ArcPy – Copying ArcSDE Geodatabase to File Geodatabase Using ArcPy

arcgis-10.1arcpydata-backupenterprise-geodatabase

I would like to make an exact copy (domains, feature datasets, feature classes, etc.) of an SDE database to a file geodatabase.

I have tried several possibilities, including:

  1. using the Copy (Data Management) process
  2. creating a new GDB and manually copying each feature dataset from
    the SDE
  3. exporting an xml workspace document from the SDE and importing it
    into the GDB

The Copy_management process does not seem like it would work for copying an SDE to a GDB, since the input and output data types must match.

The process of importing each feature dataset into a new GDB could probably be automated using Copy_management as well by iterating through each feature dataset, though it seems this could cause problems of an incomplete copy if there was an error with one of the processes.

Exporting and importing xml workspaces seems to work, though this process creates incredibly large files when the process is used on large geodatabases.

Is there a more straightforward way to copy the contents and schema of an SDE to a GDB than the ways mentioned, in a way that can be automated?

If not, are there any reasons that the above possibilities should not be used in this process?

Best Answer

I know this post is a little old but I though I would share my answer since I was faced with the same issue. The following script SHOULD copy all tables, feature classes and relationships not in a dataset and also will copy over all datasets including the feature classes, topology, etc within the dataset. It will skip over any errors durring the copy adn keep going. It will produce a log file that contains data such as the source DB item count and the destination item count so you can compare the copy and it will log errors it encounters as well.

import arcpy, os, shutil, time
import logging as log
from datetime import datetime

def formatTime(x):
    minutes, seconds_rem = divmod(x, 60)
    if minutes >= 60:
        hours, minutes_rem = divmod(minutes, 60)
        return "%02d:%02d:%02d" % (hours, minutes_rem, seconds_rem)
    else:
        minutes, seconds_rem = divmod(x, 60)
        return "00:%02d:%02d" % (minutes, seconds_rem)

def getDatabaseItemCount(workspace):
    arcpy.env.workspace = workspace
    feature_classes = []
    for dirpath, dirnames, filenames in arcpy.da.Walk(workspace,datatype="Any",type="Any"):
        for filename in filenames:
            feature_classes.append(os.path.join(dirpath, filename))
    return feature_classes, len(feature_classes)

def replicateDatabase(dbConnection, targetGDB):
    startTime = time.time()

    featSDE,cntSDE = getDatabaseItemCount(dbConnection)
    featGDB,cntGDB = getDatabaseItemCount(targetGDB)

    now = datetime.now()
    logName = now.strftime("SDE_REPLICATE_SCRIPT_%Y-%m-%d_%H-%M-%S.log")
    log.basicConfig(datefmt='%m/%d/%Y %I:%M:%S %p', format='%(asctime)s %(message)s',\
    filename=logName,level=log.INFO)

    print "Old Target Geodatabase: %s -- Feature Count: %s" %(targetGDB, cntGDB)
    log.info("Old Target Geodatabase: %s -- Feature Count: %s" %(targetGDB, cntGDB))
    print "Geodatabase being copied: %s -- Feature Count: %s" %(dbConnection, cntSDE)
    log.info("Geodatabase being copied: %s -- Feature Count: %s" %(dbConnection, cntSDE))

    arcpy.env.workspace = dbConnection

    #deletes old targetGDB
    try:
        shutil.rmtree(targetGDB)
        print "Deleted Old %s" %(os.path.split(targetGDB)[-1])
        log.info("Deleted Old %s" %(os.path.split(targetGDB)[-1]))
    except Exception as e:
        print e
        log.info(e)

    #creates a new targetGDB
    GDB_Path, GDB_Name = os.path.split(targetGDB)
    print "Now Creating New %s" %(GDB_Name)
    log.info("Now Creating New %s" %(GDB_Name))
    arcpy.CreateFileGDB_management(GDB_Path, GDB_Name)

    datasetList = [arcpy.Describe(a).name for a in arcpy.ListDatasets()]
    featureClasses = [arcpy.Describe(a).name for a in arcpy.ListFeatureClasses()]
    tables = [arcpy.Describe(a).name for a in arcpy.ListTables()]

    #Compiles a list of the previous three lists to iterate over
    allDbData = datasetList + featureClasses + tables

    for sourcePath in allDbData:
        targetName = sourcePath.split('.')[-1]
        targetPath = os.path.join(targetGDB, targetName)
        if arcpy.Exists(targetPath)==False:
            try:
                print "Atempting to Copy %s to %s" %(targetName, targetPath)
                log.info("Atempting to Copy %s to %s" %(targetName, targetPath))
                arcpy.Copy_management(sourcePath, targetPath)
                print "Finished copying %s to %s" %(targetName, targetPath)
                log.info("Finished copying %s to %s" %(targetName, targetPath))
            except Exception as e:
                print "Unable to copy %s to %s" %(targetName, targetPath)
                print e
                log.info("Unable to copy %s to %s" %(targetName, targetPath))
                log.info(e)
        else:
            print "%s already exists....skipping....." %(targetName)
            log.info("%s already exists....skipping....." %(targetName))
    featGDB,cntGDB = getDatabaseItemCount(targetGDB)
    print "Completed replication of %s -- Feature Count: %s" %(dbConnection, cntGDB)
    log.info("Completed replication of %s -- Feature Count: %s" %(dbConnection, cntGDB))
    totalTime = (time.time() - startTime)
    totalTime = formatTime(totalTime)
    log.info("Script Run Time: %s" %(totalTime))

if __name__== "__main__":
    databaseConnection = r"YOUR_SDE_CONNECTION"
    targetGDB = "DESTINATION_PATH\\SDE_Replicated.gdb"
    replicateDatabase(databaseConnection, targetGDB)   

I had really good luck with this. I was replicating an SDE database to a file geodatabase. I haven't done too extensive of testing on this script though since it fulfilled all my needs. I tested it using ArcGIS 10.3. Also, one thing to note, I was in talks with someone that has used this script and they ran into an issue with an error copying certain datasets due to improper permissions and empty tables.

Lemur - why not create your relationships based to a global id instead of the object id? That you your relationships would be preserved. If you haven't created global id's I would highly recommend it.

-update

I added a little more logic into the code to handle bad database connection paths and better logging and error handling:

import time, os, datetime, sys, logging, logging.handlers, shutil
import arcpy

########################## user defined functions ##############################

def getDatabaseItemCount(workspace):
    log = logging.getLogger("script_log")
    """returns the item count in provided database"""
    arcpy.env.workspace = workspace
    feature_classes = []
    log.info("Compiling a list of items in {0} and getting count.".format(workspace))
    for dirpath, dirnames, filenames in arcpy.da.Walk(workspace,datatype="Any",type="Any"):
        for filename in filenames:
            feature_classes.append(os.path.join(dirpath, filename))
    log.info("There are a total of {0} items in the database".format(len(feature_classes)))
    return feature_classes, len(feature_classes)

def replicateDatabase(dbConnection, targetGDB):
    log = logging.getLogger("script_log")
    startTime = time.time()

    if arcpy.Exists(dbConnection):
        featSDE,cntSDE = getDatabaseItemCount(dbConnection)
        log.info("Geodatabase being copied: %s -- Feature Count: %s" %(dbConnection, cntSDE))
        if arcpy.Exists(targetGDB):
            featGDB,cntGDB = getDatabaseItemCount(targetGDB)
            log.info("Old Target Geodatabase: %s -- Feature Count: %s" %(targetGDB, cntGDB))
            try:
                shutil.rmtree(targetGDB)
                log.info("Deleted Old %s" %(os.path.split(targetGDB)[-1]))
            except Exception as e:
                log.info(e)

        GDB_Path, GDB_Name = os.path.split(targetGDB)
        log.info("Now Creating New %s" %(GDB_Name))
        arcpy.CreateFileGDB_management(GDB_Path, GDB_Name)

        arcpy.env.workspace = dbConnection

        try:
            datasetList = [arcpy.Describe(a).name for a in arcpy.ListDatasets()]
        except Exception, e:
            datasetList = []
            log.info(e)
        try:
            featureClasses = [arcpy.Describe(a).name for a in arcpy.ListFeatureClasses()]
        except Exception, e:
            featureClasses = []
            log.info(e)
        try:
            tables = [arcpy.Describe(a).name for a in arcpy.ListTables()]
        except Exception, e:
            tables = []
            log.info(e)

        #Compiles a list of the previous three lists to iterate over
        allDbData = datasetList + featureClasses + tables

        for sourcePath in allDbData:
            targetName = sourcePath.split('.')[-1]
            targetPath = os.path.join(targetGDB, targetName)
            if not arcpy.Exists(targetPath):
                try:
                    log.info("Atempting to Copy %s to %s" %(targetName, targetPath))
                    arcpy.Copy_management(sourcePath, targetPath)
                    log.info("Finished copying %s to %s" %(targetName, targetPath))
                except Exception as e:
                    log.info("Unable to copy %s to %s" %(targetName, targetPath))
                    log.info(e)
            else:
                log.info("%s already exists....skipping....." %(targetName))

        featGDB,cntGDB = getDatabaseItemCount(targetGDB)
        log.info("Completed replication of %s -- Feature Count: %s" %(dbConnection, cntGDB))

    else:
        log.info("{0} does not exist or is not supported! \
        Please check the database path and try again.".format(dbConnection))

#####################################################################################

def formatTime(x):
    minutes, seconds_rem = divmod(x, 60)
    if minutes >= 60:
        hours, minutes_rem = divmod(minutes, 60)
        return "%02d:%02d:%02d" % (hours, minutes_rem, seconds_rem)
    else:
        minutes, seconds_rem = divmod(x, 60)
        return "00:%02d:%02d" % (minutes, seconds_rem)

if __name__ == "__main__":
    startTime = time.time()
    now = datetime.datetime.now()

    ############################### user variables #################################
    '''change these variables to the location of the database being copied, the target 
    database location and where you want the log to be stored'''

    logPath = ""
    databaseConnection = "path_to_sde_or_gdb_database"
    targetGDB = "apth_to_replicated_gdb\\Replicated.gdb"

    ############################### logging items ###################################
    # Make a global logging object.
    logName = os.path.join(logPath,(now.strftime("%Y-%m-%d_%H-%M.log")))

    log = logging.getLogger("script_log")
    log.setLevel(logging.INFO)

    h1 = logging.FileHandler(logName)
    h2 = logging.StreamHandler()

    f = logging.Formatter("[%(levelname)s] [%(asctime)s] [%(lineno)d] - %(message)s",'%m/%d/%Y %I:%M:%S %p')

    h1.setFormatter(f)
    h2.setFormatter(f)

    h1.setLevel(logging.INFO)
    h2.setLevel(logging.INFO)

    log.addHandler(h1)
    log.addHandler(h2)

    log.info('Script: {0}'.format(os.path.basename(sys.argv[0])))

    try:
        ########################## function calls ######################################

        replicateDatabase(databaseConnection, targetGDB)

        ################################################################################
    except Exception, e:
        log.exception(e)

    totalTime = formatTime((time.time() - startTime))
    log.info('--------------------------------------------------')
    log.info("Script Completed After: {0}".format(totalTime))
    log.info('--------------------------------------------------')