github/kubernetes
1
0
Fork 0
mirror of https://github.com/k3s-io/kubernetes.git synced 2025-08-08 11:38:15 +00:00
Code Issues Projects Releases Wiki Activity

Cleanup boilerpate.py

Browse Source 
- reformatted with https://github.com/psf/black
- fixed some of the https://github.com/pylint-dev/pylint warnings
This commit is contained in:
Ed Bartosh 2023-05-30 00:49:30 +03:00
parent 320d915897
commit 534f5edb53
1 changed files with 68 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

128
hack/boilerplate/boilerplate.py
View File

@ -24,23 +24,22 @@ import sys
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument( parser.add_argument(
"filenames", "filenames", help="list of files to check, all files if unspecified", nargs="*"
help="list of files to check, all files if unspecified", )
nargs='*')
rootdir = os.path.dirname(__file__) + "/../../" rootdir = os.path.dirname(__file__) + "/../../"
rootdir = os.path.abspath(rootdir) rootdir = os.path.abspath(rootdir)
parser.add_argument( parser.add_argument("--rootdir", default=rootdir, help="root directory to examine")
"--rootdir", default=rootdir, help="root directory to examine")
default_boilerplate_dir = os.path.join(rootdir, "hack/boilerplate") default_boilerplate_dir = os.path.join(rootdir, "hack/boilerplate")
parser.add_argument( parser.add_argument("--boilerplate-dir", default=default_boilerplate_dir)
"--boilerplate-dir", default=default_boilerplate_dir)
parser.add_argument( parser.add_argument(
"-v", "--verbose", "-v",
"--verbose",
help="give verbose output regarding why a file does not pass", help="give verbose output regarding why a file does not pass",
action="store_true") action="store_true",
)
args = parser.parse_args() args = parser.parse_args()
@ -53,31 +52,26 @@ def get_refs():
for path in glob.glob(os.path.join(args.boilerplate_dir, "boilerplate.*.txt")): for path in glob.glob(os.path.join(args.boilerplate_dir, "boilerplate.*.txt")):
extension = os.path.basename(path).split(".")[1] extension = os.path.basename(path).split(".")[1]
ref_file = open(path, 'r') with open(path, "r") as ref_file:
ref = ref_file.read().splitlines() refs[extension] = ref_file.read().splitlines()
ref_file.close()
refs[extension] = ref
return refs return refs
def is_generated_file(filename, data, regexs): def is_generated_file(data, regexs):
p = regexs["generated"] return regexs["generated"].search(data)
return p.search(data)
def file_passes(filename, refs, regexs): def file_passes(filename, refs, regexs):
try: try:
f = open(filename, 'r') with open(filename) as stream:
except Exception as exc: data = stream.read()
print("Unable to open %s: %s" % (filename, exc), file=verbose_out) except OSError as exc:
print(f"Unable to open {filename}: {exc}", file=verbose_out)
return False return False
data = f.read()
f.close()
# determine if the file is automatically generated # determine if the file is automatically generated
generated = is_generated_file(filename, data, regexs) generated = is_generated_file(data, regexs)
basename = os.path.basename(filename) basename = os.path.basename(filename)
extension = file_extension(filename) extension = file_extension(filename)
@ -91,51 +85,55 @@ def file_passes(filename, refs, regexs):
ref = refs[basename] ref = refs[basename]
# remove extra content from the top of files # remove extra content from the top of files
if extension == "go" or extension == "generatego": if extension in ("go", "generatego"):
p = regexs["go_build_constraints"] data, found = regexs["go_build_constraints"].subn("", data, 1)
(data, found) = p.subn("", data, 1)
elif extension in ["sh", "py"]: elif extension in ["sh", "py"]:
p = regexs["shebang"] data, found = regexs["shebang"].subn("", data, 1)
(data, found) = p.subn("", data, 1)
data = data.splitlines() data = data.splitlines()
# if our test file is smaller than the reference it surely fails! # if our test file is smaller than the reference it surely fails!
if len(ref) > len(data): if len(ref) > len(data):
print('File %s smaller than reference (%d < %d)' % print(
(filename, len(data), len(ref)), f"File {filename} smaller than reference ({len(data)} < {len(ref)})",
file=verbose_out) file=verbose_out,
)
return False return False
# trim our file to the same number of lines as the reference file # trim our file to the same number of lines as the reference file
data = data[:len(ref)] data = data[: len(ref)]
p = regexs["year"] pattern = regexs["year"]
for d in data: for line in data:
if p.search(d): if pattern.search(line):
if generated: if generated:
print('File %s has the YEAR field, but it should not be in generated file' % print(
filename, file=verbose_out) f"File {filename} has the YEAR field, but it should not be in generated file",
file=verbose_out,
)
else: else:
print('File %s has the YEAR field, but missing the year of date' % print(
filename, file=verbose_out) "File {filename} has the YEAR field, but missing the year of date",
file=verbose_out,
)
return False return False
if not generated: if not generated:
# Replace all occurrences of the regex "2014|2015|2016|2017|2018" with "YEAR" # Replace all occurrences of the regex "2014|2015|2016|2017|2018" with "YEAR"
p = regexs["date"] pattern = regexs["date"]
for i, d in enumerate(data): for i, line in enumerate(data):
(data[i], found) = p.subn('YEAR', d) data[i], found = pattern.subn("YEAR", line)
if found != 0: if found != 0:
break break
# if we don't match the reference at this point, fail # if we don't match the reference at this point, fail
if ref != data: if ref != data:
print("Header in %s does not match reference, diff:" % print(f"Header in {filename} does not match reference, diff:", file=verbose_out)
filename, file=verbose_out)
if args.verbose: if args.verbose:
print(file=verbose_out) print(file=verbose_out)
for line in difflib.unified_diff(ref, data, 'reference', filename, lineterm=''): for line in difflib.unified_diff(
ref, data, "reference", filename, lineterm=""
):
print(line, file=verbose_out) print(line, file=verbose_out)
print(file=verbose_out) print(file=verbose_out)
return False return False
@ -147,9 +145,17 @@ def file_extension(filename):
return os.path.splitext(filename)[1].split(".")[-1].lower() return os.path.splitext(filename)[1].split(".")[-1].lower()
skipped_names = ['third_party', '_gopath', '_output', '.git', 'cluster/env.sh', skipped_names = [
"vendor", "test/e2e/generated/bindata.go", "hack/boilerplate/test", "third_party",
"staging/src/k8s.io/kubectl/pkg/generated/bindata.go"] "_gopath",
"_output",
".git",
"cluster/env.sh",
"vendor",
"test/e2e/generated/bindata.go",
"hack/boilerplate/test",
"staging/src/k8s.io/kubectl/pkg/generated/bindata.go",
]
def normalize_files(files): def normalize_files(files):
@ -174,13 +180,13 @@ def get_files(extensions):
# as we would prune these later in normalize_files(). But doing it # as we would prune these later in normalize_files(). But doing it
# cuts down the amount of filesystem walking we do and cuts down # cuts down the amount of filesystem walking we do and cuts down
# the size of the file list # the size of the file list
for d in skipped_names: for dname in skipped_names:
if d in dirs: if dname in dirs:
dirs.remove(d) dirs.remove(dname)
for d in dirs: for dname in dirs:
# dirs that start with __ are ignored # dirs that start with __ are ignored
if re.match("^__", d): if dname.startswith("__"):
dirs.remove(d) dirs.remove(dname)
for name in walkfiles: for name in walkfiles:
pathname = os.path.join(root, name) pathname = os.path.join(root, name)
@ -198,21 +204,23 @@ def get_files(extensions):
def get_dates(): def get_dates():
years = datetime.datetime.now().year years = datetime.datetime.now().year
return '(%s)' % '|'.join((str(year) for year in range(2014, years+1))) return "(%s)" % "|".join(str(year) for year in range(2014, years + 1))
def get_regexs(): def get_regexs():
regexs = {} regexs = {}
# Search for "YEAR" which exists in the boilerplate, but shouldn't in the real thing # Search for "YEAR" which exists in the boilerplate, but shouldn't in the real thing
regexs["year"] = re.compile('YEAR') regexs["year"] = re.compile("YEAR")
# get_dates return 2014, 2015, 2016, 2017, or 2018 until the current year as a regex like: "(2014|2015|2016|2017|2018)"; # get_dates return 2014, 2015, 2016, 2017, or 2018 until the current year
# as a regex like: "(2014|2015|2016|2017|2018)";
# company holder names can be anything # company holder names can be anything
regexs["date"] = re.compile(get_dates()) regexs["date"] = re.compile(get_dates())
# strip the following build constraints/tags: # strip the following build constraints/tags:
# //go:build # //go:build
# // +build \n\n # // +build \n\n
regexs["go_build_constraints"] = re.compile( regexs["go_build_constraints"] = re.compile(
r"^(//(go:build| \+build).*\n)+\n", re.MULTILINE) r"^(//(go:build| \+build).*\n)+\n", re.MULTILINE
)
# strip #!.* from scripts # strip #!.* from scripts
regexs["shebang"] = re.compile(r"^(#!.*\n)\n*", re.MULTILINE) regexs["shebang"] = re.compile(r"^(#!.*\n)\n*", re.MULTILINE)
# Search for generated files # Search for generated files
@ -223,11 +231,11 @@ def get_regexs():
def main(): def main():
regexs = get_regexs() regexs = get_regexs()
refs = get_refs() refs = get_refs()
filenames = get_files(list(refs.keys())) filenames = get_files(refs)
for filename in filenames: for filename in filenames:
if not file_passes(filename, refs, regexs): if not file_passes(filename, refs, regexs):
print(filename, file=sys.stdout) print(filename)
return 0 return 0