fixed grammar, comment cleanup and greetings
This commit is contained in:
parent
acd8a6a8c7
commit
f04cd34656
4 changed files with 45 additions and 27 deletions
16
src/grammar
16
src/grammar
|
|
@ -4,16 +4,20 @@
|
|||
/ / / /_/ / / / / /___/ ____/ ___ |/ _, _/___/ / /___/ _, _/
|
||||
/_/ \____/_/ /_/_____/_/ /_/ |_/_/ |_|/____/_____/_/ |_|
|
||||
|
||||
toml : content
|
||||
toml : newlines content
|
||||
| content
|
||||
|
||||
content : content tomlEntries
|
||||
| tomlEntries
|
||||
|
||||
tomlEntries : table
|
||||
| object
|
||||
tomlEntries : table newlines
|
||||
| object newlines
|
||||
|
||||
table : '[' ID ']'
|
||||
| '[' '[' ID ']' ']'
|
||||
table : TABLE
|
||||
| ARRTABLE
|
||||
|
||||
newlines : newlines NEWLINE
|
||||
| NEWLINE
|
||||
|
||||
object : key '=' value
|
||||
| key '=' array
|
||||
|
|
@ -48,6 +52,7 @@ key : ID
|
|||
| BIN
|
||||
| OCT
|
||||
| INF
|
||||
| BOOL
|
||||
| NAN
|
||||
|
||||
value : STR
|
||||
|
|
@ -59,5 +64,6 @@ value : STR
|
|||
| BIN
|
||||
| OCT
|
||||
| INF
|
||||
| BOOL
|
||||
| NAN
|
||||
|
||||
|
|
|
|||
10
src/lexer.py
10
src/lexer.py
|
|
@ -13,7 +13,7 @@ tokens = [
|
|||
"HEX",
|
||||
"BIN",
|
||||
"OCT",
|
||||
"FLOAT", # need to implement exponents check https://toml.io/en/
|
||||
"FLOAT",
|
||||
"BOOL",
|
||||
"INF",
|
||||
"NAN",
|
||||
|
|
@ -65,25 +65,21 @@ def t_dict_close_dict(t):
|
|||
t.lexer.pop_state()
|
||||
return t
|
||||
|
||||
# needs to check if datetime is valid
|
||||
def t_DATETIME(t):
|
||||
r"\d{4}-\d{2}-\d{2}[T ]\d{2}:\d{2}:\d{2}(\.\d{1,6})?(Z|[+-]\d{2}:\d{2})"
|
||||
return t
|
||||
|
||||
|
||||
# needs to check if date is valid
|
||||
def t_DATE(t):
|
||||
r"\d{4}-\d{2}-\d{2}"
|
||||
return t
|
||||
|
||||
|
||||
# needs to check if time is valid
|
||||
def t_TIME(t):
|
||||
r"\d{2}:\d{2}:\d{2}(\.\d{1,6})?"
|
||||
return t
|
||||
|
||||
|
||||
# needs number grouping (example : flt8 = 224_617.445_991_228)
|
||||
def t_FLOAT(t):
|
||||
r"[+-]?\d+(_\d+)*\s*\.\s*\d+(_\d+)*([eE][-+]?\d+(_\d+)*)?"
|
||||
#case where float appears on the left side with spaces in between
|
||||
|
|
@ -93,13 +89,11 @@ def t_FLOAT(t):
|
|||
return t
|
||||
|
||||
|
||||
# needs number grouping (example : int6 = 5_349_221)
|
||||
def t_INT(t):
|
||||
r"[-+]?(\d+(_\d+)*)"
|
||||
return t
|
||||
|
||||
|
||||
# needs number grouping (example : hex3 = 0xdead_beef)
|
||||
def t_HEX(t):
|
||||
r"0x[0-9a-fA-F]+(_[0-9a-fA-F]+)*"
|
||||
return t
|
||||
|
|
@ -131,7 +125,6 @@ def t_BOOL(t):
|
|||
return t
|
||||
|
||||
|
||||
# ID needs to be the last so it doesnt catch everything (literally)
|
||||
def t_ID(t):
|
||||
r"(([\w_]+)|(\"[\w_]+\"|\'[\w_]+\')\s*\.\s*([\w_]+|\"[\w_]+\"|\'[\w_]+\'))(\s*\.\s*([\w_]+|\"[\w_]+\"|\'[\w_]+\'))*"
|
||||
t.value = [s.strip(" \"'") for s in t.value.split('.')]
|
||||
|
|
@ -144,7 +137,6 @@ def t_MLSTR(t):
|
|||
return t
|
||||
|
||||
|
||||
# STR needs to be the first one to catch
|
||||
def t_STR(t):
|
||||
r"(\"(?:[^\"\\]|\\.)*\")|(\'[^\']*\')"
|
||||
t.value = t.value.strip("\"'")
|
||||
|
|
|
|||
|
|
@ -158,7 +158,6 @@ def p_dict_empty(p):
|
|||
|
||||
def p_dictCont_multiple(p):
|
||||
"""dictCont : dictCont ',' dictElem"""
|
||||
# checar se os dicts nao teem keys repetidas
|
||||
duplicate_list = [k for k in p[1] if k in p[3]]
|
||||
for dup in duplicate_list:
|
||||
print(f"Duplicate inline-table key {dup}")
|
||||
|
|
@ -192,7 +191,7 @@ def p_key_id(p):
|
|||
p[0] = p[1]
|
||||
|
||||
|
||||
# the rest of the cases are the specific cases where the key as the same format as a float/int/etc
|
||||
# the rest of the cases are the specific cases where the key is the same format as a float/int/etc
|
||||
# so we need make them a singleton list.
|
||||
def p_key_rest(p):
|
||||
"""key : STR
|
||||
|
|
|
|||
|
|
@ -4,20 +4,41 @@ from tokenizer import tokenizer
|
|||
import sys
|
||||
import argparse
|
||||
|
||||
def greetings():
|
||||
print(r" ____ __ __________ __ _____ ")
|
||||
print(r" / __ \/ / /_ __/ __ \/ |/ / / ")
|
||||
print(r" / /_/ / / / / / / / / /|_/ / / ")
|
||||
print(r" / ____/ /___/ / / /_/ / / / / /___")
|
||||
print(r" /_/ /_____/_/ \____/_/ /_/_____/")
|
||||
print(r"--------------------------------------")
|
||||
print(r"Authors: Tiago Sousa and Afonso Franco")
|
||||
print(r"--------------------------------------")
|
||||
|
||||
def main():
|
||||
sys.argv
|
||||
argv_parser = argparse.ArgumentParser(prog="PLTOML",description="A command line tool to convert toml files into json using ply.")
|
||||
argv_parser.add_argument("-i","--input",help="The filepath to the target input file")
|
||||
argv_parser.add_argument("-o","--output",help="The filepath to the target output file")
|
||||
argv_parser.add_argument("-t","--tokenizer",help="This feature allows you to inspect all the tokens captured by the lexer (should only be used for debugging)")
|
||||
if sys.stdout.isatty():
|
||||
greetings()
|
||||
argv_parser = argparse.ArgumentParser(
|
||||
prog="PLTOML",
|
||||
description="A command line tool to convert toml files into json using ply.",
|
||||
)
|
||||
argv_parser.add_argument(
|
||||
"-i", "--input", help="The filepath to the target input file"
|
||||
)
|
||||
argv_parser.add_argument(
|
||||
"-o", "--output", help="The filepath to the target output file"
|
||||
)
|
||||
argv_parser.add_argument(
|
||||
"-t",
|
||||
"--tokenizer",
|
||||
help="This feature allows you to inspect all the tokens captured by the lexer (should only be used for debugging)",
|
||||
)
|
||||
|
||||
args = argv_parser.parse_args()
|
||||
if args.tokenizer is not None:
|
||||
tokenizer(args.input,args.output)
|
||||
tokenizer(args.input, args.output)
|
||||
else:
|
||||
parse(args.input,args.output)
|
||||
parse(args.input, args.output)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue