github.com/GoogleContainerTools/kaniko@v1.23.0/hack/boilerplate/boilerplate.py (about)

     1  #!/usr/bin/env python3
     2  
     3  # Copyright 2018 Google LLC
     4  #
     5  # Licensed under the Apache License, Version 2.0 (the "License");
     6  # you may not use this file except in compliance with the License.
     7  # You may obtain a copy of the License at
     8  #
     9  #     http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  
    17  from __future__ import print_function
    18  
    19  import argparse
    20  import glob
    21  import os
    22  import re
    23  import sys
    24  
    25  
    26  SKIPPED_DIRS = ["Godeps", "third_party", ".git", "vendor", "examples", "testdata"]
    27  SKIPPED_FILES = ["install_golint.sh"]
    28  
    29  parser = argparse.ArgumentParser()
    30  parser.add_argument("filenames", help="list of files to check, all files if unspecified", nargs='*')
    31  
    32  rootdir = os.path.dirname(__file__) + "/../"
    33  rootdir = os.path.abspath(rootdir)
    34  parser.add_argument("--rootdir", default=rootdir, help="root directory to examine")
    35  
    36  default_boilerplate_dir = os.path.join(rootdir, "/boilerplate")
    37  parser.add_argument("--boilerplate-dir", default=default_boilerplate_dir)
    38  args = parser.parse_args()
    39  
    40  
    41  def get_refs():
    42      refs = {}
    43  
    44      for path in glob.glob(os.path.join(args.boilerplate_dir, "boilerplate.*.txt")):
    45          extension = os.path.basename(path).split(".")[1]
    46  
    47          ref_file = open(path, 'r')
    48          ref = ref_file.read().splitlines()
    49          ref_file.close()
    50          refs[extension] = ref
    51  
    52      return refs
    53  
    54  def file_passes(filename, refs, regexs):
    55      try:
    56          f = open(filename, 'r')
    57      except:
    58          return False
    59  
    60      data = f.read()
    61      f.close()
    62  
    63      basename = os.path.basename(filename)
    64      extension = file_extension(filename)
    65      if extension != "":
    66          ref = refs[extension]
    67      else:
    68          ref = refs[basename]
    69  
    70      # remove build tags from the top of Go files
    71      if extension == "go":
    72          p = regexs["go_build_constraints_go"]
    73          (data, found) = p.subn("", data, 1)
    74  
    75      if extension == "go":
    76          p = regexs["go_build_constraints"]
    77          (data, found) = p.subn("", data, 1)
    78  
    79      # remove shebang from the top of shell files
    80      elif extension == "sh":
    81          p = regexs["shebang"]
    82          (data, found) = p.subn("", data, 1)
    83  
    84      data = data.splitlines()
    85  
    86      # if our test file is smaller than the reference it surely fails!
    87      if len(ref) > len(data):
    88          return False
    89  
    90      # trim our file to the same number of lines as the reference file
    91      data = data[:len(ref)]
    92  
    93      p = regexs["year"]
    94      for d in data:
    95          if p.search(d):
    96              return False
    97  
    98      # Replace all occurrences of the date regex with "YEAR"
    99      p = regexs["date"]
   100      for i, d in enumerate(data):
   101          (data[i], found) = p.subn('YEAR', d)
   102          if found != 0:
   103              break
   104  
   105      # if we don't match the reference at this point, fail
   106      if ref != data:
   107          return False
   108  
   109      return True
   110  
   111  def file_extension(filename):
   112      return os.path.splitext(filename)[1].split(".")[-1].lower()
   113  
   114  def normalize_files(files):
   115      newfiles = []
   116      for i, pathname in enumerate(files):
   117          if not os.path.isabs(pathname):
   118              newfiles.append(os.path.join(args.rootdir, pathname))
   119      return newfiles
   120  
   121  def get_files(extensions):
   122      files = []
   123      if len(args.filenames) > 0:
   124          files = args.filenames
   125      else:
   126          for root, dirs, walkfiles in os.walk(args.rootdir):
   127              for d in SKIPPED_DIRS:
   128                  if d in dirs:
   129                      dirs.remove(d)
   130  
   131              for name in walkfiles:
   132                  if name not in SKIPPED_FILES:
   133                      pathname = os.path.join(root, name)
   134                      files.append(pathname)
   135  
   136      files = normalize_files(files)
   137      outfiles = []
   138      for pathname in files:
   139          basename = os.path.basename(pathname)
   140          extension = file_extension(pathname)
   141          if extension in extensions or basename in extensions:
   142              outfiles.append(pathname)
   143      return outfiles
   144  
   145  def get_regexs():
   146      regexs = {}
   147      # Search for "YEAR" which exists in the boilerplate, but shouldn't in the real thing
   148      regexs["year"] = re.compile( 'YEAR' )
   149      # dates can be any year [2000-2099] company holder names can be anything
   150      regexs["date"] = re.compile( '(20\d\d)' )
   151      # strip // go:build \n\n build constraints
   152      regexs["go_build_constraints_go"] = re.compile(r"^(//go\:build.*)+\n", re.MULTILINE)
   153      # strip // +build \n\n build constraints
   154      regexs["go_build_constraints"] = re.compile(r"^(// \+build.*\n)+\n", re.MULTILINE)
   155      # strip #!.* from shell scripts
   156      regexs["shebang"] = re.compile(r"^(#!.*\n)\n*", re.MULTILINE)
   157      return regexs
   158  
   159  def main():
   160      regexs = get_regexs()
   161      refs = get_refs()
   162      filenames = get_files(refs.keys())
   163  
   164      for filename in filenames:
   165          if not file_passes(filename, refs, regexs):
   166              print(filename, file=sys.stdout)
   167  
   168  if __name__ == "__main__":
   169    sys.exit(main())