diff --git a/src/bootstraparse/modules/context_mngr.py b/src/bootstraparse/modules/context_mngr.py index d306c2c..9f1080d 100644 --- a/src/bootstraparse/modules/context_mngr.py +++ b/src/bootstraparse/modules/context_mngr.py @@ -229,17 +229,19 @@ class BaseContainer: f" Otrs[{len(self.get_others())}]" if self.get_others() else "" ) - def print_all(self, ident=''): + def print_all(self, ident=0): """ Prints the container and all its content. """ - print(ident + self.class_name()) + import rich + rich.print(" " * ident + self.class_name() + ':') for e in self: if isinstance(e, BaseContainer): - e.print_all(ident + ' ') + e.print_all(ident + 1) + if isinstance(e, syntax.SemanticType): + e.print_all(ident + 1) else: - print(ident + "> " + str(e)) - print("") + rich.print(" "*ident + "> " + str(e)) def to_container(self, filter_func=None): # noqa : C901 """ @@ -426,6 +428,7 @@ _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, } @@ -459,6 +462,8 @@ class ContextManager: self.dict_lookahead_reparse = [ "list:ulist", "list:olist", + "table:row", + "table:cell", ] self.contextualised = False @@ -705,16 +710,19 @@ class ContextManager: i -= 1 log_exception(LonelyOptionalError(self.pile[index], None), level="CRITICAL") - def print_all(self): + def print_all(self, ident=0): """ Prints the pile. """ + import rich for e in self: if isinstance(e, BaseContainer): - e.print_all() + e.print_all(ident + 1) + elif isinstance(e, syntax.SemanticType): + e.print_all(ident + 1) else: - print("> " + str(e)) - print("Matched elements:" + str(self.matched_elements)) + rich.print(" " * ident + str(e)) + rich.print("Matched elements:" + str(self.matched_elements)) # Defines all methods to manage the context of the parser as a file is being parsed diff --git a/src/bootstraparse/modules/export.py b/src/bootstraparse/modules/export.py index 38f7edc..e8311cb 100644 --- a/src/bootstraparse/modules/export.py +++ b/src/bootstraparse/modules/export.py @@ -240,11 +240,11 @@ class ContextConverter: return f"ContextConverter[{self.destination}] <{len(self.pile)}> " \ f"Status: {'initialized' if self.io_initialized else 'uninitialized'}" - def print_all(self): + def print_all(self, ident=0): """ Prints the entirety of the converted pile """ - print(self) + rich.print(self) def __eq__(self, other): return str(self) == str(other) diff --git a/src/bootstraparse/modules/syntax.py b/src/bootstraparse/modules/syntax.py index b0e01d7..bae84b4 100644 --- a/src/bootstraparse/modules/syntax.py +++ b/src/bootstraparse/modules/syntax.py @@ -86,6 +86,21 @@ class SemanticType: def __ne__(self, other): return not self.__eq__(other) + def print_all(self, ident=0): + """ + Print all lines of the token. + """ + import rich + rich.print(" "*ident + self.__class__.__name__ + ":") + if self.content: + for elt in self.content: + if isinstance(elt, cm.BaseContainer): + elt.print_all(ident+1) + elif isinstance(elt, SemanticType): + elt.print_all(ident+1) + else: + rich.print(" "*(ident+1) + str(elt)) + def counterpart(self): # noqa # FUTURE: Check for static counterpart implementation """ Function called by the context manager to know how to deal with the encapsulation of the token. @@ -283,16 +298,16 @@ class TableRowToken(FinalSemanticType, TokensToMatch): label = "table:row" -class TableCellToken(SemanticType): +class TableCellToken(FinalSemanticType): label = "table:cell" -class TableSeparatorToken(SemanticType): +class TableSeparatorToken(FinalSemanticType): label = "table:separator" -class TableCellSizeToken(SemanticType): - label = "table:cell_size" +class TableCellSizeToken(FinalSemanticType): + label = ":cell_size" class OptionalToken(SemanticType): @@ -502,9 +517,8 @@ se_start = (pps('<<') + structural_elements).add_parse_action(of_type(Structural se_end = (structural_elements + pps('>>')).add_parse_action(of_type(StructuralElementEndToken)) + pp.Opt(optional) se = se_end | se_start # Structural element table_row = pp.OneOrMore( - # pp.Regex(r'\|(\d)?')('table_colspan') + - (pp.Combine(pps('|') + pp.Word(pp.nums))('table_colspan').add_parse_action(of_type(TableCellSizeToken)) | pps('|')) + - pp.SkipTo('|')('table_cell').add_parse_action(reparse(enhanced_text), of_type(TableCellToken)) + ((pp.Combine(pps('|') + pp.Word(pp.nums))('table_colspan').add_parse_action(of_type(TableCellSizeToken)) | pps('|')) + + pp.SkipTo('|').add_parse_action(reparse(enhanced_text))('table_cell')).add_parse_action(of_type(TableCellToken)) ).add_parse_action(of_type(TableRowToken)) + pps('|') + pp.Opt(optional) table_separator = pp.OneOrMore( pps('|') + pp.Word(':-') diff --git a/tests/modules/test_context_mngr.py b/tests/modules/test_context_mngr.py index 544b33e..d3ca1e3 100644 --- a/tests/modules/test_context_mngr.py +++ b/tests/modules/test_context_mngr.py @@ -315,8 +315,8 @@ _token_list_with_expected_result = [ [ [ sy.TableRowToken([ - sy.TableCellSizeToken(["2"]), sy.TableCellToken([ + "2", sy.TextToken(["a"]), ]), sy.TableCellToken([ @@ -326,11 +326,18 @@ _token_list_with_expected_result = [ ], [ context_mngr.TableRowContainer([ - context_mngr.TableCellContainer([ - context_mngr.TextContainer([sy.TextToken(["a"])]), - ], others={"colspan": "2"}), - context_mngr.TableCellContainer([ - context_mngr.TextContainer([sy.TextToken(["b"])]), + sy.TableRowToken([ + context_mngr.TableCellContainer([ + sy.TableCellToken([ + "2", + context_mngr.TextContainer([sy.TextToken(["a"])]), + ]), + ]), + context_mngr.TableCellContainer([ + sy.TableCellToken([ + context_mngr.TextContainer([sy.TextToken(["b"])]), + ]), + ]), ]), ]), ], @@ -340,38 +347,46 @@ _token_list_with_expected_result = [ [ [ sy.TableRowToken([ - sy.TableCellSizeToken(["2"]), sy.TableCellToken([ + sy.TableCellSizeToken(["2"]), sy.TextToken(["a"]), ]), - sy.TableCellSizeToken(["3"]), sy.TableCellToken([ + sy.TableCellSizeToken(["3"]), sy.TextToken(["b"]), ]), ]), ], [ context_mngr.TableRowContainer([ - context_mngr.TableCellContainer([ # MONITOR # The colspan must be taken into account - context_mngr.TextContainer([sy.TextToken(["a"])]), - ]), - context_mngr.TableCellContainer([ - context_mngr.TextContainer([sy.TextToken(["b"])]), + sy.TableRowToken([ + context_mngr.TableCellContainer([ # MONITOR # The colspan must be taken into account + sy.TableCellToken([ + sy.TableCellSizeToken(["2"]), + context_mngr.TextContainer([sy.TextToken(["a"])]), + ]), + ]), + context_mngr.TableCellContainer([ + sy.TableCellToken([ + sy.TableCellSizeToken(["3"]), + context_mngr.TextContainer([sy.TextToken(["b"])]), + ]), + ]), ]), ]), ], __GLk(1), __XF, ], - [ - [ - sy.TableSeparatorToken(["---", "---"]), - ], - [ - error_mngr.MismatchedContainerError, - ], - __GLk(1), - ], + # [ + # [ + # sy.TableSeparatorToken(["---", "---"]), + # ], + # [ + # error_mngr.MismatchedContainerError, + # ], + # __GLk(1), + # ], [ [ sy.TableRowToken([ @@ -626,10 +641,13 @@ def test_container(): def test_context_call(init_list, expected, file_line): print(f"Executing tests @{file_line}") ctx = context_mngr.ContextManager(init_list) # noqa : F841 + # ctx.print_all() if isinstance(expected[0], context_mngr.BaseContainer) or isinstance(expected[0], sy.SemanticType): for i, e in zip(ctx(), expected): - rich.inspect(i) - rich.inspect(e) + # rich.inspect(i) + # rich.inspect(e) + i.print_all() + e.print_all() assert i == e else: with pytest.raises(expected[0]): diff --git a/tests/modules/test_syntax.py b/tests/modules/test_syntax.py index d202291..a40827b 100644 --- a/tests/modules/test_syntax.py +++ b/tests/modules/test_syntax.py @@ -458,33 +458,26 @@ dict_advanced_syntax_input_and_expected_output = { ), __GLk()), ("|2 Text1 | Text2 |", ( sy.TableRowToken([ - sy.TableCellSizeToken(['2']), - sy.TableCellToken([sy.TextToken(["Text1 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["2"]), sy.TextToken(["Text1 "])]), sy.TableCellToken([sy.TextToken(["Text2 "])]), ]), ), __GLk()), ("|2 Text1 |3 Text2 |", ( sy.TableRowToken([ - sy.TableCellSizeToken(['2']), - sy.TableCellToken([sy.TextToken(["Text1 "])]), - sy.TableCellSizeToken(['3']), - sy.TableCellToken([sy.TextToken(["Text2 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["2"]), sy.TextToken(["Text1 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["3"]), sy.TextToken(["Text2 "])]), ]), ), __GLk()), ("|2 Text1 |3 Text2 |4 Text3 |", ( sy.TableRowToken([ - sy.TableCellSizeToken(['2']), - sy.TableCellToken([sy.TextToken(["Text1 "])]), - sy.TableCellSizeToken(['3']), - sy.TableCellToken([sy.TextToken(["Text2 "])]), - sy.TableCellSizeToken(['4']), - sy.TableCellToken([sy.TextToken(["Text3 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["2"]), sy.TextToken(["Text1 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["3"]), sy.TextToken(["Text2 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["4"]), sy.TextToken(["Text3 "])]), ]), ), __GLk()), - ("|3 Text1 | Text2 | {var='test', number=11}", ( + ("|2 Text1 | Text2 | {var='test', number=11}", ( sy.TableRowToken([ - sy.TableCellSizeToken(['3']), - sy.TableCellToken([sy.TextToken(["Text1 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["2"]), sy.TextToken(["Text1 "])]), sy.TableCellToken([sy.TextToken(["Text2 "])]), ]), sy.OptionalToken([ @@ -517,8 +510,7 @@ dict_advanced_syntax_input_and_expected_output = { ), __GLk(),), ("|2 Text1 | Text2 |", ( sy.TableRowToken([ - sy.TableCellSizeToken(['2']), - sy.TableCellToken([sy.TextToken(["Text1 "])]), + sy.TableCellToken([sy.TableCellSizeToken(["2"]), sy.TextToken(["Text1 "])]), sy.TableCellToken([sy.TextToken(["Text2 "])]), ]), ), __GLk()), @@ -662,8 +654,8 @@ list_of_text_input_and_readable_output = [ # Tables ("| Text1 | Text2 |", "table", ",' />"), - ("| Text1 |3 Text2 |", "table", ",,' />"), + ("| Text1 |3 Text2 |", "table", ",,Text2 ' />' />"), ("|---|---|", "table_separator", ""), ("|:--|-:-|--:|--:|", "table_separator", ""), diff --git a/tests/modules/test_syntax_context.py b/tests/modules/test_syntax_context.py index edff5e1..ea04326 100644 --- a/tests/modules/test_syntax_context.py +++ b/tests/modules/test_syntax_context.py @@ -28,8 +28,8 @@ _type_counterpart_container = [ (syntax.HyperlinkToken, None, "self", tools.__GLk(1)), # Shouldn't be an error (syntax.TableToken, None, "error", tools.__GLk(1)), (syntax.TableRowToken, None, "self", tools.__GLk(1)), - (syntax.TableCellToken, None, "error", tools.__GLk(1)), - (syntax.TableSeparatorToken, None, "error", tools.__GLk(1)), + (syntax.TableCellToken, None, "self", tools.__GLk(1)), + (syntax.TableSeparatorToken, None, "self", tools.__GLk(1)), (syntax.BlockQuoteToken, None, "error", tools.__GLk(1)), (syntax.BlockQuoteAuthorToken, None, "error", tools.__GLk(1)), (syntax.CodeToken, "code", "token", tools.__GLk(1)),