|
| 1 | +#!/usr/bin/env python3 |
| 2 | + |
| 3 | +# Due to various technical limitations, we sometimes have files that need to be |
| 4 | +# kept identical in the repository. This script loads a database of such |
| 5 | +# files and can perform two functions: check whether they are still identical, |
| 6 | +# and overwrite the others with a master copy if needed. |
| 7 | + |
| 8 | +import hashlib |
| 9 | +import shutil |
| 10 | +import os |
| 11 | +import sys |
| 12 | +import json |
| 13 | +import re |
| 14 | +path = os.path |
| 15 | + |
| 16 | +file_groups = {} |
| 17 | + |
| 18 | +def add_prefix(prefix, relative): |
| 19 | + result = path.join(prefix, relative) |
| 20 | + if path.commonprefix((path.realpath(result), path.realpath(prefix))) != \ |
| 21 | + path.realpath(prefix): |
| 22 | + raise Exception("Path {} is not below {}".format( |
| 23 | + result, prefix)) |
| 24 | + return result |
| 25 | + |
| 26 | +def load_if_exists(prefix, json_file_relative): |
| 27 | + json_file_name = path.join(prefix, json_file_relative) |
| 28 | + if path.isfile(json_file_name): |
| 29 | + print("Loading file groups from", json_file_name) |
| 30 | + with open(json_file_name, 'r', encoding='utf-8') as fp: |
| 31 | + raw_groups = json.load(fp) |
| 32 | + prefixed_groups = { |
| 33 | + name: [ |
| 34 | + add_prefix(prefix, relative) |
| 35 | + for relative in relatives |
| 36 | + ] |
| 37 | + for name, relatives in raw_groups.items() |
| 38 | + } |
| 39 | + file_groups.update(prefixed_groups) |
| 40 | + |
| 41 | +# Generates a list of C# test files that should be in sync |
| 42 | +def csharp_test_files(): |
| 43 | + test_file_re = re.compile('.*(Bad|Good)[0-9]*\\.cs$') |
| 44 | + csharp_doc_files = { |
| 45 | + file:os.path.join(root, file) |
| 46 | + for root, dirs, files in os.walk("csharp/ql/src") |
| 47 | + for file in files |
| 48 | + if test_file_re.match(file) |
| 49 | + } |
| 50 | + return { |
| 51 | + "C# test '" + file + "'" : [os.path.join(root, file), csharp_doc_files[file]] |
| 52 | + for root, dirs, files in os.walk("csharp/ql/test") |
| 53 | + for file in files |
| 54 | + if file in csharp_doc_files |
| 55 | + } |
| 56 | + |
| 57 | +def file_checksum(filename): |
| 58 | + with open(filename, 'rb') as file_handle: |
| 59 | + return hashlib.sha1(file_handle.read()).hexdigest() |
| 60 | + |
| 61 | +def check_group(group_name, files, master_file_picker, emit_error): |
| 62 | + checksums = {file_checksum(f) for f in files} |
| 63 | + |
| 64 | + if len(checksums) == 1: |
| 65 | + return |
| 66 | + |
| 67 | + master_file = master_file_picker(files) |
| 68 | + if master_file is None: |
| 69 | + emit_error(__file__, 0, |
| 70 | + "Files from group '"+ group_name +"' not in sync.") |
| 71 | + emit_error(__file__, 0, |
| 72 | + "Run this script with a file-name argument among the " |
| 73 | + "following to overwrite the remaining files with the contents " |
| 74 | + "of that file or run with the --latest switch to update each " |
| 75 | + "group of files from the most recently modified file in the group.") |
| 76 | + for filename in files: |
| 77 | + emit_error(__file__, 0, " " + filename) |
| 78 | + else: |
| 79 | + print(" Syncing others from", master_file) |
| 80 | + for filename in files: |
| 81 | + if filename == master_file: |
| 82 | + continue |
| 83 | + print(" " + filename) |
| 84 | + os.replace(filename, filename + '~') |
| 85 | + shutil.copy(master_file, filename) |
| 86 | + print(" Backups written with '~' appended to file names") |
| 87 | + |
| 88 | +def chdir_repo_root(): |
| 89 | + root_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), '..') |
| 90 | + os.chdir(root_path) |
| 91 | + |
| 92 | +def choose_master_file(master_file, files): |
| 93 | + if master_file in files: |
| 94 | + return master_file |
| 95 | + else: |
| 96 | + return None |
| 97 | + |
| 98 | +def choose_latest_file(files): |
| 99 | + latest_time = None |
| 100 | + latest_file = None |
| 101 | + for filename in files: |
| 102 | + file_time = os.path.getmtime(filename) |
| 103 | + if (latest_time is None) or (latest_time < file_time): |
| 104 | + latest_time = file_time |
| 105 | + latest_file = filename |
| 106 | + return latest_file |
| 107 | + |
| 108 | +local_error_count = 0 |
| 109 | +def emit_local_error(path, line, error): |
| 110 | + print('ERROR: ' + path + ':' + line + " - " + error) |
| 111 | + global local_error_count |
| 112 | + local_error_count += 1 |
| 113 | + |
| 114 | +# This function is invoked directly by a CI script, which passes a different error-handling |
| 115 | +# callback. |
| 116 | +def sync_identical_files(emit_error): |
| 117 | + if len(sys.argv) == 1: |
| 118 | + master_file_picker = lambda files: None |
| 119 | + elif len(sys.argv) == 2: |
| 120 | + if sys.argv[1] == "--latest": |
| 121 | + master_file_picker = choose_latest_file |
| 122 | + elif os.path.isfile(sys.argv[1]): |
| 123 | + master_file_picker = lambda files: choose_master_file(sys.argv[1], files) |
| 124 | + else: |
| 125 | + raise Exception("File not found") |
| 126 | + else: |
| 127 | + raise Exception("Bad command line or file not found") |
| 128 | + chdir_repo_root() |
| 129 | + load_if_exists('.', 'config/identical-files.json') |
| 130 | + file_groups.update(csharp_test_files()) |
| 131 | + for group_name, files in file_groups.items(): |
| 132 | + check_group(group_name, files, master_file_picker, emit_error) |
| 133 | + |
| 134 | +def main(): |
| 135 | + sync_identical_files(emit_local_error) |
| 136 | + if local_error_count > 0: |
| 137 | + exit(1) |
| 138 | + |
| 139 | +if __name__ == "__main__": |
| 140 | + main() |
0 commit comments