From 11e4df26acfc5b306dc8dac53262ce83cc403443 Mon Sep 17 00:00:00 2001 From: vicky Date: Thu, 10 Mar 2022 17:17:46 +0100 Subject: [PATCH] created function for testing and readability --- src/bootstraparse/modules/syntax.py | 88 ++++++++++++++++++++++------- 1 file changed, 67 insertions(+), 21 deletions(-) diff --git a/src/bootstraparse/modules/syntax.py b/src/bootstraparse/modules/syntax.py index 4fb1381..034df34 100644 --- a/src/bootstraparse/modules/syntax.py +++ b/src/bootstraparse/modules/syntax.py @@ -38,27 +38,27 @@ class TextToken(SemanticType): class EnhancedToken(SemanticType): - label = "enhanced text" + label = "text:enhanced" class EtEmToken(SemanticType): - label = "em text" + label = "text:em" class EtStrongToken(SemanticType): - label = "strong text" + label = "text:strong" class EtUnderlineToken(SemanticType): - label = "underline text" + label = "text:underline" class EtStrikethroughToken(SemanticType): - label = "strikethrough text" + label = "text:strikethrough" class EtCustomSpanToken(SemanticType): - label = "custom span text" + label = "text:custom_span" def of_type(token_class): @@ -73,6 +73,40 @@ def of_type(token_class): return _of_type +def readable_markup(list_of_tokens): + """ + Function used for testing and readability purposes. Replaces matched markup with html-like tags. + :param list_of_tokens: list of matched markup tokens in analysed text. + :return: returns readable string. + :rtype: string + """ + readable_string = '' + for token in list_of_tokens: + if type(token) == str: + readable_string += token + elif token.label == 'text:em': + readable_string += _add_tag('em', readable_markup(token.content)) + elif token.label == 'text:strong': + readable_string += _add_tag('b', readable_markup(token.content)) + elif token.label == 'text:underline': + readable_string += _add_tag('u', readable_markup(token.content)) + elif token.label == 'text:strikethrough': + readable_string += _add_tag('st', readable_markup(token.content)) + elif token.label == 'text:custom_span': + readable_string += _add_tag('#', readable_markup(token.content)) + elif token.label == 'text': + readable_string += ' ' + ' '.join(token.content) + else: + raise Exception('Unknown token type' + token.label) + return readable_string[1:] + + +def _add_tag(tag, content): + if content: + return f' <{tag}>{content}' + return '' + + # create_image_token = of_type(ImageToken) # create_image_token() # Base elements @@ -80,21 +114,22 @@ quotes = pp.Word(r""""'""") value = (quotes + pp.Word(pp.alphanums + r'.') + pp.match_previous_literal(quotes) ^ pp.common.fnumber)("value") assignation = pp.Group(pp.common.identifier('var_name') + '=' + value('var_value'))("assignation") -text = pp.OneOrMore(pp.Word(pp.alphanums)) +text = pp.OneOrMore(pp.Word(pp.alphanums))('text').add_parse_action(of_type(TextToken)) # Composite elements var = '[' + pp.delimitedList(assignation ^ value)("list_vars").set_name("list_vars") + ']' # Enhanced text enhanced_text = pp.Forward() -et_em = ('*' + enhanced_text + '*')('em') -et_strong = ('**' + enhanced_text + '**')('strong') -et_underline = ('__' + enhanced_text + '__')('underline') -et_strikethrough = ('~~' + enhanced_text + '~~')('strikethrough') -custom_span = '(#' + pp.Word(pp.nums) + ')' -et_custom_span = (custom_span + enhanced_text + pp.match_previous_literal(custom_span))('custom_span') -# enhanced_text <<= -# (et_strong ^ et_em ^ et_underline ^ et_strikethrough ^ et_custom_span ^ text) + pp.Optional(enhanced_text) +et_em = (pps('*') + enhanced_text + pps('*'))('em').add_parse_action(of_type(EtEmToken)) +et_strong = (pps('**') + enhanced_text + pps('**'))('strong').add_parse_action(of_type(EtStrongToken)) +et_underline = (pps('__') + enhanced_text + pps('__'))('underline').add_parse_action(of_type(EtUnderlineToken)) +et_strikethrough = (pps('~~') + enhanced_text + pps('~~'))('strikethrough').add_parse_action(of_type(EtStrikethroughToken)) +custom_span = ('(#' + pp.Word(pp.nums)('span_id') + ')').set_name('span_tag') +et_custom_span = \ + (custom_span + enhanced_text + pp.match_previous_literal(custom_span))('custom_span')\ + .add_parse_action(of_type(EtCustomSpanToken)) +enhanced_text <<= (text | et_strong | et_em | et_underline | et_strikethrough | et_custom_span) + pp.Opt(enhanced_text) # Specific elements @@ -120,9 +155,20 @@ line_to_replace = pp.OneOrMore(pp.SkipTo(image ^ alias)('text').add_parse_action # Temporary tests if __name__ == '__main__': # pragma: no cover pp.autoname_elements() - test_string = r""" - text ***str_text* em_text** text - """ - - saucisse = enhanced_text.parse_string(test_string) - rich.inspect(saucisse) + list_strings = [ + "Normal text", + "Normal text *em text*", + "Normal text **strong text**", + "Normal text __underline text__", + "Normal text ~~strikethrough text~~", + "Normal text (#123) custom span text(#123)", + "**Strong text __underline__** normal text", + "Normal text **strong text *em text*** *em text **strong text*** normal text", + ] + enhanced_text.create_diagram("../../../dev_outputs/diagram.html") + for string in list_strings: + print('Input string:', string) + output = enhanced_text.parseString(string) + # rich.inspect(output) + print('Output string:', readable_markup(output)) + print()