All geek questions in one place

Comprehensive Python JSON object for custom dictionary conversion

I have the following JSON object -

{ "Resource": [ { "@name": "Bravo", "@signature": "h#Bravo", "@type": "ESX_5.x", "@typeDisplayName": "ESX Server", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": [ { "@data": "26.00", "@end": "01:05:00", "@interval": "60", "@start": "01:04:00" }, { "@data": "24.00", "@end": "01:04:00", "@interval": "60", "@start": "01:03:00" }, { "@data": "36.00", "@end": "01:03:00", "@interval": "60", "@start": "01:02:00" }, { "@data": "38.00", "@end": "01:02:00", "@interval": "60", "@start": "01:01:00" }, { "@data": "37.00", "@end": "01:01:00", "@interval": "60", "@start": "01:00:00" } ] }, "Resource": [ { "@name": "Tango", "@signature": "vm#Tango", "@type": "vm", "@typeDisplayName": "Virtual Machine", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": { "@data": "12.00", "@end": "04:05:00", "@interval": "60", "@start": "04:04:00" } } }, { "@name": "Charlie", "@signature": "vm#Charlie", "@type": "vm", "@typeDisplayName": "Virtual Machine", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": [ { "@data": "12.00", "@end": "04:20:00", "@interval": "60", "@start": "04:19:00" }, { "@data": "12.00", "@end": "04:19:00", "@interval": "60", "@start": "04:18:00" } ] } } ] }, { "@name": "Alpha", "@signature": "h#Alpha", "@type": "ESX_5.x", "@typeDisplayName": "ESX Server", "PerfList": [ { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": { "@data": "9", "@end": "06:10:00", "@interval": "60", "@start": "06:09:00" } }, { "@attrId": "cpuUsagemhz", "@attrName": "Usage MHz", "Data": { "@data": "479", "@end": "06:10:00", "@interval": "60", "@start": "06:09:00" } } ] } ] }

I am looking for several JSON Traversal to access all keys and convert above to the next expected python dictionary -

 d = { 'ESX_5.x' : { 'Bravo' : { "@typeDisplayName" : "ESX Server", "@signature" : "h#Bravo", "cpuUsage" : { "from_01:04:00_to_01:05:00" : 26.00, "from_01:03:00_to_01:04:00" : 24.00, "from_01:02:00_to_01:03:00" : 36.00, "from_01:01:00_to_01:02:00" : 38.00, "from_01:00:00_to_01:01:00" : 37.00, "interval" : 60 }, "vm" : { "Tango" : { "@typeDisplayName" : "Virtual Machine", "@signature" : "vm#Tango", "cpuUsage" : { "from_04:04:00_to_04:05:00" : 12.00, "interval" : 60 } }, "Charlie" : { "@typeDisplayName" : "Virtual Machine", "@signature": "vm#Charlie", "cpuUsage" : { "from_04:19:00_to_04:20:00" : "12.00", "from_04:18:00_to_04:19:00" : "12.00", "@interval": "60", } } }, }, 'Alpha' : { "@typeDisplayName" : "ESX Server", "@signature" : "h#Alpha", "cpuUsage" : { "from_06:09:00_to_06:10:00" : 9, "@interval": "60" }, "cpuUsagemhz" : { "from_06:09:00_to_06:10:00" : 479, "@interval": "60" } } } }

You need recursive functions to extract resources and PerfList and data and a configuration dictionary.

There may be possible typos / syntax_errs in the expected manual dictionary ...

HERE IS MY CODE WHAT'S FURTHER - This, however, does not correspond to the N number of invested resources.

 import json class MQLPrettyPrint(): KEY_RESPONSE = 'Response' KEY_RESULTS = 'Results' KEY_RESOURCE = 'Resource' def __init__(self,file=None): self._json_file = file self._json_data = self.read_json_file() self._json_dict = self.json_to_dict() def json_file(self): return self._json_file def read_json_file(self): json_data = "" try: JSON = open(self._json_file,"r") json_data = JSON.read() JSON.close() except: raise return json_data def json_to_dict(self): return json.loads(self._json_data) def json_data(self): return self._json_data def json_dict(self): return self._json_dict def json2mql(self): for key in self._json_dict: if key == self.KEY_RESPONSE: val = self._json_dict[key] response = self.fetch_response(val) def fetch_response(self,dict): for key in dict: if key == self.KEY_RESULTS: val = dict[key] results = self.fetch_results(val) def fetch_results(self,dict): for key in dict: if key == self.KEY_RESOURCE: val = dict[key] resource = self.fetch_resource(val) def fetch_resource(self,resources,dict={}): if isinstance(resources,list): for resource in resources: print "\n\n",resource if isinstance(resource,__builtins__.dict): #header = self.fetch_resource_header(resource) #perfList = self.fetch_perf_list(resource) self.fetch_resource(resource) elif isinstance(resources,dict): header = self.fetch_resource_header(resource) perfList = self.fetch_perf_list(resource) else: print resources def fetch_resouce_header(resource): name = resource['@name'] signature = resource['@signature'] type = resource['@type'] typeDisplayName = resource['@typeDisplayName'] resource_dict = {'@name' : name, '@signature' : signature, '@type' : type, '@typeDisplayName' : typeDisplayName} return resource_dict def fetch_perf_list(self,resource,perfDict={}): perfLists = resource['PerfList'] if isinstance(perfLists,list): for perf in perfLists: self.fetch_perf_list(perf,perfDict) elif isinstance(perfLists,dict): header = self.fetch_perf_header(perf) dataList = self.fetch_data(perf) key = "" if len(perfDict) == 0: key = header['@attrId'] perfDict[key] = header perfDict[key]['Data'] = dataList else: if not perfDict.has_key(key): perfDict[key] = header perfDict[key]['Data'] = dataList else: if perfDict.has_key('Data'): perfDict[key]['Data'].update(dataList) else: perfDict[key]['Data'] = dataList else: print perfLists return perfDict def fetch_perf_header(self,perfDict): header = {} attrID = perfDict['@attrId'] attrName = perfDict['@attrName'] header = {'@attrId' : attrID, '@attrName' : attrName} return header def fetch_data(self,perfDict,dataDict={}): dataList = perfDict['Data'] if isinstance(dataList,list): for data in dataList: #Fetch internal data self.fetch_data(data,dataDict) elif isinstance(dataList,dict): start = dataList['@start'] end = dataList['@end'] interval = dataList['@interval'] data = dataList['@data'] key = "%s_%s" % (start,end) dataDict[key] = dataList #data_dict = {key : dataList} #if len(dataDict) == 0: # dataDict[key] = data_dict #else: # dataDict['Data'].update(data_dict) else: print dataList return dataDict
+4
source share
1 answer

Sometimes, when working on nested structures using recursive functions, it is easier to think in terms of a walking function and a work function. Therefore, we want to target all the dicts contained in the json structure and perform a conversion operation on them.

The transformation of the structure in place, instead of reconstructing a new one, is much easier when working with nests. A more complex approach to building nested dicts from this json structure involves the possibility of accessing specific json elements, placing them at the correct depth and branches of the new structure; this is due to two parallel running operations.

One thing to keep in mind is to change the nested structure when walking along it, since the conversion operation can change the list in which the walking function is currently running. In this case, only the children (not brothers and sisters) first change before walking along the lower branches.

 from copy import deepcopy import json from pprint import pprint from StringIO import StringIO json_str = \ ''' { "Resource": [ { "@name": "Bravo", "@signature": "h#Bravo", "@type": "ESX_5.x", "@typeDisplayName": "ESX Server", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": [ { "@data": "26.00", "@end": "01:05:00", "@interval": "60", "@start": "01:04:00" }, { "@data": "24.00", "@end": "01:04:00", "@interval": "60", "@start": "01:03:00" }, { "@data": "36.00", "@end": "01:03:00", "@interval": "60", "@start": "01:02:00" }, { "@data": "38.00", "@end": "01:02:00", "@interval": "60", "@start": "01:01:00" }, { "@data": "37.00", "@end": "01:01:00", "@interval": "60", "@start": "01:00:00" } ] }, "Resource": [ { "@name": "Tango", "@signature": "vm#Tango", "@type": "vm", "@typeDisplayName": "Virtual Machine", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": { "@data": "12.00", "@end": "04:05:00", "@interval": "60", "@start": "04:04:00" } } }, { "@name": "Charlie", "@signature": "vm#Charlie", "@type": "vm", "@typeDisplayName": "Virtual Machine", "PerfList": { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": [ { "@data": "12.00", "@end": "04:20:00", "@interval": "60", "@start": "04:19:00" }, { "@data": "12.00", "@end": "04:19:00", "@interval": "60", "@start": "04:18:00" } ] } } ] }, { "@name": "Alpha", "@signature": "h#Alpha", "@type": "ESX_5.x", "@typeDisplayName": "ESX Server", "PerfList": [ { "@attrId": "cpuUsage", "@attrName": "Usage", "Data": { "@data": "9", "@end": "06:10:00", "@interval": "60", "@start": "06:09:00" } }, { "@attrId": "cpuUsagemhz", "@attrName": "Usage MHz", "Data": { "@data": "479", "@end": "06:10:00", "@interval": "60", "@start": "06:09:00" } } ] } ] } ''' def walk_fun_lim(ilist, func=None): ''' Recursively walk a nested list and dict structure, running func on all dicts ''' def walk_fun_lim_helper(ilist, func=None, count=0): tlist = [] ttlist = [] if(isinstance(ilist, list)): ttlist = filter(lambda x: x, func(filter(lambda x: isinstance(x, dict), ilist))) if(ttlist): tlist += ttlist for q in ilist: ttlist = filter(lambda x: x, walk_fun_lim_helper(q, func, count+1)) if(ttlist): tlist += ttlist elif(isinstance(ilist, dict)): ttlist = filter(lambda x: x, func([ilist])) if(ttlist): tlist += ttlist for q in ilist: ttlist = filter(lambda x: x, walk_fun_lim_helper(ilist[q], func, count+1)) if(ttlist): tlist += ttlist return [tlist] if(count != 0) else tlist if(func != None and hasattr(func, "__call__")): return walk_fun_lim_helper(ilist, func) else: return [] def transformers_robots_in_disguise(x): for idict in x: plist = idict.pop("PerfList", []) plist = plist if(isinstance(plist, list)) else [plist] for sub_dict in plist: sub_name = sub_dict.pop("@attrId") dlist = sub_dict.pop("Data", []) dlist = dlist if(isinstance(dlist, list)) else [dlist] new_dict = {} for sub_dict in dlist: new_dict["from_%(@start)s_to_%(@end)s" % sub_dict] = sub_dict["@data"] new_dict["@interval"] = sub_dict["@interval"] idict[sub_name] = new_dict rlist = idict.pop("Resource", []) rlist = rlist if(isinstance(rlist, list)) else [rlist] for sub_dict in rlist: sub_type = sub_dict.pop("@type") sub_name = sub_dict.pop("@name") idict.setdefault(sub_type, {})[sub_name] = sub_dict return [] json_data = json.load(StringIO(json_str)) data_copy = deepcopy(json_data) walk_fun_lim(data_copy, transformers_robots_in_disguise) pprint(data_copy)
+1
source

Source: https://habr.com/ru/post/1490974/

More articles:


All Articles