+        authhandler = HTTPBasicAuthHandler(passman)
+        if verify_ssl in [None, True]:
+            opener = build_opener(authhandler)
+        else:
+            context = ssl.create_default_context()
+            context.check_hostname = False
+            context.verify_mode = ssl.CERT_NONE
+            opener = build_opener(authhandler, HTTPSHandler(context=context))
+        install_opener(opener)
+        return url_no_usrpwd, {}
+
+    uname = pwd = None
+    if auth and len(auth) == 2:
+        uname, pwd = auth
     if not uname and not pwd:
-        uname, pwd, url_no_usrpwd = split_uname_from_url(url_with_uname)
+        (uname, pwd), url_no_usrpwd = split_auth_from_url(url_with_uname)
     else:
         url_no_usrpwd = url_with_uname
     if compat.PY3:
@@ -282,33 +309,6 @@ def get_urlopen_args(url_with_uname, uname=None, pwd=None, verify_ssl=True):
     return req, kwargs
 
 
-def get_urlopen_args_py2(uname, pwd, url_no_usrpwd, verify_ssl=True):
-    req = Request(url_no_usrpwd)
-    upstr = '{}:{}'.format(uname, pwd)
-    base64string = base64.encodestring(upstr).replace('\n', '')
-    req.add_header("Authorization", "Basic {}".format(base64string))
-    # I hope pandas can support self signed certs too
-    kwargs = {}
-    if verify_ssl not in [None, True]:
-        kwargs['context'] = ssl._create_unverified_context()
-    return req, kwargs
-
-
-def get_urlopen_args_py3(uname, pwd, url_no_usrpwd, verify_ssl=True):
-    passman = HTTPPasswordMgrWithDefaultRealm()
-    passman.add_password(None, url_no_usrpwd, uname, pwd)
-    authhandler = HTTPBasicAuthHandler(passman)
-    if verify_ssl in [None, True]:
-        opener = build_opener(authhandler)
-    else:
-        context = ssl.create_default_context()
-        context.check_hostname = False
-        context.verify_mode = ssl.CERT_NONE
-        opener = build_opener(authhandler, HTTPSHandler(context=context))
-    install_opener(opener)
-    return url_no_usrpwd, {}
-
-
 def _infer_compression(filepath_or_buffer, compression):
     """
     Get the compression method for filepath_or_buffer. If compression='infer',
diff --git a/pandas/io/excel.py b/pandas/io/excel.py
index 3a3e994dce335..62a8cc670bd60 100644
--- a/pandas/io/excel.py
+++ b/pandas/io/excel.py
@@ -212,8 +212,7 @@ def read_excel(io, sheet_name=0, header=0, skiprows=None, skip_footer=0,
     if not isinstance(io, ExcelFile):
         io = ExcelFile(io,
                        engine=engine,
-                       username=kwds.get('username', None),
-                       password=kwds.get('password', None),
+                       auth=kwds.get('auth', None),
                        verify_ssl=kwds.get('verify_ssl', None))
 
     return io._parse_excel(
@@ -264,8 +263,7 @@ def __init__(self, io, **kwds):
         if _is_url(self._io):
             verify_ssl = kwds.get('verify_ssl', None)
             ureq, kwargs = get_urlopen_args(self._io,
-                                            uname=kwds.get('username', None),
-                                            pwd=kwds.get('password', None),
+                                            auth=kwds.get('auth', None),
                                             verify_ssl=verify_ssl)
             io = _urlopen(ureq, **kwargs)
         elif not isinstance(self.io, (ExcelFile, xlrd.Book)):
diff --git a/pandas/io/html.py b/pandas/io/html.py
index 3f4e2f2773983..f14050189de27 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -117,21 +117,20 @@ def _get_skiprows(skiprows):
                     type(skiprows).__name__)
 
 
-def _read(obj, username=None, password=None, verify_ssl=None):
+def _read(obj, auth=None, verify_ssl=None):
     """Try to read from a url, file or string.
 
     Parameters
     ----------
     obj : str, unicode, or file-like
-    username: username for http basic auth
-    password: password for http basic auth
+    auth: None or (username, password) for http basic auth
     verify_ssl: Default True. Set to False to disable cert verification
     Returns
     -------
     raw_text : str
     """
     if _is_url(obj):
-        ureq, kwargs = get_urlopen_args(obj, username, password, verify_ssl)
+        ureq, kwargs = get_urlopen_args(obj, auth, verify_ssl)
         with urlopen(ureq, **kwargs) as url:
             text = url.read()
     elif hasattr(obj, 'read'):
@@ -191,14 +190,13 @@ class _HtmlFrameParser(object):
     functionality.
     """
 
-    def __init__(self, io, match, attrs, encoding, username=None,
-                 password=None, verify_ssl=None):
+    def __init__(self, io, match, attrs, encoding, auth=None,
+                 verify_ssl=None):
         self.io = io
         self.match = match
         self.attrs = attrs
         self.encoding = encoding
-        self.username = username
-        self.password = password
+        self.auth = auth
         self.verify_ssl = verify_ssl
 
     def parse_tables(self):
@@ -452,8 +450,7 @@ def _parse_tables(self, doc, match, attrs):
         return result
 
     def _setup_build_doc(self):
-        raw_text = _read(self.io, self.username,
-                         self.password, self.verify_ssl)
+        raw_text = _read(self.io, self.auth, self.verify_ssl)
         if not raw_text:
             raise ValueError('No text parsed from document: %s' % self.io)
         return raw_text
@@ -743,8 +740,7 @@ def _parse(flavor, io, match, attrs, encoding, **kwargs):
         p = parser(io, compiled_match,
                    attrs,
                    encoding,
-                   username=kwargs.get('username', None),
-                   password=kwargs.get('password', None),
+                   auth=kwargs.get('auth', None),
                    verify_ssl=kwargs.get('verify_ssl', None))
         try:
             tables = p.parse_tables()
@@ -768,7 +764,7 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
               skiprows=None, attrs=None, parse_dates=False,
               tupleize_cols=False, thousands=',', encoding=None,
               decimal='.', converters=None, na_values=None,
-              keep_default_na=True, username=None, password=None,
+              keep_default_na=True, auth=None,
               verify_ssl=False):
     r"""Read HTML tables into a ``list`` of ``DataFrame`` objects.
 
@@ -870,11 +866,7 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
 
         .. versionadded:: 0.19.0
 
-    username : str, default None
-        username for HTTP(s) basic auth
-
-    password : str, default None
-        password for HTTP(s) basic auth
+    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
 
     verify_ssl : bool, default True
         If False, ssl certificate is not verified (allow self signed SSL certs)
@@ -926,5 +918,5 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
                   parse_dates=parse_dates, tupleize_cols=tupleize_cols,
                   thousands=thousands, attrs=attrs, encoding=encoding,
                   decimal=decimal, converters=converters, na_values=na_values,
-                  keep_default_na=keep_default_na, username=username,
-                  password=password, verify_ssl=verify_ssl)
+                  keep_default_na=keep_default_na, auth=auth,
+                  verify_ssl=verify_ssl)
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
index 823b24ed2bf4a..da627cf6a3b11 100644
--- a/pandas/io/json/json.py
+++ b/pandas/io/json/json.py
@@ -174,7 +174,7 @@ def write(self):
 def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
               convert_axes=True, convert_dates=True, keep_default_dates=True,
               numpy=False, precise_float=False, date_unit=None, encoding=None,
-              lines=False, username=None, password=None, verify_ssl=None):
+              lines=False, auth=None, verify_ssl=None):
     """
     Convert a JSON string to pandas object
 
@@ -263,8 +263,7 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
 
         .. versionadded:: 0.19.0
 
-    username: str, default None. Authentication username for HTTP(s) basic auth
-    passowrd: str, default None. Authentication password for HTTP(s) basic auth
+    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
     verify_ssl: boolean, default None (True).
                     If false, allow self siged SSL certificates
 
@@ -327,8 +326,7 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
 
     filepath_or_buffer, _, _ = get_filepath_or_buffer(path_or_buf,
                                                       encoding=encoding,
-                                                      username=username,
-                                                      password=password,
+                                                      auth=auth,
                                                       verify_ssl=verify_ssl)
     if isinstance(filepath_or_buffer, compat.string_types):
         try:
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
index 03997a918dd03..3b0572872eb30 100755
--- a/pandas/io/parsers.py
+++ b/pandas/io/parsers.py
@@ -391,12 +391,11 @@ def _read(filepath_or_buffer, kwds):
         kwds['encoding'] = encoding
 
     compression = kwds.get('compression')
-    username = kwds.get('username', None)
-    password = kwds.get('password', None)
+    auth = kwds.get('auth', None)
     verify_ssl = kwds.get('verify_ssl', None)
     compression = _infer_compression(filepath_or_buffer, compression)
     filepath_or_buffer, _, compression = get_filepath_or_buffer(
-        filepath_or_buffer, encoding, compression, username, password,
+        filepath_or_buffer, encoding, compression, auth,
         verify_ssl)
     kwds['compression'] = compression
 
@@ -580,9 +579,8 @@ def parser_f(filepath_or_buffer,
                  memory_map=False,
                  float_precision=None,
 
-                 # Basic auth (http/https)
-                 username=None,
-                 password=None,
+                 # Basic auth (http/https) (username, password)
+                 auth=None,
 
                  # skip verify self signed SSL certificates
                  verify_ssl=None):
@@ -667,8 +665,7 @@ def parser_f(filepath_or_buffer,
                     infer_datetime_format=infer_datetime_format,
                     skip_blank_lines=skip_blank_lines,
 
-                    username=username,
-                    password=password,
+                    auth=auth,
                     verify_ssl=verify_ssl
                     )
 
diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
index 9964e41efa9bb..b527e3c5dc254 100644
--- a/pandas/tests/io/test_common.py
+++ b/pandas/tests/io/test_common.py
@@ -190,17 +190,6 @@ def test_write_fspath_hdf5(self):
 
         tm.assert_frame_equal(result, expected)
 
-    def test_split_url_extract_uname_pwd(self):
-        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
-                                       'aaa',
-                                       'bbb',
-                                       'https://ccc.com:1010/aaa.txt'
-                                       )]:
-            un, p, u = common.split_uname_from_url(url)
-            assert u == nurl
-            assert un == uname
-            assert p == pwd
-
 
 class TestMMapWrapper(object):
 

From 947331688227a338e673f7dc24d9e0b7eba8fc1a Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 02:01:41 -0700
Subject: [PATCH 03/14] simplify and unify py2 vs py3

---
 pandas/io/common.py         |  57 ++---
 pandas/tests/test_common.py | 475 +++++++++++++++++++-----------------
 2 files changed, 273 insertions(+), 259 deletions(-)

diff --git a/pandas/io/common.py b/pandas/io/common.py
index 72387993a740f..d4fdddbadfd94 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -51,11 +51,7 @@
 
 
 if compat.PY3:
-    from urllib.request import (urlopen, pathname2url, build_opener,
-                                install_opener,
-                                HTTPPasswordMgrWithDefaultRealm,
-                                HTTPBasicAuthHandler,
-                                HTTPSHandler)
+    from urllib.request import urlopen, pathname2url, Request
     _urlopen = urlopen
     from urllib.parse import urlparse as parse_url
     from urllib.parse import (uses_relative, uses_netloc, uses_params,
@@ -260,40 +256,14 @@ def file_path_to_url(path):
 }
 
 
-def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
-    def split_auth_from_url(url_with_uname):
-        o = parse_url(url_with_uname)
-        usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
-        url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
-        return (o.username, o.password), url_no_usrpwd
-
-    def get_urlopen_args_py2(uname, pwd, url_no_usrpwd, verify_ssl=True):
-        req = Request(url_no_usrpwd)
-        upstr = '{}:{}'.format(uname, pwd)
-        base64string = base64.encodestring(upstr).replace('\n', '')
-        req.add_header("Authorization", "Basic {}".format(base64string))
-        # I hope pandas can support self signed certs too
-        kwargs = {}
-        if verify_ssl not in [None, True]:
-            kwargs['context'] = ssl._create_unverified_context()
-        return req, kwargs
-
-    def get_urlopen_args_py3(uname, pwd, url_no_usrpwd, verify_ssl=True):
-        # not using urllib.request Request for PY3 because
-        # this looks like better code from extensibility purpose
-        passman = HTTPPasswordMgrWithDefaultRealm()
-        passman.add_password(None, url_no_usrpwd, uname, pwd)
-        authhandler = HTTPBasicAuthHandler(passman)
-        if verify_ssl in [None, True]:
-            opener = build_opener(authhandler)
-        else:
-            context = ssl.create_default_context()
-            context.check_hostname = False
-            context.verify_mode = ssl.CERT_NONE
-            opener = build_opener(authhandler, HTTPSHandler(context=context))
-        install_opener(opener)
-        return url_no_usrpwd, {}
+def split_auth_from_url(url_with_uname):
+    o = parse_url(url_with_uname)
+    usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
+    url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
+    return (o.username, o.password), url_no_usrpwd
 
+
+def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
     uname = pwd = None
     if auth and len(auth) == 2:
         uname, pwd = auth
@@ -301,11 +271,16 @@ def get_urlopen_args_py3(uname, pwd, url_no_usrpwd, verify_ssl=True):
         (uname, pwd), url_no_usrpwd = split_auth_from_url(url_with_uname)
     else:
         url_no_usrpwd = url_with_uname
+    upstr = '{}:{}'.format(uname, pwd)
     if compat.PY3:
-        fn = get_urlopen_args_py3
+        b64str = base64.b64encode(bytes(upstr, 'ascii')).decode('utf-8')
     else:
-        fn = get_urlopen_args_py2
-    req, kwargs = fn(uname, pwd, url_no_usrpwd, verify_ssl=verify_ssl)
+        b64str = base64.encodestring(upstr).replace('\n', '')
+    req = Request(url_no_usrpwd)
+    req.add_header("Authorization", "Basic {}".format(b64str))
+    kwargs = {}
+    if verify_ssl not in [None, True]:
+        kwargs['context'] = ssl._create_unverified_context()
     return req, kwargs
 
 
diff --git a/pandas/tests/test_common.py b/pandas/tests/test_common.py
index 57479be4d989f..9964e41efa9bb 100644
--- a/pandas/tests/test_common.py
+++ b/pandas/tests/test_common.py
@@ -1,223 +1,262 @@
-# -*- coding: utf-8 -*-
-
+"""
+    Tests for the pandas.io.common functionalities
+"""
+import mmap
 import pytest
-import collections
-from functools import partial
-
-import numpy as np
+import os
+from os.path import isabs
 
-from pandas import Series, Timestamp
-from pandas.compat import range, lmap
-import pandas.core.common as com
+import pandas as pd
 import pandas.util.testing as tm
 
+from pandas.io import common
+from pandas.compat import is_platform_windows, StringIO
+
+from pandas import read_csv, concat
+
+try:
+    from pathlib import Path
+except ImportError:
+    pass
+
+try:
+    from py.path import local as LocalPath
+except ImportError:
+    pass
+
+
+class CustomFSPath(object):
+    """For testing fspath on unknown objects"""
+    def __init__(self, path):
+        self.path = path
+
+    def __fspath__(self):
+        return self.path
+
+
+HERE = os.path.dirname(__file__)
+
+
+class TestCommonIOCapabilities(object):
+    data1 = """index,A,B,C,D
+foo,2,3,4,5
+bar,7,8,9,10
+baz,12,13,14,15
+qux,12,13,14,15
+foo2,12,13,14,15
+bar2,12,13,14,15
+"""
+
+    def test_expand_user(self):
+        filename = '~/sometest'
+        expanded_name = common._expand_user(filename)
+
+        assert expanded_name != filename
+        assert isabs(expanded_name)
+        assert os.path.expanduser(filename) == expanded_name
+
+    def test_expand_user_normal_path(self):
+        filename = '/somefolder/sometest'
+        expanded_name = common._expand_user(filename)
+
+        assert expanded_name == filename
+        assert os.path.expanduser(filename) == expanded_name
+
+    def test_stringify_path_pathlib(self):
+        tm._skip_if_no_pathlib()
+
+        rel_path = common._stringify_path(Path('.'))
+        assert rel_path == '.'
+        redundant_path = common._stringify_path(Path('foo//bar'))
+        assert redundant_path == os.path.join('foo', 'bar')
+
+    def test_stringify_path_localpath(self):
+        tm._skip_if_no_localpath()
+
+        path = os.path.join('foo', 'bar')
+        abs_path = os.path.abspath(path)
+        lpath = LocalPath(path)
+        assert common._stringify_path(lpath) == abs_path
+
+    def test_stringify_path_fspath(self):
+        p = CustomFSPath('foo/bar.csv')
+        result = common._stringify_path(p)
+        assert result == 'foo/bar.csv'
+
+    def test_get_filepath_or_buffer_with_path(self):
+        filename = '~/sometest'
+        filepath_or_buffer, _, _ = common.get_filepath_or_buffer(filename)
+        assert filepath_or_buffer != filename
+        assert isabs(filepath_or_buffer)
+        assert os.path.expanduser(filename) == filepath_or_buffer
+
+    def test_get_filepath_or_buffer_with_buffer(self):
+        input_buffer = StringIO()
+        filepath_or_buffer, _, _ = common.get_filepath_or_buffer(input_buffer)
+        assert filepath_or_buffer == input_buffer
+
+    def test_iterator(self):
+        reader = read_csv(StringIO(self.data1), chunksize=1)
+        result = concat(reader, ignore_index=True)
+        expected = read_csv(StringIO(self.data1))
+        tm.assert_frame_equal(result, expected)
+
+        # GH12153
+        it = read_csv(StringIO(self.data1), chunksize=1)
+        first = next(it)
+        tm.assert_frame_equal(first, expected.iloc[[0]])
+        tm.assert_frame_equal(concat(it), expected.iloc[1:])
+
+    @pytest.mark.parametrize('reader, module, path', [
+        (pd.read_csv, 'os', os.path.join(HERE, 'data', 'iris.csv')),
+        (pd.read_table, 'os', os.path.join(HERE, 'data', 'iris.csv')),
+        (pd.read_fwf, 'os', os.path.join(HERE, 'data',
+                                         'fixed_width_format.txt')),
+        (pd.read_excel, 'xlrd', os.path.join(HERE, 'data', 'test1.xlsx')),
+        (pd.read_feather, 'feather', os.path.join(HERE, 'data',
+                                                  'feather-0_3_1.feather')),
+        (pd.read_hdf, 'tables', os.path.join(HERE, 'data', 'legacy_hdf',
+                                             'datetimetz_object.h5')),
+        (pd.read_stata, 'os', os.path.join(HERE, 'data', 'stata10_115.dta')),
+        (pd.read_sas, 'os', os.path.join(HERE, 'sas', 'data',
+                                         'test1.sas7bdat')),
+        (pd.read_json, 'os', os.path.join(HERE, 'json', 'data',
+                                          'tsframe_v012.json')),
+        (pd.read_msgpack, 'os', os.path.join(HERE, 'msgpack', 'data',
+                                             'frame.mp')),
+        (pd.read_pickle, 'os', os.path.join(HERE, 'data',
+                                            'categorical_0_14_1.pickle')),
+    ])
+    def test_read_fspath_all(self, reader, module, path):
+        pytest.importorskip(module)
+
+        mypath = CustomFSPath(path)
+        result = reader(mypath)
+        expected = reader(path)
+        if path.endswith('.pickle'):
+            # categorical
+            tm.assert_categorical_equal(result, expected)
+        else:
+            tm.assert_frame_equal(result, expected)
+
+    @pytest.mark.parametrize('writer_name, writer_kwargs, module', [
+        ('to_csv', {}, 'os'),
+        ('to_excel', {'engine': 'xlwt'}, 'xlwt'),
+        ('to_feather', {}, 'feather'),
+        ('to_html', {}, 'os'),
+        ('to_json', {}, 'os'),
+        ('to_latex', {}, 'os'),
+        ('to_msgpack', {}, 'os'),
+        ('to_pickle', {}, 'os'),
+        ('to_stata', {}, 'os'),
+    ])
+    def test_write_fspath_all(self, writer_name, writer_kwargs, module):
+        p1 = tm.ensure_clean('string')
+        p2 = tm.ensure_clean('fspath')
+        df = pd.DataFrame({"A": [1, 2]})
+
+        with p1 as string, p2 as fspath:
+            pytest.importorskip(module)
+            mypath = CustomFSPath(fspath)
+            writer = getattr(df, writer_name)
+
+            writer(string, **writer_kwargs)
+            with open(string, 'rb') as f:
+                expected = f.read()
+
+            writer(mypath, **writer_kwargs)
+            with open(fspath, 'rb') as f:
+                result = f.read()
+
+            assert result == expected
+
+    def test_write_fspath_hdf5(self):
+        # Same test as write_fspath_all, except HDF5 files aren't
+        # necessarily byte-for-byte identical for a given dataframe, so we'll
+        # have to read and compare equality
+        pytest.importorskip('tables')
+
+        df = pd.DataFrame({"A": [1, 2]})
+        p1 = tm.ensure_clean('string')
+        p2 = tm.ensure_clean('fspath')
+
+        with p1 as string, p2 as fspath:
+            mypath = CustomFSPath(fspath)
+            df.to_hdf(mypath, key='bar')
+            df.to_hdf(string, key='bar')
+
+            result = pd.read_hdf(fspath, key='bar')
+            expected = pd.read_hdf(string, key='bar')
+
+        tm.assert_frame_equal(result, expected)
+
+    def test_split_url_extract_uname_pwd(self):
+        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
+                                       'aaa',
+                                       'bbb',
+                                       'https://ccc.com:1010/aaa.txt'
+                                       )]:
+            un, p, u = common.split_uname_from_url(url)
+            assert u == nurl
+            assert un == uname
+            assert p == pwd
+
+
+class TestMMapWrapper(object):
+
+    def setup_method(self, method):
+        self.mmap_file = os.path.join(tm.get_data_path(),
+                                      'test_mmap.csv')
+
+    def test_constructor_bad_file(self):
+        non_file = StringIO('I am not a file')
+        non_file.fileno = lambda: -1
+
+        # the error raised is different on Windows
+        if is_platform_windows():
+            msg = "The parameter is incorrect"
+            err = OSError
+        else:
+            msg = "[Errno 22]"
+            err = mmap.error
+
+        tm.assert_raises_regex(err, msg, common.MMapWrapper, non_file)
+
+        target = open(self.mmap_file, 'r')
+        target.close()
+
+        msg = "I/O operation on closed file"
+        tm.assert_raises_regex(
+            ValueError, msg, common.MMapWrapper, target)
+
+    def test_get_attr(self):
+        with open(self.mmap_file, 'r') as target:
+            wrapper = common.MMapWrapper(target)
+
+        attrs = dir(wrapper.mmap)
+        attrs = [attr for attr in attrs
+                 if not attr.startswith('__')]
+        attrs.append('__next__')
+
+        for attr in attrs:
+            assert hasattr(wrapper, attr)
+
+        assert not hasattr(wrapper, 'foo')
+
+    def test_next(self):
+        with open(self.mmap_file, 'r') as target:
+            wrapper = common.MMapWrapper(target)
+            lines = target.readlines()
+
+        for line in lines:
+            next_line = next(wrapper)
+            assert next_line.strip() == line.strip()
+
+        pytest.raises(StopIteration, next, wrapper)
 
-def test_mut_exclusive():
-    msg = "mutually exclusive arguments: '[ab]' and '[ab]'"
-    with tm.assert_raises_regex(TypeError, msg):
-        com._mut_exclusive(a=1, b=2)
-    assert com._mut_exclusive(a=1, b=None) == 1
-    assert com._mut_exclusive(major=None, major_axis=None) is None
-    assert com._mut_exclusive(a=None, b=2) == 2
-
-
-def test_get_callable_name():
-    from functools import partial
-    getname = com._get_callable_name
-
-    def fn(x):
-        return x
-
-    lambda_ = lambda x: x
-    part1 = partial(fn)
-    part2 = partial(part1)
-
-    class somecall(object):
-
-        def __call__(self):
-            return x  # noqa
-
-    assert getname(fn) == 'fn'
-    assert getname(lambda_)
-    assert getname(part1) == 'fn'
-    assert getname(part2) == 'fn'
-    assert getname(somecall()) == 'somecall'
-    assert getname(1) is None
-
-
-def test_any_none():
-    assert (com._any_none(1, 2, 3, None))
-    assert (not com._any_none(1, 2, 3, 4))
-
-
-def test_all_not_none():
-    assert (com._all_not_none(1, 2, 3, 4))
-    assert (not com._all_not_none(1, 2, 3, None))
-    assert (not com._all_not_none(None, None, None, None))
-
-
-def test_iterpairs():
-    data = [1, 2, 3, 4]
-    expected = [(1, 2), (2, 3), (3, 4)]
-
-    result = list(com.iterpairs(data))
-
-    assert (result == expected)
-
-
-def test_split_ranges():
-    def _bin(x, width):
-        "return int(x) as a base2 string of given width"
-        return ''.join(str((x >> i) & 1) for i in range(width - 1, -1, -1))
-
-    def test_locs(mask):
-        nfalse = sum(np.array(mask) == 0)
-
-        remaining = 0
-        for s, e in com.split_ranges(mask):
-            remaining += e - s
-
-            assert 0 not in mask[s:e]
-
-        # make sure the total items covered by the ranges are a complete cover
-        assert remaining + nfalse == len(mask)
-
-    # exhaustively test all possible mask sequences of length 8
-    ncols = 8
-    for i in range(2 ** ncols):
-        cols = lmap(int, list(_bin(i, ncols)))  # count up in base2
-        mask = [cols[i] == 1 for i in range(len(cols))]
-        test_locs(mask)
-
-    # base cases
-    test_locs([])
-    test_locs([0])
-    test_locs([1])
-
-
-def test_map_indices_py():
-    data = [4, 3, 2, 1]
-    expected = {4: 0, 3: 1, 2: 2, 1: 3}
-
-    result = com.map_indices_py(data)
-
-    assert (result == expected)
-
-
-def test_union():
-    a = [1, 2, 3]
-    b = [4, 5, 6]
-
-    union = sorted(com.union(a, b))
-
-    assert ((a + b) == union)
-
-
-def test_difference():
-    a = [1, 2, 3]
-    b = [1, 2, 3, 4, 5, 6]
-
-    inter = sorted(com.difference(b, a))
-
-    assert ([4, 5, 6] == inter)
-
-
-def test_intersection():
-    a = [1, 2, 3]
-    b = [1, 2, 3, 4, 5, 6]
-
-    inter = sorted(com.intersection(a, b))
-
-    assert (a == inter)
-
-
-def test_groupby():
-    values = ['foo', 'bar', 'baz', 'baz2', 'qux', 'foo3']
-    expected = {'f': ['foo', 'foo3'],
-                'b': ['bar', 'baz', 'baz2'],
-                'q': ['qux']}
-
-    grouped = com.groupby(values, lambda x: x[0])
-
-    for k, v in grouped:
-        assert v == expected[k]
-
-
-def test_random_state():
-    import numpy.random as npr
-    # Check with seed
-    state = com._random_state(5)
-    assert state.uniform() == npr.RandomState(5).uniform()
-
-    # Check with random state object
-    state2 = npr.RandomState(10)
-    assert (com._random_state(state2).uniform() ==
-            npr.RandomState(10).uniform())
-
-    # check with no arg random state
-    assert com._random_state() is np.random
-
-    # Error for floats or strings
-    with pytest.raises(ValueError):
-        com._random_state('test')
-
-    with pytest.raises(ValueError):
-        com._random_state(5.5)
-
-
-def test_maybe_match_name():
-
-    matched = com._maybe_match_name(
-        Series([1], name='x'), Series(
-            [2], name='x'))
-    assert (matched == 'x')
-
-    matched = com._maybe_match_name(
-        Series([1], name='x'), Series(
-            [2], name='y'))
-    assert (matched is None)
-
-    matched = com._maybe_match_name(Series([1]), Series([2], name='x'))
-    assert (matched is None)
-
-    matched = com._maybe_match_name(Series([1], name='x'), Series([2]))
-    assert (matched is None)
-
-    matched = com._maybe_match_name(Series([1], name='x'), [2])
-    assert (matched == 'x')
-
-    matched = com._maybe_match_name([1], Series([2], name='y'))
-    assert (matched == 'y')
-
-
-def test_dict_compat():
-    data_datetime64 = {np.datetime64('1990-03-15'): 1,
-                       np.datetime64('2015-03-15'): 2}
-    data_unchanged = {1: 2, 3: 4, 5: 6}
-    expected = {Timestamp('1990-3-15'): 1, Timestamp('2015-03-15'): 2}
-    assert (com._dict_compat(data_datetime64) == expected)
-    assert (com._dict_compat(expected) == expected)
-    assert (com._dict_compat(data_unchanged) == data_unchanged)
-
-
-def test_standardize_mapping():
-    # No uninitialized defaultdicts
-    with pytest.raises(TypeError):
-        com.standardize_mapping(collections.defaultdict)
-
-    # No non-mapping subtypes, instance
-    with pytest.raises(TypeError):
-        com.standardize_mapping([])
-
-    # No non-mapping subtypes, class
-    with pytest.raises(TypeError):
-        com.standardize_mapping(list)
-
-    fill = {'bad': 'data'}
-    assert (com.standardize_mapping(fill) == dict)
-
-    # Convert instance to type
-    assert (com.standardize_mapping({}) == dict)
-
-    dd = collections.defaultdict(list)
-    assert isinstance(com.standardize_mapping(dd), partial)
+    def test_unknown_engine(self):
+        with tm.ensure_clean() as path:
+            df = tm.makeDataFrame()
+            df.to_csv(path)
+            with tm.assert_raises_regex(ValueError, 'Unknown engine'):
+                read_csv(path, engine='pyt')

From 9c7524d9a5f5c9c6d520cd2b5e12f9cd4a34e17a Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 02:29:25 -0700
Subject: [PATCH 04/14] added temporary test script for
 https/basic-auth/unsigned ssl cert testing

---
 pandas/tests/test_basic_auth_self_signed.py | 36 +++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 pandas/tests/test_basic_auth_self_signed.py

diff --git a/pandas/tests/test_basic_auth_self_signed.py b/pandas/tests/test_basic_auth_self_signed.py
new file mode 100644
index 0000000000000..ba8e3db099def
--- /dev/null
+++ b/pandas/tests/test_basic_auth_self_signed.py
@@ -0,0 +1,36 @@
+# DO NOT MERGE
+# live working test that tests both scenarios:
+# pd.read_csv('https://uname:pwd@fqdn:<port>/fname.csv', verify_ssl=False)
+# pd.read_csv('https://fqdn:<port>/fname.csv', username='uname', password='pwd', verify_ssl=False)
+
+import pandas as pd
+
+uname='pandasusr'
+pwd='pandaspwd'
+url = 'https://{}pandastest.mooo.com:5000/'
+verify_ssl=False
+
+def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
+  furl = url + fname
+  kwargs = {}
+  if uname or pwd:
+    kwargs['auth']=(uname, pwd)
+  if verify_ssl is not None:
+    kwargs['verify_ssl']=verify_ssl
+  print('\n' +furl)
+  df = pd_read_fn(furl, **kwargs)
+  if type(df) is list: # html
+    df = df[0]
+  print(df.to_string(index=False))
+  print(df.to_json())
+
+fparams = [(pd.read_csv, 'aaa.csv'),
+           (pd.read_json, 'jdoc.json'),
+           (pd.read_excel, 'ex_doc.xlsx'),
+           (pd.read_html, 'html_file.html')]
+
+for pd_read_fn, fname in fparams:
+  u = url.format('{}:{}@'.format(uname, pwd))
+  get_df( u, None, None, verify_ssl, pd_read_fn, fname)
+  u2 = url.format('')
+  get_df( u2, uname, pwd, verify_ssl, pd_read_fn, fname)

From 598cf7bc53cda72d203c1dd78faeecbb63e7ed32 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 12:17:51 -0700
Subject: [PATCH 05/14] Updated comments. Removed test_basic_auth_self_signed

---
 pandas/io/common.py                         | 32 ++++++++++++++++++
 pandas/tests/io/test_common.py              | 19 +++++++++++
 pandas/tests/test_basic_auth_self_signed.py | 36 ---------------------
 3 files changed, 51 insertions(+), 36 deletions(-)
 delete mode 100644 pandas/tests/test_basic_auth_self_signed.py

diff --git a/pandas/io/common.py b/pandas/io/common.py
index d4fdddbadfd94..1d839bba71eeb 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -257,6 +257,21 @@ def file_path_to_url(path):
 
 
 def split_auth_from_url(url_with_uname):
+    """
+    If a url contains username and password, it is extracted and returned
+    along with a url that does not contain it.
+
+    Parameters
+    ----------
+    url_with_uname : a url that may or may not contain username and password
+            see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
+            //<user>:<password>@<host>:<port>/<url-path>
+
+    Returns
+    -------
+    (username, password), url_no_usrpwd : username or "", password or "", 
+         url without username or password (if it contained it )
+    """
     o = parse_url(url_with_uname)
     usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
     url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
@@ -264,6 +279,23 @@ def split_auth_from_url(url_with_uname):
 
 
 def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
+    """
+    generate args to pass to urlopen - including basic auth and and support
+    for disabling verification of SSL certificates ( useful where
+    self-signed SSL certificates are acceptable security risk -eg: Testing )
+
+    Parameters
+    ----------
+    url_with_uname : a url that may or may not contain username and password
+            see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
+            //<user>:<password>@<host>:<port>/<url-path>
+    auth : ( username/""/None, password/"", None) tuple
+    verify_ssl: If False, SSL certificate verification is disabled.
+
+    Returns
+    -------
+    Request, kwargs to pass to urlopen. kwargs may be {} or {'context': obj }
+    """
     uname = pwd = None
     if auth and len(auth) == 2:
         uname, pwd = auth
diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
index b527e3c5dc254..dd489cf37e015 100644
--- a/pandas/tests/io/test_common.py
+++ b/pandas/tests/io/test_common.py
@@ -190,6 +190,25 @@ def test_write_fspath_hdf5(self):
 
         tm.assert_frame_equal(result, expected)
 
+    def test_split_url_extract_uname_pwd(self):
+        """
+        Test extraction of username, pwd from url, if contained.
+        """
+        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
+                                       'aaa',
+                                       'bbb',
+                                       'https://ccc.com:1010/aaa.txt'
+                                       ),
+                                       ('https://ccc.com:1010/aaa.txt',
+                                       '',
+                                       '',
+                                       'https://ccc.com:1010/aaa.txt'
+                                       )]:
+            un, pw, mod_url = common.split_uname_from_url(url)
+            assert mod_url == nurl
+            assert un == uname
+            assert pw == pwd
+
 
 class TestMMapWrapper(object):
 
diff --git a/pandas/tests/test_basic_auth_self_signed.py b/pandas/tests/test_basic_auth_self_signed.py
deleted file mode 100644
index ba8e3db099def..0000000000000
--- a/pandas/tests/test_basic_auth_self_signed.py
+++ /dev/null
@@ -1,36 +0,0 @@
-# DO NOT MERGE
-# live working test that tests both scenarios:
-# pd.read_csv('https://uname:pwd@fqdn:<port>/fname.csv', verify_ssl=False)
-# pd.read_csv('https://fqdn:<port>/fname.csv', username='uname', password='pwd', verify_ssl=False)
-
-import pandas as pd
-
-uname='pandasusr'
-pwd='pandaspwd'
-url = 'https://{}pandastest.mooo.com:5000/'
-verify_ssl=False
-
-def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
-  furl = url + fname
-  kwargs = {}
-  if uname or pwd:
-    kwargs['auth']=(uname, pwd)
-  if verify_ssl is not None:
-    kwargs['verify_ssl']=verify_ssl
-  print('\n' +furl)
-  df = pd_read_fn(furl, **kwargs)
-  if type(df) is list: # html
-    df = df[0]
-  print(df.to_string(index=False))
-  print(df.to_json())
-
-fparams = [(pd.read_csv, 'aaa.csv'),
-           (pd.read_json, 'jdoc.json'),
-           (pd.read_excel, 'ex_doc.xlsx'),
-           (pd.read_html, 'html_file.html')]
-
-for pd_read_fn, fname in fparams:
-  u = url.format('{}:{}@'.format(uname, pwd))
-  get_df( u, None, None, verify_ssl, pd_read_fn, fname)
-  u2 = url.format('')
-  get_df( u2, uname, pwd, verify_ssl, pd_read_fn, fname)

From 3b454dd538e64b97c8a9734681f4417cd4b96372 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 12:49:49 -0700
Subject: [PATCH 06/14] Added what's new

---
 doc/source/whatsnew/v0.21.0.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/doc/source/whatsnew/v0.21.0.txt b/doc/source/whatsnew/v0.21.0.txt
index 039b24cc63217..eb4ecef232109 100644
--- a/doc/source/whatsnew/v0.21.0.txt
+++ b/doc/source/whatsnew/v0.21.0.txt
@@ -40,7 +40,8 @@ Other Enhancements
 - :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
 - :func:`Dataframe.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
-
+- :func:`read_csv` `read_html` `read_json` `read_html`  now accept auth in url //<user>:<password>@<host>:<port>/<url-path>, or ``auth`` tuple (username, password) parameter 
+- :func:`read_csv` `read_html` `read_json` `read_html`  now accept ``verify_ssl`` False to disable https/ssl certificate verification (eg: self signed ssl certs in testing) 
 .. _whatsnew_0210.api_breaking:
 
 Backwards incompatible API changes

From d359b2d53ffa33b8643fa276c04641cc5e0e94be Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 17:22:31 -0700
Subject: [PATCH 07/14] Updates to comments, etc + some change in username
 password logic

---
 doc/source/whatsnew/v0.21.0.txt |  4 +-
 pandas/io/common.py             | 86 ++++++++++++++++++++++++---------
 pandas/io/html.py               | 24 +++++++--
 pandas/io/json/json.py          | 13 +++--
 pandas/io/parsers.py            |  2 -
 pandas/tests/test_common.py     | 29 ++++++-----
 6 files changed, 113 insertions(+), 45 deletions(-)

diff --git a/doc/source/whatsnew/v0.21.0.txt b/doc/source/whatsnew/v0.21.0.txt
index eb4ecef232109..7baf87da18039 100644
--- a/doc/source/whatsnew/v0.21.0.txt
+++ b/doc/source/whatsnew/v0.21.0.txt
@@ -40,8 +40,8 @@ Other Enhancements
 - :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
 - :func:`Dataframe.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
-- :func:`read_csv` `read_html` `read_json` `read_html`  now accept auth in url //<user>:<password>@<host>:<port>/<url-path>, or ``auth`` tuple (username, password) parameter 
-- :func:`read_csv` `read_html` `read_json` `read_html`  now accept ``verify_ssl`` False to disable https/ssl certificate verification (eg: self signed ssl certs in testing) 
+- :func:`read_csv`, :func:`read_html`, :func:`read_json`, :func:`read_html`  now accept auth in url //<user>:<password>@<host>:<port>/<url-path>, or ``auth`` tuple (username, password) parameter 
+- :func:`read_csv`, :func:`read_html`, :func:`read_json`, :func:`read_html`  now accept ``verify_ssl`` False to disable https/ssl certificate verification (eg: self signed ssl certs in testing)  (:issue:`16716`)
 .. _whatsnew_0210.api_breaking:
 
 Backwards incompatible API changes
diff --git a/pandas/io/common.py b/pandas/io/common.py
index 1d839bba71eeb..f14fb43da2831 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -190,12 +190,27 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     ----------
     filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                          or buffer
-            supports 'https://username:password@fqdn.com:port/aaa.csv'
+            now supports 'https://<user>:<password>@<host>:<port>/<url-path>'
+            
+            .. versionadded:: 0.21.0
+            
     encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
-    compression:
-    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
-    verify_ssl: Default True. If False, allow self signed and invalid SSL
-                 certificates for https
+
+    compression : string, default None
+    
+            .. versionadded:: 0.18.1
+    
+    auth : tuple, default None 
+            A tuple of string with (username, password) string for 
+            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+            
+            .. versionadded:: 0.21.0
+
+    verify_ssl : boolean, Default True
+            If False, allow self signed and invalid SSL certificates for https
+
+            .. versionadded:: 0.21.0
+
 
     Returns
     -------
@@ -263,19 +278,34 @@ def split_auth_from_url(url_with_uname):
 
     Parameters
     ----------
-    url_with_uname : a url that may or may not contain username and password
+    url_with_uname : string
+            a url that may or may not contain username and password
             see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
             //<user>:<password>@<host>:<port>/<url-path>
+            
+            .. versionadded:: 0.21.0
 
     Returns
     -------
-    (username, password), url_no_usrpwd : username or "", password or "", 
-         url without username or password (if it contained it )
+    (username, password), url_no_usrpwd : tuple, string  Default ('', '') url
+            A tuple with (username, pwd) pair and 
+            url without username or password (if it contained it )
+
+    Raises
+    ------
+    ValueError for empty url
     """
+    if not url_with_uname: 
+        msg = "Empty url: {_type}"
+        raise ValueError(msg.format(_type=type(url_with_uname)))
     o = parse_url(url_with_uname)
-    usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
-    url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
-    return (o.username, o.password), url_no_usrpwd
+    uname = o.username if o.username else ''
+    pwd = o.password if o.password else ''
+    url_no_usrpwd = url_with_uname
+    if uname or pwd:
+        usrch = '{}:{}@{}'.format(o.username, o.password, o.hostname)
+        url_no_usrpwd = url_with_uname.replace(usrch, o.hostname)
+    return (uname, pwd), url_no_usrpwd
 
 
 def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
@@ -286,30 +316,42 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
 
     Parameters
     ----------
-    url_with_uname : a url that may or may not contain username and password
+    url_with_uname : string
+            a url that may or may not contain username and password
             see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
             //<user>:<password>@<host>:<port>/<url-path>
-    auth : ( username/""/None, password/"", None) tuple
-    verify_ssl: If False, SSL certificate verification is disabled.
+            
+            .. versionadded:: 0.21.0
+
+    auth : tuple, default None 
+            A tuple of string with (username, password) string for 
+            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+            
+            .. versionadded:: 0.21.0
+
+    verify_ssl : boolean, Default True
+            If False, allow self signed and invalid SSL certificates for https
+
+            .. versionadded:: 0.21.0
 
     Returns
     -------
     Request, kwargs to pass to urlopen. kwargs may be {} or {'context': obj }
     """
     uname = pwd = None
+    url_no_usrpwd = url_with_uname
     if auth and len(auth) == 2:
         uname, pwd = auth
     if not uname and not pwd:
         (uname, pwd), url_no_usrpwd = split_auth_from_url(url_with_uname)
-    else:
-        url_no_usrpwd = url_with_uname
-    upstr = '{}:{}'.format(uname, pwd)
-    if compat.PY3:
-        b64str = base64.b64encode(bytes(upstr, 'ascii')).decode('utf-8')
-    else:
-        b64str = base64.encodestring(upstr).replace('\n', '')
     req = Request(url_no_usrpwd)
-    req.add_header("Authorization", "Basic {}".format(b64str))
+    if uname or pwd:
+        upstr = '{}:{}'.format(uname, pwd)
+        if compat.PY3:
+            b64str = base64.b64encode(bytes(upstr, 'ascii')).decode('utf-8')
+        else:
+            b64str = base64.encodestring(upstr).replace('\n', '')
+        req.add_header("Authorization", "Basic {}".format(b64str))
     kwargs = {}
     if verify_ssl not in [None, True]:
         kwargs['context'] = ssl._create_unverified_context()
diff --git a/pandas/io/html.py b/pandas/io/html.py
index f14050189de27..7e37d856779db 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -123,8 +123,16 @@ def _read(obj, auth=None, verify_ssl=None):
     Parameters
     ----------
     obj : str, unicode, or file-like
-    auth: None or (username, password) for http basic auth
-    verify_ssl: Default True. Set to False to disable cert verification
+    auth : tuple, default None 
+            A tuple of string with (username, password) string for 
+            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+            
+            .. versionadded:: 0.21.0
+
+    verify_ssl : boolean, Default True
+            If False, allow self signed and invalid SSL certificates for https
+
+            .. versionadded:: 0.21.0
     Returns
     -------
     raw_text : str
@@ -866,10 +874,16 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
 
         .. versionadded:: 0.19.0
 
-    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
+    auth : tuple, default None 
+            A tuple of string with (username, password) string for 
+            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+            
+            .. versionadded:: 0.21.0
+
+    verify_ssl : boolean, Default True
+            If False, allow self signed and invalid SSL certificates for https
 
-    verify_ssl : bool, default True
-        If False, ssl certificate is not verified (allow self signed SSL certs)
+            .. versionadded:: 0.21.0
 
         Returns
     -------
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
index da627cf6a3b11..3aa69dd43109a 100644
--- a/pandas/io/json/json.py
+++ b/pandas/io/json/json.py
@@ -263,9 +263,16 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
 
         .. versionadded:: 0.19.0
 
-    auth: (str,str), default None. (username, password) for HTTP(s) basic auth
-    verify_ssl: boolean, default None (True).
-                    If false, allow self siged SSL certificates
+    auth : tuple, default None 
+            A tuple of string with (username, password) string for 
+            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+            
+            .. versionadded:: 0.21.0
+
+    verify_ssl : boolean, Default True
+            If False, allow self signed and invalid SSL certificates for https
+
+            .. versionadded:: 0.21.0
 
     Returns
     -------
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
index 3b0572872eb30..5a85a2bcefa61 100755
--- a/pandas/io/parsers.py
+++ b/pandas/io/parsers.py
@@ -579,10 +579,8 @@ def parser_f(filepath_or_buffer,
                  memory_map=False,
                  float_precision=None,
 
-                 # Basic auth (http/https) (username, password)
                  auth=None,
 
-                 # skip verify self signed SSL certificates
                  verify_ssl=None):
 
         # Alias sep -> delimiter.
diff --git a/pandas/tests/test_common.py b/pandas/tests/test_common.py
index 9964e41efa9bb..dc1c28a7c837f 100644
--- a/pandas/tests/test_common.py
+++ b/pandas/tests/test_common.py
@@ -189,17 +189,24 @@ def test_write_fspath_hdf5(self):
             expected = pd.read_hdf(string, key='bar')
 
         tm.assert_frame_equal(result, expected)
-
-    def test_split_url_extract_uname_pwd(self):
-        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
-                                       'aaa',
-                                       'bbb',
-                                       'https://ccc.com:1010/aaa.txt'
-                                       )]:
-            un, p, u = common.split_uname_from_url(url)
-            assert u == nurl
-            assert un == uname
-            assert p == pwd
+    
+    @pytest.mark.parametrize('url, uname, pwd, nurl', [
+        ('https://a1:b1@cc.com:101/f.csv',
+         'aaa',
+         'bbb',
+         'https://cc.com:101/f.csv'
+        ),
+        ('https://ccc.com:1010/aaa.txt',
+         '',
+         '',
+         'https://ccc.com:1010/aaa.txt'
+        ),
+    ])
+    def test_split_url_extract_uname_pwd(self, url, uname, pwd, nurl):
+        un, pw, ur = common.split_uname_from_url(url)
+        assert ur == nurl
+        assert un == uname
+        assert pw == pwd
 
 
 class TestMMapWrapper(object):

From eb03fd30384c94c6cfc37877c9c2b2570d7b81a5 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 17:55:25 -0700
Subject: [PATCH 08/14] fix to test case - had checked in wrong one

---
 pandas/tests/test_common.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/pandas/tests/test_common.py b/pandas/tests/test_common.py
index dc1c28a7c837f..31a12740eb9bf 100644
--- a/pandas/tests/test_common.py
+++ b/pandas/tests/test_common.py
@@ -192,8 +192,8 @@ def test_write_fspath_hdf5(self):
     
     @pytest.mark.parametrize('url, uname, pwd, nurl', [
         ('https://a1:b1@cc.com:101/f.csv',
-         'aaa',
-         'bbb',
+         'a1',
+         'b1',
          'https://cc.com:101/f.csv'
         ),
         ('https://ccc.com:1010/aaa.txt',
@@ -203,7 +203,7 @@ def test_write_fspath_hdf5(self):
         ),
     ])
     def test_split_url_extract_uname_pwd(self, url, uname, pwd, nurl):
-        un, pw, ur = common.split_uname_from_url(url)
+        (un, pw), ur = common.split_auth_from_url(url)
         assert ur == nurl
         assert un == uname
         assert pw == pwd

From cbe3f494fb4d5aec1e71b78cc62e89486322489a Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Thu, 13 Jul 2017 19:11:04 -0700
Subject: [PATCH 09/14] Fixing test_common.py which was mistakenly clobbered

---
 pandas/tests/io/test_common.py |  36 +--
 pandas/tests/test_common.py    | 484 +++++++++++++++------------------
 2 files changed, 237 insertions(+), 283 deletions(-)

diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
index dd489cf37e015..135385f9d6d7d 100644
--- a/pandas/tests/io/test_common.py
+++ b/pandas/tests/io/test_common.py
@@ -190,24 +190,24 @@ def test_write_fspath_hdf5(self):
 
         tm.assert_frame_equal(result, expected)
 
-    def test_split_url_extract_uname_pwd(self):
-        """
-        Test extraction of username, pwd from url, if contained.
-        """
-        for url, uname, pwd, nurl in [('https://aaa:bbb@ccc.com:1010/aaa.txt',
-                                       'aaa',
-                                       'bbb',
-                                       'https://ccc.com:1010/aaa.txt'
-                                       ),
-                                       ('https://ccc.com:1010/aaa.txt',
-                                       '',
-                                       '',
-                                       'https://ccc.com:1010/aaa.txt'
-                                       )]:
-            un, pw, mod_url = common.split_uname_from_url(url)
-            assert mod_url == nurl
-            assert un == uname
-            assert pw == pwd
+
+    @pytest.mark.parametrize('url, uname, pwd, nurl', [
+        ('https://a1:b1@cc.com:101/f.csv',
+         'a1',
+         'b1',
+         'https://cc.com:101/f.csv'
+        ),
+        ('https://ccc.com:1010/aaa.txt',
+         '',
+         '',
+         'https://ccc.com:1010/aaa.txt'
+        ),
+    ])
+    def test_split_url_extract_uname_pwd(self, url, uname, pwd, nurl):
+        (un, pw), ur = common.split_auth_from_url(url)
+        assert ur == nurl
+        assert un == uname
+        assert pw == pwd
 
 
 class TestMMapWrapper(object):
diff --git a/pandas/tests/test_common.py b/pandas/tests/test_common.py
index 31a12740eb9bf..5357a4d81f174 100644
--- a/pandas/tests/test_common.py
+++ b/pandas/tests/test_common.py
@@ -1,269 +1,223 @@
-"""
-    Tests for the pandas.io.common functionalities
-"""
-import mmap
+# -*- coding: utf-8 -*-
+
 import pytest
-import os
-from os.path import isabs
+import collections
+from functools import partial
+
+import numpy as np
 
-import pandas as pd
+from pandas import Series, Timestamp
+from pandas.compat import range, lmap
+import pandas.core.common as com
 import pandas.util.testing as tm
 
-from pandas.io import common
-from pandas.compat import is_platform_windows, StringIO
-
-from pandas import read_csv, concat
-
-try:
-    from pathlib import Path
-except ImportError:
-    pass
-
-try:
-    from py.path import local as LocalPath
-except ImportError:
-    pass
-
-
-class CustomFSPath(object):
-    """For testing fspath on unknown objects"""
-    def __init__(self, path):
-        self.path = path
-
-    def __fspath__(self):
-        return self.path
-
-
-HERE = os.path.dirname(__file__)
-
-
-class TestCommonIOCapabilities(object):
-    data1 = """index,A,B,C,D
-foo,2,3,4,5
-bar,7,8,9,10
-baz,12,13,14,15
-qux,12,13,14,15
-foo2,12,13,14,15
-bar2,12,13,14,15
-"""
-
-    def test_expand_user(self):
-        filename = '~/sometest'
-        expanded_name = common._expand_user(filename)
-
-        assert expanded_name != filename
-        assert isabs(expanded_name)
-        assert os.path.expanduser(filename) == expanded_name
-
-    def test_expand_user_normal_path(self):
-        filename = '/somefolder/sometest'
-        expanded_name = common._expand_user(filename)
-
-        assert expanded_name == filename
-        assert os.path.expanduser(filename) == expanded_name
-
-    def test_stringify_path_pathlib(self):
-        tm._skip_if_no_pathlib()
-
-        rel_path = common._stringify_path(Path('.'))
-        assert rel_path == '.'
-        redundant_path = common._stringify_path(Path('foo//bar'))
-        assert redundant_path == os.path.join('foo', 'bar')
-
-    def test_stringify_path_localpath(self):
-        tm._skip_if_no_localpath()
-
-        path = os.path.join('foo', 'bar')
-        abs_path = os.path.abspath(path)
-        lpath = LocalPath(path)
-        assert common._stringify_path(lpath) == abs_path
-
-    def test_stringify_path_fspath(self):
-        p = CustomFSPath('foo/bar.csv')
-        result = common._stringify_path(p)
-        assert result == 'foo/bar.csv'
-
-    def test_get_filepath_or_buffer_with_path(self):
-        filename = '~/sometest'
-        filepath_or_buffer, _, _ = common.get_filepath_or_buffer(filename)
-        assert filepath_or_buffer != filename
-        assert isabs(filepath_or_buffer)
-        assert os.path.expanduser(filename) == filepath_or_buffer
-
-    def test_get_filepath_or_buffer_with_buffer(self):
-        input_buffer = StringIO()
-        filepath_or_buffer, _, _ = common.get_filepath_or_buffer(input_buffer)
-        assert filepath_or_buffer == input_buffer
-
-    def test_iterator(self):
-        reader = read_csv(StringIO(self.data1), chunksize=1)
-        result = concat(reader, ignore_index=True)
-        expected = read_csv(StringIO(self.data1))
-        tm.assert_frame_equal(result, expected)
-
-        # GH12153
-        it = read_csv(StringIO(self.data1), chunksize=1)
-        first = next(it)
-        tm.assert_frame_equal(first, expected.iloc[[0]])
-        tm.assert_frame_equal(concat(it), expected.iloc[1:])
-
-    @pytest.mark.parametrize('reader, module, path', [
-        (pd.read_csv, 'os', os.path.join(HERE, 'data', 'iris.csv')),
-        (pd.read_table, 'os', os.path.join(HERE, 'data', 'iris.csv')),
-        (pd.read_fwf, 'os', os.path.join(HERE, 'data',
-                                         'fixed_width_format.txt')),
-        (pd.read_excel, 'xlrd', os.path.join(HERE, 'data', 'test1.xlsx')),
-        (pd.read_feather, 'feather', os.path.join(HERE, 'data',
-                                                  'feather-0_3_1.feather')),
-        (pd.read_hdf, 'tables', os.path.join(HERE, 'data', 'legacy_hdf',
-                                             'datetimetz_object.h5')),
-        (pd.read_stata, 'os', os.path.join(HERE, 'data', 'stata10_115.dta')),
-        (pd.read_sas, 'os', os.path.join(HERE, 'sas', 'data',
-                                         'test1.sas7bdat')),
-        (pd.read_json, 'os', os.path.join(HERE, 'json', 'data',
-                                          'tsframe_v012.json')),
-        (pd.read_msgpack, 'os', os.path.join(HERE, 'msgpack', 'data',
-                                             'frame.mp')),
-        (pd.read_pickle, 'os', os.path.join(HERE, 'data',
-                                            'categorical_0_14_1.pickle')),
-    ])
-    def test_read_fspath_all(self, reader, module, path):
-        pytest.importorskip(module)
-
-        mypath = CustomFSPath(path)
-        result = reader(mypath)
-        expected = reader(path)
-        if path.endswith('.pickle'):
-            # categorical
-            tm.assert_categorical_equal(result, expected)
-        else:
-            tm.assert_frame_equal(result, expected)
-
-    @pytest.mark.parametrize('writer_name, writer_kwargs, module', [
-        ('to_csv', {}, 'os'),
-        ('to_excel', {'engine': 'xlwt'}, 'xlwt'),
-        ('to_feather', {}, 'feather'),
-        ('to_html', {}, 'os'),
-        ('to_json', {}, 'os'),
-        ('to_latex', {}, 'os'),
-        ('to_msgpack', {}, 'os'),
-        ('to_pickle', {}, 'os'),
-        ('to_stata', {}, 'os'),
-    ])
-    def test_write_fspath_all(self, writer_name, writer_kwargs, module):
-        p1 = tm.ensure_clean('string')
-        p2 = tm.ensure_clean('fspath')
-        df = pd.DataFrame({"A": [1, 2]})
-
-        with p1 as string, p2 as fspath:
-            pytest.importorskip(module)
-            mypath = CustomFSPath(fspath)
-            writer = getattr(df, writer_name)
-
-            writer(string, **writer_kwargs)
-            with open(string, 'rb') as f:
-                expected = f.read()
-
-            writer(mypath, **writer_kwargs)
-            with open(fspath, 'rb') as f:
-                result = f.read()
-
-            assert result == expected
-
-    def test_write_fspath_hdf5(self):
-        # Same test as write_fspath_all, except HDF5 files aren't
-        # necessarily byte-for-byte identical for a given dataframe, so we'll
-        # have to read and compare equality
-        pytest.importorskip('tables')
-
-        df = pd.DataFrame({"A": [1, 2]})
-        p1 = tm.ensure_clean('string')
-        p2 = tm.ensure_clean('fspath')
-
-        with p1 as string, p2 as fspath:
-            mypath = CustomFSPath(fspath)
-            df.to_hdf(mypath, key='bar')
-            df.to_hdf(string, key='bar')
-
-            result = pd.read_hdf(fspath, key='bar')
-            expected = pd.read_hdf(string, key='bar')
-
-        tm.assert_frame_equal(result, expected)
-    
-    @pytest.mark.parametrize('url, uname, pwd, nurl', [
-        ('https://a1:b1@cc.com:101/f.csv',
-         'a1',
-         'b1',
-         'https://cc.com:101/f.csv'
-        ),
-        ('https://ccc.com:1010/aaa.txt',
-         '',
-         '',
-         'https://ccc.com:1010/aaa.txt'
-        ),
-    ])
-    def test_split_url_extract_uname_pwd(self, url, uname, pwd, nurl):
-        (un, pw), ur = common.split_auth_from_url(url)
-        assert ur == nurl
-        assert un == uname
-        assert pw == pwd
-
-
-class TestMMapWrapper(object):
-
-    def setup_method(self, method):
-        self.mmap_file = os.path.join(tm.get_data_path(),
-                                      'test_mmap.csv')
-
-    def test_constructor_bad_file(self):
-        non_file = StringIO('I am not a file')
-        non_file.fileno = lambda: -1
-
-        # the error raised is different on Windows
-        if is_platform_windows():
-            msg = "The parameter is incorrect"
-            err = OSError
-        else:
-            msg = "[Errno 22]"
-            err = mmap.error
-
-        tm.assert_raises_regex(err, msg, common.MMapWrapper, non_file)
-
-        target = open(self.mmap_file, 'r')
-        target.close()
-
-        msg = "I/O operation on closed file"
-        tm.assert_raises_regex(
-            ValueError, msg, common.MMapWrapper, target)
-
-    def test_get_attr(self):
-        with open(self.mmap_file, 'r') as target:
-            wrapper = common.MMapWrapper(target)
-
-        attrs = dir(wrapper.mmap)
-        attrs = [attr for attr in attrs
-                 if not attr.startswith('__')]
-        attrs.append('__next__')
-
-        for attr in attrs:
-            assert hasattr(wrapper, attr)
-
-        assert not hasattr(wrapper, 'foo')
-
-    def test_next(self):
-        with open(self.mmap_file, 'r') as target:
-            wrapper = common.MMapWrapper(target)
-            lines = target.readlines()
-
-        for line in lines:
-            next_line = next(wrapper)
-            assert next_line.strip() == line.strip()
-
-        pytest.raises(StopIteration, next, wrapper)
-
-    def test_unknown_engine(self):
-        with tm.ensure_clean() as path:
-            df = tm.makeDataFrame()
-            df.to_csv(path)
-            with tm.assert_raises_regex(ValueError, 'Unknown engine'):
-                read_csv(path, engine='pyt')
+
+def test_mut_exclusive():
+    msg = "mutually exclusive arguments: '[ab]' and '[ab]'"
+    with tm.assert_raises_regex(TypeError, msg):
+        com._mut_exclusive(a=1, b=2)
+    assert com._mut_exclusive(a=1, b=None) == 1
+    assert com._mut_exclusive(major=None, major_axis=None) is None
+    assert com._mut_exclusive(a=None, b=2) == 2
+
+
+def test_get_callable_name():
+    from functools import partial
+    getname = com._get_callable_name
+
+    def fn(x):
+        return x
+
+    lambda_ = lambda x: x
+    part1 = partial(fn)
+    part2 = partial(part1)
+
+    class somecall(object):
+
+        def __call__(self):
+            return x  # noqa
+
+    assert getname(fn) == 'fn'
+    assert getname(lambda_)
+    assert getname(part1) == 'fn'
+    assert getname(part2) == 'fn'
+    assert getname(somecall()) == 'somecall'
+    assert getname(1) is None
+
+
+def test_any_none():
+    assert (com._any_none(1, 2, 3, None))
+    assert (not com._any_none(1, 2, 3, 4))
+
+
+def test_all_not_none():
+    assert (com._all_not_none(1, 2, 3, 4))
+    assert (not com._all_not_none(1, 2, 3, None))
+    assert (not com._all_not_none(None, None, None, None))
+
+
+def test_iterpairs():
+    data = [1, 2, 3, 4]
+    expected = [(1, 2), (2, 3), (3, 4)]
+
+    result = list(com.iterpairs(data))
+
+    assert (result == expected)
+
+
+def test_split_ranges():
+    def _bin(x, width):
+        "return int(x) as a base2 string of given width"
+        return ''.join(str((x >> i) & 1) for i in range(width - 1, -1, -1))
+
+    def test_locs(mask):
+        nfalse = sum(np.array(mask) == 0)
+
+        remaining = 0
+        for s, e in com.split_ranges(mask):
+            remaining += e - s
+
+            assert 0 not in mask[s:e]
+
+        # make sure the total items covered by the ranges are a complete cover
+        assert remaining + nfalse == len(mask)
+
+    # exhaustively test all possible mask sequences of length 8
+    ncols = 8
+    for i in range(2 ** ncols):
+        cols = lmap(int, list(_bin(i, ncols)))  # count up in base2
+        mask = [cols[i] == 1 for i in range(len(cols))]
+        test_locs(mask)
+
+    # base cases
+    test_locs([])
+    test_locs([0])
+    test_locs([1])
+
+
+def test_map_indices_py():
+    data = [4, 3, 2, 1]
+    expected = {4: 0, 3: 1, 2: 2, 1: 3}
+
+    result = com.map_indices_py(data)
+
+    assert (result == expected)
+
+
+def test_union():
+    a = [1, 2, 3]
+    b = [4, 5, 6]
+
+    union = sorted(com.union(a, b))
+
+    assert ((a + b) == union)
+
+
+def test_difference():
+    a = [1, 2, 3]
+    b = [1, 2, 3, 4, 5, 6]
+
+    inter = sorted(com.difference(b, a))
+
+    assert ([4, 5, 6] == inter)
+
+
+def test_intersection():
+    a = [1, 2, 3]
+    b = [1, 2, 3, 4, 5, 6]
+
+    inter = sorted(com.intersection(a, b))
+
+    assert (a == inter)
+
+
+def test_groupby():
+    values = ['foo', 'bar', 'baz', 'baz2', 'qux', 'foo3']
+    expected = {'f': ['foo', 'foo3'],
+                'b': ['bar', 'baz', 'baz2'],
+                'q': ['qux']}
+
+    grouped = com.groupby(values, lambda x: x[0])
+
+    for k, v in grouped:
+        assert v == expected[k]
+
+
+def test_random_state():
+    import numpy.random as npr
+    # Check with seed
+    state = com._random_state(5)
+    assert state.uniform() == npr.RandomState(5).uniform()
+
+    # Check with random state object
+    state2 = npr.RandomState(10)
+    assert (com._random_state(state2).uniform() ==
+            npr.RandomState(10).uniform())
+
+    # check with no arg random state
+    assert com._random_state() is np.random
+
+    # Error for floats or strings
+    with pytest.raises(ValueError):
+        com._random_state('test')
+
+    with pytest.raises(ValueError):
+        com._random_state(5.5)
+
+
+def test_maybe_match_name():
+
+    matched = com._maybe_match_name(
+        Series([1], name='x'), Series(
+            [2], name='x'))
+    assert (matched == 'x')
+
+    matched = com._maybe_match_name(
+        Series([1], name='x'), Series(
+            [2], name='y'))
+    assert (matched is None)
+
+    matched = com._maybe_match_name(Series([1]), Series([2], name='x'))
+    assert (matched is None)
+
+    matched = com._maybe_match_name(Series([1], name='x'), Series([2]))
+    assert (matched is None)
+
+    matched = com._maybe_match_name(Series([1], name='x'), [2])
+    assert (matched == 'x')
+
+    matched = com._maybe_match_name([1], Series([2], name='y'))
+    assert (matched == 'y')
+
+
+def test_dict_compat():
+    data_datetime64 = {np.datetime64('1990-03-15'): 1,
+                       np.datetime64('2015-03-15'): 2}
+    data_unchanged = {1: 2, 3: 4, 5: 6}
+    expected = {Timestamp('1990-3-15'): 1, Timestamp('2015-03-15'): 2}
+    assert (com._dict_compat(data_datetime64) == expected)
+    assert (com._dict_compat(expected) == expected)
+    assert (com._dict_compat(data_unchanged) == data_unchanged)
+
+
+def test_standardize_mapping():
+    # No uninitialized defaultdicts
+    with pytest.raises(TypeError):
+        com.standardize_mapping(collections.defaultdict)
+
+    # No non-mapping subtypes, instance
+    with pytest.raises(TypeError):
+        com.standardize_mapping([])
+
+    # No non-mapping subtypes, class
+    with pytest.raises(TypeError):
+        com.standardize_mapping(list)
+
+    fill = {'bad': 'data'}
+    assert (com.standardize_mapping(fill) == dict)
+
+    # Convert instance to type
+    assert (com.standardize_mapping({}) == dict)
+
+    dd = collections.defaultdict(list)
+    assert isinstance(com.standardize_mapping(dd), partial)
\ No newline at end of file

From 437e0a2c4ec91cbb221441f96fc21be4c754c54d Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Fri, 14 Jul 2017 02:06:24 -0700
Subject: [PATCH 10/14] Fixing whitespace to meet style guidelines

---
 pandas/io/common.py            | 28 ++++++++++++++--------------
 pandas/io/html.py              | 12 ++++++------
 pandas/io/json/json.py         |  6 +++---
 pandas/tests/io/test_common.py |  5 ++---
 pandas/tests/test_common.py    |  2 +-
 5 files changed, 26 insertions(+), 27 deletions(-)

diff --git a/pandas/io/common.py b/pandas/io/common.py
index f14fb43da2831..87cc0272499e6 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -191,19 +191,19 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
                          or buffer
             now supports 'https://<user>:<password>@<host>:<port>/<url-path>'
-            
+
             .. versionadded:: 0.21.0
-            
+
     encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
 
     compression : string, default None
-    
+
             .. versionadded:: 0.18.1
-    
-    auth : tuple, default None 
-            A tuple of string with (username, password) string for 
+
+    auth : tuple, default None
+            A tuple of string with (username, password) string for
             HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
-            
+
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
@@ -282,20 +282,20 @@ def split_auth_from_url(url_with_uname):
             a url that may or may not contain username and password
             see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
             //<user>:<password>@<host>:<port>/<url-path>
-            
+
             .. versionadded:: 0.21.0
 
     Returns
     -------
     (username, password), url_no_usrpwd : tuple, string  Default ('', '') url
-            A tuple with (username, pwd) pair and 
+            A tuple with (username, pwd) pair and
             url without username or password (if it contained it )
 
     Raises
     ------
     ValueError for empty url
     """
-    if not url_with_uname: 
+    if not url_with_uname:
         msg = "Empty url: {_type}"
         raise ValueError(msg.format(_type=type(url_with_uname)))
     o = parse_url(url_with_uname)
@@ -320,13 +320,13 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
             a url that may or may not contain username and password
             see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
             //<user>:<password>@<host>:<port>/<url-path>
-            
+
             .. versionadded:: 0.21.0
 
-    auth : tuple, default None 
-            A tuple of string with (username, password) string for 
+    auth : tuple, default None
+            A tuple of string with (username, password) string for
             HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
-            
+
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
diff --git a/pandas/io/html.py b/pandas/io/html.py
index 7e37d856779db..62bca65c70427 100644
--- a/pandas/io/html.py
+++ b/pandas/io/html.py
@@ -123,10 +123,10 @@ def _read(obj, auth=None, verify_ssl=None):
     Parameters
     ----------
     obj : str, unicode, or file-like
-    auth : tuple, default None 
-            A tuple of string with (username, password) string for 
+    auth : tuple, default None
+            A tuple of string with (username, password) string for
             HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
-            
+
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
@@ -874,10 +874,10 @@ def read_html(io, match='.+', flavor=None, header=None, index_col=None,
 
         .. versionadded:: 0.19.0
 
-    auth : tuple, default None 
-            A tuple of string with (username, password) string for 
+    auth : tuple, default None
+            A tuple of string with (username, password) string for
             HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
-            
+
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
diff --git a/pandas/io/json/json.py b/pandas/io/json/json.py
index 3aa69dd43109a..b403eb45ae2cd 100644
--- a/pandas/io/json/json.py
+++ b/pandas/io/json/json.py
@@ -263,10 +263,10 @@ def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
 
         .. versionadded:: 0.19.0
 
-    auth : tuple, default None 
-            A tuple of string with (username, password) string for 
+    auth : tuple, default None
+            A tuple of string with (username, password) string for
             HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
-            
+
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
index 135385f9d6d7d..82fc4d6271f00 100644
--- a/pandas/tests/io/test_common.py
+++ b/pandas/tests/io/test_common.py
@@ -190,18 +190,17 @@ def test_write_fspath_hdf5(self):
 
         tm.assert_frame_equal(result, expected)
 
-
     @pytest.mark.parametrize('url, uname, pwd, nurl', [
         ('https://a1:b1@cc.com:101/f.csv',
          'a1',
          'b1',
          'https://cc.com:101/f.csv'
-        ),
+         ),
         ('https://ccc.com:1010/aaa.txt',
          '',
          '',
          'https://ccc.com:1010/aaa.txt'
-        ),
+         ),
     ])
     def test_split_url_extract_uname_pwd(self, url, uname, pwd, nurl):
         (un, pw), ur = common.split_auth_from_url(url)
diff --git a/pandas/tests/test_common.py b/pandas/tests/test_common.py
index 5357a4d81f174..57479be4d989f 100644
--- a/pandas/tests/test_common.py
+++ b/pandas/tests/test_common.py
@@ -220,4 +220,4 @@ def test_standardize_mapping():
     assert (com.standardize_mapping({}) == dict)
 
     dd = collections.defaultdict(list)
-    assert isinstance(com.standardize_mapping(dd), partial)
\ No newline at end of file
+    assert isinstance(com.standardize_mapping(dd), partial)

From 7b034b88ee24758700afb0908376cee6ddacbd29 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Mon, 17 Jul 2017 22:56:36 -0700
Subject: [PATCH 11/14] Added live working test case for http auth and ssl
 override. Formatting changes

---
 pandas/io/common.py | 46 ++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/pandas/io/common.py b/pandas/io/common.py
index 87cc0272499e6..30071fb4ad052 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -189,27 +189,27 @@ def get_filepath_or_buffer(filepath_or_buffer, encoding=None,
     Parameters
     ----------
     filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
-                         or buffer
-            now supports 'https://<user>:<password>@<host>:<port>/<url-path>'
+        or buffer  now supports url with username and password
+        eg: 'https://<user>:<password>@<host>:<port>/<url-path>'
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
     encoding : the encoding to use to decode py3 bytes, default is 'utf-8'
 
     compression : string, default None
 
-            .. versionadded:: 0.18.1
+        .. versionadded:: 0.18.1
 
     auth : tuple, default None
-            A tuple of string with (username, password) string for
-            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+        A tuple of string with (username, password) string for
+        HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
 
             .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
-            If False, allow self signed and invalid SSL certificates for https
+        If False, allow self signed and invalid SSL certificates for https
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
 
     Returns
@@ -279,17 +279,17 @@ def split_auth_from_url(url_with_uname):
     Parameters
     ----------
     url_with_uname : string
-            a url that may or may not contain username and password
-            see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
-            //<user>:<password>@<host>:<port>/<url-path>
+        a url that may or may not contain username and password
+        see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
+        //<user>:<password>@<host>:<port>/<url-path>
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
     Returns
     -------
     (username, password), url_no_usrpwd : tuple, string  Default ('', '') url
-            A tuple with (username, pwd) pair and
-            url without username or password (if it contained it )
+        A tuple with (username, pwd) pair and
+        url without username or password (if it contained it )
 
     Raises
     ------
@@ -317,22 +317,22 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
     Parameters
     ----------
     url_with_uname : string
-            a url that may or may not contain username and password
-            see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
-            //<user>:<password>@<host>:<port>/<url-path>
+        a url that may or may not contain username and password
+        see section 3.1 RFC 1738 https://www.ietf.org/rfc/rfc1738.txt
+        //<user>:<password>@<host>:<port>/<url-path>
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
     auth : tuple, default None
-            A tuple of string with (username, password) string for
-            HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
+        A tuple of string with (username, password) string for
+        HTTP(s) basic auth: eg auth= ('roberto', 'panda$4life')
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
     verify_ssl : boolean, Default True
-            If False, allow self signed and invalid SSL certificates for https
+        If False, allow self signed and invalid SSL certificates for https
 
-            .. versionadded:: 0.21.0
+        .. versionadded:: 0.21.0
 
     Returns
     -------

From 0a4607a36ab5d47b1a8969c2bbb1b6323752d340 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Tue, 18 Jul 2017 21:18:44 -0700
Subject: [PATCH 12/14] Really added live working test case for http auth and
 ssl override (i hope). Strict require both uname/pwd or neither

---
 doc/source/whatsnew/v0.21.0.txt   |  5 +-
 pandas/io/common.py               | 16 +++++-
 pandas/tests/io/test_http_auth.py | 89 +++++++++++++++++++++++++++++++
 3 files changed, 107 insertions(+), 3 deletions(-)
 create mode 100644 pandas/tests/io/test_http_auth.py

diff --git a/doc/source/whatsnew/v0.21.0.txt b/doc/source/whatsnew/v0.21.0.txt
index 7baf87da18039..9eef84aa69033 100644
--- a/doc/source/whatsnew/v0.21.0.txt
+++ b/doc/source/whatsnew/v0.21.0.txt
@@ -40,8 +40,9 @@ Other Enhancements
 - :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
 - :func:`Dataframe.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
-- :func:`read_csv`, :func:`read_html`, :func:`read_json`, :func:`read_html`  now accept auth in url //<user>:<password>@<host>:<port>/<url-path>, or ``auth`` tuple (username, password) parameter 
-- :func:`read_csv`, :func:`read_html`, :func:`read_json`, :func:`read_html`  now accept ``verify_ssl`` False to disable https/ssl certificate verification (eg: self signed ssl certs in testing)  (:issue:`16716`)
+- It is now possible to read data (i.e. CSV, JSON, HTML) from a HTTP/HTTPS URL that requires Basic Authentication (:issue:`16716`)
+- It is now possible to skip check of validity of SSL certificate (eg: Testing using self-signed SSL certificates) (:issue:`16716`)
+
 .. _whatsnew_0210.api_breaking:
 
 Backwards incompatible API changes
diff --git a/pandas/io/common.py b/pandas/io/common.py
index 30071fb4ad052..a353b984564c4 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -6,6 +6,7 @@
 import mmap
 import ssl
 import base64
+import warnings
 from contextlib import contextmanager, closing
 
 from pandas.compat import StringIO, BytesIO, string_types, text_type
@@ -271,6 +272,11 @@ def file_path_to_url(path):
 }
 
 
+class InsecureRequestWarning(Warning):
+    "Warned when making an unverified HTTPS request. Borrowed from requests"
+    pass
+
+
 def split_auth_from_url(url_with_uname):
     """
     If a url contains username and password, it is extracted and returned
@@ -337,6 +343,10 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
     Returns
     -------
     Request, kwargs to pass to urlopen. kwargs may be {} or {'context': obj }
+
+    Raises
+    ------
+    ValueError if only one of username or password is provided.
     """
     uname = pwd = None
     url_no_usrpwd = url_with_uname
@@ -345,16 +355,20 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
     if not uname and not pwd:
         (uname, pwd), url_no_usrpwd = split_auth_from_url(url_with_uname)
     req = Request(url_no_usrpwd)
-    if uname or pwd:
+    if uname and pwd:
         upstr = '{}:{}'.format(uname, pwd)
         if compat.PY3:
             b64str = base64.b64encode(bytes(upstr, 'ascii')).decode('utf-8')
         else:
             b64str = base64.encodestring(upstr).replace('\n', '')
         req.add_header("Authorization", "Basic {}".format(b64str))
+    elif uname or pwd:
+        raise ValueError('Only username or password provided without providing the other')
     kwargs = {}
     if verify_ssl not in [None, True]:
         kwargs['context'] = ssl._create_unverified_context()
+        msg = 'SSL certificate verification is being disabled for HTTPS. Possible security risk'
+        warnings.warn(msg, InsecureRequestWarning)
     return req, kwargs
 
 
diff --git a/pandas/tests/io/test_http_auth.py b/pandas/tests/io/test_http_auth.py
new file mode 100644
index 0000000000000..79fb7c018af31
--- /dev/null
+++ b/pandas/tests/io/test_http_auth.py
@@ -0,0 +1,89 @@
+import pytest
+import pandas as pd
+
+
+def gen_http_auth_ssl_test_cases():
+    """
+    Generate list of test case to test for : http/https, username/pwd in url
+    or as parameters, self signed ssl certs or trusted ssl certs, no auth
+    or basic auth
+    """
+    def gen_level1_tc():
+        test_cases = []
+        # The following host doesn't seem to handle urllib but handles
+        # python requests package. This is because:
+        # 'urlopen' sets header 'Host' : '<fqdn>:<port>' - acceptable RFC7230
+        # 'requests' sets header 'Host' : '<fqdn>'
+        # so pandas fails on following hosting server (uses some 'apex' server)
+        # but pandas succeeds on nginx even if port is non-default. 
+        for host, verify_ssl in [('pandas-unittest.site11.com', False, ),
+                                 ('handsome-equator.000webhostapp.com', True)
+                                 ]:
+            for sub_path, is_auth in [('no_auth/', False),
+                                      ('basic_auth/', True)]:
+                pre_ports = [('http', ''),
+                             ('https', '')]
+                for pre, port in pre_ports:
+                    test_cases.append(
+                        [host, verify_ssl, pre, port, sub_path, is_auth])
+        return test_cases
+
+    def gen_base_url(pre, auth_prefix, host, port, su_pa):
+        return '{}://{}{}{}/{}'.format(pre, auth_prefix, host, port, su_pa)
+    tc2 = []
+    uname = 'pandasusr'
+    pwd = 'pandaspwd'
+    for host, verify_ssl, pre, port, sp, is_auth in gen_level1_tc():
+        u = uname if is_auth else None
+        p = pwd if is_auth else None
+        u_no_uname = gen_base_url(pre, '', host, port, sp)
+        u_with_uname = None
+        if is_auth:
+            auth_prefix = '{}:{}@'.format(u, p) if is_auth else ''
+            u_with_uname = gen_base_url(pre, auth_prefix, host, port, sp)
+            tc2.append([u_no_uname, u, p, verify_ssl])
+            if u_with_uname and u_with_uname != u_no_uname:
+                tc2.append([u_with_uname, None, None, verify_ssl])
+        else:
+            tc2.append([u_no_uname, None, None, verify_ssl])
+    return tc2
+
+
+@pytest.mark.parametrize('url, uname, pwd, verify_ssl',
+                         gen_http_auth_ssl_test_cases())
+def test_http_auth_ssl(url, uname, pwd, verify_ssl):
+
+    def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
+        furl = url + fname
+        kwargs = {}
+        if uname or pwd:
+            kwargs['auth'] = (uname, pwd)
+        if verify_ssl is not None:
+            kwargs['verify_ssl'] = verify_ssl
+        msg = '{0: <90} -- auth:[{1: <10}/{2: <10}] v:[{3: <5}]'.format(
+              url, str(uname), str(pwd), str(verify_ssl))
+        tcsv = 'animal,bird\ndog,pigeon\ncat,emu\n'
+        j = '{"animal":{"0":"dog","1":"cat"},"bird":{"0":"pigeon","1":"emu"}}'
+        try:
+            df = pd_read_fn(furl, **kwargs)
+            if type(df) is list:  # html
+                df = df[0]
+            smatch = str(df.to_csv(index=False)) == tcsv
+            jmatch = str(df.to_json()) == j
+            res = 'Json : {}  -- String: {}'.format(jmatch, smatch)
+            if not jmatch or not smatch:
+                raise Exception(' ** ERROR:' + res)
+            else:
+                res += ' OK'
+            print(msg + ' ' + res)
+        except Exception as ex:
+            print(msg + ' ' + str(ex))
+            raise ex
+        return True
+
+    for pd_read_fn, fname in [(pd.read_csv, 'aaa.csv'),
+                              (pd.read_json, 'jdoc.json'),
+                              (pd.read_excel, 'ex_doc.xlsx'),
+                              (pd.read_html, 'html_file.html')
+                              ]:
+        assert get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname)

From 209dd58a5c088d149f98b35921934245886aa63d Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Wed, 19 Jul 2017 19:56:07 -0700
Subject: [PATCH 13/14] Lot more test cases for HTTP. However, one fails when
 run with test_html.py. Common logic update. whatsnew fixed

---
 doc/source/whatsnew/v0.21.0.txt   | 129 ++++++++++++++++++++++++------
 pandas/io/common.py               |   8 +-
 pandas/tests/io/test_http_auth.py | 120 ++++++++++++++++++++-------
 3 files changed, 198 insertions(+), 59 deletions(-)

diff --git a/doc/source/whatsnew/v0.21.0.txt b/doc/source/whatsnew/v0.21.0.txt
index 9eef84aa69033..eae60828a9e5e 100644
--- a/doc/source/whatsnew/v0.21.0.txt
+++ b/doc/source/whatsnew/v0.21.0.txt
@@ -25,34 +25,101 @@ New features
 - Added ``__fspath__`` method to :class:`~pandas.HDFStore`, :class:`~pandas.ExcelFile`,
   and :class:`~pandas.ExcelWriter` to work properly with the file system path protocol (:issue:`13823`)
 
+
+.. _whatsnew_0210.enhancements.infer_objects:
+
+``infer_objects`` type conversion
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The :meth:`DataFrame.infer_objects` and :meth:`Series.infer_objects`
+methods have been added to perform dtype inference on object columns, replacing
+some of the functionality of the deprecated ``convert_objects``
+method. See the documentation :ref:`here <basics.object_conversion>`
+for more details. (:issue:`11221`)
+
+This method only performs soft conversions on object columns, converting Python objects
+to native types, but not any coercive conversions.  For example:
+
+.. ipython:: python
+
+   df = pd.DataFrame({'A': [1, 2, 3],
+                      'B': np.array([1, 2, 3], dtype='object'),
+                      'C': ['1', '2', '3']})
+   df.dtypes
+   df.infer_objects().dtypes
+
+Note that column ``'C'`` was not converted - only scalar numeric types
+will be inferred to a new type.  Other types of conversion should be accomplished
+using the :func:`to_numeric` function (or :func:`to_datetime`, :func:`to_timedelta`).
+
+.. ipython:: python
+
+   df = df.infer_objects()
+   df['C'] = pd.to_numeric(df['C'], errors='coerce')
+   df.dtypes
+
 .. _whatsnew_0210.enhancements.other:
 
 Other Enhancements
 ^^^^^^^^^^^^^^^^^^
 
 - The ``validate`` argument for :func:`merge` function now checks whether a merge is one-to-one, one-to-many, many-to-one, or many-to-many. If a merge is found to not be an example of specified merge type, an exception of type ``MergeError`` will be raised. For more, see :ref:`here <merging.validation>` (:issue:`16270`)
-- ``Series.to_dict()`` and ``DataFrame.to_dict()`` now support an ``into`` keyword which allows you to specify the ``collections.Mapping`` subclass that you would like returned.  The default is ``dict``, which is backwards compatible. (:issue:`16122`)
-- ``RangeIndex.append`` now returns a ``RangeIndex`` object when possible (:issue:`16212`)
-- ``Series.rename_axis()`` and ``DataFrame.rename_axis()`` with ``inplace=True`` now return ``None`` while renaming the axis inplace. (:issue:`15704`)
-- :func:`to_pickle` has gained a ``protocol`` parameter (:issue:`16252`). By default, this parameter is set to `HIGHEST_PROTOCOL <https://docs.python.org/3/library/pickle.html#data-stream-format>`__
+- :func:`Series.to_dict` and :func:`DataFrame.to_dict` now support an ``into`` keyword which allows you to specify the ``collections.Mapping`` subclass that you would like returned.  The default is ``dict``, which is backwards compatible. (:issue:`16122`)
+- :func:`RangeIndex.append` now returns a ``RangeIndex`` object when possible (:issue:`16212`)
+- :func:`Series.rename_axis` and :func:`DataFrame.rename_axis` with ``inplace=True`` now return ``None`` while renaming the axis inplace. (:issue:`15704`)
+- :func:`Series.to_pickle` and :func:`DataFrame.to_pickle` have gained a ``protocol`` parameter (:issue:`16252`). By default, this parameter is set to `HIGHEST_PROTOCOL <https://docs.python.org/3/library/pickle.html#data-stream-format>`__
 - :func:`api.types.infer_dtype` now infers decimals. (:issue:`15690`)
 - :func:`read_feather` has gained the ``nthreads`` parameter for multi-threaded operations (:issue:`16359`)
 - :func:`DataFrame.clip()` and :func:`Series.clip()` have gained an ``inplace`` argument. (:issue:`15388`)
 - :func:`crosstab` has gained a ``margins_name`` parameter to define the name of the row / column that will contain the totals when ``margins=True``. (:issue:`15972`)
-- :func:`Dataframe.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
-- It is now possible to read data (i.e. CSV, JSON, HTML) from a HTTP/HTTPS URL that requires Basic Authentication (:issue:`16716`)
-- It is now possible to skip check of validity of SSL certificate (eg: Testing using self-signed SSL certificates) (:issue:`16716`)
+- :func:`DataFrame.select_dtypes` now accepts scalar values for include/exclude as well as list-like. (:issue:`16855`)
+- :func:`date_range` now accepts 'YS' in addition to 'AS' as an alias for start of year (:issue:`9313`)
+- :func:`date_range` now accepts 'Y' in addition to 'A' as an alias for end of year (:issue:`9313`)
+
+.. _whatsnew_0210.enhancements.read_csv:
+
+``read_csv`` allow basic auth and skip SSL verification
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+It is possible to read data (i.e. CSV, JSON, HTML) from a URL that is password-protected (:issue:`16716`)
+The :meth:`DataFrame.read_csv`, :meth:`DataFrame.read_html`, :meth:`DataFrame.read_json`,
+:meth:`DataFrame.read_excel` can now perform Basic Authentication over HTTP/HTTPS
+now accept an optional parameter of ``auth`` of type tuple containing username and password
+It also fixes an issue where a url containing username and password in the standard form now works:
+https://<user>:<password>@<fqdn>:<port>/<path>
+Use of username and password over HTTP (without ssl) is a security threat and not recommended.
+
+.. ipython:: python
+   url = 'http://<fqdn>:<port>/my.csv'
+   username = 'darth'
+   password = 'cand3stroypassword'
+   df = pd.read_csv(url, auth=(username, password))
+
+   # or
+   df = pd.read_csv('https://darth:cand3stroypassword@myhost.com:1010/my.csv')
+
+It is now also possible to bypass verification of SSL certificate for HTTPS call.
+The :meth:`DataFrame.read_csv`, :meth:`DataFrame.read_html`, :meth:`DataFrame.read_json`,
+:meth:`DataFrame.read_excel` can now accept an optional parameter ``verify_ssl=False`` to bypass SSL verification.
+Doing this creates a security risk and is not recommended. It will raise a warning `pandas.io.common.InsecureRequestWarning`
+This functionality is added to primarily help in testability scenarios or within private networks where obtaining SSL certificates is burdensome.
+
+.. ipython:: python
+   url = 'https://my-test-server.internal/my.csv'
+   df = pd.read_csv(url, verify_ssl=False) # succeed with pandas.io.common.InsecureRequestWarning
+   
+   df = pd.read_csv(url) # Fails by default 
 
 .. _whatsnew_0210.api_breaking:
 
 Backwards incompatible API changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
+.. _whatsnew_0210.api_breaking.pandas_eval:
+
 Improved error handling during item assignment in pd.eval
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. _whatsnew_0210.api_breaking.pandas_eval:
-
 :func:`eval` will now raise a ``ValueError`` when item assignment malfunctions, or
 inplace operations are specified, but there is no item assignment in the expression (:issue:`16732`)
 
@@ -94,9 +161,14 @@ the target. Now, a ``ValueError`` will be raised when such an input is passed in
    ...
    ValueError: Cannot operate inplace if there is no assignment
 
+.. _whatsnew_0210.api:
+
+Other API Changes
+^^^^^^^^^^^^^^^^^
+
 - Support has been dropped for Python 3.4 (:issue:`15251`)
 - The Categorical constructor no longer accepts a scalar for the ``categories`` keyword. (:issue:`16022`)
-- Accessing a non-existent attribute on a closed :class:`HDFStore` will now
+- Accessing a non-existent attribute on a closed :class:`~pandas.HDFStore` will now
   raise an ``AttributeError`` rather than a ``ClosedFileError`` (:issue:`16301`)
 - :func:`read_csv` now treats ``'null'`` strings as missing values by default (:issue:`16471`)
 - :func:`read_csv` now treats ``'n/a'`` strings as missing values by default (:issue:`16078`)
@@ -104,12 +176,6 @@ the target. Now, a ``ValueError`` will be raised when such an input is passed in
 - Compression defaults in HDF stores now follow pytable standards. Default is no compression and if ``complib`` is missing and ``complevel`` > 0 ``zlib`` is used (:issue:`15943`)
 - ``Index.get_indexer_non_unique()`` now returns a ndarray indexer rather than an ``Index``; this is consistent with ``Index.get_indexer()`` (:issue:`16819`)
 - Removed the ``@slow`` decorator from ``pandas.util.testing``, which caused issues for some downstream packages' test suites. Use ``@pytest.mark.slow`` instead, which achieves the same thing (:issue:`16850`)
-
-.. _whatsnew_0210.api:
-
-Other API Changes
-^^^^^^^^^^^^^^^^^
-
 - Moved definition of ``MergeError`` to the ``pandas.errors`` module.
 
 
@@ -119,6 +185,7 @@ Deprecations
 ~~~~~~~~~~~~
 - :func:`read_excel()` has deprecated ``sheetname`` in favor of ``sheet_name`` for consistency with ``.to_excel()`` (:issue:`10559`).
 
+- ``pd.options.html.border`` has been deprecated in favor of ``pd.options.display.html.border`` (:issue:`15793`).
 
 .. _whatsnew_0210.prior_deprecations:
 
@@ -126,10 +193,12 @@ Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 - :func:`read_excel()` has dropped the ``has_index_names`` parameter (:issue:`10967`)
+- The ``pd.options.display.height`` configuration has been dropped (:issue:`3663`)
+- The ``pd.options.display.line_width`` configuration has been dropped (:issue:`2881`)
 - The ``pd.options.display.mpl_style`` configuration has been dropped (:issue:`12190`)
 - ``Index`` has dropped the ``.sym_diff()`` method in favor of ``.symmetric_difference()`` (:issue:`12591`)
 - ``Categorical`` has dropped the ``.order()`` and ``.sort()`` methods in favor of ``.sort_values()`` (:issue:`12882`)
-- :func:`eval` and :method:`DataFrame.eval` have changed the default of ``inplace`` from ``None`` to ``False`` (:issue:`11149`)
+- :func:`eval` and :func:`DataFrame.eval` have changed the default of ``inplace`` from ``None`` to ``False`` (:issue:`11149`)
 - The function ``get_offset_name`` has been dropped in favor of the ``.freqstr`` attribute for an offset (:issue:`11834`)
 
 
@@ -138,6 +207,7 @@ Removal of prior version deprecations/changes
 Performance Improvements
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
+- Improved performance of instantiating :class:`SparseDataFrame` (:issue:`16773`)
 
 
 .. _whatsnew_0210.bug_fixes:
@@ -145,7 +215,6 @@ Performance Improvements
 Bug Fixes
 ~~~~~~~~~
 
-- Fixes regression in 0.20, :func:`Series.aggregate` and :func:`DataFrame.aggregate` allow dictionaries as return values again (:issue:`16741`)
 
 Conversion
 ^^^^^^^^^^
@@ -157,34 +226,41 @@ Indexing
 - When called with a null slice (e.g. ``df.iloc[:]``), the ``.iloc`` and ``.loc`` indexers return a shallow copy of the original object. Previously they returned the original object. (:issue:`13873`).
 - When called on an unsorted ``MultiIndex``, the ``loc`` indexer now will raise ``UnsortedIndexError`` only if proper slicing is used on non-sorted levels (:issue:`16734`).
 - Fixes regression in 0.20.3 when indexing with a string on a ``TimedeltaIndex`` (:issue:`16896`).
+- Fixed :func:`TimedeltaIndex.get_loc` handling of ``np.timedelta64`` inputs (:issue:`16909`).
+- Fix :func:`MultiIndex.sort_index` ordering when ``ascending`` argument is a list, but not all levels are specified, or are in a different order (:issue:`16934`).
+- Fixes bug where indexing with ``np.inf`` caused an ``OverflowError`` to be raised (:issue:`16957`)
+- Bug in reindexing on an empty ``CategoricalIndex`` (:issue:`16770`)
 
 I/O
 ^^^
 
 - Bug in :func:`read_csv` in which non integer values for the header argument generated an unhelpful / unrelated error message (:issue:`16338`)
 
+- Bug in :func:`read_stata` where value labels could not be read when using an iterator (:issue:`16923`)
 
 Plotting
 ^^^^^^^^
-
+- Bug in plotting methods using ``secondary_y`` and ``fontsize`` not setting secondary axis font size (:issue:`12565`)
 
 
 Groupby/Resample/Rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
 
-- Bug in ``DataFrame.resample().size()`` where an empty ``DataFrame`` did not return a ``Series`` (:issue:`14962`)
-- Bug in ``infer_freq`` causing indices with 2-day gaps during the working week to be wrongly inferred as business daily (:issue:`16624`)
-- Bug in ``.rolling.quantile()`` which incorrectly used different defaults than :func:`Series.quantile()` and :func:`DataFrame.quantile()` (:issue:`9413`, :issue:`16211`)
-
+- Bug in ``DataFrame.resample(...).size()`` where an empty ``DataFrame`` did not return a ``Series`` (:issue:`14962`)
+- Bug in :func:`infer_freq` causing indices with 2-day gaps during the working week to be wrongly inferred as business daily (:issue:`16624`)
+- Bug in ``.rolling(...).quantile()`` which incorrectly used different defaults than :func:`Series.quantile()` and :func:`DataFrame.quantile()` (:issue:`9413`, :issue:`16211`)
+- Bug in ``groupby.transform()`` that would coerce boolean dtypes back to float (:issue:`16875`)
 
 Sparse
 ^^^^^^
-
+- Bug in ``SparseSeries`` raises ``AttributeError`` when a dictionary is passed in as data (:issue:`16777`)
 
 
 Reshaping
 ^^^^^^^^^
-
+- Joining/Merging with a non unique ``PeriodIndex`` raised a TypeError (:issue:`16871`)
+- Bug when using :func:`isin` on a large object series and large comparison array (:issue:`16012`)
+- Fixes regression from 0.20, :func:`Series.aggregate` and :func:`DataFrame.aggregate` allow dictionaries as return values again (:issue:`16741`)
 
 
 Numeric
@@ -194,9 +270,10 @@ Numeric
 
 Categorical
 ^^^^^^^^^^^
-- Bug in ``:func:Series.isin()`` when called with a categorical (:issue`16639`)
+- Bug in :func:`Series.isin` when called with a categorical (:issue`16639`)
 
 
 Other
 ^^^^^
 - Bug in :func:`eval` where the ``inplace`` parameter was being incorrectly handled (:issue:`16732`)
+- Bug in ``.isin()`` in which checking membership in empty ``Series`` objects raised an error (:issue:`16991`)
diff --git a/pandas/io/common.py b/pandas/io/common.py
index a353b984564c4..0c06cc209252f 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -363,11 +363,13 @@ def get_urlopen_args(url_with_uname, auth=None, verify_ssl=True):
             b64str = base64.encodestring(upstr).replace('\n', '')
         req.add_header("Authorization", "Basic {}".format(b64str))
     elif uname or pwd:
-        raise ValueError('Only username or password provided without providing the other')
+        msg = 'Only username or password provided without the other'
+        raise ValueError(msg)
     kwargs = {}
-    if verify_ssl not in [None, True]:
+    if verify_ssl is False and url_no_usrpwd.lower().startswith('https://'):
         kwargs['context'] = ssl._create_unverified_context()
-        msg = 'SSL certificate verification is being disabled for HTTPS. Possible security risk'
+        msg = 'SSL certificate verification is being disabled for HTTPS.' + \
+              ' Possible security risk'
         warnings.warn(msg, InsecureRequestWarning)
     return req, kwargs
 
diff --git a/pandas/tests/io/test_http_auth.py b/pandas/tests/io/test_http_auth.py
index 79fb7c018af31..6e74964679b02 100644
--- a/pandas/tests/io/test_http_auth.py
+++ b/pandas/tests/io/test_http_auth.py
@@ -1,8 +1,21 @@
 import pytest
+from pandas.io.common import InsecureRequestWarning
 import pandas as pd
+import pandas.util.testing as tm
+from urllib2 import HTTPError
 
+uname = 'pandasusr'
+pwd = 'pandaspwd'
+no_auth_path = 'no_auth/'
+basic_auth_path = 'basic_auth/'
+valid_ssl_url = 'handsome-equator.000webhostapp.com'
+invalid_ssl_url = 'pandas-unittest.site11.com'
 
-def gen_http_auth_ssl_test_cases():
+
+def gen_http_auth_ssl_test_cases(uname,
+                                 pwd,
+                                 is_auth,
+                                 sub_path):
     """
     Generate list of test case to test for : http/https, username/pwd in url
     or as parameters, self signed ssl certs or trusted ssl certs, no auth
@@ -15,24 +28,20 @@ def gen_level1_tc():
         # 'urlopen' sets header 'Host' : '<fqdn>:<port>' - acceptable RFC7230
         # 'requests' sets header 'Host' : '<fqdn>'
         # so pandas fails on following hosting server (uses some 'apex' server)
-        # but pandas succeeds on nginx even if port is non-default. 
-        for host, verify_ssl in [('pandas-unittest.site11.com', False, ),
-                                 ('handsome-equator.000webhostapp.com', True)
+        # but pandas succeeds on nginx even if port is non-default.
+        for host, verify_ssl in [(invalid_ssl_url, False),
+                                 (valid_ssl_url, True)
                                  ]:
-            for sub_path, is_auth in [('no_auth/', False),
-                                      ('basic_auth/', True)]:
-                pre_ports = [('http', ''),
-                             ('https', '')]
-                for pre, port in pre_ports:
-                    test_cases.append(
-                        [host, verify_ssl, pre, port, sub_path, is_auth])
+            pre_ports = [('http', ''),
+                         ('https', '')]
+            for pre, port in pre_ports:
+                test_cases.append(
+                    [host, verify_ssl, pre, port, sub_path, is_auth])
         return test_cases
 
     def gen_base_url(pre, auth_prefix, host, port, su_pa):
         return '{}://{}{}{}/{}'.format(pre, auth_prefix, host, port, su_pa)
     tc2 = []
-    uname = 'pandasusr'
-    pwd = 'pandaspwd'
     for host, verify_ssl, pre, port, sp, is_auth in gen_level1_tc():
         u = uname if is_auth else None
         p = pwd if is_auth else None
@@ -49,9 +58,59 @@ def gen_base_url(pre, auth_prefix, host, port, su_pa):
     return tc2
 
 
+valid_no_auth = gen_http_auth_ssl_test_cases(uname='',
+                                             pwd='',
+                                             is_auth=False,
+                                             sub_path=no_auth_path)
+
+valid_auth = gen_http_auth_ssl_test_cases(uname=uname,
+                                          pwd=pwd,
+                                          is_auth=True,
+                                          sub_path=basic_auth_path)
+
+
+@pytest.mark.slow
+@pytest.mark.parametrize('url, uname, pwd, verify_ssl',
+                         valid_no_auth + valid_auth)
+def test_http_valid_auth(url, uname, pwd, verify_ssl):
+    check_http_auth(url, uname, pwd, verify_ssl)
+
+
+wrong_auth = gen_http_auth_ssl_test_cases(uname='fakepwd',
+                                          pwd='fakepwd',
+                                          is_auth=True,
+                                          sub_path=basic_auth_path)
+
+
+@pytest.mark.slow
 @pytest.mark.parametrize('url, uname, pwd, verify_ssl',
-                         gen_http_auth_ssl_test_cases())
-def test_http_auth_ssl(url, uname, pwd, verify_ssl):
+                         wrong_auth)
+def test_http_invalid_auth(url, uname, pwd, verify_ssl):
+    with pytest.raises(HTTPError):
+        check_http_auth(url, uname, pwd, verify_ssl)
+
+
+blank_uname = gen_http_auth_ssl_test_cases(uname='',
+                                           pwd='fakepwd',
+                                           is_auth=True,
+                                           sub_path=basic_auth_path)
+
+blank_pwd = gen_http_auth_ssl_test_cases(uname='fakepwd',
+                                         pwd='',
+                                         is_auth=True,
+                                         sub_path=basic_auth_path)
+
+
+@pytest.mark.slow
+@pytest.mark.parametrize('url, uname, pwd, verify_ssl',
+                         blank_uname + blank_pwd)
+def test_http_require_uname_and_pwd(url, uname, pwd, verify_ssl):
+    with pytest.raises(ValueError):
+        check_http_auth(url, uname, pwd, verify_ssl)
+
+
+@tm.network
+def check_http_auth(url, uname, pwd, verify_ssl):
 
     def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
         furl = url + fname
@@ -61,24 +120,24 @@ def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
         if verify_ssl is not None:
             kwargs['verify_ssl'] = verify_ssl
         msg = '{0: <90} -- auth:[{1: <10}/{2: <10}] v:[{3: <5}]'.format(
-              url, str(uname), str(pwd), str(verify_ssl))
+              furl, str(uname), str(pwd), str(verify_ssl))
         tcsv = 'animal,bird\ndog,pigeon\ncat,emu\n'
         j = '{"animal":{"0":"dog","1":"cat"},"bird":{"0":"pigeon","1":"emu"}}'
-        try:
+        if verify_ssl or furl.lower().startswith('http://'):
             df = pd_read_fn(furl, **kwargs)
-            if type(df) is list:  # html
-                df = df[0]
-            smatch = str(df.to_csv(index=False)) == tcsv
-            jmatch = str(df.to_json()) == j
-            res = 'Json : {}  -- String: {}'.format(jmatch, smatch)
-            if not jmatch or not smatch:
-                raise Exception(' ** ERROR:' + res)
-            else:
-                res += ' OK'
-            print(msg + ' ' + res)
-        except Exception as ex:
-            print(msg + ' ' + str(ex))
-            raise ex
+        else:
+            with tm.assert_produces_warning(InsecureRequestWarning):
+                df = pd_read_fn(furl, **kwargs)
+        if type(df) is list:  # html
+            df = df[0]
+        smatch = str(df.to_csv(index=False)) == tcsv
+        jmatch = str(df.to_json()) == j
+        res = 'Json : {}  -- String: {}'.format(jmatch, smatch)
+        if not jmatch or not smatch:
+            raise Exception(' ** ERROR:' + res)
+        else:
+            res += ' OK'
+        print(msg + ' ' + res)
         return True
 
     for pd_read_fn, fname in [(pd.read_csv, 'aaa.csv'),
@@ -87,3 +146,4 @@ def get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname):
                               (pd.read_html, 'html_file.html')
                               ]:
         assert get_df(url, uname, pwd, verify_ssl, pd_read_fn, fname)
+    return

From f520f7b9050186fe84301508daec27e310010049 Mon Sep 17 00:00:00 2001
From: Sky NSS <not-provided@hotma.com>
Date: Wed, 19 Jul 2017 20:44:47 -0700
Subject: [PATCH 14/14] Updated test case to work with py3. However still fails
 when run after 'test_html.py' with error AssertionError: Did not see expected
 warning of class 'InsecureRequestWarning'

---
 pandas/tests/io/test_http_auth.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/pandas/tests/io/test_http_auth.py b/pandas/tests/io/test_http_auth.py
index 6e74964679b02..26c9e0cf63ce5 100644
--- a/pandas/tests/io/test_http_auth.py
+++ b/pandas/tests/io/test_http_auth.py
@@ -2,7 +2,10 @@
 from pandas.io.common import InsecureRequestWarning
 import pandas as pd
 import pandas.util.testing as tm
-from urllib2 import HTTPError
+try:
+    from urllib2 import HTTPError
+except:
+    from urllib.error import HTTPError
 
 uname = 'pandasusr'
 pwd = 'pandaspwd'