From 63f5989ece18d9f1b1d309a7d54255de04d2ead2 Mon Sep 17 00:00:00 2001 From: vicky Date: Wed, 16 Mar 2022 15:39:27 +0100 Subject: [PATCH] fixed one_header --- src/bootstraparse/modules/syntax.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/src/bootstraparse/modules/syntax.py b/src/bootstraparse/modules/syntax.py index a9f4e89..162ed0a 100644 --- a/src/bootstraparse/modules/syntax.py +++ b/src/bootstraparse/modules/syntax.py @@ -177,6 +177,7 @@ structural_elements = ( pp.CaselessLiteral('aside') | pp.CaselessLiteral('section') )('structural_element') +header_element = pp.OneOrMore(pp.Literal('#')) # Optional elements @@ -205,8 +206,9 @@ se = se_end | se_start # Structural element # TODO Check nomenclature il_link = pp.Literal('[') + ... + pp.Literal('](') + quotes + http_characters + pp.match_previous_literal(quotes) + ')' # Oneline elements -# TODO: one_header should match any number of '#' I suggest either a div_element=Word("#") or a div_element=OneOrMore(pp.Literal('#')) with a pp.match_previous_literal(dive=_element) # noqa E501 (line too long) -one_header = (pp.Literal('#') + ... + pps('#')).add_parse_action(of_type(HeaderToken)) +one_header = ( + header_element + ... + pp.match_previous_literal(header_element) +).add_parse_action(of_type(HeaderToken)) one_olist = pp.line_start + ( pp.Literal('#') + pps('.') + ...('olist_text') + pp.line_end ).add_parse_action(of_type(EtOlistToken))