def readBible(oldFile, newFile):
contentOld = fileReader.getFileContentRemEmptys(oldFile)
contentNew = fileReader.getFileContentRemEmptys(newFile)
bible = database.Bible()
ommitedLinesOld = 0
ommitedLinesNew = 0
for line in contentOld:
try:
parsed = parser.parse(line)
bible.addVerset("Stary Testament", parsed[0], parsed[1],
[parsed[2], parsed[3]])
except ValueError:
ommitedLinesOld = ommitedLinesOld + 1
for line in contentNew:
try:
parsed = parser.parse(line)
bible.addVerset("Stary Testament", parsed[0], parsed[1],
[parsed[2], parsed[3]])
except ValueError:
ommitedLinesNew = ommitedLinesNew + 1
log.inf("Ommited: old " + str(ommitedLinesOld))
log.inf("Ommited: new " + str(ommitedLinesNew))
return bible
def getJournal(self):
journal = {}
journal['title'] = utils.get_text(self.tree, './/journal-title')
journal['nlmTa'] = utils.get_text(
self.tree,
'.//journal-meta/journal-id/[@journal-id-type="nlm-ta"]')
journal['isoAbbrev'] = utils.get_text(
self.tree,
'.//journal-meta/journal-id/[@journal-id-type="iso-abbrev"]')
journal['issn'] = utils.get_atrib_dic(self.tree,
'.//journal-meta/issn',
'pub-type')
journal['publisher'] = utils.get_iter_tex_dic(
self.tree, './/journal-meta/publisher/publisher-name')
self.dict['journal'] = journal
def CreateThing(url, ninterface):
met = {}
met['uid'] = url
met['netif'] = ninterface
met['LastUpdate'] = int(round(time.time() * 1000)) #in ms
url = Config.OCFModelRoot + url
ThingFactory.parser = Parser(url, 'JSON')
thng = ThingFactory.parser.Parse()
logging.debug('Parsed OCF thing from ' + url)
#Now create the thing
met['schema'] = thng['$schema']
#Metadata
for key in thng:
if not (type(thng[key]) == dict or type(thng[key]) == list):
met[key] = thng[key]
#properties
pro = {}
try:
prop = thng['definitions']
for p in prop:
ppts = prop[p]['properties']
for pp in ppts:
pro[pp] = None
except KeyError:
pro = {}
meta = ThingAttribute(**met)
props = ThingAttribute(**pro)
actns = ThingAttribute(**pro)
thing = Thing(meta, props, actns)
return thing
def CreateThing(url, ninterface):
met = {}
met['uid'] = url
met['netif'] = ninterface
met['LastUpdate'] = int(round(time.time() * 1000)) #in ms
url = Config.W3CModelRoot + url
ThingFactory.parser = Parser(url, 'JSON')
thng = ThingFactory.parser.Parse()
logging.debug('Parsed W3C thing from ' + url)
#Now create the thing
met['context'] = thng['@context']
#Metadata
for key in thng:
if not (type(thng[key]) == dict or type(thng[key]) == list):
met[key] = thng[key]
#properties
pro = {}
try:
prop = thng['interactions']
for p in prop:
if p['@type'][0] == 'Property':
pro[p['name']] = None
except KeyError:
pro = {}
meta = ThingAttribute(**met)
props = ThingAttribute(**pro)
actns = ThingAttribute(**pro)
thing = Thing(meta, props, actns)
return thing
def CreateThing(url, ninterface):
met = {}
met['uid'] = url
met['netif'] = ninterface
met['LastUpdate'] = int(round(time.time() * 1000)) #in ms
url = Config.IPSOModelRoot + url
ThingFactory.parser = Parser(url, 'XML')
thng = ThingFactory.parser.Parse()
logging.debug('Parsed IPSO thing from ' + url)
#Now create the thing
root = thng.getroot()
#Metadata
res = root.find('Object')
name = res.find('Name')
met['Name'] = name.text
met['schema'] = str(root.attrib)
#properties
pro = {}
try:
res = root.find('Object').find('Resources')
for child in res.findall('Item'):
pp = child.find('Name')
pro[pp.text] = None
except KeyError:
pro = {}
meta = ThingAttribute(**met)
props = ThingAttribute(**pro)
actns = ThingAttribute(**pro)
thing = Thing(meta, props, actns)
return thing
def getContributors(self):
tree = self.tree.findall('.//contrib-group/contrib/[@contrib-type]')
contributors = []
if tree is not None:
for e in tree:
if (e.text is not None):
contrib = {}
contrib['type'] = e.attrib['contrib-type']
contrib['name'] = utils.get_text(e, './/name/*', ', ')
contributors.append(contrib)
self.dict['contributors'] = contributors
def getAffiliations(self):
tree = self.tree.findall('.//aff')
affiliations = []
if tree is not None:
for e in tree:
aff = {'id': 'aff', 'name': '', 'country': ''}
try:
aff['id'] = e.attrib['id']
except:
pass
aff['name'] = utils.get_text(e, './/institution')
aff['address'] = utils.get_text(e, './/addr-line')
aff['country'] = utils.get_text(e, './/country')
try:
if not aff['name']:
aff['name'] = aff['address']
if not aff['name']:
aff['name'] = [t for t in e.itertext()][-1]
except:
pass
try:
if not aff['country']:
if aff['address']:
aff['country'] = aff['address'].split(
',')[-1].lstrip()
elif aff['name']:
aff['country'] = aff['name'].split(
',')[-1].lstrip()
except:
pass
affiliations.append(aff)
self.dict['affiliations'] = affiliations
def parse(self):
self.openFile()
# Title
tree_title = self.tree.find('.//title-group/article-title')
title = utils.get_iter_tex(tree_title)
self.dict['title'] = title
# Article meta
self.dict['pmid'] = utils.get_text(
self.tree, './/article-meta/article-id/[@pub-id-type="pmid"]')
self.dict['pmc'] = utils.get_text(
self.tree, './/article-meta/article-id/[@pub-id-type="pmc"]')
self.dict['doi'] = utils.get_text(
self.tree, './/article-meta/article-id/[@pub-id-type="doi"]')
self.dict['publisherId'] = utils.get_text(
self.tree,
'.//article-meta/article-id/[@pub-id-type="publisher-id"]')
# Keywords
self.dict['keywords'] = []
for i in self.tree.findall('.//article-meta/*/kwd'):
for t in i.findall('.//*'):
self.dict['keywords'].append(t.text)
if len(self.dict['keywords']) == 0:
self.dict['keywords'] = utils.get_text_array(
self.tree, './/article-meta/*/kwd')
# ElocationId
self.dict['elocationId'] = utils.get_text(
self.tree, './/journal-meta/elocationId')
# Categories
self.dict['categories'] = utils.get_text_array(
self.tree,
'.//article-meta/article-categories/*/subj-group/subject')
self.getAbstract()
self.getJournal()
self.getDate()
self.getContributors()
self.getAffiliations()
self.getCountry()
self.getKwd()
return self
def openFile(self):
handle = open(self.path, 'r')
self.content = handle.read()
self.tree = utils.read_xml(self.path, False)
handle.close()