Grammar railroad diagram
Closed this issue · 0 comments
mingodad commented
There is a tool to produce railroad diagrams (https://en.wikipedia.org/wiki/Syntax_diagram) and with a help of a custom parser we can get a nice diagram that can be used to document and understand/modify the grammar.
Copy and paste the EBNFs (one at a time) bellow at https://www.bottlecaps.de/rr/ui on the Edit Grammar tab then click on the View Diagram tab to see a navigable xhtml railroad diagram (that can also be generated offline or downloaded).
src/parser.mly.ebnf:
entry_point ::= program EOF
program ::= linebreak complete_commands linebreak
| linebreak
complete_commands ::= complete_commands newline_list complete_command
| complete_command
complete_command ::= clist separator_op
| clist
clist ::= clist separator_op and_or
| and_or
and_or ::= pipeline
| and_or AND_IF linebreak pipeline
| and_or OR_IF linebreak pipeline
pipeline ::= pipe_sequence
| Bang pipe_sequence
pipe_sequence ::= command
| pipe_sequence Pipe linebreak command
command ::= simple_command
| compound_command
| compound_command redirect_list
| function_definition
compound_command ::= brace_group
| subshell
| for_clause
| case_clause
| if_clause
| while_clause
| until_clause
subshell ::= Lparen compound_list Rparen
compound_list ::= linebreak term
| linebreak term separator
term ::= term separator and_or
| and_or
for_clause ::= For name do_group
| For name sequential_sep do_group
| For name linebreak cin sequential_sep do_group
| For name linebreak cin wordlist sequential_sep do_group
name ::= NAME
cin ::= In
wordlist ::= wordlist word
| word
case_clause ::= Case word linebreak cin linebreak case_list Esac
| Case word linebreak cin linebreak case_list_ns Esac
| Case word linebreak cin linebreak Esac
case_list_ns ::= case_list case_item_ns
| case_item_ns
case_list ::= case_list case_item
| case_item
case_item_ns ::= pattern Rparen linebreak
| pattern Rparen compound_list
| Lparen pattern Rparen linebreak
| Lparen pattern Rparen compound_list
case_item ::= pattern Rparen linebreak DSEMI linebreak
| pattern Rparen compound_list DSEMI linebreak
| Lparen pattern Rparen linebreak DSEMI linebreak
| Lparen pattern Rparen compound_list DSEMI linebreak
pattern ::= word
| pattern Pipe word
if_clause ::= If compound_list Then compound_list else_part Fi
| If compound_list Then compound_list Fi
else_part ::= Elif compound_list Then compound_list
| Elif compound_list Then compound_list else_part
| Else compound_list
while_clause ::= While compound_list do_group
until_clause ::= Until compound_list do_group
function_definition ::= fname Lparen Rparen linebreak function_body
function_body ::= compound_command
| compound_command redirect_list
fname ::= NAME
brace_group ::= Lbrace compound_list Rbrace
do_group ::= Do compound_list Done
simple_command ::= cmd_prefix cmd_word cmd_suffix
| cmd_prefix cmd_word
| cmd_prefix
| cmd_name cmd_suffix
| cmd_name
cmd_name ::= word
cmd_word ::= word
cmd_prefix ::= io_redirect
| cmd_prefix io_redirect
| ASSIGNMENT_WORD
| cmd_prefix ASSIGNMENT_WORD
cmd_suffix ::= io_redirect
| cmd_suffix io_redirect
| word
| cmd_suffix word
redirect_list ::= io_redirect
| redirect_list io_redirect
io_redirect ::= io_file
| IO_NUMBER io_file
| io_here
| IO_NUMBER io_here
io_file ::= LESS filename
| LESSAND filename
| GREAT filename
| GREATAND filename
| DGREAT filename
| LESSGREAT filename
| CLOBBER filename
filename ::= word
io_here ::= DLESS here_end
| DLESSDASH here_end
here_end ::= word
newline_list ::= NEWLINE
| newline_list NEWLINE
linebreak ::= newline_list
| /* empty */
separator_op ::= Uppersand
| Semicolon
separator ::= separator_op linebreak
| newline_list
sequential_sep ::= Semicolon linebreak
| newline_list
word ::= WORD
| NAME
intended_error ::= INTENDED_ERROR
//Tokens
//| \(\S+\) -> \("[^"]+"\)
EOF ::= "EOF"
AND_IF ::= "AND_IF"
OR_IF ::= "OR_IF"
DSEMI ::= "DSEMI"
//| DLESS wr -> Printf.sprintf "DLESS(%s)" (string_of_hd !wr)
//| DLESSDASH wr -> Printf.sprintf "DLESSDASH(%s)" (string_of_hd !wr)
CLOBBER ::= ">|"
If ::= "If"
Then ::= "Then"
Else ::= "Else"
Fi ::= "Fi"
Elif ::= "Elif"
LESSGREAT ::= "LESSGREAT"
LESSAND ::= "LESSAND"
DGREAT ::= "DGREAT"
GREATAND ::= "GREATAND"
//| WORD w -> Printf.sprintf "WORD(%s)" (unWord w)
//| ASSIGNMENT_WORD w -> Printf.sprintf "ASSIGNMENT_WORD(%s)" (string_of_assignment_word w)
//| NAME w -> Printf.sprintf "NAME(%s)" (unName w)
//| IO_NUMBER io -> Printf.sprintf "IONUMBER(%s)" (string_of_io_number io)
Do ::= "Do"
Done ::= "Done"
Case ::= "Case"
Esac ::= "Esac"
While ::= "While"
Until ::= "Until"
For ::= "For"
Lbrace ::= "Lbrace"
Rbrace ::= "Rbrace"
Bang ::= "Bang"
In ::= "In"
Pipe ::= "Pipe"
Lparen ::= "Lparen"
Rparen ::= "Rparen"
LESS ::= "LESS"
GREAT ::= "GREAT"
Uppersand ::= "Uppersand"
Semicolon ::= "Semicolon"
NEWLINE ::= "Newline"
INTENDED_ERROR ::= "INTENDED_ERROR"
src/REBracketExpressionParser.mly.ebnf:
bracket_expression ::= LBRACKET matching_list RBRACKET EOF
| LBRACKET nonmatching_list RBRACKET EOF
matching_list ::= bracket_list
nonmatching_list ::= HAT bracket_list
bracket_list ::= follow_list
| follow_list MINUS
follow_list ::= expression_term
| follow_list expression_term
expression_term ::= single_expression
| range_expression
single_expression ::= end_range
| character_class
| equivalence_class
range_expression ::= start_range end_range
| start_range MINUS
start_range ::= end_range MINUS
end_range ::= COLL_ELEM_SINGLE
| collating_symbol
collating_symbol ::= Open_dot COLL_ELEM_SINGLE Dot_close
| Open_dot COLL_ELEM_MULTI Dot_close
| Open_dot meta_char Dot_close
equivalence_class ::= Open_equal COLL_ELEM_SINGLE Equal_close
| Open_equal COLL_ELEM_MULTI Equal_close
character_class ::= Open_colon class_name Colon_close
meta_char ::= MINUS
| HAT
| RBRACKET
class_name ::= COLL_ELEM_SINGLE+
//Tokens
//| \("[^"]+"\)\s+{ \(\S+\).+
MINUS ::= "-"
HAT ::= "!"
LBRACKET ::= "["
RBRACKET ::= "]"
Open_equal ::= "[="
Equal_close ::= "=]"
Open_dot ::= "[."
Dot_close ::= ".]"
Open_colon ::= "[:"
Colon_close ::= ":]"