/usr/lib/python3/dist-packages/google/protobuf/text_format.py is in python3-protobuf 3.0.0-9.1ubuntu1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 | # Protocol Buffers - Google's data interchange format
# Copyright 2008 Google Inc. All rights reserved.
# https://developers.google.com/protocol-buffers/
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following disclaimer
# in the documentation and/or other materials provided with the
# distribution.
# * Neither the name of Google Inc. nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
"""Contains routines for printing protocol messages in text format.
Simple usage example:
# Create a proto object and serialize it to a text proto string.
message = my_proto_pb2.MyMessage(foo='bar')
text_proto = text_format.MessageToString(message)
# Parse a text proto string.
message = text_format.Parse(text_proto, my_proto_pb2.MyMessage())
"""
__author__ = 'kenton@google.com (Kenton Varda)'
import io
import re
import six
if six.PY3:
long = int # pylint: disable=redefined-builtin,invalid-name
# pylint: disable=g-import-not-at-top
from google.protobuf.internal import type_checkers
from google.protobuf import descriptor
from google.protobuf import text_encoding
__all__ = ['MessageToString', 'PrintMessage', 'PrintField', 'PrintFieldValue',
'Merge']
_INTEGER_CHECKERS = (type_checkers.Uint32ValueChecker(),
type_checkers.Int32ValueChecker(),
type_checkers.Uint64ValueChecker(),
type_checkers.Int64ValueChecker())
_FLOAT_INFINITY = re.compile('-?inf(?:inity)?f?', re.IGNORECASE)
_FLOAT_NAN = re.compile('nanf?', re.IGNORECASE)
_FLOAT_TYPES = frozenset([descriptor.FieldDescriptor.CPPTYPE_FLOAT,
descriptor.FieldDescriptor.CPPTYPE_DOUBLE])
_QUOTES = frozenset(("'", '"'))
_ANY_FULL_TYPE_NAME = 'google.protobuf.Any'
class Error(Exception):
"""Top-level module error for text_format."""
class ParseError(Error):
"""Thrown in case of text parsing or tokenizing error."""
def __init__(self, message=None, line=None, column=None):
if message is not None and line is not None:
loc = str(line)
if column is not None:
loc += ':{0}'.format(column)
message = '{0} : {1}'.format(loc, message)
if message is not None:
super(ParseError, self).__init__(message)
else:
super(ParseError, self).__init__()
self._line = line
self._column = column
def GetLine(self):
return self._line
def GetColumn(self):
return self._column
class TextWriter(object):
def __init__(self, as_utf8):
if six.PY2:
self._writer = io.BytesIO()
else:
self._writer = io.StringIO()
def write(self, val):
if six.PY2:
if isinstance(val, six.text_type):
val = val.encode('utf-8')
return self._writer.write(val)
def close(self):
return self._writer.close()
def getvalue(self):
return self._writer.getvalue()
def MessageToString(message,
as_utf8=False,
as_one_line=False,
pointy_brackets=False,
use_index_order=False,
float_format=None,
use_field_number=False,
descriptor_pool=None,
indent=0):
"""Convert protobuf message to text format.
Floating point values can be formatted compactly with 15 digits of
precision (which is the most that IEEE 754 "double" can guarantee)
using float_format='.15g'. To ensure that converting to text and back to a
proto will result in an identical value, float_format='.17g' should be used.
Args:
message: The protocol buffers message.
as_utf8: Produce text output in UTF8 format.
as_one_line: Don't introduce newlines between fields.
pointy_brackets: If True, use angle brackets instead of curly braces for
nesting.
use_index_order: If True, print fields of a proto message using the order
defined in source code instead of the field number. By default, use the
field number order.
float_format: If set, use this to specify floating point number formatting
(per the "Format Specification Mini-Language"); otherwise, str() is used.
use_field_number: If True, print field numbers instead of names.
descriptor_pool: A DescriptorPool used to resolve Any types.
indent: The indent level, in terms of spaces, for pretty print.
Returns:
A string of the text formatted protocol buffer message.
"""
out = TextWriter(as_utf8)
printer = _Printer(out, indent, as_utf8, as_one_line, pointy_brackets,
use_index_order, float_format, use_field_number,
descriptor_pool)
printer.PrintMessage(message)
result = out.getvalue()
out.close()
if as_one_line:
return result.rstrip()
return result
def _IsMapEntry(field):
return (field.type == descriptor.FieldDescriptor.TYPE_MESSAGE and
field.message_type.has_options and
field.message_type.GetOptions().map_entry)
def PrintMessage(message,
out,
indent=0,
as_utf8=False,
as_one_line=False,
pointy_brackets=False,
use_index_order=False,
float_format=None,
use_field_number=False,
descriptor_pool=None):
printer = _Printer(out, indent, as_utf8, as_one_line, pointy_brackets,
use_index_order, float_format, use_field_number,
descriptor_pool)
printer.PrintMessage(message)
def PrintField(field,
value,
out,
indent=0,
as_utf8=False,
as_one_line=False,
pointy_brackets=False,
use_index_order=False,
float_format=None):
"""Print a single field name/value pair."""
printer = _Printer(out, indent, as_utf8, as_one_line, pointy_brackets,
use_index_order, float_format)
printer.PrintField(field, value)
def PrintFieldValue(field,
value,
out,
indent=0,
as_utf8=False,
as_one_line=False,
pointy_brackets=False,
use_index_order=False,
float_format=None):
"""Print a single field value (not including name)."""
printer = _Printer(out, indent, as_utf8, as_one_line, pointy_brackets,
use_index_order, float_format)
printer.PrintFieldValue(field, value)
def _BuildMessageFromTypeName(type_name, descriptor_pool):
"""Returns a protobuf message instance.
Args:
type_name: Fully-qualified protobuf message type name string.
descriptor_pool: DescriptorPool instance.
Returns:
A Message instance of type matching type_name, or None if the a Descriptor
wasn't found matching type_name.
"""
# pylint: disable=g-import-not-at-top
from google.protobuf import message_factory
factory = message_factory.MessageFactory(descriptor_pool)
try:
message_descriptor = descriptor_pool.FindMessageTypeByName(type_name)
except KeyError:
return None
message_type = factory.GetPrototype(message_descriptor)
return message_type()
class _Printer(object):
"""Text format printer for protocol message."""
def __init__(self,
out,
indent=0,
as_utf8=False,
as_one_line=False,
pointy_brackets=False,
use_index_order=False,
float_format=None,
use_field_number=False,
descriptor_pool=None):
"""Initialize the Printer.
Floating point values can be formatted compactly with 15 digits of
precision (which is the most that IEEE 754 "double" can guarantee)
using float_format='.15g'. To ensure that converting to text and back to a
proto will result in an identical value, float_format='.17g' should be used.
Args:
out: To record the text format result.
indent: The indent level for pretty print.
as_utf8: Produce text output in UTF8 format.
as_one_line: Don't introduce newlines between fields.
pointy_brackets: If True, use angle brackets instead of curly braces for
nesting.
use_index_order: If True, print fields of a proto message using the order
defined in source code instead of the field number. By default, use the
field number order.
float_format: If set, use this to specify floating point number formatting
(per the "Format Specification Mini-Language"); otherwise, str() is
used.
use_field_number: If True, print field numbers instead of names.
descriptor_pool: A DescriptorPool used to resolve Any types.
"""
self.out = out
self.indent = indent
self.as_utf8 = as_utf8
self.as_one_line = as_one_line
self.pointy_brackets = pointy_brackets
self.use_index_order = use_index_order
self.float_format = float_format
self.use_field_number = use_field_number
self.descriptor_pool = descriptor_pool
def _TryPrintAsAnyMessage(self, message):
"""Serializes if message is a google.protobuf.Any field."""
packed_message = _BuildMessageFromTypeName(message.TypeName(),
self.descriptor_pool)
if packed_message:
packed_message.MergeFromString(message.value)
self.out.write('%s[%s]' % (self.indent * ' ', message.type_url))
self._PrintMessageFieldValue(packed_message)
self.out.write(' ' if self.as_one_line else '\n')
return True
else:
return False
def PrintMessage(self, message):
"""Convert protobuf message to text format.
Args:
message: The protocol buffers message.
"""
if (message.DESCRIPTOR.full_name == _ANY_FULL_TYPE_NAME and
self.descriptor_pool and self._TryPrintAsAnyMessage(message)):
return
fields = message.ListFields()
if self.use_index_order:
fields.sort(key=lambda x: x[0].index)
for field, value in fields:
if _IsMapEntry(field):
for key in sorted(value):
# This is slow for maps with submessage entires because it copies the
# entire tree. Unfortunately this would take significant refactoring
# of this file to work around.
#
# TODO(haberman): refactor and optimize if this becomes an issue.
entry_submsg = field.message_type._concrete_class(key=key,
value=value[key])
self.PrintField(field, entry_submsg)
elif field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
for element in value:
self.PrintField(field, element)
else:
self.PrintField(field, value)
def PrintField(self, field, value):
"""Print a single field name/value pair."""
out = self.out
out.write(' ' * self.indent)
if self.use_field_number:
out.write(str(field.number))
else:
if field.is_extension:
out.write('[')
if (field.containing_type.GetOptions().message_set_wire_format and
field.type == descriptor.FieldDescriptor.TYPE_MESSAGE and
field.label == descriptor.FieldDescriptor.LABEL_OPTIONAL):
out.write(field.message_type.full_name)
else:
out.write(field.full_name)
out.write(']')
elif field.type == descriptor.FieldDescriptor.TYPE_GROUP:
# For groups, use the capitalized name.
out.write(field.message_type.name)
else:
out.write(field.name)
if field.cpp_type != descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
# The colon is optional in this case, but our cross-language golden files
# don't include it.
out.write(': ')
self.PrintFieldValue(field, value)
if self.as_one_line:
out.write(' ')
else:
out.write('\n')
def _PrintMessageFieldValue(self, value):
if self.pointy_brackets:
openb = '<'
closeb = '>'
else:
openb = '{'
closeb = '}'
if self.as_one_line:
self.out.write(' %s ' % openb)
self.PrintMessage(value)
self.out.write(closeb)
else:
self.out.write(' %s\n' % openb)
self.indent += 2
self.PrintMessage(value)
self.indent -= 2
self.out.write(' ' * self.indent + closeb)
def PrintFieldValue(self, field, value):
"""Print a single field value (not including name).
For repeated fields, the value should be a single element.
Args:
field: The descriptor of the field to be printed.
value: The value of the field.
"""
out = self.out
if field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
self._PrintMessageFieldValue(value)
elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_ENUM:
enum_value = field.enum_type.values_by_number.get(value, None)
if enum_value is not None:
out.write(enum_value.name)
else:
out.write(str(value))
elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_STRING:
out.write('\"')
if isinstance(value, six.text_type):
out_value = value.encode('utf-8')
else:
out_value = value
if field.type == descriptor.FieldDescriptor.TYPE_BYTES:
# We need to escape non-UTF8 chars in TYPE_BYTES field.
out_as_utf8 = False
else:
out_as_utf8 = self.as_utf8
out.write(text_encoding.CEscape(out_value, out_as_utf8))
out.write('\"')
elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_BOOL:
if value:
out.write('true')
else:
out.write('false')
elif field.cpp_type in _FLOAT_TYPES and self.float_format is not None:
out.write('{1:{0}}'.format(self.float_format, value))
else:
out.write(str(value))
def Parse(text,
message,
allow_unknown_extension=False,
allow_field_number=False):
"""Parses a text representation of a protocol message into a message.
Args:
text: Message text representation.
message: A protocol buffer message to merge into.
allow_unknown_extension: if True, skip over missing extensions and keep
parsing
allow_field_number: if True, both field number and field name are allowed.
Returns:
The same message passed as argument.
Raises:
ParseError: On text parsing problems.
"""
if not isinstance(text, str):
text = text.decode('utf-8')
return ParseLines(
text.split('\n'), message, allow_unknown_extension, allow_field_number)
def Merge(text,
message,
allow_unknown_extension=False,
allow_field_number=False,
descriptor_pool=None):
"""Parses a text representation of a protocol message into a message.
Like Parse(), but allows repeated values for a non-repeated field, and uses
the last one.
Args:
text: Message text representation.
message: A protocol buffer message to merge into.
allow_unknown_extension: if True, skip over missing extensions and keep
parsing
allow_field_number: if True, both field number and field name are allowed.
descriptor_pool: A DescriptorPool used to resolve Any types.
Returns:
The same message passed as argument.
Raises:
ParseError: On text parsing problems.
"""
return MergeLines(
text.split('\n'),
message,
allow_unknown_extension,
allow_field_number,
descriptor_pool=descriptor_pool)
def ParseLines(lines,
message,
allow_unknown_extension=False,
allow_field_number=False):
"""Parses a text representation of a protocol message into a message.
Args:
lines: An iterable of lines of a message's text representation.
message: A protocol buffer message to merge into.
allow_unknown_extension: if True, skip over missing extensions and keep
parsing
allow_field_number: if True, both field number and field name are allowed.
descriptor_pool: A DescriptorPool used to resolve Any types.
Returns:
The same message passed as argument.
Raises:
ParseError: On text parsing problems.
"""
parser = _Parser(allow_unknown_extension, allow_field_number)
return parser.ParseLines(lines, message)
def MergeLines(lines,
message,
allow_unknown_extension=False,
allow_field_number=False,
descriptor_pool=None):
"""Parses a text representation of a protocol message into a message.
Args:
lines: An iterable of lines of a message's text representation.
message: A protocol buffer message to merge into.
allow_unknown_extension: if True, skip over missing extensions and keep
parsing
allow_field_number: if True, both field number and field name are allowed.
Returns:
The same message passed as argument.
Raises:
ParseError: On text parsing problems.
"""
parser = _Parser(allow_unknown_extension,
allow_field_number,
descriptor_pool=descriptor_pool)
return parser.MergeLines(lines, message)
class _Parser(object):
"""Text format parser for protocol message."""
def __init__(self,
allow_unknown_extension=False,
allow_field_number=False,
descriptor_pool=None):
self.allow_unknown_extension = allow_unknown_extension
self.allow_field_number = allow_field_number
self.descriptor_pool = descriptor_pool
def ParseFromString(self, text, message):
"""Parses a text representation of a protocol message into a message."""
if not isinstance(text, str):
text = text.decode('utf-8')
return self.ParseLines(text.split('\n'), message)
def ParseLines(self, lines, message):
"""Parses a text representation of a protocol message into a message."""
self._allow_multiple_scalars = False
self._ParseOrMerge(lines, message)
return message
def MergeFromString(self, text, message):
"""Merges a text representation of a protocol message into a message."""
return self._MergeLines(text.split('\n'), message)
def MergeLines(self, lines, message):
"""Merges a text representation of a protocol message into a message."""
self._allow_multiple_scalars = True
self._ParseOrMerge(lines, message)
return message
def _ParseOrMerge(self, lines, message):
"""Converts a text representation of a protocol message into a message.
Args:
lines: Lines of a message's text representation.
message: A protocol buffer message to merge into.
Raises:
ParseError: On text parsing problems.
"""
tokenizer = Tokenizer(lines)
while not tokenizer.AtEnd():
self._MergeField(tokenizer, message)
def _MergeField(self, tokenizer, message):
"""Merges a single protocol message field into a message.
Args:
tokenizer: A tokenizer to parse the field name and values.
message: A protocol message to record the data.
Raises:
ParseError: In case of text parsing problems.
"""
message_descriptor = message.DESCRIPTOR
if (hasattr(message_descriptor, 'syntax') and
message_descriptor.syntax == 'proto3'):
# Proto3 doesn't represent presence so we can't test if multiple
# scalars have occurred. We have to allow them.
self._allow_multiple_scalars = True
if tokenizer.TryConsume('['):
name = [tokenizer.ConsumeIdentifier()]
while tokenizer.TryConsume('.'):
name.append(tokenizer.ConsumeIdentifier())
name = '.'.join(name)
if not message_descriptor.is_extendable:
raise tokenizer.ParseErrorPreviousToken(
'Message type "%s" does not have extensions.' %
message_descriptor.full_name)
# pylint: disable=protected-access
field = message.Extensions._FindExtensionByName(name)
# pylint: enable=protected-access
if not field:
if self.allow_unknown_extension:
field = None
else:
raise tokenizer.ParseErrorPreviousToken(
'Extension "%s" not registered.' % name)
elif message_descriptor != field.containing_type:
raise tokenizer.ParseErrorPreviousToken(
'Extension "%s" does not extend message type "%s".' %
(name, message_descriptor.full_name))
tokenizer.Consume(']')
else:
name = tokenizer.ConsumeIdentifierOrNumber()
if self.allow_field_number and name.isdigit():
number = ParseInteger(name, True, True)
field = message_descriptor.fields_by_number.get(number, None)
if not field and message_descriptor.is_extendable:
field = message.Extensions._FindExtensionByNumber(number)
else:
field = message_descriptor.fields_by_name.get(name, None)
# Group names are expected to be capitalized as they appear in the
# .proto file, which actually matches their type names, not their field
# names.
if not field:
field = message_descriptor.fields_by_name.get(name.lower(), None)
if field and field.type != descriptor.FieldDescriptor.TYPE_GROUP:
field = None
if (field and field.type == descriptor.FieldDescriptor.TYPE_GROUP and
field.message_type.name != name):
field = None
if not field:
raise tokenizer.ParseErrorPreviousToken(
'Message type "%s" has no field named "%s".' %
(message_descriptor.full_name, name))
if field:
if not self._allow_multiple_scalars and field.containing_oneof:
# Check if there's a different field set in this oneof.
# Note that we ignore the case if the same field was set before, and we
# apply _allow_multiple_scalars to non-scalar fields as well.
which_oneof = message.WhichOneof(field.containing_oneof.name)
if which_oneof is not None and which_oneof != field.name:
raise tokenizer.ParseErrorPreviousToken(
'Field "%s" is specified along with field "%s", another member '
'of oneof "%s" for message type "%s".' %
(field.name, which_oneof, field.containing_oneof.name,
message_descriptor.full_name))
if field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
tokenizer.TryConsume(':')
merger = self._MergeMessageField
else:
tokenizer.Consume(':')
merger = self._MergeScalarField
if (field.label == descriptor.FieldDescriptor.LABEL_REPEATED and
tokenizer.TryConsume('[')):
# Short repeated format, e.g. "foo: [1, 2, 3]"
while True:
merger(tokenizer, message, field)
if tokenizer.TryConsume(']'):
break
tokenizer.Consume(',')
else:
merger(tokenizer, message, field)
else: # Proto field is unknown.
assert self.allow_unknown_extension
_SkipFieldContents(tokenizer)
# For historical reasons, fields may optionally be separated by commas or
# semicolons.
if not tokenizer.TryConsume(','):
tokenizer.TryConsume(';')
def _ConsumeAnyTypeUrl(self, tokenizer):
"""Consumes a google.protobuf.Any type URL and returns the type name."""
# Consume "type.googleapis.com/".
tokenizer.ConsumeIdentifier()
tokenizer.Consume('.')
tokenizer.ConsumeIdentifier()
tokenizer.Consume('.')
tokenizer.ConsumeIdentifier()
tokenizer.Consume('/')
# Consume the fully-qualified type name.
name = [tokenizer.ConsumeIdentifier()]
while tokenizer.TryConsume('.'):
name.append(tokenizer.ConsumeIdentifier())
return '.'.join(name)
def _MergeMessageField(self, tokenizer, message, field):
"""Merges a single scalar field into a message.
Args:
tokenizer: A tokenizer to parse the field value.
message: The message of which field is a member.
field: The descriptor of the field to be merged.
Raises:
ParseError: In case of text parsing problems.
"""
is_map_entry = _IsMapEntry(field)
if tokenizer.TryConsume('<'):
end_token = '>'
else:
tokenizer.Consume('{')
end_token = '}'
if (field.message_type.full_name == _ANY_FULL_TYPE_NAME and
tokenizer.TryConsume('[')):
packed_type_name = self._ConsumeAnyTypeUrl(tokenizer)
tokenizer.Consume(']')
tokenizer.TryConsume(':')
if tokenizer.TryConsume('<'):
expanded_any_end_token = '>'
else:
tokenizer.Consume('{')
expanded_any_end_token = '}'
if not self.descriptor_pool:
raise ParseError('Descriptor pool required to parse expanded Any field')
expanded_any_sub_message = _BuildMessageFromTypeName(packed_type_name,
self.descriptor_pool)
if not expanded_any_sub_message:
raise ParseError('Type %s not found in descriptor pool' %
packed_type_name)
while not tokenizer.TryConsume(expanded_any_end_token):
if tokenizer.AtEnd():
raise tokenizer.ParseErrorPreviousToken('Expected "%s".' %
(expanded_any_end_token,))
self._MergeField(tokenizer, expanded_any_sub_message)
if field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
any_message = getattr(message, field.name).add()
else:
any_message = getattr(message, field.name)
any_message.Pack(expanded_any_sub_message)
elif field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
if field.is_extension:
sub_message = message.Extensions[field].add()
elif is_map_entry:
# pylint: disable=protected-access
sub_message = field.message_type._concrete_class()
else:
sub_message = getattr(message, field.name).add()
else:
if field.is_extension:
sub_message = message.Extensions[field]
else:
sub_message = getattr(message, field.name)
sub_message.SetInParent()
while not tokenizer.TryConsume(end_token):
if tokenizer.AtEnd():
raise tokenizer.ParseErrorPreviousToken('Expected "%s".' % (end_token,))
self._MergeField(tokenizer, sub_message)
if is_map_entry:
value_cpptype = field.message_type.fields_by_name['value'].cpp_type
if value_cpptype == descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
value = getattr(message, field.name)[sub_message.key]
value.MergeFrom(sub_message.value)
else:
getattr(message, field.name)[sub_message.key] = sub_message.value
def _MergeScalarField(self, tokenizer, message, field):
"""Merges a single scalar field into a message.
Args:
tokenizer: A tokenizer to parse the field value.
message: A protocol message to record the data.
field: The descriptor of the field to be merged.
Raises:
ParseError: In case of text parsing problems.
RuntimeError: On runtime errors.
"""
_ = self.allow_unknown_extension
value = None
if field.type in (descriptor.FieldDescriptor.TYPE_INT32,
descriptor.FieldDescriptor.TYPE_SINT32,
descriptor.FieldDescriptor.TYPE_SFIXED32):
value = _ConsumeInt32(tokenizer)
elif field.type in (descriptor.FieldDescriptor.TYPE_INT64,
descriptor.FieldDescriptor.TYPE_SINT64,
descriptor.FieldDescriptor.TYPE_SFIXED64):
value = _ConsumeInt64(tokenizer)
elif field.type in (descriptor.FieldDescriptor.TYPE_UINT32,
descriptor.FieldDescriptor.TYPE_FIXED32):
value = _ConsumeUint32(tokenizer)
elif field.type in (descriptor.FieldDescriptor.TYPE_UINT64,
descriptor.FieldDescriptor.TYPE_FIXED64):
value = _ConsumeUint64(tokenizer)
elif field.type in (descriptor.FieldDescriptor.TYPE_FLOAT,
descriptor.FieldDescriptor.TYPE_DOUBLE):
value = tokenizer.ConsumeFloat()
elif field.type == descriptor.FieldDescriptor.TYPE_BOOL:
value = tokenizer.ConsumeBool()
elif field.type == descriptor.FieldDescriptor.TYPE_STRING:
value = tokenizer.ConsumeString()
elif field.type == descriptor.FieldDescriptor.TYPE_BYTES:
value = tokenizer.ConsumeByteString()
elif field.type == descriptor.FieldDescriptor.TYPE_ENUM:
value = tokenizer.ConsumeEnum(field)
else:
raise RuntimeError('Unknown field type %d' % field.type)
if field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
if field.is_extension:
message.Extensions[field].append(value)
else:
getattr(message, field.name).append(value)
else:
if field.is_extension:
if not self._allow_multiple_scalars and message.HasExtension(field):
raise tokenizer.ParseErrorPreviousToken(
'Message type "%s" should not have multiple "%s" extensions.' %
(message.DESCRIPTOR.full_name, field.full_name))
else:
message.Extensions[field] = value
else:
if not self._allow_multiple_scalars and message.HasField(field.name):
raise tokenizer.ParseErrorPreviousToken(
'Message type "%s" should not have multiple "%s" fields.' %
(message.DESCRIPTOR.full_name, field.name))
else:
setattr(message, field.name, value)
def _SkipFieldContents(tokenizer):
"""Skips over contents (value or message) of a field.
Args:
tokenizer: A tokenizer to parse the field name and values.
"""
# Try to guess the type of this field.
# If this field is not a message, there should be a ":" between the
# field name and the field value and also the field value should not
# start with "{" or "<" which indicates the beginning of a message body.
# If there is no ":" or there is a "{" or "<" after ":", this field has
# to be a message or the input is ill-formed.
if tokenizer.TryConsume(':') and not tokenizer.LookingAt(
'{') and not tokenizer.LookingAt('<'):
_SkipFieldValue(tokenizer)
else:
_SkipFieldMessage(tokenizer)
def _SkipField(tokenizer):
"""Skips over a complete field (name and value/message).
Args:
tokenizer: A tokenizer to parse the field name and values.
"""
if tokenizer.TryConsume('['):
# Consume extension name.
tokenizer.ConsumeIdentifier()
while tokenizer.TryConsume('.'):
tokenizer.ConsumeIdentifier()
tokenizer.Consume(']')
else:
tokenizer.ConsumeIdentifier()
_SkipFieldContents(tokenizer)
# For historical reasons, fields may optionally be separated by commas or
# semicolons.
if not tokenizer.TryConsume(','):
tokenizer.TryConsume(';')
def _SkipFieldMessage(tokenizer):
"""Skips over a field message.
Args:
tokenizer: A tokenizer to parse the field name and values.
"""
if tokenizer.TryConsume('<'):
delimiter = '>'
else:
tokenizer.Consume('{')
delimiter = '}'
while not tokenizer.LookingAt('>') and not tokenizer.LookingAt('}'):
_SkipField(tokenizer)
tokenizer.Consume(delimiter)
def _SkipFieldValue(tokenizer):
"""Skips over a field value.
Args:
tokenizer: A tokenizer to parse the field name and values.
Raises:
ParseError: In case an invalid field value is found.
"""
# String/bytes tokens can come in multiple adjacent string literals.
# If we can consume one, consume as many as we can.
if tokenizer.TryConsumeByteString():
while tokenizer.TryConsumeByteString():
pass
return
if (not tokenizer.TryConsumeIdentifier() and
not _TryConsumeInt64(tokenizer) and not _TryConsumeUint64(tokenizer) and
not tokenizer.TryConsumeFloat()):
raise ParseError('Invalid field value: ' + tokenizer.token)
class Tokenizer(object):
"""Protocol buffer text representation tokenizer.
This class handles the lower level string parsing by splitting it into
meaningful tokens.
It was directly ported from the Java protocol buffer API.
"""
_WHITESPACE = re.compile(r'\s+')
_COMMENT = re.compile(r'(\s*#.*$)', re.MULTILINE)
_WHITESPACE_OR_COMMENT = re.compile(r'(\s|(#.*$))+', re.MULTILINE)
_TOKEN = re.compile('|'.join([
r'[a-zA-Z_][0-9a-zA-Z_+-]*', # an identifier
r'([0-9+-]|(\.[0-9]))[0-9a-zA-Z_.+-]*', # a number
] + [ # quoted str for each quote mark
r'{qt}([^{qt}\n\\]|\\.)*({qt}|\\?$)'.format(qt=mark) for mark in _QUOTES
]))
_IDENTIFIER = re.compile(r'[^\d\W]\w*')
_IDENTIFIER_OR_NUMBER = re.compile(r'\w+')
def __init__(self, lines, skip_comments=True):
self._position = 0
self._line = -1
self._column = 0
self._token_start = None
self.token = ''
self._lines = iter(lines)
self._current_line = ''
self._previous_line = 0
self._previous_column = 0
self._more_lines = True
self._skip_comments = skip_comments
self._whitespace_pattern = (skip_comments and self._WHITESPACE_OR_COMMENT
or self._WHITESPACE)
self._SkipWhitespace()
self.NextToken()
def LookingAt(self, token):
return self.token == token
def AtEnd(self):
"""Checks the end of the text was reached.
Returns:
True iff the end was reached.
"""
return not self.token
def _PopLine(self):
while len(self._current_line) <= self._column:
try:
self._current_line = next(self._lines)
except StopIteration:
self._current_line = ''
self._more_lines = False
return
else:
self._line += 1
self._column = 0
def _SkipWhitespace(self):
while True:
self._PopLine()
match = self._whitespace_pattern.match(self._current_line, self._column)
if not match:
break
length = len(match.group(0))
self._column += length
def TryConsume(self, token):
"""Tries to consume a given piece of text.
Args:
token: Text to consume.
Returns:
True iff the text was consumed.
"""
if self.token == token:
self.NextToken()
return True
return False
def Consume(self, token):
"""Consumes a piece of text.
Args:
token: Text to consume.
Raises:
ParseError: If the text couldn't be consumed.
"""
if not self.TryConsume(token):
raise self.ParseError('Expected "%s".' % token)
def ConsumeComment(self):
result = self.token
if not self._COMMENT.match(result):
raise self.ParseError('Expected comment.')
self.NextToken()
return result
def TryConsumeIdentifier(self):
try:
self.ConsumeIdentifier()
return True
except ParseError:
return False
def ConsumeIdentifier(self):
"""Consumes protocol message field identifier.
Returns:
Identifier string.
Raises:
ParseError: If an identifier couldn't be consumed.
"""
result = self.token
if not self._IDENTIFIER.match(result):
raise self.ParseError('Expected identifier.')
self.NextToken()
return result
def TryConsumeIdentifierOrNumber(self):
try:
self.ConsumeIdentifierOrNumber()
return True
except ParseError:
return False
def ConsumeIdentifierOrNumber(self):
"""Consumes protocol message field identifier.
Returns:
Identifier string.
Raises:
ParseError: If an identifier couldn't be consumed.
"""
result = self.token
if not self._IDENTIFIER_OR_NUMBER.match(result):
raise self.ParseError('Expected identifier or number.')
self.NextToken()
return result
def TryConsumeInteger(self):
try:
# Note: is_long only affects value type, not whether an error is raised.
self.ConsumeInteger()
return True
except ParseError:
return False
def ConsumeInteger(self, is_long=False):
"""Consumes an integer number.
Args:
is_long: True if the value should be returned as a long integer.
Returns:
The integer parsed.
Raises:
ParseError: If an integer couldn't be consumed.
"""
try:
result = _ParseAbstractInteger(self.token, is_long=is_long)
except ValueError as e:
raise self.ParseError(str(e))
self.NextToken()
return result
def TryConsumeFloat(self):
try:
self.ConsumeFloat()
return True
except ParseError:
return False
def ConsumeFloat(self):
"""Consumes an floating point number.
Returns:
The number parsed.
Raises:
ParseError: If a floating point number couldn't be consumed.
"""
try:
result = ParseFloat(self.token)
except ValueError as e:
raise self.ParseError(str(e))
self.NextToken()
return result
def ConsumeBool(self):
"""Consumes a boolean value.
Returns:
The bool parsed.
Raises:
ParseError: If a boolean value couldn't be consumed.
"""
try:
result = ParseBool(self.token)
except ValueError as e:
raise self.ParseError(str(e))
self.NextToken()
return result
def TryConsumeByteString(self):
try:
self.ConsumeByteString()
return True
except ParseError:
return False
def ConsumeString(self):
"""Consumes a string value.
Returns:
The string parsed.
Raises:
ParseError: If a string value couldn't be consumed.
"""
the_bytes = self.ConsumeByteString()
try:
return six.text_type(the_bytes, 'utf-8')
except UnicodeDecodeError as e:
raise self._StringParseError(e)
def ConsumeByteString(self):
"""Consumes a byte array value.
Returns:
The array parsed (as a string).
Raises:
ParseError: If a byte array value couldn't be consumed.
"""
the_list = [self._ConsumeSingleByteString()]
while self.token and self.token[0] in _QUOTES:
the_list.append(self._ConsumeSingleByteString())
return b''.join(the_list)
def _ConsumeSingleByteString(self):
"""Consume one token of a string literal.
String literals (whether bytes or text) can come in multiple adjacent
tokens which are automatically concatenated, like in C or Python. This
method only consumes one token.
Returns:
The token parsed.
Raises:
ParseError: When the wrong format data is found.
"""
text = self.token
if len(text) < 1 or text[0] not in _QUOTES:
raise self.ParseError('Expected string but found: %r' % (text,))
if len(text) < 2 or text[-1] != text[0]:
raise self.ParseError('String missing ending quote: %r' % (text,))
try:
result = text_encoding.CUnescape(text[1:-1])
except ValueError as e:
raise self.ParseError(str(e))
self.NextToken()
return result
def ConsumeEnum(self, field):
try:
result = ParseEnum(field, self.token)
except ValueError as e:
raise self.ParseError(str(e))
self.NextToken()
return result
def ParseErrorPreviousToken(self, message):
"""Creates and *returns* a ParseError for the previously read token.
Args:
message: A message to set for the exception.
Returns:
A ParseError instance.
"""
return ParseError(message, self._previous_line + 1,
self._previous_column + 1)
def ParseError(self, message):
"""Creates and *returns* a ParseError for the current token."""
return ParseError(message, self._line + 1, self._column + 1)
def _StringParseError(self, e):
return self.ParseError('Couldn\'t parse string: ' + str(e))
def NextToken(self):
"""Reads the next meaningful token."""
self._previous_line = self._line
self._previous_column = self._column
self._column += len(self.token)
self._SkipWhitespace()
if not self._more_lines:
self.token = ''
return
match = self._TOKEN.match(self._current_line, self._column)
if not match and not self._skip_comments:
match = self._COMMENT.match(self._current_line, self._column)
if match:
token = match.group(0)
self.token = token
else:
self.token = self._current_line[self._column]
# Aliased so it can still be accessed by current visibility violators.
# TODO(dbarnett): Migrate violators to textformat_tokenizer.
_Tokenizer = Tokenizer # pylint: disable=invalid-name
def _ConsumeInt32(tokenizer):
"""Consumes a signed 32bit integer number from tokenizer.
Args:
tokenizer: A tokenizer used to parse the number.
Returns:
The integer parsed.
Raises:
ParseError: If a signed 32bit integer couldn't be consumed.
"""
return _ConsumeInteger(tokenizer, is_signed=True, is_long=False)
def _ConsumeUint32(tokenizer):
"""Consumes an unsigned 32bit integer number from tokenizer.
Args:
tokenizer: A tokenizer used to parse the number.
Returns:
The integer parsed.
Raises:
ParseError: If an unsigned 32bit integer couldn't be consumed.
"""
return _ConsumeInteger(tokenizer, is_signed=False, is_long=False)
def _TryConsumeInt64(tokenizer):
try:
_ConsumeInt64(tokenizer)
return True
except ParseError:
return False
def _ConsumeInt64(tokenizer):
"""Consumes a signed 32bit integer number from tokenizer.
Args:
tokenizer: A tokenizer used to parse the number.
Returns:
The integer parsed.
Raises:
ParseError: If a signed 32bit integer couldn't be consumed.
"""
return _ConsumeInteger(tokenizer, is_signed=True, is_long=True)
def _TryConsumeUint64(tokenizer):
try:
_ConsumeUint64(tokenizer)
return True
except ParseError:
return False
def _ConsumeUint64(tokenizer):
"""Consumes an unsigned 64bit integer number from tokenizer.
Args:
tokenizer: A tokenizer used to parse the number.
Returns:
The integer parsed.
Raises:
ParseError: If an unsigned 64bit integer couldn't be consumed.
"""
return _ConsumeInteger(tokenizer, is_signed=False, is_long=True)
def _TryConsumeInteger(tokenizer, is_signed=False, is_long=False):
try:
_ConsumeInteger(tokenizer, is_signed=is_signed, is_long=is_long)
return True
except ParseError:
return False
def _ConsumeInteger(tokenizer, is_signed=False, is_long=False):
"""Consumes an integer number from tokenizer.
Args:
tokenizer: A tokenizer used to parse the number.
is_signed: True if a signed integer must be parsed.
is_long: True if a long integer must be parsed.
Returns:
The integer parsed.
Raises:
ParseError: If an integer with given characteristics couldn't be consumed.
"""
try:
result = ParseInteger(tokenizer.token, is_signed=is_signed, is_long=is_long)
except ValueError as e:
raise tokenizer.ParseError(str(e))
tokenizer.NextToken()
return result
def ParseInteger(text, is_signed=False, is_long=False):
"""Parses an integer.
Args:
text: The text to parse.
is_signed: True if a signed integer must be parsed.
is_long: True if a long integer must be parsed.
Returns:
The integer value.
Raises:
ValueError: Thrown Iff the text is not a valid integer.
"""
# Do the actual parsing. Exception handling is propagated to caller.
result = _ParseAbstractInteger(text, is_long=is_long)
# Check if the integer is sane. Exceptions handled by callers.
checker = _INTEGER_CHECKERS[2 * int(is_long) + int(is_signed)]
checker.CheckValue(result)
return result
def _ParseAbstractInteger(text, is_long=False):
"""Parses an integer without checking size/signedness.
Args:
text: The text to parse.
is_long: True if the value should be returned as a long integer.
Returns:
The integer value.
Raises:
ValueError: Thrown Iff the text is not a valid integer.
"""
# Do the actual parsing. Exception handling is propagated to caller.
try:
# We force 32-bit values to int and 64-bit values to long to make
# alternate implementations where the distinction is more significant
# (e.g. the C++ implementation) simpler.
if is_long:
return int(text, 0)
else:
return int(text, 0)
except ValueError:
raise ValueError('Couldn\'t parse integer: %s' % text)
def ParseFloat(text):
"""Parse a floating point number.
Args:
text: Text to parse.
Returns:
The number parsed.
Raises:
ValueError: If a floating point number couldn't be parsed.
"""
try:
# Assume Python compatible syntax.
return float(text)
except ValueError:
# Check alternative spellings.
if _FLOAT_INFINITY.match(text):
if text[0] == '-':
return float('-inf')
else:
return float('inf')
elif _FLOAT_NAN.match(text):
return float('nan')
else:
# assume '1.0f' format
try:
return float(text.rstrip('f'))
except ValueError:
raise ValueError('Couldn\'t parse float: %s' % text)
def ParseBool(text):
"""Parse a boolean value.
Args:
text: Text to parse.
Returns:
Boolean values parsed
Raises:
ValueError: If text is not a valid boolean.
"""
if text in ('true', 't', '1'):
return True
elif text in ('false', 'f', '0'):
return False
else:
raise ValueError('Expected "true" or "false".')
def ParseEnum(field, value):
"""Parse an enum value.
The value can be specified by a number (the enum value), or by
a string literal (the enum name).
Args:
field: Enum field descriptor.
value: String value.
Returns:
Enum value number.
Raises:
ValueError: If the enum value could not be parsed.
"""
enum_descriptor = field.enum_type
try:
number = int(value, 0)
except ValueError:
# Identifier.
enum_value = enum_descriptor.values_by_name.get(value, None)
if enum_value is None:
raise ValueError('Enum type "%s" has no value named %s.' %
(enum_descriptor.full_name, value))
else:
# Numeric value.
enum_value = enum_descriptor.values_by_number.get(number, None)
if enum_value is None:
raise ValueError('Enum type "%s" has no value with number %d.' %
(enum_descriptor.full_name, number))
return enum_value.number
|