def getCommonDatesLocations(iterator,metadata,times,locations,dimensions,k):
vNInd = '0'
overallDateFormat = iterator.overallDateFormat if hasattr(iterator,'overallDateFormat') else ''
dateFormat = iterator.dateFormat if hasattr(iterator,'dateFormat') else ''
overallDate = iterator.overallDate if hasattr(iterator,'overallDate') else ''
if overallDateFormat or dateFormat:
DF = overallDateFormat + dateFormat
F = td.mongotimeformatter(DF)
T1 = [F(overallDate + x) for x in iterator.columnGroups['timeColNames'] if x in dimensions[k]]
if overallDateFormat:
reverseF = td.reverse(dateFormat)
T2 = [F(overallDate + y) for y in map(reverseF,times[k])]
else:
T2 = times[k]
mindate = min(T1 + T2)
maxdate = max(T1 + T2)
divisions = uniqify(ListUnion([td.getLowest(t) for t in T1 + T2]))
metadata[k]['beginDate'] = mindate
metadata[k]['endDate'] = maxdate
metadata[k]['dateDivisions'] = divisions
#locations
if locations[k]:
if hasattr(iterator,'overallLocation'):
locs = [loc.integrate(iterator.overallLocation,l) for l in locations[k]]
else:
locs = locations[k]
locs = locListUniqify(locs)
metadata[k]['spatialDivisions'] = uniqify(ListUnion([loc.divisions(x) for x in locs]))
metadata[k]['commonLocation'] = reduce(loc.intersect,locs)
def initialize_argdict(collection):
d = {} ; ArgDict = {}
sliceCols = uniqify(Flatten(collection.sliceCols))
sliceColList = ListUnion([[x] if x.split('.')[0] in collection.columns else collection.columnGroups.get(x,[]) for x in sliceCols])
if hasattr(collection,'contentCols'):
contentColList = ListUnion([[x] if x.split('.')[0] in collection.columns else collection.columnGroups.get(x,[]) for x in collection.contentCols])
contentCols = uniqify(contentColList + sliceColList)
else:
contentCols = sliceColList
contentColNums = getStrs(collection,contentCols)
ArgDict['contentColNums'] = contentColNums
if hasattr(collection,'dateFormat'):
dateFormat = collection.dateFormat
ArgDict['overallDateFormat'] = dateFormat
timeFormatter = td.mongotimeformatter(dateFormat)
ArgDict['timeFormatter'] = timeFormatter
else:
dateFormat = ''
if hasattr(collection,'overallDate'):
od = collection.overallDate['date']
odf = collection.overallDate['format']
ArgDict['overallDate'] = od
overallDateFormat = odf + dateFormat
ArgDict['overallDateFormat'] = overallDateFormat
timeFormatter = td.mongotimeformatter(overallDateFormat)
ArgDict['timeFormatter'] = timeFormatter
OD = timeFormatter(overallDate +'X'*len(dateFormat))
ArgDict['dateDivisions'] = td.getLowest(OD)
ArgDict['datePhrases'] = [td.phrase(OD)]
ArgDict['mindate'] = OD
ArgDict['maxdate'] = OD
if dateFormat:
reverseTimeFormatter = td.reverse(dateFormat)
ArgDict['reverseTimeFormatter'] = reverseTimeFormatter
else:
od = ''
if 'timeColNames' in collection.columnGroups.keys():
timeColNamesInd = getNums(collection,collection.columnGroups['timeColNames'])
tcs = [timeFormatter(od + t) for t in collection.columnGroups['timeColNames']]
ArgDict['timeColNames'] = tcs
ArgDict['timeColNameInds'] = timeColNamesInd
ArgDict['timeColNameDivisions'] = [[td.TIME_DIVISIONS[x] for x in td.getLowest(tc)] for tc in tcs]
ArgDict['timeColNamePhrases'] = [td.phrase(t) for t in tcs]
if 'timeColumns' in collection.columnGroups.keys():
ArgDict['timeColInds'] = getNums(collection,collection.columnGroups['timeColumns'])
#overall location
if hasattr(collection,'overallLocation'):
ol = collection.overallLocation
ArgDict['overallLocation'] = ol
else:
ol = None
#get divisions and phrases from OverallLocation and SpaceColNames
if 'spaceColNames' in collection.columnGroups.keys():
spaceColNames = collection.columnGroups['spaceColNames']
ArgDict['spaceColNames'] = [loc.integrate(ol,x) for x in spaceColNames]
if 'spaceColumns' in collection.columnGroups.keys():
ArgDict['spaceColInds'] = getNums(collection,collection.columnGroups['spaceColumns'])
Source = collection.source
SourceNameDict = son.SON([(k,Source[k]['name'] if isinstance(Source[k],dict) else Source[k]) for k in Source.keys()])
SourceAbbrevDict = dict([(k,Source[k]['shortName']) for k in Source.keys() if isinstance(Source[k],dict) and 'shortName' in Source[k].keys() ])
d['sourceSpec'] = json.dumps(SourceNameDict,default=ju.default)
d['agency'] = SourceNameDict['agency']
d['subagency'] = SourceNameDict['subagency']
d['dataset'] = SourceNameDict['dataset']
for k in SourceNameDict.keys():
d['source_' + str(k).lower()] = SourceNameDict[k]
for k in SourceAbbrevDict.keys():
d['source_' + str(k).lower() + '_acronym'] = SourceAbbrevDict[k]
d['source'] = ' '.join(SourceNameDict.values() + SourceAbbrevDict.values())
if 'subcollections' in collection.columns:
ArgDict['subColInd'] = collection.columns.index('subcollections')
value_processor_instructions = stringifyDictElements(collection.valueProcessors)
vpcontext = commonjs.translatorContext(value_processor_instructions)
ArgDict['valueProcessors'],ArgDict['valueProcessorsKey'] = get_processors(value_processor_instructions,collection, vpcontext ,commonjs.js_call)
return d, ArgDict
