raphael/minishell
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update: commented the python code so it is more readable

Browse source
This commit is contained in:
maix0 2024-09-26 17:50:57 +02:00
parent 285104a19a
commit c284eb3786
3 changed files with 16 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
parser/token.py/app.py
View file

@ -1,5 +1,5 @@
import str_to_token
import prettier
import concat
import ttoken
s = input("> ")

5
parser/token.py/concat.py
View file

@ -1,20 +1,25 @@
from ttoken import *
# This function will make a "big" token that will represent a word in the shell sense
def concat(tokens: list[Token]):
i = 0
out = []
while i < len(tokens):
tok = tokens[i]
# if the token is a token that can be inside a word, then we start createing a WORD "metaToken"
if tok.is_word():
word = Token(TokenType.WORD, subtokens=[])
word.subtokens.append(tok)
j = 1
# then we get every token after the first that is also a word and we push them
while i + j < len(tokens) and (tokens[i + j]).is_word():
word.subtokens.append(tokens[i + j])
j += 1
i += j
out.append(word)
else:
# otherwise we just push the token alone
out.append(tok)
i += 1
return out

10
parser/token.py/str_to_token.py
View file

@ -7,6 +7,7 @@ def is_quote(c: chr):
return c == "'" or c == '"'
# This function takes the string and seperate them into different tokens depending on the quotes
def str_to_token(s: str):
tokens = []
current_token = None
@ -15,15 +16,20 @@ def str_to_token(s: str):
while i < len(s):
c = s[i]
if quote == 0:
# if we have a quote, juste push the current token if any, then switch the the correct quote token
if is_quote(c):
if current_token != None:
tokens.append(current_token)
quote = c
current_token = Token(TT.DQUOTE if c == '"' else TT.SQUOTE, string="")
else:
# here we have no quote, so we first create a token if none exist, then handle special stuff
# like whitespace for example, or any character we want to spit in a single token of their own (; $ | &)
if current_token == None:
current_token = Token(TT.NQUOTE, string="")
if c.isspace():
# we have a whitespace, then create a whitespace token, and push the current token
# if it isn't empty and not whitesace
if (
len(current_token.string) != 0
and current_token.ty != TT.WHITESPACE
@ -31,6 +37,7 @@ def str_to_token(s: str):
tokens.append(current_token)
current_token = Token(TT.WHITESPACE, string="")
else:
# we DON'T have a whitespace, then if the current token is a whitespace, just push it and set the new token to raw_string
if current_token.ty == TT.WHITESPACE:
tokens.append(current_token)
current_token = Token(TT.NQUOTE, string="")
@ -65,6 +72,7 @@ def str_to_token(s: str):
else:
current_token.append_char(c)
elif quote == "'":
# we are in a single quotem basically we push until we have another single quote
if c == "'":
tokens.append(current_token)
current_token = None
@ -74,6 +82,7 @@ def str_to_token(s: str):
current_token = Token(TT.SQUOTE, string="")
current_token.append_char(c)
elif quote == '"':
# we are in a double quotem basically we push until we have another double quote
if c == '"':
tokens.append(current_token)
current_token = None
@ -85,6 +94,7 @@ def str_to_token(s: str):
else:
print("you fucked up you quote thingy")
i += 1
# if the current token is not none and the current token is "no quote" then we push it
if current_token != None and current_token.ty == TT.NQUOTE:
tokens.append(current_token)
return tokens