u'CitedBy',
'prior',
'family lenght',
'CitO',
'CitP'
]
print "\n> Hi! This is DataTable Families formater", ndf
if 'Description' + ndf in os.listdir(ListBiblioPath):
with open(ListBiblioPath + '//' + ndf, 'r') as data:
dico = LoadBiblioFile(ListBiblioPath, ndf)
else: #Retrocompatibility
print "please use Comptatibilizer"
sys.exit()
LstBrevet = dico['brevets']
if dico.has_key('requete'):
requete = dico["requete"]
print "Using ", ndf, " file. Found ", len(
dico["brevets"]), " patents! Formating to HMTL tables"
LstExp = []
LstExp2 = []
#just for testing last fnction in gathered should deseapear soon
for brev in LstBrevet:
#brev = CleanPatent(brev)
tempo = dict() # this one for DataTable
tempo2 = dict() #the one for pitable
countryInv = [] #new field
countryApp = []
# data = registered_client.family('publication', , 'biblio')
registered_client.accept_type = 'application/json'
for ndf in [fic2 for fic2 in os.listdir(ResultBiblioPath) if fic2.count('Description')==0]:
if ndf.startswith('Families'):
typeSrc = 'Families'
else:
typeSrc = ''
if 'Description'+ndf or 'Description'+ndf.lower() in os.listdir(ResultListPath): # NEW 12/12/15 new gatherer append data to pickle file in order to consume less memory
ficBrevet = LoadBiblioFile(ResultListPath, ndf)
else: #Retrocompatibility
print 'gather your data again. sorry'
sys.exit()
if ficBrevet.has_key('brevets'):
lstBrevet = ficBrevet['brevets']
# if data.has_key('requete'):
# DataBrevet['requete'] = data["requete"]
print "Found ",typeSrc, ' file and', len(lstBrevet), " patents! Gathering contents"
else:
print 'gather your data again'
sys.exit()
registered_client = epo_ops.Client(key, secret)
# data = registered_client.family('publication', , 'biblio')
registered_client.accept_type = 'application/json'
BiblioPatents = []
#making the directory saving patents
RepDir = ResultPathContent
try:
fic = open(ResultPath + '//' + ndf, 'r')
print "loading data file ", ndf + ' from ', ResultPath, " directory."
if 'Description' + ndf or "Description" + ndf.title() in os.listdir(
ResultPath
): # NEW 12/12/15 new gatherer append data to pickle file in order to consume less memory
data = LoadBiblioFile(ResultPath, ndf)
else: #Retrocompatibility :-)
print "gather your data again"
sys.exit()
if isinstance(data, collections.Mapping):
ListeBrevet = data['brevets']
if data.has_key('number'):
print "Found ", data["number"], " patents! and ", len(
ListeBrevet), " gathered."
else:
print 'data corrupted. Do something (destroying data directory is a nice idea)'
sys.exit()
print len(ListeBrevet), " patents loaded from file."
print "Augmenting list with families."
ficOk = True
except:
print "file ", ResultPath + "/" + ndf, " missing. try gather again."
ficOk = False
ndf2 = "Complete" + ndf
ListLab = [pat['label'] for pat in ListeBrevet]
data2 = LoadBiblioFile(ResultBiblioPath, 'Families' + ndf)
nbFam = len(data2['brevets'])
else: #Retrocompatibility
print "please use Comptatibilizer"
#if 'Fusion' in data.keys()with open( ResultBiblioPath+'//Families'+ndf, 'r') as ficBib:
# data2 = cPickle.load(ficBib)
else:
nbFam = 0
import datetime
today = datetime.datetime.today()
date = today.strftime('%d, %b %Y')
totalPatents = ""
if data.has_key("brevets"): #compatibility, this may be useless
totalPatents = len(data["brevets"])
else:
totalPatents = "see datatable :-)"
# new method to count documents by type
totalsPerType = []
totalsPerFamilyType = []
if Gather:
def generateTotal(content):
path = os.path.join(ResultContentsPath, content)
if os.path.isdir(path):
lstfic = os.listdir(path)
languages = set([str(fi[0:2]) for fi in lstfic])
totalLanguages = {l: 0 for l in languages}
u'CitedBy', # the list of docs (patents) cititng this patent
'CitP', # the patents cited by this patent
'CitO' # the other docs cited by this patent
] #"citations"
if 'Description' + ndf in os.listdir(
ListBiblioPath
): # NEW 12/12/15 new gatherer append data to pickle file in order to consume less memory
dico = LoadBiblioFile(ListBiblioPath, ndf)
else: #Retrocompatibility
with open(ListBiblioPath + '//' + ndf, 'r') as data:
dico = cPickle.load(data)
LstBrevet = dico['brevets']
if dico.has_key('requete'):
requete = dico["requete"]
if dico.has_key('number'):
print "Found ", dico["number"], " patents! Formating to HMTL tables"
else:
print "Found ", len(LstBrevet), " patents! Formating to HMTL tables"
LstExp = []
LstExp2 = []
#just for testing las fnction in gathered should deseapear soon
##next may need clarifying update
for brev in LstBrevet:
#brev = CleanPatent(brev)
tempo = dict() # this one for DataTable
for ndf in set(srcFile):
if 'Description' + ndf in os.listdir(
ListBiblioPath
): # NEW 12/12/15 new gatherer append data to pickle file in order to consume less memory
DataBrevet = LoadBiblioFile(ListBiblioPath, ndf)
print "\n> Hi! This is FormateExportPivotTable"
else: #Retrocompatibility... prévious test is ugly: there is an issue with filename in lowercase (sometimes)
print "please use Comptatibilizer"
DataBrevet = LoadBiblioFile(ListBiblioPath,
ndf) #so I try to laod it....
if isinstance(DataBrevet, collections.Mapping):
#data = DataBrevet
LstBrevet = DataBrevet['brevets']
if DataBrevet.has_key('number'):
print "Found ", DataBrevet[
"number"], " patents! Formating into HMTL Pivot tables"
else:
print "Found ", len(
DataBrevet["brevets"]
), " patents! Trying to format into HMTL Pivot tables"
else:
print "Please delete you data directory... incompatible old stuff in it"
print "or try Comptatibilizer before"
LstExp = []
LstExp2 = []
#just for testing las fnction in gathered should deseapear soon
if ndf.count('Families') > 0:
#clesRef2 = ['label', 'year', 'priority-active-indicator', 'kind', 'applicant', 'country', 'inventor', "CPC", 'IPCR4', 'IPCR7', "Inventor-Country", "Applicant-Country", 'Citations'] #'citations','representative',
clesRef2 = [
