def get_tree(text):
text = text.replace("\r\n", "\n")
text = text.replace("\r", "\n")
token_stream = get_lexer(text, DocumentLexer)
# first stage tree contains the full parse tree, including empty nodes
# such as <p> </p> and <p> <br> </p>.
first_stage_tree = build_parse_tree(token_stream)
# second stage tree clears up the empty text elements
second_stage_tree = filter_tree(first_stage_tree)
return second_stage_tree
def parse_comment(text):
from catonmat.parser.lexer import CommentLexer
# TODO: this method is 1:1 as pageparser.py:parsepage(),
# merge them!
text = text.replace("\r\n", "\n")
text = text.replace("\r", "\n")
token_stream = get_lexer(text, CommentLexer)
# first stage tree contains the full parse tree, including empty nodes
# such as <p> </p> and <p> <br> </p>.
first_stage_tree = build_parse_tree(token_stream)
# second stage tree clears up the empty text elements
second_stage_tree = filter_tree(first_stage_tree)
buffer = StringIO()
build_html(second_stage_tree, buffer)
return buffer.getvalue()