Kode

Skrip ini berguna untuk mengaudit metadata. Skrip ini dapat dijalankan di beberapa geodatabase enterprise, dan akan membuat file CSV keluaran dengan kolom berikut: 'Geodatabase', 'Set Data Fitur', 'Kelas Fitur', 'Referensi Spasial', 'Jumlah Baris', 'Jumlah Kolom', 'Judul Metadata', 'Deskripsi Metadata', 'Ringkasan Metadata', 'Kredit Metadata', 'Metadata Batasan Akses'.

Untuk menggunakan skrip ini, Anda perlu mengubah Baris 19 agar menunjuk ke file koneksi SDE Anda.

import csv
import os

from arcpy import Describe
from arcpy import env
from arcpy import GetCount_management
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy import metadata as md

# the output CSV file name
output_csv_file = 'enterprise_gdbs_results.csv'

# or use this to make the output CSV file name the same as the script name
# output_csv_file = os.path.basename(__file__).replace('.py','.csv')

# change this path to use your SDE connection files
sde_connection_files = 'c:/gis/sde_connection_files'

with open(output_csv_file,'w',newline='') as csv_file:
    csv_writer = csv.writer(csv_file, delimiter=',')
    column_headers = [
        'Geodatabase', 'Feature Dataset', 'Feature Class', 
        'Spatial Reference', 'Row Count', 'Column Count', 
        'Metadata Title', 'Metadata Description', 'Metadata Summary',
        'Metadata Credits', 'Metadata Access Constraints'
    ]
    
    csv_writer.writerow(column_headers)

    for (folder, dirs, files) in os.walk(sde_connection_files):
        for file in files:
            if(not file.startswith('_') and file.endswith('.sde')):
                geodatabase = file.split('@')[1]

                wksp = os.path.join(folder,file)
                env.workspace = wksp

                datasets = ListDatasets(feature_type='feature')
                datasets = [''] + datasets if datasets is not None else []

                for dataset in datasets:
                    for feature_class in ListFeatureClasses(dataset):
                        desc = Describe(feature_class)
                        spatial_reference = desc.SpatialReference.factoryCode
                        count = GetCount_management(feature_class)[0]
                        column_count = len(ListFields(feature_class))
                        metadata = md.Metadata(feature_class)

                        row = [
                            geodatabase,dataset,feature_class,
                            spatial_reference,count,column_count,
                            metadata.title,metadata.description,
                            metadata.summary,metadata.credits,
                            metadata.accessConstraints    
                        ]

                        print(row)
                        
                        csv_writer.writerow(row)

Skrip ini berguna untuk mengaudit metadata. Skrip dapat dijalankan di beberapa file geodatabases, dan akan membuat file CSV keluaran dengan kolom berikut: 'Terakhir Dimodifikasi','File Geodatabase', 'Set Data Fitur', 'Kelas Fitur', 'Referensi Spasial', 'Jumlah Baris', 'Jumlah Kolom', 'Judul Metadata', 'Deskripsi Metadata', 'Ringkasan Metadata', 'Metadata Kredit', 'Batasan Akses Metadata'.

import csv
import os
import time

from arcpy import Describe
from arcpy import env
from arcpy import GetCount_management
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy import metadata as md

folder = r'...'
log = open('log.txt', 'w')
output_csv_file = os.path.basename(__file__).replace('.py','.csv')

with open(output_csv_file,'w',newline='') as csv_file:
    csv_writer = csv.writer(csv_file, delimiter=',')
    column_headers = [
        'Last Modified','File Geodatabase', 'Feature Dataset', 'Feature Class', 
        'Spatial Reference', 'Row Count', 'Column Count', 
        'Metadata Title', 'Metadata Description', 'Metadata Summary',
        'Metadata Credits', 'Metadata Access Constraints'
    ]
    
    csv_writer.writerow(column_headers)

    for (folder, dirs, files) in os.walk(folder):
        if(folder.endswith('.gdb')):
            print(folder)

            last_modified = '???'

            try:
                last_modified = time.ctime(max(os.stat(root).st_mtime for root,_,_ in os.walk(folder)))
            except:
                msg = 'Error getting last modified date for {}'.format(folder)
                print(msg)
                log.write('{}\n'.format(msg))
                pass

            fgdb = folder
            env.workspace = fgdb

            datasets = []

            try:
                datasets = ListDatasets(feature_type='feature')
                datasets = [''] + datasets if datasets is not None else []
            except:
                msg = 'Error getting datasets for {}'.format(folder)
                print(msg)
                log.write('{}\n'.format(msg))
                pass

            for dataset in datasets:
                for feature_class in ListFeatureClasses(dataset):
                    desc = Describe(feature_class)
                    spatial_reference = desc.SpatialReference.factoryCode
                    count = GetCount_management(feature_class)[0]
                    column_count = len(ListFields(feature_class))
                
                    metadata = None
                    row = []

                    try:
                        metadata = md.Metadata(feature_class)
                        row = [
                            last_modified,
                            fgdb,dataset,feature_class,
                            spatial_reference,count,column_count,
                            metadata.title,metadata.description,
                            metadata.summary,metadata.credits,
                            metadata.accessConstraints    
                        ]
                    except:
                        row = [
                            last_modified,
                            fgdb,dataset,feature_class,
                            spatial_reference,count,column_count,
                            'error','error','error','error','error'    
                        ]
                        pass

                    csv_writer.writerow(row)

log.close()

Terkadang saat data dikonversi dari shapefile ke kelas fitur, atau jika tidak hati-hati saat menjalankan alat geoproses, kelas fitur bisa berakhir dengan kolom yang mubazir. Misalnya, kelas fitur bisa memiliki bidang bernama "OBJECTID" dan mungkin ada bidang lain bernama "OBJECTID_1" di kelas fitur yang sama. Salah satu bidang ini harusnya adalah bidang OID untuk kelas fitur, namun terkadang tidak jelas bidang OBJECTID mana yang benar. Script di bawah ini tidak perlu mengetahui field mana yang merupakan field OID karena Baris 35 akan gagal jika field tersebut tidak dapat dihapus, dan skrip akan terus berjalan. Skrip di bawah ini menunjukkan dua cara berbeda untuk memeriksa nama bidang, yaitu nama bidang dapat dimasukkan ke dalam daftar pada Baris 10, atau nama bidang dapat diawali dengan "OBJECTID" pada Baris 33. Untuk skrip ini, bidang yang dihapus akan ditampilkan ke file CSV. Nama file CSV keluaran sama dengan nama skrip Python - lihat Baris 12. Sebelum menjalankan skrip, sebaiknya beri komentar pada Baris 35, jalankan skrip, dan periksa file CSV keluaran untuk melihat bidang mana yang akan dihapus. Selain itu, setelah dihapus, kolom tersebut tidak dapat dipulihkan, jadi jika ragu, file geodatabases harus dicadangkan terlebih dahulu.

import csv
import os

from arcpy import env
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy import ListFields
from arcpy.management import DeleteField

fields_to_delete = ['objectid', 'objectid_1', 'objectid_12', 'shape_le_1', 'shape_leng', 'shape_length', 'shape__length', 'shape__area']
input_folder = r'...'
output_csv_file = os.path.basename(__file__).replace('.py','.csv')

with open(output_csv_file, 'w', newline='') as csv_file:
    csv_writer = csv.writer(csv_file)
    csv_writer.writerow(['File Geodatabase','Feature Dataset', 'Feature Class', 'Field'])

    for (folder, dirs, files) in os.walk(input_folder):
        if(folder.endswith('.gdb')):
            file_geodatabase = folder
            print('Processing {}'.format(file_geodatabase))

            env.workspace = file_geodatabase

            feature_datasets = ListDatasets(feature_type='feature')
            feature_datasets = [''] + feature_datasets if feature_datasets is not None else []

            for feature_dataset in feature_datasets:
                feature_classes = ListFeatureClasses(feature_dataset=feature_dataset)

                for feature_class in feature_classes:
                    for field in ListFields(feature_class):
                        if field.name.lower() in fields_to_delete or field.name.lower().startswith('objectid'):
                            try:
                                DeleteField(feature_class, field.name)
                                csv_writer.writerow([file_geodatabase, feature_dataset, feature_class, field.name])
                            
                            except:
                                pass

Sebelum memublikasikan layanan peta atau layanan fitur, sebaiknya hitung ulang luasan kelas fitur terlebih dahulu. Hal ini karena terkadang cakupan kelas fitur bisa saja salah. Ada beberapa hal yang dapat menyebabkan luasan kelas fitur salah, antara lain menjalankan tugas geoproses pada data yang mengubah luasan data, dan luasan kelas fitur juga bisa salah saat mengimpor data karena luasan kelas fitur awal mungkin telah dihitung berdasarkan subset data yang diimpor. Cara mudah pertama untuk melihat kesalahan tingkat kelas fitur adalah ketika mengklik tombol zoom-to-layer, peta tidak memperbesar ke tingkat yang benar. Tanda lain bahwa luas lapisan salah adalah lapisan tersebut tidak ditampilkan dengan benar. Misalnya, saat mengimpor file GeoJSON berukuran besar, file tersebut mungkin tidak ditampilkan dengan benar di ArcGIS Pro hingga luasnya dihitung ulang untuk kelas fitur tersebut.

import os

from arcpy import env
from arcpy import ListDatasets
from arcpy import ListFeatureClasses
from arcpy.management import RecalculateFeatureClassExtent

input_folder = r'...'

for (folder, dirs, files) in os.walk(input_folder):
    if(folder.endswith('.gdb')):
        env.workspace = folder

        feature_datasets = ListDatasets(feature_type='feature')
        feature_datasets = [''] + feature_datasets if feature_datasets is not None else []

        for feature_dataset in feature_datasets:
            feature_classes = ListFeatureClasses(feature_dataset=feature_dataset)

            for feature_class in feature_classes:
                print('{}\t{}\t{}'.format(folder, feature_dataset, feature_class))
                RecalculateFeatureClassExtent(feature_class)

Skrip ini untuk membuat daftar semua shapefile dalam direktori untuk membantu memahami berapa banyak shapefile yang Anda miliki, sehingga mereka dapat dimigrasikan ke kelas fitur dalam geodatabase file atau geodatabase perusahaan. Perhatikan bahwa shapefile umumnya harus dihindari karena beberapa alasan. Format shapefile adalah format yang sangat lama dan ada format yang jauh lebih baik untuk berbagi data spasial. Shapefile memiliki kompresi yang buruk dan ketika data diekspor ke shapefile, nama field terpotong menjadi sepuluh karakter, sehingga sulit untuk menebak nama field aslinya. Gunakan kelas fitur geodatabase, geopackages, geojson, atau format lain sebelum mempertimbangkan untuk menggunakan shapefile.

import csv
import os

# change the input folder here for the directory you want to search
input_folder = r'\\...\...'

# change the file name here to the output file you want
results_file = 'shapefiles.csv'

extns = ['.aih', '.ain', '.atx', '.cpg', '.dbf', '.fbn', '.fbx', '.ixs', '.mxs', '.prj', '.sbn', '.sbx', '.shp', '.shx', '.xml']

with open(results_file, 'w', newline='') as csvfile:
    csvwriter = csv.writer(csvfile)
    column_headers = ['Folder','Shapefile'] + extns
    csvwriter.writerow(column_headers)

    for (folder, dirs, files) in os.walk(input_folder):
        for file in files:
            if(file.endswith('.shp')):
                shapefile_name = file.replace('.shp','')

                line = [folder,shapefile_name]

                for extn in extns:
                    file_path = os.path.join(folder,'{}{}'.format(shapefile_name,extn))
                    file_exists = 'Y' if os.path.exists(file_path) else 'N'
                    line.append(file_exists)
                
                csvwriter.writerow(line)

Skrip ini mencantumkan info lapisan untuk MXD (file ArcMap) dan APRX (file ArcGIS Pro). Hasilnya adalah output ke file CSV dan berisi kolom berikut:

Perhatikan bahwa ArcMap menggunakan Python 2 dan ArcGIS Pro menggunakan Python 3, jadi agar skrip berfungsi dengan Python 3 untuk file MXD, kami mengonversi MXD menjadi APRX pada skrip di bawah ini. APRX ini hanya ada di memori dan tidak akan disimpan ke disk (tetapi dapat disimpan ke disk jika diperlukan).

Untuk menjalankannya di bawah ini, ubah baris 5 dan 7 dan secara manual buat APRX kosong yang dapat dikloning ke memori (baris 7).

import csv
import os

from arcpy.mp import ArcGISProject

directory = r'\\...\...'
blank_aprx = r'\\...\...\temp.aprx'
results_file = os.path.basename(__file__).replace('.py','.csv')

# create a CSV file
with open(results_file, 'w', newline='') as csvfile:
    csvwriter = csv.writer(csvfile)

    # write out the column headers in the CSV file
    csvwriter.writerow(['File Path','Folder','File Name','File Type','Map / Data Frame','Layer Name','Layer Source','Is Broken','Definition Query'])

    # loop through all of the folders and files in the input directory
    for folder, dirs, files in os.walk(directory):
        for file in files:
            file_path = os.path.join(folder,file)
            
            # check if it is an MXD file - we need to convert the MXD to APRX (in-memory) because we cannot use Python 3 with MXDs
            if file.endswith('.mxd'):     
                file_type = 'mxd'
                aprx = ArcGISProject(blank_aprx)
                aprx.importDocument(file_path)

            #  check if it is an APRX file
            elif file.endswith('.aprx'):
                file_type = 'aprx'
                aprx = ArcGISProject(file_path)
            
            else:
                # file is not an MXD or APRX, so skip the loop below
                continue

            # list all layers within the 'maps' (for APRXs), or 'data frames' (for MXDs)
            for map in aprx.listMaps():
                for layer in map.listLayers():
                    # if the layer is not a group layer and has a data source
                    if layer.supports('dataSource'):
                        # check if the layer is broken
                        isBroken = layer.isBroken if layer.supports('isBroken') else 'n/a'
                        # check if the layer has a definition query (the WHERE clause in a normal SQL statement - definition queries use SQL)
                        definitionQuery = layer.definitionQuery if layer.supports('definitionQuery') else 'n/a'
                        line = [file_path, folder, file, file_type, map.name, layer.name, layer.dataSource, isBroken, definitionQuery]

                        # write the results to CSV
                        csvwriter.writerow(line)

            # delete the in-memory aprx
            del aprx

print('Results file: {}'.format(results_file))

Skrip ini mencantumkan info layanan untuk semua layanan dan menampilkan hasilnya ke CSV. Header kolom dalam CSV tercantum di bawah ini:

Sebelum menjalankan skrip, ubah parameter dari Baris 22 menjadi 31.

import csv
import json
import requests

def getToken(url, params):
    response = requests.post(url, params)
    token = json.loads(response.text)['token']
    return token

def fetchUrl(url):
    params = {
        'f': 'json',
        'token': token
    }

    response = requests.post(url, params)
    data = json.loads(response.text)

    return data

web_adaptor = 'arcgis' # web adaptor or load balancer 
token_url = 'https://{}/portal/sharing/rest/generateToken'.format(map_server)

params = {
    'f': 'json',
    'referer': 'https://.../portal/sharing/rest/generateToken',
    'username': 'portaladmin',
    'password': '**************'
}

token = getToken(token_url, params)

''' 
    ArcGIS Admin URL - we are using the admin URL, not the 
    Services Directory URL because the Services Directory will 
    only list the services that are started/running.  We also
    want to know about the stopped services.
'''
admin_url = 'https://{}/{}/admin/services'.format(map_server,web_adaptor)

params = {
    'f': 'json',
    'token': token
}

response = requests.get(admin_url, params)
data = json.loads(response.text)

folders = data['folders']
foldersToExclude = ['System','Utilities']

for folder in foldersToExclude:
    folders.remove(folder)

services = data['services'] 

with open('map_service_info.csv', 'w', newline='') as csv_file:
    csv_writer = csv.writer(csv_file)

    column_names = ['Map Server', 'Folder', 'Service name', 'Service type', 'URL', 'Published By', 'Path', 'Service Description', 'Copyright Info']
    csv_writer.writerow(column_names)

    for service in services:
        folder = ''
        service_name = service['serviceName']
        service_type = service['type']
        url = '{}/{}.{}'.format(admin_url,service_name,service_type)
       
        service_info = fetchUrl(url)
        service_description = service_info['description']
        user_name = service_info['properties']['userName'] if 'userName' in service_info['properties'] else ''
        copyright_info = service_info['properties']['copyright'] if 'copyright' in service_info['properties'] else ''
        path = service_info['properties']['path'] if 'path' in service_info['properties'] else ''

        row = [map_server, folder, service_name, service_type, url, user_name, path, service_description, copyright_info]
        csv_writer.writerow(row)

    for folder in folders:
        url = '{}/{}'.format(admin_url,folder)
        folder_info = fetchUrl(url)

        for service in folder_info['services']:
            folder = folder_info['folderName']
            service_name = service['serviceName']
            service_type = service['type']
            url = '{}/{}/{}.{}'.format(admin_url, folder, service_name, service_type, url)

            service_info = fetchUrl(url)
            service_description = service_info['description']
            user_name = service_info['properties']['userName'] if 'userName' in service_info['properties'] else ''
            copyright_info = service_info['properties']['copyright'] if 'copyright' in service_info['properties'] else ''
            path = service_info['properties']['path'] if 'path' in service_info['properties'] else ''

            row = [map_server, folder, service_name, service_type, url, user_name, path, service_description, copyright_info]
            csv_writer.writerow(row)