|
| 1 | +#!/usr/bin/env python3 |
| 2 | +import os |
| 3 | +import re |
| 4 | +import argparse |
| 5 | +from datetime import datetime |
| 6 | + |
| 7 | +# Regex to match copyright years (e.g., 2002-2025, 2025, 2002-2026) |
| 8 | +FORMAT_REGEX = re.compile(r"Copyright \(c\) (\d{4})-(\d{4})(?:,)? University Corporation for Atmospheric Research") |
| 9 | +COPYRIGHT_REGEX = re.compile(r"(?i)copyright") |
| 10 | +DATE_REGEX = re.compile(r"\s*(?:\(c\)\s*|=\s*(?:u\')?)?(\d{4})(?:-(\d{4}))?") |
| 11 | +NLDATE_REGEX = re.compile(r"^\s*(?:\!|\%|\/\/|\*)?\s*(?:\(c\)\s*|=\s*(?:u\')?|u\')?(\d{4})(?:-(\d{4}))?") |
| 12 | + |
| 13 | +# List of root directories to skip |
| 14 | +SKIP_ROOTDIRS = ['.git', 'obj', 'mod', 'lib'] |
| 15 | + |
| 16 | +# List of file extensions to skip |
| 17 | +SKIP_EXTENSIONS = ['.vsd', '.eps'] |
| 18 | + |
| 19 | +# List of directories to skip |
| 20 | +SKIP_DIRS = [ |
| 21 | + os.path.normpath('src/Infrastructure/Mesh/src/Zoltan'), |
| 22 | + os.path.normpath('src/Infrastructure/Mesh/src/Lapack'), |
| 23 | + os.path.normpath('src/Infrastructure/Mesh/src/Moab'), |
| 24 | + os.path.normpath('src/Infrastructure/Base/include/nlohmann'), |
| 25 | + os.path.normpath('src/prologue/yaml-cpp'), |
| 26 | + os.path.normpath('src/Infrastructure/IO/PIO'), |
| 27 | + os.path.normpath('src/Infrastructure/Mesh/include/sacado'), |
| 28 | + os.path.normpath('src/addon/esmpy/src/esmpy/util/enum'), |
| 29 | +] |
| 30 | + |
| 31 | +# List of specific files to skip |
| 32 | +SKIP_FILES = [ |
| 33 | + os.path.normpath('scripts/maintain_copyrights.py'), |
| 34 | + os.path.normpath('src/doc/ESMF_quickstart.tex'), |
| 35 | + os.path.normpath('src/Infrastructure/Trace/include/ESMCI_HashNode.h'), |
| 36 | + os.path.normpath('src/Infrastructure/Trace/include/ESMCI_HashMap.h'), |
| 37 | + os.path.normpath('src/Infrastructure/Trace/include/ESMCI_KeyHash.h'), |
| 38 | + os.path.normpath('src/Infrastructure/Trace/include/esmftrc.h'), |
| 39 | + os.path.normpath('src/Infrastructure/Trace/include/metadata'), |
| 40 | + os.path.normpath('src/Infrastructure/Trace/include/esmftrc-bitfield.h'), |
| 41 | + os.path.normpath('src/Infrastructure/Trace/src/esmftrc.c'), |
| 42 | + os.path.normpath('src/Infrastructure/Util/include/dmp_diff.hpp'), |
| 43 | +] |
| 44 | + |
| 45 | +# List of copyright line matches to skip |
| 46 | +SKIP_MATCHES = [ |
| 47 | + "HashMap Development Team", |
| 48 | + "Philippe Proulx", |
| 49 | + "Mathieu Desnoyers", |
| 50 | + "The diff-match-patch Authors", |
| 51 | + "Victor Grishchenko", |
| 52 | +] |
| 53 | + |
| 54 | +def print_exclusions(): |
| 55 | + """ |
| 56 | + Print the lists of excluded file extensions, directories, files, and line |
| 57 | + matches. |
| 58 | + """ |
| 59 | + print("### Exclusions") |
| 60 | + print("\nExclude file extensions:") |
| 61 | + for d in SKIP_EXTENSIONS: |
| 62 | + print("- " + d) |
| 63 | + print("\nExclude directories:") |
| 64 | + for d in SKIP_DIRS: |
| 65 | + print("- " + d) |
| 66 | + print("\nExclude files:") |
| 67 | + for f in SKIP_FILES: |
| 68 | + print("- " + f) |
| 69 | + print("\nExclude lines matching:") |
| 70 | + for m in SKIP_MATCHES: |
| 71 | + print("- " + m) |
| 72 | + print("") |
| 73 | + |
| 74 | +def find_outdated_copyrights(search_year, loutdated=False): |
| 75 | + """ |
| 76 | + Find all copyright years in the codebase that are older than the given |
| 77 | + search year. |
| 78 | + """ |
| 79 | + outdated = [] |
| 80 | + for root, dirs, files in os.walk('.'): |
| 81 | + # Skip root directories |
| 82 | + if any(skip in root for skip in SKIP_ROOTDIRS): |
| 83 | + continue |
| 84 | + # Skip specified directories |
| 85 | + rel_root = os.path.normpath(os.path.relpath(root, '.')) |
| 86 | + if any(rel_root.startswith(skip_dir) for skip_dir in SKIP_DIRS): |
| 87 | + continue |
| 88 | + for fname in files: |
| 89 | + # Skip files with extensions in SKIP_EXTENSIONS |
| 90 | + if any(fname.lower().endswith(ext) for ext in SKIP_EXTENSIONS): |
| 91 | + continue |
| 92 | + path = os.path.join(root, fname) |
| 93 | + # Skip specific files |
| 94 | + rel_path = os.path.normpath(os.path.relpath(path, '.')) |
| 95 | + if rel_path in SKIP_FILES: |
| 96 | + continue |
| 97 | + try: |
| 98 | + with open(path, 'r', encoding='utf-8') as f: |
| 99 | + lines = f.readlines() |
| 100 | + for i in range(len(lines)): |
| 101 | + line = lines[i] |
| 102 | + nline = lines[i+1] if i < len(lines)-1 else "" |
| 103 | + cmatch = COPYRIGHT_REGEX.search(line) |
| 104 | + if cmatch: |
| 105 | + # Skip lines matching SKIP_MATCHES |
| 106 | + if any(skip_str in line for skip_str in SKIP_MATCHES): |
| 107 | + continue |
| 108 | + dmatch = DATE_REGEX.search(line, pos=cmatch.end()) |
| 109 | + if dmatch: |
| 110 | + fwarn = not(FORMAT_REGEX.search(line)) |
| 111 | + syear = int(dmatch.group(1)) |
| 112 | + eyear = int(dmatch.group(2)) if dmatch.group(2) else syear |
| 113 | + pos = dmatch.end()-3 |
| 114 | + if eyear != search_year: |
| 115 | + outdated.append((path, i+1, pos, eyear, bool(fwarn))) |
| 116 | + else: |
| 117 | + nmatch = NLDATE_REGEX.search(nline) |
| 118 | + if nmatch: |
| 119 | + fwarn = not(FORMAT_REGEX.search(nline)) |
| 120 | + syear = int(nmatch.group(1)) |
| 121 | + eyear = int(nmatch.group(2)) if nmatch.group(2) else syear |
| 122 | + pos = nmatch.end()-3 |
| 123 | + if eyear != search_year: |
| 124 | + outdated.append((path, i+2, pos, eyear, bool(fwarn))) |
| 125 | + except UnicodeDecodeError: |
| 126 | + # Skip files that cannot be decoded as UTF-8 |
| 127 | + continue |
| 128 | + if loutdated: |
| 129 | + print_outdated_copyrights(outdated) |
| 130 | + return outdated |
| 131 | + |
| 132 | +def print_outdated_copyrights(outdated_list): |
| 133 | + """ |
| 134 | + Print each outdated copyright year in the outdated list as a markdown table. |
| 135 | + """ |
| 136 | + if outdated_list: |
| 137 | + print("### Outdated Copyright Years") |
| 138 | + print("\n| file:line:position | year | warning |") |
| 139 | + print("|--------------------|------|---------|") |
| 140 | + for file, line, pos, year, fwarn in outdated_list: |
| 141 | + if fwarn: |
| 142 | + print(f"| {file}:{line}:{pos} | {year} | ! |") |
| 143 | + else: |
| 144 | + print(f"| {file}:{line}:{pos} | {year} | |") |
| 145 | + print("") |
| 146 | + |
| 147 | +def format_warnings(outdated_list): |
| 148 | + """ |
| 149 | + Print warnings for copyright years that may not be in the correct format. |
| 150 | + """ |
| 151 | + fwarnings = [] |
| 152 | + if outdated_list: |
| 153 | + for file, line, pos, year, fwarn in outdated_list: |
| 154 | + if fwarn: |
| 155 | + fwarnings.append((file, line, pos, year)) |
| 156 | + if fwarnings: |
| 157 | + print("### Format Warnings") |
| 158 | + print("\nCheck Copyright Format: " |
| 159 | + " \n Copyright (c) YYYY-YYYY, University Corporation for" |
| 160 | + " Atmospheric Research") |
| 161 | + print("\n| file:line:position | year | warning |") |
| 162 | + print("|--------------------|------|---------|") |
| 163 | + for file, line, pos, year in fwarnings: |
| 164 | + print(f"|{file}:{line}:{pos} | {year} | ! |") |
| 165 | + print("") |
| 166 | + return fwarnings |
| 167 | + |
| 168 | +def update_copyrights(update_list, new_year, add=False, lupdated=False): |
| 169 | + """ |
| 170 | + For each copyright year in update list, replace the old |
| 171 | + copyright year with the new copyright year. |
| 172 | + """ |
| 173 | + updated = [] |
| 174 | + if update_list: |
| 175 | + for file, line, pos, year, fwarn in update_list: |
| 176 | + with open(file, 'r', newline="") as f: |
| 177 | + lines = f.readlines() |
| 178 | + oldline = lines[line-1] |
| 179 | + newline = oldline[:pos-1] + str(new_year) + oldline[pos-1+len(str(year)):] |
| 180 | + lines[line-1] = newline |
| 181 | + with open(file, 'w') as f: |
| 182 | + f.writelines(lines) |
| 183 | + updated.append((file, line, pos, year, new_year, fwarn)) |
| 184 | + if add: |
| 185 | + os.system(f"git add {file}") |
| 186 | + if lupdated: |
| 187 | + print_updated_copyrights(updated) |
| 188 | + return updated |
| 189 | + |
| 190 | +def print_updated_copyrights(updated_list): |
| 191 | + """ |
| 192 | + Print each updated copyright year in the updated list as a markdown table. |
| 193 | + """ |
| 194 | + if updated_list: |
| 195 | + print("### Updated Copyright Years") |
| 196 | + print("\n| file:line:position | old year | new year | warning |") |
| 197 | + print("|--------------------|----------|----------|---------|") |
| 198 | + for file, line, pos, oyear, nyear, ewarn in updated_list: |
| 199 | + if ewarn: |
| 200 | + print(f"{file}:{line}:{pos} | {oyear} | {nyear} | ! |") |
| 201 | + else: |
| 202 | + print(f"{file}:{line}:{pos} | {oyear} | {nyear} | |") |
| 203 | + print("") |
| 204 | + |
| 205 | +if __name__ == "__main__": |
| 206 | + parser = argparse.ArgumentParser(description="check and update copyright years.") |
| 207 | + parser.add_argument('-y', '--year', type=int, default=datetime.now().year, help='year to check copyright against (default: current year)') |
| 208 | + parser.add_argument('-l', '--list', action='store_true', default=False, help='list outdated copyright years') |
| 209 | + parser.add_argument('-w', '--warnings', action='store_true', default=False, help='list warnings for updating copyright years') |
| 210 | + parser.add_argument('-u', '--update', action='store_true', default=False, help='update outdated copyright years') |
| 211 | + parser.add_argument('-a', '--add', action='store_true', default=False, help='run git add on updated files') |
| 212 | + parser.add_argument('-x', '--exclusions', action='store_true', default=False, help='list excluded extensions, directories, files, and patterns') |
| 213 | + |
| 214 | + args = parser.parse_args() |
| 215 | + |
| 216 | + if args.exclusions: |
| 217 | + print_exclusions() |
| 218 | + outdated = find_outdated_copyrights(args.year, |
| 219 | + (args.list and not args.update)) |
| 220 | + if args.update: |
| 221 | + updated = update_copyrights(outdated, args.year, args.add, args.list) |
| 222 | + else: |
| 223 | + updated = [] |
| 224 | + if args.warnings: |
| 225 | + fwarnings = format_warnings(outdated) |
| 226 | + else: |
| 227 | + fwarnings = [] |
| 228 | + |
| 229 | + print(f"Total outdated copyright years: {len(outdated)}") |
| 230 | + if args.update: |
| 231 | + print(f"Total updated copyright years: {len(updated)}") |
| 232 | + if args.warnings: |
| 233 | + print(f"Total warnings: {len(fwarnings)}") |
0 commit comments