From a981df2487f1b000c30fbb0dd064f8f321a60e96 Mon Sep 17 00:00:00 2001 From: Dandaedre Date: Wed, 16 Mar 2022 14:54:39 +0100 Subject: [PATCH] Reached 100% coverage and did updated the markup to match the new parsing direction --- src/bootstraparse/modules/syntax.py | 35 ++++------- tests/modules/test_syntax.py | 92 ++++++++++++++++++++++++++++- 2 files changed, 104 insertions(+), 23 deletions(-) diff --git a/src/bootstraparse/modules/syntax.py b/src/bootstraparse/modules/syntax.py index b0a535e..e446b92 100644 --- a/src/bootstraparse/modules/syntax.py +++ b/src/bootstraparse/modules/syntax.py @@ -137,32 +137,23 @@ def readable_markup(list_of_tokens): 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:] + readable_string += _add_tag(token) + return readable_string -def _add_tag(tag, content): - if content: - return f' <{tag}>{content}' - return '' +def _add_tag(token): + """ + Function used for testing and readability purposes. Replaces matched markup with html-like tags. + :param token: matched markup token in analysed text. + :return: returns readable string. + """ + if token.label == 'text': + return token.content[0] + if token.content: + return "<{} = '{}' />".format(token.label, ",".join(token.content)) -# create_image_token = of_type(ImageToken) -# create_image_token() - # Base elements quotes = pp.Word(r""""'""") value = (quotes + pp.Word(pp.alphanums + r'.') + pp.match_previous_literal(quotes) ^ @@ -212,7 +203,7 @@ il_link = pp.Literal('[') + ... + pp.Literal('](') + pp.QuotedString("'\"", esc_ # 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 = (pp.Literal('#') + ... + pps('#')).add_parse_action(of_type(HeaderToken)) # TODO: Don't use "^" (longest match wins) use "|" (first match wins) # TODO: add a ("name") ? # TODO: Suppress the "." one_olist = pp.line_start + \ diff --git a/tests/modules/test_syntax.py b/tests/modules/test_syntax.py index ec77fef..51bb2e2 100644 --- a/tests/modules/test_syntax.py +++ b/tests/modules/test_syntax.py @@ -3,6 +3,9 @@ import pytest import bootstraparse.modules.syntax as sy +############################################################################################################## +# PRE-PARSER +############################################################################################################## # Dictionary of all label and associated token used in the Pre_parser list_of_token_types = { "alias": sy.AliasToken, @@ -48,6 +51,10 @@ expressions_to_match = { } +############################################################################################################## +# PARSER +############################################################################################################## + # Testing the parser lexical elements dict_advanced_syntax_input_and_expected_output = { # Enhanced text # TODO : Test optional inline args @@ -127,7 +134,7 @@ dict_advanced_syntax_input_and_expected_output = { ("div>> [class='blue', 123#]{var='test', number=11}", (sy.UnimplementedToken(["div", ">>", sy.UnimplementedToken(["[", "class='blue'", ",", "123#", "]"]), sy.UnimplementedToken(["{", "var='test'", ",", "number=11", "}"])]))), # noqa E501 (line too long) ], - # Elements + # List Elements "one_olist": [ # Matches a one-level ordered list element, must be at the beginning of the line # Drop the "." from the match @@ -181,6 +188,53 @@ dict_advanced_syntax_input_and_expected_output = { ], } +list_add_tag_input_and_expected_output = [ + # Test cases for the add_tag function + # Input: + (sy.TextToken(["Text"]), "Text"), + (sy.EtEmToken(["*"]), ""), + (sy.EtStrongToken(["**"]), ""), + (sy.EtUnderlineToken(["__"]), ""), + (sy.EtStrikethroughToken(["~~"]), ""), + (sy.StructuralElementStartToken(["div"]), ""), + (sy.StructuralElementEndToken(["div"]), ""), + (sy.EtCustomSpanToken(["(#12)"]), ""), + (sy.HeaderToken(["#", "Text"]), "
"), +] + + +list_of_text_input_and_readable_output = [ + # Header + ("# Text1 #", "one_header", ""), + ("## Text2 ##", "one_header", ""), + + # Text + ("*Italic*", "et_em", "Italic"), + ("__Underline__", "et_underline", "Underline"), + ("**Bold**", "et_strong", "Bold"), + ("~~Strikethrough~~", "et_strikethrough", "Strikethrough"), + ("Text *bold __underline__ still bold*", "enhanced_text", "Text bold underline still bold"), # noqa E501 (line too long) + ("[link]('http://www.google.com')", "il_link", ""), + + # Structural elements + ("<"), + ("div>>", "se", ">>"), + + # Lists + ("- Text", "et_ulist", ""), + ("12. Text", "et_olist", ""), + ("# Text", "et_olist", ""), + + # Tables + ("| Text1 | Text2 |", "table", ""), + ("| Text1 |3 Text2 |", "table", ""), + ("|---|---|", "table_separator", ""), + ("|:--|-:-|--:|--:|", "table_separator", ""), + + # Other Mostly for testing and coverage + ("'", "quotes", "'"), +] + @pytest.mark.parametrize("token_name,token_class", list_of_token_types.items()) def test_token_type_exists(token_name, token_class): @@ -286,3 +340,39 @@ def test_advanced_expression_and_token_creation(expression, tokens): assert result is not None for token, expected_token in zip(result, expected_tokens): assert token == expected_token + + +######################################################################################################################## +# TEXT OUTPUT +######################################################################################################################## +# Test the add tag function + +@pytest.mark.parametrize("token, expected_output", list_add_tag_input_and_expected_output) +def test__add_tag(token, expected_output): + """ + Test that the add_tag function works correctly. + :param token: The token to test. + :param expected_output: The expected output. + :type token: sy.SemanticType + :type expected_output: str + """ + assert sy._add_tag(token) == expected_output + + +# Test text functions +@pytest.mark.parametrize("token_list, parsing_expression, expected", list_of_text_input_and_readable_output) +def test_readable_markup(token_list, parsing_expression, expected): + """ + Test that the readable markup is correctly generated. + :param token_list: The list of tokens. + :param parsing_expression: The parsing expression. + :param expected: The expected readable markup. + :type token_list: str + :type parsing_expression: str + :type expected: str + """ + expr = find_expression_from_str(parsing_expression) + assert isinstance(expr, pyparsing.ParserElement) + result = expr.parse_string(token_list) + assert result is not None + assert sy.readable_markup(result) == expected