Merge pull request #52 from pyexcel/dev

Release 0.5.9

CHANGELOG.rst

@@ -1,10 +1,19 @@
 Change log
 ================================================================================
 
+0.5.9 - 23.08.2018
+--------------------------------------------------------------------------------
+
+added
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+#. `pyexcel#148 <https://github.com/pyexcel/pyexcel/issues/148>`_, support
+   force_file_type
+
 0.5.8 - 16.08.2018
 --------------------------------------------------------------------------------
 
-fixed
+added
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 #. `#49 <https://github.com/pyexcel/pyexcel-io/issues/49>`_, support additional

changelog.yml

@@ -2,7 +2,13 @@ name: pyexcel-io
 organisation: pyexcel
 releases:
 - changes:
-  - action: fixed
+  - action: added
+    details:
+    - '`pyexcel#148`, support force_file_type'
+  date: 23.08.2018
+  version: 0.5.9
+- changes:
+  - action: added
     details:
     - '`#49`, support additional options when detecting float values in csv format. default_float_nan, ignore_nan_text'
   date: 16.08.2018

docs/source/conf.py

@@ -29,9 +29,9 @@
 author = u'C.W.'
 
 # The short X.Y version
-version = u'0.5.8'
+version = u'0.5.9'
 # The full version, including alpha/beta/rc tags
-release = u'0.5.8'
+release = u'0.5.9'
 
 
 # -- General configuration ---------------------------------------------------

pyexcel-io.yml

@@ -1,9 +1,9 @@
 overrides: "pyexcel.yaml"
 name: "pyexcel-io"
 nick_name: io
-version: 0.5.8
-current_version: 0.5.8
-release: 0.5.8
+version: 0.5.9
+current_version: 0.5.9
+release: 0.5.9
 dependencies:
   - ordereddict;python_version<"2.7"
   - lml==0.0.1

pyexcel_io/__init__.py

@@ -18,7 +18,9 @@
 
 BLACK_LIST = [__name__, "pyexcel_webio", "pyexcel_text"]
 WHITE_LIST = [
-    "pyexcel_io.readers", "pyexcel_io.writers", "pyexcel_io.database"
+    "pyexcel_io.readers",
+    "pyexcel_io.writers",
+    "pyexcel_io.database",
 ]
 PREFIX = "pyexcel_"
 

pyexcel_io/_compact.py

@@ -33,7 +33,6 @@
 except ImportError:
 
     class NullHandler(logging.Handler):
-
         def emit(self, record):
             pass
 
@@ -46,7 +45,6 @@ def emit(self, record):
     irange = xrange
 
     class Iterator(object):
-
         def next(self):
             return type(self).__next__(self)
 

pyexcel_io/book.py

@@ -16,6 +16,7 @@ class RWInterface(object):
     """
     The common methods for book reader and writer
     """
+
     stream_type = None
 
     def __init__(self):

pyexcel_io/constants.py

@@ -16,11 +16,21 @@
 MESSAGE_ERROR_02 = "No content, file name. Nothing is given"
 MESSAGE_ERROR_03 = "cannot handle unknown content"
 MESSAGE_WRONG_IO_INSTANCE = "Wrong io instance is passed for your file format."
-MESSAGE_CANNOT_WRITE_STREAM_FORMATTER = "Cannot write content of file type %s to stream"
-MESSAGE_CANNOT_READ_STREAM_FORMATTER = "Cannot read content of file type %s from stream"
-MESSAGE_CANNOT_WRITE_FILE_TYPE_FORMATTER = "Cannot write content of file type %s to file %s"
-MESSAGE_CANNOT_READ_FILE_TYPE_FORMATTER = "Cannot read content of file type %s from file %s"
-MESSAGE_LOADING_FORMATTER = "The plugin for file type %s is not installed. Please install %s"
+MESSAGE_CANNOT_WRITE_STREAM_FORMATTER = (
+    "Cannot write content of file type %s to stream"
+)
+MESSAGE_CANNOT_READ_STREAM_FORMATTER = (
+    "Cannot read content of file type %s from stream"
+)
+MESSAGE_CANNOT_WRITE_FILE_TYPE_FORMATTER = (
+    "Cannot write content of file type %s to file %s"
+)
+MESSAGE_CANNOT_READ_FILE_TYPE_FORMATTER = (
+    "Cannot read content of file type %s from file %s"
+)
+MESSAGE_LOADING_FORMATTER = (
+    "The plugin for file type %s is not installed. Please install %s"
+)
 MESSAGE_EMPTY_ARRAY = "One empty row is found"
 MESSAGE_IGNORE_ROW = "One row is ignored"
 MESSAGE_DB_EXCEPTION = """
@@ -47,5 +57,5 @@
 DEFAULT_MULTI_CSV_SEPARATOR = "__"
 SEPARATOR_FORMATTER = "---%s---" % DEFAULT_NAME + "%s"
 SEPARATOR_MATCHER = "---%s:(.*)---" % DEFAULT_NAME
-DEFAULT_CSV_STREAM_FILE_FORMATTER = ("---%s:" % DEFAULT_NAME + "%s---%s")
+DEFAULT_CSV_STREAM_FILE_FORMATTER = "---%s:" % DEFAULT_NAME + "%s---%s"
 DEFAULT_CSV_NEWLINE = "\r\n"

pyexcel_io/database/importers/django.py

@@ -81,8 +81,7 @@ def create_sheet(self, sheet_name):
             )
         else:
             raise Exception(
-                "Sheet: %s does not match any given models."
-                % sheet_name
+                "Sheet: %s does not match any given models." % sheet_name
                 + "Please be aware of case sensitivity."
             )
 

pyexcel_io/database/importers/sqlalchemy.py

@@ -18,6 +18,7 @@ class PyexcelSQLSkipRowException(Exception):
     Raised this exception to skipping a row
     while data import
     """
+
     pass
 
 
@@ -93,8 +94,7 @@ def create_sheet(self, sheet_name):
             )
         else:
             raise Exception(
-                "Sheet: %s does not match any given tables."
-                % sheet_name
+                "Sheet: %s does not match any given tables." % sheet_name
                 + "Please be aware of case sensitivity."
             )
 

pyexcel_io/exceptions.py

@@ -11,14 +11,17 @@
 
 class NoSupportingPluginFound(Exception):
     """raised when an known file extension is seen"""
+
     pass
 
 
 class SupportingPluginAvailableButNotInstalled(Exception):
     """raised when a known plugin is not installed"""
+
     pass
 
 
 class UpgradePlugin(Exception):
     """raised when a known plugin is not compatible"""
+
     pass

pyexcel_io/io.py

@@ -23,6 +23,8 @@ def iget_data(afile, file_type=None, **keywords):
     :param sheet_index: the index of the sheet to be loaded
     :param sheets: a list of sheet to be loaded
     :param file_type: used only when filename is not a physial file name
+    :param force_file_type: used only when filename refers to a physical file
+                            and it is intended to open it as forced file type.
     :param streaming: toggles the type of returned data. The values of the
                       returned dictionary remain as generator if it is set
                       to True. Default is False.
@@ -147,6 +149,7 @@ def load_data(
     file_content=None,
     file_stream=None,
     file_type=None,
+    force_file_type=None,
     sheet_name=None,
     sheet_index=None,
     sheets=None,
@@ -158,6 +161,8 @@ def load_data(
 
     :param filename: actual file name, a file stream or actual content
     :param file_type: used only when filename is not a physial file name
+    :param force_file_type: used only when filename refers to a physical file
+                            and it is intended to open it as forced file type.
     :param sheet_name: the name of the sheet to be loaded
     :param sheet_index: the index of the sheet to be loaded
     :param keywords: any other parameters
@@ -169,10 +174,13 @@ def load_data(
         raise IOError(constants.MESSAGE_ERROR_02)
 
     if file_type is None:
-        try:
-            file_type = file_name.split(".")[-1]
-        except AttributeError:
-            raise Exception("file_name should be a string type")
+        if force_file_type:
+            file_type = force_file_type
+        else:
+            try:
+                file_type = file_name.split(".")[-1]
+            except AttributeError:
+                raise Exception("file_name should be a string type")
 
     reader = READERS.get_a_plugin(file_type, library)
     if file_name:

pyexcel_io/plugins.py

@@ -98,7 +98,9 @@ def raise_exception(self, file_type):
             message = "Please install "
             if len(plugins) > 1:
                 message += ERROR_MESSAGE_FORMATTER % (
-                    self.action, file_type, ",".join(plugins)
+                    self.action,
+                    file_type,
+                    ",".join(plugins),
                 )
             else:
                 message += plugins[0]

pyexcel_io/readers/csvr.py

@@ -84,7 +84,7 @@ def __next__(self):
                 if bom_header == BOM_BIG_ENDIAN:
                     self.__endian = BIG_ENDIAN
         elif self.__endian == LITTLE_ENDIAN:
-            line = line[self.__zeros_left_in_2_row:]
+            line = line[self.__zeros_left_in_2_row :]  # flake8: noqa
         if self.__endian == LITTLE_ENDIAN:
             line = line.rstrip()
         line = line.decode(self.__encoding)
@@ -168,14 +168,14 @@ def __convert_cell(self, csv_cell_text):
             ret = service.detect_int_value(csv_cell_text, self.__pep_0515_off)
         if ret is None and self.__auto_detect_float:
             ret = service.detect_float_value(
-                csv_cell_text, self.__pep_0515_off,
+                csv_cell_text,
+                self.__pep_0515_off,
                 ignore_nan_text=self.__ignore_nan_text,
-                default_float_nan=self.__default_float_nan
+                default_float_nan=self.__default_float_nan,
             )
             shall_we_ignore_the_conversion = (
-                (ret in [float("inf"), float("-inf")])
-                and self.__ignore_infinity
-            )
+                ret in [float("inf"), float("-inf")]
+            ) and self.__ignore_infinity
             if shall_we_ignore_the_conversion:
                 ret = None
         if ret is None and self.__auto_detect_datetime:

pyexcel_io/service.py

@@ -40,9 +40,8 @@ def detect_date_value(cell_text):
 
 
 def detect_float_value(
-        cell_text, pep_0515_off=True,
-        ignore_nan_text=False,
-        default_float_nan=None):
+    cell_text, pep_0515_off=True, ignore_nan_text=False, default_float_nan=None
+):
     should_we_skip_it = (
         cell_text.startswith("0") and cell_text.startswith("0.") is False
     )

setup.py

@@ -11,15 +11,15 @@
 
 NAME = 'pyexcel-io'
 AUTHOR = 'C.W.'
-VERSION = '0.5.8'
+VERSION = '0.5.9'
 EMAIL = 'wangc_2011@hotmail.com'
 LICENSE = 'New BSD'
 DESCRIPTION = (
     'A python library to read and write structured data in csv, zipped csv' +
     'format and to/from databases'
 )
 URL = 'https://github.com/pyexcel/pyexcel-io'
-DOWNLOAD_URL = '%s/archive/0.5.8.tar.gz' % URL
+DOWNLOAD_URL = '%s/archive/0.5.9.tar.gz' % URL
 FILES = ['README.rst', 'CHANGELOG.rst']
 KEYWORDS = [
     'API',
@@ -63,8 +63,8 @@
 # You do not need to read beyond this line
 PUBLISH_COMMAND = '{0} setup.py sdist bdist_wheel upload -r pypi'.format(
     sys.executable)
-GS_COMMAND = ('gs pyexcel-io v0.5.8 ' +
-              "Find 0.5.8 in changelog for more details")
+GS_COMMAND = ('gs pyexcel-io v0.5.9 ' +
+              "Find 0.5.9 in changelog for more details")
 NO_GS_MESSAGE = ('Automatic github release is disabled. ' +
                  'Please install gease to enable it.')
 UPLOAD_FAILED_MSG = (

test.bat

@@ -1,2 +1,2 @@
 pip freeze
-nosetests --with-coverage --cover-package pyexcel_io --cover-package tests --with-doctest --doctest-extension=.rst README.rst docs/source pyexcel_io && flake8 . --exclude=.moban.d,docs --builtins=unicode,xrange,long
+nosetests --with-coverage --cover-package pyexcel_io --cover-package tests tests --with-doctest --doctest-extension=.rst README.rst docs/source pyexcel_io && flake8 . --exclude=.moban.d,docs --builtins=unicode,xrange,long

test.sh

@@ -1,2 +1,2 @@
 pip freeze
-nosetests --with-coverage --cover-package pyexcel_io --cover-package tests --with-doctest --doctest-extension=.rst README.rst docs/source pyexcel_io && flake8 . --exclude=.moban.d,docs --builtins=unicode,xrange,long
+nosetests --with-coverage --cover-package pyexcel_io --cover-package tests tests --with-doctest --doctest-extension=.rst README.rst docs/source pyexcel_io && flake8 . --exclude=.moban.d,docs --builtins=unicode,xrange,long

tests/fixtures/force_file_type.txt

@@ -0,0 +1 @@
+1,2,3

tests/test_base.py

@@ -1,6 +1,4 @@
-from pyexcel_io.sheet import (
-    SheetReader, SheetWriter, NamedContent
-)
+from pyexcel_io.sheet import SheetReader, SheetWriter, NamedContent
 from pyexcel_io.book import BookWriter
 from pyexcel_io.utils import is_empty_array
 from nose.tools import raises
@@ -28,7 +26,6 @@ def write_row(self, array):
 
 
 class TestSheetReader:
-
     @raises(Exception)
     def test_abstractness(self):
         reader = SheetReader("test")
@@ -54,13 +51,13 @@ def name(self):
 
             def to_array(self):
                 pass
+
         b = B(name)
         b.to_array()
         assert b.name == name
 
 
 class TestSheetWriter:
-
     @raises(NotImplementedError)
     def test_abstractness(self):
         writer = SheetWriter("te", "st", "abstract")
@@ -71,28 +68,20 @@ class D(SheetWriter):
             def write_row(self, row):
                 pass
 
-        d = D('t', 'e', 's')
+        d = D("t", "e", "s")
         d.write_row([11, 11])
 
     def test_writer(self):
         native_sheet = NamedContent("test", [])
-        content = [
-            [1, 2],
-            [3, 4],
-            [5, 6]
-        ]
+        content = [[1, 2], [3, 4], [5, 6]]
         writer = ArrayWriter(None, native_sheet, "test")
         writer.write_row(content[0])
         writer.write_array(content[1:])
         assert native_sheet.payload == content
 
     def test_writer2(self):
         native_sheet = NamedContent("test", [])
-        content = [
-            [1, 2],
-            [3, 4],
-            [5, 6]
-        ]
+        content = [[1, 2], [3, 4], [5, 6]]
         writer = ArrayWriter(None, native_sheet, None)
         writer.write_row(content[0])
         writer.write_array(content[1:])