Skip to content

Commit

Permalink
Make , and ; behave like \n as unscoped set delimiters.
Browse files Browse the repository at this point in the history
  • Loading branch information
@debiatan
debiatan committed Feb 25, 2021
1 parent 37fefae commit 4a4f4db
Show file tree
Hide file tree
Showing 3 changed files with 86 additions and 54 deletions.
16 changes: 8 additions & 8 deletions samples/output_parse/examples/output/parsed_example.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,28 +43,28 @@ Node {
Tag: @test_tag
Node {
Kind: Label,
Flags: 00000000000100000000000000000000,
Flag Names: Identifier,
Flags: 00000001000100000000000000000000,
Flag Names: BeforeComma, Identifier,
String: y,
Whole String: y,
Node {
Kind: Label,
Flags: 00000001000100000000000000000000,
Flag Names: BeforeComma, Identifier,
Flags: 00000000000100000000000000000000,
Flag Names: Identifier,
String: float,
Whole String: float,
}
}
Node {
Kind: Label,
Flags: 00000000000100000000000000000000,
Flag Names: Identifier,
Flags: 00000001010100000000000000000000,
Flag Names: BeforeComma, AfterComma, Identifier,
String: z,
Whole String: z,
Node {
Kind: Label,
Flags: 00000001000100000000000000000000,
Flag Names: BeforeComma, Identifier,
Flags: 00000000000100000000000000000000,
Flag Names: Identifier,
String: i32,
Whole String: i32,
}
Expand Down
19 changes: 14 additions & 5 deletions source/md_impl.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1683,20 +1683,29 @@ _MD_ParseSet(MD_ParseCtx *ctx, MD_Node *parent, _MD_ParseSetFlags flags,
// NOTE(rjf): Separators.
{
MD_b32 result = 0;
if(MD_Parse_Require(ctx, MD_S8Lit(","), MD_TokenKind_Symbol))
if(terminate_with_separator)
{
MD_Token next_token = MD_Parse_PeekSkipSome(ctx, 0);
if(next_token.kind == MD_TokenKind_Newline ||
(next_token.kind == MD_TokenKind_Symbol &&
(MD_StringMatch(next_token.string, MD_S8Lit(","), 0) ||
MD_StringMatch(next_token.string, MD_S8Lit(";"), 0))))
{
result = 1;
}
}
else if(MD_Parse_Require(ctx, MD_S8Lit(","), MD_TokenKind_Symbol))
{
result |= 1;
child->flags |= MD_NodeFlag_BeforeComma;
next_child_flags |= MD_NodeFlag_AfterComma;
}
else if(MD_Parse_Require(ctx, MD_S8Lit(";"), MD_TokenKind_Symbol))
{
result |= 1;
child->flags |= MD_NodeFlag_BeforeSemicolon;
next_child_flags |= MD_NodeFlag_AfterSemicolon;
}
result |= (MD_Parse_PeekSkipSome(ctx, 0).kind == MD_TokenKind_Newline);
if(result && terminate_with_separator)

if(result)
{
goto end_parse;
}
Expand Down
105 changes: 64 additions & 41 deletions tests/grammar.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,74 +11,97 @@

//// Arbitrarily deep tree, possibly empty
// file : [@child set]
// set : '{' [@child set] '}' | set [' ' @sibling set]
// set : '{' [@child set] '}' | set [separator @sibling set]
// separator : ' ' | '\n' | ',' | ';'

//// Labeled leaves
// file : [@child set]
// set : @fill 'A' | '{' [@child set] '}' | set [' ' @sibling set]
// set : @fill 'A' | '{' [@child set] '}' | set [separator @sibling set]
// separator : ' ' | '\n' | ',' | ';'

//// Labels also on internal nodes ('iset' is an implicitly separated set)
//// Labeled internal nodes
// file : [@child set]
// set : @fill 'A' [':' @child iset '\n'] | [@fill 'A' ':'] scoped_set | set [' ' @sibling set]
// iset : @fill 'A' [iset_tail]
// iset_tail : ':' @child iset | ' ' @sibling iset | ':' scoped_set | ' ' @sibling scoped_set
// set : @fill 'A' | [@fill 'A' ':'] scoped_set | set [separator @sibling set]
// separator : ' ' | '\n' | ',' | ';'
// scoped_set : '{' [@child set] '}'

//// Unscoped tests (feels like there should be an easier way to express this)
// file : general_set
// general_set : { [@child set] | [@child uns_set] }
// set : @fill 'A' | set [sep1 @sibling set] | scoped_set | uns_set sep2 @sibling set
// uns_set : @fill 'A' [uns_set_tail]
// uns_set_tail : ':' @child uns_set | ' ' @sibling uns_set | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' general_set '}'
// sep1 : ' ' | '\n' | ',' | ';'
// sep2 : '\n'| ',' | ';'

//// Tags
// file : [@child set]
// file : general_set
// general_set : { [@child set] | [@child uns_set] }
// set : {[tag_list] untagged_set}
// iset : {[tag_list] untagged_iset}
// uns_set : {[tag_list] untagged_uns_set}
// tag_list : '@' @tag tag ' ' [tag_list]
// tag : @fill 'T'['(' [@child set] ')']
// untagged_set : @fill 'A' [':' @child iset '\n'] | [@fill 'A' ':'] scoped_set | set [' ' @sibling set]
// untagged_iset : @fill 'A' [iset_tail]
// iset_tail : ':' @child iset | ' ' @sibling iset | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' [@child set] '}'
// tag : @fill 'T'['(' general_set ')']
// untagged_set : @fill 'A' | set [sep1 @sibling set] | scoped_set | uns_set sep2 @sibling set
// untagged_uns_set: @fill 'A' [uns_set_tail]
// uns_set_tail : ':' @child uns_set | ' ' @sibling uns_set | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' general_set '}'
// sep1 : ' ' | '\n' | ',' | ';'
// sep2 : '\n'| ',' | ';'

//// Alternative scope markers
// file : [@child set]
// file : general_set
// general_set : { [@child set] | [@child uns_set] }
// set : {[tag_list] untagged_set}
// iset : {[tag_list] untagged_iset}
// uns_set : {[tag_list] untagged_uns_set}
// tag_list : '@' @tag tag ' ' [tag_list]
// tag : @fill 'T'['(' [@child set] ')']
// untagged_set : @fill 'A' [':' @child iset '\n'] | [@fill 'A' ':'] scoped_set | set [' ' @sibling set]
// untagged_iset : @fill 'A' [iset_tail]
// iset_tail : ':' @child iset | ' ' @sibling iset | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' [@child set] '}' | scope_beg [@child set] scope_end
// scope_beg : '(' | '['
// scope_end : ')' | ']'
// tag : @fill 'T'['(' general_set ')']
// untagged_set : @fill 'A' | set [sep1 @sibling set] | scoped_set | uns_set sep2 @sibling set
// untagged_uns_set: @fill 'A' [uns_set_tail]
// uns_set_tail : ':' @child uns_set | ' ' @sibling uns_set | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' general_set '}' | alt_scope_beg general_set alt_scope_end
// alt_scope_beg : '(' | '['
// alt_scope_end : ')' | ']'
// sep1 : ' ' | '\n' | ',' | ';'
// sep2 : '\n'| ',' | ';'

//// Identifiers
// file : [@child set]
// file : general_set
// general_set : { [@child set] | [@child uns_set] }
// set : {[tag_list] untagged_set}
// iset : {[tag_list] untagged_iset}
// uns_set : {[tag_list] untagged_uns_set}
// tag_list : '@' @tag tag ' ' [tag_list]
// tag : @fill id['(' [@child set] ')']
// untagged_set : @fill 'A' [':' @child iset '\n'] | [@fill 'A' ':'] scoped_set | set [' ' @sibling set]
// untagged_iset : @fill 'A' [iset_tail]
// iset_tail : ':' @child iset | ' ' @sibling iset | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' [@child set] '}' | scope_beg [@child set] scope_end
// scope_beg : '(' | '['
// scope_end : ')' | ']'
// id : alpha [alphanumeric]
// tag : @fill id['(' general_set ')']
// untagged_set : @fill 'A' | set [sep1 @sibling set] | scoped_set | uns_set sep2 @sibling set
// untagged_uns_set: @fill 'A' [uns_set_tail]
// uns_set_tail : ':' @child uns_set | ' ' @sibling uns_set | ':' scoped_set | ' ' @sibling scoped_set
// scoped_set : '{' general_set '}' | alt_scope_beg general_set alt_scope_end
// alt_scope_beg : '(' | '['
// alt_scope_end : ')' | ']'
// sep1 : ' ' | '\n' | ',' | ';'
// sep2 : '\n'| ',' | ';'
// id : alpha [alphanumeric] | '_' [alphanumeric]
// alphanumeric : alpha [alphanumeric] | digit [alphanumeric] | '_' [alphanumeric]
// alpha : lowercase | uppercase
// lowercase : 'a'|'b'|'c'|'d'|'e'|'f'|'g'|'h'|'i'|'j'|'k'|'l'|'m'|'n'|'o'|'p'|'q'|'r'|'s'|'t'|'u'|'v'|'w'|'z'|'y'|'z'
// uppercase : 'A'|'B'|'C'|'D'|'E'|'F'|'G'|'H'|'I'|'J'|'K'|'L'|'M'|'N'|'O'|'P'|'Q'|'R'|'S'|'T'|'U'|'V'|'W'|'Z'|'Y'|'Z'
// digit : '0'|'1'|'2'|'3'|'4'|'5'|'6'|'7'|'8'|'9'

//// General labels
file : [@child set]
file : general_set
general_set : { [@child set] | [@child uns_set] }
set : {[tag_list] untagged_set}
iset : {[tag_list] untagged_iset}
uns_set : {[tag_list] untagged_uns_set}
tag_list : '@' @tag tag ' ' [tag_list]
tag : @fill id['(' [@child set] ')']
untagged_set : @fill label [':' @child iset '\n'] | [@fill label ':'] scoped_set | set [' ' @sibling set]
untagged_iset : @fill label [iset_tail]
iset_tail : ':' @child iset | ' ' @sibling iset | ':' scoped_set | ' ' @sibling scoped_set
scoped_set : '{' [@child set] '}' | scope_beg [@child set] scope_end
scope_beg : '(' | '['
scope_end : ')' | ']'
tag : @fill id['(' general_set ')']
untagged_set : @fill label | set [sep1 @sibling set] | scoped_set | uns_set sep2 @sibling set
untagged_uns_set: @fill label [uns_set_tail]
uns_set_tail : ':' @child uns_set | ' ' @sibling uns_set | ':' scoped_set | ' ' @sibling scoped_set
scoped_set : '{' general_set '}' | alt_scope_beg general_set alt_scope_end
alt_scope_beg : '(' | '['
alt_scope_end : ')' | ']'
sep1 : ' ' | '\n' | ',' | ';'
sep2 : '\n'| ',' | ';'
id : alpha [alphanumeric] | '_' [alphanumeric]
alphanumeric : alpha [alphanumeric] | digit [alphanumeric] | '_' [alphanumeric]
alpha : lowercase | uppercase
Expand Down

0 comments on commit 4a4f4db

Please sign in to comment.