1#! /usr/bin/env python3 2# __ __ _ 3# ___\ \/ /_ __ __ _| |_ 4# / _ \\ /| '_ \ / _` | __| 5# | __// \| |_) | (_| | |_ 6# \___/_/\_\ .__/ \__,_|\__| 7# |_| XML parser 8# 9# Copyright (c) 2019-2025 Sebastian Pipping <sebastian@pipping.org> 10# Copyright (c) 2021 Tim Bray <tbray@textuality.com> 11# Licensed under the MIT license: 12# 13# Permission is hereby granted, free of charge, to any person obtaining 14# a copy of this software and associated documentation files (the 15# "Software"), to deal in the Software without restriction, including 16# without limitation the rights to use, copy, modify, merge, publish, 17# distribute, sublicense, and/or sell copies of the Software, and to permit 18# persons to whom the Software is furnished to do so, subject to the 19# following conditions: 20# 21# The above copyright notice and this permission notice shall be included 22# in all copies or substantial portions of the Software. 23# 24# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 25# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 26# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN 27# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 28# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 29# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 30# USE OR OTHER DEALINGS IN THE SOFTWARE. 31 32import argparse 33 34epilog = """ 35environment variables: 36 EXPAT_ACCOUNTING_DEBUG=(0|1|2|3) 37 Control verbosity of accounting debugging (default: 0) 38 EXPAT_ENTITY_DEBUG=(0|1) 39 Control verbosity of entity debugging (default: 0) 40 EXPAT_ENTROPY_DEBUG=(0|1) 41 Control verbosity of entropy debugging (default: 0) 42 EXPAT_MALLOC_DEBUG=(0|1|2) 43 Control verbosity of allocation tracker (default: 0) 44 45exit status: 46 0 the input files are well-formed and the output (if requested) was written successfully 47 1 could not allocate data structures, signals a serious problem with execution environment 48 2 one or more input files were not well-formed 49 3 could not create an output file 50 4 command-line argument error 51 52xmlwf of libexpat is software libre, licensed under the MIT license. 53Please report bugs at https://github.com/libexpat/libexpat/issues -- thank you! 54""" 55 56usage = """ 57 %(prog)s [OPTIONS] [FILE ...] 58 %(prog)s -h|--help 59 %(prog)s -v|--version 60""" 61 62parser = argparse.ArgumentParser(prog='xmlwf', add_help=False, 63 usage=usage, 64 description='xmlwf - Determines if an XML document is well-formed', 65 formatter_class=argparse.RawTextHelpFormatter, 66 epilog=epilog) 67 68input_related = parser.add_argument_group('input control arguments') 69input_related.add_argument('-s', action='store_true', help='print an error if the document is not [s]tandalone') 70input_related.add_argument('-n', action='store_true', help='enable [n]amespace processing') 71input_related.add_argument('-p', action='store_true', help='enable processing of external DTDs and [p]arameter entities') 72input_related.add_argument('-x', action='store_true', help='enable processing of e[x]ternal entities') 73input_related.add_argument('-e', action='store', metavar='ENCODING', help='override any in-document [e]ncoding declaration') 74input_related.add_argument('-w', action='store_true', help='enable support for [W]indows code pages') 75input_related.add_argument('-r', action='store_true', help='disable memory-mapping and use [r]ead calls instead') 76input_related.add_argument('-g', metavar='BYTES', help='buffer size to request per call pair to XML_[G]etBuffer and read (default: 8 KiB)') 77input_related.add_argument('-k', action='store_true', help='when processing multiple files, [k]eep processing after first file with error') 78 79output_related = parser.add_argument_group('output control arguments') 80output_related.add_argument('-d', action='store', metavar='DIRECTORY', help='output [d]estination directory') 81output_mode = output_related.add_mutually_exclusive_group() 82output_mode.add_argument('-c', action='store_true', help='write a [c]opy of input XML, not canonical XML') 83output_mode.add_argument('-m', action='store_true', help='write [m]eta XML, not canonical XML') 84output_mode.add_argument('-t', action='store_true', help='write no XML output for [t]iming of plain parsing') 85output_related.add_argument('-N', action='store_true', help='enable adding doctype and [n]otation declarations') 86 87billion_laughs = parser.add_argument_group('amplification attack protection (e.g. billion laughs)', 88 description='NOTE: ' 89 'If you ever need to increase these values ' 90 'for non-attack payload, please file a bug report.') 91billion_laughs.add_argument('-a', metavar='FACTOR', 92 help='set maximum tolerated [a]mplification factor (default: 100.0)') 93billion_laughs.add_argument('-b', metavar='BYTES', help='set number of output [b]ytes needed to activate (default: 8 MiB/64 MiB)') 94 95reparse_deferral = parser.add_argument_group('reparse deferral') 96reparse_deferral.add_argument('-q', action='store_true', 97 help='disable reparse deferral, and allow [q]uadratic parse runtime with large tokens') 98 99parser.add_argument('files', metavar='FILE', nargs='*', help='file to process (default: STDIN)') 100 101info = parser.add_argument_group('info arguments') 102info = info.add_mutually_exclusive_group() 103info.add_argument('-h', '--help', action='store_true', help='show this [h]elp message and exit') 104info.add_argument('-v', '--version', action='store_true', help='show program\'s [v]ersion number and exit') 105 106 107if __name__ == '__main__': 108 parser.print_help() 109