Bugfix/bulk import

CHANGELOG.rst

@@ -13,20 +13,20 @@
 
 1.3.4
 =====
-* Bugfix: Query iterrator now returns all elements instead of a premature empty list
+* Bugfix: Query iterator now returns all elements instead of a premature empty list
 * Bugfix: Collection naming when using the arango's name argument
 * New: Schema validation example
-* New: Satelite graphs
+* New: Satellite graphs
 
 1.3.3
 =====
 
 * SSL certificate support
 * More doc
 * Fixed on_load schema validation
-* Gevent, monkey patcjing breaks python's multi=processing. Removed grequests as the default, back to requests.
+* Gevent, monkey patching breaks python's multi=processing. Removed grequests as the default, back to requests.
 * Removed grequests and gevent as hard dependencies. Added explicit error messages, to prompt users can install them if needed.
-* Jwauth is not in it's own file
+* Jwauth is not in its own file
 * Generic rest call to database support (action) for connection, database.
 * Foxx support
 * Tasks create, delete, fetch support
@@ -37,7 +37,7 @@
 * Validation bug fixes
 * New Numeric, Int, Bool, String, Enumeration, Range validators
 * Fields can have default values
-* When creationg a new document, Collection will serve one populated with defaults
+* When creating a new document, Collection will serve one populated with defaults
 * stastd support thx to: @dothebart
 * properties definition in schema
 * AQL errors now come with prints and line numbers for everyone's convenience
@@ -60,15 +60,15 @@
 =====
 
 * Added bulk import to connection
-* Added binvars to explain
+* Added bindvars to explain
 
 1.2.8
 =====
 
 * BugFix: recursive field validation
 * BugFix: fullCount option now works
 * Length validator will raise a ValidationError if value has no length
-* users can now specify custon json encoders
+* users can now specify custom json encoders
 
 1.2.7
 =====
@@ -124,7 +124,7 @@
 * Support for ArangoDB 3.X, pyArango no longer supports 2.X versions
 * Support for authentication
 * User support added
-* Adedd AikidoSession to seemlessly manage request sessions
+* Added AikidoSession to seemlessly manage request sessions
 * AikidoSession stores basic stats about the requests
 * AikidoSession detects 401 errors and notifies the user that authentication is required
 * AikidoSession detects connection errors and notifies the user that arango is probably not running

README.rst

@@ -13,8 +13,8 @@ pyArango
    :alt: downloads_week
    :target: https://pepy.tech/project/pyarango/week
 
-.. image:: https://travis-ci.org/tariqdaouda/pyArango.svg?branch=1.2.2
-    :target: https://travis-ci.org/tariqdaouda/pyArango
+.. image:: https://travis-ci.com/Alexsaphir/pyArango.svg?branch=master
+    :target: https://travis-ci.com/github/Alexsaphir/pyArango
 .. image:: https://img.shields.io/badge/python-2.7%2C%203.5-blue.svg
 .. image:: https://img.shields.io/badge/arangodb-3.0-blue.svg
 
@@ -29,7 +29,7 @@ Key Features
 pyArango is geared toward the developer. It's here to help to you develop really cool apps using ArangoDB, really fast.
 
  - Light and simple interface
- - Built-in validation of fields on seting or on saving
+ - Built-in validation of fields on setting or on saving
  - Support for all index types
  - Supports graphs, traversals and all types of queries
  - Caching of documents with Insertions and Lookups in O(1)
@@ -79,7 +79,7 @@ Initialization and document saving
   conn = Connection()
 
   conn.createDatabase(name="test_db")
-  db = self.conn["test_db"] # all databases are loaded automatically into the connection and are accessible in this fashion
+  db = conn["test_db"] # all databases are loaded automatically into the connection and are accessible in this fashion
   collection = db.createCollection(name="users") # all collections are also loaded automatically
 
   # collection.delete() # self explanatory
@@ -159,9 +159,9 @@ from **Validator** and implement a **validate()** method:
       }
 
       _fields = {
-          'name': Field(validators=[VAL.NotNull(), String_val()]),
-          'anything': Field(),
-          'species': Field(validators=[VAL.NotNull(), VAL.Length(5, 15), String_val()])
+          'name': COL.Field(validators=[VAL.NotNull(), String_val()]),
+          'anything': COL.Field(),
+          'species': COL.Field(validators=[VAL.NotNull(), VAL.Length(5, 15), String_val()])
       }
 
   collection = db.createCollection('Humans')
@@ -189,17 +189,17 @@ In addition, you can also define collection properties_ (creation arguments for
       }
 
       _fields = {
-          'name': Field(validators=[VAL.NotNull(), String_val()]),
-          'anything': Field(),
-          'species': Field(validators=[VAL.NotNull(), VAL.Length(5, 15), String_val()])
+          'name': COL.Field(validators=[VAL.NotNull(), String_val()]),
+          'anything': COL.Field(),
+          'species': COL.Field(validators=[VAL.NotNull(), VAL.Length(5, 15), String_val()])
       }
 
 .. _properties: https://docs.arangodb.com/3.1/HTTP/Collection/Creating.html
 
 A note on inheritence
 ----------------------
 
-There is no inheritence of the "_validation" and "_fields" dictionaries.
+There is no inheritance of the "_validation" and "_fields" dictionaries.
 If a class does not fully define its own, the defaults will be automatically assigned to any missing value.
 
 Creating Edges
@@ -310,6 +310,50 @@ to that document are also deleted:
  # deleting one of them along with the edge
  theGraph.deleteVertex(h2)
 
+Creating a Satellite Graph
+-----------------
+
+If you want to benefit from the advantages of satellite graphs, you can also create them of course.
+Please read the official ArangoDB Documentation for further technical information.
+
+.. code:: python
+
+  from pyArango.connection import *
+  from pyArango.collection import Collection, Edges, Field
+  from pyArango.graph import Graph, EdgeDefinition
+
+  databaseName = "satellite_graph_db"
+
+  conn = Connection()
+
+  # Cleanup (if needed)
+  try:
+      conn.createDatabase(name=databaseName)
+  except Exception:
+      pass
+
+  # Select our "satellite_graph_db" database
+  db = conn[databaseName] # all databases are loaded automatically into the connection and are accessible in this fashion
+
+  # Define our vertex to use
+  class Humans(Collection):
+      _fields = {
+          "name": Field()
+      }
+
+  # Define our edge to use
+  class Friend(Edges):
+      _fields = {
+          "lifetime": Field()
+      }
+
+  # Here's how you define a Satellite Graph
+  class MySatelliteGraph(Graph) :
+      _edgeDefinitions = [EdgeDefinition("Friend", fromCollections=["Humans"], toCollections=["Humans"])]
+      _orphanedCollections = []
+
+  theSatelliteGraph = db.createSatelliteGraph("MySatelliteGraph")
+
 Document Cache
 --------------
 

examples/createSocialGraph.py

@@ -36,11 +36,11 @@ def __init__(self):
                if self.db.hasGraph('social'):
                    raise Exception("The social graph was already provisioned! remove it first")
 
-               self.female   = self.db.createCollection('Collection', "female")
-               self.male     = self.db.createCollection('Collection', "male")
-               
-               self.relation = self.db.createCollection('Edges', "relation")
-               
+               self.female   = self.db.createCollection(className='Collection', name='female')
+               self.male     = self.db.createCollection(className='Collection', name='male')
+
+               self.relation = self.db.createCollection(className='Edges', name='relation')
+
                g = self.db.createGraph("social")
 
                a = g.createVertex('female', {"name": 'Alice',  "_key": 'alice'});

examples/json_schema_validation_in_db.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+import sys
+import time
+from pyArango.connection import *
+from pyArango.graph import *
+from pyArango.collection import *
+
+def main():
+    conn = Connection(username="", password="")
+    db = conn["_system"]
+    name = "pyArangoValidation"
+
+    schema = {
+        "rule" : {
+            "properties" : {
+                "value" : {
+                    "type" : "number"
+                }
+            }
+        },
+        "level" : "strict",
+        "message" : "invalid document - schema validation failed!"
+    }
+
+    collection = None
+    if db.hasCollection(name):
+        db[name].delete() # drop
+        db.reloadCollections() # work around drop should reload...
+
+    collection = db.createCollection(
+        name = name,
+        schema = schema
+    )
+
+    try:
+        d = collection.createDocument()
+        d["value"] = "bar"
+        d.save()
+    except Exception as e:
+        print(e)
+
+    d = collection.createDocument()
+    d["value"] = 3
+    d.save()
+
+    print(collection.fetchAll())
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())

pyArango/collection.py

@@ -789,10 +789,8 @@ def bulkImport_json(self, filename, onDuplicate="error", formatType="auto", **pa
             data = f.read()
             r = self.connection.session.post(url, params = params, data = data)
 
-            try:
-                errorMessage = "At least: %d errors. The first one is: '%s'\n\n more in <this_exception>.data" % (len(data), data[0]["errorMessage"])
-            except KeyError:
-                raise UpdateError(data['errorMessage'], data)
+            if r.status_code != 201:
+                raise UpdateError('Unable to bulk import JSON', r)
 
     def bulkImport_values(self, filename, onDuplicate="error", **params):
         """bulk import from a file repecting arango's json format"""
@@ -804,10 +802,8 @@ def bulkImport_values(self, filename, onDuplicate="error", **params):
             data = f.read()
             r = self.connection.session.post(url, params = params, data = data)
 
-            try:
-                errorMessage = "At least: %d errors. The first one is: '%s'\n\n more in <this_exception>.data" % (len(data), data[0]["errorMessage"])
-            except KeyError:
-                raise UpdateError(data['errorMessage'], data)
+            if r.status_code != 201:
+                raise UpdateError('Unable to bulk import values', r)
 
     def truncate(self):
         """deletes every document in the collection"""

pyArango/database.py

@@ -143,7 +143,7 @@ def fetchDocument(self, _id):
         sid = _id.split("/")
         return self[sid[0]][sid[1]]
 
-    def createGraph(self, name, createCollections = True, isSmart = False, numberOfShards = None, smartGraphAttribute = None):
+    def createGraph(self, name, createCollections = True, isSmart = False, numberOfShards = None, smartGraphAttribute = None, replicationFactor = None, writeConcern = None):
         """Creates a graph and returns it. 'name' must be the name of a class inheriting from Graph.
         Checks will be performed to make sure that every collection mentionned in the edges definition exist. Raises a ValueError in case of
         a non-existing collection."""
@@ -171,6 +171,10 @@ def _checkCollectionList(lst):
             options['numberOfShards'] = numberOfShards
         if smartGraphAttribute:
             options['smartGraphAttribute'] = smartGraphAttribute
+        if replicationFactor:
+            options['replicationFactor'] = replicationFactor
+        if writeConcern:
+            options['writeConcern'] = writeConcern
 
         payload = {
                 "name": name,
@@ -195,6 +199,9 @@ def _checkCollectionList(lst):
             raise CreationError(data["errorMessage"], data)
         return self.graphs[name]
 
+    def createSatelliteGraph(self, name, createCollections = True):
+        return self.createGraph(name, createCollections, False, None, None, "satellite", None);
+
     def hasCollection(self, name):
         """returns true if the databse has a collection by the name of 'name'"""
         return name in self.collections
@@ -217,10 +224,15 @@ def dropAllCollections(self):
                 self[collection_name].delete()
         return
 
-    def AQLQuery(self, query, batchSize = 100, rawResults = False, bindVars = {}, options = {}, count = False, fullCount = False,
+    def AQLQuery(self, query, batchSize = 100, rawResults = False, bindVars = None, options = None, count = False, fullCount = False,
                  json_encoder = None, **moreArgs):
         """Set rawResults = True if you want the query to return dictionnaries instead of Document objects.
         You can use **moreArgs to pass more arguments supported by the api, such as ttl=60 (time to live)"""
+        if bindVars is None:
+            bindVars = {}
+        if options is None:
+            options = {}
+
         return AQLQuery(self, query, rawResults = rawResults, batchSize = batchSize, bindVars  = bindVars, options = options, count = count, fullCount = fullCount,
                         json_encoder = json_encoder, **moreArgs)
 
@@ -452,8 +464,11 @@ def no_fetch_run(
             return
         raise AQLFetchError("No results should be returned for the query.")
 
-    def explainAQLQuery(self, query, bindVars={}, allPlans = False):
+    def explainAQLQuery(self, query, bindVars = None, allPlans = False):
         """Returns an explanation of the query. Setting allPlans to True will result in ArangoDB returning all possible plans. False returns only the optimal plan"""
+        if bindVars is None:
+            bindVars = {}
+
         payload = {'query' : query, 'bindVars' : bindVars, 'allPlans' : allPlans}
         request = self.connection.session.post(self.getExplainURL(), data = json.dumps(payload, default=str))
         return request.json()
@@ -499,6 +514,14 @@ def transaction(self, collections, action, waitForSync = False, lockTimeout = No
     def __repr__(self):
         return "ArangoDB database: %s" % self.name
 
+    def __contains__(self, _id):
+        """allows to check if _id:str is the id of an existing document"""
+        col, key = _id.split('/')
+        try:
+            return key in self[col]
+        except KeyError:
+            return False
+
     def __getitem__(self, collectionName):
         """use database[collectionName] to get a collection from the database"""
         try:

pyArango/document.py

@@ -7,7 +7,12 @@ class DocumentStore(object):
     """Store all the data of a document in hierarchy of stores and handles validation.
     Does not store private information, these are in the document."""
 
-    def __init__(self, collection, validators={}, initDct={}, patch=False, subStore=False, validateInit=False):
+    def __init__(self, collection, validators=None, initDct=None, patch=False, subStore=False, validateInit=False):
+        if validators is None:
+            validators = {}
+        if initDct is None:
+            initDct = {}
+
         self.store = {}
         self.patchStore = {}
         self.collection = collection
@@ -131,7 +136,7 @@ def __dict__(self):
         return dict(self.store) + dict(self.patchStore)
 
     def __contains__(self, field):
-        return field in store
+        return field in self.store
 
     def __getitem__(self, field):
         """Get an element from the store"""

pyArango/query.py

@@ -153,8 +153,10 @@ def __init__(self, database, query, batchSize, bindVars, options, count, fullCou
         except QueryError as e:
             raise AQLQueryError( message = e.message, query = self.query, errors = e.errors)
 
-    def explain(self, bindVars={}, allPlans = False):
+    def explain(self, bindVars = None, allPlans = False):
         """Returns an explanation of the query. Setting allPlans to True will result in ArangoDB returning all possible plans. False returns only the optimal plan"""
+        if bindVars is None:
+            bindVars = {}
         return self.database.explainAQLQuery(self.query, bindVars, allPlans)
 
     def _raiseInitFailed(self, request):

pyArango/tests/tests.py

@@ -339,6 +339,16 @@ def test_document_fetch_by_key(self):
         doc2 = collection.fetchDocument(doc._key)
         self.assertEqual(doc._id, doc2._id)
 
+    def test_database_contains_id(self):
+        collection = self.db.createCollection(name="lala")
+        doc = collection.createDocument()
+        doc["name"] = 'iop'
+        doc.save()
+        result = doc["_id"] in self.db
+        self.assertTrue(result)
+        result = doc["_id"] + '1' in self.db
+        self.assertFalse(result)
+
     # @unittest.skip("stand by")
     def test_document_set_private_w_rest(self):
         collection = self.db.createCollection(name = "lala")