summaryrefslogtreecommitdiffstats
path: root/Lib/email/feedparser.py
diff options
context:
space:
mode:
authorThomas Wouters <thomas@python.org>2006-04-21 10:40:58 (GMT)
committerThomas Wouters <thomas@python.org>2006-04-21 10:40:58 (GMT)
commit49fd7fa4431da299196d74087df4a04f99f9c46f (patch)
tree35ace5fe78d3d52c7a9ab356ab9f6dbf8d4b71f4 /Lib/email/feedparser.py
parent9ada3d6e29d5165dadacbe6be07bcd35cfbef59d (diff)
downloadcpython-49fd7fa4431da299196d74087df4a04f99f9c46f.zip
cpython-49fd7fa4431da299196d74087df4a04f99f9c46f.tar.gz
cpython-49fd7fa4431da299196d74087df4a04f99f9c46f.tar.bz2
Merge p3yk branch with the trunk up to revision 45595. This breaks a fair
number of tests, all because of the codecs/_multibytecodecs issue described here (it's not a Py3K issue, just something Py3K discovers): http://mail.python.org/pipermail/python-dev/2006-April/064051.html Hye-Shik Chang promised to look for a fix, so no need to fix it here. The tests that are expected to break are: test_codecencodings_cn test_codecencodings_hk test_codecencodings_jp test_codecencodings_kr test_codecencodings_tw test_codecs test_multibytecodec This merge fixes an actual test failure (test_weakref) in this branch, though, so I believe merging is the right thing to do anyway.
Diffstat (limited to 'Lib/email/feedparser.py')
-rw-r--r--Lib/email/feedparser.py480
1 files changed, 480 insertions, 0 deletions
diff --git a/Lib/email/feedparser.py b/Lib/email/feedparser.py
new file mode 100644
index 0000000..afb02b3
--- /dev/null
+++ b/Lib/email/feedparser.py
@@ -0,0 +1,480 @@
+# Copyright (C) 2004-2006 Python Software Foundation
+# Authors: Baxter, Wouters and Warsaw
+# Contact: email-sig@python.org
+
+"""FeedParser - An email feed parser.
+
+The feed parser implements an interface for incrementally parsing an email
+message, line by line. This has advantages for certain applications, such as
+those reading email messages off a socket.
+
+FeedParser.feed() is the primary interface for pushing new data into the
+parser. It returns when there's nothing more it can do with the available
+data. When you have no more data to push into the parser, call .close().
+This completes the parsing and returns the root message object.
+
+The other advantage of this parser is that it will never throw a parsing
+exception. Instead, when it finds something unexpected, it adds a 'defect' to
+the current message. Defects are just instances that live on the message
+object's .defects attribute.
+"""
+
+__all__ = ['FeedParser']
+
+import re
+
+from email import errors
+from email import message
+
+NLCRE = re.compile('\r\n|\r|\n')
+NLCRE_bol = re.compile('(\r\n|\r|\n)')
+NLCRE_eol = re.compile('(\r\n|\r|\n)$')
+NLCRE_crack = re.compile('(\r\n|\r|\n)')
+# RFC 2822 $3.6.8 Optional fields. ftext is %d33-57 / %d59-126, Any character
+# except controls, SP, and ":".
+headerRE = re.compile(r'^(From |[\041-\071\073-\176]{1,}:|[\t ])')
+EMPTYSTRING = ''
+NL = '\n'
+
+NeedMoreData = object()
+
+
+
+class BufferedSubFile(object):
+ """A file-ish object that can have new data loaded into it.
+
+ You can also push and pop line-matching predicates onto a stack. When the
+ current predicate matches the current line, a false EOF response
+ (i.e. empty string) is returned instead. This lets the parser adhere to a
+ simple abstraction -- it parses until EOF closes the current message.
+ """
+ def __init__(self):
+ # The last partial line pushed into this object.
+ self._partial = ''
+ # The list of full, pushed lines, in reverse order
+ self._lines = []
+ # The stack of false-EOF checking predicates.
+ self._eofstack = []
+ # A flag indicating whether the file has been closed or not.
+ self._closed = False
+
+ def push_eof_matcher(self, pred):
+ self._eofstack.append(pred)
+
+ def pop_eof_matcher(self):
+ return self._eofstack.pop()
+
+ def close(self):
+ # Don't forget any trailing partial line.
+ self._lines.append(self._partial)
+ self._partial = ''
+ self._closed = True
+
+ def readline(self):
+ if not self._lines:
+ if self._closed:
+ return ''
+ return NeedMoreData
+ # Pop the line off the stack and see if it matches the current
+ # false-EOF predicate.
+ line = self._lines.pop()
+ # RFC 2046, section 5.1.2 requires us to recognize outer level
+ # boundaries at any level of inner nesting. Do this, but be sure it's
+ # in the order of most to least nested.
+ for ateof in self._eofstack[::-1]:
+ if ateof(line):
+ # We're at the false EOF. But push the last line back first.
+ self._lines.append(line)
+ return ''
+ return line
+
+ def unreadline(self, line):
+ # Let the consumer push a line back into the buffer.
+ assert line is not NeedMoreData
+ self._lines.append(line)
+
+ def push(self, data):
+ """Push some new data into this object."""
+ # Handle any previous leftovers
+ data, self._partial = self._partial + data, ''
+ # Crack into lines, but preserve the newlines on the end of each
+ parts = NLCRE_crack.split(data)
+ # The *ahem* interesting behaviour of re.split when supplied grouping
+ # parentheses is that the last element of the resulting list is the
+ # data after the final RE. In the case of a NL/CR terminated string,
+ # this is the empty string.
+ self._partial = parts.pop()
+ # parts is a list of strings, alternating between the line contents
+ # and the eol character(s). Gather up a list of lines after
+ # re-attaching the newlines.
+ lines = []
+ for i in range(len(parts) // 2):
+ lines.append(parts[i*2] + parts[i*2+1])
+ self.pushlines(lines)
+
+ def pushlines(self, lines):
+ # Reverse and insert at the front of the lines.
+ self._lines[:0] = lines[::-1]
+
+ def is_closed(self):
+ return self._closed
+
+ def __iter__(self):
+ return self
+
+ def next(self):
+ line = self.readline()
+ if line == '':
+ raise StopIteration
+ return line
+
+
+
+class FeedParser:
+ """A feed-style parser of email."""
+
+ def __init__(self, _factory=message.Message):
+ """_factory is called with no arguments to create a new message obj"""
+ self._factory = _factory
+ self._input = BufferedSubFile()
+ self._msgstack = []
+ self._parse = self._parsegen().next
+ self._cur = None
+ self._last = None
+ self._headersonly = False
+
+ # Non-public interface for supporting Parser's headersonly flag
+ def _set_headersonly(self):
+ self._headersonly = True
+
+ def feed(self, data):
+ """Push more data into the parser."""
+ self._input.push(data)
+ self._call_parse()
+
+ def _call_parse(self):
+ try:
+ self._parse()
+ except StopIteration:
+ pass
+
+ def close(self):
+ """Parse all remaining data and return the root message object."""
+ self._input.close()
+ self._call_parse()
+ root = self._pop_message()
+ assert not self._msgstack
+ # Look for final set of defects
+ if root.get_content_maintype() == 'multipart' \
+ and not root.is_multipart():
+ root.defects.append(errors.MultipartInvariantViolationDefect())
+ return root
+
+ def _new_message(self):
+ msg = self._factory()
+ if self._cur and self._cur.get_content_type() == 'multipart/digest':
+ msg.set_default_type('message/rfc822')
+ if self._msgstack:
+ self._msgstack[-1].attach(msg)
+ self._msgstack.append(msg)
+ self._cur = msg
+ self._last = msg
+
+ def _pop_message(self):
+ retval = self._msgstack.pop()
+ if self._msgstack:
+ self._cur = self._msgstack[-1]
+ else:
+ self._cur = None
+ return retval
+
+ def _parsegen(self):
+ # Create a new message and start by parsing headers.
+ self._new_message()
+ headers = []
+ # Collect the headers, searching for a line that doesn't match the RFC
+ # 2822 header or continuation pattern (including an empty line).
+ for line in self._input:
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ if not headerRE.match(line):
+ # If we saw the RFC defined header/body separator
+ # (i.e. newline), just throw it away. Otherwise the line is
+ # part of the body so push it back.
+ if not NLCRE.match(line):
+ self._input.unreadline(line)
+ break
+ headers.append(line)
+ # Done with the headers, so parse them and figure out what we're
+ # supposed to see in the body of the message.
+ self._parse_headers(headers)
+ # Headers-only parsing is a backwards compatibility hack, which was
+ # necessary in the older parser, which could throw errors. All
+ # remaining lines in the input are thrown into the message body.
+ if self._headersonly:
+ lines = []
+ while True:
+ line = self._input.readline()
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ if line == '':
+ break
+ lines.append(line)
+ self._cur.set_payload(EMPTYSTRING.join(lines))
+ return
+ if self._cur.get_content_type() == 'message/delivery-status':
+ # message/delivery-status contains blocks of headers separated by
+ # a blank line. We'll represent each header block as a separate
+ # nested message object, but the processing is a bit different
+ # than standard message/* types because there is no body for the
+ # nested messages. A blank line separates the subparts.
+ while True:
+ self._input.push_eof_matcher(NLCRE.match)
+ for retval in self._parsegen():
+ if retval is NeedMoreData:
+ yield NeedMoreData
+ continue
+ break
+ msg = self._pop_message()
+ # We need to pop the EOF matcher in order to tell if we're at
+ # the end of the current file, not the end of the last block
+ # of message headers.
+ self._input.pop_eof_matcher()
+ # The input stream must be sitting at the newline or at the
+ # EOF. We want to see if we're at the end of this subpart, so
+ # first consume the blank line, then test the next line to see
+ # if we're at this subpart's EOF.
+ while True:
+ line = self._input.readline()
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ break
+ while True:
+ line = self._input.readline()
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ break
+ if line == '':
+ break
+ # Not at EOF so this is a line we're going to need.
+ self._input.unreadline(line)
+ return
+ if self._cur.get_content_maintype() == 'message':
+ # The message claims to be a message/* type, then what follows is
+ # another RFC 2822 message.
+ for retval in self._parsegen():
+ if retval is NeedMoreData:
+ yield NeedMoreData
+ continue
+ break
+ self._pop_message()
+ return
+ if self._cur.get_content_maintype() == 'multipart':
+ boundary = self._cur.get_boundary()
+ if boundary is None:
+ # The message /claims/ to be a multipart but it has not
+ # defined a boundary. That's a problem which we'll handle by
+ # reading everything until the EOF and marking the message as
+ # defective.
+ self._cur.defects.append(errors.NoBoundaryInMultipartDefect())
+ lines = []
+ for line in self._input:
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ lines.append(line)
+ self._cur.set_payload(EMPTYSTRING.join(lines))
+ return
+ # Create a line match predicate which matches the inter-part
+ # boundary as well as the end-of-multipart boundary. Don't push
+ # this onto the input stream until we've scanned past the
+ # preamble.
+ separator = '--' + boundary
+ boundaryre = re.compile(
+ '(?P<sep>' + re.escape(separator) +
+ r')(?P<end>--)?(?P<ws>[ \t]*)(?P<linesep>\r\n|\r|\n)?$')
+ capturing_preamble = True
+ preamble = []
+ linesep = False
+ while True:
+ line = self._input.readline()
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ if line == '':
+ break
+ mo = boundaryre.match(line)
+ if mo:
+ # If we're looking at the end boundary, we're done with
+ # this multipart. If there was a newline at the end of
+ # the closing boundary, then we need to initialize the
+ # epilogue with the empty string (see below).
+ if mo.group('end'):
+ linesep = mo.group('linesep')
+ break
+ # We saw an inter-part boundary. Were we in the preamble?
+ if capturing_preamble:
+ if preamble:
+ # According to RFC 2046, the last newline belongs
+ # to the boundary.
+ lastline = preamble[-1]
+ eolmo = NLCRE_eol.search(lastline)
+ if eolmo:
+ preamble[-1] = lastline[:-len(eolmo.group(0))]
+ self._cur.preamble = EMPTYSTRING.join(preamble)
+ capturing_preamble = False
+ self._input.unreadline(line)
+ continue
+ # We saw a boundary separating two parts. Consume any
+ # multiple boundary lines that may be following. Our
+ # interpretation of RFC 2046 BNF grammar does not produce
+ # body parts within such double boundaries.
+ while True:
+ line = self._input.readline()
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ mo = boundaryre.match(line)
+ if not mo:
+ self._input.unreadline(line)
+ break
+ # Recurse to parse this subpart; the input stream points
+ # at the subpart's first line.
+ self._input.push_eof_matcher(boundaryre.match)
+ for retval in self._parsegen():
+ if retval is NeedMoreData:
+ yield NeedMoreData
+ continue
+ break
+ # Because of RFC 2046, the newline preceding the boundary
+ # separator actually belongs to the boundary, not the
+ # previous subpart's payload (or epilogue if the previous
+ # part is a multipart).
+ if self._last.get_content_maintype() == 'multipart':
+ epilogue = self._last.epilogue
+ if epilogue == '':
+ self._last.epilogue = None
+ elif epilogue is not None:
+ mo = NLCRE_eol.search(epilogue)
+ if mo:
+ end = len(mo.group(0))
+ self._last.epilogue = epilogue[:-end]
+ else:
+ payload = self._last.get_payload()
+ if isinstance(payload, basestring):
+ mo = NLCRE_eol.search(payload)
+ if mo:
+ payload = payload[:-len(mo.group(0))]
+ self._last.set_payload(payload)
+ self._input.pop_eof_matcher()
+ self._pop_message()
+ # Set the multipart up for newline cleansing, which will
+ # happen if we're in a nested multipart.
+ self._last = self._cur
+ else:
+ # I think we must be in the preamble
+ assert capturing_preamble
+ preamble.append(line)
+ # We've seen either the EOF or the end boundary. If we're still
+ # capturing the preamble, we never saw the start boundary. Note
+ # that as a defect and store the captured text as the payload.
+ # Everything from here to the EOF is epilogue.
+ if capturing_preamble:
+ self._cur.defects.append(errors.StartBoundaryNotFoundDefect())
+ self._cur.set_payload(EMPTYSTRING.join(preamble))
+ epilogue = []
+ for line in self._input:
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ self._cur.epilogue = EMPTYSTRING.join(epilogue)
+ return
+ # If the end boundary ended in a newline, we'll need to make sure
+ # the epilogue isn't None
+ if linesep:
+ epilogue = ['']
+ else:
+ epilogue = []
+ for line in self._input:
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ epilogue.append(line)
+ # Any CRLF at the front of the epilogue is not technically part of
+ # the epilogue. Also, watch out for an empty string epilogue,
+ # which means a single newline.
+ if epilogue:
+ firstline = epilogue[0]
+ bolmo = NLCRE_bol.match(firstline)
+ if bolmo:
+ epilogue[0] = firstline[len(bolmo.group(0)):]
+ self._cur.epilogue = EMPTYSTRING.join(epilogue)
+ return
+ # Otherwise, it's some non-multipart type, so the entire rest of the
+ # file contents becomes the payload.
+ lines = []
+ for line in self._input:
+ if line is NeedMoreData:
+ yield NeedMoreData
+ continue
+ lines.append(line)
+ self._cur.set_payload(EMPTYSTRING.join(lines))
+
+ def _parse_headers(self, lines):
+ # Passed a list of lines that make up the headers for the current msg
+ lastheader = ''
+ lastvalue = []
+ for lineno, line in enumerate(lines):
+ # Check for continuation
+ if line[0] in ' \t':
+ if not lastheader:
+ # The first line of the headers was a continuation. This
+ # is illegal, so let's note the defect, store the illegal
+ # line, and ignore it for purposes of headers.
+ defect = errors.FirstHeaderLineIsContinuationDefect(line)
+ self._cur.defects.append(defect)
+ continue
+ lastvalue.append(line)
+ continue
+ if lastheader:
+ # XXX reconsider the joining of folded lines
+ lhdr = EMPTYSTRING.join(lastvalue)[:-1].rstrip('\r\n')
+ self._cur[lastheader] = lhdr
+ lastheader, lastvalue = '', []
+ # Check for envelope header, i.e. unix-from
+ if line.startswith('From '):
+ if lineno == 0:
+ # Strip off the trailing newline
+ mo = NLCRE_eol.search(line)
+ if mo:
+ line = line[:-len(mo.group(0))]
+ self._cur.set_unixfrom(line)
+ continue
+ elif lineno == len(lines) - 1:
+ # Something looking like a unix-from at the end - it's
+ # probably the first line of the body, so push back the
+ # line and stop.
+ self._input.unreadline(line)
+ return
+ else:
+ # Weirdly placed unix-from line. Note this as a defect
+ # and ignore it.
+ defect = errors.MisplacedEnvelopeHeaderDefect(line)
+ self._cur.defects.append(defect)
+ continue
+ # Split the line on the colon separating field name from value.
+ i = line.find(':')
+ if i < 0:
+ defect = errors.MalformedHeaderDefect(line)
+ self._cur.defects.append(defect)
+ continue
+ lastheader = line[:i]
+ lastvalue = [line[i+1:].lstrip()]
+ # Done with all the lines, so handle the last header.
+ if lastheader:
+ # XXX reconsider the joining of folded lines
+ self._cur[lastheader] = EMPTYSTRING.join(lastvalue).rstrip('\r\n')
generated by cgit v0.12 at 2025-12-16 08:47:25 (GMT)
'n1085' href='#n1085'>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 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 

/* New getargs implementation */

#include "Python.h"
#include "pycore_tupleobject.h"

#include <ctype.h>
#include <float.h>


#ifdef __cplusplus
extern "C" {
#endif
int PyArg_Parse(PyObject *, const char *, ...);
int PyArg_ParseTuple(PyObject *, const char *, ...);
int PyArg_VaParse(PyObject *, const char *, va_list);

int PyArg_ParseTupleAndKeywords(PyObject *, PyObject *,
                                const char *, char **, ...);
int PyArg_VaParseTupleAndKeywords(PyObject *, PyObject *,
                                const char *, char **, va_list);

int _PyArg_ParseTupleAndKeywordsFast(PyObject *, PyObject *,
                                            struct _PyArg_Parser *, ...);
int _PyArg_VaParseTupleAndKeywordsFast(PyObject *, PyObject *,
                                            struct _PyArg_Parser *, va_list);

#ifdef HAVE_DECLSPEC_DLL
/* Export functions */
PyAPI_FUNC(int) _PyArg_Parse_SizeT(PyObject *, const char *, ...);
PyAPI_FUNC(int) _PyArg_ParseStack_SizeT(PyObject *const *args, Py_ssize_t nargs,
                                        const char *format, ...);
PyAPI_FUNC(int) _PyArg_ParseStackAndKeywords_SizeT(PyObject *const *args, Py_ssize_t nargs,
                                        PyObject *kwnames,
                                        struct _PyArg_Parser *parser, ...);
PyAPI_FUNC(int) _PyArg_ParseTuple_SizeT(PyObject *, const char *, ...);
PyAPI_FUNC(int) _PyArg_ParseTupleAndKeywords_SizeT(PyObject *, PyObject *,
                                                  const char *, char **, ...);
PyAPI_FUNC(PyObject *) _Py_BuildValue_SizeT(const char *, ...);
PyAPI_FUNC(int) _PyArg_VaParse_SizeT(PyObject *, const char *, va_list);
PyAPI_FUNC(int) _PyArg_VaParseTupleAndKeywords_SizeT(PyObject *, PyObject *,
                                              const char *, char **, va_list);

PyAPI_FUNC(int) _PyArg_ParseTupleAndKeywordsFast_SizeT(PyObject *, PyObject *,
                                            struct _PyArg_Parser *, ...);
PyAPI_FUNC(int) _PyArg_VaParseTupleAndKeywordsFast_SizeT(PyObject *, PyObject *,
                                            struct _PyArg_Parser *, va_list);
#endif

#define FLAG_COMPAT 1
#define FLAG_SIZE_T 2

typedef int (*destr_t)(PyObject *, void *);


/* Keep track of "objects" that have been allocated or initialized and
   which will need to be deallocated or cleaned up somehow if overall
   parsing fails.
*/
typedef struct {
  void *item;
  destr_t destructor;
} freelistentry_t;

typedef struct {
  freelistentry_t *entries;
  int first_available;
  int entries_malloced;
} freelist_t;

#define STATIC_FREELIST_ENTRIES 8

/* Forward */
static int vgetargs1_impl(PyObject *args, PyObject *const *stack, Py_ssize_t nargs,
                          const char *format, va_list *p_va, int flags);
static int vgetargs1(PyObject *, const char *, va_list *, int);
static void seterror(Py_ssize_t, const char *, int *, const char *, const char *);
static const char *convertitem(PyObject *, const char **, va_list *, int, int *,
                               char *, size_t, freelist_t *);
static const char *converttuple(PyObject *, const char **, va_list *, int,
                                int *, char *, size_t, int, freelist_t *);
static const char *convertsimple(PyObject *, const char **, va_list *, int,
                                 char *, size_t, freelist_t *);
static Py_ssize_t convertbuffer(PyObject *, const void **p, const char **);
static int getbuffer(PyObject *, Py_buffer *, const char**);

static int vgetargskeywords(PyObject *, PyObject *,
                            const char *, char **, va_list *, int);
static int vgetargskeywordsfast(PyObject *, PyObject *,
                            struct _PyArg_Parser *, va_list *, int);
static int vgetargskeywordsfast_impl(PyObject *const *args, Py_ssize_t nargs,
                          PyObject *keywords, PyObject *kwnames,
                          struct _PyArg_Parser *parser,
                          va_list *p_va, int flags);
static const char *skipitem(const char **, va_list *, int);

int
PyArg_Parse(PyObject *args, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1(args, format, &va, FLAG_COMPAT);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_Parse_SizeT(PyObject *args, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1(args, format, &va, FLAG_COMPAT|FLAG_SIZE_T);
    va_end(va);
    return retval;
}


int
PyArg_ParseTuple(PyObject *args, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1(args, format, &va, 0);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseTuple_SizeT(PyObject *args, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1(args, format, &va, FLAG_SIZE_T);
    va_end(va);
    return retval;
}


int
_PyArg_ParseStack(PyObject *const *args, Py_ssize_t nargs, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1_impl(NULL, args, nargs, format, &va, 0);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseStack_SizeT(PyObject *const *args, Py_ssize_t nargs, const char *format, ...)
{
    int retval;
    va_list va;

    va_start(va, format);
    retval = vgetargs1_impl(NULL, args, nargs, format, &va, FLAG_SIZE_T);
    va_end(va);
    return retval;
}


int
PyArg_VaParse(PyObject *args, const char *format, va_list va)
{
    va_list lva;
    int retval;

    va_copy(lva, va);

    retval = vgetargs1(args, format, &lva, 0);
    va_end(lva);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_VaParse_SizeT(PyObject *args, const char *format, va_list va)
{
    va_list lva;
    int retval;

    va_copy(lva, va);

    retval = vgetargs1(args, format, &lva, FLAG_SIZE_T);
    va_end(lva);
    return retval;
}


/* Handle cleanup of allocated memory in case of exception */

static int
cleanup_ptr(PyObject *self, void *ptr)
{
    if (ptr) {
        PyMem_FREE(ptr);
    }
    return 0;
}

static int
cleanup_buffer(PyObject *self, void *ptr)
{
    Py_buffer *buf = (Py_buffer *)ptr;
    if (buf) {
        PyBuffer_Release(buf);
    }
    return 0;
}

static int
addcleanup(void *ptr, freelist_t *freelist, destr_t destructor)
{
    int index;

    index = freelist->first_available;
    freelist->first_available += 1;

    freelist->entries[index].item = ptr;
    freelist->entries[index].destructor = destructor;

    return 0;
}

static int
cleanreturn(int retval, freelist_t *freelist)
{
    int index;

    if (retval == 0) {
      /* A failure occurred, therefore execute all of the cleanup
         functions.
      */
      for (index = 0; index < freelist->first_available; ++index) {
          freelist->entries[index].destructor(NULL,
                                              freelist->entries[index].item);
      }
    }
    if (freelist->entries_malloced)
        PyMem_FREE(freelist->entries);
    return retval;
}


static int
vgetargs1_impl(PyObject *compat_args, PyObject *const *stack, Py_ssize_t nargs, const char *format,
               va_list *p_va, int flags)
{
    char msgbuf[256];
    int levels[32];
    const char *fname = NULL;
    const char *message = NULL;
    int min = -1;
    int max = 0;
    int level = 0;
    int endfmt = 0;
    const char *formatsave = format;
    Py_ssize_t i;
    const char *msg;
    int compat = flags & FLAG_COMPAT;
    freelistentry_t static_entries[STATIC_FREELIST_ENTRIES];
    freelist_t freelist;

    assert(nargs == 0 || stack != NULL);

    freelist.entries = static_entries;
    freelist.first_available = 0;
    freelist.entries_malloced = 0;

    flags = flags & ~FLAG_COMPAT;

    while (endfmt == 0) {
        int c = *format++;
        switch (c) {
        case '(':
            if (level == 0)
                max++;
            level++;
            if (level >= 30)
                Py_FatalError("too many tuple nesting levels "
                              "in argument format string");
            break;
        case ')':
            if (level == 0)
                Py_FatalError("excess ')' in getargs format");
            else
                level--;
            break;
        case '\0':
            endfmt = 1;
            break;
        case ':':
            fname = format;
            endfmt = 1;
            break;
        case ';':
            message = format;
            endfmt = 1;
            break;
        case '|':
            if (level == 0)
                min = max;
            break;
        default:
            if (level == 0) {
                if (Py_ISALPHA(c))
                    if (c != 'e') /* skip encoded */
                        max++;
            }
            break;
        }
    }

    if (level != 0)
        Py_FatalError(/* '(' */ "missing ')' in getargs format");

    if (min < 0)
        min = max;

    format = formatsave;

    if (max > STATIC_FREELIST_ENTRIES) {
        freelist.entries = PyMem_NEW(freelistentry_t, max);
        if (freelist.entries == NULL) {
            PyErr_NoMemory();
            return 0;
        }
        freelist.entries_malloced = 1;
    }

    if (compat) {
        if (max == 0) {
            if (compat_args == NULL)
                return 1;
            PyErr_Format(PyExc_TypeError,
                         "%.200s%s takes no arguments",
                         fname==NULL ? "function" : fname,
                         fname==NULL ? "" : "()");
            return cleanreturn(0, &freelist);
        }
        else if (min == 1 && max == 1) {
            if (compat_args == NULL) {
                PyErr_Format(PyExc_TypeError,
                             "%.200s%s takes at least one argument",
                             fname==NULL ? "function" : fname,
                             fname==NULL ? "" : "()");
                return cleanreturn(0, &freelist);
            }
            msg = convertitem(compat_args, &format, p_va, flags, levels,
                              msgbuf, sizeof(msgbuf), &freelist);
            if (msg == NULL)
                return cleanreturn(1, &freelist);
            seterror(levels[0], msg, levels+1, fname, message);
            return cleanreturn(0, &freelist);
        }
        else {
            PyErr_SetString(PyExc_SystemError,
                "old style getargs format uses new features");
            return cleanreturn(0, &freelist);
        }
    }

    if (nargs < min || max < nargs) {
        if (message == NULL)
            PyErr_Format(PyExc_TypeError,
                         "%.150s%s takes %s %d argument%s (%zd given)",
                         fname==NULL ? "function" : fname,
                         fname==NULL ? "" : "()",
                         min==max ? "exactly"
                         : nargs < min ? "at least" : "at most",
                         nargs < min ? min : max,
                         (nargs < min ? min : max) == 1 ? "" : "s",
                         nargs);
        else
            PyErr_SetString(PyExc_TypeError, message);
        return cleanreturn(0, &freelist);
    }

    for (i = 0; i < nargs; i++) {
        if (*format == '|')
            format++;
        msg = convertitem(stack[i], &format, p_va,
                          flags, levels, msgbuf,
                          sizeof(msgbuf), &freelist);
        if (msg) {
            seterror(i+1, msg, levels, fname, message);
            return cleanreturn(0, &freelist);
        }
    }

    if (*format != '\0' && !Py_ISALPHA(*format) &&
        *format != '(' &&
        *format != '|' && *format != ':' && *format != ';') {
        PyErr_Format(PyExc_SystemError,
                     "bad format string: %.200s", formatsave);
        return cleanreturn(0, &freelist);
    }

    return cleanreturn(1, &freelist);
}

static int
vgetargs1(PyObject *args, const char *format, va_list *p_va, int flags)
{
    PyObject **stack;
    Py_ssize_t nargs;

    if (!(flags & FLAG_COMPAT)) {
        assert(args != NULL);

        if (!PyTuple_Check(args)) {
            PyErr_SetString(PyExc_SystemError,
                "new style getargs format but argument is not a tuple");
            return 0;
        }

        stack = _PyTuple_ITEMS(args);
        nargs = PyTuple_GET_SIZE(args);
    }
    else {
        stack = NULL;
        nargs = 0;
    }

    return vgetargs1_impl(args, stack, nargs, format, p_va, flags);
}


static void
seterror(Py_ssize_t iarg, const char *msg, int *levels, const char *fname,
         const char *message)
{
    char buf[512];
    int i;
    char *p = buf;

    if (PyErr_Occurred())
        return;
    else if (message == NULL) {
        if (fname != NULL) {
            PyOS_snprintf(p, sizeof(buf), "%.200s() ", fname);
            p += strlen(p);
        }
        if (iarg != 0) {
            PyOS_snprintf(p, sizeof(buf) - (p - buf),
                          "argument %" PY_FORMAT_SIZE_T "d", iarg);
            i = 0;
            p += strlen(p);
            while (i < 32 && levels[i] > 0 && (int)(p-buf) < 220) {
                PyOS_snprintf(p, sizeof(buf) - (p - buf),
                              ", item %d", levels[i]-1);
                p += strlen(p);
                i++;
            }
        }
        else {
            PyOS_snprintf(p, sizeof(buf) - (p - buf), "argument");
            p += strlen(p);
        }
        PyOS_snprintf(p, sizeof(buf) - (p - buf), " %.256s", msg);
        message = buf;
    }
    if (msg[0] == '(') {
        PyErr_SetString(PyExc_SystemError, message);
    }
    else {
        PyErr_SetString(PyExc_TypeError, message);
    }
}


/* Convert a tuple argument.
   On entry, *p_format points to the character _after_ the opening '('.
   On successful exit, *p_format points to the closing ')'.
   If successful:
      *p_format and *p_va are updated,
      *levels and *msgbuf are untouched,
      and NULL is returned.
   If the argument is invalid:
      *p_format is unchanged,
      *p_va is undefined,
      *levels is a 0-terminated list of item numbers,
      *msgbuf contains an error message, whose format is:
     "must be <typename1>, not <typename2>", where:
        <typename1> is the name of the expected type, and
        <typename2> is the name of the actual type,
      and msgbuf is returned.
*/

static const char *
converttuple(PyObject *arg, const char **p_format, va_list *p_va, int flags,
             int *levels, char *msgbuf, size_t bufsize, int toplevel,
             freelist_t *freelist)
{
    int level = 0;
    int n = 0;
    const char *format = *p_format;
    int i;
    Py_ssize_t len;

    for (;;) {
        int c = *format++;
        if (c == '(') {
            if (level == 0)
                n++;
            level++;
        }
        else if (c == ')') {
            if (level == 0)
                break;
            level--;
        }
        else if (c == ':' || c == ';' || c == '\0')
            break;
        else if (level == 0 && Py_ISALPHA(c))
            n++;
    }

    if (!PySequence_Check(arg) || PyBytes_Check(arg)) {
        levels[0] = 0;
        PyOS_snprintf(msgbuf, bufsize,
                      toplevel ? "expected %d arguments, not %.50s" :
                      "must be %d-item sequence, not %.50s",
                  n,
                  arg == Py_None ? "None" : arg->ob_type->tp_name);
        return msgbuf;
    }

    len = PySequence_Size(arg);
    if (len != n) {
        levels[0] = 0;
        if (toplevel) {
            PyOS_snprintf(msgbuf, bufsize,
                          "expected %d argument%s, not %" PY_FORMAT_SIZE_T "d",
                          n,
                          n == 1 ? "" : "s",
                          len);
        }
        else {
            PyOS_snprintf(msgbuf, bufsize,
                          "must be sequence of length %d, "
                          "not %" PY_FORMAT_SIZE_T "d",
                          n, len);
        }
        return msgbuf;
    }

    format = *p_format;
    for (i = 0; i < n; i++) {
        const char *msg;
        PyObject *item;
        item = PySequence_GetItem(arg, i);
        if (item == NULL) {
            PyErr_Clear();
            levels[0] = i+1;
            levels[1] = 0;
            strncpy(msgbuf, "is not retrievable", bufsize);
            return msgbuf;
        }
        msg = convertitem(item, &format, p_va, flags, levels+1,
                          msgbuf, bufsize, freelist);
        /* PySequence_GetItem calls tp->sq_item, which INCREFs */
        Py_XDECREF(item);
        if (msg != NULL) {
            levels[0] = i+1;
            return msg;
        }
    }

    *p_format = format;
    return NULL;
}


/* Convert a single item. */

static const char *
convertitem(PyObject *arg, const char **p_format, va_list *p_va, int flags,
            int *levels, char *msgbuf, size_t bufsize, freelist_t *freelist)
{
    const char *msg;
    const char *format = *p_format;

    if (*format == '(' /* ')' */) {
        format++;
        msg = converttuple(arg, &format, p_va, flags, levels, msgbuf,
                           bufsize, 0, freelist);
        if (msg == NULL)
            format++;
    }
    else {
        msg = convertsimple(arg, &format, p_va, flags,
                            msgbuf, bufsize, freelist);
        if (msg != NULL)
            levels[0] = 0;
    }
    if (msg == NULL)
        *p_format = format;
    return msg;
}



/* Format an error message generated by convertsimple().
   displayname must be UTF-8 encoded.
*/

void
_PyArg_BadArgument(const char *fname, const char *displayname,
                   const char *expected, PyObject *arg)
{
    PyErr_Format(PyExc_TypeError,
                 "%.200s() %.200s must be %.50s, not %.50s",
                 fname, displayname, expected,
                 arg == Py_None ? "None" : arg->ob_type->tp_name);
}

static const char *
converterr(const char *expected, PyObject *arg, char *msgbuf, size_t bufsize)
{
    assert(expected != NULL);
    assert(arg != NULL);
    if (expected[0] == '(') {
        PyOS_snprintf(msgbuf, bufsize,
                      "%.100s", expected);
    }
    else {
        PyOS_snprintf(msgbuf, bufsize,
                      "must be %.50s, not %.50s", expected,
                      arg == Py_None ? "None" : arg->ob_type->tp_name);
    }
    return msgbuf;
}

#define CONV_UNICODE "(unicode conversion error)"

/* Explicitly check for float arguments when integers are expected.
   Return 1 for error, 0 if ok.
   XXX Should be removed after the end of the deprecation period in
   _PyLong_FromNbIndexOrNbInt. */
static int
float_argument_error(PyObject *arg)
{
    if (PyFloat_Check(arg)) {
        PyErr_SetString(PyExc_TypeError,
                        "integer argument expected, got float" );
        return 1;
    }
    else
        return 0;
}

/* Convert a non-tuple argument.  Return NULL if conversion went OK,
   or a string with a message describing the failure.  The message is
   formatted as "must be <desired type>, not <actual type>".
   When failing, an exception may or may not have been raised.
   Don't call if a tuple is expected.

   When you add new format codes, please don't forget poor skipitem() below.
*/

static const char *
convertsimple(PyObject *arg, const char **p_format, va_list *p_va, int flags,
              char *msgbuf, size_t bufsize, freelist_t *freelist)
{
    /* For # codes */
#define FETCH_SIZE      int *q=NULL;Py_ssize_t *q2=NULL;\
    if (flags & FLAG_SIZE_T) q2=va_arg(*p_va, Py_ssize_t*); \
    else { \
        if (PyErr_WarnEx(PyExc_DeprecationWarning, \
                    "PY_SSIZE_T_CLEAN will be required for '#' formats", 1)) { \
            return NULL; \
        } \
        q=va_arg(*p_va, int*); \
    }
#define STORE_SIZE(s)   \
    if (flags & FLAG_SIZE_T) \
        *q2=s; \
    else { \
        if (INT_MAX < s) { \
            PyErr_SetString(PyExc_OverflowError, \
                "size does not fit in an int"); \
            return converterr("", arg, msgbuf, bufsize); \
        } \
        *q = (int)s; \
    }
#define BUFFER_LEN      ((flags & FLAG_SIZE_T) ? *q2:*q)
#define RETURN_ERR_OCCURRED return msgbuf

    const char *format = *p_format;
    char c = *format++;
    const char *sarg;

    switch (c) {

    case 'b': { /* unsigned byte -- very short int */
        char *p = va_arg(*p_va, char *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsLong(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else if (ival < 0) {
            PyErr_SetString(PyExc_OverflowError,
                            "unsigned byte integer is less than minimum");
            RETURN_ERR_OCCURRED;
        }
        else if (ival > UCHAR_MAX) {
            PyErr_SetString(PyExc_OverflowError,
                            "unsigned byte integer is greater than maximum");
            RETURN_ERR_OCCURRED;
        }
        else
            *p = (unsigned char) ival;
        break;
    }

    case 'B': {/* byte sized bitfield - both signed and unsigned
                  values allowed */
        char *p = va_arg(*p_va, char *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsUnsignedLongMask(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = (unsigned char) ival;
        break;
    }

    case 'h': {/* signed short int */
        short *p = va_arg(*p_va, short *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsLong(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else if (ival < SHRT_MIN) {
            PyErr_SetString(PyExc_OverflowError,
                            "signed short integer is less than minimum");
            RETURN_ERR_OCCURRED;
        }
        else if (ival > SHRT_MAX) {
            PyErr_SetString(PyExc_OverflowError,
                            "signed short integer is greater than maximum");
            RETURN_ERR_OCCURRED;
        }
        else
            *p = (short) ival;
        break;
    }

    case 'H': { /* short int sized bitfield, both signed and
                   unsigned allowed */
        unsigned short *p = va_arg(*p_va, unsigned short *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsUnsignedLongMask(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = (unsigned short) ival;
        break;
    }

    case 'i': {/* signed int */
        int *p = va_arg(*p_va, int *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsLong(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else if (ival > INT_MAX) {
            PyErr_SetString(PyExc_OverflowError,
                            "signed integer is greater than maximum");
            RETURN_ERR_OCCURRED;
        }
        else if (ival < INT_MIN) {
            PyErr_SetString(PyExc_OverflowError,
                            "signed integer is less than minimum");
            RETURN_ERR_OCCURRED;
        }
        else
            *p = ival;
        break;
    }

    case 'I': { /* int sized bitfield, both signed and
                   unsigned allowed */
        unsigned int *p = va_arg(*p_va, unsigned int *);
        unsigned int ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = (unsigned int)PyLong_AsUnsignedLongMask(arg);
        if (ival == (unsigned int)-1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = ival;
        break;
    }

    case 'n': /* Py_ssize_t */
    {
        PyObject *iobj;
        Py_ssize_t *p = va_arg(*p_va, Py_ssize_t *);
        Py_ssize_t ival = -1;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        iobj = PyNumber_Index(arg);
        if (iobj != NULL) {
            ival = PyLong_AsSsize_t(iobj);
            Py_DECREF(iobj);
        }
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        *p = ival;
        break;
    }
    case 'l': {/* long int */
        long *p = va_arg(*p_va, long *);
        long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsLong(arg);
        if (ival == -1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = ival;
        break;
    }

    case 'k': { /* long sized bitfield */
        unsigned long *p = va_arg(*p_va, unsigned long *);
        unsigned long ival;
        if (PyLong_Check(arg))
            ival = PyLong_AsUnsignedLongMask(arg);
        else
            return converterr("int", arg, msgbuf, bufsize);
        *p = ival;
        break;
    }

    case 'L': {/* long long */
        long long *p = va_arg( *p_va, long long * );
        long long ival;
        if (float_argument_error(arg))
            RETURN_ERR_OCCURRED;
        ival = PyLong_AsLongLong(arg);
        if (ival == (long long)-1 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = ival;
        break;
    }

    case 'K': { /* long long sized bitfield */
        unsigned long long *p = va_arg(*p_va, unsigned long long *);
        unsigned long long ival;
        if (PyLong_Check(arg))
            ival = PyLong_AsUnsignedLongLongMask(arg);
        else
            return converterr("int", arg, msgbuf, bufsize);
        *p = ival;
        break;
    }

    case 'f': {/* float */
        float *p = va_arg(*p_va, float *);
        double dval = PyFloat_AsDouble(arg);
        if (dval == -1.0 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = (float) dval;
        break;
    }

    case 'd': {/* double */
        double *p = va_arg(*p_va, double *);
        double dval = PyFloat_AsDouble(arg);
        if (dval == -1.0 && PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = dval;
        break;
    }

    case 'D': {/* complex double */
        Py_complex *p = va_arg(*p_va, Py_complex *);
        Py_complex cval;
        cval = PyComplex_AsCComplex(arg);
        if (PyErr_Occurred())
            RETURN_ERR_OCCURRED;
        else
            *p = cval;
        break;
    }

    case 'c': {/* char */
        char *p = va_arg(*p_va, char *);
        if (PyBytes_Check(arg) && PyBytes_Size(arg) == 1)
            *p = PyBytes_AS_STRING(arg)[0];
        else if (PyByteArray_Check(arg) && PyByteArray_Size(arg) == 1)
            *p = PyByteArray_AS_STRING(arg)[0];
        else
            return converterr("a byte string of length 1", arg, msgbuf, bufsize);
        break;
    }

    case 'C': {/* unicode char */
        int *p = va_arg(*p_va, int *);
        int kind;
        void *data;

        if (!PyUnicode_Check(arg))
            return converterr("a unicode character", arg, msgbuf, bufsize);

        if (PyUnicode_READY(arg))
            RETURN_ERR_OCCURRED;

        if (PyUnicode_GET_LENGTH(arg) != 1)
            return converterr("a unicode character", arg, msgbuf, bufsize);

        kind = PyUnicode_KIND(arg);
        data = PyUnicode_DATA(arg);
        *p = PyUnicode_READ(kind, data, 0);
        break;
    }

    case 'p': {/* boolean *p*redicate */
        int *p = va_arg(*p_va, int *);
        int val = PyObject_IsTrue(arg);
        if (val > 0)
            *p = 1;
        else if (val == 0)
            *p = 0;
        else
            RETURN_ERR_OCCURRED;
        break;
    }

    /* XXX WAAAAH!  's', 'y', 'z', 'u', 'Z', 'e', 'w' codes all
       need to be cleaned up! */

    case 'y': {/* any bytes-like object */
        void **p = (void **)va_arg(*p_va, char **);
        const char *buf;
        Py_ssize_t count;
        if (*format == '*') {
            if (getbuffer(arg, (Py_buffer*)p, &buf) < 0)
                return converterr(buf, arg, msgbuf, bufsize);
            format++;
            if (addcleanup(p, freelist, cleanup_buffer)) {
                return converterr(
                    "(cleanup problem)",
                    arg, msgbuf, bufsize);
            }
            break;
        }
        count = convertbuffer(arg, (const void **)p, &buf);
        if (count < 0)
            return converterr(buf, arg, msgbuf, bufsize);
        if (*format == '#') {
            FETCH_SIZE;
            STORE_SIZE(count);
            format++;
        } else {
            if (strlen(*p) != (size_t)count) {
                PyErr_SetString(PyExc_ValueError, "embedded null byte");
                RETURN_ERR_OCCURRED;
            }
        }
        break;
    }

    case 's': /* text string or bytes-like object */
    case 'z': /* text string, bytes-like object or None */
    {
        if (*format == '*') {
            /* "s*" or "z*" */
            Py_buffer *p = (Py_buffer *)va_arg(*p_va, Py_buffer *);

            if (c == 'z' && arg == Py_None)
                PyBuffer_FillInfo(p, NULL, NULL, 0, 1, 0);
            else if (PyUnicode_Check(arg)) {
                Py_ssize_t len;
                sarg = PyUnicode_AsUTF8AndSize(arg, &len);
                if (sarg == NULL)
                    return converterr(CONV_UNICODE,
                                      arg, msgbuf, bufsize);
                PyBuffer_FillInfo(p, arg, (void *)sarg, len, 1, 0);
            }
            else { /* any bytes-like object */
                const char *buf;
                if (getbuffer(arg, p, &buf) < 0)
                    return converterr(buf, arg, msgbuf, bufsize);
            }
            if (addcleanup(p, freelist, cleanup_buffer)) {
                return converterr(
                    "(cleanup problem)",
                    arg, msgbuf, bufsize);
            }
            format++;
        } else if (*format == '#') { /* a string or read-only bytes-like object */
            /* "s#" or "z#" */
            const void **p = (const void **)va_arg(*p_va, const char **);
            FETCH_SIZE;

            if (c == 'z' && arg == Py_None) {
                *p = NULL;
                STORE_SIZE(0);
            }
            else if (PyUnicode_Check(arg)) {
                Py_ssize_t len;
                sarg = PyUnicode_AsUTF8AndSize(arg, &len);
                if (sarg == NULL)
                    return converterr(CONV_UNICODE,
                                      arg, msgbuf, bufsize);
                *p = sarg;
                STORE_SIZE(len);
            }
            else { /* read-only bytes-like object */
                /* XXX Really? */
                const char *buf;
                Py_ssize_t count = convertbuffer(arg, p, &buf);
                if (count < 0)
                    return converterr(buf, arg, msgbuf, bufsize);
                STORE_SIZE(count);
            }
            format++;
        } else {
            /* "s" or "z" */
            const char **p = va_arg(*p_va, const char **);
            Py_ssize_t len;
            sarg = NULL;

            if (c == 'z' && arg == Py_None)
                *p = NULL;
            else if (PyUnicode_Check(arg)) {
                sarg = PyUnicode_AsUTF8AndSize(arg, &len);
                if (sarg == NULL)
                    return converterr(CONV_UNICODE,
                                      arg, msgbuf, bufsize);
                if (strlen(sarg) != (size_t)len) {
                    PyErr_SetString(PyExc_ValueError, "embedded null character");
                    RETURN_ERR_OCCURRED;
                }
                *p = sarg;
            }
            else
                return converterr(c == 'z' ? "str or None" : "str",
                                  arg, msgbuf, bufsize);
        }
        break;
    }

    case 'u': /* raw unicode buffer (Py_UNICODE *) */
    case 'Z': /* raw unicode buffer or None */
    {
        Py_UNICODE **p = va_arg(*p_va, Py_UNICODE **);

        if (*format == '#') {
            /* "u#" or "Z#" */
            FETCH_SIZE;

            if (c == 'Z' && arg == Py_None) {
                *p = NULL;
                STORE_SIZE(0);
            }
            else if (PyUnicode_Check(arg)) {
                Py_ssize_t len;
                *p = PyUnicode_AsUnicodeAndSize(arg, &len);
                if (*p == NULL)
                    RETURN_ERR_OCCURRED;
                STORE_SIZE(len);
            }
            else
                return converterr(c == 'Z' ? "str or None" : "str",
                                  arg, msgbuf, bufsize);
            format++;
        } else {
            /* "u" or "Z" */
            if (c == 'Z' && arg == Py_None)
                *p = NULL;
            else if (PyUnicode_Check(arg)) {
                Py_ssize_t len;
                *p = PyUnicode_AsUnicodeAndSize(arg, &len);
                if (*p == NULL)
                    RETURN_ERR_OCCURRED;
                if (wcslen(*p) != (size_t)len) {
                    PyErr_SetString(PyExc_ValueError, "embedded null character");
                    RETURN_ERR_OCCURRED;
                }
            } else
                return converterr(c == 'Z' ? "str or None" : "str",
                                  arg, msgbuf, bufsize);
        }
        break;
    }

    case 'e': {/* encoded string */
        char **buffer;
        const char *encoding;
        PyObject *s;
        int recode_strings;
        Py_ssize_t size;
        const char *ptr;

        /* Get 'e' parameter: the encoding name */
        encoding = (const char *)va_arg(*p_va, const char *);
        if (encoding == NULL)
            encoding = PyUnicode_GetDefaultEncoding();

        /* Get output buffer parameter:
           's' (recode all objects via Unicode) or
           't' (only recode non-string objects)
        */
        if (*format == 's')
            recode_strings = 1;
        else if (*format == 't')
            recode_strings = 0;
        else
            return converterr(
                "(unknown parser marker combination)",
                arg, msgbuf, bufsize);
        buffer = (char **)va_arg(*p_va, char **);
        format++;
        if (buffer == NULL)
            return converterr("(buffer is NULL)",
                              arg, msgbuf, bufsize);

        /* Encode object */
        if (!recode_strings &&
            (PyBytes_Check(arg) || PyByteArray_Check(arg))) {
            s = arg;
            Py_INCREF(s);
            if (PyBytes_Check(arg)) {
                size = PyBytes_GET_SIZE(s);
                ptr = PyBytes_AS_STRING(s);
            }
            else {
                size = PyByteArray_GET_SIZE(s);
                ptr = PyByteArray_AS_STRING(s);
            }
        }
        else if (PyUnicode_Check(arg)) {
            /* Encode object; use default error handling */
            s = PyUnicode_AsEncodedString(arg,
                                          encoding,
                                          NULL);
            if (s == NULL)
                return converterr("(encoding failed)",
                                  arg, msgbuf, bufsize);
            assert(PyBytes_Check(s));
            size = PyBytes_GET_SIZE(s);
            ptr = PyBytes_AS_STRING(s);
            if (ptr == NULL)
                ptr = "";
        }
        else {
            return converterr(
                recode_strings ? "str" : "str, bytes or bytearray",
                arg, msgbuf, bufsize);
        }

        /* Write output; output is guaranteed to be 0-terminated */
        if (*format == '#') {
            /* Using buffer length parameter '#':

               - if *buffer is NULL, a new buffer of the
               needed size is allocated and the data
               copied into it; *buffer is updated to point
               to the new buffer; the caller is
               responsible for PyMem_Free()ing it after
               usage

               - if *buffer is not NULL, the data is
               copied to *buffer; *buffer_len has to be
               set to the size of the buffer on input;
               buffer overflow is signalled with an error;
               buffer has to provide enough room for the
               encoded string plus the trailing 0-byte

               - in both cases, *buffer_len is updated to
               the size of the buffer /excluding/ the
               trailing 0-byte

            */
            int *q = NULL; Py_ssize_t *q2 = NULL;
            if (flags & FLAG_SIZE_T) {
                q2 = va_arg(*p_va, Py_ssize_t*);
            }
            else {
                if (PyErr_WarnEx(PyExc_DeprecationWarning,
                            "PY_SSIZE_T_CLEAN will be required for '#' formats", 1))
                {
                    Py_DECREF(s);
                    return NULL;
                }
                q = va_arg(*p_va, int*);
            }

            format++;
            if (q == NULL && q2 == NULL) {
                Py_DECREF(s);
                return converterr(
                    "(buffer_len is NULL)",
                    arg, msgbuf, bufsize);
            }
            if (*buffer == NULL) {
                *buffer = PyMem_NEW(char, size + 1);
                if (*buffer == NULL) {
                    Py_DECREF(s);
                    PyErr_NoMemory();
                    RETURN_ERR_OCCURRED;
                }
                if (addcleanup(*buffer, freelist, cleanup_ptr)) {
                    Py_DECREF(s);
                    return converterr(
                        "(cleanup problem)",
                        arg, msgbuf, bufsize);
                }
            } else {
                if (size + 1 > BUFFER_LEN) {
                    Py_DECREF(s);
                    PyErr_Format(PyExc_ValueError,
                                 "encoded string too long "
                                 "(%zd, maximum length %zd)",
                                 (Py_ssize_t)size, (Py_ssize_t)(BUFFER_LEN-1));
                    RETURN_ERR_OCCURRED;
                }
            }
            memcpy(*buffer, ptr, size+1);

            if (flags & FLAG_SIZE_T) {
                *q2 = size;
            }
            else {
                if (INT_MAX < size) {
                    Py_DECREF(s);
                    PyErr_SetString(PyExc_OverflowError,
                                    "size does not fit in an int");
                    return converterr("", arg, msgbuf, bufsize);
                }
                *q = (int)size;
            }
        } else {
            /* Using a 0-terminated buffer:

               - the encoded string has to be 0-terminated
               for this variant to work; if it is not, an
               error raised

               - a new buffer of the needed size is
               allocated and the data copied into it;
               *buffer is updated to point to the new
               buffer; the caller is responsible for
               PyMem_Free()ing it after usage

            */
            if ((Py_ssize_t)strlen(ptr) != size) {
                Py_DECREF(s);
                return converterr(
                    "encoded string without null bytes",
                    arg, msgbuf, bufsize);
            }
            *buffer = PyMem_NEW(char, size + 1);
            if (*buffer == NULL) {
                Py_DECREF(s);
                PyErr_NoMemory();
                RETURN_ERR_OCCURRED;
            }
            if (addcleanup(*buffer, freelist, cleanup_ptr)) {
                Py_DECREF(s);
                return converterr("(cleanup problem)",
                                arg, msgbuf, bufsize);
            }
            memcpy(*buffer, ptr, size+1);
        }
        Py_DECREF(s);
        break;
    }

    case 'S': { /* PyBytes object */
        PyObject **p = va_arg(*p_va, PyObject **);
        if (PyBytes_Check(arg))
            *p = arg;
        else
            return converterr("bytes", arg, msgbuf, bufsize);
        break;
    }

    case 'Y': { /* PyByteArray object */
        PyObject **p = va_arg(*p_va, PyObject **);
        if (PyByteArray_Check(arg))
            *p = arg;
        else
            return converterr("bytearray", arg, msgbuf, bufsize);
        break;
    }

    case 'U': { /* PyUnicode object */
        PyObject **p = va_arg(*p_va, PyObject **);
        if (PyUnicode_Check(arg)) {
            if (PyUnicode_READY(arg) == -1)
                RETURN_ERR_OCCURRED;
            *p = arg;
        }
        else
            return converterr("str", arg, msgbuf, bufsize);
        break;
    }

    case 'O': { /* object */
        PyTypeObject *type;
        PyObject **p;
        if (*format == '!') {
            type = va_arg(*p_va, PyTypeObject*);
            p = va_arg(*p_va, PyObject **);
            format++;
            if (PyType_IsSubtype(arg->ob_type, type))
                *p = arg;
            else
                return converterr(type->tp_name, arg, msgbuf, bufsize);

        }
        else if (*format == '&') {
            typedef int (*converter)(PyObject *, void *);
            converter convert = va_arg(*p_va, converter);
            void *addr = va_arg(*p_va, void *);
            int res;
            format++;
            if (! (res = (*convert)(arg, addr)))
                return converterr("(unspecified)",
                                  arg, msgbuf, bufsize);
            if (res == Py_CLEANUP_SUPPORTED &&
                addcleanup(addr, freelist, convert) == -1)
                return converterr("(cleanup problem)",
                                arg, msgbuf, bufsize);
        }
        else {
            p = va_arg(*p_va, PyObject **);
            *p = arg;
        }
        break;
    }


    case 'w': { /* "w*": memory buffer, read-write access */
        void **p = va_arg(*p_va, void **);

        if (*format != '*')
            return converterr(
                "(invalid use of 'w' format character)",
                arg, msgbuf, bufsize);
        format++;

        /* Caller is interested in Py_buffer, and the object
           supports it directly. */
        if (PyObject_GetBuffer(arg, (Py_buffer*)p, PyBUF_WRITABLE) < 0) {
            PyErr_Clear();
            return converterr("read-write bytes-like object",
                              arg, msgbuf, bufsize);
        }
        if (!PyBuffer_IsContiguous((Py_buffer*)p, 'C')) {
            PyBuffer_Release((Py_buffer*)p);
            return converterr("contiguous buffer", arg, msgbuf, bufsize);
        }
        if (addcleanup(p, freelist, cleanup_buffer)) {
            return converterr(
                "(cleanup problem)",
                arg, msgbuf, bufsize);
        }
        break;
    }

    default:
        return converterr("(impossible<bad format char>)", arg, msgbuf, bufsize);

    }

    *p_format = format;
    return NULL;

#undef FETCH_SIZE
#undef STORE_SIZE
#undef BUFFER_LEN
#undef RETURN_ERR_OCCURRED
}

static Py_ssize_t
convertbuffer(PyObject *arg, const void **p, const char **errmsg)
{
    PyBufferProcs *pb = Py_TYPE(arg)->tp_as_buffer;
    Py_ssize_t count;
    Py_buffer view;

    *errmsg = NULL;
    *p = NULL;
    if (pb != NULL && pb->bf_releasebuffer != NULL) {
        *errmsg = "read-only bytes-like object";
        return -1;
    }

    if (getbuffer(arg, &view, errmsg) < 0)
        return -1;
    count = view.len;
    *p = view.buf;
    PyBuffer_Release(&view);
    return count;
}

static int
getbuffer(PyObject *arg, Py_buffer *view, const char **errmsg)
{
    if (PyObject_GetBuffer(arg, view, PyBUF_SIMPLE) != 0) {
        *errmsg = "bytes-like object";
        return -1;
    }
    if (!PyBuffer_IsContiguous(view, 'C')) {
        PyBuffer_Release(view);
        *errmsg = "contiguous buffer";
        return -1;
    }
    return 0;
}

/* Support for keyword arguments donated by
   Geoff Philbrick <philbric@delphi.hks.com> */

/* Return false (0) for error, else true. */
int
PyArg_ParseTupleAndKeywords(PyObject *args,
                            PyObject *keywords,
                            const char *format,
                            char **kwlist, ...)
{
    int retval;
    va_list va;

    if ((args == NULL || !PyTuple_Check(args)) ||
        (keywords != NULL && !PyDict_Check(keywords)) ||
        format == NULL ||
        kwlist == NULL)
    {
        PyErr_BadInternalCall();
        return 0;
    }

    va_start(va, kwlist);
    retval = vgetargskeywords(args, keywords, format, kwlist, &va, 0);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseTupleAndKeywords_SizeT(PyObject *args,
                                  PyObject *keywords,
                                  const char *format,
                                  char **kwlist, ...)
{
    int retval;
    va_list va;

    if ((args == NULL || !PyTuple_Check(args)) ||
        (keywords != NULL && !PyDict_Check(keywords)) ||
        format == NULL ||
        kwlist == NULL)
    {
        PyErr_BadInternalCall();
        return 0;
    }

    va_start(va, kwlist);
    retval = vgetargskeywords(args, keywords, format,
                              kwlist, &va, FLAG_SIZE_T);
    va_end(va);
    return retval;
}


int
PyArg_VaParseTupleAndKeywords(PyObject *args,
                              PyObject *keywords,
                              const char *format,
                              char **kwlist, va_list va)
{
    int retval;
    va_list lva;

    if ((args == NULL || !PyTuple_Check(args)) ||
        (keywords != NULL && !PyDict_Check(keywords)) ||
        format == NULL ||
        kwlist == NULL)
    {
        PyErr_BadInternalCall();
        return 0;
    }

    va_copy(lva, va);

    retval = vgetargskeywords(args, keywords, format, kwlist, &lva, 0);
    va_end(lva);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_VaParseTupleAndKeywords_SizeT(PyObject *args,
                                    PyObject *keywords,
                                    const char *format,
                                    char **kwlist, va_list va)
{
    int retval;
    va_list lva;

    if ((args == NULL || !PyTuple_Check(args)) ||
        (keywords != NULL && !PyDict_Check(keywords)) ||
        format == NULL ||
        kwlist == NULL)
    {
        PyErr_BadInternalCall();
        return 0;
    }

    va_copy(lva, va);

    retval = vgetargskeywords(args, keywords, format,
                              kwlist, &lva, FLAG_SIZE_T);
    va_end(lva);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseTupleAndKeywordsFast(PyObject *args, PyObject *keywords,
                            struct _PyArg_Parser *parser, ...)
{
    int retval;
    va_list va;

    va_start(va, parser);
    retval = vgetargskeywordsfast(args, keywords, parser, &va, 0);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseTupleAndKeywordsFast_SizeT(PyObject *args, PyObject *keywords,
                            struct _PyArg_Parser *parser, ...)
{
    int retval;
    va_list va;

    va_start(va, parser);
    retval = vgetargskeywordsfast(args, keywords, parser, &va, FLAG_SIZE_T);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseStackAndKeywords(PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames,
                  struct _PyArg_Parser *parser, ...)
{
    int retval;
    va_list va;

    va_start(va, parser);
    retval = vgetargskeywordsfast_impl(args, nargs, NULL, kwnames, parser, &va, 0);
    va_end(va);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_ParseStackAndKeywords_SizeT(PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames,
                        struct _PyArg_Parser *parser, ...)
{
    int retval;
    va_list va;

    va_start(va, parser);
    retval = vgetargskeywordsfast_impl(args, nargs, NULL, kwnames, parser, &va, FLAG_SIZE_T);
    va_end(va);
    return retval;
}


PyAPI_FUNC(int)
_PyArg_VaParseTupleAndKeywordsFast(PyObject *args, PyObject *keywords,
                            struct _PyArg_Parser *parser, va_list va)
{
    int retval;
    va_list lva;

    va_copy(lva, va);

    retval = vgetargskeywordsfast(args, keywords, parser, &lva, 0);
    va_end(lva);
    return retval;
}

PyAPI_FUNC(int)
_PyArg_VaParseTupleAndKeywordsFast_SizeT(PyObject *args, PyObject *keywords,
                            struct _PyArg_Parser *parser, va_list va)
{
    int retval;
    va_list lva;

    va_copy(lva, va);

    retval = vgetargskeywordsfast(args, keywords, parser, &lva, FLAG_SIZE_T);
    va_end(lva);
    return retval;
}

int
PyArg_ValidateKeywordArguments(PyObject *kwargs)
{
    if (!PyDict_Check(kwargs)) {
        PyErr_BadInternalCall();
        return 0;
    }
    if (!_PyDict_HasOnlyStringKeys(kwargs)) {
        PyErr_SetString(PyExc_TypeError,
                        "keywords must be strings");
        return 0;
    }
    return 1;
}

#define IS_END_OF_FORMAT(c) (c == '\0' || c == ';' || c == ':')

static int
vgetargskeywords(PyObject *args, PyObject *kwargs, const char *format,
                 char **kwlist, va_list *p_va, int flags)
{
    char msgbuf[512];
    int levels[32];
    const char *fname, *msg, *custom_msg;
    int min = INT_MAX;
    int max = INT_MAX;
    int i, pos, len;
    int skip = 0;
    Py_ssize_t nargs, nkwargs;
    PyObject *current_arg;
    freelistentry_t static_entries[STATIC_FREELIST_ENTRIES];
    freelist_t freelist;

    freelist.entries = static_entries;
    freelist.first_available = 0;
    freelist.entries_malloced = 0;

    assert(args != NULL && PyTuple_Check(args));
    assert(kwargs == NULL || PyDict_Check(kwargs));
    assert(format != NULL);
    assert(kwlist != NULL);
    assert(p_va != NULL);

    /* grab the function name or custom error msg first (mutually exclusive) */
    fname = strchr(format, ':');
    if (fname) {
        fname++;
        custom_msg = NULL;
    }
    else {
        custom_msg = strchr(format,';');
        if (custom_msg)
            custom_msg++;
    }

    /* scan kwlist and count the number of positional-only parameters */
    for (pos = 0; kwlist[pos] && !*kwlist[pos]; pos++) {
    }
    /* scan kwlist and get greatest possible nbr of args */
    for (len = pos; kwlist[len]; len++) {
        if (!*kwlist[len]) {
            PyErr_SetString(PyExc_SystemError,
                            "Empty keyword parameter name");
            return cleanreturn(0, &freelist);
        }
    }

    if (len > STATIC_FREELIST_ENTRIES) {
        freelist.entries = PyMem_NEW(freelistentry_t, len);
        if (freelist.entries == NULL) {
            PyErr_NoMemory();
            return 0;
        }
        freelist.entries_malloced = 1;
    }

    nargs = PyTuple_GET_SIZE(args);
    nkwargs = (kwargs == NULL) ? 0 : PyDict_GET_SIZE(kwargs);
    if (nargs + nkwargs > len) {
        /* Adding "keyword" (when nargs == 0) prevents producing wrong error
           messages in some special cases (see bpo-31229). */
        PyErr_Format(PyExc_TypeError,
                     "%.200s%s takes at most %d %sargument%s (%zd given)",
                     (fname == NULL) ? "function" : fname,
                     (fname == NULL) ? "" : "()",
                     len,
                     (nargs == 0) ? "keyword " : "",
                     (len == 1) ? "" : "s",
                     nargs + nkwargs);
        return cleanreturn(0, &freelist);
    }

    /* convert tuple args and keyword args in same loop, using kwlist to drive process */
    for (i = 0; i < len; i++) {
        if (*format == '|') {
            if (min != INT_MAX) {
                PyErr_SetString(PyExc_SystemError,
                                "Invalid format string (| specified twice)");
                return cleanreturn(0, &freelist);
            }

            min = i;
            format++;

            if (max != INT_MAX) {
                PyErr_SetString(PyExc_SystemError,
                                "Invalid format string ($ before |)");
                return cleanreturn(0, &freelist);
            }
        }
        if (*format == '$') {
            if (max != INT_MAX) {
                PyErr_SetString(PyExc_SystemError,
                                "Invalid format string ($ specified twice)");
                return cleanreturn(0, &freelist);
            }

            max = i;
            format++;

            if (max < pos) {
                PyErr_SetString(PyExc_SystemError,
                                "Empty parameter name after $");
                return cleanreturn(0, &freelist);
            }
            if (skip) {
                /* Now we know the minimal and the maximal numbers of
                 * positional arguments and can raise an exception with
                 * informative message (see below). */
                break;
            }
            if (max < nargs) {
                if (max == 0) {
                    PyErr_Format(PyExc_TypeError,
                                 "%.200s%s takes no positional arguments",
                                 (fname == NULL) ? "function" : fname,
                                 (fname == NULL) ? "" : "()");
                }
                else {
                    PyErr_Format(PyExc_TypeError,
                                 "%.200s%s takes %s %d positional argument%s"
                                 " (%zd given)",
                                 (fname == NULL) ? "function" : fname,
                                 (fname == NULL) ? "" : "()",
                                 (min != INT_MAX) ? "at most" : "exactly",
                                 max,
                                 max == 1 ? "" : "s",
                                 nargs);
                }
                return cleanreturn(0, &freelist);
            }
        }
        if (IS_END_OF_FORMAT(*format)) {
            PyErr_Format(PyExc_SystemError,
                         "More keyword list entries (%d) than "
                         "format specifiers (%d)", len, i);
            return cleanreturn(0, &freelist);
        }
        if (!skip) {
            if (i < nargs) {
                current_arg = PyTuple_GET_ITEM(args, i);
            }
            else if (nkwargs && i >= pos) {
                current_arg = _PyDict_GetItemStringWithError(kwargs, kwlist[i]);
                if (current_arg) {
                    --nkwargs;
                }
                else if (PyErr_Occurred()) {
                    return cleanreturn(0, &freelist);
                }
            }
            else {
                current_arg = NULL;
            }

            if (current_arg) {
                msg = convertitem(current_arg, &format, p_va, flags,
                    levels, msgbuf, sizeof(msgbuf), &freelist);
                if (msg) {
                    seterror(i+1, msg, levels, fname, custom_msg);
                    return cleanreturn(0, &freelist);
                }
                continue;
            }

            if (i < min) {
                if (i < pos) {
                    assert (min == INT_MAX);
                    assert (max == INT_MAX);
                    skip = 1;
                    /* At that moment we still don't know the minimal and
                     * the maximal numbers of positional arguments.  Raising
                     * an exception is deferred until we encounter | and $
                     * or the end of the format. */
                }
                else {
                    PyErr_Format(PyExc_TypeError,  "%.200s%s missing required "
                                 "argument '%s' (pos %d)",
                                 (fname == NULL) ? "function" : fname,
                                 (fname == NULL) ? "" : "()",
                                 kwlist[i], i+1);
                    return cleanreturn(0, &freelist);
                }
            }
            /* current code reports success when all required args
             * fulfilled and no keyword args left, with no further
             * validation. XXX Maybe skip this in debug build ?
             */
            if (!nkwargs && !skip) {
                return cleanreturn(1, &freelist);
            }
        }

        /* We are into optional args, skip through to any remaining
         * keyword args */
        msg = skipitem(&format, p_va, flags);
        if (msg) {
            PyErr_Format(PyExc_SystemError, "%s: '%s'", msg,
                         format);
            return cleanreturn(0, &freelist);
        }
    }

    if (skip) {
        PyErr_Format(PyExc_TypeError,
                     "%.200s%s takes %s %d positional argument%s"
                     " (%zd given)",
                     (fname == NULL) ? "function" : fname,
                     (fname == NULL) ? "" : "()",
                     (Py_MIN(pos, min) < i) ? "at least" : "exactly",
                     Py_MIN(pos, min),
                     Py_MIN(pos, min) == 1 ? "" : "s",
                     nargs);
        return cleanreturn(0, &freelist);
    }

    if (!IS_END_OF_FORMAT(*format) && (*format != '|') && (*format != '$')) {
        PyErr_Format(PyExc_SystemError,
            "more argument specifiers than keyword list entries "
            "(remaining format:'%s')", format);
        return cleanreturn(0, &freelist);
    }

    if (nkwargs > 0) {
        PyObject *key;
        Py_ssize_t j;
        /* make sure there are no arguments given by name and position */
        for (i = pos; i < nargs; i++) {
            current_arg = _PyDict_GetItemStringWithError(kwargs, kwlist[i]);
            if (current_arg) {
                /* arg present in tuple and in dict */
                PyErr_Format(PyExc_TypeError,
                             "argument for %.200s%s given by name ('%s') "
                             "and position (%d)",
                             (fname == NULL) ? "function" : fname,
                             (fname == NULL) ? "" : "()",
                             kwlist[i], i+1);
                return cleanreturn(0, &freelist);
            }
            else if (PyErr_Occurred()) {
                return cleanreturn(0, &freelist);
            }
        }
        /* make sure there are no extraneous keyword arguments */
        j = 0;
        while (PyDict_Next(kwargs, &j, &key, NULL)) {
            int match = 0;
            if (!PyUnicode_Check(key)) {
                PyErr_SetString(PyExc_TypeError,
                                "keywords must be strings");
                return cleanreturn(0, &freelist);
            }
            for (i = pos; i < len; i++) {
                if (_PyUnicode_EqualToASCIIString(key, kwlist[i])) {
                    match = 1;
                    break;
                }
            }
            if (!match) {
                PyErr_Format(PyExc_TypeError,
                             "'%U' is an invalid keyword "
                             "argument for %.200s%s",
                             key,
                             (fname == NULL) ? "this function" : fname,
                             (fname == NULL) ? "" : "()");
                return cleanreturn(0, &freelist);
            }
        }
    }

    return cleanreturn(1, &freelist);
}


/* List of static parsers. */
static struct _PyArg_Parser *static_arg_parsers = NULL;

static int
parser_init(struct _PyArg_Parser *parser)
{
    const char * const *keywords;
    const char *format, *msg;
    int i, len, min, max, nkw;
    PyObject *kwtuple;

    assert(parser->keywords != NULL);
    if (parser->kwtuple != NULL) {
        return 1;
    }

    keywords = parser->keywords;
    /* scan keywords and count the number of positional-only parameters */
    for (i = 0; keywords[i] && !*keywords[i]; i++) {
    }
    parser->pos = i;
    /* scan keywords and get greatest possible nbr of args */
    for (; keywords[i]; i++) {
        if (!*keywords[i]) {
            PyErr_SetString(PyExc_SystemError,
                            "Empty keyword parameter name");
            return 0;
        }
    }
    len = i;

    format = parser->format;
    if (format) {
        /* grab the function name or custom error msg first (mutually exclusive) */
        parser->fname = strchr(parser->format, ':');
        if (parser->fname) {
            parser->fname++;
            parser->custom_msg = NULL;
        }
        else {
            parser->custom_msg = strchr(parser->format,';');
            if (parser->custom_msg)
                parser->custom_msg++;
        }

        min = max = INT_MAX;
        for (i = 0; i < len; i++) {
            if (*format == '|') {
                if (min != INT_MAX) {
                    PyErr_SetString(PyExc_SystemError,
                                    "Invalid format string (| specified twice)");
                    return 0;
                }
                if (max != INT_MAX) {
                    PyErr_SetString(PyExc_SystemError,
                                    "Invalid format string ($ before |)");
                    return 0;
                }
                min = i;
                format++;
            }
            if (*format == '$') {
                if (max != INT_MAX) {
                    PyErr_SetString(PyExc_SystemError,
                                    "Invalid format string ($ specified twice)");
                    return 0;
                }
                if (i < parser->pos) {
                    PyErr_SetString(PyExc_SystemError,
                                    "Empty parameter name after $");
                    return 0;
                }
                max = i;
                format++;
            }
            if (IS_END_OF_FORMAT(*format)) {
                PyErr_Format(PyExc_SystemError,
                            "More keyword list entries (%d) than "
                            "format specifiers (%d)", len, i);
                return 0;
            }

            msg = skipitem(&format, NULL, 0);
            if (msg) {
                PyErr_Format(PyExc_SystemError, "%s: '%s'", msg,
                            format);
                return 0;
            }
        }
        parser->min = Py_MIN(min, len);
        parser->max = Py_MIN(max, len);

        if (!IS_END_OF_FORMAT(*format) && (*format != '|') && (*format != '$')) {
            PyErr_Format(PyExc_SystemError,
                "more argument specifiers than keyword list entries "
                "(remaining format:'%s')", format);
            return 0;
        }
    }

    nkw = len - parser->pos;
    kwtuple = PyTuple_New(nkw);
    if (kwtuple == NULL) {
        return 0;
    }
    keywords = parser->keywords + parser->pos;
    for (i = 0; i < nkw; i++) {
        PyObject *str = PyUnicode_FromString(keywords[i]);
        if (str == NULL) {
            Py_DECREF(kwtuple);
            return 0;
        }
        PyUnicode_InternInPlace(&str);
        PyTuple_SET_ITEM(kwtuple, i, str);
    }
    parser->kwtuple = kwtuple;

    assert(parser->next == NULL);
    parser->next = static_arg_parsers;
    static_arg_parsers = parser;
    return 1;
}

static void
parser_clear(struct _PyArg_Parser *parser)
{
    Py_CLEAR(parser->kwtuple);
}

static PyObject*
find_keyword(PyObject *kwnames, PyObject *const *kwstack, PyObject *key)
{
    Py_ssize_t i, nkwargs;

    nkwargs = PyTuple_GET_SIZE(kwnames);
    for (i=0; i < nkwargs; i++) {
        PyObject *kwname = PyTuple_GET_ITEM(kwnames, i);

        /* ptr==ptr should match in most cases since keyword keys
           should be interned strings */
        if (kwname == key) {
            return kwstack[i];
        }
        assert(PyUnicode_Check(kwname));
        if (_PyUnicode_EQ(kwname, key)) {
            return kwstack[i];
        }
    }
    return NULL;
}

static int
vgetargskeywordsfast_impl(PyObject *const *args, Py_ssize_t nargs,
                          PyObject *kwargs, PyObject *kwnames,
                          struct _PyArg_Parser *parser,
                          va_list *p_va, int flags)
{
    PyObject *kwtuple;
    char msgbuf[512];
    int levels[32];
    const char *format;
    const char *msg;
    PyObject *keyword;
    int i, pos, len;
    Py_ssize_t nkwargs;
    PyObject *current_arg;
    freelistentry_t static_entries[STATIC_FREELIST_ENTRIES];
    freelist_t freelist;
    PyObject *const *kwstack = NULL;

    freelist.entries = static_entries;
    freelist.first_available = 0;
    freelist.entries_malloced = 0;

    assert(kwargs == NULL || PyDict_Check(kwargs));
    assert(kwargs == NULL || kwnames == NULL);
    assert(p_va != NULL);

    if (parser == NULL) {
        PyErr_BadInternalCall();
        return 0;
    }

    if (kwnames != NULL && !PyTuple_Check(kwnames)) {
        PyErr_BadInternalCall();
        return 0;
    }

    if (!parser_init(parser)) {
        return 0;
    }

    kwtuple = parser->kwtuple;
    pos = parser->pos;
    len = pos + (int)PyTuple_GET_SIZE(kwtuple);

    if (len > STATIC_FREELIST_ENTRIES) {
        freelist.entries = PyMem_NEW(freelistentry_t, len);
        if (freelist.entries == NULL) {
            PyErr_NoMemory();
            return 0;
        }
        freelist.entries_malloced = 1;
    }

    if (kwargs != NULL) {
        nkwargs = PyDict_GET_SIZE(kwargs);
    }
    else if (kwnames != NULL) {
        nkwargs = PyTuple_GET_SIZE(kwnames);
        kwstack = args + nargs;
    }
    else {
        nkwargs = 0;
    }
    if (nargs + nkwargs > len) {
        /* Adding "keyword" (when nargs == 0) prevents producing wrong error
           messages in some special cases (see bpo-31229). */
        PyErr_Format(PyExc_TypeError,
                     "%.200s%s takes at most %d %sargument%s (%zd given)",
                     (parser->fname == NULL) ? "function" : parser->fname,
                     (parser->fname == NULL) ? "" : "()",
                     len,
                     (nargs == 0) ? "keyword " : "",
                     (len == 1) ? "" : "s",
                     nargs + nkwargs);
        return cleanreturn(0, &freelist);
    }
    if (parser->max < nargs) {
        if (parser->max == 0) {
            PyErr_Format(PyExc_TypeError,
                         "%.200s%s takes no positional arguments",
                         (parser->fname == NULL) ? "function" : parser->fname,
                         (parser->fname == NULL) ? "" : "()");
        }
        else {
            PyErr_Format(PyExc_TypeError,
                         "%.200s%s takes %s %d positional argument%s (%zd given)",
                         (parser->fname == NULL) ? "function" : parser->fname,
                         (parser->fname == NULL) ? "" : "()",
                         (parser->min < parser->max) ? "at most" : "exactly",
                         parser->max,
                         parser->max == 1 ? "" : "s",
                         nargs);
        }
        return cleanreturn(0, &freelist);
    }

    format = parser->format;
    /* convert tuple args and keyword args in same loop, using kwtuple to drive process */
    for (i = 0; i < len; i++) {
        if (*format == '|') {
            format++;
        }
        if (*format == '$') {
            format++;
        }
        assert(!IS_END_OF_FORMAT(*format));

        if (i < nargs) {
            current_arg = args[i];
        }
        else if (nkwargs && i >= pos) {
            keyword = PyTuple_GET_ITEM(kwtuple, i - pos);
            if (kwargs != NULL) {
                current_arg = PyDict_GetItemWithError(kwargs, keyword);
                if (!current_arg && PyErr_Occurred()) {
                    return cleanreturn(0, &freelist);
                }
            }
            else {
                current_arg = find_keyword(kwnames, kwstack, keyword);
            }
            if (current_arg) {
                --nkwargs;
            }
        }
        else {
            current_arg = NULL;
        }

        if (current_arg) {
            msg = convertitem(current_arg, &format, p_va, flags,
                levels, msgbuf, sizeof(msgbuf), &freelist);
            if (msg) {
                seterror(i+1, msg, levels, parser->fname, parser->custom_msg);
                return cleanreturn(0, &freelist);
            }
            continue;
        }

        if (i < parser->min) {
            /* Less arguments than required */
            if (i < pos) {
                Py_ssize_t min = Py_MIN(pos, parser->min);
                PyErr_Format(PyExc_TypeError,
                             "%.200s%s takes %s %d positional argument%s"
                             " (%zd given)",
                             (parser->fname == NULL) ? "function" : parser->fname,
                             (parser->fname == NULL) ? "" : "()",
                             min < parser->max ? "at least" : "exactly",
                             min,
                             min == 1 ? "" : "s",
                             nargs);
            }
            else {
                keyword = PyTuple_GET_ITEM(kwtuple, i - pos);
                PyErr_Format(PyExc_TypeError,  "%.200s%s missing required "
                             "argument '%U' (pos %d)",
                             (parser->fname == NULL) ? "function" : parser->fname,
                             (parser->fname == NULL) ? "" : "()",
                             keyword, i+1);
            }
            return cleanreturn(0, &freelist);
        }
        /* current code reports success when all required args
         * fulfilled and no keyword args left, with no further
         * validation. XXX Maybe skip this in debug build ?
         */
        if (!nkwargs) {
            return cleanreturn(1, &freelist);
        }

        /* We are into optional args, skip through to any remaining
         * keyword args */
        msg = skipitem(&format, p_va, flags);
        assert(msg == NULL);
    }

    assert(IS_END_OF_FORMAT(*format) || (*format == '|') || (*format == '$'));

    if (nkwargs > 0) {
        Py_ssize_t j;
        /* make sure there are no arguments given by name and position */
        for (i = pos; i < nargs; i++) {
            keyword = PyTuple_GET_ITEM(kwtuple, i - pos);
            if (kwargs != NULL) {
                current_arg = PyDict_GetItemWithError(kwargs, keyword);
                if (!current_arg && PyErr_Occurred()) {
                    return cleanreturn(0, &freelist);
                }
            }
            else {
                current_arg = find_keyword(kwnames, kwstack, keyword);
            }
            if (current_arg) {
                /* arg present in tuple and in dict */
                PyErr_Format(PyExc_TypeError,
                             "argument for %.200s%s given by name ('%U') "
                             "and position (%d)",
                             (parser->fname == NULL) ? "function" : parser->fname,
                             (parser->fname == NULL) ? "" : "()",
                             keyword, i+1);
                return cleanreturn(0, &freelist);
            }
        }
        /* make sure there are no extraneous keyword arguments */
        j = 0;
        while (1) {
            int match;
            if (kwargs != NULL) {
                if (!PyDict_Next(kwargs, &j, &keyword, NULL))
                    break;
            }
            else {
                if (j >= PyTuple_GET_SIZE(kwnames))
                    break;
                keyword = PyTuple_GET_ITEM(kwnames, j);
                j++;
            }

            match = PySequence_Contains(kwtuple, keyword);
            if (match <= 0) {
                if (!match) {
                    PyErr_Format(PyExc_TypeError,
                                 "'%S' is an invalid keyword "
                                 "argument for %.200s%s",
                                 keyword,
                                 (parser->fname == NULL) ? "this function" : parser->fname,
                                 (parser->fname == NULL) ? "" : "()");
                }
                return cleanreturn(0, &freelist);
            }
        }
    }

    return cleanreturn(1, &freelist);
}

static int
vgetargskeywordsfast(PyObject *args, PyObject *keywords,
                     struct _PyArg_Parser *parser, va_list *p_va, int flags)
{
    PyObject **stack;
    Py_ssize_t nargs;

    if (args == NULL
        || !PyTuple_Check(args)
        || (keywords != NULL && !PyDict_Check(keywords)))
    {
        PyErr_BadInternalCall();
        return 0;
    }

    stack = _PyTuple_ITEMS(args);
    nargs = PyTuple_GET_SIZE(args);
    return vgetargskeywordsfast_impl(stack, nargs, keywords, NULL,
                                     parser, p_va, flags);
}


#undef _PyArg_UnpackKeywords

PyObject * const *
_PyArg_UnpackKeywords(PyObject *const *args, Py_ssize_t nargs,
                      PyObject *kwargs, PyObject *kwnames,
                      struct _PyArg_Parser *parser,
                      int minpos, int maxpos, int minkw,
                      PyObject **buf)
{
    PyObject *kwtuple;
    PyObject *keyword;
    int i, posonly, minposonly, maxargs;
    int reqlimit = minkw ? maxpos + minkw : minpos;
    Py_ssize_t nkwargs;
    PyObject *current_arg;
    PyObject * const *kwstack = NULL;

    assert(kwargs == NULL || PyDict_Check(kwargs));
    assert(kwargs == NULL || kwnames == NULL);

    if (parser == NULL) {
        PyErr_BadInternalCall();
        return NULL;
    }

    if (kwnames != NULL && !PyTuple_Check(kwnames)) {
        PyErr_BadInternalCall();
        return NULL;
    }

    if (args == NULL && nargs == 0) {
        args = buf;
    }

    if (!parser_init(parser)) {
        return NULL;
    }

    kwtuple = parser->kwtuple;
    posonly = parser->pos;
    minposonly = Py_MIN(posonly, minpos);
    maxargs = posonly + (int)PyTuple_GET_SIZE(kwtuple);

    if (kwargs != NULL) {
        nkwargs = PyDict_GET_SIZE(kwargs);
    }
    else if (kwnames != NULL) {
        nkwargs = PyTuple_GET_SIZE(kwnames);
        kwstack = args + nargs;
    }
    else {
        nkwargs = 0;
    }
    if (nkwargs == 0 && minkw == 0 && minpos <= nargs && nargs <= maxpos) {
        /* Fast path. */
        return args;
    }
    if (nargs + nkwargs > maxargs) {
        /* Adding "keyword" (when nargs == 0) prevents producing wrong error
           messages in some special cases (see bpo-31229). */
        PyErr_Format(PyExc_TypeError,
                     "%.200s%s takes at most %d %sargument%s (%zd given)",
                     (parser->fname == NULL) ? "function" : parser->fname,
                     (parser->fname == NULL) ? "" : "()",
                     maxargs,
                     (nargs == 0) ? "keyword " : "",
                     (maxargs == 1) ? "" : "s",
                     nargs + nkwargs);
        return NULL;
    }
    if (nargs > maxpos) {
        if (maxpos == 0) {
            PyErr_Format(PyExc_TypeError,
                         "%.200s%s takes no positional arguments",
                         (parser->fname == NULL) ? "function" : parser->fname,
                         (parser->fname == NULL) ? "" : "()");
        }
        else {
            PyErr_Format(PyExc_TypeError,
                         "%.200s%s takes %s %d positional argument%s (%zd given)",
                         (parser->fname == NULL) ? "function" : parser->fname,
                         (parser->fname == NULL) ? "" : "()",
                         (minpos < maxpos) ? "at most" : "exactly",
                         maxpos,
                         (maxpos == 1) ? "" : "s",
                         nargs);
        }
        return NULL;
    }
    if (nargs < minposonly) {
        PyErr_Format(PyExc_TypeError,
                     "%.200s%s takes %s %d positional argument%s"
                     " (%zd given)",
                     (parser->fname == NULL) ? "function" : parser->fname,
                     (parser->fname == NULL) ? "" : "()",
                     minposonly < maxpos ? "at least" : "exactly",
                     minposonly,
                     minposonly == 1 ? "" : "s",
                     nargs);
        return NULL;
    }

    /* copy tuple args */
    for (i = 0; i < nargs; i++) {
        buf[i] = args[i];
    }

    /* copy keyword args using kwtuple to drive process */
    for (i = Py_MAX((int)nargs, posonly); i < maxargs; i++) {
        if (nkwargs) {
            keyword = PyTuple_GET_ITEM(kwtuple, i - posonly);
            if (kwargs != NULL) {
                current_arg = PyDict_GetItemWithError(kwargs, keyword);
                if (!current_arg && PyErr_Occurred()) {
                    return NULL;
                }
            }
            else {
                current_arg = find_keyword(kwnames, kwstack, keyword);
            }
        }
        else if (i >= reqlimit) {
            break;
        }
        else {
            current_arg = NULL;
        }

        buf[i] = current_arg;

        if (current_arg) {
            --nkwargs;
        }
        else if (i < minpos || (maxpos <= i && i < reqlimit)) {
            /* Less arguments than required */
            keyword = PyTuple_GET_ITEM(kwtuple, i - posonly);
            PyErr_Format(PyExc_TypeError,  "%.200s%s missing required "
                         "argument '%U' (pos %d)",
                         (parser->fname == NULL) ? "function" : parser->fname,
                         (parser->fname == NULL) ? "" : "()",
                         keyword, i+1);
            return NULL;
        }
    }

    if (nkwargs > 0) {
        Py_ssize_t j;
        /* make sure there are no arguments given by name and position */
        for (i = posonly; i < nargs; i++) {
            keyword = PyTuple_GET_ITEM(kwtuple, i - posonly);
            if (kwargs != NULL) {
                current_arg = PyDict_GetItemWithError(kwargs, keyword);
                if (!current_arg && PyErr_Occurred()) {
                    return NULL;
                }
            }
            else {
                current_arg = find_keyword(kwnames, kwstack, keyword);
            }
            if (current_arg) {
                /* arg present in tuple and in dict */
                PyErr_Format(PyExc_TypeError,
                             "argument for %.200s%s given by name ('%U') "
                             "and position (%d)",
                             (parser->fname == NULL) ? "function" : parser->fname,
                             (parser->fname == NULL) ? "" : "()",
                             keyword, i+1);
                return NULL;
            }
        }
        /* make sure there are no extraneous keyword arguments */
        j = 0;
        while (1) {
            int match;
            if (kwargs != NULL) {
                if (!PyDict_Next(kwargs, &j, &keyword, NULL))
                    break;
            }
            else {
                if (j >= PyTuple_GET_SIZE(kwnames))
                    break;
                keyword = PyTuple_GET_ITEM(kwnames, j);
                j++;
            }

            match = PySequence_Contains(kwtuple, keyword);
            if (match <= 0) {
                if (!match) {
                    PyErr_Format(PyExc_TypeError,
                                 "'%S' is an invalid keyword "
                                 "argument for %.200s%s",
                                 keyword,
                                 (parser->fname == NULL) ? "this function" : parser->fname,
                                 (parser->fname == NULL) ? "" : "()");
                }
                return NULL;
            }
        }
    }

    return buf;
}


static const char *
skipitem(const char **p_format, va_list *p_va, int flags)
{
    const char *format = *p_format;
    char c = *format++;

    switch (c) {

    /*
     * codes that take a single data pointer as an argument
     * (the type of the pointer is irrelevant)
     */

    case 'b': /* byte -- very short int */
    case 'B': /* byte as bitfield */
    case 'h': /* short int */
    case 'H': /* short int as bitfield */
    case 'i': /* int */
    case 'I': /* int sized bitfield */
    case 'l': /* long int */
    case 'k': /* long int sized bitfield */
    case 'L': /* long long */
    case 'K': /* long long sized bitfield */
    case 'n': /* Py_ssize_t */
    case 'f': /* float */
    case 'd': /* double */
    case 'D': /* complex double */
    case 'c': /* char */
    case 'C': /* unicode char */
    case 'p': /* boolean predicate */
    case 'S': /* string object */
    case 'Y': /* string object */
    case 'U': /* unicode string object */
        {
            if (p_va != NULL) {
                (void) va_arg(*p_va, void *);
            }
            break;
        }

    /* string codes */

    case 'e': /* string with encoding */
        {
            if (p_va != NULL) {
                (void) va_arg(*p_va, const char *);
            }
            if (!(*format == 's' || *format == 't'))
                /* after 'e', only 's' and 't' is allowed */
                goto err;
            format++;
        }
        /* fall through */

    case 's': /* string */
    case 'z': /* string or None */
    case 'y': /* bytes */
    case 'u': /* unicode string */
    case 'Z': /* unicode string or None */
    case 'w': /* buffer, read-write */
        {
            if (p_va != NULL) {
                (void) va_arg(*p_va, char **);
            }
            if (*format == '#') {
                if (p_va != NULL) {
                    if (flags & FLAG_SIZE_T)
                        (void) va_arg(*p_va, Py_ssize_t *);
                    else {
                        if (PyErr_WarnEx(PyExc_DeprecationWarning,
                                    "PY_SSIZE_T_CLEAN will be required for '#' formats", 1)) {
                            return NULL;
                        }
                        (void) va_arg(*p_va, int *);
                    }
                }
                format++;
            } else if ((c == 's' || c == 'z' || c == 'y' || c == 'w')
                       && *format == '*')
            {
                format++;
            }
            break;
        }

    case 'O': /* object */
        {
            if (*format == '!') {
                format++;
                if (p_va != NULL) {
                    (void) va_arg(*p_va, PyTypeObject*);
                    (void) va_arg(*p_va, PyObject **);
                }
            }
            else if (*format == '&') {
                typedef int (*converter)(PyObject *, void *);
                if (p_va != NULL) {
                    (void) va_arg(*p_va, converter);
                    (void) va_arg(*p_va, void *);
                }
                format++;
            }
            else {
                if (p_va != NULL) {
                    (void) va_arg(*p_va, PyObject **);
                }
            }
            break;
        }

    case '(':           /* bypass tuple, not handled at all previously */
        {
            const char *msg;
            for (;;) {
                if (*format==')')
                    break;
                if (IS_END_OF_FORMAT(*format))
                    return "Unmatched left paren in format "
                           "string";
                msg = skipitem(&format, p_va, flags);
                if (msg)
                    return msg;
            }
            format++;
            break;
        }

    case ')':
        return "Unmatched right paren in format string";

    default:
err:
        return "impossible<bad format char>";

    }

    *p_format = format;
    return NULL;
}


#undef _PyArg_CheckPositional

int
_PyArg_CheckPositional(const char *name, Py_ssize_t nargs,
                       Py_ssize_t min, Py_ssize_t max)
{
    assert(min >= 0);
    assert(min <= max);

    if (nargs < min) {
        if (name != NULL)
            PyErr_Format(
                PyExc_TypeError,
                "%.200s expected %s%zd argument%s, got %zd",
                name, (min == max ? "" : "at least "), min, min == 1 ? "" : "s", nargs);
        else
            PyErr_Format(
                PyExc_TypeError,
                "unpacked tuple should have %s%zd element%s,"
                " but has %zd",
                (min == max ? "" : "at least "), min, min == 1 ? "" : "s", nargs);
        return 0;
    }

    if (nargs == 0) {
        return 1;
    }

    if (nargs > max) {
        if (name != NULL)
            PyErr_Format(
                PyExc_TypeError,
                "%.200s expected %s%zd argument%s, got %zd",
                name, (min == max ? "" : "at most "), max, max == 1 ? "" : "s", nargs);
        else
            PyErr_Format(
                PyExc_TypeError,
                "unpacked tuple should have %s%zd element%s,"
                " but has %zd",
                (min == max ? "" : "at most "), max, max == 1 ? "" : "s", nargs);
        return 0;
    }

    return 1;
}

static int
unpack_stack(PyObject *const *args, Py_ssize_t nargs, const char *name,
             Py_ssize_t min, Py_ssize_t max, va_list vargs)
{
    Py_ssize_t i;
    PyObject **o;

    if (!_PyArg_CheckPositional(name, nargs, min, max)) {
        return 0;
    }

    for (i = 0; i < nargs; i++) {
        o = va_arg(vargs, PyObject **);
        *o = args[i];
    }
    return 1;
}

int
PyArg_UnpackTuple(PyObject *args, const char *name, Py_ssize_t min, Py_ssize_t max, ...)
{
    PyObject **stack;
    Py_ssize_t nargs;
    int retval;
    va_list vargs;

    if (!PyTuple_Check(args)) {
        PyErr_SetString(PyExc_SystemError,
            "PyArg_UnpackTuple() argument list is not a tuple");
        return 0;
    }
    stack = _PyTuple_ITEMS(args);
    nargs = PyTuple_GET_SIZE(args);

#ifdef HAVE_STDARG_PROTOTYPES
    va_start(vargs, max);
#else
    va_start(vargs);
#endif
    retval = unpack_stack(stack, nargs, name, min, max, vargs);
    va_end(vargs);
    return retval;
}

int
_PyArg_UnpackStack(PyObject *const *args, Py_ssize_t nargs, const char *name,
                   Py_ssize_t min, Py_ssize_t max, ...)
{
    int retval;
    va_list vargs;

#ifdef HAVE_STDARG_PROTOTYPES
    va_start(vargs, max);
#else
    va_start(vargs);
#endif
    retval = unpack_stack(args, nargs, name, min, max, vargs);
    va_end(vargs);
    return retval;
}


#undef _PyArg_NoKeywords
#undef _PyArg_NoPositional

/* For type constructors that don't take keyword args
 *
 * Sets a TypeError and returns 0 if the args/kwargs is
 * not empty, returns 1 otherwise
 */
int
_PyArg_NoKeywords(const char *funcname, PyObject *kwargs)
{
    if (kwargs == NULL) {
        return 1;
    }
    if (!PyDict_CheckExact(kwargs)) {
        PyErr_BadInternalCall();
        return 0;
    }
    if (PyDict_GET_SIZE(kwargs) == 0) {
        return 1;
    }

    PyErr_Format(PyExc_TypeError, "%.200s() takes no keyword arguments",
                    funcname);
    return 0;
}


int
_PyArg_NoPositional(const char *funcname, PyObject *args)
{
    if (args == NULL)
        return 1;
    if (!PyTuple_CheckExact(args)) {
        PyErr_BadInternalCall();
        return 0;
    }
    if (PyTuple_GET_SIZE(args) == 0)
        return 1;

    PyErr_Format(PyExc_TypeError, "%.200s() takes no positional arguments",
                    funcname);
    return 0;
}

void
_PyArg_Fini(void)
{
    struct _PyArg_Parser *tmp, *s = static_arg_parsers;
    while (s) {
        tmp = s->next;
        s->next = NULL;
        parser_clear(s);
        s = tmp;
    }
    static_arg_parsers = NULL;
}

#ifdef __cplusplus
};
#endif
generated by cgit v0.12 at 2025-12-16 08:47:25 (GMT)