9.8 $Sˆl–äY>”Ê:”�ã`S�ÿÚ „l"ußÙÀ×?÷S # Scanner produces tokens of the following types: # STREAM-START # STREAM-END # DIRECTIVE(name, value) # DOCUMENT-START # DOCUMENT-END # BLOCK-SEQUENCE-START # BLOCK-MAPPING-START # BLOCK-END # FLOW-SEQUENCE-START # FLOW-MAPPING-START # FLOW-SEQUENCE-END # FLOW-MAPPING-END # BLOCK-ENTRY # FLOW-ENTRY # KEY # VALUE # ALIAS(value) # ANCHOR(value) # TAG(value) # SCALAR(value, plain, style) # # Read comments in the Scanner code for more details. # __all__ = ['Scanner', 'ScannerError'] from .error import MarkedYAMLError from .tokens import * class ScannerError(MarkedYAMLError): pass class SimpleKey: # See below simple keys treatment. def __init__(self, token_number, required, index, line, column, mark): self.token_number = token_number self.required = required self.index = index self.line = line self.column = column self.mark = mark class Scanner: def __init__(self): """Initialize the scanner.""" # It is assumed that Scanner and Reader will have a common descendant. # Reader do the dirty work of checking for BOM and converting the # input data to Unicode. It also adds NUL to the end. # # Reader supports the following methods # self.peek(i=0) # peek the next i-th character # self.prefix(l=1) # peek the next l characters # self.forward(l=1) # read the next l characters and move the pointer. # Had we reached the end of the stream? self.done = False # The number of unclosed '{' and '['. `flow_level == 0` means block # context. self.flow_level = 0 # List of processed tokens that are not yet emitted. self.tokens = [] # Add the STREAM-START token. self.fetch_stream_start() # Number of tokens that were emitted through the `get_token` method. self.tokens_taken = 0 # The current indentation level. self.indent = -1 # Past indentation levels. self.indents = [] # Variables related to simple keys treatment. # A simple key is a key that is not denoted by the '?' indicator. # Example of simple keys: # --- # block simple key: value # ? not a simple key: # : { flow simple key: value } # We emit the KEY token before all keys, so when we find a potential # simple key, we try to locate the corresponding ':' indicator. # Simple keys should be limited to a single line and 1024 characters. # Can a simple key start at the current position? A simple key may # start: # - at the beginning of the line, not counting indentation spaces # (in block context), # - after '{', '[', ',' (in the flow context), # - after '?', ':', '-' (in the block context). # In the block context, this flag also signifies if a block collection # may start at the current position. self.allow_simple_key = True # Keep track of possible simple keys. This is a dictionary. The key # is `flow_level`; there can be no more that one possible simple key # for each level. The value is a SimpleKey record: # (token_number, required, index, line, column, mark) # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), # '[', or '{' tokens. self.possible_simple_keys = {} # Public methods. def check_token(self, *choices): # Check if the next token is one of the given types. while self.need_more_tokens(): self.fetch_more_tokens() if self.tokens: if not choices: return True for choice in choices: if isinstance(self.tokens[0], choice): return True return False def peek_token(self): # Return the next token, but do not delete if from the queue. # Return None if no more tokens.