Merge branch 'release-0.7.0'

.gitignore

@@ -14,5 +14,7 @@ spark-warehouse/
 derby.log
 
 *.ipynb*
-docs/doctrees
-docs/.buildinfo
+
+# Sphinx documentation
+docs/_build/
+docs/source/api/

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 repos:
--   repo: https://github.com/ambv/black
+-   repo: https://github.com/psf/black
     rev: stable
     hooks:
     - id: black

MANIFEST.in

@@ -0,0 +1,4 @@
+include README.rst
+include LICENSE
+include requirements.txt
+include test-requirements.txt

Makefile

@@ -0,0 +1,12 @@
+sphinx:
+	cd docs && \
+	make -f Makefile clean && \
+	make -f Makefile html && \
+	cd ..
+
+ghpages:
+	git checkout gh-pages && \
+	cp -r docs/build/html/* . && \
+	git add -u && \
+	git add -A && \
+	PRE_COMMIT_ALLOW_NO_CONFIG=1 git commit -m "Updated generated Sphinx documentation"

datacompy/_version.py

@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.6.0"
+__version__ = "0.7.0"

datacompy/core.py

@@ -24,6 +24,7 @@
 import logging
 import os
 
+
 import numpy as np
 import pandas as pd
 
@@ -61,7 +62,8 @@ class Compare:
     df2_name : str, optional
         A string name for the second dataframe
     ignore_spaces : bool, optional
-        Flag to strip whitespace (including newlines) from string columns
+        Flag to strip whitespace (including newlines) from string columns (including any join
+        columns)
     ignore_case : bool, optional
         Flag to ignore the case of string columns
 
@@ -229,6 +231,13 @@ def _dataframe_merge(self, ignore_spaces):
         else:
             params = {"on": self.join_columns}
 
+        if ignore_spaces:
+            for column in self.join_columns:
+                if self.df1[column].dtype.kind == "O":
+                    self.df1[column] = self.df1[column].str.strip()
+                if self.df2[column].dtype.kind == "O":
+                    self.df2[column] = self.df2[column].str.strip()
+
         outer_join = self.df1.merge(
             self.df2, how="outer", suffixes=("_df1", "_df2"), indicator=True, **params
         )
@@ -424,6 +433,25 @@ def sample_mismatch(self, column, sample_count=10, for_display=False):
             ]
         return to_return
 
+    def all_mismatch(self):
+        """All rows with any columns that have a mismatch. Returns all df1 and df2 versions of the columns and join
+        columns.
+
+        Returns
+        -------
+        Pandas.DataFrame
+            All rows of the intersection dataframe, containing any columns, that don't match.
+        """
+        match_list = []
+        return_list = []
+        for col in self.intersect_rows.columns:
+            if col.endswith("_match"):
+                match_list.append(col)
+                return_list.extend([col[:-6] + "_df1", col[:-6] + "_df2"])
+
+        mm_bool = self.intersect_rows[match_list].all(axis="columns")
+        return self.intersect_rows[~mm_bool][self.join_columns + return_list]
+
     def report(self, sample_count=10):
         """Returns a string representation of a report.  The representation can
         then be printed or saved to a file.

docs/.nojekyll

@@ -1 +0,0 @@
-

docs/Makefile

@@ -0,0 +1,29 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SPHINXPROJ    = datacompy
+SOURCEDIR     = source
+BUILDDIR      = build
+SPHINXAPI     = sphinx-apidoc
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+html: apidoc
+	$(SPHINXBUILD) -b html $(SPHINXOPTS) $(SOURCEDIR) $(BUILDDIR)/html
+
+apidoc:
+	$(SPHINXAPI) -f -o source/api ../datacompy
+	@echo "Regenerated API docs in ./source/api"
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)