def serializeGraph(g, xmlfile, write=False):
res = {}
for attr in g.attributes():
res[attr] = g[attr]
pipeline = []
for v in g.vs:
n = copy.deepcopy(v["varSet"])
n["name"] = v["name"]
pipeline.append(n)
res['pipeline'] = pipeline
root = "LocalisationTest"
xmlTree = ht.dict2et(res,
root,
listnames={
"pipeline": "filter",
"dependencies": "dependency",
"paramInts": "paramInt",
"paramFloats": "ParamFloat"
})
xmlString = prettify(xmlTree)
if not write:
return xmlString
else:
text_file = open(xmlfile, "w")
text_file.write("{0}".format(xmlString))
text_file.close()
def transform_pom_yaml_to_xml(path=None, fileName="pom.yaml", modelVersion="4.0.0", indent=" ", encoding="utf-8"):
if path == None:
path = os.getcwd()
path = path + os.sep + fileName
try:
with open(path, "r") as f:
content = f.read()
except IOError:
sys.exit("POM not fount at '%s'" % path)
pom = yaml.load(content)
if not "project" in pom:
sys.exit("'project' root node not found")
else:
pom = __preprocess_attributes(pom)
if not "modelVersion" in pom["project"]:
pom["project"]["modelVersion"] = modelVersion
elif not pom["project"]["modelVersion"] == modelVersion:
sys.exit("Unsupported modelVersion " + pom["project"]["modelVersion"])
pom["project"]["@xmlns"] = "http://maven.apache.org/POM/%s" % modelVersion
pom["project"]["@xmlns:xsi"] = "http://www.w3.org/2001/XMLSchema-instance"
pom["project"]["@xsi:schemaLocation"] = "http://maven.apache.org/POM/%s http://maven.apache.org/maven-v%s.xsd" % (modelVersion, modelVersion.replace(".", "_"))
xml = dict2et(pom)
dom = minidom.parseString(ElementTree.tostring(xml[0], encoding))
print dom.toprettyxml(indent)
def processFile(l):
[js_file_path] = l
try:
# Compute AST but don't store, it's huge
try:
parser = Acorn()
(acorn_ast, acorn_ok) = parser.run(os.path.join(corpus_root, js_file_path))
except:
return (js_file_path, None, 'Parser fail')
if not acorn_ok:
return (js_file_path, None, 'Parser fail')
functions = []
ast_ok = True
try:
# Read ast in json format
ast = json.loads(acorn_ast)
# Convert to ElementTree xml
root = dict2et(ast)
# Find all function declarations
# Record character positions in original file
for fd in root.findall("*//item[type='FunctionDeclaration']"):
functions.append((fd.find('start').text,
fd.find('end').text))
except:
ast_ok = False
if not ast_ok:
return (js_file_path, None, 'JSON fail')
# FIXME: FunctionExpression is different from FunctionDeclaration
# FIXME: Can there be nested FunctionDeclarations?
try:
js = open(os.path.join(corpus_root, js_file_path), 'r').read().decode("utf-8")
except UnicodeDecodeError:
js = open(os.path.join(corpus_root, js_file_path), 'r').read()
# Extract functions
for (start, end) in functions:
# extract function body
f_body = js[int(start):int(end)]
num_lines = f_body.count('\n')
# write body to file
f_file = os.path.basename(js_file_path).split('.')[0] + '_' + start + '_' + end + '.js'
f_path = os.path.join(output_path, f_file)
f = open(f_path, 'wb')
try:
f.write(f_body)
except UnicodeEncodeError:
f.write(f_body.encode("utf-8"))
f.close()
return (js_file_path, 'OK')
# # check if not too short and not too long
# statinfo_js = os.stat(f_path)
# num_bytes = statinfo_js.st_size
#
# # Num tokens
# try:
# tokens = Lexer(f_path).tokenList
# except:
# return (js_file_path, None, 'Lexer fail')
#
# names = [t for (tt,t) in tokens if is_token_subtype(tt, Token.Name)]
# nameCounter = Counter(names)
#
# if len(nameCounter.keys()):
# num_names = len(nameCounter.keys())
# mean_name_occurences = mean(nameCounter.values())
# median_name_occurences = median(nameCounter.values())
# else:
# num_names = 0
# mean_name_occurences = 0.0
# median_name_occurences = 0.0
#
# return (js_file_path, f_file, num_lines,
# num_bytes, num_names,
# '%.2f' % float(mean_name_occurences),
# '%.2f' % float(median_name_occurences))
except Exception, e:
return (js_file_path, None, str(e))
count += 1
v = possibleValue['code'] if possibleValue else None
p = praw.replace("[x]", v or "" )
if v:
v = re.sub("\(.*\)", "", v).replace("@", "").replace("*", "")
if len(p.split(".")) == 1: v = p
parent = ".".join(p.split(".")[:-1])
predicate = p.replace(".", ":", 1).replace(".","_")
paths[p] = {
'fhir_path': p,
'type': v,
'subs': []
}
if parent in paths:
paths[parent]['subs'].append({
'predicate': predicate,
'fhir_path': p,
'relative_xpath': "/".join(['f:'+x for x in p.replace(paths[parent]['fhir_path']+".", "").split(".")]),
'type': v
})
for f in FILES: process(f)
return {'fhirdefs': paths.values()}
t = tree(glob.glob(PROFILE_DIR + "/*.profile.json"))
#print json.dumps(t, sort_keys=True,indent=2)
v = ElementTree.tostring(dict2et(t, None, listnames = {'fhirdefs': 'path', 'subs': 'sub'}))
import pprint
#pp = pprint.PrettyPrinter(indent=4)
#pp.pprint(t)
dom = parseString(v)
print("\n".join(dom.toprettyxml().split("\n")[1:])).replace("<fhirdefs>", "<l:fhirdefs xmlns:l=\"http://local-mods\">").replace("</fhirdefs>", "</l:fhirdefs>")
p,
'relative_xpath':
"/".join([
'f:' + x for x in p.replace(
paths[parent]['fhir_path'] +
".", "").split(".")
]),
'type':
v
})
for f in FILES:
process(f)
return {'fhirdefs': paths.values()}
t = tree(glob.glob(PROFILE_DIR + "/*.profile.json"))
#print json.dumps(t, sort_keys=True,indent=2)
v = ElementTree.tostring(
dict2et(t, None, listnames={
'fhirdefs': 'path',
'subs': 'sub'
}))
import pprint
#pp = pprint.PrettyPrinter(indent=4)
#pp.pprint(t)
dom = parseString(v)
print("\n".join(dom.toprettyxml().split("\n")[1:])).replace(
"<fhirdefs>", "<l:fhirdefs xmlns:l=\"http://local-mods\">").replace(
"</fhirdefs>", "</l:fhirdefs>")