generate-notice-files.py revision f5a97d7fbbda5ec8ad4ea73a8035d7fa88bbe1da 
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"""
17Usage: generate-notice-files [plain text output file] [html output file] [file title] [directory of notices]
18
19Generate the Android notice files, including both text and html files.
20
21-h to display this usage message and exit.
22"""
23from collections import defaultdict
24import getopt
25import hashlib
26import itertools
27import os
28import os.path
29import re
30import sys
31
32MD5_BLOCKSIZE = 1024 * 1024
33HTML_ESCAPE_TABLE = {
34    "&": "&",
35    '"': """,
36    "'": "'",
37    ">": ">",
38    "<": "&lt;",
39    }
40
41try:
42  opts, args = getopt.getopt(sys.argv[1:], "h")
43except getopt.GetoptError, err:
44    print str(err)
45    print __doc__
46    sys.exit(2)
47
48for o, a in opts:
49  if o == "-h":
50    print __doc__
51    sys.exit(2)
52  else:
53    print >> sys.stderr, "unhandled option %s" % (o,)
54
55if len(args) != 4:
56    print """need exactly four arguments, the two output files, the file title
57             and the directory containing notices, not %d""" % (len(args),)
58    print __doc__
59    sys.exit(1)
60
61def hexify(s):
62    return ("%02x"*len(s)) % tuple(map(ord, s))
63
64def md5sum(filename):
65    """Calculate an MD5 of the file given by FILENAME,
66    and return hex digest as a string.
67    Output should be compatible with md5sum command"""
68
69    f = open(filename, "rb")
70    sum = hashlib.md5()
71    while 1:
72        block = f.read(MD5_BLOCKSIZE)
73        if not block:
74            break
75        sum.update(block)
76    f.close()
77    return hexify(sum.digest())
78
79
80def html_escape(text):
81    """Produce entities within text."""
82    return "".join(HTML_ESCAPE_TABLE.get(c,c) for c in text)
83
84HTML_OUTPUT_CSS="""
85<style type="text/css">
86body { padding: 0; font-family: sans-serif; }
87.same-license { background-color: #eeeeee; border-top: 20px solid white; padding: 10px; }
88.label { font-weight: bold; }
89.file-list { margin-left: 1em; color: blue; }
90</style>
91"""
92
93def combine_notice_files_html(file_hash, input_dir, output_filename):
94    """Combine notice files in FILE_HASH and output a HTML version to OUTPUT_FILENAME."""
95
96    SRC_DIR_STRIP_RE = re.compile(input_dir + "(/.*).txt")
97
98    # Set up a filename to row id table (anchors inside tables don't work in
99    # most browsers, but href's to table row ids do)
100    id_table = {}
101    id_count = 0
102    for value in file_hash.values():
103        for filename in value:
104             id_table[filename] = id_count
105        id_count += 1
106
107    # Open the output file, and output the header pieces
108    output_file = open(output_filename, "wb")
109
110    print >> output_file, "<html><head>"
111    print >> output_file, HTML_OUTPUT_CSS
112    print >> output_file, '</head><body topmargin="0" leftmargin="0" rightmargin="0" bottommargin="0">'
113
114    # Output our table of contents
115    print >> output_file, '<div class="toc">'
116    print >> output_file, "<ul>"
117
118    # Flatten the list of lists into a single list of filenames
119    sorted_filenames = sorted(itertools.chain.from_iterable(file_hash.values()))
120
121    # Print out a nice table of contents
122    for filename in sorted_filenames:
123        stripped_filename = SRC_DIR_STRIP_RE.sub(r"\1", filename)
124        print >> output_file, '<li><a href="#id%d">%s</a></li>' % (id_table.get(filename), stripped_filename)
125
126    print >> output_file, "</ul>"
127    print >> output_file, "</div><!-- table of contents -->"
128    # Output the individual notice file lists
129    print >>output_file, '<table cellpadding="0" cellspacing="0" border="0">'
130    for value in file_hash.values():
131        print >> output_file, '<tr id="id%d"><td class="same-license">' % id_table.get(value[0])
132        print >> output_file, '<div class="label">Notices for file(s):</div>'
133        print >> output_file, '<div class="file-list">'
134        for filename in sorted(value):
135            print >> output_file, "%s <br/>" % (SRC_DIR_STRIP_RE.sub(r"\1", filename))
136        print >> output_file, "</div><!-- file-list -->"
137        print >> output_file
138        print >> output_file, '<pre class="license-text">'
139        print >> output_file, html_escape(open(value[0]).read())
140        print >> output_file, "</pre><!-- license-text -->"
141        print >> output_file, "</td></tr><!-- same-license -->"
142        print >> output_file
143        print >> output_file
144        print >> output_file
145
146    # Finish off the file output
147    print >> output_file, "</table>"
148    print >> output_file, "</body></html>"
149    output_file.close()
150
151def combine_notice_files_text(file_hash, input_dir, output_filename, file_title):
152    """Combine notice files in FILE_HASH and output a text version to OUTPUT_FILENAME."""
153
154    SRC_DIR_STRIP_RE = re.compile(input_dir + "(/.*).txt")
155    output_file = open(output_filename, "wb")
156    print >> output_file, file_title
157    for value in file_hash.values():
158      print >> output_file, "============================================================"
159      print >> output_file, "Notices for file(s):"
160      for filename in sorted(value):
161        print >> output_file, SRC_DIR_STRIP_RE.sub(r"\1", filename)
162      print >> output_file, "------------------------------------------------------------"
163      print >> output_file, open(value[0]).read()
164    output_file.close()
165
166def main(args):
167    txt_output_file = args[0]
168    html_output_file = args[1]
169    file_title = args[2]
170
171    # Find all the notice files and md5 them
172    input_dir = os.path.normpath(args[3])
173    files_with_same_hash = defaultdict(list)
174    for root, dir, files in os.walk(input_dir):
175        for file in files:
176            if file.endswith(".txt"):
177                filename = os.path.join(root, file)
178                file_md5sum = md5sum(filename)
179                files_with_same_hash[file_md5sum].append(filename)
180
181
182    print "Combining NOTICE files into HTML"
183    combine_notice_files_html(files_with_same_hash, input_dir, html_output_file)
184    print "Combining NOTICE files into text"
185    combine_notice_files_text(files_with_same_hash, input_dir, txt_output_file, file_title)
186
187if __name__ == "__main__":
188    main(args)
189