WIP Table

This commit is contained in:
Maximilien Rigaut 2022-06-15 16:58:40 +02:00
parent 6654dcbb84
commit d30d8f7ad5
No known key found for this signature in database
GPG Key ID: 4F14B23709ADA5B1
4 changed files with 96 additions and 39 deletions

View File

@ -401,6 +401,11 @@ class TableCellContainer(BaseContainer):
pass
class TableCellSizeContainer(BaseContainer):
type = "table"
subtype = "t_cell"
class LinebreakContainer(BaseContainer):
def export(self, _):
if len(self.content) == 1:
@ -428,7 +433,7 @@ _to_container = {
"table:row": TableRowContainer,
"table:cell": TableCellContainer, # Should be an error I beleive ?
"table:separator": TableSeparatorContainer, # Should be an error I beleive ?
"table:cell_size": TableCellContainer,
"table:cell_size": TableCellSizeContainer,
}
@ -452,19 +457,24 @@ class ContextManager:
self.name = name
self.ident = ident
self.matched_elements = {}
self.dict_lookahead = {
self._dict_lookahead = {
"list:ulist": ["list:ulist"],
"list:olist": ["list:olist"],
"table:row": ["table:separator", "table:row"], # future: Implement tables
"table:cell": ["table:separator", "table:cell"],
"blockquotes": [], # future: Implement blockquotes
"linebreak": ["linebreak"],
}
self.dict_lookahead_reparse = [
self._dict_custom_lookahead = {
"table:row": self.table_lookahead, # future: Implement tables
}
self._dict_lookahead_reparse = [
"list:ulist",
"list:olist",
"table:row",
"table:cell",
]
self.contextualised = False
def encapsulate(self, start, end):
@ -575,11 +585,16 @@ class ContextManager:
self.pile[index] = None
# Group together multiple one-lines
elif token.label in self.dict_lookahead:
elif token.label in self._dict_lookahead:
lookahead_return = self.lookahead(token, index)
index += lookahead_return[0]
line_number += lookahead_return[1]
elif token.label in self._dict_custom_lookahead:
lookahead_return = self._dict_custom_lookahead[token.label](token, index)
index += lookahead_return[0]
line_number += lookahead_return[1]
# future: advanced lookahead for * logic
# elif token.label in self.dict_advanced_lookahead:
@ -658,13 +673,13 @@ class ContextManager:
"""
range_to_encapsulate = 0
line_skipped = 0
if self.parsed_list[index].label in self.dict_lookahead_reparse:
if self.parsed_list[index].label in self._dict_lookahead_reparse:
self.recontext(self.parsed_list[index])
i = index + 1
while i < len(self.parsed_list):
if self.parsed_list[i].label in self.dict_lookahead[token.label]:
if self.parsed_list[i].label in self.dict_lookahead_reparse:
if self.parsed_list[i].label in self._dict_lookahead[token.label]:
if self.parsed_list[i].label in self._dict_lookahead_reparse:
self.recontext(self.parsed_list[i])
self.pile.append(self.parsed_list[i])
range_to_encapsulate += 1
@ -681,6 +696,37 @@ class ContextManager:
self.encapsulate(index, index + range_to_encapsulate)
return range_to_encapsulate, line_skipped
def table_lookahead(self, token, index):
"""
Method to lookahead for a table.
Parameters
----------
token : syntax.Table
Token to lookahead for.
index : int
Index of the token in the pile.
Returns
-------
int : Index of the next token to lookahead for.
"""
range_to_encapsulate = 0
i = index + 1
while i < len(self.parsed_list):
if self.parsed_list[i].label == "linebreak":
self.pile.append(self.parsed_list[i])
range_to_encapsulate += 1
if self.parsed_list[i-1].label == "linebreak":
break
elif self.parsed_list[i].label in ["table:row", "table:separator"]:
self.pile.append(self.table_recontext(self.parsed_list[i]))
range_to_encapsulate += 1
elif self.parsed_list[i].label == "table:cell_size":
if not isinstance(self.pile[i-1], TableRowContainer):
raise MismatchedContainerError(token, "A table cell size must be preceded by a table row.")
self.pile[i-1].cell_size = self.parsed_list[i]
self.pile.append(None) # Unsure if this is the best way to do it.
range_to_encapsulate += 1
def recontext(self, token):
"""
Function to recontextualise the content of a token.
@ -691,6 +737,17 @@ class ContextManager:
"""
token.content = ContextManager(token.content, name=self.name)()
def table_recontext(self, token):
"""
Function to recontextualise the content of a table.
"""
for elt in token.content:
if isinstance(elt, syntax.TableCellToken):
elt.content = ContextManager(elt.content, name=self.name)()
elif isinstance(elt, syntax.TableCellSizeToken):
pass # Continue Here
elt.content = ContextManager(elt.content, name=self.name)()
def get_last_container_in_pile(self, index):
"""
Returns the last element in the pile if it is a Container, raises an error otherwise.

View File

@ -17,7 +17,7 @@ from bootstraparse.modules.tools import __GLk # __GFi, __GFu, __GL
_ERRORS = ["ParsingError", "MismatchedContainerError"]
def init_logging(filename=None, loglevel="ERROR", filemode='w', handler=None):
def init_logging(filename=None, loglevel="DEBUG", filemode='w', handler=None):
"""
Initializes logging
:param filename: The path for the log file
@ -135,7 +135,7 @@ class MismatchedContainerError(BootstraparseError):
"""
The token is not final and cannot be contained. Indicative of a mismatched token.
"""
def __init__(self, token):
def __init__(self, token, message=""):
"""
Initializes the MismatchedContainerError class with the token that was not final
:param token: The token that is not final
@ -150,7 +150,7 @@ class MismatchedContainerError(BootstraparseError):
self.line = None
self.label = None
self.name = None
super().__init__(f"Could not process {self.label} at line {self.line} in file {self.name}.")
super().__init__(f"Could not process {self.label} at line {self.line} in file {self.name}. {message}")
class LonelyOptionalError(BootstraparseError):

View File

@ -329,7 +329,7 @@ _token_list_with_expected_result = [
sy.TableRowToken([
context_mngr.TableCellContainer([
sy.TableCellToken([
"2",
sy.TableCellSizeToken(["2"]),
context_mngr.TextContainer([sy.TextToken(["a"])]),
]),
]),

View File

@ -622,46 +622,46 @@ list_add_tag_input_and_expected_output = [
# test_readable_markup
list_of_text_input_and_readable_output = [
# Header
("# Text1 #", "one_header", "<header = '#,Text1 ' />"),
("## Text2 ##", "one_header", "<header = '##,Text2 ' />"),
("# Text1 #", "one_header", "<header = '#,Text1 ' />", __GL()),
("## Text2 ##", "one_header", "<header = '##,Text2 ' />", __GL()),
# Text
# il_link | et_strong | et_em | et_strikethrough | et_underline | et_custom_span
("*Italic*", "et_em", "<text:em />"),
("__Underline__", "et_underline", "<text:underline />"),
("**Bold**", "et_strong", "<text:strong />"),
("~~Strikethrough~~", "et_strikethrough", "<text:strikethrough />"),
("*Italic*", "et_em", "<text:em />", __GL()),
("__Underline__", "et_underline", "<text:underline />", __GL()),
("**Bold**", "et_strong", "<text:strong />", __GL()),
("~~Strikethrough~~", "et_strikethrough", "<text:strikethrough />", __GL()),
("Text *bold __underline__ still bold*", "enhanced_text",
"Text <text:em /> bold <text:underline /> underline <text:underline /> still bold <text:em />"),
"Text <text:em /> bold <text:underline /> underline <text:underline /> still bold <text:em />", __GL()),
# noqa E501 (line too long)
("[link]('http://www.google.com')", "il_link", "<hyperlink = '[link]('http://www.google.com')' />"),
("[link]('http://www.google.com')", "il_link", "<hyperlink = '[link]('http://www.google.com')' />", __GL()),
("Reverse order:(#123) Span, __underline__ ~~strikethrough~~ **emphasis * Strong**", "enhanced_text",
"Reverse order: <text:custom_span:123 /> Span, <text:underline /> underline <text:underline /> <text:strikethrough /> strikethrough <text:strikethrough /> <text:strong /> emphasis <text:em /> Strong <text:strong />"), # noqa E501 (line too long)
"Reverse order: <text:custom_span:123 /> Span, <text:underline /> underline <text:underline /> <text:strikethrough /> strikethrough <text:strikethrough /> <text:strong /> emphasis <text:em /> Strong <text:strong />", __GL()), # noqa E501 (line too long)
# Structural elements
("<<div", "se", "<se:start:div = 'div' />"),
("div>>", "se", "<se:end:div = 'div' />"),
("<<article", "se", "<se:start:article = 'article' />"),
("article>>", "se", "<se:end:article = 'article' />"),
("<<aside", "se", "<se:start:aside = 'aside' />"),
("aside>>", "se", "<se:end:aside = 'aside' />"),
("<<section", "se", "<se:start:section = 'section' />"),
("section>>", "se", "<se:end:section = 'section' />"),
("<<div", "se", "<se:start:div = 'div' />", __GL()),
("div>>", "se", "<se:end:div = 'div' />", __GL()),
("<<article", "se", "<se:start:article = 'article' />", __GL()),
("article>>", "se", "<se:end:article = 'article' />", __GL()),
("<<aside", "se", "<se:start:aside = 'aside' />", __GL()),
("aside>>", "se", "<se:end:aside = 'aside' />", __GL()),
("<<section", "se", "<se:start:section = 'section' />", __GL()),
("section>>", "se", "<se:end:section = 'section' />", __GL()),
# Lists
("- Text", "one_ulist", "<list:ulist = 'Text' />"),
("#. Text", "one_olist", "<list:olist = 'Text' />"),
("- Text", "one_ulist", "<list:ulist = 'Text' />", __GL()),
("#. Text", "one_olist", "<list:olist = 'Text' />", __GL()),
# Tables
("| Text1 | Text2 |", "table", "<table:row = '<table:cell = 'Text1 ' />,<table:cell = 'Text2 ' />' />"),
("| Text1 |3 Text2 |", "table", "<table:row = '<table:cell = 'Text1 ' />,<table:cell = '<:cell_size = '3' "
"/>,Text2 ' />' />"),
("|---|---|", "table_separator", "<table:separator = '---,---' />"),
("|:--|-:-|--:|--:|", "table_separator", "<table:separator = ':--,-:-,--:,--:' />"),
("| Text1 | Text2 |", "table", "<table:row = '<table:cell = 'Text1 ' />,<table:cell = 'Text2 ' />' />", __GL()),
("| Text1 |3 Text2 |", "table", "<table:row = '<table:cell = 'Text1 ' />,<table:cell = '<table:cell_size = '3' "
"/>,Text2 ' />' />", __GL()),
("|---|---|", "table_separator", "<table:separator = '---,---' />", __GL()),
("|:--|-:-|--:|--:|", "table_separator", "<table:separator = ':--,-:-,--:,--:' />", __GL()),
# Other Mostly for testing and coverage
("'", "quotes", "'"),
(" -", "line", "-"),
("'", "quotes", "'", __GL()),
(" -", "line", "-", __GL()),
]
@ -852,8 +852,8 @@ def test__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):
@pytest.mark.parametrize("token_list, parsing_expression, expected, line", list_of_text_input_and_readable_output)
def test_readable_markup(token_list, parsing_expression, expected, line):
"""
Test that the readable markup is correctly generated.
:param token_list: The list of tokens.