results name in parse action now that ungrouped names are not reported at two levels
+ openTag.addParseAction(lambda t: t.__setitem__("start" + "".join(resname.replace(":", " ").title().split()), t.copy()))
+ closeTag = closeTag("end" + "".join(resname.replace(":", " ").title().split())).setName("" % resname)
+ openTag.tag = resname
+ closeTag.tag = resname
+ openTag.tag_body = SkipTo(closeTag())
+ return openTag, closeTag
+
+def makeHTMLTags(tagStr):
+ """Helper to construct opening and closing tag expressions for HTML,
+ given a tag name. Matches tags in either upper or lower case,
+ attributes with namespaces and with quoted or unquoted values.
+
+ Example::
+
+ text = '| More info at the pyparsing wiki page | '
+ # makeHTMLTags returns pyparsing expressions for the opening and
+ # closing tags as a 2-tuple
+ a, a_end = makeHTMLTags("A")
+ link_expr = a + SkipTo(a_end)("link_text") + a_end
+
+ for link in link_expr.searchString(text):
+ # attributes in the tag (like "href" shown here) are
+ # also accessible as named results
+ print(link.link_text, '->', link.href)
+
+ prints::
+
+ pyparsing -> https://github.com/pyparsing/pyparsing/wiki
+ """
+ return _makeTags(tagStr, False)
+
+def makeXMLTags(tagStr):
+ """Helper to construct opening and closing tag expressions for XML,
+ given a tag name. Matches tags only in the given upper/lower case.
+
+ Example: similar to :class:`makeHTMLTags`
+ """
+ return _makeTags(tagStr, True)
+
+def withAttribute(*args, **attrDict):
+ """Helper to create a validating parse action to be used with start
+ tags created with :class:`makeXMLTags` or
+ :class:`makeHTMLTags`. Use ``withAttribute`` to qualify
+ a starting tag with a required attribute value, to avoid false
+ matches on common tags such as ```` or ````.
+
+ Call ``withAttribute`` with a series of attribute names and
+ values. Specify the list of filter attributes names and values as:
+
+ - keyword arguments, as in ``(align="right")``, or
+ - as an explicit dict with ``**`` operator, when an attribute
+ name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}``
+ - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))``
+
+ For attribute names with a namespace prefix, you must use the second
+ form. Attribute names are matched insensitive to upper/lower case.
+
+ If just testing for ``class`` (with or without a namespace), use
+ :class:`withClass`.
+
+ To verify that the attribute exists, but without specifying a value,
+ pass ``withAttribute.ANY_VALUE`` as the value.
+
+ Example::
+
+ html = '''
+
+ Some text
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ this has no type
+
+
+ '''
+ div,div_end = makeHTMLTags("div")
+
+ # only match div tag having a type attribute with value "grid"
+ div_grid = div().setParseAction(withAttribute(type="grid"))
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ # construct a match with any div tag having a type attribute, regardless of the value
+ div_any_type = div().setParseAction(withAttribute(type=withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+
+ prints::
+
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
+ if args:
+ attrs = args[:]
+ else:
+ attrs = attrDict.items()
+ attrs = [(k, v) for k, v in attrs]
+ def pa(s, l, tokens):
+ for attrName, attrValue in attrs:
+ if attrName not in tokens:
+ raise ParseException(s, l, "no matching attribute " + attrName)
+ if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue:
+ raise ParseException(s, l, "attribute '%s' has value '%s', must be '%s'" %
+ (attrName, tokens[attrName], attrValue))
+ return pa
+withAttribute.ANY_VALUE = object()
+
+def withClass(classname, namespace=''):
+ """Simplified version of :class:`withAttribute` when
+ matching on a div class - made difficult because ``class`` is
+ a reserved word in Python.
+
+ Example::
+
+ html = '''
+
+ Some text
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ this <div> has no class
+
+
+ '''
+ div,div_end = makeHTMLTags("div")
+ div_grid = div().setParseAction(withClass("grid"))
+
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ div_any_type = div().setParseAction(withClass(withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+
+ prints::
+
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
+ classattr = "%s:class" % namespace if namespace else "class"
+ return withAttribute(**{classattr: classname})
+
+opAssoc = SimpleNamespace()
+opAssoc.LEFT = object()
+opAssoc.RIGHT = object()
+
+def infixNotation(baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')')):
+ """Helper method for constructing grammars of expressions made up of
+ operators working in a precedence hierarchy. Operators may be unary
+ or binary, left- or right-associative. Parse actions can also be
+ attached to operator expressions. The generated parser will also
+ recognize the use of parentheses to override operator precedences
+ (see example below).
+
+ Note: if you define a deep operator list, you may see performance
+ issues when using infixNotation. See
+ :class:`ParserElement.enablePackrat` for a mechanism to potentially
+ improve your parser performance.
+
+ Parameters:
+ - baseExpr - expression representing the most basic element for the
+ nested
+ - opList - list of tuples, one for each operator precedence level
+ in the expression grammar; each tuple is of the form ``(opExpr,
+ numTerms, rightLeftAssoc, parseAction)``, where:
+
+ - opExpr is the pyparsing expression for the operator; may also
+ be a string, which will be converted to a Literal; if numTerms
+ is 3, opExpr is a tuple of two expressions, for the two
+ operators separating the 3 terms
+ - numTerms is the number of terms for this operator (must be 1,
+ 2, or 3)
+ - rightLeftAssoc is the indicator whether the operator is right
+ or left associative, using the pyparsing-defined constants
+ ``opAssoc.RIGHT`` and ``opAssoc.LEFT``.
+ - parseAction is the parse action to be associated with
+ expressions matching this operator expression (the parse action
+ tuple member may be omitted); if the parse action is passed
+ a tuple or list of functions, this is equivalent to calling
+ ``setParseAction(*fn)``
+ (:class:`ParserElement.setParseAction`)
+ - lpar - expression for matching left-parentheses
+ (default= ``Suppress('(')``)
+ - rpar - expression for matching right-parentheses
+ (default= ``Suppress(')')``)
+
+ Example::
+
+ # simple example of four-function arithmetic with ints and
+ # variable names
+ integer = pyparsing_common.signed_integer
+ varname = pyparsing_common.identifier
+
+ arith_expr = infixNotation(integer | varname,
+ [
+ ('-', 1, opAssoc.RIGHT),
+ (oneOf('* /'), 2, opAssoc.LEFT),
+ (oneOf('+ -'), 2, opAssoc.LEFT),
+ ])
+
+ arith_expr.runTests('''
+ 5+3*6
+ (5+3)*6
+ -2--11
+ ''', fullDump=False)
+
+ prints::
+
+ 5+3*6
+ [[5, '+', [3, '*', 6]]]
+
+ (5+3)*6
+ [[[5, '+', 3], '*', 6]]
+
+ -2--11
+ [[['-', 2], '-', ['-', 11]]]
+ """
+ # captive version of FollowedBy that does not do parse actions or capture results names
+ class _FB(FollowedBy):
+ def parseImpl(self, instring, loc, doActions=True):
+ self.expr.tryParse(instring, loc)
+ return loc, []
+
+ ret = Forward()
+ lastExpr = baseExpr | (lpar + ret + rpar)
+ for i, operDef in enumerate(opList):
+ opExpr, arity, rightLeftAssoc, pa = (operDef + (None, ))[:4]
+ termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr
+ if arity == 3:
+ if opExpr is None or len(opExpr) != 2:
+ raise ValueError(
+ "if numterms=3, opExpr must be a tuple or list of two expressions")
+ opExpr1, opExpr2 = opExpr
+ thisExpr = Forward().setName(termName)
+ if rightLeftAssoc == opAssoc.LEFT:
+ if arity == 1:
+ matchExpr = _FB(lastExpr + opExpr) + Group(lastExpr + OneOrMore(opExpr))
+ elif arity == 2:
+ if opExpr is not None:
+ matchExpr = _FB(lastExpr + opExpr + lastExpr) + Group(lastExpr + OneOrMore(opExpr + lastExpr))
+ else:
+ matchExpr = _FB(lastExpr + lastExpr) + Group(lastExpr + OneOrMore(lastExpr))
+ elif arity == 3:
+ matchExpr = (_FB(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr)
+ + Group(lastExpr + OneOrMore(opExpr1 + lastExpr + opExpr2 + lastExpr)))
+ else:
+ raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
+ elif rightLeftAssoc == opAssoc.RIGHT:
+ if arity == 1:
+ # try to avoid LR with this extra test
+ if not isinstance(opExpr, Optional):
+ opExpr = Optional(opExpr)
+ matchExpr = _FB(opExpr.expr + thisExpr) + Group(opExpr + thisExpr)
+ elif arity == 2:
+ if opExpr is not None:
+ matchExpr = _FB(lastExpr + opExpr + thisExpr) + Group(lastExpr + OneOrMore(opExpr + thisExpr))
+ else:
+ matchExpr = _FB(lastExpr + thisExpr) + Group(lastExpr + OneOrMore(thisExpr))
+ elif arity == 3:
+ matchExpr = (_FB(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr)
+ + Group(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr))
+ else:
+ raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
+ else:
+ raise ValueError("operator must indicate right or left associativity")
+ if pa:
+ if isinstance(pa, (tuple, list)):
+ matchExpr.setParseAction(*pa)
+ else:
+ matchExpr.setParseAction(pa)
+ thisExpr <<= (matchExpr.setName(termName) | lastExpr)
+ lastExpr = thisExpr
+ ret <<= lastExpr
+ return ret
+
+operatorPrecedence = infixNotation
+"""(Deprecated) Former name of :class:`infixNotation`, will be
+dropped in a future release."""
+
+dblQuotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').setName("string enclosed in double quotes")
+sglQuotedString = Combine(Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").setName("string enclosed in single quotes")
+quotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"'
+ | Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").setName("quotedString using single or double quotes")
+unicodeString = Combine(_L('u') + quotedString.copy()).setName("unicode string literal")
+
+def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
+ """Helper method for defining nested lists enclosed in opening and
+ closing delimiters ("(" and ")" are the default).
+
+ Parameters:
+ - opener - opening character for a nested list
+ (default= ``"("``); can also be a pyparsing expression
+ - closer - closing character for a nested list
+ (default= ``")"``); can also be a pyparsing expression
+ - content - expression for items within the nested lists
+ (default= ``None``)
+ - ignoreExpr - expression for ignoring opening and closing
+ delimiters (default= :class:`quotedString`)
+
+ If an expression is not provided for the content argument, the
+ nested expression will capture all whitespace-delimited content
+ between delimiters as a list of separate values.
+
+ Use the ``ignoreExpr`` argument to define expressions that may
+ contain opening or closing characters that should not be treated as
+ opening or closing characters for nesting, such as quotedString or
+ a comment expression. Specify multiple expressions using an
+ :class:`Or` or :class:`MatchFirst`. The default is
+ :class:`quotedString`, but if no expressions are to be ignored, then
+ pass ``None`` for this argument.
+
+ Example::
+
+ data_type = oneOf("void int short long char float double")
+ decl_data_type = Combine(data_type + Optional(Word('*')))
+ ident = Word(alphas+'_', alphanums+'_')
+ number = pyparsing_common.number
+ arg = Group(decl_data_type + ident)
+ LPAR, RPAR = map(Suppress, "()")
+
+ code_body = nestedExpr('{', '}', ignoreExpr=(quotedString | cStyleComment))
+
+ c_function = (decl_data_type("type")
+ + ident("name")
+ + LPAR + Optional(delimitedList(arg), [])("args") + RPAR
+ + code_body("body"))
+ c_function.ignore(cStyleComment)
+
+ source_code = '''
+ int is_odd(int x) {
+ return (x%2);
+ }
+
+ int dec_to_hex(char hchar) {
+ if (hchar >= '0' && hchar <= '9') {
+ return (ord(hchar)-ord('0'));
+ } else {
+ return (10+ord(hchar)-ord('A'));
+ }
+ }
+ '''
+ for func in c_function.searchString(source_code):
+ print("%(name)s (%(type)s) args: %(args)s" % func)
+
+
+ prints::
+
+ is_odd (int) args: [['int', 'x']]
+ dec_to_hex (int) args: [['char', 'hchar']]
+ """
+ if opener == closer:
+ raise ValueError("opening and closing strings cannot be the same")
+ if content is None:
+ if isinstance(opener, basestring) and isinstance(closer, basestring):
+ if len(opener) == 1 and len(closer) == 1:
+ if ignoreExpr is not None:
+ content = (Combine(OneOrMore(~ignoreExpr
+ + CharsNotIn(opener
+ + closer
+ + ParserElement.DEFAULT_WHITE_CHARS, exact=1)
+ )
+ ).setParseAction(lambda t: t[0].strip()))
+ else:
+ content = (empty.copy() + CharsNotIn(opener
+ + closer
+ + ParserElement.DEFAULT_WHITE_CHARS
+ ).setParseAction(lambda t: t[0].strip()))
+ else:
+ if ignoreExpr is not None:
+ content = (Combine(OneOrMore(~ignoreExpr
+ + ~Literal(opener)
+ + ~Literal(closer)
+ + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1))
+ ).setParseAction(lambda t: t[0].strip()))
+ else:
+ content = (Combine(OneOrMore(~Literal(opener)
+ + ~Literal(closer)
+ + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1))
+ ).setParseAction(lambda t: t[0].strip()))
+ else:
+ raise ValueError("opening and closing arguments must be strings if no content expression is given")
+ ret = Forward()
+ if ignoreExpr is not None:
+ ret <<= Group(Suppress(opener) + ZeroOrMore(ignoreExpr | ret | content) + Suppress(closer))
+ else:
+ ret <<= Group(Suppress(opener) + ZeroOrMore(ret | content) + Suppress(closer))
+ ret.setName('nested %s%s expression' % (opener, closer))
+ return ret
+
+def indentedBlock(blockStatementExpr, indentStack, indent=True):
+ """Helper method for defining space-delimited indentation blocks,
+ such as those used to define block statements in Python source code.
+
+ Parameters:
+
+ - blockStatementExpr - expression defining syntax of statement that
+ is repeated within the indented block
+ - indentStack - list created by caller to manage indentation stack
+ (multiple statementWithIndentedBlock expressions within a single
+ grammar should share a common indentStack)
+ - indent - boolean indicating whether block must be indented beyond
+ the current level; set to False for block of left-most
+ statements (default= ``True``)
+
+ A valid block must contain at least one ``blockStatement``.
+
+ Example::
+
+ data = '''
+ def A(z):
+ A1
+ B = 100
+ G = A2
+ A2
+ A3
+ B
+ def BB(a,b,c):
+ BB1
+ def BBA():
+ bba1
+ bba2
+ bba3
+ C
+ D
+ def spam(x,y):
+ def eggs(z):
+ pass
+ '''
+
+
+ indentStack = [1]
+ stmt = Forward()
+
+ identifier = Word(alphas, alphanums)
+ funcDecl = ("def" + identifier + Group("(" + Optional(delimitedList(identifier)) + ")") + ":")
+ func_body = indentedBlock(stmt, indentStack)
+ funcDef = Group(funcDecl + func_body)
+
+ rvalue = Forward()
+ funcCall = Group(identifier + "(" + Optional(delimitedList(rvalue)) + ")")
+ rvalue << (funcCall | identifier | Word(nums))
+ assignment = Group(identifier + "=" + rvalue)
+ stmt << (funcDef | assignment | identifier)
+
+ module_body = OneOrMore(stmt)
+
+ parseTree = module_body.parseString(data)
+ parseTree.pprint()
+
+ prints::
+
+ [['def',
+ 'A',
+ ['(', 'z', ')'],
+ ':',
+ [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]],
+ 'B',
+ ['def',
+ 'BB',
+ ['(', 'a', 'b', 'c', ')'],
+ ':',
+ [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]],
+ 'C',
+ 'D',
+ ['def',
+ 'spam',
+ ['(', 'x', 'y', ')'],
+ ':',
+ [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]]
+ """
+ backup_stack = indentStack[:]
+
+ def reset_stack():
+ indentStack[:] = backup_stack
+
+ def checkPeerIndent(s, l, t):
+ if l >= len(s): return
+ curCol = col(l, s)
+ if curCol != indentStack[-1]:
+ if curCol > indentStack[-1]:
+ raise ParseException(s, l, "illegal nesting")
+ raise ParseException(s, l, "not a peer entry")
+
+ def checkSubIndent(s, l, t):
+ curCol = col(l, s)
+ if curCol > indentStack[-1]:
+ indentStack.append(curCol)
+ else:
+ raise ParseException(s, l, "not a subentry")
+
+ def checkUnindent(s, l, t):
+ if l >= len(s): return
+ curCol = col(l, s)
+ if not(indentStack and curCol in indentStack):
+ raise ParseException(s, l, "not an unindent")
+ if curCol < indentStack[-1]:
+ indentStack.pop()
+
+ NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress(), stopOn=StringEnd())
+ INDENT = (Empty() + Empty().setParseAction(checkSubIndent)).setName('INDENT')
+ PEER = Empty().setParseAction(checkPeerIndent).setName('')
+ UNDENT = Empty().setParseAction(checkUnindent).setName('UNINDENT')
+ if indent:
+ smExpr = Group(Optional(NL)
+ + INDENT
+ + OneOrMore(PEER + Group(blockStatementExpr) + Optional(NL), stopOn=StringEnd())
+ + UNDENT)
+ else:
+ smExpr = Group(Optional(NL)
+ + OneOrMore(PEER + Group(blockStatementExpr) + Optional(NL), stopOn=StringEnd())
+ + UNDENT)
+ smExpr.setFailAction(lambda a, b, c, d: reset_stack())
+ blockStatementExpr.ignore(_bslash + LineEnd())
+ return smExpr.setName('indented block')
+
+alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]")
+punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]")
+
+anyOpenTag, anyCloseTag = makeHTMLTags(Word(alphas, alphanums + "_:").setName('any tag'))
+_htmlEntityMap = dict(zip("gt lt amp nbsp quot apos".split(), '><& "\''))
+commonHTMLEntity = Regex('&(?P ' + '|'.join(_htmlEntityMap.keys()) +");").setName("common HTML entity")
+def replaceHTMLEntity(t):
+ """Helper parser action to replace common HTML entities with their special characters"""
+ return _htmlEntityMap.get(t.entity)
+
+# it's easy to get these comment structures wrong - they're very common, so may as well make them available
+cStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/').setName("C style comment")
+"Comment of the form ``/* ... */``"
+
+htmlComment = Regex(r"").setName("HTML comment")
+"Comment of the form ````"
+
+restOfLine = Regex(r".*").leaveWhitespace().setName("rest of line")
+dblSlashComment = Regex(r"//(?:\\\n|[^\n])*").setName("// comment")
+"Comment of the form ``// ... (to end of line)``"
+
+cppStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/' | dblSlashComment).setName("C++ style comment")
+"Comment of either form :class:`cStyleComment` or :class:`dblSlashComment`"
+
+javaStyleComment = cppStyleComment
+"Same as :class:`cppStyleComment`"
+
+pythonStyleComment = Regex(r"#.*").setName("Python style comment")
+"Comment of the form ``# ... (to end of line)``"
+
+_commasepitem = Combine(OneOrMore(Word(printables, excludeChars=',')
+ + Optional(Word(" \t")
+ + ~Literal(",") + ~LineEnd()))).streamline().setName("commaItem")
+commaSeparatedList = delimitedList(Optional(quotedString.copy() | _commasepitem, default="")).setName("commaSeparatedList")
+"""(Deprecated) Predefined expression of 1 or more printable words or
+quoted strings, separated by commas.
+
+This expression is deprecated in favor of :class:`pyparsing_common.comma_separated_list`.
+"""
+
+# some other useful expressions - using lower-case class name since we are really using this as a namespace
+class pyparsing_common:
+ """Here are some common low-level expressions that may be useful in
+ jump-starting parser development:
+
+ - numeric forms (:class:`integers`, :class:`reals`,
+ :class:`scientific notation`)
+ - common :class:`programming identifiers`
+ - network addresses (:class:`MAC`,
+ :class:`IPv4`, :class:`IPv6`)
+ - ISO8601 :class:`dates` and
+ :class:`datetime`
+ - :class:`UUID`
+ - :class:`comma-separated list`
+
+ Parse actions:
+
+ - :class:`convertToInteger`
+ - :class:`convertToFloat`
+ - :class:`convertToDate`
+ - :class:`convertToDatetime`
+ - :class:`stripHTMLTags`
+ - :class:`upcaseTokens`
+ - :class:`downcaseTokens`
+
+ Example::
+
+ pyparsing_common.number.runTests('''
+ # any int or real number, returned as the appropriate type
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.fnumber.runTests('''
+ # any int or real number, returned as float
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.hex_integer.runTests('''
+ # hex numbers
+ 100
+ FF
+ ''')
+
+ pyparsing_common.fraction.runTests('''
+ # fractions
+ 1/2
+ -3/4
+ ''')
+
+ pyparsing_common.mixed_integer.runTests('''
+ # mixed fractions
+ 1
+ 1/2
+ -3/4
+ 1-3/4
+ ''')
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests('''
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ ''')
+
+ prints::
+
+ # any int or real number, returned as the appropriate type
+ 100
+ [100]
+
+ -100
+ [-100]
+
+ +100
+ [100]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # any int or real number, returned as float
+ 100
+ [100.0]
+
+ -100
+ [-100.0]
+
+ +100
+ [100.0]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # hex numbers
+ 100
+ [256]
+
+ FF
+ [255]
+
+ # fractions
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ # mixed fractions
+ 1
+ [1]
+
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ 1-3/4
+ [1.75]
+
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ [UUID('12345678-1234-5678-1234-567812345678')]
+ """
+
+ convertToInteger = tokenMap(int)
+ """
+ Parse action for converting parsed integers to Python int
+ """
+
+ convertToFloat = tokenMap(float)
+ """
+ Parse action for converting parsed numbers to Python float
+ """
+
+ integer = Word(nums).setName("integer").setParseAction(convertToInteger)
+ """expression that parses an unsigned integer, returns an int"""
+
+ hex_integer = Word(hexnums).setName("hex integer").setParseAction(tokenMap(int, 16))
+ """expression that parses a hexadecimal integer, returns an int"""
+
+ signed_integer = Regex(r'[+-]?\d+').setName("signed integer").setParseAction(convertToInteger)
+ """expression that parses an integer with optional leading sign, returns an int"""
+
+ fraction = (signed_integer().setParseAction(convertToFloat) + '/' + signed_integer().setParseAction(convertToFloat)).setName("fraction")
+ """fractional expression of an integer divided by an integer, returns a float"""
+ fraction.addParseAction(lambda t: t[0]/t[-1])
+
+ mixed_integer = (fraction | signed_integer + Optional(Optional('-').suppress() + fraction)).setName("fraction or mixed integer-fraction")
+ """mixed integer of the form 'integer - fraction', with optional leading integer, returns float"""
+ mixed_integer.addParseAction(sum)
+
+ real = Regex(r'[+-]?(?:\d+\.\d*|\.\d+)').setName("real number").setParseAction(convertToFloat)
+ """expression that parses a floating point number and returns a float"""
+
+ sci_real = Regex(r'[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)').setName("real number with scientific notation").setParseAction(convertToFloat)
+ """expression that parses a floating point number with optional
+ scientific notation and returns a float"""
+
+ # streamlining this expression makes the docs nicer-looking
+ number = (sci_real | real | signed_integer).streamline()
+ """any numeric expression, returns the corresponding Python type"""
+
+ fnumber = Regex(r'[+-]?\d+\.?\d*([eE][+-]?\d+)?').setName("fnumber").setParseAction(convertToFloat)
+ """any int or real number, returned as float"""
+
+ identifier = Word(alphas + '_', alphanums + '_').setName("identifier")
+ """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')"""
+
+ ipv4_address = Regex(r'(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}').setName("IPv4 address")
+ "IPv4 address (``0.0.0.0 - 255.255.255.255``)"
+
+ _ipv6_part = Regex(r'[0-9a-fA-F]{1,4}').setName("hex_integer")
+ _full_ipv6_address = (_ipv6_part + (':' + _ipv6_part) * 7).setName("full IPv6 address")
+ _short_ipv6_address = (Optional(_ipv6_part + (':' + _ipv6_part) * (0, 6))
+ + "::"
+ + Optional(_ipv6_part + (':' + _ipv6_part) * (0, 6))
+ ).setName("short IPv6 address")
+ _short_ipv6_address.addCondition(lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8)
+ _mixed_ipv6_address = ("::ffff:" + ipv4_address).setName("mixed IPv6 address")
+ ipv6_address = Combine((_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).setName("IPv6 address")).setName("IPv6 address")
+ "IPv6 address (long, short, or mixed form)"
+
+ mac_address = Regex(r'[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}').setName("MAC address")
+ "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)"
+
+ @staticmethod
+ def convertToDate(fmt="%Y-%m-%d"):
+ """
+ Helper to create a parse action for converting parsed date string to Python datetime.date
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``)
+
+ Example::
+
+ date_expr = pyparsing_common.iso8601_date.copy()
+ date_expr.setParseAction(pyparsing_common.convertToDate())
+ print(date_expr.parseString("1999-12-31"))
+
+ prints::
+
+ [datetime.date(1999, 12, 31)]
+ """
+ def cvt_fn(s, l, t):
+ try:
+ return datetime.strptime(t[0], fmt).date()
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ @staticmethod
+ def convertToDatetime(fmt="%Y-%m-%dT%H:%M:%S.%f"):
+ """Helper to create a parse action for converting parsed
+ datetime string to Python datetime.datetime
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``)
+
+ Example::
+
+ dt_expr = pyparsing_common.iso8601_datetime.copy()
+ dt_expr.setParseAction(pyparsing_common.convertToDatetime())
+ print(dt_expr.parseString("1999-12-31T23:59:59.999"))
+
+ prints::
+
+ [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)]
+ """
+ def cvt_fn(s, l, t):
+ try:
+ return datetime.strptime(t[0], fmt)
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ iso8601_date = Regex(r'(?P\d{4})(?:-(?P\d\d)(?:-(?P\d\d))?)?').setName("ISO8601 date")
+ "ISO8601 date (``yyyy-mm-dd``)"
+
+ iso8601_datetime = Regex(r'(?P\d{4})-(?P\d\d)-(?P\d\d)[T ](?P\d\d):(?P\d\d)(:(?P\d\d(\.\d*)?)?)?(?PZ|[+-]\d\d:?\d\d)?').setName("ISO8601 datetime")
+ "ISO8601 datetime (``yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)``) - trailing seconds, milliseconds, and timezone optional; accepts separating ``'T'`` or ``' '``"
+
+ uuid = Regex(r'[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}').setName("UUID")
+ "UUID (``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``)"
+
+ _html_stripper = anyOpenTag.suppress() | anyCloseTag.suppress()
+ @staticmethod
+ def stripHTMLTags(s, l, tokens):
+ """Parse action to remove HTML tags from web page HTML source
+
+ Example::
+
+ # strip HTML links from normal text
+ text = 'More info at the pyparsing wiki page | '
+ td, td_end = makeHTMLTags("TD")
+ table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end
+ print(table_text.parseString(text).body)
+
+ Prints::
+
+ More info at the pyparsing wiki page
+ """
+ return pyparsing_common._html_stripper.transformString(tokens[0])
+
+ _commasepitem = Combine(OneOrMore(~Literal(",")
+ + ~LineEnd()
+ + Word(printables, excludeChars=',')
+ + Optional(White(" \t")))).streamline().setName("commaItem")
+ comma_separated_list = delimitedList(Optional(quotedString.copy()
+ | _commasepitem, default='')
+ ).setName("comma separated list")
+ """Predefined expression of 1 or more printable words or quoted strings, separated by commas."""
+
+ upcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).upper()))
+ """Parse action to convert tokens to upper case."""
+
+ downcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).lower()))
+ """Parse action to convert tokens to lower case."""
+
+
+class _lazyclassproperty(object):
+ def __init__(self, fn):
+ self.fn = fn
+ self.__doc__ = fn.__doc__
+ self.__name__ = fn.__name__
+
+ def __get__(self, obj, cls):
+ if cls is None:
+ cls = type(obj)
+ if not hasattr(cls, '_intern') or any(cls._intern is getattr(superclass, '_intern', [])
+ for superclass in cls.__mro__[1:]):
+ cls._intern = {}
+ attrname = self.fn.__name__
+ if attrname not in cls._intern:
+ cls._intern[attrname] = self.fn(cls)
+ return cls._intern[attrname]
+
+
+class unicode_set(object):
+ """
+ A set of Unicode characters, for language-specific strings for
+ ``alphas``, ``nums``, ``alphanums``, and ``printables``.
+ A unicode_set is defined by a list of ranges in the Unicode character
+ set, in a class attribute ``_ranges``, such as::
+
+ _ranges = [(0x0020, 0x007e), (0x00a0, 0x00ff),]
+
+ A unicode set can also be defined using multiple inheritance of other unicode sets::
+
+ class CJK(Chinese, Japanese, Korean):
+ pass
+ """
+ _ranges = []
+
+ @classmethod
+ def _get_chars_for_ranges(cls):
+ ret = []
+ for cc in cls.__mro__:
+ if cc is unicode_set:
+ break
+ for rr in cc._ranges:
+ ret.extend(range(rr[0], rr[-1] + 1))
+ return [unichr(c) for c in sorted(set(ret))]
+
+ @_lazyclassproperty
+ def printables(cls):
+ "all non-whitespace characters in this range"
+ return u''.join(filterfalse(unicode.isspace, cls._get_chars_for_ranges()))
+
+ @_lazyclassproperty
+ def alphas(cls):
+ "all alphabetic characters in this range"
+ return u''.join(filter(unicode.isalpha, cls._get_chars_for_ranges()))
+
+ @_lazyclassproperty
+ def nums(cls):
+ "all numeric digit characters in this range"
+ return u''.join(filter(unicode.isdigit, cls._get_chars_for_ranges()))
+
+ @_lazyclassproperty
+ def alphanums(cls):
+ "all alphanumeric characters in this range"
+ return cls.alphas + cls.nums
+
+
+class pyparsing_unicode(unicode_set):
+ """
+ A namespace class for defining common language unicode_sets.
+ """
+ _ranges = [(32, sys.maxunicode)]
+
+ class Latin1(unicode_set):
+ "Unicode set for Latin-1 Unicode Character Range"
+ _ranges = [(0x0020, 0x007e), (0x00a0, 0x00ff),]
+
+ class LatinA(unicode_set):
+ "Unicode set for Latin-A Unicode Character Range"
+ _ranges = [(0x0100, 0x017f),]
+
+ class LatinB(unicode_set):
+ "Unicode set for Latin-B Unicode Character Range"
+ _ranges = [(0x0180, 0x024f),]
+
+ class Greek(unicode_set):
+ "Unicode set for Greek Unicode Character Ranges"
+ _ranges = [
+ (0x0370, 0x03ff), (0x1f00, 0x1f15), (0x1f18, 0x1f1d), (0x1f20, 0x1f45), (0x1f48, 0x1f4d),
+ (0x1f50, 0x1f57), (0x1f59,), (0x1f5b,), (0x1f5d,), (0x1f5f, 0x1f7d), (0x1f80, 0x1fb4), (0x1fb6, 0x1fc4),
+ (0x1fc6, 0x1fd3), (0x1fd6, 0x1fdb), (0x1fdd, 0x1fef), (0x1ff2, 0x1ff4), (0x1ff6, 0x1ffe),
+ ]
+
+ class Cyrillic(unicode_set):
+ "Unicode set for Cyrillic Unicode Character Range"
+ _ranges = [(0x0400, 0x04ff)]
+
+ class Chinese(unicode_set):
+ "Unicode set for Chinese Unicode Character Range"
+ _ranges = [(0x4e00, 0x9fff), (0x3000, 0x303f),]
+
+ class Japanese(unicode_set):
+ "Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges"
+ _ranges = []
+
+ class Kanji(unicode_set):
+ "Unicode set for Kanji Unicode Character Range"
+ _ranges = [(0x4E00, 0x9Fbf), (0x3000, 0x303f),]
+
+ class Hiragana(unicode_set):
+ "Unicode set for Hiragana Unicode Character Range"
+ _ranges = [(0x3040, 0x309f),]
+
+ class Katakana(unicode_set):
+ "Unicode set for Katakana Unicode Character Range"
+ _ranges = [(0x30a0, 0x30ff),]
+
+ class Korean(unicode_set):
+ "Unicode set for Korean Unicode Character Range"
+ _ranges = [(0xac00, 0xd7af), (0x1100, 0x11ff), (0x3130, 0x318f), (0xa960, 0xa97f), (0xd7b0, 0xd7ff), (0x3000, 0x303f),]
+
+ class CJK(Chinese, Japanese, Korean):
+ "Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range"
+ pass
+
+ class Thai(unicode_set):
+ "Unicode set for Thai Unicode Character Range"
+ _ranges = [(0x0e01, 0x0e3a), (0x0e3f, 0x0e5b),]
+
+ class Arabic(unicode_set):
+ "Unicode set for Arabic Unicode Character Range"
+ _ranges = [(0x0600, 0x061b), (0x061e, 0x06ff), (0x0700, 0x077f),]
+
+ class Hebrew(unicode_set):
+ "Unicode set for Hebrew Unicode Character Range"
+ _ranges = [(0x0590, 0x05ff),]
+
+ class Devanagari(unicode_set):
+ "Unicode set for Devanagari Unicode Character Range"
+ _ranges = [(0x0900, 0x097f), (0xa8e0, 0xa8ff)]
+
+pyparsing_unicode.Japanese._ranges = (pyparsing_unicode.Japanese.Kanji._ranges
+ + pyparsing_unicode.Japanese.Hiragana._ranges
+ + pyparsing_unicode.Japanese.Katakana._ranges)
+
+# define ranges in language character sets
+if PY_3:
+ setattr(pyparsing_unicode, u"العربية", pyparsing_unicode.Arabic)
+ setattr(pyparsing_unicode, u"中文", pyparsing_unicode.Chinese)
+ setattr(pyparsing_unicode, u"кириллица", pyparsing_unicode.Cyrillic)
+ setattr(pyparsing_unicode, u"Ελληνικά", pyparsing_unicode.Greek)
+ setattr(pyparsing_unicode, u"עִברִית", pyparsing_unicode.Hebrew)
+ setattr(pyparsing_unicode, u"日本語", pyparsing_unicode.Japanese)
+ setattr(pyparsing_unicode.Japanese, u"漢字", pyparsing_unicode.Japanese.Kanji)
+ setattr(pyparsing_unicode.Japanese, u"カタカナ", pyparsing_unicode.Japanese.Katakana)
+ setattr(pyparsing_unicode.Japanese, u"ひらがな", pyparsing_unicode.Japanese.Hiragana)
+ setattr(pyparsing_unicode, u"한국어", pyparsing_unicode.Korean)
+ setattr(pyparsing_unicode, u"ไทย", pyparsing_unicode.Thai)
+ setattr(pyparsing_unicode, u"देवनागरी", pyparsing_unicode.Devanagari)
+
+
+class pyparsing_test:
+ """
+ namespace class for classes useful in writing unit tests
+ """
+
+ class reset_pyparsing_context:
+ """
+ Context manager to be used when writing unit tests that modify pyparsing config values:
+ - packrat parsing
+ - default whitespace characters.
+ - default keyword characters
+ - literal string auto-conversion class
+ - __diag__ settings
+
+ Example:
+ with reset_pyparsing_context():
+ # test that literals used to construct a grammar are automatically suppressed
+ ParserElement.inlineLiteralsUsing(Suppress)
+
+ term = Word(alphas) | Word(nums)
+ group = Group('(' + term[...] + ')')
+
+ # assert that the '()' characters are not included in the parsed tokens
+ self.assertParseAndCheckLisst(group, "(abc 123 def)", ['abc', '123', 'def'])
+
+ # after exiting context manager, literals are converted to Literal expressions again
+ """
+
+ def __init__(self):
+ self._save_context = {}
+
+ def save(self):
+ self._save_context["default_whitespace"] = ParserElement.DEFAULT_WHITE_CHARS
+ self._save_context["default_keyword_chars"] = Keyword.DEFAULT_KEYWORD_CHARS
+ self._save_context[
+ "literal_string_class"
+ ] = ParserElement._literalStringClass
+ self._save_context["packrat_enabled"] = ParserElement._packratEnabled
+ self._save_context["packrat_parse"] = ParserElement._parse
+ self._save_context["__diag__"] = {
+ name: getattr(__diag__, name) for name in __diag__._all_names
+ }
+ self._save_context["__compat__"] = {
+ "collect_all_And_tokens": __compat__.collect_all_And_tokens
+ }
+ return self
+
+ def restore(self):
+ # reset pyparsing global state
+ if (
+ ParserElement.DEFAULT_WHITE_CHARS
+ != self._save_context["default_whitespace"]
+ ):
+ ParserElement.setDefaultWhitespaceChars(
+ self._save_context["default_whitespace"]
+ )
+ Keyword.DEFAULT_KEYWORD_CHARS = self._save_context["default_keyword_chars"]
+ ParserElement.inlineLiteralsUsing(
+ self._save_context["literal_string_class"]
+ )
+ for name, value in self._save_context["__diag__"].items():
+ setattr(__diag__, name, value)
+ ParserElement._packratEnabled = self._save_context["packrat_enabled"]
+ ParserElement._parse = self._save_context["packrat_parse"]
+ __compat__.collect_all_And_tokens = self._save_context["__compat__"]
+
+ def __enter__(self):
+ return self.save()
+
+ def __exit__(self, *args):
+ return self.restore()
+
+ class TestParseResultsAsserts:
+ """
+ A mixin class to add parse results assertion methods to normal unittest.TestCase classes.
+ """
+ def assertParseResultsEquals(
+ self, result, expected_list=None, expected_dict=None, msg=None
+ ):
+ """
+ Unit test assertion to compare a ParseResults object with an optional expected_list,
+ and compare any defined results names with an optional expected_dict.
+ """
+ if expected_list is not None:
+ self.assertEqual(expected_list, result.asList(), msg=msg)
+ if expected_dict is not None:
+ self.assertEqual(expected_dict, result.asDict(), msg=msg)
+
+ def assertParseAndCheckList(
+ self, expr, test_string, expected_list, msg=None, verbose=True
+ ):
+ """
+ Convenience wrapper assert to test a parser element and input string, and assert that
+ the resulting ParseResults.asList() is equal to the expected_list.
+ """
+ result = expr.parseString(test_string, parseAll=True)
+ if verbose:
+ print(result.dump())
+ self.assertParseResultsEquals(result, expected_list=expected_list, msg=msg)
+
+ def assertParseAndCheckDict(
+ self, expr, test_string, expected_dict, msg=None, verbose=True
+ ):
+ """
+ Convenience wrapper assert to test a parser element and input string, and assert that
+ the resulting ParseResults.asDict() is equal to the expected_dict.
+ """
+ result = expr.parseString(test_string, parseAll=True)
+ if verbose:
+ print(result.dump())
+ self.assertParseResultsEquals(result, expected_dict=expected_dict, msg=msg)
+
+ def assertRunTestResults(
+ self, run_tests_report, expected_parse_results=None, msg=None
+ ):
+ """
+ Unit test assertion to evaluate output of ParserElement.runTests(). If a list of
+ list-dict tuples is given as the expected_parse_results argument, then these are zipped
+ with the report tuples returned by runTests and evaluated using assertParseResultsEquals.
+ Finally, asserts that the overall runTests() success value is True.
+
+ :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests
+ :param expected_parse_results (optional): [tuple(str, list, dict, Exception)]
+ """
+ run_test_success, run_test_results = run_tests_report
+
+ if expected_parse_results is not None:
+ merged = [
+ (rpt[0], rpt[1], expected)
+ for rpt, expected in zip(run_test_results, expected_parse_results)
+ ]
+ for test_string, result, expected in merged:
+ # expected should be a tuple containing a list and/or a dict or an exception,
+ # and optional failure message string
+ # an empty tuple will skip any result validation
+ fail_msg = next(
+ (exp for exp in expected if isinstance(exp, str)), None
+ )
+ expected_exception = next(
+ (
+ exp
+ for exp in expected
+ if isinstance(exp, type) and issubclass(exp, Exception)
+ ),
+ None,
+ )
+ if expected_exception is not None:
+ with self.assertRaises(
+ expected_exception=expected_exception, msg=fail_msg or msg
+ ):
+ if isinstance(result, Exception):
+ raise result
+ else:
+ expected_list = next(
+ (exp for exp in expected if isinstance(exp, list)), None
+ )
+ expected_dict = next(
+ (exp for exp in expected if isinstance(exp, dict)), None
+ )
+ if (expected_list, expected_dict) != (None, None):
+ self.assertParseResultsEquals(
+ result,
+ expected_list=expected_list,
+ expected_dict=expected_dict,
+ msg=fail_msg or msg,
+ )
+ else:
+ # warning here maybe?
+ print("no validation for {!r}".format(test_string))
+
+ # do this last, in case some specific test results can be reported instead
+ self.assertTrue(
+ run_test_success, msg=msg if msg is not None else "failed runTests"
+ )
+
+ @contextmanager
+ def assertRaisesParseException(self, exc_type=ParseException, msg=None):
+ with self.assertRaises(exc_type, msg=msg):
+ yield
+
+
+if __name__ == "__main__":
+
+ selectToken = CaselessLiteral("select")
+ fromToken = CaselessLiteral("from")
+
+ ident = Word(alphas, alphanums + "_$")
+
+ columnName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ columnNameList = Group(delimitedList(columnName)).setName("columns")
+ columnSpec = ('*' | columnNameList)
+
+ tableName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ tableNameList = Group(delimitedList(tableName)).setName("tables")
+
+ simpleSQL = selectToken("command") + columnSpec("columns") + fromToken + tableNameList("tables")
+
+ # demo runTests method, including embedded comments in test string
+ simpleSQL.runTests("""
+ # '*' as column list and dotted table name
+ select * from SYS.XYZZY
+
+ # caseless match on "SELECT", and casts back to "select"
+ SELECT * from XYZZY, ABC
+
+ # list of column names, and mixed case SELECT keyword
+ Select AA,BB,CC from Sys.dual
+
+ # multiple tables
+ Select A, B, C from Sys.dual, Table2
+
+ # invalid SELECT keyword - should fail
+ Xelect A, B, C from Sys.dual
+
+ # incomplete command - should fail
+ Select
+
+ # invalid column name - should fail
+ Select ^^^ frox Sys.dual
+
+ """)
+
+ pyparsing_common.number.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ # any int or real number, returned as float
+ pyparsing_common.fnumber.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ pyparsing_common.hex_integer.runTests("""
+ 100
+ FF
+ """)
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests("""
+ 12345678-1234-5678-1234-567812345678
+ """)
diff --git a/shotgun_api3/lib/requirements.txt b/shotgun_api3/lib/requirements.txt
new file mode 100644
index 000000000..a3bc11436
--- /dev/null
+++ b/shotgun_api3/lib/requirements.txt
@@ -0,0 +1,33 @@
+# Copyright (c) 2009-2019, Shotgun Software Inc.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# - Redistributions of source code must retain the above copyright notice,
+# this list of conditions and the following disclaimer.
+#
+# - Redistributions in binary form must reproduce the above copyright notice,
+# this list of conditions and the following disclaimer in the documentation
+# and/or other materials provided with the distribution.
+#
+# - Neither the name of the Shotgun Software Inc nor the names of its
+# contributors may be used to endorse or promote products derived from this
+# software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+# This file is unused. It is left there so Github can warn us is a CVE is
+# released for our dependencies.
+httplib2==0.22.0
+certifi==2024.7.4
+pyparsing==2.4.7
diff --git a/shotgun_api3/lib/sgtimezone.py b/shotgun_api3/lib/sgtimezone.py
index ef06c8640..df0b73281 100644
--- a/shotgun_api3/lib/sgtimezone.py
+++ b/shotgun_api3/lib/sgtimezone.py
@@ -1,13 +1,25 @@
#! /opt/local/bin/python
+
+# Copyright (c) 2019 Shotgun Software Inc.
+#
+# CONFIDENTIAL AND PROPRIETARY
+#
+# This work is provided "AS IS" and subject to the Shotgun Pipeline Toolkit
+# Source Code License included in this distribution package. See LICENSE.
+# By accessing, using, copying or modifying this work you indicate your
+# agreement to the Shotgun Pipeline Toolkit Source Code License. All rights
+# not expressly granted therein are reserved by Shotgun Software Inc.
+
# ----------------------------------------------------------------------------
# SG_TIMEZONE module
-# this is rolled into the this shotgun api file to avoid having to require
+# this is rolled into the this shotgun api file to avoid having to require
# current users of api2 to install new modules and modify PYTHONPATH info.
# ----------------------------------------------------------------------------
-from datetime import tzinfo, timedelta, datetime
+from datetime import tzinfo, timedelta
import time as _time
+
class SgTimezone(object):
'''
Shotgun's server infrastructure is configured for Coordinated Universal
@@ -16,14 +28,14 @@ class SgTimezone(object):
'''
ZERO = timedelta(0)
- STDOFFSET = timedelta(seconds = -_time.timezone)
+ STDOFFSET = timedelta(seconds=-_time.timezone)
if _time.daylight:
- DSTOFFSET = timedelta(seconds = -_time.altzone)
+ DSTOFFSET = timedelta(seconds=-_time.altzone)
else:
DSTOFFSET = STDOFFSET
DSTDIFF = DSTOFFSET - STDOFFSET
-
- def __init__(self):
+
+ def __init__(self):
self.utc = UTC()
self.local = LocalTimezone()
@@ -42,28 +54,30 @@ def LocalTimezone(cls):
class, we allow instantiation via SgTimezone
'''
return LocalTimezone()
-
+
+
class UTC(tzinfo):
'''
Implementation of datetime's tzinfo to provide consistent calculated
offsets against Coordinated Universal Time (UTC)
'''
-
+
def utcoffset(self, dt):
return SgTimezone.ZERO
-
+
def tzname(self, dt):
return "UTC"
-
+
def dst(self, dt):
return SgTimezone.ZERO
+
class LocalTimezone(tzinfo):
'''
Implementation of datetime's tzinfo to provide convenient conversion
between Shotgun server time and local user time
'''
-
+
def utcoffset(self, dt):
'''
Difference between the user's local timezone and UTC timezone in seconds
@@ -72,7 +86,7 @@ def utcoffset(self, dt):
return SgTimezone.DSTOFFSET
else:
return SgTimezone.STDOFFSET
-
+
def dst(self, dt):
'''
Daylight savings time (dst) offset in seconds
@@ -81,14 +95,14 @@ def dst(self, dt):
return SgTimezone.DSTDIFF
else:
return SgTimezone.ZERO
-
+
def tzname(self, dt):
'''
Name of the user's local timezone, including a reference
to daylight savings time (dst) if applicable
'''
return _time.tzname[self._isdst(dt)]
-
+
def _isdst(self, dt):
'''
Calculate whether the timestamp in question was in daylight savings
diff --git a/shotgun_api3/lib/simplejson/__init__.py b/shotgun_api3/lib/simplejson/__init__.py
deleted file mode 100644
index 210b957a9..000000000
--- a/shotgun_api3/lib/simplejson/__init__.py
+++ /dev/null
@@ -1,438 +0,0 @@
-r"""JSON (JavaScript Object Notation) is a subset of
-JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
-interchange format.
-
-:mod:`simplejson` exposes an API familiar to users of the standard library
-:mod:`marshal` and :mod:`pickle` modules. It is the externally maintained
-version of the :mod:`json` library contained in Python 2.6, but maintains
-compatibility with Python 2.4 and Python 2.5 and (currently) has
-significant performance advantages, even without using the optional C
-extension for speedups.
-
-Encoding basic Python object hierarchies::
-
- >>> import simplejson as json
- >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
- '["foo", {"bar": ["baz", null, 1.0, 2]}]'
- >>> print json.dumps("\"foo\bar")
- "\"foo\bar"
- >>> print json.dumps(u'\u1234')
- "\u1234"
- >>> print json.dumps('\\')
- "\\"
- >>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
- {"a": 0, "b": 0, "c": 0}
- >>> from StringIO import StringIO
- >>> io = StringIO()
- >>> json.dump(['streaming API'], io)
- >>> io.getvalue()
- '["streaming API"]'
-
-Compact encoding::
-
- >>> import simplejson as json
- >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
- '[1,2,3,{"4":5,"6":7}]'
-
-Pretty printing::
-
- >>> import simplejson as json
- >>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=' ')
- >>> print '\n'.join([l.rstrip() for l in s.splitlines()])
- {
- "4": 5,
- "6": 7
- }
-
-Decoding JSON::
-
- >>> import simplejson as json
- >>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
- >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
- True
- >>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
- True
- >>> from StringIO import StringIO
- >>> io = StringIO('["streaming API"]')
- >>> json.load(io)[0] == 'streaming API'
- True
-
-Specializing JSON object decoding::
-
- >>> import simplejson as json
- >>> def as_complex(dct):
- ... if '__complex__' in dct:
- ... return complex(dct['real'], dct['imag'])
- ... return dct
- ...
- >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
- ... object_hook=as_complex)
- (1+2j)
- >>> from decimal import Decimal
- >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
- True
-
-Specializing JSON object encoding::
-
- >>> import simplejson as json
- >>> def encode_complex(obj):
- ... if isinstance(obj, complex):
- ... return [obj.real, obj.imag]
- ... raise TypeError(repr(o) + " is not JSON serializable")
- ...
- >>> json.dumps(2 + 1j, default=encode_complex)
- '[2.0, 1.0]'
- >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
- '[2.0, 1.0]'
- >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
- '[2.0, 1.0]'
-
-
-Using simplejson.tool from the shell to validate and pretty-print::
-
- $ echo '{"json":"obj"}' | python -m simplejson.tool
- {
- "json": "obj"
- }
- $ echo '{ 1.2:3.4}' | python -m simplejson.tool
- Expecting property name: line 1 column 2 (char 2)
-"""
-__version__ = '2.1.6'
-__all__ = [
- 'dump', 'dumps', 'load', 'loads',
- 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
- 'OrderedDict',
-]
-
-__author__ = 'Bob Ippolito '
-
-from decimal import Decimal
-
-from decoder import JSONDecoder, JSONDecodeError
-from encoder import JSONEncoder
-def _import_OrderedDict():
- import collections
- try:
- return collections.OrderedDict
- except AttributeError:
- import ordered_dict
- return ordered_dict.OrderedDict
-OrderedDict = _import_OrderedDict()
-
-def _import_c_make_encoder():
- try:
- from simplejson._speedups import make_encoder
- return make_encoder
- except ImportError:
- return None
-
-_default_encoder = JSONEncoder(
- skipkeys=False,
- ensure_ascii=True,
- check_circular=True,
- allow_nan=True,
- indent=None,
- separators=None,
- encoding='utf-8',
- default=None,
- use_decimal=False,
-)
-
-def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- encoding='utf-8', default=None, use_decimal=False, **kw):
- """Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
- ``.write()``-supporting file-like object).
-
- If ``skipkeys`` is true then ``dict`` keys that are not basic types
- (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
- will be skipped instead of raising a ``TypeError``.
-
- If ``ensure_ascii`` is false, then the some chunks written to ``fp``
- may be ``unicode`` instances, subject to normal Python ``str`` to
- ``unicode`` coercion rules. Unless ``fp.write()`` explicitly
- understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
- to cause an error.
-
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``OverflowError`` (or worse).
-
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
- in strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
-
- If *indent* is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If ``separators`` is an ``(item_separator, dict_separator)`` tuple
- then it will be used instead of the default ``(', ', ': ')`` separators.
- ``(',', ':')`` is the most compact JSON representation.
-
- ``encoding`` is the character encoding for str instances, default is UTF-8.
-
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
-
- If *use_decimal* is true (default: ``False``) then decimal.Decimal
- will be natively serialized to JSON with full precision.
-
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg.
-
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- encoding == 'utf-8' and default is None and not use_decimal
- and not kw):
- iterable = _default_encoder.iterencode(obj)
- else:
- if cls is None:
- cls = JSONEncoder
- iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators, encoding=encoding,
- default=default, use_decimal=use_decimal, **kw).iterencode(obj)
- # could accelerate with writelines in some versions of Python, at
- # a debuggability cost
- for chunk in iterable:
- fp.write(chunk)
-
-
-def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- encoding='utf-8', default=None, use_decimal=False, **kw):
- """Serialize ``obj`` to a JSON formatted ``str``.
-
- If ``skipkeys`` is false then ``dict`` keys that are not basic types
- (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
- will be skipped instead of raising a ``TypeError``.
-
- If ``ensure_ascii`` is false, then the return value will be a
- ``unicode`` instance subject to normal Python ``str`` to ``unicode``
- coercion rules instead of being escaped to an ASCII ``str``.
-
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``OverflowError`` (or worse).
-
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
- strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
-
- If ``indent`` is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If ``separators`` is an ``(item_separator, dict_separator)`` tuple
- then it will be used instead of the default ``(', ', ': ')`` separators.
- ``(',', ':')`` is the most compact JSON representation.
-
- ``encoding`` is the character encoding for str instances, default is UTF-8.
-
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
-
- If *use_decimal* is true (default: ``False``) then decimal.Decimal
- will be natively serialized to JSON with full precision.
-
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg.
-
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- encoding == 'utf-8' and default is None and not use_decimal
- and not kw):
- return _default_encoder.encode(obj)
- if cls is None:
- cls = JSONEncoder
- return cls(
- skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators, encoding=encoding, default=default,
- use_decimal=use_decimal, **kw).encode(obj)
-
-
-_default_decoder = JSONDecoder(encoding=None, object_hook=None,
- object_pairs_hook=None)
-
-
-def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None,
- use_decimal=False, **kw):
- """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
- a JSON document) to a Python object.
-
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- If *use_decimal* is true (default: ``False``) then it implies
- parse_float=decimal.Decimal for parity with ``dump``.
-
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
-
- """
- return loads(fp.read(),
- encoding=encoding, cls=cls, object_hook=object_hook,
- parse_float=parse_float, parse_int=parse_int,
- parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,
- use_decimal=use_decimal, **kw)
-
-
-def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None,
- use_decimal=False, **kw):
- """Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
- document) to a Python object.
-
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- If *use_decimal* is true (default: ``False``) then it implies
- parse_float=decimal.Decimal for parity with ``dump``.
-
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
-
- """
- if (cls is None and encoding is None and object_hook is None and
- parse_int is None and parse_float is None and
- parse_constant is None and object_pairs_hook is None
- and not use_decimal and not kw):
- return _default_decoder.decode(s)
- if cls is None:
- cls = JSONDecoder
- if object_hook is not None:
- kw['object_hook'] = object_hook
- if object_pairs_hook is not None:
- kw['object_pairs_hook'] = object_pairs_hook
- if parse_float is not None:
- kw['parse_float'] = parse_float
- if parse_int is not None:
- kw['parse_int'] = parse_int
- if parse_constant is not None:
- kw['parse_constant'] = parse_constant
- if use_decimal:
- if parse_float is not None:
- raise TypeError("use_decimal=True implies parse_float=Decimal")
- kw['parse_float'] = Decimal
- return cls(encoding=encoding, **kw).decode(s)
-
-
-def _toggle_speedups(enabled):
- import simplejson.decoder as dec
- import simplejson.encoder as enc
- import simplejson.scanner as scan
- c_make_encoder = _import_c_make_encoder()
- if enabled:
- dec.scanstring = dec.c_scanstring or dec.py_scanstring
- enc.c_make_encoder = c_make_encoder
- enc.encode_basestring_ascii = (enc.c_encode_basestring_ascii or
- enc.py_encode_basestring_ascii)
- scan.make_scanner = scan.c_make_scanner or scan.py_make_scanner
- else:
- dec.scanstring = dec.py_scanstring
- enc.c_make_encoder = None
- enc.encode_basestring_ascii = enc.py_encode_basestring_ascii
- scan.make_scanner = scan.py_make_scanner
- dec.make_scanner = scan.make_scanner
- global _default_decoder
- _default_decoder = JSONDecoder(
- encoding=None,
- object_hook=None,
- object_pairs_hook=None,
- )
- global _default_encoder
- _default_encoder = JSONEncoder(
- skipkeys=False,
- ensure_ascii=True,
- check_circular=True,
- allow_nan=True,
- indent=None,
- separators=None,
- encoding='utf-8',
- default=None,
- )
diff --git a/shotgun_api3/lib/simplejson/_speedups.c b/shotgun_api3/lib/simplejson/_speedups.c
deleted file mode 100644
index 8b3474702..000000000
--- a/shotgun_api3/lib/simplejson/_speedups.c
+++ /dev/null
@@ -1,2652 +0,0 @@
-#include "Python.h"
-#include "structmember.h"
-#if PY_VERSION_HEX < 0x02070000 && !defined(PyOS_string_to_double)
-#define PyOS_string_to_double json_PyOS_string_to_double
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception);
-static double
-json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception) {
- double x;
- assert(endptr == NULL);
- assert(overflow_exception == NULL);
- PyFPE_START_PROTECT("json_PyOS_string_to_double", return -1.0;)
- x = PyOS_ascii_atof(s);
- PyFPE_END_PROTECT(x)
- return x;
-}
-#endif
-#if PY_VERSION_HEX < 0x02060000 && !defined(Py_TYPE)
-#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
-#endif
-#if PY_VERSION_HEX < 0x02060000 && !defined(Py_SIZE)
-#define Py_SIZE(ob) (((PyVarObject*)(ob))->ob_size)
-#endif
-#if PY_VERSION_HEX < 0x02050000 && !defined(PY_SSIZE_T_MIN)
-typedef int Py_ssize_t;
-#define PY_SSIZE_T_MAX INT_MAX
-#define PY_SSIZE_T_MIN INT_MIN
-#define PyInt_FromSsize_t PyInt_FromLong
-#define PyInt_AsSsize_t PyInt_AsLong
-#endif
-#ifndef Py_IS_FINITE
-#define Py_IS_FINITE(X) (!Py_IS_INFINITY(X) && !Py_IS_NAN(X))
-#endif
-
-#ifdef __GNUC__
-#define UNUSED __attribute__((__unused__))
-#else
-#define UNUSED
-#endif
-
-#define DEFAULT_ENCODING "utf-8"
-
-#define PyScanner_Check(op) PyObject_TypeCheck(op, &PyScannerType)
-#define PyScanner_CheckExact(op) (Py_TYPE(op) == &PyScannerType)
-#define PyEncoder_Check(op) PyObject_TypeCheck(op, &PyEncoderType)
-#define PyEncoder_CheckExact(op) (Py_TYPE(op) == &PyEncoderType)
-#define Decimal_Check(op) (PyObject_TypeCheck(op, DecimalTypePtr))
-
-static PyTypeObject PyScannerType;
-static PyTypeObject PyEncoderType;
-static PyTypeObject *DecimalTypePtr;
-
-typedef struct _PyScannerObject {
- PyObject_HEAD
- PyObject *encoding;
- PyObject *strict;
- PyObject *object_hook;
- PyObject *pairs_hook;
- PyObject *parse_float;
- PyObject *parse_int;
- PyObject *parse_constant;
- PyObject *memo;
-} PyScannerObject;
-
-static PyMemberDef scanner_members[] = {
- {"encoding", T_OBJECT, offsetof(PyScannerObject, encoding), READONLY, "encoding"},
- {"strict", T_OBJECT, offsetof(PyScannerObject, strict), READONLY, "strict"},
- {"object_hook", T_OBJECT, offsetof(PyScannerObject, object_hook), READONLY, "object_hook"},
- {"object_pairs_hook", T_OBJECT, offsetof(PyScannerObject, pairs_hook), READONLY, "object_pairs_hook"},
- {"parse_float", T_OBJECT, offsetof(PyScannerObject, parse_float), READONLY, "parse_float"},
- {"parse_int", T_OBJECT, offsetof(PyScannerObject, parse_int), READONLY, "parse_int"},
- {"parse_constant", T_OBJECT, offsetof(PyScannerObject, parse_constant), READONLY, "parse_constant"},
- {NULL}
-};
-
-typedef struct _PyEncoderObject {
- PyObject_HEAD
- PyObject *markers;
- PyObject *defaultfn;
- PyObject *encoder;
- PyObject *indent;
- PyObject *key_separator;
- PyObject *item_separator;
- PyObject *sort_keys;
- PyObject *skipkeys;
- PyObject *key_memo;
- int fast_encode;
- int allow_nan;
- int use_decimal;
-} PyEncoderObject;
-
-static PyMemberDef encoder_members[] = {
- {"markers", T_OBJECT, offsetof(PyEncoderObject, markers), READONLY, "markers"},
- {"default", T_OBJECT, offsetof(PyEncoderObject, defaultfn), READONLY, "default"},
- {"encoder", T_OBJECT, offsetof(PyEncoderObject, encoder), READONLY, "encoder"},
- {"indent", T_OBJECT, offsetof(PyEncoderObject, indent), READONLY, "indent"},
- {"key_separator", T_OBJECT, offsetof(PyEncoderObject, key_separator), READONLY, "key_separator"},
- {"item_separator", T_OBJECT, offsetof(PyEncoderObject, item_separator), READONLY, "item_separator"},
- {"sort_keys", T_OBJECT, offsetof(PyEncoderObject, sort_keys), READONLY, "sort_keys"},
- {"skipkeys", T_OBJECT, offsetof(PyEncoderObject, skipkeys), READONLY, "skipkeys"},
- {"key_memo", T_OBJECT, offsetof(PyEncoderObject, key_memo), READONLY, "key_memo"},
- {NULL}
-};
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars);
-static PyObject *
-ascii_escape_unicode(PyObject *pystr);
-static PyObject *
-ascii_escape_str(PyObject *pystr);
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr);
-void init_speedups(void);
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr);
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx);
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-scanner_dealloc(PyObject *self);
-static int
-scanner_clear(PyObject *self);
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds);
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds);
-static void
-encoder_dealloc(PyObject *self);
-static int
-encoder_clear(PyObject *self);
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level);
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level);
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level);
-static PyObject *
-_encoded_const(PyObject *obj);
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end);
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj);
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr);
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr);
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj);
-
-#define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '"')
-#define IS_WHITESPACE(c) (((c) == ' ') || ((c) == '\t') || ((c) == '\n') || ((c) == '\r'))
-
-#define MIN_EXPANSION 6
-#ifdef Py_UNICODE_WIDE
-#define MAX_EXPANSION (2 * MIN_EXPANSION)
-#else
-#define MAX_EXPANSION MIN_EXPANSION
-#endif
-
-static int
-_convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr)
-{
- /* PyObject to Py_ssize_t converter */
- *size_ptr = PyInt_AsSsize_t(o);
- if (*size_ptr == -1 && PyErr_Occurred())
- return 0;
- return 1;
-}
-
-static PyObject *
-_convertPyInt_FromSsize_t(Py_ssize_t *size_ptr)
-{
- /* Py_ssize_t to PyObject converter */
- return PyInt_FromSsize_t(*size_ptr);
-}
-
-static Py_ssize_t
-ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars)
-{
- /* Escape unicode code point c to ASCII escape sequences
- in char *output. output must have at least 12 bytes unused to
- accommodate an escaped surrogate pair "\uXXXX\uXXXX" */
- output[chars++] = '\\';
- switch (c) {
- case '\\': output[chars++] = (char)c; break;
- case '"': output[chars++] = (char)c; break;
- case '\b': output[chars++] = 'b'; break;
- case '\f': output[chars++] = 'f'; break;
- case '\n': output[chars++] = 'n'; break;
- case '\r': output[chars++] = 'r'; break;
- case '\t': output[chars++] = 't'; break;
- default:
-#ifdef Py_UNICODE_WIDE
- if (c >= 0x10000) {
- /* UTF-16 surrogate pair */
- Py_UNICODE v = c - 0x10000;
- c = 0xd800 | ((v >> 10) & 0x3ff);
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- c = 0xdc00 | (v & 0x3ff);
- output[chars++] = '\\';
- }
-#endif
- output[chars++] = 'u';
- output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf];
- output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf];
- output[chars++] = "0123456789abcdef"[(c ) & 0xf];
- }
- return chars;
-}
-
-static PyObject *
-ascii_escape_unicode(PyObject *pystr)
-{
- /* Take a PyUnicode pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t max_output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- Py_UNICODE *input_unicode;
-
- input_chars = PyUnicode_GET_SIZE(pystr);
- input_unicode = PyUnicode_AS_UNICODE(pystr);
-
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- max_output_size = 2 + (input_chars * MAX_EXPANSION);
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- chars = 0;
- output[chars++] = '"';
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = input_unicode[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- if (output_size - chars < (1 + MAX_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- Py_ssize_t new_output_size = output_size * 2;
- /* This is an upper bound */
- if (new_output_size > max_output_size) {
- new_output_size = max_output_size;
- }
- /* Make sure that the output size changed before resizing */
- if (new_output_size != output_size) {
- output_size = new_output_size;
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-ascii_escape_str(PyObject *pystr)
-{
- /* Take a PyString pystr and return a new ASCII-only escaped PyString */
- Py_ssize_t i;
- Py_ssize_t input_chars;
- Py_ssize_t output_size;
- Py_ssize_t chars;
- PyObject *rval;
- char *output;
- char *input_str;
-
- input_chars = PyString_GET_SIZE(pystr);
- input_str = PyString_AS_STRING(pystr);
-
- /* Fast path for a string that's already ASCII */
- for (i = 0; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (!S_CHAR(c)) {
- /* If we have to escape something, scan the string for unicode */
- Py_ssize_t j;
- for (j = i; j < input_chars; j++) {
- c = (Py_UNICODE)(unsigned char)input_str[j];
- if (c > 0x7f) {
- /* We hit a non-ASCII character, bail to unicode mode */
- PyObject *uni;
- uni = PyUnicode_DecodeUTF8(input_str, input_chars, "strict");
- if (uni == NULL) {
- return NULL;
- }
- rval = ascii_escape_unicode(uni);
- Py_DECREF(uni);
- return rval;
- }
- }
- break;
- }
- }
-
- if (i == input_chars) {
- /* Input is already ASCII */
- output_size = 2 + input_chars;
- }
- else {
- /* One char input can be up to 6 chars output, estimate 4 of these */
- output_size = 2 + (MIN_EXPANSION * 4) + input_chars;
- }
- rval = PyString_FromStringAndSize(NULL, output_size);
- if (rval == NULL) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- output[0] = '"';
-
- /* We know that everything up to i is ASCII already */
- chars = i + 1;
- memcpy(&output[1], input_str, i);
-
- for (; i < input_chars; i++) {
- Py_UNICODE c = (Py_UNICODE)(unsigned char)input_str[i];
- if (S_CHAR(c)) {
- output[chars++] = (char)c;
- }
- else {
- chars = ascii_escape_char(c, output, chars);
- }
- /* An ASCII char can't possibly expand to a surrogate! */
- if (output_size - chars < (1 + MIN_EXPANSION)) {
- /* There's more than four, so let's resize by a lot */
- output_size *= 2;
- if (output_size > 2 + (input_chars * MIN_EXPANSION)) {
- output_size = 2 + (input_chars * MIN_EXPANSION);
- }
- if (_PyString_Resize(&rval, output_size) == -1) {
- return NULL;
- }
- output = PyString_AS_STRING(rval);
- }
- }
- output[chars++] = '"';
- if (_PyString_Resize(&rval, chars) == -1) {
- return NULL;
- }
- return rval;
-}
-
-static void
-raise_errmsg(char *msg, PyObject *s, Py_ssize_t end)
-{
- /* Use the Python function simplejson.decoder.errmsg to raise a nice
- looking ValueError exception */
- static PyObject *JSONDecodeError = NULL;
- PyObject *exc;
- if (JSONDecodeError == NULL) {
- PyObject *decoder = PyImport_ImportModule("simplejson.decoder");
- if (decoder == NULL)
- return;
- JSONDecodeError = PyObject_GetAttrString(decoder, "JSONDecodeError");
- Py_DECREF(decoder);
- if (JSONDecodeError == NULL)
- return;
- }
- exc = PyObject_CallFunction(JSONDecodeError, "(zOO&)", msg, s, _convertPyInt_FromSsize_t, &end);
- if (exc) {
- PyErr_SetObject(JSONDecodeError, exc);
- Py_DECREF(exc);
- }
-}
-
-static PyObject *
-join_list_unicode(PyObject *lst)
-{
- /* return u''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyUnicode_FromUnicode(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-join_list_string(PyObject *lst)
-{
- /* return ''.join(lst) */
- static PyObject *joinfn = NULL;
- if (joinfn == NULL) {
- PyObject *ustr = PyString_FromStringAndSize(NULL, 0);
- if (ustr == NULL)
- return NULL;
-
- joinfn = PyObject_GetAttrString(ustr, "join");
- Py_DECREF(ustr);
- if (joinfn == NULL)
- return NULL;
- }
- return PyObject_CallFunctionObjArgs(joinfn, lst, NULL);
-}
-
-static PyObject *
-_build_rval_index_tuple(PyObject *rval, Py_ssize_t idx) {
- /* return (rval, idx) tuple, stealing reference to rval */
- PyObject *tpl;
- PyObject *pyidx;
- /*
- steal a reference to rval, returns (rval, idx)
- */
- if (rval == NULL) {
- return NULL;
- }
- pyidx = PyInt_FromSsize_t(idx);
- if (pyidx == NULL) {
- Py_DECREF(rval);
- return NULL;
- }
- tpl = PyTuple_New(2);
- if (tpl == NULL) {
- Py_DECREF(pyidx);
- Py_DECREF(rval);
- return NULL;
- }
- PyTuple_SET_ITEM(tpl, 0, rval);
- PyTuple_SET_ITEM(tpl, 1, pyidx);
- return tpl;
-}
-
-#define APPEND_OLD_CHUNK \
- if (chunk != NULL) { \
- if (chunks == NULL) { \
- chunks = PyList_New(0); \
- if (chunks == NULL) { \
- goto bail; \
- } \
- } \
- if (PyList_Append(chunks, chunk)) { \
- goto bail; \
- } \
- Py_CLEAR(chunk); \
- }
-
-static PyObject *
-scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyString pystr.
- end is the index of the first character after the quote.
- encoding is the encoding of pystr (must be an ASCII superset)
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyString (if ASCII-only) or PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyString_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- int has_unicode = 0;
- char *buf = PyString_AS_STRING(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = (unsigned char)buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- else if (c > 0x7f) {
- has_unicode = 1;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- PyObject *strchunk;
- APPEND_OLD_CHUNK
- strchunk = PyString_FromStringAndSize(&buf[end], next - end);
- if (strchunk == NULL) {
- goto bail;
- }
- if (has_unicode) {
- chunk = PyUnicode_FromEncodedObject(strchunk, encoding, NULL);
- Py_DECREF(strchunk);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- chunk = strchunk;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- if (c > 0x7f) {
- has_unicode = 1;
- }
- APPEND_OLD_CHUNK
- if (has_unicode) {
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- else {
- char c_char = Py_CHARMASK(c);
- chunk = PyString_FromStringAndSize(&c_char, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyString_FromStringAndSize("", 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_string(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
-
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-
-static PyObject *
-scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr)
-{
- /* Read the JSON string from PyUnicode pystr.
- end is the index of the first character after the quote.
- if strict is zero then literal control characters are allowed
- *next_end_ptr is a return-by-reference index of the character
- after the end quote
-
- Return value is a new PyUnicode
- */
- PyObject *rval;
- Py_ssize_t len = PyUnicode_GET_SIZE(pystr);
- Py_ssize_t begin = end - 1;
- Py_ssize_t next = begin;
- const Py_UNICODE *buf = PyUnicode_AS_UNICODE(pystr);
- PyObject *chunks = NULL;
- PyObject *chunk = NULL;
-
- if (end < 0 || len <= end) {
- PyErr_SetString(PyExc_ValueError, "end is out of bounds");
- goto bail;
- }
- while (1) {
- /* Find the end of the string or the next escape */
- Py_UNICODE c = 0;
- for (next = end; next < len; next++) {
- c = buf[next];
- if (c == '"' || c == '\\') {
- break;
- }
- else if (strict && c <= 0x1f) {
- raise_errmsg("Invalid control character at", pystr, next);
- goto bail;
- }
- }
- if (!(c == '"' || c == '\\')) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- /* Pick up this chunk if it's not zero length */
- if (next != end) {
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&buf[end], next - end);
- if (chunk == NULL) {
- goto bail;
- }
- }
- next++;
- if (c == '"') {
- end = next;
- break;
- }
- if (next == len) {
- raise_errmsg("Unterminated string starting at", pystr, begin);
- goto bail;
- }
- c = buf[next];
- if (c != 'u') {
- /* Non-unicode backslash escapes */
- end = next + 1;
- switch (c) {
- case '"': break;
- case '\\': break;
- case '/': break;
- case 'b': c = '\b'; break;
- case 'f': c = '\f'; break;
- case 'n': c = '\n'; break;
- case 'r': c = '\r'; break;
- case 't': c = '\t'; break;
- default: c = 0;
- }
- if (c == 0) {
- raise_errmsg("Invalid \\escape", pystr, end - 2);
- goto bail;
- }
- }
- else {
- c = 0;
- next++;
- end = next + 4;
- if (end >= len) {
- raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1);
- goto bail;
- }
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- Py_UNICODE digit = buf[next];
- c <<= 4;
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
-#ifdef Py_UNICODE_WIDE
- /* Surrogate pair */
- if ((c & 0xfc00) == 0xd800) {
- Py_UNICODE c2 = 0;
- if (end + 6 >= len) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- if (buf[next++] != '\\' || buf[next++] != 'u') {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- end += 6;
- /* Decode 4 hex digits */
- for (; next < end; next++) {
- c2 <<= 4;
- Py_UNICODE digit = buf[next];
- switch (digit) {
- case '0': case '1': case '2': case '3': case '4':
- case '5': case '6': case '7': case '8': case '9':
- c2 |= (digit - '0'); break;
- case 'a': case 'b': case 'c': case 'd': case 'e':
- case 'f':
- c2 |= (digit - 'a' + 10); break;
- case 'A': case 'B': case 'C': case 'D': case 'E':
- case 'F':
- c2 |= (digit - 'A' + 10); break;
- default:
- raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5);
- goto bail;
- }
- }
- if ((c2 & 0xfc00) != 0xdc00) {
- raise_errmsg("Unpaired high surrogate", pystr, end - 5);
- goto bail;
- }
- c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00));
- }
- else if ((c & 0xfc00) == 0xdc00) {
- raise_errmsg("Unpaired low surrogate", pystr, end - 5);
- goto bail;
- }
-#endif
- }
- APPEND_OLD_CHUNK
- chunk = PyUnicode_FromUnicode(&c, 1);
- if (chunk == NULL) {
- goto bail;
- }
- }
-
- if (chunks == NULL) {
- if (chunk != NULL)
- rval = chunk;
- else
- rval = PyUnicode_FromUnicode(NULL, 0);
- }
- else {
- APPEND_OLD_CHUNK
- rval = join_list_unicode(chunks);
- if (rval == NULL) {
- goto bail;
- }
- Py_CLEAR(chunks);
- }
- *next_end_ptr = end;
- return rval;
-bail:
- *next_end_ptr = -1;
- Py_XDECREF(chunk);
- Py_XDECREF(chunks);
- return NULL;
-}
-
-PyDoc_STRVAR(pydoc_scanstring,
- "scanstring(basestring, end, encoding, strict=True) -> (str, end)\n"
- "\n"
- "Scan the string s for a JSON string. End is the index of the\n"
- "character in s after the quote that started the JSON string.\n"
- "Unescapes all valid JSON string escape sequences and raises ValueError\n"
- "on attempt to decode an invalid string. If strict is False then literal\n"
- "control characters are allowed in the string.\n"
- "\n"
- "Returns a tuple of the decoded string and the index of the character in s\n"
- "after the end quote."
-);
-
-static PyObject *
-py_scanstring(PyObject* self UNUSED, PyObject *args)
-{
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t end;
- Py_ssize_t next_end = -1;
- char *encoding = NULL;
- int strict = 1;
- if (!PyArg_ParseTuple(args, "OO&|zi:scanstring", &pystr, _convertPyInt_AsSsize_t, &end, &encoding, &strict)) {
- return NULL;
- }
- if (encoding == NULL) {
- encoding = DEFAULT_ENCODING;
- }
- if (PyString_Check(pystr)) {
- rval = scanstring_str(pystr, end, encoding, strict, &next_end);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scanstring_unicode(pystr, end, strict, &next_end);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- return _build_rval_index_tuple(rval, next_end);
-}
-
-PyDoc_STRVAR(pydoc_encode_basestring_ascii,
- "encode_basestring_ascii(basestring) -> str\n"
- "\n"
- "Return an ASCII-only JSON representation of a Python string"
-);
-
-static PyObject *
-py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr)
-{
- /* Return an ASCII-only JSON representation of a Python string */
- /* METH_O */
- if (PyString_Check(pystr)) {
- return ascii_escape_str(pystr);
- }
- else if (PyUnicode_Check(pystr)) {
- return ascii_escape_unicode(pystr);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
-}
-
-static void
-scanner_dealloc(PyObject *self)
-{
- /* Deallocate scanner object */
- scanner_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-scanner_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_VISIT(s->encoding);
- Py_VISIT(s->strict);
- Py_VISIT(s->object_hook);
- Py_VISIT(s->pairs_hook);
- Py_VISIT(s->parse_float);
- Py_VISIT(s->parse_int);
- Py_VISIT(s->parse_constant);
- Py_VISIT(s->memo);
- return 0;
-}
-
-static int
-scanner_clear(PyObject *self)
-{
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- Py_CLEAR(s->memo);
- return 0;
-}
-
-static PyObject *
-_parse_object_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyString pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook or
- object_pairs_hook can change that)
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- char *encoding = PyString_AS_STRING(s->encoding);
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_str(pystr, idx + 1, encoding, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON data type */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_object_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON object from PyUnicode pystr.
- idx is the index of the first character after the opening curly brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing curly brace.
-
- Returns a new PyObject (usually a dict, but object_hook can change that)
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *rval = NULL;
- PyObject *pairs = NULL;
- PyObject *item;
- PyObject *key = NULL;
- PyObject *val = NULL;
- int strict = PyObject_IsTrue(s->strict);
- int has_pairs_hook = (s->pairs_hook != Py_None);
- Py_ssize_t next_idx;
-
- if (has_pairs_hook) {
- pairs = PyList_New(0);
- if (pairs == NULL)
- return NULL;
- }
- else {
- rval = PyDict_New();
- if (rval == NULL)
- return NULL;
- }
-
- /* skip whitespace after { */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the object is non-empty */
- if (idx <= end_idx && str[idx] != '}') {
- while (idx <= end_idx) {
- PyObject *memokey;
-
- /* read key */
- if (str[idx] != '"') {
- raise_errmsg("Expecting property name", pystr, idx);
- goto bail;
- }
- key = scanstring_unicode(pystr, idx + 1, strict, &next_idx);
- if (key == NULL)
- goto bail;
- memokey = PyDict_GetItem(s->memo, key);
- if (memokey != NULL) {
- Py_INCREF(memokey);
- Py_DECREF(key);
- key = memokey;
- }
- else {
- if (PyDict_SetItem(s->memo, key, key) < 0)
- goto bail;
- }
- idx = next_idx;
-
- /* skip whitespace between key and : delimiter, read :, skip whitespace */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- if (idx > end_idx || str[idx] != ':') {
- raise_errmsg("Expecting : delimiter", pystr, idx);
- goto bail;
- }
- idx++;
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL)
- goto bail;
-
- if (has_pairs_hook) {
- item = PyTuple_Pack(2, key, val);
- if (item == NULL)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- if (PyList_Append(pairs, item) == -1) {
- Py_DECREF(item);
- goto bail;
- }
- Py_DECREF(item);
- }
- else {
- if (PyDict_SetItem(rval, key, val) < 0)
- goto bail;
- Py_CLEAR(key);
- Py_CLEAR(val);
- }
- idx = next_idx;
-
- /* skip whitespace before } or , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the object is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == '}') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , delimiter */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be '}' */
- if (idx > end_idx || str[idx] != '}') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
-
- /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */
- if (s->pairs_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(pairs);
- *next_idx_ptr = idx + 1;
- return val;
- }
-
- /* if object_hook is not None: rval = object_hook(rval) */
- if (s->object_hook != Py_None) {
- val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL);
- if (val == NULL)
- goto bail;
- Py_DECREF(rval);
- rval = val;
- val = NULL;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(rval);
- Py_XDECREF(key);
- Py_XDECREF(val);
- Py_XDECREF(pairs);
- return NULL;
-}
-
-static PyObject *
-_parse_array_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term and de-tuplefy the (rval, idx) */
- val = scan_once_str(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_array_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON array from PyString pystr.
- idx is the index of the first character after the opening brace.
- *next_idx_ptr is a return-by-reference index to the first character after
- the closing brace.
-
- Returns a new PyList
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- PyObject *val = NULL;
- PyObject *rval = PyList_New(0);
- Py_ssize_t next_idx;
- if (rval == NULL)
- return NULL;
-
- /* skip whitespace after [ */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* only loop if the array is non-empty */
- if (idx <= end_idx && str[idx] != ']') {
- while (idx <= end_idx) {
-
- /* read any JSON term */
- val = scan_once_unicode(s, pystr, idx, &next_idx);
- if (val == NULL) {
- if (PyErr_ExceptionMatches(PyExc_StopIteration)) {
- PyErr_Clear();
- raise_errmsg("Expecting object", pystr, idx);
- }
- goto bail;
- }
-
- if (PyList_Append(rval, val) == -1)
- goto bail;
-
- Py_CLEAR(val);
- idx = next_idx;
-
- /* skip whitespace between term and , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
-
- /* bail if the array is closed or we didn't get the , delimiter */
- if (idx > end_idx) break;
- if (str[idx] == ']') {
- break;
- }
- else if (str[idx] != ',') {
- raise_errmsg("Expecting , delimiter", pystr, idx);
- goto bail;
- }
- idx++;
-
- /* skip whitespace after , */
- while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++;
- }
- }
-
- /* verify that idx < end_idx, str[idx] should be ']' */
- if (idx > end_idx || str[idx] != ']') {
- raise_errmsg("Expecting object", pystr, end_idx);
- goto bail;
- }
- *next_idx_ptr = idx + 1;
- return rval;
-bail:
- Py_XDECREF(val);
- Py_DECREF(rval);
- return NULL;
-}
-
-static PyObject *
-_parse_constant(PyScannerObject *s, char *constant, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON constant from PyString pystr.
- constant is the constant string that was found
- ("NaN", "Infinity", "-Infinity").
- idx is the index of the first character of the constant
- *next_idx_ptr is a return-by-reference index to the first character after
- the constant.
-
- Returns the result of parse_constant
- */
- PyObject *cstr;
- PyObject *rval;
- /* constant is "NaN", "Infinity", or "-Infinity" */
- cstr = PyString_InternFromString(constant);
- if (cstr == NULL)
- return NULL;
-
- /* rval = parse_constant(constant) */
- rval = PyObject_CallFunctionObjArgs(s->parse_constant, cstr, NULL);
- idx += PyString_GET_SIZE(cstr);
- Py_DECREF(cstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyString pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
-
- /* save the index of the 'e' or 'E' just in case we need to backtrack */
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyString_FromStringAndSize(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- /* rval = PyFloat_FromDouble(PyOS_ascii_atof(PyString_AS_STRING(numstr))); */
- double d = PyOS_string_to_double(PyString_AS_STRING(numstr),
- NULL, NULL);
- if (d == -1.0 && PyErr_Occurred())
- return NULL;
- rval = PyFloat_FromDouble(d);
- }
- }
- else {
- /* parse as an int using a fast path if available, otherwise call user defined method */
- if (s->parse_int != (PyObject *)&PyInt_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- else {
- rval = PyInt_FromString(PyString_AS_STRING(numstr), NULL, 10);
- }
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-_match_number_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) {
- /* Read a JSON number from PyUnicode pystr.
- idx is the index of the first character of the number
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of that number:
- PyInt, PyLong, or PyFloat.
- May return other types if parse_int or parse_float are set
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t end_idx = PyUnicode_GET_SIZE(pystr) - 1;
- Py_ssize_t idx = start;
- int is_float = 0;
- PyObject *rval;
- PyObject *numstr;
-
- /* read a sign if it's there, make sure it's not the end of the string */
- if (str[idx] == '-') {
- idx++;
- if (idx > end_idx) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- }
-
- /* read as many integer digits as we find as long as it doesn't start with 0 */
- if (str[idx] >= '1' && str[idx] <= '9') {
- idx++;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
- /* if it starts with 0 we only expect one integer digit */
- else if (str[idx] == '0') {
- idx++;
- }
- /* no integer digits, error */
- else {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
-
- /* if the next char is '.' followed by a digit then read all float digits */
- if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') {
- is_float = 1;
- idx += 2;
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
- }
-
- /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */
- if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) {
- Py_ssize_t e_start = idx;
- idx++;
-
- /* read an exponent sign if present */
- if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++;
-
- /* read all digits */
- while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++;
-
- /* if we got a digit, then parse as float. if not, backtrack */
- if (str[idx - 1] >= '0' && str[idx - 1] <= '9') {
- is_float = 1;
- }
- else {
- idx = e_start;
- }
- }
-
- /* copy the section we determined to be a number */
- numstr = PyUnicode_FromUnicode(&str[start], idx - start);
- if (numstr == NULL)
- return NULL;
- if (is_float) {
- /* parse as a float using a fast path if available, otherwise call user defined method */
- if (s->parse_float != (PyObject *)&PyFloat_Type) {
- rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL);
- }
- else {
- rval = PyFloat_FromString(numstr, NULL);
- }
- }
- else {
- /* no fast path for unicode -> int, just call */
- rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL);
- }
- Py_DECREF(numstr);
- *next_idx_ptr = idx;
- return rval;
-}
-
-static PyObject *
-scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyString pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- char *str = PyString_AS_STRING(pystr);
- Py_ssize_t length = PyString_GET_SIZE(pystr);
- PyObject *rval = NULL;
- int fallthrough = 0;
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- if (Py_EnterRecursiveCall(" while decoding a JSON document"))
- return NULL;
- switch (str[idx]) {
- case '"':
- /* string */
- rval = scanstring_str(pystr, idx + 1,
- PyString_AS_STRING(s->encoding),
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- break;
- case '{':
- /* object */
- rval = _parse_object_str(s, pystr, idx + 1, next_idx_ptr);
- break;
- case '[':
- /* array */
- rval = _parse_array_str(s, pystr, idx + 1, next_idx_ptr);
- break;
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- rval = Py_None;
- }
- else
- fallthrough = 1;
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- rval = Py_True;
- }
- else
- fallthrough = 1;
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- rval = Py_False;
- }
- else
- fallthrough = 1;
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- rval = _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- rval = _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- rval = _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- default:
- fallthrough = 1;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- if (fallthrough)
- rval = _match_number_str(s, pystr, idx, next_idx_ptr);
- Py_LeaveRecursiveCall();
- return rval;
-}
-
-static PyObject *
-scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr)
-{
- /* Read one JSON term (of any kind) from PyUnicode pystr.
- idx is the index of the first character of the term
- *next_idx_ptr is a return-by-reference index to the first character after
- the number.
-
- Returns a new PyObject representation of the term.
- */
- Py_UNICODE *str = PyUnicode_AS_UNICODE(pystr);
- Py_ssize_t length = PyUnicode_GET_SIZE(pystr);
- PyObject *rval = NULL;
- int fallthrough = 0;
- if (idx >= length) {
- PyErr_SetNone(PyExc_StopIteration);
- return NULL;
- }
- if (Py_EnterRecursiveCall(" while decoding a JSON document"))
- return NULL;
- switch (str[idx]) {
- case '"':
- /* string */
- rval = scanstring_unicode(pystr, idx + 1,
- PyObject_IsTrue(s->strict),
- next_idx_ptr);
- break;
- case '{':
- /* object */
- rval = _parse_object_unicode(s, pystr, idx + 1, next_idx_ptr);
- break;
- case '[':
- /* array */
- rval = _parse_array_unicode(s, pystr, idx + 1, next_idx_ptr);
- break;
- case 'n':
- /* null */
- if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') {
- Py_INCREF(Py_None);
- *next_idx_ptr = idx + 4;
- rval = Py_None;
- }
- else
- fallthrough = 1;
- break;
- case 't':
- /* true */
- if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') {
- Py_INCREF(Py_True);
- *next_idx_ptr = idx + 4;
- rval = Py_True;
- }
- else
- fallthrough = 1;
- break;
- case 'f':
- /* false */
- if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') {
- Py_INCREF(Py_False);
- *next_idx_ptr = idx + 5;
- rval = Py_False;
- }
- else
- fallthrough = 1;
- break;
- case 'N':
- /* NaN */
- if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') {
- rval = _parse_constant(s, "NaN", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- case 'I':
- /* Infinity */
- if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') {
- rval = _parse_constant(s, "Infinity", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- case '-':
- /* -Infinity */
- if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') {
- rval = _parse_constant(s, "-Infinity", idx, next_idx_ptr);
- }
- else
- fallthrough = 1;
- break;
- default:
- fallthrough = 1;
- }
- /* Didn't find a string, object, array, or named constant. Look for a number. */
- if (fallthrough)
- rval = _match_number_unicode(s, pystr, idx, next_idx_ptr);
- Py_LeaveRecursiveCall();
- return rval;
-}
-
-static PyObject *
-scanner_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to scan_once_{str,unicode} */
- PyObject *pystr;
- PyObject *rval;
- Py_ssize_t idx;
- Py_ssize_t next_idx = -1;
- static char *kwlist[] = {"string", "idx", NULL};
- PyScannerObject *s;
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:scan_once", kwlist, &pystr, _convertPyInt_AsSsize_t, &idx))
- return NULL;
-
- if (PyString_Check(pystr)) {
- rval = scan_once_str(s, pystr, idx, &next_idx);
- }
- else if (PyUnicode_Check(pystr)) {
- rval = scan_once_unicode(s, pystr, idx, &next_idx);
- }
- else {
- PyErr_Format(PyExc_TypeError,
- "first argument must be a string, not %.80s",
- Py_TYPE(pystr)->tp_name);
- return NULL;
- }
- PyDict_Clear(s->memo);
- return _build_rval_index_tuple(rval, next_idx);
-}
-
-static PyObject *
-scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyScannerObject *s;
- s = (PyScannerObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->encoding = NULL;
- s->strict = NULL;
- s->object_hook = NULL;
- s->pairs_hook = NULL;
- s->parse_float = NULL;
- s->parse_int = NULL;
- s->parse_constant = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-scanner_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Initialize Scanner object */
- PyObject *ctx;
- static char *kwlist[] = {"context", NULL};
- PyScannerObject *s;
-
- assert(PyScanner_Check(self));
- s = (PyScannerObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "O:make_scanner", kwlist, &ctx))
- return -1;
-
- if (s->memo == NULL) {
- s->memo = PyDict_New();
- if (s->memo == NULL)
- goto bail;
- }
-
- /* PyString_AS_STRING is used on encoding */
- s->encoding = PyObject_GetAttrString(ctx, "encoding");
- if (s->encoding == NULL)
- goto bail;
- if (s->encoding == Py_None) {
- Py_DECREF(Py_None);
- s->encoding = PyString_InternFromString(DEFAULT_ENCODING);
- }
- else if (PyUnicode_Check(s->encoding)) {
- PyObject *tmp = PyUnicode_AsEncodedString(s->encoding, NULL, NULL);
- Py_DECREF(s->encoding);
- s->encoding = tmp;
- }
- if (s->encoding == NULL || !PyString_Check(s->encoding))
- goto bail;
-
- /* All of these will fail "gracefully" so we don't need to verify them */
- s->strict = PyObject_GetAttrString(ctx, "strict");
- if (s->strict == NULL)
- goto bail;
- s->object_hook = PyObject_GetAttrString(ctx, "object_hook");
- if (s->object_hook == NULL)
- goto bail;
- s->pairs_hook = PyObject_GetAttrString(ctx, "object_pairs_hook");
- if (s->pairs_hook == NULL)
- goto bail;
- s->parse_float = PyObject_GetAttrString(ctx, "parse_float");
- if (s->parse_float == NULL)
- goto bail;
- s->parse_int = PyObject_GetAttrString(ctx, "parse_int");
- if (s->parse_int == NULL)
- goto bail;
- s->parse_constant = PyObject_GetAttrString(ctx, "parse_constant");
- if (s->parse_constant == NULL)
- goto bail;
-
- return 0;
-
-bail:
- Py_CLEAR(s->encoding);
- Py_CLEAR(s->strict);
- Py_CLEAR(s->object_hook);
- Py_CLEAR(s->pairs_hook);
- Py_CLEAR(s->parse_float);
- Py_CLEAR(s->parse_int);
- Py_CLEAR(s->parse_constant);
- return -1;
-}
-
-PyDoc_STRVAR(scanner_doc, "JSON scanner object");
-
-static
-PyTypeObject PyScannerType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Scanner", /* tp_name */
- sizeof(PyScannerObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- scanner_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- scanner_call, /* tp_call */
- 0, /* tp_str */
- 0,/* PyObject_GenericGetAttr, */ /* tp_getattro */
- 0,/* PyObject_GenericSetAttr, */ /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- scanner_doc, /* tp_doc */
- scanner_traverse, /* tp_traverse */
- scanner_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- scanner_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- scanner_init, /* tp_init */
- 0,/* PyType_GenericAlloc, */ /* tp_alloc */
- scanner_new, /* tp_new */
- 0,/* PyObject_GC_Del, */ /* tp_free */
-};
-
-static PyObject *
-encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
-{
- PyEncoderObject *s;
- s = (PyEncoderObject *)type->tp_alloc(type, 0);
- if (s != NULL) {
- s->markers = NULL;
- s->defaultfn = NULL;
- s->encoder = NULL;
- s->indent = NULL;
- s->key_separator = NULL;
- s->item_separator = NULL;
- s->sort_keys = NULL;
- s->skipkeys = NULL;
- s->key_memo = NULL;
- }
- return (PyObject *)s;
-}
-
-static int
-encoder_init(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* initialize Encoder object */
- static char *kwlist[] = {"markers", "default", "encoder", "indent", "key_separator", "item_separator", "sort_keys", "skipkeys", "allow_nan", "key_memo", "use_decimal", NULL};
-
- PyEncoderObject *s;
- PyObject *markers, *defaultfn, *encoder, *indent, *key_separator;
- PyObject *item_separator, *sort_keys, *skipkeys, *allow_nan, *key_memo, *use_decimal;
-
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OOOOOOOOOOO:make_encoder", kwlist,
- &markers, &defaultfn, &encoder, &indent, &key_separator, &item_separator,
- &sort_keys, &skipkeys, &allow_nan, &key_memo, &use_decimal))
- return -1;
-
- s->markers = markers;
- s->defaultfn = defaultfn;
- s->encoder = encoder;
- s->indent = indent;
- s->key_separator = key_separator;
- s->item_separator = item_separator;
- s->sort_keys = sort_keys;
- s->skipkeys = skipkeys;
- s->key_memo = key_memo;
- s->fast_encode = (PyCFunction_Check(s->encoder) && PyCFunction_GetFunction(s->encoder) == (PyCFunction)py_encode_basestring_ascii);
- s->allow_nan = PyObject_IsTrue(allow_nan);
- s->use_decimal = PyObject_IsTrue(use_decimal);
-
- Py_INCREF(s->markers);
- Py_INCREF(s->defaultfn);
- Py_INCREF(s->encoder);
- Py_INCREF(s->indent);
- Py_INCREF(s->key_separator);
- Py_INCREF(s->item_separator);
- Py_INCREF(s->sort_keys);
- Py_INCREF(s->skipkeys);
- Py_INCREF(s->key_memo);
- return 0;
-}
-
-static PyObject *
-encoder_call(PyObject *self, PyObject *args, PyObject *kwds)
-{
- /* Python callable interface to encode_listencode_obj */
- static char *kwlist[] = {"obj", "_current_indent_level", NULL};
- PyObject *obj;
- PyObject *rval;
- Py_ssize_t indent_level;
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:_iterencode", kwlist,
- &obj, _convertPyInt_AsSsize_t, &indent_level))
- return NULL;
- rval = PyList_New(0);
- if (rval == NULL)
- return NULL;
- if (encoder_listencode_obj(s, rval, obj, indent_level)) {
- Py_DECREF(rval);
- return NULL;
- }
- return rval;
-}
-
-static PyObject *
-_encoded_const(PyObject *obj)
-{
- /* Return the JSON string representation of None, True, False */
- if (obj == Py_None) {
- static PyObject *s_null = NULL;
- if (s_null == NULL) {
- s_null = PyString_InternFromString("null");
- }
- Py_INCREF(s_null);
- return s_null;
- }
- else if (obj == Py_True) {
- static PyObject *s_true = NULL;
- if (s_true == NULL) {
- s_true = PyString_InternFromString("true");
- }
- Py_INCREF(s_true);
- return s_true;
- }
- else if (obj == Py_False) {
- static PyObject *s_false = NULL;
- if (s_false == NULL) {
- s_false = PyString_InternFromString("false");
- }
- Py_INCREF(s_false);
- return s_false;
- }
- else {
- PyErr_SetString(PyExc_ValueError, "not a const");
- return NULL;
- }
-}
-
-static PyObject *
-encoder_encode_float(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a PyFloat */
- double i = PyFloat_AS_DOUBLE(obj);
- if (!Py_IS_FINITE(i)) {
- if (!s->allow_nan) {
- PyErr_SetString(PyExc_ValueError, "Out of range float values are not JSON compliant");
- return NULL;
- }
- if (i > 0) {
- return PyString_FromString("Infinity");
- }
- else if (i < 0) {
- return PyString_FromString("-Infinity");
- }
- else {
- return PyString_FromString("NaN");
- }
- }
- /* Use a better float format here? */
- return PyObject_Repr(obj);
-}
-
-static PyObject *
-encoder_encode_string(PyEncoderObject *s, PyObject *obj)
-{
- /* Return the JSON representation of a string */
- if (s->fast_encode)
- return py_encode_basestring_ascii(NULL, obj);
- else
- return PyObject_CallFunctionObjArgs(s->encoder, obj, NULL);
-}
-
-static int
-_steal_list_append(PyObject *lst, PyObject *stolen)
-{
- /* Append stolen and then decrement its reference count */
- int rval = PyList_Append(lst, stolen);
- Py_DECREF(stolen);
- return rval;
-}
-
-static int
-encoder_listencode_obj(PyEncoderObject *s, PyObject *rval, PyObject *obj, Py_ssize_t indent_level)
-{
- /* Encode Python object obj to a JSON term, rval is a PyList */
- int rv = -1;
- if (Py_EnterRecursiveCall(" while encoding a JSON document"))
- return rv;
- do {
- if (obj == Py_None || obj == Py_True || obj == Py_False) {
- PyObject *cstr = _encoded_const(obj);
- if (cstr != NULL)
- rv = _steal_list_append(rval, cstr);
- }
- else if (PyString_Check(obj) || PyUnicode_Check(obj))
- {
- PyObject *encoded = encoder_encode_string(s, obj);
- if (encoded != NULL)
- rv = _steal_list_append(rval, encoded);
- }
- else if (PyInt_Check(obj) || PyLong_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded != NULL)
- rv = _steal_list_append(rval, encoded);
- }
- else if (PyFloat_Check(obj)) {
- PyObject *encoded = encoder_encode_float(s, obj);
- if (encoded != NULL)
- rv = _steal_list_append(rval, encoded);
- }
- else if (PyList_Check(obj) || PyTuple_Check(obj)) {
- rv = encoder_listencode_list(s, rval, obj, indent_level);
- }
- else if (PyDict_Check(obj)) {
- rv = encoder_listencode_dict(s, rval, obj, indent_level);
- }
- else if (s->use_decimal && Decimal_Check(obj)) {
- PyObject *encoded = PyObject_Str(obj);
- if (encoded != NULL)
- rv = _steal_list_append(rval, encoded);
- }
- else {
- PyObject *ident = NULL;
- PyObject *newobj;
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(obj);
- if (ident == NULL)
- break;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- Py_DECREF(ident);
- break;
- }
- if (PyDict_SetItem(s->markers, ident, obj)) {
- Py_DECREF(ident);
- break;
- }
- }
- newobj = PyObject_CallFunctionObjArgs(s->defaultfn, obj, NULL);
- if (newobj == NULL) {
- Py_XDECREF(ident);
- break;
- }
- rv = encoder_listencode_obj(s, rval, newobj, indent_level);
- Py_DECREF(newobj);
- if (rv) {
- Py_XDECREF(ident);
- rv = -1;
- }
- else if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident)) {
- Py_XDECREF(ident);
- rv = -1;
- }
- Py_XDECREF(ident);
- }
- }
- } while (0);
- Py_LeaveRecursiveCall();
- return rv;
-}
-
-static int
-encoder_listencode_dict(PyEncoderObject *s, PyObject *rval, PyObject *dct, Py_ssize_t indent_level)
-{
- /* Encode Python dict dct a JSON term, rval is a PyList */
- static PyObject *open_dict = NULL;
- static PyObject *close_dict = NULL;
- static PyObject *empty_dict = NULL;
- static PyObject *iteritems = NULL;
- PyObject *kstr = NULL;
- PyObject *ident = NULL;
- PyObject *iter = NULL;
- PyObject *item = NULL;
- PyObject *items = NULL;
- PyObject *encoded = NULL;
- int skipkeys;
- Py_ssize_t idx;
-
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL) {
- open_dict = PyString_InternFromString("{");
- close_dict = PyString_InternFromString("}");
- empty_dict = PyString_InternFromString("{}");
- iteritems = PyString_InternFromString("iteritems");
- if (open_dict == NULL || close_dict == NULL || empty_dict == NULL || iteritems == NULL)
- return -1;
- }
- if (PyDict_Size(dct) == 0)
- return PyList_Append(rval, empty_dict);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(dct);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, dct)) {
- goto bail;
- }
- }
-
- if (PyList_Append(rval, open_dict))
- goto bail;
-
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
-
- if (PyObject_IsTrue(s->sort_keys)) {
- /* First sort the keys then replace them with (key, value) tuples. */
- Py_ssize_t i, nitems;
- if (PyDict_CheckExact(dct))
- items = PyDict_Keys(dct);
- else
- items = PyMapping_Keys(dct);
- if (items == NULL)
- goto bail;
- if (!PyList_Check(items)) {
- PyErr_SetString(PyExc_ValueError, "keys must return list");
- goto bail;
- }
- if (PyList_Sort(items) < 0)
- goto bail;
- nitems = PyList_GET_SIZE(items);
- for (i = 0; i < nitems; i++) {
- PyObject *key, *value;
- key = PyList_GET_ITEM(items, i);
- value = PyDict_GetItem(dct, key);
- item = PyTuple_Pack(2, key, value);
- if (item == NULL)
- goto bail;
- PyList_SET_ITEM(items, i, item);
- Py_DECREF(key);
- }
- }
- else {
- if (PyDict_CheckExact(dct))
- items = PyDict_Items(dct);
- else
- items = PyMapping_Items(dct);
- }
- if (items == NULL)
- goto bail;
- iter = PyObject_GetIter(items);
- Py_DECREF(items);
- if (iter == NULL)
- goto bail;
-
- skipkeys = PyObject_IsTrue(s->skipkeys);
- idx = 0;
- while ((item = PyIter_Next(iter))) {
- PyObject *encoded, *key, *value;
- if (!PyTuple_Check(item) || Py_SIZE(item) != 2) {
- PyErr_SetString(PyExc_ValueError, "items must return 2-tuples");
- goto bail;
- }
- key = PyTuple_GET_ITEM(item, 0);
- if (key == NULL)
- goto bail;
- value = PyTuple_GET_ITEM(item, 1);
- if (value == NULL)
- goto bail;
-
- encoded = PyDict_GetItem(s->key_memo, key);
- if (encoded != NULL) {
- Py_INCREF(encoded);
- }
- else if (PyString_Check(key) || PyUnicode_Check(key)) {
- Py_INCREF(key);
- kstr = key;
- }
- else if (PyFloat_Check(key)) {
- kstr = encoder_encode_float(s, key);
- if (kstr == NULL)
- goto bail;
- }
- else if (key == Py_True || key == Py_False || key == Py_None) {
- /* This must come before the PyInt_Check because
- True and False are also 1 and 0.*/
- kstr = _encoded_const(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (PyInt_Check(key) || PyLong_Check(key)) {
- kstr = PyObject_Str(key);
- if (kstr == NULL)
- goto bail;
- }
- else if (skipkeys) {
- Py_DECREF(item);
- continue;
- }
- else {
- /* TODO: include repr of key */
- PyErr_SetString(PyExc_TypeError, "keys must be a string");
- goto bail;
- }
-
- if (idx) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
-
- if (encoded == NULL) {
- encoded = encoder_encode_string(s, kstr);
- Py_CLEAR(kstr);
- if (encoded == NULL)
- goto bail;
- if (PyDict_SetItem(s->key_memo, key, encoded))
- goto bail;
- }
- if (PyList_Append(rval, encoded)) {
- goto bail;
- }
- Py_CLEAR(encoded);
- if (PyList_Append(rval, s->key_separator))
- goto bail;
- if (encoder_listencode_obj(s, rval, value, indent_level))
- goto bail;
- Py_CLEAR(item);
- idx += 1;
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_dict))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(encoded);
- Py_XDECREF(items);
- Py_XDECREF(iter);
- Py_XDECREF(kstr);
- Py_XDECREF(ident);
- return -1;
-}
-
-
-static int
-encoder_listencode_list(PyEncoderObject *s, PyObject *rval, PyObject *seq, Py_ssize_t indent_level)
-{
- /* Encode Python list seq to a JSON term, rval is a PyList */
- static PyObject *open_array = NULL;
- static PyObject *close_array = NULL;
- static PyObject *empty_array = NULL;
- PyObject *ident = NULL;
- PyObject *iter = NULL;
- PyObject *obj = NULL;
- int is_true;
- int i = 0;
-
- if (open_array == NULL || close_array == NULL || empty_array == NULL) {
- open_array = PyString_InternFromString("[");
- close_array = PyString_InternFromString("]");
- empty_array = PyString_InternFromString("[]");
- if (open_array == NULL || close_array == NULL || empty_array == NULL)
- return -1;
- }
- ident = NULL;
- is_true = PyObject_IsTrue(seq);
- if (is_true == -1)
- return -1;
- else if (is_true == 0)
- return PyList_Append(rval, empty_array);
-
- if (s->markers != Py_None) {
- int has_key;
- ident = PyLong_FromVoidPtr(seq);
- if (ident == NULL)
- goto bail;
- has_key = PyDict_Contains(s->markers, ident);
- if (has_key) {
- if (has_key != -1)
- PyErr_SetString(PyExc_ValueError, "Circular reference detected");
- goto bail;
- }
- if (PyDict_SetItem(s->markers, ident, seq)) {
- goto bail;
- }
- }
-
- iter = PyObject_GetIter(seq);
- if (iter == NULL)
- goto bail;
-
- if (PyList_Append(rval, open_array))
- goto bail;
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level += 1;
- /*
- newline_indent = '\n' + (_indent * _current_indent_level)
- separator = _item_separator + newline_indent
- buf += newline_indent
- */
- }
- while ((obj = PyIter_Next(iter))) {
- if (i) {
- if (PyList_Append(rval, s->item_separator))
- goto bail;
- }
- if (encoder_listencode_obj(s, rval, obj, indent_level))
- goto bail;
- i++;
- Py_CLEAR(obj);
- }
- Py_CLEAR(iter);
- if (PyErr_Occurred())
- goto bail;
- if (ident != NULL) {
- if (PyDict_DelItem(s->markers, ident))
- goto bail;
- Py_CLEAR(ident);
- }
- if (s->indent != Py_None) {
- /* TODO: DOES NOT RUN */
- indent_level -= 1;
- /*
- yield '\n' + (_indent * _current_indent_level)
- */
- }
- if (PyList_Append(rval, close_array))
- goto bail;
- return 0;
-
-bail:
- Py_XDECREF(obj);
- Py_XDECREF(iter);
- Py_XDECREF(ident);
- return -1;
-}
-
-static void
-encoder_dealloc(PyObject *self)
-{
- /* Deallocate Encoder */
- encoder_clear(self);
- Py_TYPE(self)->tp_free(self);
-}
-
-static int
-encoder_traverse(PyObject *self, visitproc visit, void *arg)
-{
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_VISIT(s->markers);
- Py_VISIT(s->defaultfn);
- Py_VISIT(s->encoder);
- Py_VISIT(s->indent);
- Py_VISIT(s->key_separator);
- Py_VISIT(s->item_separator);
- Py_VISIT(s->sort_keys);
- Py_VISIT(s->skipkeys);
- Py_VISIT(s->key_memo);
- return 0;
-}
-
-static int
-encoder_clear(PyObject *self)
-{
- /* Deallocate Encoder */
- PyEncoderObject *s;
- assert(PyEncoder_Check(self));
- s = (PyEncoderObject *)self;
- Py_CLEAR(s->markers);
- Py_CLEAR(s->defaultfn);
- Py_CLEAR(s->encoder);
- Py_CLEAR(s->indent);
- Py_CLEAR(s->key_separator);
- Py_CLEAR(s->item_separator);
- Py_CLEAR(s->sort_keys);
- Py_CLEAR(s->skipkeys);
- Py_CLEAR(s->key_memo);
- return 0;
-}
-
-PyDoc_STRVAR(encoder_doc, "_iterencode(obj, _current_indent_level) -> iterable");
-
-static
-PyTypeObject PyEncoderType = {
- PyObject_HEAD_INIT(NULL)
- 0, /* tp_internal */
- "simplejson._speedups.Encoder", /* tp_name */
- sizeof(PyEncoderObject), /* tp_basicsize */
- 0, /* tp_itemsize */
- encoder_dealloc, /* tp_dealloc */
- 0, /* tp_print */
- 0, /* tp_getattr */
- 0, /* tp_setattr */
- 0, /* tp_compare */
- 0, /* tp_repr */
- 0, /* tp_as_number */
- 0, /* tp_as_sequence */
- 0, /* tp_as_mapping */
- 0, /* tp_hash */
- encoder_call, /* tp_call */
- 0, /* tp_str */
- 0, /* tp_getattro */
- 0, /* tp_setattro */
- 0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
- encoder_doc, /* tp_doc */
- encoder_traverse, /* tp_traverse */
- encoder_clear, /* tp_clear */
- 0, /* tp_richcompare */
- 0, /* tp_weaklistoffset */
- 0, /* tp_iter */
- 0, /* tp_iternext */
- 0, /* tp_methods */
- encoder_members, /* tp_members */
- 0, /* tp_getset */
- 0, /* tp_base */
- 0, /* tp_dict */
- 0, /* tp_descr_get */
- 0, /* tp_descr_set */
- 0, /* tp_dictoffset */
- encoder_init, /* tp_init */
- 0, /* tp_alloc */
- encoder_new, /* tp_new */
- 0, /* tp_free */
-};
-
-static PyMethodDef speedups_methods[] = {
- {"encode_basestring_ascii",
- (PyCFunction)py_encode_basestring_ascii,
- METH_O,
- pydoc_encode_basestring_ascii},
- {"scanstring",
- (PyCFunction)py_scanstring,
- METH_VARARGS,
- pydoc_scanstring},
- {NULL, NULL, 0, NULL}
-};
-
-PyDoc_STRVAR(module_doc,
-"simplejson speedups\n");
-
-void
-init_speedups(void)
-{
- PyObject *m, *decimal;
- PyScannerType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyScannerType) < 0)
- return;
- PyEncoderType.tp_new = PyType_GenericNew;
- if (PyType_Ready(&PyEncoderType) < 0)
- return;
-
- decimal = PyImport_ImportModule("decimal");
- if (decimal == NULL)
- return;
- DecimalTypePtr = (PyTypeObject*)PyObject_GetAttrString(decimal, "Decimal");
- Py_DECREF(decimal);
- if (DecimalTypePtr == NULL)
- return;
-
- m = Py_InitModule3("_speedups", speedups_methods, module_doc);
- Py_INCREF((PyObject*)&PyScannerType);
- PyModule_AddObject(m, "make_scanner", (PyObject*)&PyScannerType);
- Py_INCREF((PyObject*)&PyEncoderType);
- PyModule_AddObject(m, "make_encoder", (PyObject*)&PyEncoderType);
-}
diff --git a/shotgun_api3/lib/simplejson/decoder.py b/shotgun_api3/lib/simplejson/decoder.py
deleted file mode 100644
index e5496d6e7..000000000
--- a/shotgun_api3/lib/simplejson/decoder.py
+++ /dev/null
@@ -1,421 +0,0 @@
-"""Implementation of JSONDecoder
-"""
-import re
-import sys
-import struct
-
-from simplejson.scanner import make_scanner
-def _import_c_scanstring():
- try:
- from simplejson._speedups import scanstring
- return scanstring
- except ImportError:
- return None
-c_scanstring = _import_c_scanstring()
-
-__all__ = ['JSONDecoder']
-
-FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
-
-def _floatconstants():
- _BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
- # The struct module in Python 2.4 would get frexp() out of range here
- # when an endian is specified in the format string. Fixed in Python 2.5+
- if sys.byteorder != 'big':
- _BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
- nan, inf = struct.unpack('dd', _BYTES)
- return nan, inf, -inf
-
-NaN, PosInf, NegInf = _floatconstants()
-
-
-class JSONDecodeError(ValueError):
- """Subclass of ValueError with the following additional properties:
-
- msg: The unformatted error message
- doc: The JSON document being parsed
- pos: The start index of doc where parsing failed
- end: The end index of doc where parsing failed (may be None)
- lineno: The line corresponding to pos
- colno: The column corresponding to pos
- endlineno: The line corresponding to end (may be None)
- endcolno: The column corresponding to end (may be None)
-
- """
- def __init__(self, msg, doc, pos, end=None):
- ValueError.__init__(self, errmsg(msg, doc, pos, end=end))
- self.msg = msg
- self.doc = doc
- self.pos = pos
- self.end = end
- self.lineno, self.colno = linecol(doc, pos)
- if end is not None:
- self.endlineno, self.endcolno = linecol(doc, end)
- else:
- self.endlineno, self.endcolno = None, None
-
-
-def linecol(doc, pos):
- lineno = doc.count('\n', 0, pos) + 1
- if lineno == 1:
- colno = pos
- else:
- colno = pos - doc.rindex('\n', 0, pos)
- return lineno, colno
-
-
-def errmsg(msg, doc, pos, end=None):
- # Note that this function is called from _speedups
- lineno, colno = linecol(doc, pos)
- if end is None:
- #fmt = '{0}: line {1} column {2} (char {3})'
- #return fmt.format(msg, lineno, colno, pos)
- fmt = '%s: line %d column %d (char %d)'
- return fmt % (msg, lineno, colno, pos)
- endlineno, endcolno = linecol(doc, end)
- #fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
- #return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
- fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
- return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
-
-
-_CONSTANTS = {
- '-Infinity': NegInf,
- 'Infinity': PosInf,
- 'NaN': NaN,
-}
-
-STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
-BACKSLASH = {
- '"': u'"', '\\': u'\\', '/': u'/',
- 'b': u'\b', 'f': u'\f', 'n': u'\n', 'r': u'\r', 't': u'\t',
-}
-
-DEFAULT_ENCODING = "utf-8"
-
-def py_scanstring(s, end, encoding=None, strict=True,
- _b=BACKSLASH, _m=STRINGCHUNK.match):
- """Scan the string s for a JSON string. End is the index of the
- character in s after the quote that started the JSON string.
- Unescapes all valid JSON string escape sequences and raises ValueError
- on attempt to decode an invalid string. If strict is False then literal
- control characters are allowed in the string.
-
- Returns a tuple of the decoded string and the index of the character in s
- after the end quote."""
- if encoding is None:
- encoding = DEFAULT_ENCODING
- chunks = []
- _append = chunks.append
- begin = end - 1
- while 1:
- chunk = _m(s, end)
- if chunk is None:
- raise JSONDecodeError(
- "Unterminated string starting at", s, begin)
- end = chunk.end()
- content, terminator = chunk.groups()
- # Content is contains zero or more unescaped string characters
- if content:
- if not isinstance(content, unicode):
- content = unicode(content, encoding)
- _append(content)
- # Terminator is the end of string, a literal control character,
- # or a backslash denoting that an escape sequence follows
- if terminator == '"':
- break
- elif terminator != '\\':
- if strict:
- msg = "Invalid control character %r at" % (terminator,)
- #msg = "Invalid control character {0!r} at".format(terminator)
- raise JSONDecodeError(msg, s, end)
- else:
- _append(terminator)
- continue
- try:
- esc = s[end]
- except IndexError:
- raise JSONDecodeError(
- "Unterminated string starting at", s, begin)
- # If not a unicode escape sequence, must be in the lookup table
- if esc != 'u':
- try:
- char = _b[esc]
- except KeyError:
- msg = "Invalid \\escape: " + repr(esc)
- raise JSONDecodeError(msg, s, end)
- end += 1
- else:
- # Unicode escape sequence
- esc = s[end + 1:end + 5]
- next_end = end + 5
- if len(esc) != 4:
- msg = "Invalid \\uXXXX escape"
- raise JSONDecodeError(msg, s, end)
- uni = int(esc, 16)
- # Check for surrogate pair on UCS-4 systems
- if 0xd800 <= uni <= 0xdbff and sys.maxunicode > 65535:
- msg = "Invalid \\uXXXX\\uXXXX surrogate pair"
- if not s[end + 5:end + 7] == '\\u':
- raise JSONDecodeError(msg, s, end)
- esc2 = s[end + 7:end + 11]
- if len(esc2) != 4:
- raise JSONDecodeError(msg, s, end)
- uni2 = int(esc2, 16)
- uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
- next_end += 6
- char = unichr(uni)
- end = next_end
- # Append the unescaped character
- _append(char)
- return u''.join(chunks), end
-
-
-# Use speedup if available
-scanstring = c_scanstring or py_scanstring
-
-WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
-WHITESPACE_STR = ' \t\n\r'
-
-def JSONObject((s, end), encoding, strict, scan_once, object_hook,
- object_pairs_hook, memo=None,
- _w=WHITESPACE.match, _ws=WHITESPACE_STR):
- # Backwards compatibility
- if memo is None:
- memo = {}
- memo_get = memo.setdefault
- pairs = []
- # Use a slice to prevent IndexError from being raised, the following
- # check will raise a more specific ValueError if the string is empty
- nextchar = s[end:end + 1]
- # Normally we expect nextchar == '"'
- if nextchar != '"':
- if nextchar in _ws:
- end = _w(s, end).end()
- nextchar = s[end:end + 1]
- # Trivial empty object
- if nextchar == '}':
- if object_pairs_hook is not None:
- result = object_pairs_hook(pairs)
- return result, end + 1
- pairs = {}
- if object_hook is not None:
- pairs = object_hook(pairs)
- return pairs, end + 1
- elif nextchar != '"':
- raise JSONDecodeError("Expecting property name", s, end)
- end += 1
- while True:
- key, end = scanstring(s, end, encoding, strict)
- key = memo_get(key, key)
-
- # To skip some function call overhead we optimize the fast paths where
- # the JSON key separator is ": " or just ":".
- if s[end:end + 1] != ':':
- end = _w(s, end).end()
- if s[end:end + 1] != ':':
- raise JSONDecodeError("Expecting : delimiter", s, end)
-
- end += 1
-
- try:
- if s[end] in _ws:
- end += 1
- if s[end] in _ws:
- end = _w(s, end + 1).end()
- except IndexError:
- pass
-
- try:
- value, end = scan_once(s, end)
- except StopIteration:
- raise JSONDecodeError("Expecting object", s, end)
- pairs.append((key, value))
-
- try:
- nextchar = s[end]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end]
- except IndexError:
- nextchar = ''
- end += 1
-
- if nextchar == '}':
- break
- elif nextchar != ',':
- raise JSONDecodeError("Expecting , delimiter", s, end - 1)
-
- try:
- nextchar = s[end]
- if nextchar in _ws:
- end += 1
- nextchar = s[end]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end]
- except IndexError:
- nextchar = ''
-
- end += 1
- if nextchar != '"':
- raise JSONDecodeError("Expecting property name", s, end - 1)
-
- if object_pairs_hook is not None:
- result = object_pairs_hook(pairs)
- return result, end
- pairs = dict(pairs)
- if object_hook is not None:
- pairs = object_hook(pairs)
- return pairs, end
-
-def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
- values = []
- nextchar = s[end:end + 1]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end:end + 1]
- # Look-ahead for trivial empty array
- if nextchar == ']':
- return values, end + 1
- _append = values.append
- while True:
- try:
- value, end = scan_once(s, end)
- except StopIteration:
- raise JSONDecodeError("Expecting object", s, end)
- _append(value)
- nextchar = s[end:end + 1]
- if nextchar in _ws:
- end = _w(s, end + 1).end()
- nextchar = s[end:end + 1]
- end += 1
- if nextchar == ']':
- break
- elif nextchar != ',':
- raise JSONDecodeError("Expecting , delimiter", s, end)
-
- try:
- if s[end] in _ws:
- end += 1
- if s[end] in _ws:
- end = _w(s, end + 1).end()
- except IndexError:
- pass
-
- return values, end
-
-class JSONDecoder(object):
- """Simple JSON decoder
-
- Performs the following translations in decoding by default:
-
- +---------------+-------------------+
- | JSON | Python |
- +===============+===================+
- | object | dict |
- +---------------+-------------------+
- | array | list |
- +---------------+-------------------+
- | string | unicode |
- +---------------+-------------------+
- | number (int) | int, long |
- +---------------+-------------------+
- | number (real) | float |
- +---------------+-------------------+
- | true | True |
- +---------------+-------------------+
- | false | False |
- +---------------+-------------------+
- | null | None |
- +---------------+-------------------+
-
- It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
- their corresponding ``float`` values, which is outside the JSON spec.
-
- """
-
- def __init__(self, encoding=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, strict=True,
- object_pairs_hook=None):
- """
- *encoding* determines the encoding used to interpret any
- :class:`str` objects decoded by this instance (``'utf-8'`` by
- default). It has no effect when decoding :class:`unicode` objects.
-
- Note that currently only encodings that are a superset of ASCII work,
- strings of other encodings should be passed in as :class:`unicode`.
-
- *object_hook*, if specified, will be called with the result of every
- JSON object decoded and its return value will be used in place of the
- given :class:`dict`. This can be used to provide custom
- deserializations (e.g. to support JSON-RPC class hinting).
-
- *object_pairs_hook* is an optional function that will be called with
- the result of any object literal decode with an ordered list of pairs.
- The return value of *object_pairs_hook* will be used instead of the
- :class:`dict`. This feature can be used to implement custom decoders
- that rely on the order that the key and value pairs are decoded (for
- example, :func:`collections.OrderedDict` will remember the order of
- insertion). If *object_hook* is also defined, the *object_pairs_hook*
- takes priority.
-
- *parse_float*, if specified, will be called with the string of every
- JSON float to be decoded. By default, this is equivalent to
- ``float(num_str)``. This can be used to use another datatype or parser
- for JSON floats (e.g. :class:`decimal.Decimal`).
-
- *parse_int*, if specified, will be called with the string of every
- JSON int to be decoded. By default, this is equivalent to
- ``int(num_str)``. This can be used to use another datatype or parser
- for JSON integers (e.g. :class:`float`).
-
- *parse_constant*, if specified, will be called with one of the
- following strings: ``'-Infinity'``, ``'Infinity'``, ``'NaN'``. This
- can be used to raise an exception if invalid JSON numbers are
- encountered.
-
- *strict* controls the parser's behavior when it encounters an
- invalid control character in a string. The default setting of
- ``True`` means that unescaped control characters are parse errors, if
- ``False`` then control characters will be allowed in strings.
-
- """
- self.encoding = encoding
- self.object_hook = object_hook
- self.object_pairs_hook = object_pairs_hook
- self.parse_float = parse_float or float
- self.parse_int = parse_int or int
- self.parse_constant = parse_constant or _CONSTANTS.__getitem__
- self.strict = strict
- self.parse_object = JSONObject
- self.parse_array = JSONArray
- self.parse_string = scanstring
- self.memo = {}
- self.scan_once = make_scanner(self)
-
- def decode(self, s, _w=WHITESPACE.match):
- """Return the Python representation of ``s`` (a ``str`` or ``unicode``
- instance containing a JSON document)
-
- """
- obj, end = self.raw_decode(s, idx=_w(s, 0).end())
- end = _w(s, end).end()
- if end != len(s):
- raise JSONDecodeError("Extra data", s, end, len(s))
- return obj
-
- def raw_decode(self, s, idx=0):
- """Decode a JSON document from ``s`` (a ``str`` or ``unicode``
- beginning with a JSON document) and return a 2-tuple of the Python
- representation and the index in ``s`` where the document ended.
-
- This can be used to decode a JSON document from a string that may
- have extraneous data at the end.
-
- """
- try:
- obj, end = self.scan_once(s, idx)
- except StopIteration:
- raise JSONDecodeError("No JSON object could be decoded", s, idx)
- return obj, end
diff --git a/shotgun_api3/lib/simplejson/encoder.py b/shotgun_api3/lib/simplejson/encoder.py
deleted file mode 100644
index f43f6f430..000000000
--- a/shotgun_api3/lib/simplejson/encoder.py
+++ /dev/null
@@ -1,503 +0,0 @@
-"""Implementation of JSONEncoder
-"""
-import re
-from decimal import Decimal
-
-def _import_speedups():
- try:
- from simplejson import _speedups
- return _speedups.encode_basestring_ascii, _speedups.make_encoder
- except ImportError:
- return None, None
-c_encode_basestring_ascii, c_make_encoder = _import_speedups()
-
-from simplejson.decoder import PosInf
-
-ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
-ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
-HAS_UTF8 = re.compile(r'[\x80-\xff]')
-ESCAPE_DCT = {
- '\\': '\\\\',
- '"': '\\"',
- '\b': '\\b',
- '\f': '\\f',
- '\n': '\\n',
- '\r': '\\r',
- '\t': '\\t',
-}
-for i in range(0x20):
- #ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
- ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
-
-FLOAT_REPR = repr
-
-def encode_basestring(s):
- """Return a JSON representation of a Python string
-
- """
- if isinstance(s, str) and HAS_UTF8.search(s) is not None:
- s = s.decode('utf-8')
- def replace(match):
- return ESCAPE_DCT[match.group(0)]
- return u'"' + ESCAPE.sub(replace, s) + u'"'
-
-
-def py_encode_basestring_ascii(s):
- """Return an ASCII-only JSON representation of a Python string
-
- """
- if isinstance(s, str) and HAS_UTF8.search(s) is not None:
- s = s.decode('utf-8')
- def replace(match):
- s = match.group(0)
- try:
- return ESCAPE_DCT[s]
- except KeyError:
- n = ord(s)
- if n < 0x10000:
- #return '\\u{0:04x}'.format(n)
- return '\\u%04x' % (n,)
- else:
- # surrogate pair
- n -= 0x10000
- s1 = 0xd800 | ((n >> 10) & 0x3ff)
- s2 = 0xdc00 | (n & 0x3ff)
- #return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
- return '\\u%04x\\u%04x' % (s1, s2)
- return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
-
-
-encode_basestring_ascii = (
- c_encode_basestring_ascii or py_encode_basestring_ascii)
-
-class JSONEncoder(object):
- """Extensible JSON encoder for Python data structures.
-
- Supports the following objects and types by default:
-
- +-------------------+---------------+
- | Python | JSON |
- +===================+===============+
- | dict | object |
- +-------------------+---------------+
- | list, tuple | array |
- +-------------------+---------------+
- | str, unicode | string |
- +-------------------+---------------+
- | int, long, float | number |
- +-------------------+---------------+
- | True | true |
- +-------------------+---------------+
- | False | false |
- +-------------------+---------------+
- | None | null |
- +-------------------+---------------+
-
- To extend this to recognize other objects, subclass and implement a
- ``.default()`` method with another method that returns a serializable
- object for ``o`` if possible, otherwise it should call the superclass
- implementation (to raise ``TypeError``).
-
- """
- item_separator = ', '
- key_separator = ': '
- def __init__(self, skipkeys=False, ensure_ascii=True,
- check_circular=True, allow_nan=True, sort_keys=False,
- indent=None, separators=None, encoding='utf-8', default=None,
- use_decimal=False):
- """Constructor for JSONEncoder, with sensible defaults.
-
- If skipkeys is false, then it is a TypeError to attempt
- encoding of keys that are not str, int, long, float or None. If
- skipkeys is True, such items are simply skipped.
-
- If ensure_ascii is true, the output is guaranteed to be str
- objects with all incoming unicode characters escaped. If
- ensure_ascii is false, the output will be unicode object.
-
- If check_circular is true, then lists, dicts, and custom encoded
- objects will be checked for circular references during encoding to
- prevent an infinite recursion (which would cause an OverflowError).
- Otherwise, no such check takes place.
-
- If allow_nan is true, then NaN, Infinity, and -Infinity will be
- encoded as such. This behavior is not JSON specification compliant,
- but is consistent with most JavaScript based encoders and decoders.
- Otherwise, it will be a ValueError to encode such floats.
-
- If sort_keys is true, then the output of dictionaries will be
- sorted by key; this is useful for regression tests to ensure
- that JSON serializations can be compared on a day-to-day basis.
-
- If indent is a string, then JSON array elements and object members
- will be pretty-printed with a newline followed by that string repeated
- for each level of nesting. ``None`` (the default) selects the most compact
- representation without any newlines. For backwards compatibility with
- versions of simplejson earlier than 2.1.0, an integer is also accepted
- and is converted to a string with that many spaces.
-
- If specified, separators should be a (item_separator, key_separator)
- tuple. The default is (', ', ': '). To get the most compact JSON
- representation you should specify (',', ':') to eliminate whitespace.
-
- If specified, default is a function that gets called for objects
- that can't otherwise be serialized. It should return a JSON encodable
- version of the object or raise a ``TypeError``.
-
- If encoding is not None, then all input strings will be
- transformed into unicode using that encoding prior to JSON-encoding.
- The default is UTF-8.
-
- If use_decimal is true (not the default), ``decimal.Decimal`` will
- be supported directly by the encoder. For the inverse, decode JSON
- with ``parse_float=decimal.Decimal``.
-
- """
-
- self.skipkeys = skipkeys
- self.ensure_ascii = ensure_ascii
- self.check_circular = check_circular
- self.allow_nan = allow_nan
- self.sort_keys = sort_keys
- self.use_decimal = use_decimal
- if isinstance(indent, (int, long)):
- indent = ' ' * indent
- self.indent = indent
- if separators is not None:
- self.item_separator, self.key_separator = separators
- elif indent is not None:
- self.item_separator = ','
- if default is not None:
- self.default = default
- self.encoding = encoding
-
- def default(self, o):
- """Implement this method in a subclass such that it returns
- a serializable object for ``o``, or calls the base implementation
- (to raise a ``TypeError``).
-
- For example, to support arbitrary iterators, you could
- implement default like this::
-
- def default(self, o):
- try:
- iterable = iter(o)
- except TypeError:
- pass
- else:
- return list(iterable)
- return JSONEncoder.default(self, o)
-
- """
- raise TypeError(repr(o) + " is not JSON serializable")
-
- def encode(self, o):
- """Return a JSON string representation of a Python data structure.
-
- >>> from simplejson import JSONEncoder
- >>> JSONEncoder().encode({"foo": ["bar", "baz"]})
- '{"foo": ["bar", "baz"]}'
-
- """
- # This is for extremely simple cases and benchmarks.
- if isinstance(o, basestring):
- if isinstance(o, str):
- _encoding = self.encoding
- if (_encoding is not None
- and not (_encoding == 'utf-8')):
- o = o.decode(_encoding)
- if self.ensure_ascii:
- return encode_basestring_ascii(o)
- else:
- return encode_basestring(o)
- # This doesn't pass the iterator directly to ''.join() because the
- # exceptions aren't as detailed. The list call should be roughly
- # equivalent to the PySequence_Fast that ''.join() would do.
- chunks = self.iterencode(o, _one_shot=True)
- if not isinstance(chunks, (list, tuple)):
- chunks = list(chunks)
- if self.ensure_ascii:
- return ''.join(chunks)
- else:
- return u''.join(chunks)
-
- def iterencode(self, o, _one_shot=False):
- """Encode the given object and yield each string
- representation as available.
-
- For example::
-
- for chunk in JSONEncoder().iterencode(bigobject):
- mysocket.write(chunk)
-
- """
- if self.check_circular:
- markers = {}
- else:
- markers = None
- if self.ensure_ascii:
- _encoder = encode_basestring_ascii
- else:
- _encoder = encode_basestring
- if self.encoding != 'utf-8':
- def _encoder(o, _orig_encoder=_encoder, _encoding=self.encoding):
- if isinstance(o, str):
- o = o.decode(_encoding)
- return _orig_encoder(o)
-
- def floatstr(o, allow_nan=self.allow_nan,
- _repr=FLOAT_REPR, _inf=PosInf, _neginf=-PosInf):
- # Check for specials. Note that this type of test is processor
- # and/or platform-specific, so do tests which don't depend on
- # the internals.
-
- if o != o:
- text = 'NaN'
- elif o == _inf:
- text = 'Infinity'
- elif o == _neginf:
- text = '-Infinity'
- else:
- return _repr(o)
-
- if not allow_nan:
- raise ValueError(
- "Out of range float values are not JSON compliant: " +
- repr(o))
-
- return text
-
-
- key_memo = {}
- if (_one_shot and c_make_encoder is not None
- and self.indent is None):
- _iterencode = c_make_encoder(
- markers, self.default, _encoder, self.indent,
- self.key_separator, self.item_separator, self.sort_keys,
- self.skipkeys, self.allow_nan, key_memo, self.use_decimal)
- else:
- _iterencode = _make_iterencode(
- markers, self.default, _encoder, self.indent, floatstr,
- self.key_separator, self.item_separator, self.sort_keys,
- self.skipkeys, _one_shot, self.use_decimal)
- try:
- return _iterencode(o, 0)
- finally:
- key_memo.clear()
-
-
-class JSONEncoderForHTML(JSONEncoder):
- """An encoder that produces JSON safe to embed in HTML.
-
- To embed JSON content in, say, a script tag on a web page, the
- characters &, < and > should be escaped. They cannot be escaped
- with the usual entities (e.g. &) because they are not expanded
- within |