1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
|
from __future__ import generators
import sys
import inspect, tokenize
import py
cpy_compile = compile
# DON'T IMPORT PY HERE
class Source(object):
""" a mutable object holding a source code fragment,
possibly deindenting it.
"""
def __init__(self, *parts, **kwargs):
self.lines = lines = []
de = kwargs.get('deindent', True)
rstrip = kwargs.get('rstrip', True)
for part in parts:
if not part:
partlines = []
if isinstance(part, Source):
partlines = part.lines
elif isinstance(part, (unicode, str)):
partlines = part.split('\n')
if rstrip:
while partlines:
if partlines[-1].strip():
break
partlines.pop()
else:
partlines = getsource(part, deindent=de).lines
if de:
partlines = deindent(partlines)
lines.extend(partlines)
def __eq__(self, other):
try:
return self.lines == other.lines
except AttributeError:
if isinstance(other, str):
return str(self) == other
return False
def __getitem__(self, key):
if isinstance(key, int):
return self.lines[key]
else:
if key.step not in (None, 1):
raise IndexError("cannot slice a Source with a step")
return self.__getslice__(key.start, key.stop)
def __len__(self):
return len(self.lines)
def __getslice__(self, start, end):
newsource = Source()
newsource.lines = self.lines[start:end]
return newsource
def strip(self):
""" return new source object with trailing
and leading blank lines removed.
"""
start, end = 0, len(self)
while start < end and not self.lines[start].strip():
start += 1
while end > start and not self.lines[end-1].strip():
end -= 1
source = Source()
source.lines[:] = self.lines[start:end]
return source
def putaround(self, before='', after='', indent=' ' * 4):
""" return a copy of the source object with
'before' and 'after' wrapped around it.
"""
before = Source(before)
after = Source(after)
newsource = Source()
lines = [ (indent + line) for line in self.lines]
newsource.lines = before.lines + lines + after.lines
return newsource
def indent(self, indent=' ' * 4):
""" return a copy of the source object with
all lines indented by the given indent-string.
"""
newsource = Source()
newsource.lines = [(indent+line) for line in self.lines]
return newsource
def getstatement(self, lineno):
""" return Source statement which contains the
given linenumber (counted from 0).
"""
start, end = self.getstatementrange(lineno)
return self[start:end]
def getstatementrange(self, lineno):
""" return (start, end) tuple which spans the minimal
statement region which containing the given lineno.
"""
# XXX there must be a better than these heuristic ways ...
# XXX there may even be better heuristics :-)
if not (0 <= lineno < len(self)):
raise IndexError("lineno out of range")
# 1. find the start of the statement
from codeop import compile_command
for start in range(lineno, -1, -1):
trylines = self.lines[start:lineno+1]
# quick hack to indent the source and get it as a string in one go
trylines.insert(0, 'def xxx():')
trysource = '\n '.join(trylines)
# ^ space here
try:
compile_command(trysource)
except (SyntaxError, OverflowError, ValueError):
pass
else:
break # got a valid or incomplete statement
# 2. find the end of the statement
for end in range(lineno+1, len(self)+1):
trysource = self[start:end]
if trysource.isparseable():
break
return start, end
def getblockend(self, lineno):
# XXX
lines = [x + '\n' for x in self.lines[lineno:]]
blocklines = inspect.getblock(lines)
#print blocklines
return lineno + len(blocklines) - 1
def deindent(self, offset=None):
""" return a new source object deindented by offset.
If offset is None then guess an indentation offset from
the first non-blank line. Subsequent lines which have a
lower indentation offset will be copied verbatim as
they are assumed to be part of multilines.
"""
# XXX maybe use the tokenizer to properly handle multiline
# strings etc.pp?
newsource = Source()
newsource.lines[:] = deindent(self.lines, offset)
return newsource
def isparseable(self, deindent=True):
""" return True if source is parseable, heuristically
deindenting it by default.
"""
import parser
if deindent:
source = str(self.deindent())
else:
source = str(self)
try:
parser.suite(source+'\n')
except (parser.ParserError, SyntaxError):
return False
else:
return True
def __str__(self):
return "\n".join(self.lines)
def compile(self, filename=None, mode='exec',
flag=generators.compiler_flag, dont_inherit=0):
""" return compiled code object. if filename is None
invent an artificial filename which displays
the source/line position of the caller frame.
"""
if not filename or py.path.local(filename).check(file=0):
frame = sys._getframe(1) # the caller
filename = '%s<%s:%d>' % (filename, frame.f_code.co_filename,
frame.f_lineno)
source = "\n".join(self.lines) + '\n'
try:
co = cpy_compile(source, filename, mode, flag)
except SyntaxError, ex:
# re-represent syntax errors from parsing python strings
msglines = self.lines[:ex.lineno]
if ex.offset:
msglines.append(" "*ex.offset + '^')
msglines.append("syntax error probably generated here: %s" % filename)
newex = SyntaxError('\n'.join(msglines))
newex.offset = ex.offset
newex.lineno = ex.lineno
newex.text = ex.text
raise newex
else:
co_filename = MyStr(filename)
co_filename.__source__ = self
return py.code.Code(co).new(rec=1, co_filename=co_filename)
#return newcode_withfilename(co, co_filename)
#
# public API shortcut functions
#
def compile_(source, filename=None, mode='exec', flags=
generators.compiler_flag, dont_inherit=0):
""" compile the given source to a raw code object,
which points back to the source code through
"co_filename.__source__". All code objects
contained in the code object will recursively
also have this special subclass-of-string
filename.
"""
s = Source(source)
co = s.compile(filename, mode, flags)
return co
#
# various helper functions
#
class MyStr(str):
""" custom string which allows to add attributes. """
def getsource(obj, **kwargs):
if hasattr(obj, 'func_code'):
obj = obj.func_code
elif hasattr(obj, 'f_code'):
obj = obj.f_code
try:
fullsource = obj.co_filename.__source__
except AttributeError:
try:
strsrc = inspect.getsource(obj)
except IndentationError:
strsrc = "\"Buggy python version consider upgrading, cannot get source\""
assert isinstance(strsrc, str)
return Source(strsrc, **kwargs)
else:
lineno = obj.co_firstlineno - 1
end = fullsource.getblockend(lineno)
return fullsource[lineno:end+1]
def deindent(lines, offset=None):
if offset is None:
for line in lines:
line = line.expandtabs()
s = line.lstrip()
if s:
offset = len(line)-len(s)
break
else:
offset = 0
if offset == 0:
return list(lines)
newlines = []
def readline_generator(lines):
for line in lines:
yield line + '\n'
while True:
yield ''
readline = readline_generator(lines).next
try:
for _, _, (sline, _), (eline, _), _ in tokenize.generate_tokens(readline):
if sline > len(lines):
break # End of input reached
if sline > len(newlines):
line = lines[sline - 1].expandtabs()
if line.lstrip() and line[:offset].isspace():
line = line[offset:] # Deindent
newlines.append(line)
for i in range(sline, eline):
# Don't deindent continuing lines of
# multiline tokens (i.e. multiline strings)
newlines.append(lines[i])
except (IndentationError, tokenize.TokenError):
pass
# Add any lines we didn't see. E.g. if an exception was raised.
newlines.extend(lines[len(newlines):])
return newlines
|