Started tokenizing, still struggling with strings

master
Ruben Dahl 2023-04-09 20:13:03 +02:00
parent 5d1935023a
commit aa8d03d296
No known key found for this signature in database
GPG Key ID: D9B193810A18673E
1 changed files with 97 additions and 25 deletions

122
pyne.py
View File

@ -4,45 +4,107 @@ from decorators import deprecated, todo, wip
from enum import Enum
from pyne_errors import ParserError, FileError
import datatypes
import os
import re
import sys
def debugprint(output):
if "PYNE_DEBUG" in os.environ:
print(output)
@dataclass
class PyneObject:
value: datatypes.Variable
VAR_STORE: list[PyneObject] = []
class Pyne:
def __init__(self, path: str, args: list[str]):
self.args = args
self.path = path if self._validate(path) else None
@todo(
"Tokenize the parser so it doesn't try to match the whole line, gotta find a way for it to do the strings though"
)
@wip
def parse(self) -> list[PyneObject]:
objects: list[PyneObject] = []
# VAR_STORE: list[PyneObject] = []
col = 1
is_str_begin = False
with open(self.path) as f:
for row, line in enumerate(f.readlines(), 1):
for var in datatypes.VAR_MATCH:
regex = re.compile(var)
res = regex.match(line[:-1])
if res:
objects.append(
varname = ""
strbuf = ""
debugprint(line)
if "=" in line:
debugprint("if '=' in line")
varname = line.split("=")[0].split(" ")[0]
debugprint(f"{varname = }")
col += len(varname) + line.find("=")
splitline = (
line[line.find("=") + 1 if varname != "" else 0 :]
.strip()
.split(" ")
)
debugprint(f"{splitline = }")
for token in splitline:
debugprint(f"{token = }")
if is_str_begin:
debugprint("is_str_begin = true")
strbuf += token
if datatypes.STR_MATCH_BEGIN.match(token):
debugprint("Matched opening quote")
is_str_begin = True
strbuf += token
if datatypes.STR_MATCH_END.match(token):
debugprint("Matched end quote")
is_str_begin = False
VAR_STORE.append(
PyneObject(
datatypes.Variable(
None, datatypes.VAR_MATCH[var], line[:-1]
)
datatypes.Variable(varname, datatypes.STRING, strbuf)
)
)
break
continue
else:
raise ParserError(f"[{self.path}:{row}] Token {line} not found.")
if len(objects) == 0:
objects.append(datatypes.NONE_TYPE)
return objects
for var in datatypes.VAR_MATCH:
if token == varname:
break
if token == "":
break
if is_str_begin:
break
res = var.match(token)
if res:
VAR_STORE.append(
PyneObject(
datatypes.Variable(
varname, datatypes.VAR_MATCH[var], token
)
)
)
break
else:
raise ParserError(
f"{self.path}:{row}:{col}: Invalid token `{token}`"
)
col += len(token)
debugprint(f"{VAR_STORE=}")
# for var in datatypes.VAR_MATCH:
# res = var.match(line[:-1])
# if res:
# VAR_STORE.append(
# PyneObject(
# datatypes.Variable(
# None, datatypes.VAR_MATCH[var], line[:-1]
# )
# )
# )
# break
# continue
# else:
# raise ParserError(
# f"[{self.path}:{row}] Token `{line[:-1]}` not found."
# )
return VAR_STORE
def _validate(self, path: str) -> bool:
"""
@ -59,13 +121,23 @@ def main() -> int:
parser.add_argument("file", nargs=1, help="The input file")
args = parser.parse_args()
print(args)
# obj = PyneObject(
# datatypes.Variable(
# "test",
# datatypes.Datatype.STRING,
# datatypes.Data(datatypes.Datatype.STRING, '"Hello World"'),
# )
# )
# # dt = datatypes.Data(datatypes.Datatype.INTEGER, 24)
# # obj.value.value = dt
# dt = datatypes.Data(datatypes.Datatype.STRING, '"Goodbye World"')
# obj.value.value = dt
# print(obj.value.value.type, obj.value.value.value)
# return 0
pyne = Pyne(args.file[0], None)
try:
for obj in pyne.parse():
print(obj)
return 0
except ParserError as e:
print(f"Found invalid token: {e}")
for obj in pyne.parse():
print(obj)
return 0
if __name__ == "__main__":