wipo-gbd-transformation 1.1.54__py3-none-any.whl → 1.1.55__py3-none-any.whl

gbdtransformation/brands/chtm/filters.py

@@ -1,183 +1,155 @@
 import re
 
-def get_kind(info):
-    if info.marart:
-        nbs = info.marart.marartn
-
-        if not isinstance(nbs, list):
-            nbs = [nbs]
-
-        for nb in nbs:
-            if nb == '6':
-                return ['Collective']
-
-    return ['Individual']
-
-def get_verbal(info):
-    if info.markve:
-        return info.markve
-
-    # or get it from the picture remark
-    if info.marpicrem:
-        return info.marpicrem.replace('((fig.))', '')
-
-def structure_gs(gsgr):
-    if not gsgr: return {}
-
-    nc = {} # nice classes and eventual goods services
-    gs = [] # unclassified goods and services
-
-    nice = gsgr.intregg
-    if not isinstance(nice, list):
-        nice = [nice]
-
-    # get the nice classes
-    for n in nice:
-        nc[n.nicclai] = []
-
-    # get the goods and services
-    terms = gsgr.gstermt
-    try:
-        # terml means unclassified
-        terms_lines = terms.gsterml
-        if not isinstance(terms_lines, list):
-            terms_lines = [terms_lines]
-
-        l = []
-        for t in terms_lines:
-            if t:
-                l += t.split('\n')
-
-        terms_lines = l
-    except:
-        # classified (nice class indicated inline)
-        terms_lines = terms.split('\n') if terms else []
-        terms_lines = [line.strip() for line in terms_lines if line.strip()]
-
-    nc_gs = gs
-    for line in terms_lines:
-        # get the numeric prefix if the line
-        matches = re.findall(r'^0?(\d+):? (.*)', line)
-        if len(matches):
-            # split the class number and the rest of the line
-            (cls, line) = matches[0]
-            # try and find the nice class defined before
-            # if not found, go to unclassified
-            nc_gs = nc.get(cls, gs)
-        nc_gs.append(line.strip())
-
-    # join the lines then split on ';'
-    for cls in nc:
-        gslines = nc[cls]
-        if len(gslines):
-            nc[cls] = [term.strip().rstrip('.') for term in ' '.join(gslines).split(';')]
-
-    return (nc, gs)
-
-def get_roles(info):
-    persons = info.regadr
-
-    if not isinstance(persons, list):
-        persons = [persons]
-
-    matches = {
-        'applicants': [],
-        'representatives': [],
-        'correspondence': None
-    }
-
-    def _get_person_info(p):
-        info = {}
-        nameadd = p.nameadd
-
-        try:
-            name = nameadd.namel.namell
-            if isinstance(name, list):
-                name = list(filter(None, name))
-                name = ' '.join(name)
-        except:
-            name = nameadd.namel
-
-        try:
-            addr = nameadd.addrl.addrll
-            if isinstance(addr, list):
-                addr = list(filter(None, addr))
-                addr = ', '.join(addr)
-        except:
-            addr = nameadd.addrl
-
-        # complete the address with zipcode and city
-        if nameadd.plainco:
-            if addr: addr += ', '
-            else: addr = ''
-            addr += (nameadd.plainco)
-
-        return {'name': name, 'addr': addr, 'nat': nameadd.nat}
-
-    for p in persons:
-        role = p.addrrole
-        if role == '1':
-            matches['applicants'].append(_get_person_info(p))
-        elif role == '3':
-            matches['representatives'].append(_get_person_info(p))
-        elif role == '11':
-            matches['correspondence'] = _get_person_info(p)
-        # Licensee
-        elif role == '6': continue
-        # Bankruptcy office
-        elif role == '7': continue
-        # Usufructuary
-        elif role == '8': continue
-        # Pawnee
-        elif role == '9': continue
-        # Collection office
-        elif role == '10': continue
-        # Sub-Licensee
-        elif role == '17': continue
-        # Limited Licensee
-        elif role == '19': continue
-        # Exclusive Licensee
-        elif role == '20': continue
-        else:
-            raise Exception('unindentified role [%s]' % role)
-
-    return matches
-
-def get_representatives(info):
-    persons = info.regadr
-    representatives = [p for p in persons if p.addrrole == '3']
-
-    return representatives
-
-def get_correspondence(info):
-    persons = info.regadr
-    correspondence = [p for p in persons if p.addrrole == '11']
-
-    if len(correspondence): return correspondence[0]
-
-def translate_status(status, deld):
-    if deld: return 'Ended'
-    if status == '0': return 'Pending'
-    if status == '1': return 'Registered'
-
-    raise Exception('Status "%s" unmapped' % status)
-
-def translate_feature(feature, marart):
-    if feature == '1': return 'Word'
-    if feature == '2': return 'Figurative'
-    if feature == '3': return 'Combined'
-    if feature == '4':
-        if not marart: return 'Undefined'
-        # we do not support multi-value
-        # for features. take the first one
-        if isinstance(marart.marartn, list):
-            marart.marartn = marart.marartn.pop()
-        if marart.marartn == '10': return 'Sound'
-        if marart.marartn == '11': return 'Three dimensional'
-        if marart.marartn == '12': return 'Colour'
-        if marart.marartn == '14': return 'Motion'
-        if marart.marartn == '15': return 'Position'
-        if marart.marartn == '16': return 'Hologram'
-
-    raise Exception('Feature "%s" unmapped' % feature)
-
+# namespaces defined in XML and to be ignored in procecssing
+ignore_namespace = [
+    'http://www.wipo.int/standards/XMLSchema/ST96/Common',
+    'http://www.oasis-open.org/tables/exchange/1.0',
+    'http://www.wipo.int/standards/XMLSchema/ST96/Trademark',
+    'http://www.w3.org/2001/XMLSchema-instance',
+    'urn:ige:schema:xsd:st96trademarksuperset-1.0.0'
+]
+
+def translate_kind(kind):
+    if not kind: return ['Individual']
+
+    if kind == 'Individual mark': return ['Individual']
+    if kind == 'Collective mark': return ['Collective']
+
+    return 'Unknown'
+    #raise Exception('kind "%s" is not mapped.' % kind)
+
+def translate_status(status):
+    if not status: return 'Ended'
+
+    if status in ['Registered', 
+                  'Registration published']: 
+        return 'Registered'
+
+    if status in ['Application published',
+                  'Application filed',
+                  'Application opposed',
+                  'Application accepted']:
+        return 'Pending'
+
+    if status in ['Application refused',
+                  'Registration cancelled',
+                  'Application cancelled']:
+        return 'Ended'
+
+    return 'Unknown'
+    #raise Exception('Status "%s" unmapped' % status)
+
+def translate_feature(feature):
+    """translation of mark feature"""
+    if not feature: return 'Undefined'
+    feature = feature.upper()
+    if feature == 'COMBINED': return 'Combined'
+    if feature == 'WORD': return 'Word'
+    if feature == 'STYLIZED CHARACTERS': return 'Stylized characters'
+    if feature == 'FIGURATIVE': return 'Figurative'
+    if feature == 'SOUND': return 'Sound'
+    if feature == '_3_D': return 'Three dimensional'
+    if feature == '3-D': return 'Three dimensional'
+    if feature == 'THREE DIMENSIONAL': return 'Three dimensional'
+    if feature == 'POSITION': return 'Position'
+    if feature == 'HOLOGRAM': return 'Hologram'
+    if feature == 'TRACER': return 'Tracer'
+    if feature == 'PATTERN': return 'Pattern'
+    if feature == 'OLFACTORY': return 'Olfactory'
+    if feature == 'MULTIMEDIA': return 'Multimedia'
+    if feature == 'MOTION': return 'Motion'
+    return 'Unknown'
+
+    #return feature.lower().capitalize()
+    # raise Exception to recognize unmapped values
+    #raise Exception('Feature "%s" unmapped' % feature)
+
+def get_registration_nb(trademark, tmstatus):
+    if trademark.RegistrationNumber:
+        return trademark.RegistrationNumber
+
+    # default registration number to application number
+    # in case none is provided
+    if tmstatus in ['Registered', 'Expired']:
+        return trademark.ApplicationNumber.ApplicationNumberText
+
+def get_goods_services(goods_services):
+    nc_gs = {} # classified
+    if not goods_services:
+        goods_services = []
+
+    if not isinstance(goods_services, list):
+        goods_services = [goods_services]
+
+    for goods_service in goods_services:
+        code = goods_service.ClassNumber
+        if code and not code == '0':
+            nc_gs[code] = {}
+            desc = goods_service.GoodsServicesDescription
+
+            if hasattr(desc, '__value'):
+                terms = desc.__value
+            else:
+                terms = desc
+
+            if terms:
+                nc_gs[code]['terms'] = terms
+            else:
+                continue
+
+            if hasattr(desc, '_languageCode'):
+                lang = desc._languageCode
+                nc_gs[code]['lang'] = lang.lower()
+
+    return nc_gs
+
+def  get_entity_addr(addr):
+    if not addr: return None
+    return "%s %s %s" % (addr.AddressStreet, addr.AddressCity, addr.AddressPostcode)
+def  get_entity_name(name):
+    if not name: return
+    if name.OrganizationName: return name.OrganizationName
+    return "%s %s" % (name.FirstName, name.LastName )
+def  get_entity_kind(name):
+    if not name: return
+    if name.OrganizationName: return 'Legal entity'
+    return 'Natural person'
+
+def get_full_address(postalStructuredAddress):
+    if "AddressLineText" not in postalStructuredAddress:
+        return
+    result = ""
+    first = True
+    for addressLineText in postalStructuredAddress["AddressLineText"]:
+        if hasattr(addressLineText, '__value'):
+            if first:
+                first = False
+            else:
+                result += ", "
+            result += addressLineText.__value
+    if len(result) == 0:
+        return
+    else: 
+        return result.strip()
+
+def select_priority_date(priority):
+    if priority == None:
+        return None
+    if "PriorityApplicationFilingDate" in priority:
+        return priority["PriorityApplicationFilingDate"]
+    elif "PriorityRegistrationDate" in priority:
+        return priority["PriorityRegistrationDate"]
+    else:
+        return None
+
+def clean_verbal_element(element_text):
+    if element_text == None:
+        return None
+    element_text = element_text.replace("((fig.))", "")
+    return element_text.strip()
+
+def local_guess_language(content):
+    if content == None:
+        return None
+    from langdetect import detect
+    return detect(content)

gbdtransformation/brands/chtm/schema

@@ -1,91 +1,79 @@
-/transac[@deleteflag=0]
-/transac
-__/marhist
-____/histdata
-______/artnr
-______/colclai
-______/evdat
-______/evdatint
-______/gazchap
-______/gaznum
-______/gsgr
-________/gstermt
-__________/gsterml
-________/intregg
-__________/nicclai
-______/marart
-________/marartn
-______/marpicn
-______/marrec
-______/marrem
-______/prigr
-________/prio
-__________/priappd
-__________/prinat
-__________/prinr
-________/prirem
-______/pubdate
-______/publcode
-______/publicate
-______/publrem
-______/regadr
-________/addrrole
-________/nameadd
-__________/addrl
-____________/addrll
-__________/namel
-____________/namell
-__________/nat
-__________/plainco
-______/register
-______/snapshot
-______/valid
-__/marinfo
-____/basannd
-____/basappn
-____/basdeld
-____/basipikey
-____/basregd
-____/basregn
-____/basregper
-____/basstate
-____/colclai
-____/expirationdate
-____/firstgazd
-____/firstgazn
-____/gsgr
-______/gstermt
-________/gsterml
-______/intregg
-________/nicclai
-____/lastgazd
-____/lastgazn
-____/marart
-______/marartn
-____/markve
-____/marpicd
-____/marpicn
-____/marpicrem
-____/marrem
-____/martype
-____/oppositiongr
-______/oppositiondate
-______/oppositionstate
-____/origlan
-____/prigr
-______/prio
-________/priappd
-________/prinat
-________/prinr
-______/prirem
-____/regadr
-______/addrrole
-______/nameadd
-________/addrl
-__________/addrll
-________/namel
-__________/namell
-________/nat
-________/plainco
-____/renewalgr
-______/renewalt
+/Trademark
+__/ApplicantBag
+____/Applicant
+______/Contact
+________/Name
+__________/PersonName
+____________/PersonFullName
+________/PostalAddressBag
+__________/PostalAddress
+____________/PostalStructuredAddress
+______________/AddressLineText
+______________/AddressLineText[@sequenceNumber=1]
+______________/CountryCode
+______/LegalEntityName
+__/ApplicationDate
+__/ApplicationNumber
+____/ApplicationNumberText
+__/CHMarkCategory
+__/ExpiryDate
+__/GoodsServicesBag
+____/GoodsServices
+______/ClassDescriptionBag
+________/ClassDescription
+__________/ClassNumber
+__________/GoodsServicesDescriptionText
+______/GoodsServicesClassificationBag
+________/GoodsServicesClassification
+__________/ClassNumber
+__________/ClassificationKindCode
+__/MarkCategory
+__/MarkCurrentStatusCode
+__/MarkRepresentation
+____/MarkFeatureCategory
+____/MarkReproduction
+______/MarkImageBag
+________/MarkImage
+__________/FileName
+__________/MarkImageColourClaimedText
+______/WordMarkSpecification
+________/MarkSignificantVerbalElementText
+__/PriorityBag
+____/Priority
+______/PriorityApplicationFilingDate
+______/PriorityCountryCode
+______/PriorityRegistrationDate
+______/PriorityRegistrationNumber
+__/PublicationBag
+____/Publication
+______/NationalPublication
+________/PublicationCategoryText
+________/PublicationStatusCategory
+________/RegistrationChangeBag
+__________/RegistrationChange
+____________/ChangeDescriptionText
+____________/ChangeText
+______/PublicationDate
+______/PublicationIdentifier
+______/PublicationIdentifier[@officeCode=CH]
+______/PublicationPage
+__/RegistrationDate
+__/RegistrationNumber
+__/RegistrationOfficeCode
+__/RepresentativeBag
+____/Representative
+______/Contact
+________/Name
+__________/PersonName
+____________/PersonFullName
+________/PostalAddressBag
+__________/PostalAddress
+____________/PostalStructuredAddress
+______________/AddressLineText
+______________/AddressLineText[@sequenceNumber=1]
+______________/CountryCode
+______/LegalEntityName
+__/TradeDistinctivenessIndicator
+__/Version
+____/VersionDateTime
+______________________________/TrademarkApplicationType_V7_1.xsd]