I have a heirarchy of tables in a MySQL 5.6 database that I need to query to a JSON format for use by a javascript tree structure.
Just as a test in my flask I did the following for just the top level
def get_all_customers():
response_object = {'status': 'success'}
cnx = mysql.connector.connect(user="", password="", database="", host="localhost", port=3306)
cursor = cnx.cursor()
cursor.execute('SELECT idx, name FROM listcustomers ORDER BY name')
data = []
for idx, name in cursor:
data.append({'id': idx, 'label':name, 'otherProp': "Customer"})
response_object['customers'] = data
return jsonify(response_object)
which returns
[
{ id: 1,
label: "customer 1",
otherProp: "Customer"
},
...
]
But each customer has locations, and each location has areas, and each area has assets, and each asset has projects, and I need to also query them into children of this json object. So, for example, just going one level deeper to locations, I would need something like this -
[
{ id: 1,
label: "customer 1",
otherProp: "Customer",
children: [
{
id: 5,
label: "location 5",
otherProp: "Location"
},
...
]
},
...
]
where in my database listlocatiosn who links to listcustomers via the it's parentCustomerId column. How can I manage this? Eventually this tree will have about 13,000 objects so I know just querying the data and then parsing it with python would be far more inefficient than if I am able to query properly to begin with.
Related
I'm having a difficult time figuring out how to pull specific information from a json file.
So far I have this:
# Import json library
import json
# Open json database file
with open('jsondatabase.json', 'r') as f:
data = json.load(f)
# assign variables from json data and convert to usable information
identifier = data['ID']
identifier = str(identifier)
name = data['name']
name = str(name)
# Collect data from user to compare with data in json file
print("Please enter your numerical identifier and name: ")
user_id = input("Numerical identifier: ")
user_name = input("Name: ")
if user_id == identifier and user_name == name:
print("Your inputs matched. Congrats.")
else:
print("Your inputs did not match our data. Please try again.")
And that works great for a simple JSON file like this:
{
"ID": "123",
"name": "Bobby"
}
But ideally I need to create a more complex JSON file and can't find deeper information on how to pull specific information from something like this:
{
"Parent": [
{
"Parent_1": [
{
"Name": "Bobby",
"ID": "123"
}
],
"Parent_2": [
{
"Name": "Linda",
"ID": "321"
}
]
}
]
}
Here is an example that you might be able to pick apart.
You could either:
Make a custom de-jsonify object_hook as shown below and do something with it. There is a good tutorial here.
Just gobble up the whole dictionary that you get without a custom de-jsonify and drill down into it and make a list or set of the results. (not shown)
Example:
import json
from collections import namedtuple
data = '''
{
"Parents":
[
{
"Name": "Bobby",
"ID": "123"
},
{
"Name": "Linda",
"ID": "321"
}
]
}
'''
Parent = namedtuple('Parent', ['name', 'id'])
def dejsonify(json_str: dict):
if json_str.get("Name"):
parent = Parent(json_str.get('Name'), int(json_str.get('ID')))
return parent
return json_str
res = json.loads(data, object_hook=dejsonify)
print(res)
# then we can do whatever... if you need lookups by name/id,
# we could put the result into a dictionary
all_parents = {(p.name, p.id) : p for p in res['Parents']}
lookup_from_input = ('Bobby', 123)
print(f'found match: {all_parents.get(lookup_from_input)}')
Result:
{'Parents': [Parent(name='Bobby', id=123), Parent(name='Linda', id=321)]}
found match: Parent(name='Bobby', id=123)
Let's say I have the following document in a MongoDB database:
{
"assist_leaders" : {
"Steve Nash" : {
"team" : "Phoenix Suns",
"position" : "PG",
"draft_data" : {
"class" : 1996,
"pick" : 15,
"selected_by" : "Phoenix Suns",
"college" : "Santa Clara"
}
},
"LeBron James" : {
"team" : "Cleveland Cavaliers",
"position" : "SF",
"draft_data" : {
"class" : 2003,
"pick" : 1,
"selected_by" : "Cleveland Cavaliers",
"college" : "None"
}
},
}
}
I'm trying to collect a few values under "draft_data" for each player in an ORDERED list. The list needs to look like the following for this particular document:
[ [1996, 15, "Phoenix Suns"], [2003, 1, "Cleveland Cavaliers"] ]
That is, each nested list must contain the values corresponding to the "pick", "selected_by", and "class" keys, in that order. I also need the "Steve Nash" data to come before the "LeBron James" data.
How can I achieve this using pymongo? Note that the structure of the data is not set in stone so I can change this if that makes the code simpler.
I'd extract the data and turn it into a list in Python, once you've retrieved the document from MongoDB:
for doc in db.collection.find():
for name, info in doc['assist_leaders'].items():
draft_data = info['draft_data']
lst = [draft_data['class'], draft_data['pick'], draft_data['selected_by']]
print name, lst
List comprehension is the way to go here (Note: don't forget .iteritems() in Python2 or .items() in Python3 or you'll get a ValueError: too many values to unpack).
import pymongo
import numpy as np
client = pymongo.MongoClient()
db = client[database_name]
dataList = [v for i in ["Steve Nash", "LeBron James"]
for key in ["class", "pick", "selected_by"]
for document in db.collection_name.find({"assist_leaders": {"$exists": 1}})
for k, v in document["assist_leaders"][i]["draft_data"].iteritems()
if k == key]
print dataList
# [1996, 15, "Phoenix Suns", 2003, 1, "Cleveland Cavaliers"]
matrix = np.reshape(dataList, [2,3])
print matrix
# [ [1996, 15, "Phoenix Suns"],
# [2003, 1, "Cleveland Cavaliers"] ]
I have retrieved remote json using urllib.request in python3 and would like to to dump, line by line, the value of the IP addresses only (ie. ip:127.0.0.1 would be 127.0.0.1, next line is next IP) if it matches certain criteria. Other key values include a score (one integer value per category) and category (one or more string values possible).
I want to check if the score is higher than, say 10, AND the category number equals a list of one OR more values. If it fits the params, I just need those IP addresses added line by line to a text file.
Here is how I retrieve the json:
ip_fetch = urllib.request.urlopen('https://testonly.com/ip.json').read().decode('utf8')
I have the json module loaded, but don't know where to go from here.
Example of json data I'm working with, more than one category:
"127.0.0.1" : {
"Test" : "10",
"Prod" : "20"
},
I wrote a simple example that should show you how to iterate trough json objects and how to write to a file:
import json
j = json.loads(test)
threshold = 10
validCategories = ["Test"]
f=open("test.txt",'w')
for ip, categories in j.items():
addToList = False
for category, rank in categories.items():
if category in validCategories and int(rank) >= threshold:
addToList = True
if addToList:
f.write("{}\n".format(ip))
f.close()
I hope that helps you to get started. For testing I used the following json-string:
test = """
{
"127.0.0.1" : {
"Test" : "10",
"Prod" : "20"
},
"127.0.0.2" : {
"Test" : "5",
"Prod" : "20"
},
"127.0.0.3" : {
"Test" : "5",
"Prod" : "5",
"Test2": "20"
}
}
"""
I have an Ecto model as such:
defmodule Project.Category do
use Project.Web, :model
schema "categories" do
field :name, :string
field :list_order, :integer
field :parent_id, :integer
belongs_to :menu, Project.Menu
has_many :subcategories, Project.Category, foreign_key: :parent_id
timestamps
end
#required_fields ~w(name list_order)
#optional_fields ~w(menu_id parent_id)
def changeset(model, params \\ :empty) do
model
|> cast(params, #required_fields, #optional_fields)
end
end
As you can see the Category model can reference itself via the subcategories atom.
Here is the view associated with this model:
defmodule Project.CategoryView do
use Project.Web, :view
def render("show.json", %{category: category}) do
json = %{
id: category.id,
name: category.name,
list_order: category.list_order
parent_id: category.parent_id
}
if is_list(category.subcategories) do
children = render_many(category.subcategories, Project.CategoryView, "show.json")
Map.put(json, :subcategories, children)
else
json
end
end
end
I have an if condition on subcategories so that I can play nice with Poison when they are not preloaded.
Finally, here are my 2 controller functions that invoke this view:
defmodule Project.CategoryController do
use Project.Web, :controller
alias Project.Category
def show(conn, %{"id" => id}) do
category = Repo.get!(Category, id)
render conn, "show.json", category: category
end
def showWithChildren(conn, %{"id" => id}) do
category = Repo.get!(Category, id)
|> Repo.preload [:subcategories, subcategories: :subcategories]
render conn, "show.json", category: category
end
end
The show function works fine:
{
"parent_id": null,
"name": "a",
"list_order": 4,
"id": 7
}
However, my showWithChildren function is limited to 2 levels of nesting because of how I use preloading:
{
"subcategories": [
{
"subcategories": [
{
"parent_id": 10,
"name": "d",
"list_order": 4,
"id": 11
}
],
"parent_id": 7,
"name": "c",
"list_order": 4,
"id": 10
},
{
"subcategories": [],
"parent_id": 7,
"name": "b",
"list_order": 9,
"id": 13
}
],
"parent_id": null,
"name": "a",
"list_order": 4,
"id": 7
}
For example, the category item 11 above also has subcategories but I am unable to reach them. Those subcategories can also have subcategories themselves, so the potential depth of the hierarchy is n.
I am aware that I need some recursive magic but since I'm new to both functional programming and Elixir, I cannot wrap my head around it. Any help is greatly appreciated.
You can consider doing the preloading in the view, so it works recursively:
def render("show.json", %{category: category}) do
%{id: category.id,
name: category.name,
list_order: category.list_order
parent_id: category.parent_id}
|> add_subcategories(category)
end
defp add_subcategories(json, %{subcategories: subcategories}) when is_list(subcategories) do
children =
subcategories
|> Repo.preload(:subcategories)
|> render_many(Project.CategoryView, "show.json")
Map.put(json, :subcategories, children)
end
defp add_subcategories(json, _category) do
json
end
Keep in mind this is not ideal for two reasons:
Ideally you don't want to do queries in views (but this is is recursive, so it is easier to piggyback in the view rendering)
You are going to emit multiple queries for the second level of subcategories
There is a book called SQL Antipatterns and, if I am not mistaken, it covers how to write tree structures. Your example is exposed as an antipattern in one of the free chapters. It is an excellent book and they explore solutions for all antipatterns.
PS: you want show_with_children and not showWithChildren.
I am using Postgres' json data type but want to do a query/ordering with data that is nested within the json.
I want to order or query with .where on the json data type. For example, I want to query for users that have a follower count > 500 or I want to order by follower or following count.
Thanks!
Example:
model User
data: {
"photos"=>[
{"type"=>"facebook", "type_id"=>"facebook", "type_name"=>"Facebook", "url"=>"facebook.com"}
],
"social_profiles"=>[
{"type"=>"vimeo", "type_id"=>"vimeo", "type_name"=>"Vimeo", "url"=>"http://vimeo.com/", "username"=>"v", "id"=>"1"},
{"bio"=>"I am not a person, but a series of plants", "followers"=>1500, "following"=>240, "type"=>"twitter", "type_id"=>"twitter", "type_name"=>"Twitter", "url"=>"http://www.twitter.com/", "username"=>"123", "id"=>"123"}
]
}
For any who stumbles upon this. I have come up with a list of queries using ActiveRecord and Postgres' JSON data type. Feel free to edit this to make it more clear.
Documentation to the JSON operators used below: https://www.postgresql.org/docs/current/functions-json.html.
# Sort based on the Hstore data:
Post.order("data->'hello' DESC")
=> #<ActiveRecord::Relation [
#<Post id: 4, data: {"hi"=>"23", "hello"=>"22"}>,
#<Post id: 3, data: {"hi"=>"13", "hello"=>"21"}>,
#<Post id: 2, data: {"hi"=>"3", "hello"=>"2"}>,
#<Post id: 1, data: {"hi"=>"2", "hello"=>"1"}>]>
# Where inside a JSON object:
Record.where("data ->> 'likelihood' = '0.89'")
# Example json object:
r.column_data
=> {"data1"=>[1, 2, 3],
"data2"=>"data2-3",
"array"=>[{"hello"=>1}, {"hi"=>2}],
"nest"=>{"nest1"=>"yes"}}
# Nested search:
Record.where("column_data -> 'nest' ->> 'nest1' = 'yes' ")
# Search within array:
Record.where("column_data #>> '{data1,1}' = '2' ")
# Search within a value that's an array:
Record.where("column_data #> '{array,0}' ->> 'hello' = '1' ")
# this only find for one element of the array.
# All elements:
Record.where("column_data ->> 'array' LIKE '%hello%' ") # bad
Record.where("column_data ->> 'array' LIKE ?", "%hello%") # good
According to this http://edgeguides.rubyonrails.org/active_record_postgresql.html#json
there's a difference in using -> and ->>:
# db/migrate/20131220144913_create_events.rb
create_table :events do |t|
t.json 'payload'
end
# app/models/event.rb
class Event < ActiveRecord::Base
end
# Usage
Event.create(payload: { kind: "user_renamed", change: ["jack", "john"]})
event = Event.first
event.payload # => {"kind"=>"user_renamed", "change"=>["jack", "john"]}
## Query based on JSON document
# The -> operator returns the original JSON type (which might be an object), whereas ->> returns text
Event.where("payload->>'kind' = ?", "user_renamed")
So you should try Record.where("data ->> 'status' = 200 ") or the operator that suits your query (http://www.postgresql.org/docs/current/static/functions-json.html).
Your question doesn't seem to correspond to the data you've shown, but if your table is named users and data is a field in that table with JSON like {count:123}, then the query
SELECT * WHERE data->'count' > 500 FROM users
will work. Take a look at your database schema to make sure you understand the layout and check that the query works before complicating it with Rails conventions.
JSON filtering in Rails
Event.create( payload: [{ "name": 'Jack', "age": 12 },
{ "name": 'John', "age": 13 },
{ "name": 'Dohn', "age": 24 }]
Event.where('payload #> ?', '[{"age": 12}]')
#You can also filter by name key
Event.where('payload #> ?', '[{"name": "John"}]')
#You can also filter by {"name":"Jack", "age":12}
Event.where('payload #> ?', {"name":"Jack", "age":12}.to_json)
You can find more about this here