1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
#!/usr/bin/env python3
#
# make-usb - Creates a file containing vendor and product ids.
# It use the databases from
# - The USB ID Repository: https://usb-ids.gowdy.us (http://www.linux-usb.org), mirrored at Sourceforge
# - libgphoto2 from gPhoto: https://github.com/gphoto/libgphoto2 (http://gphoto.org), available at GitHub
# to create our file epan/dissectors/usb.c
import re
import sys
import urllib.request, urllib.error, urllib.parse
MODE_IDLE = 0
MODE_VENDOR_PRODUCT = 1
MIN_VENDORS = 3400 # 3409 as of 2020-11-15
MIN_PRODUCTS = 20000 # 20361 as of 2020-11-15
mode = MODE_IDLE
req_headers = { 'User-Agent': 'Wireshark make-usb' }
req = urllib.request.Request('https://sourceforge.net/p/linux-usb/repo/HEAD/tree/trunk/htdocs/usb.ids?format=raw', headers=req_headers)
response = urllib.request.urlopen(req)
lines = response.read().decode('UTF-8', 'replace').splitlines()
vendors = dict()
products = dict()
vendors_str="static const value_string usb_vendors_vals[] = {\n"
products_str="static const value_string usb_products_vals[] = {\n"
# Escape backslashes, quotes, control characters and non-ASCII characters.
escapes = {}
for i in range(256):
if i in b'\\"':
escapes[i] = '\\%c' % i
elif i in range(0x20, 0x80) or i in b'\t':
escapes[i] = chr(i)
else:
escapes[i] = '\\%03o' % i
for utf8line in lines:
# Convert single backslashes to double (escaped) backslashes, escape quotes, etc.
utf8line = utf8line.rstrip()
utf8line = re.sub(r"\?+", "?", utf8line)
line = ''.join(escapes[byte] for byte in utf8line.encode('utf8'))
if line == "# Vendors, devices and interfaces. Please keep sorted.":
mode = MODE_VENDOR_PRODUCT
continue
elif line == "# List of known device classes, subclasses and protocols":
mode = MODE_IDLE
continue
if mode == MODE_VENDOR_PRODUCT:
if re.match("^[0-9a-f]{4}", line):
last_vendor=line[:4]
vendors[last_vendor] = line[4:].strip()
elif re.match("^\t[0-9a-f]{4}", line):
line = line.strip()
product = "%s%s"%(last_vendor, line[:4])
products[product] = line[4:].strip()
req = urllib.request.Request('https://raw.githubusercontent.com/gphoto/libgphoto2/master/camlibs/ptp2/library.c', headers=req_headers)
response = urllib.request.urlopen(req)
lines = response.read().decode('UTF-8', 'replace').splitlines()
mode = MODE_IDLE
for line in lines:
if mode == MODE_IDLE and re.match(r".*\bmodels\[\]", line):
mode = MODE_VENDOR_PRODUCT
continue
if mode == MODE_VENDOR_PRODUCT and re.match(r"};", line):
mode = MODE_IDLE
if mode == MODE_IDLE:
continue
m = re.match(r"\s*{\"(.*):(.*)\",\s*0x([0-9a-fA-F]{4}),\s*0x([0-9a-fA-F]{4}),.*},", line)
if m is not None:
manuf = m.group(1).strip()
model = re.sub(r"\(.*\)", "", m.group(2)).strip()
product = m.group(3) + m.group(4)
products[product] = ' '.join((manuf, model))
req = urllib.request.Request('https://raw.githubusercontent.com/gphoto/libgphoto2/master/camlibs/ptp2/music-players.h', headers=req_headers)
response = urllib.request.urlopen(req)
lines = response.read().decode('UTF-8', 'replace').splitlines()
for line in lines:
m = re.match(r"\s*{\s*\"(.*)\",\s*0x([0-9a-fA-F]{4}),\s*\"(.*)\",\s*0x([0-9a-fA-F]{4}),", line)
if m is not None:
manuf = m.group(1).strip()
model = m.group(3).strip()
product = m.group(2) + m.group(4)
products[product] = ' '.join((manuf, model))
if (len(vendors) < MIN_VENDORS):
sys.stderr.write("Not enough vendors: %d\n" % len(vendors))
sys.exit(1)
if (len(products) < MIN_PRODUCTS):
sys.stderr.write("Not enough products: %d\n" % len(products))
sys.exit(1)
vendors = {k.lower(): v for k, v in vendors.items()}
for v in sorted(vendors):
vendors_str += " { 0x%s, \"%s\" },\n"%(v,vendors[v])
vendors_str += """ { 0, NULL }\n};
value_string_ext ext_usb_vendors_vals = VALUE_STRING_EXT_INIT(usb_vendors_vals);
"""
products = {k.lower(): v for k, v in products.items()}
for p in sorted(products):
products_str += " { 0x%s, \"%s\" },\n"%(p,products[p])
products_str += """ { 0, NULL }\n};
value_string_ext ext_usb_products_vals = VALUE_STRING_EXT_INIT(usb_products_vals);
"""
header="""/* usb.c
* USB vendor id and product ids
* This file was generated by running python ./tools/make-usb.py
* Don't change it directly.
*
* Copyright 2012, Michal Labedzki for Tieto Corporation
*
* Other values imported from libghoto2/camlibs/ptp2/library.c, music-players.h
*
* Copyright (C) 2001-2005 Mariusz Woloszyn <emsi@ipartners.pl>
* Copyright (C) 2003-2013 Marcus Meissner <marcus@jet.franken.de>
* Copyright (C) 2005 Hubert Figuiere <hfiguiere@teaser.fr>
* Copyright (C) 2009 Axel Waggershauser <awagger@web.de>
* Copyright (C) 2005-2007 Richard A. Low <richard@wentnet.com>
* Copyright (C) 2005-2012 Linus Walleij <triad@df.lth.se>
* Copyright (C) 2007 Ted Bullock
* Copyright (C) 2012 Sony Mobile Communications AB
*
* Wireshark - Network traffic analyzer
* By Gerald Combs <gerald@wireshark.org>
* Copyright 1998 Gerald Combs
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
/*
* XXX We should probably parse a USB ID file at program start instead
* of generating this file.
*/
#include "config.h"
#include <epan/packet.h>
"""
f = open('epan/dissectors/usb.c', 'w')
f.write(header)
f.write("\n")
f.write(vendors_str)
f.write("\n\n")
f.write(products_str)
f.write("\n")
f.close()
print("Success!")
|
