format repo using git-filter-repo

format-everything.py

#!/usr/bin/env python3

"""
This script is meant to format all java files in your repo using maven-formatter-plugin
"""

import argparse
import os
import sys
import subprocess
import tempfile
import uuid
try:
  import git_filter_repo as fr
except ImportError:
  raise SystemExit("Error: Couldn't find git_filter_repo.py.  Did you forget to make a symlink to git-filter-repo named git_filter_repo.py or did you forget to put the latter in your PYTHONPATH?")

tmpdir = None
blobs_handled = {}
cat_file_process = None
def lint_with_real_filenames(commit, metadata):
  filenames_to_tmp_map = {}
  for change in commit.file_changes:
    if change.type == b'D':
      continue
    elif not change.filename.lower().endswith(b".java"):
      continue
    else:
      # Get the old blob contents
      cat_file_process.stdin.write(change.blob_id + b'\n')
      cat_file_process.stdin.flush()
      objhash, objtype, objsize = cat_file_process.stdout.readline().split()
      contents_plus_newline = cat_file_process.stdout.read(int(objsize)+1)

      # Write it out to a file with the same basename
      filename = os.path.join(tmpdir, os.fsencode(str(uuid.uuid4()) + ".java"))

      filenames_to_tmp_map[change.filename] = filename

      with open(filename, "wb") as f:
        f.write(contents_plus_newline[:-1])

  files_to_format = []
  for filename in filenames_to_tmp_map:
    files_to_format.append(os.path.basename(filenames_to_tmp_map[filename]).decode("utf-8"))

  # Format the file
  separator = ","
  subprocess.check_call(["mvn",
                         # "-X"
                         "net.revelc.code.formatter:formatter-maven-plugin:2.11.0:format",
                         "\"-Dconfigfile=/Users/%USERNAME%/Desktop/style.xml\"",
                         "\"-DsourceDirectory=" + tmpdir.decode('utf-8') + "/\"",
                         "\"-Dformatter.includes="+ separator.join(files_to_format) +"\""])

  # update history
  for change in commit.file_changes:
    if change.blob_id in blobs_handled:
      change.blob_id = blobs_handled[change.blob_id]
    elif change.type == b'D':
          continue
    elif not change.filename.lower().endswith(b".java"):
      continue
    else:
      filename = filenames_to_tmp_map[change.filename]
      # Get the new contents
      with open(filename, "rb") as f:
        blob = fr.Blob(f.read())

      # Insert the new file into the filter's stream, and remove the tempfile
      filter.insert(blob)
      os.remove(filename)

      # Record our handling of the blob and use it for this change
      blobs_handled[change.blob_id] = blob.id
      change.blob_id = blob.id

args = fr.FilteringOptions.default_options()
args.force = True

# actually start formatting procedure
tmpdir = tempfile.mkdtemp().encode()
cat_file_process = subprocess.Popen(['git', 'cat-file', '--batch'],
                                  stdin = subprocess.PIPE,
                                  stdout = subprocess.PIPE)
filter = fr.RepoFilter(args, commit_callback=lint_with_real_filenames)
filter.run()
cat_file_process.stdin.close()
cat_file_process.wait()