Django的：合併對象

Question

我有這樣的模式：

class Place(models.Model): 
    name = models.CharField(max_length=80, db_index=True) 
    city = models.ForeignKey(City) 
    address = models.CharField(max_length=255, db_index=True) 
    # and so on 

由於我從許多來源導入他們，我的網站的用戶能夠添加新的地方，我需要一種方法來從他們合併管理界面。問題是，名字是不是很可靠的，因爲他們可以在許多不同的方式拼寫等 我已經習慣了用這樣的：

class Place(models.Model): 
    name = models.CharField(max_length=80, db_index=True) # canonical 
    city = models.ForeignKey(City) 
    address = models.CharField(max_length=255, db_index=True) 
    # and so on 

class PlaceName(models.Model): 
    name = models.CharField(max_length=80, db_index=True) 
    place = models.ForeignKey(Place) 

這樣的查詢

Place.objects.get(placename__name='St Paul\'s Cathedral', city=london) 

和合並像這

class PlaceAdmin(admin.ModelAdmin): 
    actions = ('merge',) 

    def merge(self, request, queryset): 
     main = queryset[0] 
     tail = queryset[1:] 

     PlaceName.objects.filter(place__in=tail).update(place=main) 
     SomeModel1.objects.filter(place__in=tail).update(place=main) 
     SomeModel2.objects.filter(place__in=tail).update(place=main) 
     # ... etc ... 

     for t in tail: 
      t.delete() 

     self.message_user(request, "%s is merged with other places, now you can give it a canonical name." % main) 
    merge.short_description = "Merge places" 

正如你所看到的，我必須用FK更新所有其他模型以放置新的值。但這不是很好的解決方案，因爲我必須將每個新模型添加到此列表中。

如何在刪除某些對象之前「級聯更新」所有外鍵？

或者，也許還有其他的解決方案做/避免合併

Answer 1

如果有人位數的，這裏真的是把這個通用代碼：

def merge(self, request, queryset): 
    main = queryset[0] 
    tail = queryset[1:] 

    related = main._meta.get_all_related_objects() 

    valnames = dict() 
    for r in related: 
     valnames.setdefault(r.model, []).append(r.field.name) 

    for place in tail: 
     for model, field_names in valnames.iteritems(): 
      for field_name in field_names: 
       model.objects.filter(**{field_name: place}).update(**{field_name: main}) 

     place.delete() 

    self.message_user(request, "%s is merged with other places, now you can give it a canonical name." % main) 

Answer 2

基於對接受的答案在評論中提供的片段，我能夠開發以下內容。此代碼不處理GenericForeignKeys。我不贊成使用它們，因爲我認爲這表示您使用的模型存在問題。

此代碼處理unique_together限制，阻止原子事務與我發現的其他片段完成。無可否認，它的實施有點令人費解。我也使用django-audit-log，並且我不想將這些記錄與更改合併。我也想適當修改創建和修改的字段。此代碼可以與Django 1.10和更新的Model _meta API一起使用。

from django.db import transaction 
from django.utils import timezone 
from django.db.models import Model 

def flatten(l, a=None): 
    """Flattens a list.""" 
    if a is None: 
     a = [] 
    for i in l: 
     if isinstance(i, Iterable) and type(i) != str: 
      flatten(i, a) 
     else: 
      a.append(i) 
    return a 


@transaction.atomic() 
def merge(primary_object, alias_objects=list()): 
    """ 
    Use this function to merge model objects (i.e. Users, Organizations, Polls, 
    etc.) and migrate all of the related fields from the alias objects to the 
    primary object. This does not look at GenericForeignKeys. 

    Usage: 
    from django.contrib.auth.models import User 
    primary_user = User.objects.get(email='good_email@example.com') 
    duplicate_user = User.objects.get(email='good_email+duplicate@example.com') 
    merge_model_objects(primary_user, duplicate_user) 
    """ 
    if not isinstance(alias_objects, list): 
     alias_objects = [alias_objects] 

    # check that all aliases are the same class as primary one and that 
    # they are subclass of model 
    primary_class = primary_object.__class__ 

    if not issubclass(primary_class, Model): 
     raise TypeError('Only django.db.models.Model subclasses can be merged') 

    for alias_object in alias_objects: 
     if not isinstance(alias_object, primary_class): 
      raise TypeError('Only models of same class can be merged') 

    for alias_object in alias_objects: 
     if alias_object != primary_object: 
      for attr_name in dir(alias_object): 
       if 'auditlog' not in attr_name: 
        attr = getattr(alias_object, attr_name, None) 
        if attr and "RelatedManager" in type(attr).__name__: 
         if attr.exists(): 
          if type(attr).__name__ == "ManyRelatedManager": 
           for instance in attr.all(): 
            getattr(alias_object, attr_name).remove(instance) 
            getattr(primary_object, attr_name).add(instance) 
          else: 
           # do an update on the related model 
           # we have to stop ourselves from violating unique_together 
           field = attr.field.name 
           model = attr.model 
           unique = [f for f in flatten(model._meta.unique_together) if f != field] 
           updater = model.objects.filter(**{field: alias_object}) 
           if len(unique) == 1: 
            to_exclude = { 
             "%s__in" % unique[0]: model.objects.filter(
              **{field: primary_object} 
             ).values_list(unique[0], flat=True) 
            } 
           # Concat requires at least 2 arguments 
           elif len(unique) > 1: 
            casted = {"%s_casted" % f: Cast(f, TextField()) for f in unique} 
            to_exclude = { 
             'checksum__in': model.objects.filter(
              **{field: primary_object} 
             ).annotate(**casted).annotate(
              checksum=Concat(*casted.keys(), output_field=TextField()) 
             ).values_list('checksum', flat=True) 
            } 
            updater = updater.annotate(**casted).annotate(
             checksum=Concat(*casted.keys(), output_field=TextField()) 
            ) 
           else: 
            to_exclude = {} 

           # perform the update 
           updater.exclude(**to_exclude).update(**{field: primary_object}) 

           # delete the records that would have been duplicated 
           model.objects.filter(**{field: alias_object}).delete() 

      if hasattr(primary_object, "created"): 
       if alias_object.created and primary_object.created: 
        primary_object.created = min(alias_object.created, primary_object.created) 
       if primary_object.created: 
        if primary_object.created == alias_object.created: 
         primary_object.created_by = alias_object.created_by 
       primary_object.modified = timezone.now() 

      alias_object.delete() 

    primary_object.save() 
    return primary_object 

Answer 3

在Django 1.10上測試。希望它可以服務。

Django的擴展merge_model_instances管理命令：

def merge(primary_object, alias_objects, model): 
"""Merge 2 or more objects from the same django model 
The alias objects will be deleted and all the references 
towards them will be replaced by references toward the 
primary object 
""" 
if not isinstance(alias_objects, list): 
    alias_objects = [alias_objects] 

if not isinstance(primary_object, model): 
    raise TypeError('Only %s instances can be merged' % model) 

for alias_object in alias_objects: 
    if not isinstance(alias_object, model): 
     raise TypeError('Only %s instances can be merged' % model) 

for alias_object in alias_objects: 
    # Get all the related Models and the corresponding field_name 
    related_models = [(o.related_model, o.field.name) for o in alias_object._meta.related_objects] 
    for (related_model, field_name) in related_models: 
     relType = related_model._meta.get_field(field_name).get_internal_type() 
     if relType == "ForeignKey": 
      qs = related_model.objects.filter(**{ field_name: alias_object }) 
      for obj in qs: 
       setattr(obj, field_name, primary_object) 
       obj.save() 
     elif relType == "ManyToManyField": 
      qs = related_model.objects.filter(**{ field_name: alias_object }) 
      for obj in qs: 
       mtmRel = getattr(obj, field_name) 
       mtmRel.remove(alias_object) 
       mtmRel.add(primary_object) 
    alias_object.delete() 
return True 

Answer 4

兩個圖書館現在最多最新的模型合併，納入相關的模型的功能存在。

Django Super Deduper