Created
September 26, 2016 20:26
-
-
Save harjitmoe/127d3349ade6d09ce5357ac710c2b78a to your computer and use it in GitHub Desktop.
Proof-of-concept Python preprocessing for Unicode variable names.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- mode: python; coding: utf-8 -*- | |
"""Unicode Names preprocessor for Python 2.""" | |
# Modified from tokenize module as support for parsing Unicode names | |
# had to be added. | |
old_doc = """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.""" | |
__author__ = 'Thomas Hori modifying 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 x | |
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) | |
NameInitialPat = r"(?=\D)\w" | |
xn__name_initial__n19xy13i = re.compile(NameInitialPat, re.U) | |
Name = NameInitialPat + r'\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), (re.U, re.U, re.U, re.U)) | |
endprogs = {"'": re.compile(Single, re.U), '"': re.compile(Double, re.U), | |
"'''": 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) | |
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 | |
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, coding=None): | |
""" | |
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 | |
numchars = '0123456789' | |
contstr, needcont = '', 0 | |
contline = None | |
indents = [0] | |
while 1: # loop over lines in stream | |
try: | |
if not coding: | |
try: | |
line = readline().decode("ascii") | |
except UnicodeError: | |
raise SyntaxError("SyntaxError: Non-ASCII character in file, but no encoding declared; see http://www.python.org/peps/pep-0263.html for details") | |
else: | |
line = readline().decode(coding) | |
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': | |
yield (NL if parenlev > 0 else NEWLINE, | |
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 xn__name_initial__n19xy13i.match(initial): # 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), '') | |
def xn__has_unicode__610wg75h(s): | |
try: | |
s.encode("ascii") | |
except UnicodeError: | |
return True | |
return False | |
# Note that class-private name mangling doesn't work on names containing unicode 文字. | |
# Probably better off (too complicated, arcane and unpythonic) | |
modeline = re.compile("coding[=:]\s*([-\w.]+)") | |
import sys | |
if len(sys.argv) > 1: | |
gena = open(sys.argv[1]).readlines() | |
else: | |
gena = sys.stdin.readlines() | |
gena = list(gena) | |
look_for_modeline = gena[0]+gena[1] | |
model = modeline.search(look_for_modeline) | |
if model: | |
coding = model.group(1) | |
else: | |
coding = None | |
gen = generate_tokens(iter(gena).next, coding) | |
out = [] | |
for a,b,c,d,e in gen: | |
if (a == NAME) and xn__has_unicode__610wg75h(b): | |
out.append((a,"xn__"+b.replace("_","-").encode("punycode").replace("-","_").decode("ascii").encode(coding or "ascii"),c,d,e)) | |
else: | |
out.append((a,b.encode(coding or "ascii"),c,d,e)) | |
print untokenize(out) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment