8a91d86783
Although the boilerplate checker was very fast it can be faster. With this change we can hand the boilerplate a list of files which need to be checked or give it no files. If given no files it will run all files in the repo. Before you had to explicitly tell the boiler checker the 'extention' of the the files. In this case we let the checker figure it out and load the headers as needed. Doing the whole repo takes about 0.4 seconds. Doing a single go file takes < .04 seconds.
159 lines
4.6 KiB
Python
Executable File
159 lines
4.6 KiB
Python
Executable File
#!/usr/bin/env python
|
|
|
|
# Copyright 2015 The Kubernetes Authors All rights reserved.
|
|
#
|
|
# Licensed 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.
|
|
|
|
from __future__ import print_function
|
|
|
|
import argparse
|
|
import glob
|
|
import json
|
|
import mmap
|
|
import os
|
|
import re
|
|
import sys
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("filenames", help="list of files to check, all files if unspecified", nargs='*')
|
|
args = parser.parse_args()
|
|
|
|
rootdir = os.path.dirname(__file__) + "/../../"
|
|
rootdir = os.path.abspath(rootdir)
|
|
|
|
def get_refs():
|
|
refs = {}
|
|
for path in glob.glob(os.path.join(rootdir, "hack/boilerplate/boilerplate.*.txt")):
|
|
extension = os.path.basename(path).split(".")[1]
|
|
|
|
ref_file = open(path, 'r')
|
|
ref = ref_file.read().splitlines()
|
|
ref_file.close()
|
|
refs[extension] = ref
|
|
|
|
return refs
|
|
|
|
def file_passes(filename, refs, regexs):
|
|
try:
|
|
f = open(filename, 'r')
|
|
except:
|
|
return False
|
|
|
|
data = f.read()
|
|
f.close()
|
|
|
|
extension = file_extension(filename)
|
|
ref = refs[extension]
|
|
|
|
# remove build tags from the top of Go files
|
|
if extension == "go":
|
|
p = regexs["go_build_constraints"]
|
|
(data, found) = p.subn("", data, 1)
|
|
|
|
# remove shebang from the top of shell files
|
|
if extension == "sh":
|
|
p = regexs["shebang"]
|
|
(data, found) = p.subn("", data, 1)
|
|
|
|
data = data.splitlines()
|
|
|
|
# if our test file is smaller than the reference it surely fails!
|
|
if len(ref) > len(data):
|
|
return False
|
|
|
|
# trim our file to the same number of lines as the reference file
|
|
data = data[:len(ref)]
|
|
|
|
p = regexs["year"]
|
|
for d in data:
|
|
if p.search(d):
|
|
return False
|
|
|
|
# Replace all occurrences of the regex "2015|2014" with "YEAR"
|
|
p = regexs["date"]
|
|
for i, d in enumerate(data):
|
|
(data[i], found) = p.subn('YEAR', d)
|
|
if found != 0:
|
|
break
|
|
|
|
# if we don't match the reference at this point, fail
|
|
if ref != data:
|
|
return False
|
|
|
|
return True
|
|
|
|
def file_extension(filename):
|
|
return os.path.splitext(filename)[1].split(".")[-1].lower()
|
|
|
|
skipped_dirs = ['Godeps', 'third_party', '_output', '.git']
|
|
def normalize_files(files):
|
|
newfiles = []
|
|
for pathname in files:
|
|
if any(x in pathname for x in skipped_dirs):
|
|
continue
|
|
newfiles.append(pathname)
|
|
for i, pathname in enumerate(newfiles):
|
|
if not os.path.isabs(pathname):
|
|
newfiles[i] = os.path.join(rootdir, pathname)
|
|
return newfiles
|
|
|
|
def get_files(extensions):
|
|
files = []
|
|
if len(args.filenames) > 0:
|
|
files = args.filenames
|
|
else:
|
|
for root, dirs, walkfiles in os.walk(rootdir):
|
|
# don't visit certain dirs. This is just a performance improvement
|
|
# as we would prune these later in normalize_files(). But doing it
|
|
# cuts down the amount of filesystem walking we do and cuts down
|
|
# the size of the file list
|
|
for d in skipped_dirs:
|
|
if d in dirs:
|
|
dirs.remove(d)
|
|
|
|
for name in walkfiles:
|
|
pathname = os.path.join(root, name)
|
|
files.append(pathname)
|
|
|
|
files = normalize_files(files)
|
|
outfiles = []
|
|
for pathname in files:
|
|
extension = file_extension(pathname)
|
|
if extension in extensions:
|
|
outfiles.append(pathname)
|
|
return outfiles
|
|
|
|
def get_regexs():
|
|
regexs = {}
|
|
# Search for "YEAR" which exists in the boilerplate, but shouldn't in the real thing
|
|
regexs["year"] = re.compile( 'YEAR' )
|
|
# dates can be 2014 or 2015, company holder names can be anything
|
|
regexs["date"] = re.compile( '(2014|2015)' )
|
|
# strip // +build \n\n build constraints
|
|
regexs["go_build_constraints"] = re.compile(r"^(// \+build.*\n)+\n", re.MULTILINE)
|
|
# strip #!.* from shell scripts
|
|
regexs["shebang"] = re.compile(r"^(#!.*\n)\n*", re.MULTILINE)
|
|
return regexs
|
|
|
|
def main():
|
|
regexs = get_regexs()
|
|
refs = get_refs()
|
|
filenames = get_files(refs.keys())
|
|
|
|
for filename in filenames:
|
|
if not file_passes(filename, refs, regexs):
|
|
print(filename, file=sys.stdout)
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|