aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMechCoder <manojkumarsivaraj334@gmail.com>2015-07-15 08:25:53 -0700
committerDavies Liu <davies.liu@gmail.com>2015-07-15 08:25:53 -0700
commit20bb10f8644a92a57496b5df639008832b30e34d (patch)
tree9b455807bd130409773697ab566feb05c29f729b
parentadb33d3665770daf2ccb8915d19e198be9dc3b47 (diff)
downloadspark-20bb10f8644a92a57496b5df639008832b30e34d.tar.gz
spark-20bb10f8644a92a57496b5df639008832b30e34d.tar.bz2
spark-20bb10f8644a92a57496b5df639008832b30e34d.zip
[SPARK-8706] [PYSPARK] [PROJECT INFRA] Add pylint checks to PySpark
This adds Pylint checks to PySpark. For now this lazy installs using easy_install to /dev/pylint (similar to the pep8 script). We still need to figure out what rules to be allowed. Author: MechCoder <manojkumarsivaraj334@gmail.com> Closes #7241 from MechCoder/pylint and squashes the following commits: 2fc7291 [MechCoder] Remove pylint test fail 6d883a2 [MechCoder] Silence warnings and make pylint tests fail to check if it works in jenkins f3a5e17 [MechCoder] undefined-variable ca8b749 [MechCoder] Minor changes 71629f8 [MechCoder] remove trailing whitespace 8498ff9 [MechCoder] Remove blacklisted arguments and pointless statements check 1dbd094 [MechCoder] Disable all checks for now 8b8aa8a [MechCoder] Add pylint configuration file 7871bb1 [MechCoder] [SPARK-8706] [PySpark] [Project infra] Add pylint checks to PySpark
-rwxr-xr-xdev/lint-python57
-rw-r--r--pylintrc404
-rw-r--r--python/pyspark/ml/param/shared.py4
-rw-r--r--python/pyspark/tests.py3
4 files changed, 457 insertions, 11 deletions
diff --git a/dev/lint-python b/dev/lint-python
index 0c3586462c..e02dff220e 100755
--- a/dev/lint-python
+++ b/dev/lint-python
@@ -21,12 +21,14 @@ SCRIPT_DIR="$( cd "$( dirname "$0" )" && pwd )"
SPARK_ROOT_DIR="$(dirname "$SCRIPT_DIR")"
PATHS_TO_CHECK="./python/pyspark/ ./ec2/spark_ec2.py ./examples/src/main/python/ ./dev/sparktestsupport"
PATHS_TO_CHECK="$PATHS_TO_CHECK ./dev/run-tests.py ./python/run-tests.py"
-PYTHON_LINT_REPORT_PATH="$SPARK_ROOT_DIR/dev/python-lint-report.txt"
+PEP8_REPORT_PATH="$SPARK_ROOT_DIR/dev/pep8-report.txt"
+PYLINT_REPORT_PATH="$SPARK_ROOT_DIR/dev/pylint-report.txt"
+PYLINT_INSTALL_INFO="$SPARK_ROOT_DIR/dev/pylint-info.txt"
cd "$SPARK_ROOT_DIR"
# compileall: https://docs.python.org/2/library/compileall.html
-python -B -m compileall -q -l $PATHS_TO_CHECK > "$PYTHON_LINT_REPORT_PATH"
+python -B -m compileall -q -l $PATHS_TO_CHECK > "$PEP8_REPORT_PATH"
compile_status="${PIPESTATUS[0]}"
# Get pep8 at runtime so that we don't rely on it being installed on the build server.
@@ -47,11 +49,36 @@ if [ ! -e "$PEP8_SCRIPT_PATH" ]; then
fi
fi
+# Easy install pylint in /dev/pylint. To easy_install into a directory, the PYTHONPATH should
+# be set to the directory.
+# dev/pylint should be appended to the PATH variable as well.
+# Jenkins by default installs the pylint3 version, so for now this just checks the code quality
+# of python3.
+export "PYTHONPATH=$SPARK_ROOT_DIR/dev/pylint"
+export "PYLINT_HOME=$PYTHONPATH"
+export "PATH=$PYTHONPATH:$PATH"
+
+if [ ! -d "$PYLINT_HOME" ]; then
+ mkdir "$PYLINT_HOME"
+ # Redirect the annoying pylint installation output.
+ easy_install -d "$PYLINT_HOME" pylint==1.4.4 &>> "$PYLINT_INSTALL_INFO"
+ easy_install_status="$?"
+
+ if [ "$easy_install_status" -ne 0 ]; then
+ echo "Unable to install pylint locally in \"$PYTHONPATH\"."
+ cat "$PYLINT_INSTALL_INFO"
+ exit "$easy_install_status"
+ fi
+
+ rm "$PYLINT_INSTALL_INFO"
+
+fi
+
# There is no need to write this output to a file
#+ first, but we do so so that the check status can
#+ be output before the report, like with the
#+ scalastyle and RAT checks.
-python "$PEP8_SCRIPT_PATH" --ignore=E402,E731,E241,W503,E226 $PATHS_TO_CHECK >> "$PYTHON_LINT_REPORT_PATH"
+python "$PEP8_SCRIPT_PATH" --ignore=E402,E731,E241,W503,E226 $PATHS_TO_CHECK >> "$PEP8_REPORT_PATH"
pep8_status="${PIPESTATUS[0]}"
if [ "$compile_status" -eq 0 -a "$pep8_status" -eq 0 ]; then
@@ -61,13 +88,27 @@ else
fi
if [ "$lint_status" -ne 0 ]; then
- echo "Python lint checks failed."
- cat "$PYTHON_LINT_REPORT_PATH"
+ echo "PEP8 checks failed."
+ cat "$PEP8_REPORT_PATH"
+else
+ echo "PEP8 checks passed."
+fi
+
+rm "$PEP8_REPORT_PATH"
+
+for to_be_checked in "$PATHS_TO_CHECK"
+do
+ pylint --rcfile="$SPARK_ROOT_DIR/pylintrc" $to_be_checked >> "$PYLINT_REPORT_PATH"
+done
+
+if [ "${PIPESTATUS[0]}" -ne 0 ]; then
+ lint_status=1
+ echo "Pylint checks failed."
+ cat "$PYLINT_REPORT_PATH"
else
- echo "Python lint checks passed."
+ echo "Pylint checks passed."
fi
-# rm "$PEP8_SCRIPT_PATH"
-rm "$PYTHON_LINT_REPORT_PATH"
+rm "$PYLINT_REPORT_PATH"
exit "$lint_status"
diff --git a/pylintrc b/pylintrc
new file mode 100644
index 0000000000..0617759603
--- /dev/null
+++ b/pylintrc
@@ -0,0 +1,404 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+[MASTER]
+
+# Specify a configuration file.
+#rcfile=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Profiled execution.
+profile=no
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=pyspark.heapq3
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Use multiple processes to speed up Pylint.
+jobs=1
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code
+extension-pkg-whitelist=
+
+# Allow optimization of some AST trees. This will activate a peephole AST
+# optimizer, which will apply various small optimizations. For instance, it can
+# be used to obtain the result of joining multiple strings with the addition
+# operator. Joining a lot of strings can lead to a maximum recursion error in
+# Pylint and this flag can prevent that. It has one side effect, the resulting
+# AST will be different than the one from reality.
+optimize-ast=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED
+confidence=
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time. See also the "--disable" option for examples.
+enable=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once).You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use"--disable=all --enable=classes
+# --disable=W"
+
+# These errors are arranged in order of number of warning given in pylint.
+# If you would like to improve the code quality of pyspark, remove any of these disabled errors
+# run ./dev/lint-python and see if the errors raised by pylint can be fixed.
+
+disable=invalid-name,missing-docstring,protected-access,unused-argument,no-member,unused-wildcard-import,redefined-builtin,too-many-arguments,unused-variable,too-few-public-methods,bad-continuation,duplicate-code,redefined-outer-name,too-many-ancestors,import-error,superfluous-parens,unused-import,line-too-long,no-name-in-module,unnecessary-lambda,import-self,no-self-use,unidiomatic-typecheck,fixme,too-many-locals,cyclic-import,too-many-branches,bare-except,wildcard-import,dangerous-default-value,broad-except,too-many-public-methods,deprecated-lambda,anomalous-backslash-in-string,too-many-lines,reimported,too-many-statements,bad-whitespace,unpacking-non-sequence,too-many-instance-attributes,abstract-method,old-style-class,global-statement,attribute-defined-outside-init,arguments-differ,undefined-all-variable,no-init,useless-else-on-loop,super-init-not-called,notimplemented-raised,too-many-return-statements,pointless-string-statement,global-variable-undefined,bad-classmethod-argument,too-many-format-args,parse-error,no-self-argument,pointless-statement,undefined-variable
+
+
+[REPORTS]
+
+# Set the output format. Available formats are text, parseable, colorized, msvs
+# (visual studio) and html. You can also give a reporter class, eg
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Put messages in a separate file for each module / package specified on the
+# command line instead of printing them on stdout. Reports (if any) will be
+# written in a file name "pylint_global.[txt|html]".
+files-output=no
+
+# Tells whether to display a full report or only the messages
+reports=no
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Add a comment according to your evaluation note. This is used by the global
+# evaluation report (RP0004).
+comment=no
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details
+#msg-template=
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,XXX,TODO
+
+
+[BASIC]
+
+# Required attributes for module, separated by a comma
+required-attributes=
+
+# List of builtins function names that should not be used, separated by a comma
+bad-functions=
+
+# Good variable names which should always be accepted, separated by a comma
+good-names=i,j,k,ex,Run,_
+
+# Bad variable names which should always be refused, separated by a comma
+bad-names=baz,toto,tutu,tata
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Include a hint for the correct naming format with invalid-name
+include-naming-hint=no
+
+# Regular expression matching correct function names
+function-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for function names
+function-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression matching correct variable names
+variable-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for variable names
+variable-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression matching correct constant names
+const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__))$
+
+# Naming hint for constant names
+const-name-hint=(([A-Z_][A-Z0-9_]*)|(__.*__))$
+
+# Regular expression matching correct attribute names
+attr-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for attribute names
+attr-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression matching correct argument names
+argument-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for argument names
+argument-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression matching correct class attribute names
+class-attribute-rgx=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$
+
+# Naming hint for class attribute names
+class-attribute-name-hint=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$
+
+# Regular expression matching correct inline iteration names
+inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$
+
+# Naming hint for inline iteration names
+inlinevar-name-hint=[A-Za-z_][A-Za-z0-9_]*$
+
+# Regular expression matching correct class names
+class-rgx=[A-Z_][a-zA-Z0-9]+$
+
+# Naming hint for class names
+class-name-hint=[A-Z_][a-zA-Z0-9]+$
+
+# Regular expression matching correct module names
+module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
+
+# Naming hint for module names
+module-name-hint=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
+
+# Regular expression matching correct method names
+method-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for method names
+method-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=__.*__
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+
+[FORMAT]
+
+# Maximum number of characters on a single line.
+max-line-length=100
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+# List of optional constructs for which whitespace checking is disabled
+no-space-check=trailing-comma,dict-separator
+
+# Maximum number of lines in a module
+max-module-lines=1000
+
+# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1
+# tab).
+indent-string=' '
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+
+[SIMILARITIES]
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+
+[VARIABLES]
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# A regular expression matching the name of dummy variables (i.e. expectedly
+# not used).
+dummy-variables-rgx=_$|dummy
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid to define new builtins when possible.
+additional-builtins=
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,_cb
+
+
+[SPELLING]
+
+# Spelling dictionary name. Available dictionaries: none. To make it working
+# install python-enchant package.
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to indicated private dictionary in
+# --spelling-private-dict-file option instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[LOGGING]
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format
+logging-modules=logging
+
+
+[TYPECHECK]
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis
+ignored-modules=
+
+# List of classes names for which member attributes should not be checked
+# (useful for classes with attributes dynamically set).
+ignored-classes=SQLObject
+
+# When zope mode is activated, add a predefined set of Zope acquired attributes
+# to generated-members.
+zope=no
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E0201 when accessed. Python regular
+# expressions are accepted.
+generated-members=REQUEST,acl_users,aq_parent
+
+
+[CLASSES]
+
+# List of interface methods to ignore, separated by a comma. This is used for
+# instance to not check methods defines in Zope's Interface base class.
+ignore-iface-methods=isImplementedBy,deferred,extends,names,namesAndDescriptions,queryDescriptionFor,getBases,getDescriptionFor,getDoc,getName,getTaggedValue,getTaggedValueTags,isEqualOrExtendedBy,setTaggedValue,isImplementedByInstancesOf,adaptWith,is_implemented_by
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,__new__,setUp
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,_fields,_replace,_source,_make
+
+
+[IMPORTS]
+
+# Deprecated modules which should not be used, separated by a comma
+deprecated-modules=regsub,TERMIOS,Bastion,rexec
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled)
+import-graph=
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled)
+ext-import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled)
+int-import-graph=
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method
+max-args=5
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore
+ignored-argument-names=_.*
+
+# Maximum number of locals for function / method body
+max-locals=15
+
+# Maximum number of return / yield for function / method body
+max-returns=6
+
+# Maximum number of branch for function / method body
+max-branches=12
+
+# Maximum number of statements in function / method body
+max-statements=50
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "Exception"
+overgeneral-exceptions=Exception
diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py
index bc088e4c29..5951247263 100644
--- a/python/pyspark/ml/param/shared.py
+++ b/python/pyspark/ml/param/shared.py
@@ -444,7 +444,7 @@ class DecisionTreeParams(Params):
minInfoGain = Param(Params._dummy(), "minInfoGain", "Minimum information gain for a split to be considered at a tree node.")
maxMemoryInMB = Param(Params._dummy(), "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
cacheNodeIds = Param(Params._dummy(), "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.")
-
+
def __init__(self):
super(DecisionTreeParams, self).__init__()
@@ -460,7 +460,7 @@ class DecisionTreeParams(Params):
self.maxMemoryInMB = Param(self, "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
#: param for If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.
self.cacheNodeIds = Param(self, "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.")
-
+
def setMaxDepth(self, value):
"""
Sets the value of :py:attr:`maxDepth`.
diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py
index c5c0add49d..2122501680 100644
--- a/python/pyspark/tests.py
+++ b/python/pyspark/tests.py
@@ -893,7 +893,8 @@ class RDDTests(ReusedPySparkTestCase):
self.assertRaises(Py4JJavaError, rdd.pipe('cc', checkCode=True).collect)
result = rdd.pipe('cat').collect()
result.sort()
- [self.assertEqual(x, y) for x, y in zip(data, result)]
+ for x, y in zip(data, result):
+ self.assertEqual(x, y)
self.assertRaises(Py4JJavaError, rdd.pipe('grep 4', checkCode=True).collect)
self.assertEqual([], rdd.pipe('grep 4').collect())