#!/usr/bin/env python # # Copyright 2007 Neal Norwitz # Portions Copyright 2007 Google Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """Tokenize C++ source code.""" __author__ = 'nnorwitz@google.com (Neal Norwitz)' try: # Python 3.x import builtins except ImportError: # Python 2.x import __builtin__ as builtins import sys from cpp import utils if not hasattr(builtins, 'set'): # Nominal support for Python 2.3. from sets import Set as set # Add $ as a valid identifier char since so much code uses it. _letters = 'abcdefghijklmnopqrstuvwxyz' VALID_IDENTIFIER_CHARS = set(_letters + _letters.upper() + '_0123456789$') HEX_DIGITS = set('0123456789abcdefABCDEF') INT_OR_FLOAT_DIGITS = set('01234567890eE-+') # C++0x string preffixes. _STR_PREFIXES = set(('R', 'u8', 'u8R', 'u', 'uR', 'U', 'UR', 'L', 'LR')) # Token types. UNKNOWN = 'UNKNOWN' SYNTAX = 'SYNTAX' CONSTANT = 'CONSTANT' NAME = 'NAME' PREPROCESSOR = 'PREPROCESSOR' # Where the token originated from. This can be used for backtracking. # It is always set to WHENCE_STREAM in this code. WHENCE_STREAM, WHENCE_QUEUE = range(2) class Token(object): """Data container to represent a C++ token. Tokens can be identifiers, syntax char(s), constants, or pre-processor directives. start contains the index of the first char of the token in the source end contains the index of the last char of the token in the source """ def __init__(self, token_type, name, start, end): self.token_type = token_type self.name = name self.start = start self.end = end self.whence = WHENCE_STREAM def __str__(self): if not utils.DEBUG: return 'Token(%r)' % self.name return 'Token(%r, %s, %s)' % (self.name, self.start, self.end) __repr__ = __str__ def _GetString(source, start, i): i = source.find('"', i+1) while source[i-1] == '\\': # Count the trailing backslashes. backslash_count = 1 j = i - 2 while source[j] == '\\': backslash_count += 1 j -= 1 # When trailing backslashes are even, they escape each other. if (backslash_count % 2) == 0: break i = source.find('"', i+1) return i + 1 def _GetChar(source, start, i): # NOTE(nnorwitz): may not be quite correct, should be good enough. i = source.find("'", i+1) while source[i-1] == '\\': # Need to special case '\\'. if (i - 2) > start and source[i-2] == '\\': break i = source.find("'", i+1) # Try to handle unterminated single quotes (in a #if 0 block). if i < 0: i = start return i + 1 def GetTokens(source): """Returns a sequence of Tokens. Args: source: string of C++ source code. Yields: Token that represents the next token in the source. """ # Cache various valid character sets for speed. valid_identifier_chars = VALID_IDENTIFIER_CHARS hex_digits = HEX_DIGITS int_or_float_digits = INT_OR_FLOAT_DIGITS int_or_float_digits2 = int_or_float_digits | set('.') # Only ignore errors while in a #if 0 block. ignore_errors = False count_ifs = 0 i = 0 end = len(source) while i < end: # Skip whitespace. while i < end and source[i].isspace(): i += 1 if i >= end: return token_type = UNKNOWN start = i c = source[i] if c.isalpha() or c == '_': # Find a string token. token_type = NAME while source[i] in valid_identifier_chars: i += 1 # String and character constants can look like a name if # they are something like L"". if (source[i] == "'" and (i - start) == 1 and source[start:i] in 'uUL'): # u, U, and L are valid C++0x character preffixes. token_type = CONSTANT i = _GetChar(source, start, i) elif source[i] == "'" and source[start:i] in _STR_PREFIXES: token_type = CONSTANT i = _GetString(source, start, i) elif c == '/' and source[i+1] == '/': # Find // comments. i = source.find('\n', i) if i == -1: # Handle EOF. i = end continue elif c == '/' and source[i+1] == '*': # Find /* comments. */ i = source.find('*/', i) + 2 continue elif c in ':+-<>&|*=': # : or :: (plus other chars). token_type = SYNTAX i += 1 new_ch = source[i] if new_ch == c and c != '>': # Treat ">>" as two tokens. i += 1 elif c == '-' and new_ch == '>': i += 1 elif new_ch == '=': i += 1 elif c in '()[]{}~!?^%;/.,': # Handle single char tokens. token_type = SYNTAX i += 1 if c == '.' and source[i].isdigit(): token_type = CONSTANT i += 1 while source[i] in int_or_float_digits: i += 1 # Handle float suffixes. for suffix in ('l', 'f'): if suffix == source[i:i+1].lower(): i += 1 break elif c.isdigit(): # Find integer. token_type = CONSTANT if c == '0' and source[i+1] in 'xX': # Handle hex digits. i += 2 while source[i] in hex_digits: i += 1 else: while source[i] in int_or_float_digits2: i += 1 # Handle integer (and float) suffixes. for suffix in ('ull', 'll', 'ul', 'l', 'f', 'u'): size = len(suffix) if suffix == source[i:i+size].lower(): i += size break elif c == '"': # Find string. token_type = CONSTANT i = _GetString(source, start, i) elif c == "'": # Find char. token_type = CONSTANT i = _GetChar(source, start, i) elif c == '#': # Find pre-processor command. token_type = PREPROCESSOR got_if = source[i:i+3] == '#if' and source[i+3:i+4].isspace() if got_if: count_ifs += 1 elif source[i:i+6] == '#endif': count_ifs -= 1 if count_ifs == 0: ignore_errors = False # TODO(nnorwitz): handle preprocessor statements (\ continuations). while 1: i1 = source.find('\n', i) i2 = source.find('//', i) i3 = source.find('/*', i) i4 = source.find('"', i) # NOTE(nnorwitz): doesn't handle comments in #define macros. # Get the first important symbol (newline, comment, EOF/end). i = min([x for x in (i1, i2, i3, i4, end) if x != -1]) # Handle #include "dir//foo.h" properly. if source[i] == '"': i = source.find('"', i+1) + 1 assert i > 0 continue # Keep going if end of the line and the line ends with \. if not (i == i1 and source[i-1] == '\\'): if got_if: condition = source[start+4:i].lstrip() if (condition.startswith('0') or condition.startswith('(0)')): ignore_errors = True break i += 1 elif c == '\\': # Handle \ in code. # This is different from the pre-processor \ handling. i += 1 continue elif ignore_errors: # The tokenizer seems to be in pretty good shape. This # raise is conditionally disabled so that bogus code # in an #if 0 block can be handled. Since we will ignore # it anyways, this is probably fine. So disable the # exception and return the bogus char. i += 1 else: sys.stderr.write('Got invalid token in %s @ %d token:%s: %r\n' % ('?', i, c, source[i-10:i+10])) raise RuntimeError('unexpected token') if i <= 0: print('Invalid index, exiting now.') return yield Token(token_type, source[start:i], start, i) if __name__ == '__main__': def main(argv): """Driver mostly for testing purposes.""" for filename in argv[1:]: source = utils.ReadFile(filename) if source is None: continue for token in GetTokens(source): print('%-12s: %s' % (token.token_type, token.name)) # print('\r%6.2f%%' % (100.0 * index / token.end),) sys.stdout.write('\n') main(sys.argv) 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
#!/usr/bin/env python
#
# Copyright 2007 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tool for uploading diffs from a version control system to the codereview app.
Usage summary: upload.py [options] [-- diff_options]
Diff options are passed to the diff command of the underlying system.
Supported version control systems:
Git
Mercurial
Subversion
It is important for Git/Mercurial users to specify a tree/node/branch to diff
against by using the '--rev' option.
"""
# This code is derived from appcfg.py in the App Engine SDK (open source),
# and from ASPN recipe #146306.
import cookielib
import getpass
import logging
import md5
import mimetypes
import optparse
import os
import re
import socket
import subprocess
import sys
import urllib
import urllib2
import urlparse
try:
import readline
except ImportError:
pass
# The logging verbosity:
# 0: Errors only.
# 1: Status messages.
# 2: Info logs.
# 3: Debug logs.
verbosity = 1
# Max size of patch or base file.
MAX_UPLOAD_SIZE = 900 * 1024
def GetEmail(prompt):
"""Prompts the user for their email address and returns it.
The last used email address is saved to a file and offered up as a suggestion
to the user. If the user presses enter without typing in anything the last
used email address is used. If the user enters a new address, it is saved
for next time we prompt.
"""
last_email_file_name = os.path.expanduser("~/.last_codereview_email_address")
last_email = ""
if os.path.exists(last_email_file_name):
try:
last_email_file = open(last_email_file_name, "r")
last_email = last_email_file.readline().strip("\n")
last_email_file.close()
prompt += " [%s]" % last_email
except IOError, e:
pass
email = raw_input(prompt + ": ").strip()
if email:
try:
last_email_file = open(last_email_file_name, "w")
last_email_file.write(email)
last_email_file.close()
except IOError, e:
pass
else:
email = last_email
return email
def StatusUpdate(msg):
"""Print a status message to stdout.
If 'verbosity' is greater than 0, print the message.
Args:
msg: The string to print.
"""
if verbosity > 0:
print msg
def ErrorExit(msg):
"""Print an error message to stderr and exit."""
print >>sys.stderr, msg
sys.exit(1)
class ClientLoginError(urllib2.HTTPError):
"""Raised to indicate there was an error authenticating with ClientLogin."""
def __init__(self, url, code, msg, headers, args):
urllib2.HTTPError.__init__(self, url, code, msg, headers, None)
self.args = args
self.reason = args["Error"]
class AbstractRpcServer(object):
"""Provides a common interface for a simple RPC server."""
def __init__(self, host, auth_function, host_override=None, extra_headers={},
save_cookies=False):
"""Creates a new HttpRpcServer.
Args:
host: The host to send requests to.
auth_function: A function that takes no arguments and returns an
(email, password) tuple when called. Will be called if authentication
is required.
host_override: The host header to send to the server (defaults to host).
extra_headers: A dict of extra headers to append to every request.
save_cookies: If True, save the authentication cookies to local disk.
If False, use an in-memory cookiejar instead. Subclasses must
implement this functionality. Defaults to False.
"""
self.host = host
self.host_override = host_override
self.auth_function = auth_function
self.authenticated = False
self.extra_headers = extra_headers
self.save_cookies = save_cookies
self.opener = self._GetOpener()
if self.host_override:
logging.info("Server: %s; Host: %s", self.host, self.host_override)
else:
logging.info("Server: %s", self.host)
def _GetOpener(self):
"""Returns an OpenerDirector for making HTTP requests.
Returns:
A urllib2.OpenerDirector object.
"""
raise NotImplementedError()
def _CreateRequest(self, url, data=None):
"""Creates a new urllib request."""
logging.debug("Creating request for: '%s' with payload:\n%s", url, data)
req = urllib2.Request(url, data=data)
if self.host_override:
req.add_header("Host", self.host_override)
for key, value in self.extra_headers.iteritems():
req.add_header(key, value)
return req
def _GetAuthToken(self, email, password):
"""Uses ClientLogin to authenticate the user, returning an auth token.
Args:
email: The user's email address
password: The user's password
Raises:
ClientLoginError: If there was an error authenticating with ClientLogin.
HTTPError: If there was some other form of HTTP error.
Returns:
The authentication token returned by ClientLogin.
"""
account_type = "GOOGLE"
if self.host.endswith(".google.com"):
# Needed for use inside Google.
account_type = "HOSTED"
req = self._CreateRequest(
url="https://www.google.com/accounts/ClientLogin",
data=urllib.urlencode({
"Email": email,
"Passwd": password,
"service": "ah",
"source": "rietveld-codereview-upload",
"accountType": account_type,
}),
)
try:
response = self.opener.open(req)
response_body = response.read()
response_dict = dict(x.split("=")
for x in response_body.split("\n") if x)
return response_dict["Auth"]
except urllib2.HTTPError, e:
if e.code == 403:
body = e.read()
response_dict = dict(x.split("=", 1) for x in body.split("\n") if x)
raise ClientLoginError(req.get_full_url(), e.code, e.msg,
e.headers, response_dict)
else:
raise
def _GetAuthCookie(self, auth_token):
"""Fetches authentication cookies for an authentication token.
Args:
auth_token: The authentication token returned by ClientLogin.
Raises:
HTTPError: If there was an error fetching the authentication cookies.
"""
# This is a dummy value to allow us to identify when we're successful.
continue_location = "http://localhost/"
args = {"continue": continue_location, "auth": auth_token}
req = self._CreateRequest("http://%s/_ah/login?%s" %
(self.host, urllib.urlencode(args)))
try:
response = self.opener.open(req)
except urllib2.HTTPError, e:
response = e
if (response.code != 302 or
response.info()["location"] != continue_location):
raise urllib2.HTTPError(req.get_full_url(), response.code, response.msg,
response.headers, response.fp)
self.authenticated = True
def _Authenticate(self):
"""Authenticates the user.
The authentication process works as follows:
1) We get a username and password from the user
2) We use ClientLogin to obtain an AUTH token for the user
(see http://code.google.com/apis/accounts/AuthForInstalledApps.html).
3) We pass the auth token to /_ah/login on the server to obtain an
authentication cookie. If login was successful, it tries to redirect
us to the URL we provided.
If we attempt to access the upload API without first obtaining an
authentication cookie, it returns a 401 response and directs us to
authenticate ourselves with ClientLogin.
"""
for i in range(3):
credentials = self.auth_function()
try:
auth_token = self._GetAuthToken(credentials[0], credentials[1])
except ClientLoginError, e:
if e.reason == "BadAuthentication":
print >>sys.stderr, "Invalid username or password."
continue
if e.reason == "CaptchaRequired":
print >>sys.stderr, (
"Please go to\n"
"https://www.google.com/accounts/DisplayUnlockCaptcha\n"
"and verify you are a human. Then try again.")
break
if e.reason == "NotVerified":
print >>sys.stderr, "Account not verified."
break
if e.reason == "TermsNotAgreed":
print >>sys.stderr, "User has not agreed to TOS."
break
if e.reason == "AccountDeleted":
print >>sys.stderr, "The user account has been deleted."
break
if e.reason == "AccountDisabled":
print >>sys.stderr, "The user account has been disabled."
break
if e.reason == "ServiceDisabled":
print >>sys.stderr, ("The user's access to the service has been "
"disabled.")
break
if e.reason == "ServiceUnavailable":
print >>sys.stderr, "The service is not available; try again later."
break
raise
self._GetAuthCookie(auth_token)
return
def Send(self, request_path, payload=None,
content_type="application/octet-stream",
timeout=None,
**kwargs):
"""Sends an RPC and returns the response.
Args:
request_path: The path to send the request to, eg /api/appversion/create.
payload: The body of the request, or None to send an empty request.
content_type: The Content-Type header to use.
timeout: timeout in seconds; default None i.e. no timeout.
(Note: for large requests on OS X, the timeout doesn't work right.)
kwargs: Any keyword arguments are converted into query string parameters.
Returns:
The response body, as a string.
"""
# TODO: Don't require authentication. Let the server say
# whether it is necessary.
if not self.authenticated:
self._Authenticate()
old_timeout = socket.getdefaulttimeout()
socket.setdefaulttimeout(timeout)
try:
tries = 0
while True:
tries += 1
args = dict(kwargs)
url = "http://%s%s" % (self.host, request_path)
if args:
url += "?" + urllib.urlencode(args)
req = self._CreateRequest(url=url, data=payload)
req.add_header("Content-Type", content_type)
try:
f = self.opener.open(req)
response = f.read()
f.close()
return response
except urllib2.HTTPError, e:
if tries > 3:
raise
elif e.code == 401:
self._Authenticate()
## elif e.code >= 500 and e.code < 600:
## # Server Error - try again.
## continue
else:
raise
finally:
socket.setdefaulttimeout(old_timeout)
class HttpRpcServer(AbstractRpcServer):
"""Provides a simplified RPC-style interface for HTTP requests."""
def _Authenticate(self):
"""Save the cookie jar after authentication."""
super(HttpRpcServer, self)._Authenticate()
if self.save_cookies:
StatusUpdate("Saving authentication cookies to %s" % self.cookie_file)
self.cookie_jar.save()
def _GetOpener(self):
"""Returns an OpenerDirector that supports cookies and ignores redirects.
Returns:
A urllib2.OpenerDirector object.
"""
opener = urllib2.OpenerDirector()
opener.add_handler(urllib2.ProxyHandler())
opener.add_handler(urllib2.UnknownHandler())
opener.add_handler(urllib2.HTTPHandler())
opener.add_handler(urllib2.HTTPDefaultErrorHandler())
opener.add_handler(urllib2.HTTPSHandler())
opener.add_handler(urllib2.HTTPErrorProcessor())
if self.save_cookies:
self.cookie_file = os.path.expanduser("~/.codereview_upload_cookies")
self.cookie_jar = cookielib.MozillaCookieJar(self.cookie_file)
if os.path.exists(self.cookie_file):
try:
self.cookie_jar.load()
self.authenticated = True
StatusUpdate("Loaded authentication cookies from %s" %
self.cookie_file)
except (cookielib.LoadError, IOError):
# Failed to load cookies - just ignore them.
pass
else:
# Create an empty cookie file with mode 600
fd = os.open(self.cookie_file, os.O_CREAT, 0600)
os.close(fd)
# Always chmod the cookie file
os.chmod(self.cookie_file, 0600)
else:
# Don't save cookies across runs of update.py.
self.cookie_jar = cookielib.CookieJar()
opener.add_handler(urllib2.HTTPCookieProcessor(self.cookie_jar))
return opener
parser = optparse.OptionParser(usage="%prog [options] [-- diff_options]")
parser.add_option("-y", "--assume_yes", action="store_true",
dest="assume_yes", default=False,
help="Assume that the answer to yes/no questions is 'yes'.")
# Logging
group = parser.add_option_group("Logging options")
group.add_option("-q", "--quiet", action="store_const", const=0,
dest="verbose", help="Print errors only.")
group.add_option("-v", "--verbose", action="store_const", const=2,
dest="verbose", default=1,
help="Print info level logs (default).")
group.add_option("--noisy", action="store_const", const=3,
dest="verbose", help="Print all logs.")
# Review server
group = parser.add_option_group("Review server options")
group.add_option("-s", "--server", action="store", dest="server",
default="codereview.appspot.com",
metavar="SERVER",
help=("The server to upload to. The format is host[:port]. "
"Defaults to 'codereview.appspot.com'."))
group.add_option("-e", "--email", action="store", dest="email",
metavar="EMAIL", default=None,
help="The username to use. Will prompt if omitted.")
group.add_option("-H", "--host", action="store", dest="host",
metavar="HOST", default=None,
help="Overrides the Host header sent with all RPCs.")
group.add_option("--no_cookies", action="store_false",
dest="save_cookies", default=True,
help="Do not save authentication cookies to local disk.")
# Issue
group = parser.add_option_group("Issue options")
group.add_option("-d", "--description", action="store", dest="description",
metavar="DESCRIPTION", default=None,
help="Optional description when creating an issue.")
group.add_option("-f", "--description_file", action="store",
dest="description_file", metavar="DESCRIPTION_FILE",
default=None,
help="Optional path of a file that contains "
"the description when creating an issue.")
group.add_option("-r", "--reviewers", action="store", dest="reviewers",
metavar="REVIEWERS", default=None,
help="Add reviewers (comma separated email addresses).")
group.add_option("--cc", action="store", dest="cc",
metavar="CC", default=None,
help="Add CC (comma separated email addresses).")
# Upload options
group = parser.add_option_group("Patch options")
group.add_option("-m", "--message", action="store", dest="message",
metavar="MESSAGE", default=None,
help="A message to identify the patch. "
"Will prompt if omitted.")
group.add_option("-i", "--issue", type="int", action="store",
metavar="ISSUE", default=None,
help="Issue number to which to add. Defaults to new issue.")
group.add_option("--download_base", action="store_true",
dest="download_base", default=False,
help="Base files will be downloaded by the server "
"(side-by-side diffs may not work on files with CRs).")
group.add_option("--rev", action="store", dest="revision",
metavar="REV", default=None,
help="Branch/tree/revision to diff against (used by DVCS).")
group.add_option("--send_mail", action="store_true",
dest="send_mail", default=False,
help="Send notification email to reviewers.")
def GetRpcServer(options):
"""Returns an instance of an AbstractRpcServer.
Returns:
A new AbstractRpcServer, on which RPC calls can be made.
"""
rpc_server_class = HttpRpcServer
def GetUserCredentials():
"""Prompts the user for a username and password."""
email = options.email
if email is None:
email = GetEmail("Email (login for uploading to %s)" % options.server)
password = getpass.getpass("Password for %s: " % email)
return (email, password)
# If this is the dev_appserver, use fake authentication.
host = (options.host or options.server).lower()
if host == "localhost" or host.startswith("localhost:"):
email = options.email
if email is None:
email = "test@example.com"
logging.info("Using debug user %s. Override with --email" % email)
server = rpc_server_class(
options.server,
lambda: (email, "password"),
host_override=options.host,
extra_headers={"Cookie":
'dev_appserver_login="%s:False"' % email},
save_cookies=options.save_cookies)
# Don't try to talk to ClientLogin.
server.authenticated = True
return server
return rpc_server_class(options.server, GetUserCredentials,
host_override=options.host,
save_cookies=options.save_cookies)
def EncodeMultipartFormData(fields, files):
"""Encode form fields for multipart/form-data.
Args:
fields: A sequence of (name, value) elements for regular form fields.
files: A sequence of (name, filename, value) elements for data to be
uploaded as files.
Returns:
(content_type, body) ready for httplib.HTTP instance.
Source:
http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/146306
"""
BOUNDARY = '-M-A-G-I-C---B-O-U-N-D-A-R-Y-'
CRLF = '\r\n'
lines = []
for (key, value) in fields:
lines.append('--' + BOUNDARY)
lines.append('Content-Disposition: form-data; name="%s"' % key)
lines.append('')
lines.append(value)
for (key, filename, value) in files:
lines.append('--' + BOUNDARY)
lines.append('Content-Disposition: form-data; name="%s"; filename="%s"' %
(key, filename))
lines.append('Content-Type: %s' % GetContentType(filename))
lines.append('')
lines.append(value)
lines.append('--' + BOUNDARY + '--')
lines.append('')
body = CRLF.join(lines)
content_type = 'multipart/form-data; boundary=%s' % BOUNDARY
return content_type, body
def GetContentType(filename):
"""Helper to guess the content-type from the filename."""
return mimetypes.guess_type(filename)[0] or 'application/octet-stream'
# Use a shell for subcommands on Windows to get a PATH search.
use_shell = sys.platform.startswith("win")
def RunShellWithReturnCode(command, print_output=False,
universal_newlines=True):
"""Executes a command and returns the output from stdout and the return code.
Args:
command: Command to execute.
print_output: If True, the output is printed to stdout.
If False, both stdout and stderr are ignored.
universal_newlines: Use universal_newlines flag (default: True).
Returns:
Tuple (output, return code)
"""
logging.info("Running %s", command)
p = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
shell=use_shell, universal_newlines=universal_newlines)
if print_output:
output_array = []
while True:
line = p.stdout.readline()
if not line:
break
print line.strip("\n")
output_array.append(line)
output = "".join(output_array)
else:
output = p.stdout.read()
p.wait()
errout = p.stderr.read()
if print_output and errout:
print >>sys.stderr, errout
p.stdout.close()
p.stderr.close()
return output, p.returncode
def RunShell(command, silent_ok=False, universal_newlines=True,
print_output=False):
data, retcode = RunShellWithReturnCode(command, print_output,
universal_newlines)
if retcode:
ErrorExit("Got error status from %s:\n%s" % (command, data))
if not silent_ok and not data:
ErrorExit("No output from %s" % command)
return data
class VersionControlSystem(object):
"""Abstract base class providing an interface to the VCS."""
def __init__(self, options):
"""Constructor.
Args:
options: Command line options.
"""
self.options = options
def GenerateDiff(self, args):
"""Return the current diff as a string.
Args:
args: Extra arguments to pass to the diff command.
"""
raise NotImplementedError(
"abstract method -- subclass %s must override" % self.__class__)
def GetUnknownFiles(self):
"""Return a list of files unknown to the VCS."""
raise NotImplementedError(
"abstract method -- subclass %s must override" % self.__class__)
def CheckForUnknownFiles(self):
"""Show an "are you sure?" prompt if there are unknown files."""
unknown_files = self.GetUnknownFiles()
if unknown_files:
print "The following files are not added to version control:"
for line in unknown_files:
print line
prompt = "Are you sure to continue?(y/N) "
answer = raw_input(prompt).strip()
if answer != "y":
ErrorExit("User aborted")
def GetBaseFile(self, filename):
"""Get the content of the upstream version of a file.
Returns:
A tuple (base_content, new_content, is_binary, status)
base_content: The contents of the base file.
new_content: For text files, this is empty. For binary files, this is
the contents of the new file, since the diff output won't contain
information to reconstruct the current file.
is_binary: True iff the file is binary.
status: The status of the file.
"""
raise NotImplementedError(
"abstract method -- subclass %s must override" % self.__class__)
def GetBaseFiles(self, diff):
"""Helper that calls GetBase file for each file in the patch.
Returns:
A dictionary that maps from filename to GetBaseFile's tuple. Filenames
are retrieved based on lines that start with "Index:" or
"Property changes on:".
"""
files = {}
for line in diff.splitlines(True):
if line.startswith('Index:') or line.startswith('Property changes on:'):
unused, filename = line.split(':', 1)
# On Windows if a file has property changes its filename uses '\'
# instead of '/'.
filename = filename.strip().replace('\\', '/')
files[filename] = self.GetBaseFile(filename)
return files
def UploadBaseFiles(self, issue, rpc_server, patch_list, patchset, options,
files):
"""Uploads the base files (and if necessary, the current ones as well)."""
def UploadFile(filename, file_id, content, is_binary, status, is_base):
"""Uploads a file to the server."""
file_too_large = False
if is_base:
type = "base"
else:
type = "current"
if len(content) > MAX_UPLOAD_SIZE:
print ("Not uploading the %s file for %s because it's too large." %
(type, filename))
file_too_large = True
content = ""
checksum = md5.new(content).hexdigest()
if options.verbose > 0 and not file_too_large:
print "Uploading %s file for %s" % (type, filename)
url = "/%d/upload_content/%d/%d" % (int(issue), int(patchset), file_id)
form_fields = [("filename", filename),
("status", status),
("checksum", checksum),
("is_binary", str(is_binary)),
("is_current", str(not is_base)),
]
if file_too_large:
form_fields.append(("file_too_large", "1"))
if options.email:
form_fields.append(("user", options.email))
ctype, body = EncodeMultipartFormData(form_fields,
[("data", filename, content)])
response_body = rpc_server.Send(url, body,
content_type=ctype)
if not response_body.startswith("OK"):
StatusUpdate(" --> %s" % response_body)
sys.exit(1)
patches = dict()
[patches.setdefault(v, k) for k, v in patch_list]
for filename in patches.keys():
base_content, new_content, is_binary, status = files[filename]
file_id_str = patches.get(filename)
if file_id_str.find("nobase") != -1:
base_content = None
file_id_str = file_id_str[file_id_str.rfind("_") + 1:]
file_id = int(file_id_str)
if base_content != None:
UploadFile(filename, file_id, base_content, is_binary, status, True)
if new_content != None:
UploadFile(filename, file_id, new_content, is_binary, status, False)
def IsImage(self, filename):
"""Returns true if the filename has an image extension."""
mimetype = mimetypes.guess_type(filename)[0]
if not mimetype:
return False
return mimetype.startswith("image/")
class SubversionVCS(VersionControlSystem):
"""Implementation of the VersionControlSystem interface for Subversion."""
def __init__(self, options):
super(SubversionVCS, self).__init__(options)
if self.options.revision:
match = re.match(r"(\d+)(:(\d+))?", self.options.revision)
if not match: