Experimental: mitogen: Remove minification of Python source code
Done on the basis that sending a few more bytes of the network is quicker than tokenizing and untokeninzing the modules.pull/942/head
Alex Willmer
2 years ago
parent
ec212a10d8
commit
2c7f2b4a99
@ -1,453 +0,0 @@
|
||||
"""Tokenization help for Python programs.
|
||||
|
||||
generate_tokens(readline) is a generator that breaks a stream of
|
||||
text into Python tokens. It accepts a readline-like method which is called
|
||||
repeatedly to get the next line of input (or "" for EOF). It generates
|
||||
5-tuples with these members:
|
||||
|
||||
the token type (see token.py)
|
||||
the token (a string)
|
||||
the starting (row, column) indices of the token (a 2-tuple of ints)
|
||||
the ending (row, column) indices of the token (a 2-tuple of ints)
|
||||
the original line (string)
|
||||
|
||||
It is designed to match the working of the Python tokenizer exactly, except
|
||||
that it produces COMMENT tokens for comments and gives type OP for all
|
||||
operators
|
||||
|
||||
Older entry points
|
||||
tokenize_loop(readline, tokeneater)
|
||||
tokenize(readline, tokeneater=printtoken)
|
||||
are the same, except instead of generating tokens, tokeneater is a callback
|
||||
function to which the 5 fields described above are passed as 5 arguments,
|
||||
each time a new token is found."""
|
||||
|
||||
# !mitogen: minify_safe
|
||||
|
||||
__author__ = 'Ka-Ping Yee <ping@lfw.org>'
|
||||
__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
|
||||
'Skip Montanaro, Raymond Hettinger')
|
||||
|
||||
from itertools import chain
|
||||
import string, re
|
||||
from token import *
|
||||
|
||||
import token
|
||||
__all__ = [x for x in dir(token) if not x.startswith("_")]
|
||||
__all__ += ["COMMENT", "tokenize", "generate_tokens", "NL", "untokenize"]
|
||||
del token
|
||||
|
||||
COMMENT = N_TOKENS
|
||||
tok_name[COMMENT] = 'COMMENT'
|
||||
NL = N_TOKENS + 1
|
||||
tok_name[NL] = 'NL'
|
||||
N_TOKENS += 2
|
||||
|
||||
def group(*choices): return '(' + '|'.join(choices) + ')'
|
||||
def any(*choices): return group(*choices) + '*'
|
||||
def maybe(*choices): return group(*choices) + '?'
|
||||
|
||||
Whitespace = r'[ \f\t]*'
|
||||
Comment = r'#[^\r\n]*'
|
||||
Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
|
||||
Name = r'[a-zA-Z_]\w*'
|
||||
|
||||
Hexnumber = r'0[xX][\da-fA-F]+[lL]?'
|
||||
Octnumber = r'(0[oO][0-7]+)|(0[0-7]*)[lL]?'
|
||||
Binnumber = r'0[bB][01]+[lL]?'
|
||||
Decnumber = r'[1-9]\d*[lL]?'
|
||||
Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
|
||||
Exponent = r'[eE][-+]?\d+'
|
||||
Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent)
|
||||
Expfloat = r'\d+' + Exponent
|
||||
Floatnumber = group(Pointfloat, Expfloat)
|
||||
Imagnumber = group(r'\d+[jJ]', Floatnumber + r'[jJ]')
|
||||
Number = group(Imagnumber, Floatnumber, Intnumber)
|
||||
|
||||
# Tail end of ' string.
|
||||
Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
|
||||
# Tail end of " string.
|
||||
Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
|
||||
# Tail end of ''' string.
|
||||
Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
|
||||
# Tail end of """ string.
|
||||
Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
|
||||
Triple = group("[uUbB]?[rR]?'''", '[uUbB]?[rR]?"""')
|
||||
# Single-line ' or " string.
|
||||
String = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
|
||||
r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"')
|
||||
|
||||
# Because of leftmost-then-longest match semantics, be sure to put the
|
||||
# longest operators first (e.g., if = came before ==, == would get
|
||||
# recognized as two instances of =).
|
||||
Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"<>", r"!=",
|
||||
r"//=?",
|
||||
r"[+\-*/%&|^=<>]=?",
|
||||
r"~")
|
||||
|
||||
Bracket = '[][(){}]'
|
||||
Special = group(r'\r?\n', r'[:;.,`@]')
|
||||
Funny = group(Operator, Bracket, Special)
|
||||
|
||||
PlainToken = group(Number, Funny, String, Name)
|
||||
Token = Ignore + PlainToken
|
||||
|
||||
# First (or only) line of ' or " string.
|
||||
ContStr = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
|
||||
group("'", r'\\\r?\n'),
|
||||
r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
|
||||
group('"', r'\\\r?\n'))
|
||||
PseudoExtras = group(r'\\\r?\n|\Z', Comment, Triple)
|
||||
PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
|
||||
|
||||
tokenprog, pseudoprog, single3prog, double3prog = map(
|
||||
re.compile, (Token, PseudoToken, Single3, Double3))
|
||||
endprogs = {"'": re.compile(Single), '"': re.compile(Double),
|
||||
"'''": single3prog, '"""': double3prog,
|
||||
"r'''": single3prog, 'r"""': double3prog,
|
||||
"u'''": single3prog, 'u"""': double3prog,
|
||||
"ur'''": single3prog, 'ur"""': double3prog,
|
||||
"R'''": single3prog, 'R"""': double3prog,
|
||||
"U'''": single3prog, 'U"""': double3prog,
|
||||
"uR'''": single3prog, 'uR"""': double3prog,
|
||||
"Ur'''": single3prog, 'Ur"""': double3prog,
|
||||
"UR'''": single3prog, 'UR"""': double3prog,
|
||||
"b'''": single3prog, 'b"""': double3prog,
|
||||
"br'''": single3prog, 'br"""': double3prog,
|
||||
"B'''": single3prog, 'B"""': double3prog,
|
||||
"bR'''": single3prog, 'bR"""': double3prog,
|
||||
"Br'''": single3prog, 'Br"""': double3prog,
|
||||
"BR'''": single3prog, 'BR"""': double3prog,
|
||||
'r': None, 'R': None, 'u': None, 'U': None,
|
||||
'b': None, 'B': None}
|
||||
|
||||
triple_quoted = {}
|
||||
for t in ("'''", '"""',
|
||||
"r'''", 'r"""', "R'''", 'R"""',
|
||||
"u'''", 'u"""', "U'''", 'U"""',
|
||||
"ur'''", 'ur"""', "Ur'''", 'Ur"""',
|
||||
"uR'''", 'uR"""', "UR'''", 'UR"""',
|
||||
"b'''", 'b"""', "B'''", 'B"""',
|
||||
"br'''", 'br"""', "Br'''", 'Br"""',
|
||||
"bR'''", 'bR"""', "BR'''", 'BR"""'):
|
||||
triple_quoted[t] = t
|
||||
single_quoted = {}
|
||||
for t in ("'", '"',
|
||||
"r'", 'r"', "R'", 'R"',
|
||||
"u'", 'u"', "U'", 'U"',
|
||||
"ur'", 'ur"', "Ur'", 'Ur"',
|
||||
"uR'", 'uR"', "UR'", 'UR"',
|
||||
"b'", 'b"', "B'", 'B"',
|
||||
"br'", 'br"', "Br'", 'Br"',
|
||||
"bR'", 'bR"', "BR'", 'BR"' ):
|
||||
single_quoted[t] = t
|
||||
|
||||
tabsize = 8
|
||||
|
||||
class TokenError(Exception): pass
|
||||
|
||||
class StopTokenizing(Exception): pass
|
||||
|
||||
def printtoken(type, token, srow_scol, erow_ecol, line): # for testing
|
||||
srow, scol = srow_scol
|
||||
erow, ecol = erow_ecol
|
||||
print("%d,%d-%d,%d:\t%s\t%s" % \
|
||||
(srow, scol, erow, ecol, tok_name[type], repr(token)))
|
||||
|
||||
def tokenize(readline, tokeneater=printtoken):
|
||||
"""
|
||||
The tokenize() function accepts two parameters: one representing the
|
||||
input stream, and one providing an output mechanism for tokenize().
|
||||
|
||||
The first parameter, readline, must be a callable object which provides
|
||||
the same interface as the readline() method of built-in file objects.
|
||||
Each call to the function should return one line of input as a string.
|
||||
|
||||
The second parameter, tokeneater, must also be a callable object. It is
|
||||
called once for each token, with five arguments, corresponding to the
|
||||
tuples generated by generate_tokens().
|
||||
"""
|
||||
try:
|
||||
tokenize_loop(readline, tokeneater)
|
||||
except StopTokenizing:
|
||||
pass
|
||||
|
||||
# backwards compatible interface
|
||||
def tokenize_loop(readline, tokeneater):
|
||||
for token_info in generate_tokens(readline):
|
||||
tokeneater(*token_info)
|
||||
|
||||
class Untokenizer:
|
||||
|
||||
def __init__(self):
|
||||
self.tokens = []
|
||||
self.prev_row = 1
|
||||
self.prev_col = 0
|
||||
|
||||
def add_whitespace(self, start):
|
||||
row, col = start
|
||||
if row < self.prev_row or row == self.prev_row and col < self.prev_col:
|
||||
raise ValueError("start ({},{}) precedes previous end ({},{})"
|
||||
.format(row, col, self.prev_row, self.prev_col))
|
||||
row_offset = row - self.prev_row
|
||||
if row_offset:
|
||||
self.tokens.append("\\\n" * row_offset)
|
||||
self.prev_col = 0
|
||||
col_offset = col - self.prev_col
|
||||
if col_offset:
|
||||
self.tokens.append(" " * col_offset)
|
||||
|
||||
def untokenize(self, iterable):
|
||||
it = iter(iterable)
|
||||
indents = []
|
||||
startline = False
|
||||
for t in it:
|
||||
if len(t) == 2:
|
||||
self.compat(t, it)
|
||||
break
|
||||
tok_type, token, start, end, line = t
|
||||
if tok_type == ENDMARKER:
|
||||
break
|
||||
if tok_type == INDENT:
|
||||
indents.append(token)
|
||||
continue
|
||||
elif tok_type == DEDENT:
|
||||
indents.pop()
|
||||
self.prev_row, self.prev_col = end
|
||||
continue
|
||||
elif tok_type in (NEWLINE, NL):
|
||||
startline = True
|
||||
elif startline and indents:
|
||||
indent = indents[-1]
|
||||
if start[1] >= len(indent):
|
||||
self.tokens.append(indent)
|
||||
self.prev_col = len(indent)
|
||||
startline = False
|
||||
self.add_whitespace(start)
|
||||
self.tokens.append(token)
|
||||
self.prev_row, self.prev_col = end
|
||||
if tok_type in (NEWLINE, NL):
|
||||
self.prev_row += 1
|
||||
self.prev_col = 0
|
||||
return "".join(self.tokens)
|
||||
|
||||
def compat(self, token, iterable):
|
||||
indents = []
|
||||
toks_append = self.tokens.append
|
||||
startline = token[0] in (NEWLINE, NL)
|
||||
prevstring = False
|
||||
|
||||
for tok in chain([token], iterable):
|
||||
toknum, tokval = tok[:2]
|
||||
|
||||
if toknum in (NAME, NUMBER):
|
||||
tokval += ' '
|
||||
|
||||
# Insert a space between two consecutive strings
|
||||
if toknum == STRING:
|
||||
if prevstring:
|
||||
tokval = ' ' + tokval
|
||||
prevstring = True
|
||||
else:
|
||||
prevstring = False
|
||||
|
||||
if toknum == INDENT:
|
||||
indents.append(tokval)
|
||||
continue
|
||||
elif toknum == DEDENT:
|
||||
indents.pop()
|
||||
continue
|
||||
elif toknum in (NEWLINE, NL):
|
||||
startline = True
|
||||
elif startline and indents:
|
||||
toks_append(indents[-1])
|
||||
startline = False
|
||||
toks_append(tokval)
|
||||
|
||||
def untokenize(iterable):
|
||||
"""Transform tokens back into Python source code.
|
||||
|
||||
Each element returned by the iterable must be a token sequence
|
||||
with at least two elements, a token number and token value. If
|
||||
only two tokens are passed, the resulting output is poor.
|
||||
|
||||
Round-trip invariant for full input:
|
||||
Untokenized source will match input source exactly
|
||||
|
||||
Round-trip invariant for limited intput:
|
||||
# Output text will tokenize the back to the input
|
||||
t1 = [tok[:2] for tok in generate_tokens(f.readline)]
|
||||
newcode = untokenize(t1)
|
||||
readline = iter(newcode.splitlines(1)).next
|
||||
t2 = [tok[:2] for tok in generate_tokens(readline)]
|
||||
assert t1 == t2
|
||||
"""
|
||||
ut = Untokenizer()
|
||||
return ut.untokenize(iterable)
|
||||
|
||||
def generate_tokens(readline):
|
||||
"""
|
||||
The generate_tokens() generator requires one argument, readline, which
|
||||
must be a callable object which provides the same interface as the
|
||||
readline() method of built-in file objects. Each call to the function
|
||||
should return one line of input as a string. Alternately, readline
|
||||
can be a callable function terminating with StopIteration:
|
||||
readline = open(myfile).next # Example of alternate readline
|
||||
|
||||
The generator produces 5-tuples with these members: the token type; the
|
||||
token string; a 2-tuple (srow, scol) of ints specifying the row and
|
||||
column where the token begins in the source; a 2-tuple (erow, ecol) of
|
||||
ints specifying the row and column where the token ends in the source;
|
||||
and the line on which the token was found. The line passed is the
|
||||
logical line; continuation lines are included.
|
||||
"""
|
||||
lnum = parenlev = continued = 0
|
||||
namechars, numchars = string.ascii_letters + '_', '0123456789'
|
||||
contstr, needcont = '', 0
|
||||
contline = None
|
||||
indents = [0]
|
||||
|
||||
while 1: # loop over lines in stream
|
||||
try:
|
||||
line = readline()
|
||||
except StopIteration:
|
||||
line = ''
|
||||
lnum += 1
|
||||
pos, max = 0, len(line)
|
||||
|
||||
if contstr: # continued string
|
||||
if not line:
|
||||
raise TokenError("EOF in multi-line string", strstart)
|
||||
endmatch = endprog.match(line)
|
||||
if endmatch:
|
||||
pos = end = endmatch.end(0)
|
||||
yield (STRING, contstr + line[:end],
|
||||
strstart, (lnum, end), contline + line)
|
||||
contstr, needcont = '', 0
|
||||
contline = None
|
||||
elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
|
||||
yield (ERRORTOKEN, contstr + line,
|
||||
strstart, (lnum, len(line)), contline)
|
||||
contstr = ''
|
||||
contline = None
|
||||
continue
|
||||
else:
|
||||
contstr = contstr + line
|
||||
contline = contline + line
|
||||
continue
|
||||
|
||||
elif parenlev == 0 and not continued: # new statement
|
||||
if not line: break
|
||||
column = 0
|
||||
while pos < max: # measure leading whitespace
|
||||
if line[pos] == ' ':
|
||||
column += 1
|
||||
elif line[pos] == '\t':
|
||||
column = (column//tabsize + 1)*tabsize
|
||||
elif line[pos] == '\f':
|
||||
column = 0
|
||||
else:
|
||||
break
|
||||
pos += 1
|
||||
if pos == max:
|
||||
break
|
||||
|
||||
if line[pos] in '#\r\n': # skip comments or blank lines
|
||||
if line[pos] == '#':
|
||||
comment_token = line[pos:].rstrip('\r\n')
|
||||
nl_pos = pos + len(comment_token)
|
||||
yield (COMMENT, comment_token,
|
||||
(lnum, pos), (lnum, pos + len(comment_token)), line)
|
||||
yield (NL, line[nl_pos:],
|
||||
(lnum, nl_pos), (lnum, len(line)), line)
|
||||
else:
|
||||
yield ((NL, COMMENT)[line[pos] == '#'], line[pos:],
|
||||
(lnum, pos), (lnum, len(line)), line)
|
||||
continue
|
||||
|
||||
if column > indents[-1]: # count indents or dedents
|
||||
indents.append(column)
|
||||
yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
|
||||
while column < indents[-1]:
|
||||
if column not in indents:
|
||||
raise IndentationError(
|
||||
"unindent does not match any outer indentation level",
|
||||
("<tokenize>", lnum, pos, line))
|
||||
indents = indents[:-1]
|
||||
yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
|
||||
|
||||
else: # continued statement
|
||||
if not line:
|
||||
raise TokenError("EOF in multi-line statement", (lnum, 0))
|
||||
continued = 0
|
||||
|
||||
while pos < max:
|
||||
pseudomatch = pseudoprog.match(line, pos)
|
||||
if pseudomatch: # scan for tokens
|
||||
start, end = pseudomatch.span(1)
|
||||
spos, epos, pos = (lnum, start), (lnum, end), end
|
||||
if start == end:
|
||||
continue
|
||||
token, initial = line[start:end], line[start]
|
||||
|
||||
if initial in numchars or \
|
||||
(initial == '.' and token != '.'): # ordinary number
|
||||
yield (NUMBER, token, spos, epos, line)
|
||||
elif initial in '\r\n':
|
||||
if parenlev > 0:
|
||||
n = NL
|
||||
else:
|
||||
n = NEWLINE
|
||||
yield (n, token, spos, epos, line)
|
||||
elif initial == '#':
|
||||
assert not token.endswith("\n")
|
||||
yield (COMMENT, token, spos, epos, line)
|
||||
elif token in triple_quoted:
|
||||
endprog = endprogs[token]
|
||||
endmatch = endprog.match(line, pos)
|
||||
if endmatch: # all on one line
|
||||
pos = endmatch.end(0)
|
||||
token = line[start:pos]
|
||||
yield (STRING, token, spos, (lnum, pos), line)
|
||||
else:
|
||||
strstart = (lnum, start) # multiple lines
|
||||
contstr = line[start:]
|
||||
contline = line
|
||||
break
|
||||
elif initial in single_quoted or \
|
||||
token[:2] in single_quoted or \
|
||||
token[:3] in single_quoted:
|
||||
if token[-1] == '\n': # continued string
|
||||
strstart = (lnum, start)
|
||||
endprog = (endprogs[initial] or endprogs[token[1]] or
|
||||
endprogs[token[2]])
|
||||
contstr, needcont = line[start:], 1
|
||||
contline = line
|
||||
break
|
||||
else: # ordinary string
|
||||
yield (STRING, token, spos, epos, line)
|
||||
elif initial in namechars: # ordinary name
|
||||
yield (NAME, token, spos, epos, line)
|
||||
elif initial == '\\': # continued stmt
|
||||
continued = 1
|
||||
else:
|
||||
if initial in '([{':
|
||||
parenlev += 1
|
||||
elif initial in ')]}':
|
||||
parenlev -= 1
|
||||
yield (OP, token, spos, epos, line)
|
||||
else:
|
||||
yield (ERRORTOKEN, line[pos],
|
||||
(lnum, pos), (lnum, pos+1), line)
|
||||
pos += 1
|
||||
|
||||
for indent in indents[1:]: # pop remaining indent levels
|
||||
yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
|
||||
yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
|
||||
|
||||
if __name__ == '__main__': # testing
|
||||
import sys
|
||||
if len(sys.argv) > 1:
|
||||
tokenize(open(sys.argv[1]).readline)
|
||||
else:
|
||||
tokenize(sys.stdin.readline)
|
||||
@ -1,143 +0,0 @@
|
||||
# Copyright 2017, Alex Willmer
|
||||
#
|
||||
# Redistribution and use in source and binary forms, with or without
|
||||
# modification, are permitted provided that the following conditions are met:
|
||||
#
|
||||
# 1. Redistributions of source code must retain the above copyright notice,
|
||||
# this list of conditions and the following disclaimer.
|
||||
#
|
||||
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
||||
# this list of conditions and the following disclaimer in the documentation
|
||||
# and/or other materials provided with the distribution.
|
||||
#
|
||||
# 3. Neither the name of the copyright holder nor the names of its contributors
|
||||
# may be used to endorse or promote products derived from this software without
|
||||
# specific prior written permission.
|
||||
#
|
||||
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
|
||||
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
||||
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
||||
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
||||
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
||||
# POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
# !mitogen: minify_safe
|
||||
|
||||
import sys
|
||||
|
||||
try:
|
||||
from io import StringIO
|
||||
except ImportError:
|
||||
from StringIO import StringIO
|
||||
|
||||
import mitogen.core
|
||||
|
||||
if sys.version_info < (2, 7, 11):
|
||||
from mitogen.compat import tokenize
|
||||
else:
|
||||
import tokenize
|
||||
|
||||
|
||||
def minimize_source(source):
|
||||
"""
|
||||
Remove comments and docstrings from Python `source`, preserving line
|
||||
numbers and syntax of empty blocks.
|
||||
|
||||
:param str source:
|
||||
The source to minimize.
|
||||
|
||||
:returns str:
|
||||
The minimized source.
|
||||
"""
|
||||
source = mitogen.core.to_text(source)
|
||||
tokens = tokenize.generate_tokens(StringIO(source).readline)
|
||||
tokens = strip_comments(tokens)
|
||||
tokens = strip_docstrings(tokens)
|
||||
tokens = reindent(tokens)
|
||||
return tokenize.untokenize(tokens)
|
||||
|
||||
|
||||
def strip_comments(tokens):
|
||||
"""
|
||||
Drop comment tokens from a `tokenize` stream.
|
||||
|
||||
Comments on lines 1-2 are kept, to preserve hashbang and encoding.
|
||||
Trailing whitespace is remove from all lines.
|
||||
"""
|
||||
prev_typ = None
|
||||
prev_end_col = 0
|
||||
for typ, tok, (start_row, start_col), (end_row, end_col), line in tokens:
|
||||
if typ in (tokenize.NL, tokenize.NEWLINE):
|
||||
if prev_typ in (tokenize.NL, tokenize.NEWLINE):
|
||||
start_col = 0
|
||||
else:
|
||||
start_col = prev_end_col
|
||||
end_col = start_col + 1
|
||||
elif typ == tokenize.COMMENT and start_row > 2:
|
||||
continue
|
||||
prev_typ = typ
|
||||
prev_end_col = end_col
|
||||
yield typ, tok, (start_row, start_col), (end_row, end_col), line
|
||||
|
||||
|
||||
def strip_docstrings(tokens):
|
||||
"""
|
||||
Replace docstring tokens with NL tokens in a `tokenize` stream.
|
||||
|
||||
Any STRING token not part of an expression is deemed a docstring.
|
||||
Indented docstrings are not yet recognised.
|
||||
"""
|
||||
stack = []
|
||||
state = 'wait_string'
|
||||
for t in tokens:
|
||||
typ = t[0]
|
||||
if state == 'wait_string':
|
||||
if typ in (tokenize.NL, tokenize.COMMENT):
|
||||
yield t
|
||||
elif typ in (tokenize.DEDENT, tokenize.INDENT, tokenize.STRING):
|
||||
stack.append(t)
|
||||
elif typ == tokenize.NEWLINE:
|
||||
stack.append(t)
|
||||
start_line, end_line = stack[0][2][0], stack[-1][3][0]+1
|
||||
for i in range(start_line, end_line):
|
||||
yield tokenize.NL, '\n', (i, 0), (i,1), '\n'
|
||||
for t in stack:
|
||||
if t[0] in (tokenize.DEDENT, tokenize.INDENT):
|
||||
yield t[0], t[1], (i+1, t[2][1]), (i+1, t[3][1]), t[4]
|
||||
del stack[:]
|
||||
else:
|
||||
stack.append(t)
|
||||
for t in stack: yield t
|
||||
del stack[:]
|
||||
state = 'wait_newline'
|
||||
elif state == 'wait_newline':
|
||||
if typ == tokenize.NEWLINE:
|
||||
state = 'wait_string'
|
||||
yield t
|
||||
|
||||
|
||||
def reindent(tokens, indent=' '):
|
||||
"""
|
||||
Replace existing indentation in a token steam, with `indent`.
|
||||
"""
|
||||
old_levels = []
|
||||
old_level = 0
|
||||
new_level = 0
|
||||
for typ, tok, (start_row, start_col), (end_row, end_col), line in tokens:
|
||||
if typ == tokenize.INDENT:
|
||||
old_levels.append(old_level)
|
||||
old_level = len(tok)
|
||||
new_level += 1
|
||||
tok = indent * new_level
|
||||
elif typ == tokenize.DEDENT:
|
||||
old_level = old_levels.pop()
|
||||
new_level -= 1
|
||||
start_col = max(0, start_col - old_level + new_level)
|
||||
if start_row == end_row:
|
||||
end_col = start_col + len(tok)
|
||||
yield typ, tok, (start_row, start_col), (end_row, end_col), line
|
||||
@ -1,112 +0,0 @@
|
||||
import codecs
|
||||
import glob
|
||||
import pprint
|
||||
import sys
|
||||
|
||||
import mitogen.minify
|
||||
import testlib
|
||||
|
||||
|
||||
def read_sample(fname):
|
||||
sample_path = testlib.data_path('minimize_samples/' + fname)
|
||||
sample_file = open(sample_path)
|
||||
sample = sample_file.read()
|
||||
sample_file.close()
|
||||
return sample
|
||||
|
||||
|
||||
class MinimizeSourceTest(testlib.TestCase):
|
||||
func = staticmethod(mitogen.minify.minimize_source)
|
||||
|
||||
def test_class(self):
|
||||
original = read_sample('class.py')
|
||||
expected = read_sample('class_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_comment(self):
|
||||
original = read_sample('comment.py')
|
||||
expected = read_sample('comment_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_def(self):
|
||||
original = read_sample('def.py')
|
||||
expected = read_sample('def_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_hashbang(self):
|
||||
original = read_sample('hashbang.py')
|
||||
expected = read_sample('hashbang_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_mod(self):
|
||||
original = read_sample('mod.py')
|
||||
expected = read_sample('mod_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_pass(self):
|
||||
original = read_sample('pass.py')
|
||||
expected = read_sample('pass_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
def test_obstacle_course(self):
|
||||
original = read_sample('obstacle_course.py')
|
||||
expected = read_sample('obstacle_course_min.py')
|
||||
self.assertEqual(expected, self.func(original))
|
||||
|
||||
|
||||
class MitogenCoreTest(testlib.TestCase):
|
||||
# Verify minimize_source() succeeds for all built-in modules.
|
||||
func = staticmethod(mitogen.minify.minimize_source)
|
||||
|
||||
def read_source(self, name):
|
||||
fp = codecs.open(name, encoding='utf-8')
|
||||
try:
|
||||
return fp.read()
|
||||
finally:
|
||||
fp.close()
|
||||
|
||||
def _test_syntax_valid(self, minified, name):
|
||||
compile(minified, name, 'exec')
|
||||
|
||||
def _test_line_counts_match(self, original, minified):
|
||||
self.assertEqual(original.count('\n'),
|
||||
minified.count('\n'))
|
||||
|
||||
def _test_non_blank_lines_match(self, name, original, minified):
|
||||
# Verify first token matches. We just want to ensure line numbers make
|
||||
# sense, this is good enough.
|
||||
olines = original.splitlines()
|
||||
mlines = minified.splitlines()
|
||||
for i, (orig, mini) in enumerate(zip(olines, mlines)):
|
||||
if i < 2:
|
||||
assert orig == mini
|
||||
continue
|
||||
|
||||
owords = orig.split()
|
||||
mwords = mini.split()
|
||||
assert len(mwords) == 0 or (mwords[0] == owords[0]), pprint.pformat({
|
||||
'line': i+1,
|
||||
'filename': name,
|
||||
'owords': owords,
|
||||
'mwords': mwords,
|
||||
})
|
||||
|
||||
PY_24_25_SKIP = [
|
||||
# cProfile unsupported on 2.4, 2.6+ syntax is fine here.
|
||||
'mitogen/profiler.py',
|
||||
]
|
||||
|
||||
def test_minify_all(self):
|
||||
for name in glob.glob('mitogen/*.py'):
|
||||
if name in self.PY_24_25_SKIP and sys.version_info < (2, 6):
|
||||
continue
|
||||
original = self.read_source(name)
|
||||
try:
|
||||
minified = self.func(original)
|
||||
except Exception:
|
||||
print('file was: ' + name)
|
||||
raise
|
||||
|
||||
self._test_syntax_valid(minified, name)
|
||||
self._test_line_counts_match(original, minified)
|
||||
self._test_non_blank_lines_match(name, original, minified)
|
||||
Loading…
Reference in New Issue