| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 1 | #!/usr/bin/env python |
| 2 | # |
| 3 | # Copyright (C) 2012 The Android Open Source Project |
| 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 | """ |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 17 | Usage: generate-notice-files --text-output [plain text output file] \ |
| 18 | --html-output [html output file] \ |
| 19 | --xml-output [xml output file] \ |
| 20 | -t [file title] -s [directory of notices] |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 21 | |
| 22 | Generate the Android notice files, including both text and html files. |
| 23 | |
| 24 | -h to display this usage message and exit. |
| 25 | """ |
| 26 | from collections import defaultdict |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 27 | import argparse |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 28 | import hashlib |
| 29 | import itertools |
| 30 | import os |
| 31 | import os.path |
| 32 | import re |
| 33 | import sys |
| 34 | |
| 35 | MD5_BLOCKSIZE = 1024 * 1024 |
| 36 | HTML_ESCAPE_TABLE = { |
| 37 | "&": "&", |
| 38 | '"': """, |
| 39 | "'": "'", |
| 40 | ">": ">", |
| 41 | "<": "<", |
| 42 | } |
| 43 | |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 44 | def hexify(s): |
| 45 | return ("%02x"*len(s)) % tuple(map(ord, s)) |
| 46 | |
| 47 | def md5sum(filename): |
| 48 | """Calculate an MD5 of the file given by FILENAME, |
| 49 | and return hex digest as a string. |
| 50 | Output should be compatible with md5sum command""" |
| 51 | |
| 52 | f = open(filename, "rb") |
| 53 | sum = hashlib.md5() |
| 54 | while 1: |
| 55 | block = f.read(MD5_BLOCKSIZE) |
| 56 | if not block: |
| 57 | break |
| 58 | sum.update(block) |
| 59 | f.close() |
| 60 | return hexify(sum.digest()) |
| 61 | |
| 62 | |
| 63 | def html_escape(text): |
| 64 | """Produce entities within text.""" |
| 65 | return "".join(HTML_ESCAPE_TABLE.get(c,c) for c in text) |
| 66 | |
| 67 | HTML_OUTPUT_CSS=""" |
| 68 | <style type="text/css"> |
| 69 | body { padding: 0; font-family: sans-serif; } |
| 70 | .same-license { background-color: #eeeeee; border-top: 20px solid white; padding: 10px; } |
| 71 | .label { font-weight: bold; } |
| 72 | .file-list { margin-left: 1em; color: blue; } |
| 73 | </style> |
| 74 | """ |
| 75 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 76 | def combine_notice_files_html(file_hash, input_dirs, output_filename): |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 77 | """Combine notice files in FILE_HASH and output a HTML version to OUTPUT_FILENAME.""" |
| 78 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 79 | SRC_DIR_STRIP_RE = re.compile("(?:" + "|".join(input_dirs) + ")(/.*).txt") |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 80 | |
| 81 | # Set up a filename to row id table (anchors inside tables don't work in |
| 82 | # most browsers, but href's to table row ids do) |
| 83 | id_table = {} |
| 84 | id_count = 0 |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 85 | for value in file_hash: |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 86 | for filename in value: |
| 87 | id_table[filename] = id_count |
| 88 | id_count += 1 |
| 89 | |
| 90 | # Open the output file, and output the header pieces |
| 91 | output_file = open(output_filename, "wb") |
| 92 | |
| 93 | print >> output_file, "<html><head>" |
| 94 | print >> output_file, HTML_OUTPUT_CSS |
| 95 | print >> output_file, '</head><body topmargin="0" leftmargin="0" rightmargin="0" bottommargin="0">' |
| 96 | |
| 97 | # Output our table of contents |
| 98 | print >> output_file, '<div class="toc">' |
| 99 | print >> output_file, "<ul>" |
| 100 | |
| 101 | # Flatten the list of lists into a single list of filenames |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 102 | sorted_filenames = sorted(itertools.chain.from_iterable(file_hash)) |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 103 | |
| 104 | # Print out a nice table of contents |
| 105 | for filename in sorted_filenames: |
| 106 | stripped_filename = SRC_DIR_STRIP_RE.sub(r"\1", filename) |
| 107 | print >> output_file, '<li><a href="#id%d">%s</a></li>' % (id_table.get(filename), stripped_filename) |
| 108 | |
| 109 | print >> output_file, "</ul>" |
| 110 | print >> output_file, "</div><!-- table of contents -->" |
| 111 | # Output the individual notice file lists |
| 112 | print >>output_file, '<table cellpadding="0" cellspacing="0" border="0">' |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 113 | for value in file_hash: |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 114 | print >> output_file, '<tr id="id%d"><td class="same-license">' % id_table.get(value[0]) |
| 115 | print >> output_file, '<div class="label">Notices for file(s):</div>' |
| 116 | print >> output_file, '<div class="file-list">' |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 117 | for filename in value: |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 118 | print >> output_file, "%s <br/>" % (SRC_DIR_STRIP_RE.sub(r"\1", filename)) |
| 119 | print >> output_file, "</div><!-- file-list -->" |
| 120 | print >> output_file |
| 121 | print >> output_file, '<pre class="license-text">' |
| 122 | print >> output_file, html_escape(open(value[0]).read()) |
| 123 | print >> output_file, "</pre><!-- license-text -->" |
| 124 | print >> output_file, "</td></tr><!-- same-license -->" |
| 125 | print >> output_file |
| 126 | print >> output_file |
| 127 | print >> output_file |
| 128 | |
| 129 | # Finish off the file output |
| 130 | print >> output_file, "</table>" |
| 131 | print >> output_file, "</body></html>" |
| 132 | output_file.close() |
| 133 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 134 | def combine_notice_files_text(file_hash, input_dirs, output_filename, file_title): |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 135 | """Combine notice files in FILE_HASH and output a text version to OUTPUT_FILENAME.""" |
| 136 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 137 | SRC_DIR_STRIP_RE = re.compile("(?:" + "|".join(input_dirs) + ")(/.*).txt") |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 138 | output_file = open(output_filename, "wb") |
| 139 | print >> output_file, file_title |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 140 | for value in file_hash: |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 141 | print >> output_file, "============================================================" |
| 142 | print >> output_file, "Notices for file(s):" |
| Dan Willemsen | 8ae4984 | 2015-11-10 12:37:23 -0800 | [diff] [blame] | 143 | for filename in value: |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 144 | print >> output_file, SRC_DIR_STRIP_RE.sub(r"\1", filename) |
| 145 | print >> output_file, "------------------------------------------------------------" |
| 146 | print >> output_file, open(value[0]).read() |
| 147 | output_file.close() |
| 148 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 149 | def combine_notice_files_xml(files_with_same_hash, input_dirs, output_filename): |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 150 | """Combine notice files in FILE_HASH and output a XML version to OUTPUT_FILENAME.""" |
| 151 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 152 | SRC_DIR_STRIP_RE = re.compile("(?:" + "|".join(input_dirs) + ")(/.*).txt") |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 153 | |
| 154 | # Set up a filename to row id table (anchors inside tables don't work in |
| 155 | # most browsers, but href's to table row ids do) |
| 156 | id_table = {} |
| 157 | for file_key in files_with_same_hash.keys(): |
| 158 | for filename in files_with_same_hash[file_key]: |
| 159 | id_table[filename] = file_key |
| 160 | |
| 161 | # Open the output file, and output the header pieces |
| 162 | output_file = open(output_filename, "wb") |
| 163 | |
| 164 | print >> output_file, '<?xml version="1.0" encoding="utf-8"?>' |
| 165 | print >> output_file, "<licenses>" |
| 166 | |
| 167 | # Flatten the list of lists into a single list of filenames |
| 168 | sorted_filenames = sorted(id_table.keys()) |
| 169 | |
| 170 | # Print out a nice table of contents |
| 171 | for filename in sorted_filenames: |
| 172 | stripped_filename = SRC_DIR_STRIP_RE.sub(r"\1", filename) |
| 173 | print >> output_file, '<file-name contentId="%s">%s</file-name>' % (id_table.get(filename), stripped_filename) |
| 174 | |
| 175 | print >> output_file |
| 176 | print >> output_file |
| 177 | |
| 178 | processed_file_keys = [] |
| 179 | # Output the individual notice file lists |
| 180 | for filename in sorted_filenames: |
| 181 | file_key = id_table.get(filename) |
| 182 | if file_key in processed_file_keys: |
| 183 | continue |
| 184 | processed_file_keys.append(file_key) |
| 185 | |
| 186 | print >> output_file, '<file-content contentId="%s"><![CDATA[%s]]></file-content>' % (file_key, html_escape(open(filename).read())) |
| 187 | print >> output_file |
| 188 | |
| 189 | # Finish off the file output |
| 190 | print >> output_file, "</licenses>" |
| 191 | output_file.close() |
| 192 | |
| 193 | def get_args(): |
| 194 | parser = argparse.ArgumentParser() |
| 195 | parser.add_argument( |
| 196 | '--text-output', required=True, |
| 197 | help='The text output file path.') |
| 198 | parser.add_argument( |
| 199 | '--html-output', |
| 200 | help='The html output file path.') |
| 201 | parser.add_argument( |
| 202 | '--xml-output', |
| 203 | help='The xml output file path.') |
| 204 | parser.add_argument( |
| 205 | '-t', '--title', required=True, |
| 206 | help='The file title.') |
| 207 | parser.add_argument( |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 208 | '-s', '--source-dir', required=True, action='append', |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 209 | help='The directory containing notices.') |
| 210 | parser.add_argument( |
| 211 | '-i', '--included-subdirs', action='append', |
| 212 | help='The sub directories which should be included.') |
| 213 | parser.add_argument( |
| 214 | '-e', '--excluded-subdirs', action='append', |
| 215 | help='The sub directories which should be excluded.') |
| 216 | return parser.parse_args() |
| 217 | |
| 218 | def main(argv): |
| 219 | args = get_args() |
| 220 | |
| 221 | txt_output_file = args.text_output |
| 222 | html_output_file = args.html_output |
| 223 | xml_output_file = args.xml_output |
| 224 | file_title = args.title |
| 225 | included_subdirs = [] |
| 226 | excluded_subdirs = [] |
| 227 | if args.included_subdirs is not None: |
| 228 | included_subdirs = args.included_subdirs |
| 229 | if args.excluded_subdirs is not None: |
| 230 | excluded_subdirs = args.excluded_subdirs |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 231 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 232 | input_dirs = [os.path.normpath(source_dir) for source_dir in args.source_dir] |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 233 | # Find all the notice files and md5 them |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 234 | for input_dir in input_dirs: |
| 235 | files_with_same_hash = defaultdict(list) |
| 236 | for root, dir, files in os.walk(input_dir): |
| 237 | for file in files: |
| 238 | matched = True |
| 239 | if len(included_subdirs) > 0: |
| 240 | matched = False |
| 241 | for subdir in included_subdirs: |
| 242 | if (root == (input_dir + '/' + subdir) or |
| 243 | root.startswith(input_dir + '/' + subdir + '/')): |
| 244 | matched = True |
| 245 | break |
| 246 | elif len(excluded_subdirs) > 0: |
| 247 | for subdir in excluded_subdirs: |
| 248 | if (root == (input_dir + '/' + subdir) or |
| 249 | root.startswith(input_dir + '/' + subdir + '/')): |
| 250 | matched = False |
| 251 | break |
| 252 | if matched and file.endswith(".txt"): |
| 253 | filename = os.path.join(root, file) |
| 254 | file_md5sum = md5sum(filename) |
| 255 | files_with_same_hash[file_md5sum].append(filename) |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 256 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 257 | filesets = [sorted(files_with_same_hash[md5]) for md5 in sorted(files_with_same_hash.keys())] |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 258 | |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 259 | combine_notice_files_text(filesets, input_dirs, txt_output_file, file_title) |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 260 | |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 261 | if html_output_file is not None: |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 262 | combine_notice_files_html(filesets, input_dirs, html_output_file) |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 263 | |
| 264 | if xml_output_file is not None: |
| Bob Badour | 5e9e1fb | 2020-07-17 20:47:42 -0700 | [diff] [blame] | 265 | combine_notice_files_xml(files_with_same_hash, input_dirs, xml_output_file) |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 266 | |
| Daniel Berlin | f5a97d7 | 2012-03-29 10:33:19 -0400 | [diff] [blame] | 267 | if __name__ == "__main__": |
| Jaekyun Seok | 3b7560b | 2017-04-19 15:26:47 +0900 | [diff] [blame] | 268 | main(sys.argv) |