def extract_optional_attribute_value(line_to_parse, value_index):
"""
Determine and extract an optional attribute value.
"""
non_whitespace_index, _ = ParserHelper.extract_whitespace(
line_to_parse, value_index
)
if (
non_whitespace_index < len(line_to_parse)
and line_to_parse[non_whitespace_index]
!= HtmlHelper.__html_attribute_name_value_separator
) or non_whitespace_index >= len(line_to_parse):
return non_whitespace_index
non_whitespace_index += 1
non_whitespace_index, _ = ParserHelper.extract_whitespace(
line_to_parse, non_whitespace_index
)
if non_whitespace_index < len(line_to_parse):
first_character_of_value = line_to_parse[non_whitespace_index]
if first_character_of_value == HtmlHelper.__html_attribute_value_double:
(
non_whitespace_index,
extracted_text,
) = ParserHelper.collect_until_character(
line_to_parse,
non_whitespace_index + 1,
HtmlHelper.__html_attribute_value_double,
)
if non_whitespace_index == len(line_to_parse):
return -1
non_whitespace_index += 1
elif first_character_of_value == HtmlHelper.__html_attribute_value_single:
(
non_whitespace_index,
extracted_text,
) = ParserHelper.collect_until_character(
line_to_parse,
non_whitespace_index + 1,
HtmlHelper.__html_attribute_value_single,
)
if non_whitespace_index == len(line_to_parse):
return -1
non_whitespace_index += 1
else:
(
non_whitespace_index,
extracted_text,
) = ParserHelper.collect_until_one_of_characters(
line_to_parse,
non_whitespace_index,
HtmlHelper.__html_tag_attribute_value_terminators,
)
if not extracted_text:
non_whitespace_index = -1
else:
non_whitespace_index = -1
return non_whitespace_index
def test_simple_case_from_middle():
"""
Make sure that we test a simple extraction from the middle of the string.
"""
# Arrange
input_string = "this is a test"
start_index = 5
character_to_match = " "
expected_output = (7, "is")
# Act
actual_output = ParserHelper.collect_until_character(
input_string, start_index, character_to_match)
# Assert
assert expected_output == actual_output
def test_empty_string_with_good_index():
"""
Make sure that an empty string is handled properly with a good index
"""
# Arrange
input_string = ""
start_index = 0
character_to_match = " "
expected_output = (0, "")
# Act
actual_output = ParserHelper.collect_until_character(
input_string, start_index, character_to_match)
# Assert
assert expected_output == actual_output
def test_empty_string_with_bad_left_index():
"""
Make sure that an empty string is handled properly with an index that is too far to the left.
"""
# Arrange
input_string = ""
start_index = -1
character_to_match = " "
expected_output = (None, None)
# Act
actual_output = ParserHelper.collect_until_character(
input_string, start_index, character_to_match)
# Assert
assert expected_output == actual_output
def test_already_on_whitespace():
"""
Make sure that we test extracting while already on a whitespace character.
"""
# Arrange
input_string = "this is a test"
start_index = 9
character_to_match = " "
expected_output = (9, "")
# Act
actual_output = ParserHelper.collect_until_character(
input_string, start_index, character_to_match)
# Assert
assert expected_output == actual_output
def __parse_tag_attributes(text_to_parse, start_index):
"""
Handle the parsing of the attributes for an open tag.
"""
parse_index, _ = ParserHelper.collect_while_one_of_characters(
text_to_parse, start_index, HtmlHelper.__tag_attribute_name_characters
)
end_name_index, extracted_whitespace = ParserHelper.extract_any_whitespace(
text_to_parse, parse_index
)
if ParserHelper.is_character_at_index(
text_to_parse,
end_name_index,
HtmlHelper.__html_attribute_name_value_separator,
):
(
value_start_index,
extracted_whitespace,
) = ParserHelper.extract_any_whitespace(text_to_parse, end_name_index + 1)
if ParserHelper.is_character_at_index_one_of(
text_to_parse,
value_start_index,
HtmlHelper.__html_attribute_value_single,
):
value_end_index, _ = ParserHelper.collect_until_character(
text_to_parse,
value_start_index + 1,
HtmlHelper.__html_attribute_value_single,
)
if not ParserHelper.is_character_at_index(
text_to_parse,
value_end_index,
HtmlHelper.__html_attribute_value_single,
):
return None, -1
value_end_index += 1
elif ParserHelper.is_character_at_index_one_of(
text_to_parse,
value_start_index,
HtmlHelper.__html_attribute_value_double,
):
value_end_index, _ = ParserHelper.collect_until_character(
text_to_parse,
value_start_index + 1,
HtmlHelper.__html_attribute_value_double,
)
if not ParserHelper.is_character_at_index(
text_to_parse,
value_end_index,
HtmlHelper.__html_attribute_value_double,
):
return None, -1
value_end_index += 1
else:
value_end_index, _ = ParserHelper.collect_until_one_of_characters(
text_to_parse,
value_start_index,
HtmlHelper.__unquoted_attribute_value_stop,
)
end_name_index, extracted_whitespace = ParserHelper.extract_any_whitespace(
text_to_parse, value_end_index
)
return end_name_index, extracted_whitespace
def __parse_tag_attributes(
text_to_parse: str, start_index: int
) -> Tuple[Optional[int], Optional[str]]:
"""
Handle the parsing of the attributes for an open tag.
"""
parse_index, _ = ParserHelper.collect_while_one_of_characters(
text_to_parse, start_index, HtmlHelper.__tag_attribute_name_characters
)
assert parse_index is not None
end_name_index, extracted_whitespace = ParserHelper.extract_any_whitespace(
text_to_parse, parse_index
)
assert end_name_index is not None
if ParserHelper.is_character_at_index(
text_to_parse,
end_name_index,
HtmlHelper.__html_attribute_name_value_separator,
):
(
value_start_index,
extracted_whitespace,
) = ParserHelper.extract_any_whitespace(text_to_parse, end_name_index + 1)
assert value_start_index is not None
value_end_index: Optional[int] = None
if ParserHelper.is_character_at_index_one_of(
text_to_parse,
value_start_index,
HtmlHelper.__html_attribute_value_single,
):
value_end_index, _ = ParserHelper.collect_until_character(
text_to_parse,
value_start_index + 1,
HtmlHelper.__html_attribute_value_single,
)
assert value_end_index is not None
if not ParserHelper.is_character_at_index(
text_to_parse,
value_end_index,
HtmlHelper.__html_attribute_value_single,
):
return None, None
value_end_index += 1
elif ParserHelper.is_character_at_index_one_of(
text_to_parse,
value_start_index,
HtmlHelper.__html_attribute_value_double,
):
value_end_index, _ = ParserHelper.collect_until_character(
text_to_parse,
value_start_index + 1,
HtmlHelper.__html_attribute_value_double,
)
assert value_end_index is not None
if not ParserHelper.is_character_at_index(
text_to_parse,
value_end_index,
HtmlHelper.__html_attribute_value_double,
):
return None, None
value_end_index += 1
else:
value_end_index, _ = ParserHelper.collect_until_one_of_characters(
text_to_parse,
value_start_index,
HtmlHelper.__unquoted_attribute_value_stop,
)
assert value_end_index is not None
end_name_index, extracted_whitespace = ParserHelper.extract_any_whitespace(
text_to_parse, value_end_index
)
return end_name_index, extracted_whitespace
