The built-in compare tool seems to be designed to check two featureclasses after a copy and edit.I cannot see the point of stopping after find the first difference without saying which one.What we really need is a compare using a static key (which used to be called the user-id).The fastest way to do this uses the Python Set operations which run in milliseconds.But first you have to create the set for each of the featureclasses which takes some time with a SearchCursor.This only takes a few seconds.Finally you need to create a selection or new featureclass containing the deletes/adds/changes.This is easy enough but a bit slower, taking perhaps minutes. Use an SQL query using IN (list_of_keys)You need to keep track of the primary key for each feature. Do this using a Dictionary keyed with the key and containing all the attributes that you want to compare. Comparing shapes is difficult because it requires them to be in a standalone object so you have to unpack the shape field into a Python string. Instead use the area or length as a proxy for the shape and round it to a suitable precision eg int(round(row.shape.area)*100))#NAME: delta_road.py
#AUTHOR: Kevin Bell
#EMAIL: kevin.bell@slcgov.com
#DATE: 20071207
# edited by Kim Ollivier
#PURPOSE: create adds/deletes layer files by comparing 2 point
# feature classes shape and attributes. If the shape has
# not changed, but any of the attributes have, the feature
# will show as a delete, and an add.
#NOTE: buildDict method has hard coded primary key and attribute names.
# mods :
# use sets for del/add
# write out featureclass differences
# do not use centroid for lines, they have changed in a year! suggest length
# do not use shape for non-points
# dont forget to index keys for definition layers
def buildDeltaLayers(inFC1, inFC2):
'''build an adds and deletes lyr for a given chrono FC '''
print inFC1, inFC2
d1 = buildDict(inFC1)
d2 = buildDict(inFC2)
# find set differences and intersections to reduce dictionary comparisons
startTime = time.clock()
s1 = set(d1.keys())
s2 = set(d2.keys())
sNew = s2 - s1
print "New",len(sNew)
sDel = s1 - s2
print "Del",len(sDel)
sInt = s1.intersection(s2)
print "Int",len(sInt)
print "sets done"
stopTime = time.clock()
elapsedTime = stopTime - startTime
print "elapsed time = " + str(round(elapsedTime, 1)) + " seconds"
# could weed the dictionaries but will that be slower than just using the intersection set?
compareList = valuesChanged(d1,d2,sInt)
print "Changes",len(compareList)
stopTime = time.clock()
elapsedTime = stopTime - startTime
print "elapsed time = " + str(round(elapsedTime, 1)) + " seconds"
changes = len(compareList)
if changes > 0 and changes < 50000:
print "Changes to be written",changes
makeLYR(inFC2, compareList, "rdchg")
else :
print "no changes, or too many to be believed",changes
# must create delete layer first
# to allow new features to be filtered for ID renumbering
if len(sDel) > 0 :
makeLYR(inFC1, sDel,"rddel")
if len(sNew) > 0 :
makeLYR(inFC2, sNew,"rdnew")
def valuesChanged(dict1, dict2,sBoth):
'''get a list of keys from one dict if a corresponding dict's values are different'''
## outList = [key for key in set(dict1.keys() + dict2.keys()) if dict1.get(key) != dict2.get(key)]
outList = [key for key in sBoth if dict1.get(key) != dict2.get(key)]
return outList
def buildDict(inputFC): #-----BEWARE OF HARDCODED PRIMARY KEY AND ATTRIBUTES BELOW!!!!!
'''Build a dictionary of the primary key, and its fields'''
startTime = time.clock()
d = {}
cur = gp.SearchCursor(inputFC)
row = cur.Next()
while row:
# only need to check primary keys and shape
# oops row.shape.centroid always fails - why?? because its only an object reference
# you have to get out the coordinates and put it in a real Python object
d[row.GetValue(pk)] = [row.name.upper().strip() ]#, round(row.shape.length)]
# d[row.GetValue(pk)] = [round(row.shape.length)]
row = cur.Next()
del cur
print inputFC,
stopTime = time.clock()
elapsedTime = stopTime - startTime
print "dict created, elapsed time = " + str(round(elapsedTime, 1)) + " seconds"
return d
def makeLYR(fc, inList, outLyrName): # BEWARE OF HARDCODED PRIMARY KEY BELOW
'''Given a list, return a LYR file'''
startTime = time.clock()
wc = str(tuple(inList))
print outLyrName,len(inList)
whereclause = pk+" IN " + wc # <----IF DATA ISN'T FILE GDB, YOU MAY NEED QUOTES/BRACKETS
# print whereclause
gp.MakeFeatureLayer_management (fc, outLyrName, whereclause)
print outLyrName,"ORIG layer count",gp.GetCount(outLyrName).GetOutput(0)
# remove changes of just RCL_ID
if outLyrName == 'rdnew':
print "RDDEL layer count",gp.GetCount("rddel").GetOutput(0)
gp.SelectLayerByLocation_management(outLyrName, "WITHIN", "rddel","","REMOVE_FROM_SELECTION")
print "Made NEW layer",outLyrName,round(time.clock() - startTime)," seconds"
print outLyrName,"NEW layer count",gp.GetCount(outLyrName).GetOutput(0)
gp.RefreshCatalog(delta_gdb)
print outLyrName,"layer count",gp.GetCount(outLyrName).GetOutput(0)
layerfn = os.path.dirname(delta_gdb)+"/"+outLyrName +".lyr"
if gp.Exists(layerfn) :
gp.Delete(layerfn)
##gp.SaveToLayerFile_management(outLyrName, layerfn)
# print "saved layer",round(time.clock() - startTime)
deltaFC = delta_gdb+"/"+outLyrName
# Warning, featureclass MUST be indexed on PK!
if not gp.Exists(fc) :
print fc,"not found"
## gp.AddIndex_management(fc,pk,fc+"_"+pk+"_idx")
if gp.Exists(deltaFC):
gp.Delete(deltaFC)
gp.CopyFeatures_management(outLyrName,deltaFC)
stopTime = time.clock()
elapsedTime = stopTime - startTime
print outLyrName,"elapsed time = " + str(round(elapsedTime, 1)) + " seconds"
#----------------------------------------------------------------------
print "----------- delta road ----------------"
import arcgisscripting, time,os,sys
gp = arcgisscripting.create(9.3)
gp.overwriteoutput = True
try :
last_gdb = sys.argv[1]
current_gdb = sys.argv[2]
delta_gdb = sys.argv[3]
except :
last_gdb = "E:/road_jan2009.gdb"
current_gdb = "e:/crs/mobile/mobile.gdb"
delta_gdb = "E:/crs/road_roadname.gdb"
if not os.path.exists(delta_gdb) :
gp.CreateFileGDB_management(os.path.dirname(delta_gdb), os.path.basename(delta_gdb))
gp.Workspace = delta_gdb
gp.OverwriteOutput = 1
print
for laydef in [["road","RCL_ID"]] :
layer = laydef[0]
pk = laydef[1]
startTime = time.clock()
print "Start"
old = last_gdb+"/"+layer
new = current_gdb+"/"+layer
ready = True
if not gp.Exists(old) :
print old,'not found'
ready = False
if not gp.Exists(new) :
print new,'not found'
ready = False
if ready :
buildDeltaLayers(old,new)
msg = "Your del/change/add fc's are in:"
gp.AddMessage(msg)
print str(gp.workspace)
gp.AddMessage(str(gp.workspace))
stopTime = time.clock()
elapsedTime = stopTime - startTime
print layer,"total elapsed time = " + str(round(elapsedTime, 1)) + " seconds"
else :
print "not ready"
# del gp
print "-------------------------------------------------------------"
gp.AddMessage("finished")
