#-------------------------------------------------------------------------------
# Name:  Search Directories and ID MXD Layer Sources
# Purpose:  This script runs through a mothership directory searching out MXDs
#
# Author:      John Spence, Spatial Data Administrator, City of Bellevue
#
# Created:  November 17, 2020
# Modified:
# Modification Purpose:
#
#
#
#-------------------------------------------------------------------------------


# 888888888888888888888888888888888888888888888888888888888888888888888888888888
# ------------------------------- Configuration --------------------------------
# Set the data store location for all your MXDs below.
# ShareLevel options include PUBLIC or PRIVATE.
# ShareOrg options include SHARE_ORGANIZATION or NO_SHARE_ORGANIZATION
# ShareGroups options are to place the name of a group in there.
#
# ------------------------------- Dependencies ---------------------------------
#
#
# 888888888888888888888888888888888888888888888888888888888888888888888888888888
#
# Data Store Location Where MXDs Reside
data_store_path_MXD = r"\\fileserver\data\GISPublished\Production"
#
# Where the Output will reside from the search
inCsv = r"\\fileserver\data\GISPublished\Production"
#
# File Name Pre-Fix for the Output
fileprefix = 'Production_'
#
# ------------------------------------------------------------------------------
# DO NOT UPDATE BELOW THIS LINE OR RISK DOOM AND DISPAIR!  Have a nice day!
# ------------------------------------------------------------------------------

# Import Python libraries
import arcpy, os, sys, datetime, csv
import xml.dom.minidom as DOM
import pandas as pd
#import xlsxwriter
import collections
from os import listdir
from os.path import isfile, join

arcpy.env.overwriteOutput = False

def dirWalk():

    for dirpath, dirnames, filenames in os.walk(data_store_path_MXD):
        if 'System' in dirnames:
            dirnames.remove('System')
        if 'Utilities' in dirnames:
            dirnames.remove('Utilities')
        if '.site' in dirnames:
            dirnames.remove('.site')
        if 'SampleWorldCities.MapServer' in dirnames:
            dirnames.remove('SampleWorldCities.MapServer')

        for filenames in [f for f in filenames if f.endswith(".mxd")]:
            print ("Target found:  " + os.path.join(dirpath,filenames))
            data_path_MXD = dirpath
            mxdfile = filenames
            findMXD (data_path_MXD, mxdfile, inCsv, inXLS)
    return

def findMXD(data_path_MXD, mxdfile, inCsv, inXLS):

    mxd_service_name = mxdfile
    name = mxd_service_name.replace('.mxd', '')
    currentDT = datetime.datetime.now()
    print ("Sources Task Started:  " + str(currentDT))
    print ("Source name:  " + name)
    doc = data_path_MXD + '\\' + mxdfile
    print (doc)

    mxdInfo(doc, mxd_service_name, inCsv, inXLS, data_path_MXD)
    currentDT = datetime.datetime.now()
    print ("Sources Task Completed:  " + str(currentDT) + "\n")

    return

def mxdInfo(doc, mxd_service_name, inCsv, inXLS, data_path_MXD):

    layer = []

    mxd = arcpy.mapping.MapDocument(doc)

    a = collections.OrderedDict()

    for lyr in arcpy.mapping.ListLayers(mxd):
        if lyr.supports("SERVICEPROPERTIES"):
            servProp = lyr.serviceProperties
            lName = lyr.name
            try:
                ldquery = lyr.definitionQuery
            except:
                ldquery = 'None'
            dbName = servProp.get('Database', 'N/A')
            serviceName = servProp.get('Service', 'N/A')
            serverName = serviceName.split(':')
            userName = servProp.get('UserName', 'N/A')
            workspace = lyr.supports('WORKSPACEPATH')
            try:
                dq_layer = 'True'
                dq = lyr.supports('DEFINITIONQUERY')
            except:
                dq_layer = 'False'
                dq = 'N/A'
            mxdpath = data_path_MXD
        else:
            print "SERVICEPROPERTIES not supported on " + lyr.name
            continue
        if lyr.supports("DATASOURCE"):
            dSource = str(lyr.dataSource)
            fcName = dSource.split('.sde\\')
            print "Layer Name: " + lyr.name
            try:
                print "Feature Class: " + fcName[1]
            except Exception as e:
                print "Feature Class:  Unknown issue"
                print e
        else:
            print "DATASOURCE not supported on " + lyr.name
            continue

##        a["MXD File Name"] = mxd_service_name
##        a["Layer Name"] = lName
##        a["Server"] = serverName[2]
##        a["Database"] = dbName
##        a["Feature Class"] = fcName[1]
##        a["User Name"] = userName
##        a["Definition Query"] = ldquery
##        a["Workspace"] = workspace
##        a["MXD Path"] = mxdpath
##        layer.append(a)
##
##        df_l = pd.DataFrame(layer)
##        writer = pd.ExcelWriter (inXLS, engine='xlsxwriter')
##        df_l.to_excel (writer, sheet_name='MXD Sources')
        ##writer.save()

        #write out to csv
        if not os.path.isfile(inCsv):
            csvFile = open(inCsv, 'wb')
            try:
                writer = csv.writer(csvFile)
                writer.writerow(('MXD', 'Layer Name', 'Server', 'Database', 'Feature Class', 'User Name', 'Definition Query', 'Workspace', 'MXD Path', 'Test 1', 'Test 2'))
                writer.writerow((mxd_service_name, lName, serverName[2], dbName, fcName[1], userName, ldquery, workspace, mxdpath, dq_layer, dq))
            except:
                print "error writing first row of csv"
        else:
            csvFile = open(inCsv, 'ab')
            try:
                writer = csv.writer(csvFile)
                writer.writerow((mxd_service_name, lName, serverName[2], dbName, fcName[1], userName, ldquery, workspace, mxdpath, dq_layer, dq))
            except Exception as e:
                print "error writing to csv"
                print e

    del mxd
    return


#-------------------------------------------------------------------------------
#
#
#                                 MAIN SCRIPT
#
#
#-------------------------------------------------------------------------------

inXLS = inCsv + '\\' + fileprefix + 'MXDSources_' + str(datetime.datetime.now().date()) + '.xlsx'
inCsv = inCsv + '\\' + fileprefix + 'MXDSources_' + str(datetime.datetime.now().date()) + '.csv'

dirWalk()