Script to remove Python comments/docstrings
Is there a Python script or tool available which can remove comments and docstrings from Python source?
It should take care of cases like:
"""
aas
"""
def f():
m = {
u'x':
u'y'
} # faake docstring ;)
if 1:
'string' >> m
if 2:
'string' , m
if 3:
'string' > m
So at last I have come up with a simple script, which uses the tokenize module and removes comment tokens. It seems to work pretty well, except that I am not able to remove docstrings in all cases. See if you can improve it to remove docstrings.
import cStringIO
import tokenize
def remove_comments(src):
"""
This reads tokens using tokenize.generate_tokens and recombines them
using tokenize.untokenize, and skipping comment/docstring tokens in between
"""
f = cStringIO.StringIO(src)
class SkipException(Exception): pass
processed_tokens = []
last_token = None
# go thru all the tokens and try to skip comments and docstrings
for tok in tokenize.generate_tokens(f.readline):
t_type, t_string, t_srow_scol, t_erow_ecol, t_line = tok
try:
if t_type == tokenize.COMMENT:
raise SkipException()
elif t_type == tokenize.STRING:
if last_token is None or last_token[0] in [tokenize.INDENT]:
# FIXEME: this may remove valid strings too?
#raise SkipException()
pass
except SkipException:
pass
else:
processed_tokens.append(tok)
last_token = tok
return tokenize.untokenize(processed_tokens)
Also I would like to test it on a very large collection of scripts with good unit test coverage. Can you suggest such a open source project?
I'm the author of the "mygod, he has written a python interpreter using regex..." (i.e. pyminifier) mentioned at that link below =).
I just wanted to chime in and say that I've improved the code quite a bit using the tokenizer module (which I discovered thanks to this question =) ).
You'll be happy to note that the code no longer relies so much on regular expressions and uses tokenizer to great effect. Anyway, here's the remove_comments_and_docstrings() function from pyminifier
(Note: It works properly with the edge cases that previously-posted code breaks on):
import cStringIO, tokenize
def remove_comments_and_docstrings(source):
"""
Returns 'source' minus comments and docstrings.
"""
io_obj = cStringIO.StringIO(source)
out = ""
prev_toktype = tokenize.INDENT
last_lineno = -1
last_col = 0
for tok in tokenize.generate_tokens(io_obj.readline):
token_type = tok[0]
token_string = tok[1]
start_line, start_col = tok[2]
end_line, end_col = tok[3]
ltext = tok[4]
# The following two conditionals preserve indentation.
# This is necessary because we're not using tokenize.untokenize()
# (because it spits out code with copious amounts of oddly-placed
# whitespace).
if start_line > last_lineno:
last_col = 0
if start_col > last_col:
out += (" " * (start_col - last_col))
# Remove comments:
if token_type == tokenize.COMMENT:
pass
# This series of conditionals removes docstrings:
elif token_type == tokenize.STRING:
if prev_toktype != tokenize.INDENT:
# This is likely a docstring; double-check we're not inside an operator:
if prev_toktype != tokenize.NEWLINE:
# Note regarding NEWLINE vs NL: The tokenize module
# differentiates between newlines that start a new statement
# and newlines inside of operators such as parens, brackes,
# and curly braces. Newlines inside of operators are
# NEWLINE and newlines that start new code are NL.
# Catch whole-module docstrings:
if start_col > 0:
# Unlabelled indentation means we're inside an operator
out += token_string
# Note regarding the INDENT token: The tokenize module does
# not label indentation inside of an operator (parens,
# brackets, and curly braces) as actual indentation.
# For example:
# def foo():
# "The spaces before this docstring are tokenize.INDENT"
# test = [
# "The spaces before this string do not get a token"
# ]
else:
out += token_string
prev_toktype = token_type
last_col = end_col
last_lineno = end_line
return out
This does the job:
""" Strip comments and docstrings from a file.
"""
import sys, token, tokenize
def do_file(fname):
""" Run on just one file.
"""
source = open(fname)
mod = open(fname + ",strip", "w")
prev_toktype = token.INDENT
first_line = None
last_lineno = -1
last_col = 0
tokgen = tokenize.generate_tokens(source.readline)
for toktype, ttext, (slineno, scol), (elineno, ecol), ltext in tokgen:
if 0: # Change to if 1 to see the tokens fly by.
print("%10s %-14s %-20r %r" % (
tokenize.tok_name.get(toktype, toktype),
"%d.%d-%d.%d" % (slineno, scol, elineno, ecol),
ttext, ltext
))
if slineno > last_lineno:
last_col = 0
if scol > last_col:
mod.write(" " * (scol - last_col))
if toktype == token.STRING and prev_toktype == token.INDENT:
# Docstring
mod.write("#--")
elif toktype == tokenize.COMMENT:
# Comment
mod.write("##\n")
else:
mod.write(ttext)
prev_toktype = toktype
last_col = ecol
last_lineno = elineno
if __name__ == '__main__':
do_file(sys.argv[1])
I'm leaving stub comments in the place of docstrings and comments since it simplifies the code. If you remove them completely, you also have to get rid of indentation before them.
Here is a modification of Dan's solution to make it run for Python3 + also remove empty lines + make it ready-to-use:
import io, tokenize, re
def remove_comments_and_docstrings(source):
io_obj = io.StringIO(source)
out = ""
prev_toktype = tokenize.INDENT
last_lineno = -1
last_col = 0
for tok in tokenize.generate_tokens(io_obj.readline):
token_type = tok[0]
token_string = tok[1]
start_line, start_col = tok[2]
end_line, end_col = tok[3]
ltext = tok[4]
if start_line > last_lineno:
last_col = 0
if start_col > last_col:
out += (" " * (start_col - last_col))
if token_type == tokenize.COMMENT:
pass
elif token_type == tokenize.STRING:
if prev_toktype != tokenize.INDENT:
if prev_toktype != tokenize.NEWLINE:
if start_col > 0:
out += token_string
else:
out += token_string
prev_toktype = token_type
last_col = end_col
last_lineno = end_line
out = '\n'.join(l for l in out.splitlines() if l.strip())
return out
with open('test.py', 'r') as f:
print(remove_comments_and_docstrings(f.read()))