示例#1
0
def delete_saved_search(search_name, owner):
    """Deletes an existing saved search. This is used when overwriting a saved search."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        get_url = "{0}/api/rest/display/ssearch/export".format(voyager_server)
        get_response = requests.get(get_url,
                                    verify=verify_ssl,
                                    headers={
                                        'Content-type':
                                        'application/json',
                                        'x-access-token':
                                        task_utils.get_security_token(owner)
                                    })
        if get_response.status_code == 200:
            delete_url = ''
            saved_searches = get_response.json()['searches']
            for ss in saved_searches:
                if ss['title'] == search_name:
                    search_id = ss['id']
                    delete_url = "{0}/api/rest/display/ssearch/{1}".format(
                        voyager_server, search_id)
                    break
            if delete_url:
                res = requests.delete(delete_url,
                                      verify=verify_ssl,
                                      headers={
                                          'Content-type':
                                          'application/json',
                                          'x-access-token':
                                          task_utils.get_security_token(owner)
                                      })
                if not res.status_code == 200:
                    if hasattr(res, 'content'):
                        return False, eval(res.content)['error']
                    else:
                        return False, 'Error creating saved search: {0}: {1}'.format(
                            search_name, res.reason)
                else:
                    return True, ''
            else:
                return True, ''
        else:
            return False, eval(get_response.content)['message']
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
示例#2
0
def get_existing_saved_search_query(search_name, owner):
    """Retrieves the query from an existing saved search."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        get_url = "{0}/api/rest/display/ssearch/export".format(voyager_server)
        get_response = requests.get(get_url,
                                    headers={
                                        'Content-type':
                                        'application/json',
                                        'x-access-token':
                                        task_utils.get_security_token(owner)
                                    })
        search_query = ''
        if get_response.status_code == 200:
            saved_searches = get_response.json()['searches']
            for ss in saved_searches:
                if ss['title'] == search_name:
                    search_query = ss['path']
        return True, search_query
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
示例#3
0
def delete_items(fq_query, q_query, thumbs, metadata, layers, owner):
    """Delete items from the index using the Voyager API."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        # voyager_server = "http://localhost:8888"
        if not q_query and fq_query:
            query = fq_query
            fq = ""
        else:
            query = q_query
            fq = "&fq={0}".format(fq_query)

        url = "{0}/api/rest/index/records?query={1}{2}&items=true&thumbnails={3}&metadata={4}&layers={5}".format(
            voyager_server, query, fq, thumbs, metadata, layers)
        response = requests.delete(url,
                                   headers={
                                       'Content-type':
                                       'application/json',
                                       'x-access-token':
                                       task_utils.get_security_token(owner)
                                   })
        if response.status_code == 200:
            return True, 'Deleted items: {0}'.format(response.json())
        else:
            return False, 'Error deleting items: {0}: {1}'.format(
                'delete_items', response.reason)
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
示例#4
0
def execute(request):
    """Move files to a target folder.
    :param request: json as a dict.
    """
    moved = 0
    skipped = 0
    errors = 0
    new_folder = False

    parameters = request['params']
    target_folder = task_utils.get_parameter_value(parameters, 'target_folder', 'value')
    flatten_results = task_utils.get_parameter_value(parameters, 'flatten_results', 'value')
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])
    if target_folder:
        if not os.path.exists(target_folder):
            os.makedirs(target_folder)
            new_folder = True

    num_results, response_index = task_utils.get_result_count(parameters)
    task_utils.CHUNK_SIZE = num_results
    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'move_files')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),headers=headers)

        input_items = task_utils.get_input_items(results.json()['response']['docs'], True, True)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

        result = move_files(input_items, target_folder, flatten_results)
        moved += result[0]
        errors += result[1]
        skipped += result[2]
        status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'move_files')

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), moved, skipped, errors, errors_reasons, skipped_reasons)
示例#5
0
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    copied = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    target_dirs = ''
    target_folder = task_utils.get_parameter_value(parameters, 'target_folder', 'value')
    flatten_results = task_utils.get_parameter_value(parameters, 'flatten_results', 'value')
    if not flatten_results:
        target_dirs = os.path.splitdrive(target_folder)[1]
        flatten_results = 'false'
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Query the index for results in groups of 25.
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'copy_files')
    i = 0.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        input_items = task_utils.get_input_items(results.json()['response']['docs'], list_components=True)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        result = copy_files(input_items, target_folder, flatten_results, target_dirs)
        copied += result[0]
        errors += result[1]
        skipped += result[2]

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), copied, skipped, errors, errors_reasons, skipped_reasons)
示例#6
0
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    copied = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    target_dirs = ''
    target_folder = task_utils.get_parameter_value(parameters, 'target_folder', 'value')
    flatten_results = task_utils.get_parameter_value(parameters, 'flatten_results', 'value')
    if not flatten_results:
        target_dirs = os.path.splitdrive(target_folder)[1]
        flatten_results = 'false'
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Query the index for results in groups of 25.
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'copy_files')
    i = 0.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), verify=verify_ssl, headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)

        input_items = task_utils.get_input_items(results.json()['response']['docs'], list_components=True)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        result = copy_files(input_items, target_folder, flatten_results, target_dirs)
        copied += result[0]
        errors += result[1]
        skipped += result[2]

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), copied, skipped, errors, errors_reasons, skipped_reasons)
示例#7
0
def create_saved_search(search_name, groups, owner, query, has_q):
    """Create the saved search using Voyager API."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        url = "{0}/api/rest/display/ssearch".format(voyager_server)
        if query:
            template_id = get_display_tempate_id(owner)
            if has_q:
                if query.endswith('/'):
                    path = "/q=" + query + 'disp={0}'.format(template_id)
                else:
                    path = "/q=" + query + '/disp={0}'.format(template_id)
            else:
                if query.endswith('/'):
                    path = "/" + query + 'disp={0}'.format(template_id)
                else:
                    path = "/" + query + '/disp={0}'.format(template_id)
            query = {
                "title": str(search_name),
                "owner": str(owner['name']),
                "path": str(path),
                "share": groups,
                "overwrite": True
            }
        else:
            query = {
                "title": search_name,
                "owner": owner['name'],
                "path": "",
                "share": groups
            }
        response = requests.post(url,
                                 json.dumps(query),
                                 verify=verify_ssl,
                                 headers={
                                     'Content-type':
                                     'application/json',
                                     'x-access-token':
                                     task_utils.get_security_token(owner)
                                 })
        if response.status_code == 200:
            return True, 'Created save search: {0}'.format(
                response.json()['title'])
        else:
            if hasattr(response, 'content'):
                return False, eval(response.content)['error']
            else:
                return False, 'Error creating saved search: {0}: {1}'.format(
                    search_name, response.reason)
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
示例#8
0
def get_display_tempate_id(owner):
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        get_url = "{0}/api/rest/display/config/default".format(voyager_server)
        get_response = requests.get(get_url,
                                    headers={
                                        'Content-type':
                                        'application/json',
                                        'x-access-token':
                                        task_utils.get_security_token(owner)
                                    })
        if get_response.status_code == 200:
            return get_response.json()['id']
        else:
            return ''
    except requests.HTTPError:
        return ''
    except requests.exceptions.InvalidURL:
        return ''
    except requests.RequestException:
        return ''
示例#9
0
def execute(request):
    """Exports search results a CSV, shapefile or XML document.
    :param request: json as a dict.
    """
    chunk_size = task_utils.CHUNK_SIZE
    file_name = task_utils.get_parameter_value(request['params'], 'file_name', 'value')
    fields = task_utils.get_parameter_value(request['params'], 'fields', 'value')
    out_format = task_utils.get_parameter_value(request['params'], 'output_format', 'value')

    if not 'path' in fields and 'path:[absolute]' in fields:
        fields.append('path')

    if 'geo' in fields:
        i_geo = fields.index('geo')
        fields.remove('geo')
        fields.insert(i_geo, '[geo]')


    # Create the temporary workspace.
    task_folder = os.path.join(request['folder'], 'temp')
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    num_results, response_index = task_utils.get_result_count(request['params'])
    query = '{0}/select?&wt=json&fl={1}'.format(sys.argv[2].split('=')[1], ','.join(fields))
    if 'query' in request['params'][response_index]:
        # Voyager Search Traditional UI
        for p in request['params']:
            if 'query' in p:
                request_qry = p['query']
                break
        if 'voyager.list' in request_qry:
            query += '&voyager.list={0}'.format(request_qry['voyager.list'])

        # Replace spaces with %20 & remove \\ to avoid HTTP Error 400.
        if 'fq' in request_qry:
            try:
                query += '&fq={0}'.format(request_qry['fq'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['fq']:
                    query += '&fq={0}'.format(qry).replace("\\", "").replace(' ', '%20')
        if 'q' in request_qry:
            try:
                query += '&q={0}'.format(request_qry['q'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['q']:
                    query += '&q={0}'.format(qry).replace("\\", "").replace(' ', '%20')
        if 'place' in request_qry:
            try:
                query += '&place={0}'.format(request_qry['place'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['place']:
                    query += '&place={0}'.format(qry).replace("\\", "").replace(' ', '%20')
        if 'place.op' in request_qry:
            query += '&place.op={0}'.format(request_qry['place.op'])

        query += '&rows={0}&start={1}'
        exported_cnt = 0.
        for i in xrange(0, num_results, chunk_size):
            req = urllib2.Request(query.replace('{0}', str(chunk_size)).replace('{1}', str(i)), headers=headers)
            for n in urllib2.urlopen(req):
                jobs = eval(n.replace('null', '"null"'))['response']['docs']
                if out_format == 'CSV':
                    export_to_csv(jobs, file_name, task_folder, fields)
                elif out_format == 'XML':
                    export_to_xml(jobs, file_name, task_folder)
                elif out_format == 'SHP':
                    export_to_shp(jobs, file_name, task_folder)
                exported_cnt += chunk_size
                if exported_cnt > num_results:
                    status_writer.send_percent(100, 'exported: 100%', 'export_results')
                else:
                    percent_done = exported_cnt / num_results
                    status_writer.send_percent(percent_done, '{0}: {1:.0f}%'.format("exported", percent_done * 100), 'export_results')
    else:
        # Voyager Search Portal/Cart UI
        ids = []
        for p in request['params']:
            if 'ids' in p:
                ids = p['ids']
                break
        groups = task_utils.grouper(list(ids), chunk_size, '')
        i = 0
        for group in groups:
            i += len([v for v in group if not v == ''])
            req = urllib2.Request(query + '&ids={0}'.format(','.join(group)), headers=headers)
            results = urllib2.urlopen(req)
            jobs = eval(results.read())['response']['docs']
            if out_format == 'CSV':
                export_to_csv(jobs, file_name, task_folder, fields)
            elif out_format == 'XML':
                export_to_xml(jobs, file_name, task_folder)
            elif out_format == 'SHP':
                export_to_shp(jobs, file_name, task_folder)
            percent_done = float(i) / num_results
            status_writer.send_percent(percent_done, '{0}: {1:.0f}%'.format("exported", percent_done * 100), 'export_results')

    # Zip up outputs.
    if exported_count == 0:
        task_utils.report(os.path.join(request['folder'], '__report.json'), exported_count, 0, errors_count, errors_reasons)
    else:
        task_utils.report(os.path.join(request['folder'], '__report.json'), exported_count, 0, errors_count, errors_reasons)
    zip_file = task_utils.zip_data(task_folder, 'output.zip')
    shutil.move(zip_file, os.path.join(os.path.dirname(task_folder), os.path.basename(zip_file)))
示例#10
0
def execute(request):
    """Replace the workspace path for layer files and map document layers.
    :param request: json as a dict.
    """
    updated = 0
    skipped = 0
    parameters = request['params']
    backup = task_utils.get_parameter_value(parameters, 'create_backup',
                                            'value')
    old_data_source = task_utils.get_parameter_value(parameters,
                                                     'old_data_source',
                                                     'value').lower()
    new_data_source = task_utils.get_parameter_value(parameters,
                                                     'new_data_source',
                                                     'value')

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    if not arcpy.Exists(new_data_source):
        status_writer.send_state(
            status.STAT_FAILED,
            _('{0} does not exist').format(new_data_source))
        return

    if os.path.splitext(new_data_source)[1] not in ('.gdb', '.mdb', '.sde'):
        new_dataset = os.path.basename(new_data_source)
        dsc = arcpy.Describe(os.path.dirname(new_data_source))
    else:
        dsc = arcpy.Describe(new_data_source)
        new_dataset = ''
    wks_type = 'NONE'
    if dsc.dataType == 'FeatureDataset':
        new_workspace = dsc.path
        wks_type = get_workspace_type(new_workspace)
    elif dsc.dataType == 'Workspace':
        new_workspace = dsc.catalogPath
        wks_type = get_workspace_type(new_workspace)
    elif dsc.dataType == 'Folder':
        dsc = arcpy.Describe(new_data_source)
        new_workspace = dsc.catalogPath
        if new_dataset.endswith('.shp'):
            wks_type = 'SHAPEFILE_WORKSPACE'
            new_dataset = new_dataset.rsplit('.shp')[0]
        else:
            if arcpy.Describe(new_data_source).dataType == 'RasterDataset':
                wks_type = 'RASTER_WORKSPACE'
    elif dsc.dataType == 'CadDrawingDataset':
        new_workspace = dsc.path
        wks_type = 'CAD_WORKSPACE'
    else:
        new_workspace = os.path.dirname(new_data_source)

    num_results, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}'.format(sys.argv[2].split('=')[1], '/select?&wt=json')
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, num_results),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, num_results),
                                    task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'),
                               'replace_data_source')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "{0}&rows={1}&start={2}".format(
                fl, task_utils.CHUNK_SIZE, group[0]),
                                   verify=verify_ssl,
                                   headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
        else:
            results = requests.get(query + "{0}&rows={1}&start={2}".format(
                fl, task_utils.CHUNK_SIZE, group[0]),
                                   verify=verify_ssl,
                                   headers=headers)

        input_items = task_utils.get_input_items(
            results.json()['response']['docs'], True)
        if not input_items:
            input_items = task_utils.get_input_items(
                parameters[response_index]['response']['docs'])
        result = replace_data_source(input_items, old_data_source,
                                     new_workspace, new_dataset, wks_type,
                                     backup, headers)
        updated += result[0]
        skipped += result[1]
        status_writer.send_percent(
            i / num_results, '{0}: {1:.0f}%'.format("Processed",
                                                    i / num_results * 100),
            'replace_data_source')

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'),
                      updated,
                      skipped,
                      skipped_details=skipped_reasons)
示例#11
0
def execute(request):
    """Exports search results a CSV, shapefile or XML document.
    :param request: json as a dict.
    """

    # Get SSL trust setting.
    verify_ssl = task_utils.get_ssl_mode()

    chunk_size = task_utils.CHUNK_SIZE

    file_name = task_utils.get_parameter_value(request['params'], 'file_name',
                                               'value')
    fields = task_utils.get_parameter_value(request['params'], 'fields',
                                            'value')
    out_format = task_utils.get_parameter_value(request['params'],
                                                'output_format', 'value')

    if not 'path' in fields and 'path:[absolute]' in fields:
        fields.append('path')

    if 'geo' in fields:
        i_geo = fields.index('geo')
        fields.remove('geo')
        fields.insert(i_geo, '[geo]')

    # Create the temporary workspace.
    task_folder = os.path.join(request['folder'], 'temp')
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    num_results, response_index = task_utils.get_result_count(
        request['params'])

    if len(sys.argv) == 2:
        query = '{0}/solr/v0/select?&wt=json&fl={1}'.format(
            'http://localhost:8888', ','.join(fields))
    else:
        query = '{0}/select?&wt=json&fl={1}'.format(sys.argv[2].split('=')[1],
                                                    ','.join(fields))

    if 'query' in request['params'][response_index]:
        # Voyager Search Traditional UI
        for p in request['params']:
            if 'query' in p:
                request_qry = p['query']
                break
        if 'voyager.list' in request_qry:
            query += '&voyager.list={0}'.format(request_qry['voyager.list'])

        # Replace spaces with %20 & remove \\ to avoid HTTP Error 400.
        if 'fq' in request_qry:
            try:
                if isinstance(request_qry['fq'], list):
                    for fq in request_qry['fq']:
                        try:
                            query += '&fq={0}'.format(str(fq))
                        except UnicodeEncodeError:
                            query += '&fq={0}'.format(str(fq.encode('utf-8')))
                else:
                    query += '&fq={0}'.format(request_qry['fq'])
                if '{!expand}' in query:
                    query = query.replace('{!expand}', '')
                if '{!tag' in query:
                    tag = re.findall('{!(.*?)}', query)
                    if tag:
                        tag_str = "{!" + tag[0] + "}"
                        query = query.replace(tag_str, '')
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['fq']:
                    query += '&fq={0}'.format(qry).replace("\\", "").replace(
                        ' ', '%20')
        if 'q' in request_qry:
            try:
                query += '&q={0}'.format(request_qry['q'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except UnicodeEncodeError:
                query += '&q={0}'.format(
                    request_qry['q'].encode('utf-8').replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['q']:
                    query += '&q={0}'.format(qry).replace("\\", "").replace(
                        ' ', '%20')
        if 'place' in request_qry:
            try:
                query += '&place={0}'.format(request_qry['place'].replace(
                    "\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['place']:
                    query += '&place={0}'.format(qry).replace("\\",
                                                              "").replace(
                                                                  ' ', '%20')
        if 'place.op' in request_qry:
            query += '&place.op={0}'.format(request_qry['place.op'])

        query += '&rows={0}&start={1}'
        exported_cnt = 0.
        for i in range(0, num_results, chunk_size):
            url = query.replace('{0}', str(chunk_size)).replace('{1}', str(i))
            res = requests.get(url, verify=verify_ssl, headers=headers)

            jobs = res.json()['response']['docs']
            if out_format == 'CSV':
                export_to_csv(jobs, file_name, task_folder, fields)
            elif out_format == 'XML':
                export_to_xml(jobs, file_name, task_folder)
            elif out_format == 'SHP':
                export_to_shp(jobs, file_name, task_folder)
            exported_cnt += chunk_size
            if exported_cnt > num_results:
                status_writer.send_percent(100, 'exported: 100%',
                                           'export_results')
            else:
                percent_done = exported_cnt / num_results
                status_writer.send_percent(
                    percent_done,
                    '{0}: {1:.0f}%'.format("exported", percent_done * 100),
                    'export_results')
    else:
        # Voyager Search Portal/Cart UI
        ids = []
        for p in request['params']:
            if 'ids' in p:
                ids = p['ids']
                break
        groups = task_utils.grouper(list(ids), chunk_size, '')
        i = 0
        for group in groups:
            i += len([v for v in group if not v == ''])
            results = requests.get(query + '&ids={0}'.format(','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
            jobs = eval(results.text)['response']['docs']
            if out_format == 'CSV':
                export_to_csv(jobs, file_name, task_folder, fields)
            elif out_format == 'XML':
                export_to_xml(jobs, file_name, task_folder)
            elif out_format == 'SHP':
                export_to_shp(jobs, file_name, task_folder)
            percent_done = float(i) / num_results
            status_writer.send_percent(
                percent_done, '{0}: {1:.0f}%'.format("exported",
                                                     percent_done * 100),
                'export_results')

    # Zip up outputs.
    if exported_count == 0:
        status_writer.send_state(status.STAT_FAILED)
        task_utils.report(os.path.join(request['folder'], '__report.json'),
                          exported_count, 0, errors_count, errors_reasons)
    else:
        task_utils.report(os.path.join(request['folder'], '__report.json'),
                          exported_count, 0, errors_count, errors_reasons)
        zip_file = task_utils.zip_data(task_folder,
                                       '{0}.zip'.format(file_name))
        shutil.move(
            zip_file,
            os.path.join(os.path.dirname(task_folder),
                         os.path.basename(zip_file)))
示例#12
0
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    created = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']
    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # meta_folder = task_utils.get_parameter_value(parameters, 'meta_data_folder', 'value')
    voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
    url = "{0}/api/rest/system/settings".format(voyager_server)
    response = requests.get(url, verify=verify_ssl, headers=headers)
    meta_folder = response.json()['folders']['meta']
    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'),
                               'create_layer_files')
    i = 0.

    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)

        docs = results.json()['response']['docs']
        # docs = eval(results.read().replace('false', 'False').replace('true', 'True'))['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']
        input_items = []
        for doc in docs:
            if 'path' in doc:
                input_items.append(
                    (doc['id'], doc['path'], doc['name'], doc['location']))
        result = create_layer_file(input_items, meta_folder, voyager_server,
                                   headers)
        created += result[0]
        errors += result[1]
        skipped += result[2]

    try:
        shutil.copy2(
            os.path.join(os.path.dirname(os.path.dirname(__file__)),
                         'supportfiles', '_thumb.png'), request['folder'])
    except IOError:
        pass
    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'],
                                   '__report.json'), created, skipped, errors,
                      errors_reasons, skipped_reasons)
示例#13
0
def execute(request):
    """Zips all input files to output.zip.
    :param request: json as a dict.
    """
    zipped = 0
    skipped = 0
    parameters = request['params']
    flatten_results = task_utils.get_parameter_value(parameters, 'flatten_results', 'value')
    if not flatten_results:
        flatten_results = False
    zip_file_location = request['folder']
    if not os.path.exists(zip_file_location):
        os.makedirs(request['folder'])

    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'output'
    zip_file = os.path.join(zip_file_location, '{0}.zip'.format(output_file_name))
    zipper = task_utils.ZipFileManager(zip_file, 'w', zipfile.ZIP_DEFLATED)
    num_results, response_index = task_utils.get_result_count(parameters)
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    #query = '{0}{1}{2}'.format("http://localhost:8888/solr/v0", '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'zip_files')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        input_items = task_utils.get_input_items(results.json()['response']['docs'], list_components=True)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'], list_components=True)
        result = zip_files(zipper, input_items, zip_file_location, flatten_results)
        zipped += result[0]
        skipped += result[1]
        status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'zip_files')

    zipper.close()

    if zipped == 0:
        status_writer.send_state(status.STAT_FAILED, _('No results were zipped.'))
        return

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), zipped, skipped, skipped_details=skipped_reasons)
示例#14
0
def execute(request):
    """Builds raster pyramids for input raster datasets.
    :param request: json as a dict.
    """
    processed = 0
    skipped = 0
    parameters = request['params']

    # Get the extent for for which to use to calculate statistics.
    extent = ''
    try:
        try:
            ext = task_utils.get_parameter_value(parameters,
                                                 'processing_extent', 'wkt')
            if ext:
                sr = task_utils.get_spatial_reference("4326")
                extent = task_utils.from_wkt(ext, sr)
        except KeyError:
            ext = task_utils.get_parameter_value(parameters,
                                                 'processing_extent',
                                                 'feature')
            if ext:
                extent = arcpy.Describe(ext).extent
    except KeyError:
        pass

    horizontal_skip_factor = task_utils.get_parameter_value(
        parameters, 'horizontal_skip_factor', 'value')
    vertical_skip_factor = task_utils.get_parameter_value(
        parameters, 'vertical_skip_factor', 'value')
    ignore_pixel_values = task_utils.get_parameter_value(
        parameters, 'ignore_pixel_values', 'value')

    # Create the task folder to hold report files.
    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    num_results, response_index = task_utils.get_result_count(parameters)
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1],
                                   '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results),
                                        task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(
                list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE,
                '')
        else:
            groups = task_utils.grouper(range(0, num_results),
                                        task_utils.CHUNK_SIZE, '')

        # Begin processing
        status_writer.send_percent(0.0, _('Starting to process...'),
                                   'calculate_raster_statistics')
        i = 0.
        for group in groups:
            i += len(group) - group.count('')
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(
                    task_utils.CHUNK_SIZE, group[0]),
                                       verify=verify_ssl,
                                       headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(
                    query + '{0}&ids={1}'.format(fl, ','.join(group)),
                    verify=verify_ssl,
                    headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(
                    task_utils.CHUNK_SIZE, group[0]),
                                       verify=verify_ssl,
                                       headers=headers)

            input_items = task_utils.get_input_items(
                results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(
                    parameters[response_index]['response']['docs'])

            result = calculate_raster_statistics(input_items, extent,
                                                 horizontal_skip_factor,
                                                 vertical_skip_factor,
                                                 ignore_pixel_values)
            processed += result[0]
            skipped += result[1]
            status_writer.send_percent(
                i / num_results,
                '{0}: {1:.0f}%'.format("Processed", i / num_results * 100),
                'calculate_raster_statistics')
    else:
        input_items = task_utils.get_input_items(
            parameters[response_index]['response']['docs'])
        processed, skipped = calculate_raster_statistics(
            input_items, extent, horizontal_skip_factor, vertical_skip_factor,
            ignore_pixel_values, True)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'),
                      processed,
                      skipped,
                      skipped_details=skipped_reasons)
示例#15
0
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    created = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    meta_folder = task_utils.get_parameter_value(parameters, 'meta_data_folder', 'value')
    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'create_layer_files')
    i = 0.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        # docs = eval(results.read().replace('false', 'False').replace('true', 'True'))['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']
        input_items = []
        for doc in docs:
            if 'path' in doc:
                input_items.append((doc['id'], doc['path'], doc['name'], doc['location']))
        result = create_layer_file(input_items, meta_folder)
        created += result[0]
        errors += result[1]
        skipped += result[2]

    try:
        shutil.copy2(os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', '_thumb.png'), request['folder'])
    except IOError:
        pass
    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), created, skipped, errors, errors_reasons, skipped_reasons)
def execute(request):
    """Clips selected search results using the clip geometry.
    :param request: json as a dict.
    """
    clipped = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']

    # Retrieve the clip features.
    clip_features = task_utils.get_parameter_value(parameters, 'clip_features', 'value')

    # Retrieve the coordinate system code.
    out_coordinate_system = int(task_utils.get_parameter_value(parameters, 'output_projection', 'code'))

    # Retrieve the output format, create mxd and output file name parameter values.
    out_format = task_utils.get_parameter_value(parameters, 'output_format', 'value')
    create_mxd = task_utils.get_parameter_value(parameters, 'create_mxd', 'value')
    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'clip_results'

    # Create the temporary workspace if clip_feature_class:
    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Set the output coordinate system.
    if not out_coordinate_system == 0:  # Same as Input
        out_sr = task_utils.get_spatial_reference(out_coordinate_system)
        arcpy.env.outputCoordinateSystem = out_sr

    # Set the output workspace.
    status_writer.send_status(_('Setting the output workspace...'))
    if not out_format == 'SHP':
        out_workspace = arcpy.CreateFileGDB_management(out_workspace, 'output.gdb').getOutput(0)
    arcpy.env.workspace = out_workspace

    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl

    # Get the Clip features by id.
    id = clip_features['id']
    clip_query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', "&fl=id,path,fullpath:[absolute],absolute_path:[absolute],[lyrFile],[geo]&q=id:{0}".format(id))
    clip_result = requests.get(clip_query, headers=headers)
    clipper = clip_result.json()['response']['docs'][0]
    if 'absolute_path' in clipper and not clipper['absolute_path'].startswith('s3'):
        clip_features = clipper['absolute_path']
    elif '[lyrFile]' in clipper:
        clip_features = clipper['[lyrFile]']
    elif '[geo]' in clipper:
        clip_features = arcpy.AsShape(clipper['[geo]']).projectAs(arcpy.SpatialReference(4326))
    elif 'absolute_path' in clipper and clipper['absolute_path'].startswith('s3'):
        base_name = os.path.basename(clipper['path'])
        temp_folder = tempfile.mkdtemp()
        if '[downloadURL]' in clipper:
            download = os.path.join(temp_folder, os.path.basename(clipper['[downloadURL]']))
            response = requests.get(clipper['[downloadURL]'])
            with open(download, 'wb') as fp:
                fp.write(response.content)
            if download.endswith('.zip'):
                zip = zipfile.ZipFile(download)
                zip.extractall(temp_folder)
                clip_features = os.path.join(temp_folder, base_name)
            else:
                clip_features = download
    else:
        bbox = clipper['bbox'].split()
        extent = arcpy.Extent(*bbox)
        pt_array = arcpy.Array([extent.lowerLeft, extent.upperLeft, extent.upperRight, extent.lowerRight])
        clip_features = arcpy.Polygon(pt_array, 4326)

    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'clip_data')
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
                input_rows[doc['name']].append(doc)
        if input_rows:
            result = clip_data(input_rows, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = clip_data(input_items, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _('No items to process. Check if items exist.'))
            return

    if arcpy.env.workspace.endswith('.gdb'):
        out_workspace = os.path.dirname(arcpy.env.workspace)
    if clipped > 0:
        try:
            if out_format == 'MPK':
                mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                mxd = task_utils.create_mxd(out_workspace, mxd_template, 'output')
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_mpk(out_workspace, mxd, files_to_package)
                shutil.move(os.path.join(out_workspace, 'output.mpk'),
                            os.path.join(os.path.dirname(out_workspace), '{0}.mpk'.format(output_file_name)))
            elif out_format == 'LPK':
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_lpk(out_workspace, output_file_name, files_to_package)
            elif out_format == 'KML':
                task_utils.convert_to_kml(os.path.join(out_workspace, "output.gdb"))
                arcpy.env.workspace = ''
                arcpy.RefreshCatalog(os.path.join(out_workspace, "output.gdb"))
                try:
                    arcpy.Delete_management(os.path.join(out_workspace, "output.gdb"))
                except arcpy.ExecuteError:
                    pass
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
            else:
                if create_mxd:
                    mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                    task_utils.create_mxd(out_workspace, mxd_template, 'output')
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        except arcpy.ExecuteError as ee:
            status_writer.send_state(status.STAT_FAILED, _(ee))
            sys.exit(1)
    else:
        status_writer.send_state(status.STAT_FAILED, _('No output created. Zero inputs were clipped.'))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), clipped, skipped, errors, errors_reasons, skipped_reasons)
示例#17
0
def execute(request):
    """Exports search results a CSV, shapefile or XML document.
    :param request: json as a dict.
    """
    chunk_size = task_utils.CHUNK_SIZE
    file_name = task_utils.get_parameter_value(request['params'], 'file_name',
                                               'value')
    fields = task_utils.get_parameter_value(request['params'], 'fields',
                                            'value')
    out_format = task_utils.get_parameter_value(request['params'],
                                                'output_format', 'value')

    if not 'path' in fields and 'path:[absolute]' in fields:
        fields.append('path')

    if 'geo' in fields:
        i_geo = fields.index('geo')
        fields.remove('geo')
        fields.insert(i_geo, '[geo]')

    # Create the temporary workspace.
    task_folder = os.path.join(request['folder'], 'temp')
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    num_results, response_index = task_utils.get_result_count(
        request['params'])
    query = '{0}/select?&wt=json&fl={1}'.format(sys.argv[2].split('=')[1],
                                                ','.join(fields))
    if 'query' in request['params'][response_index]:
        # Voyager Search Traditional UI
        for p in request['params']:
            if 'query' in p:
                request_qry = p['query']
                break
        if 'voyager.list' in request_qry:
            query += '&voyager.list={0}'.format(request_qry['voyager.list'])

        # Replace spaces with %20 & remove \\ to avoid HTTP Error 400.
        if 'fq' in request_qry:
            try:
                query += '&fq={0}'.format(request_qry['fq'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['fq']:
                    query += '&fq={0}'.format(qry).replace("\\", "").replace(
                        ' ', '%20')
        if 'q' in request_qry:
            try:
                query += '&q={0}'.format(request_qry['q'].replace("\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['q']:
                    query += '&q={0}'.format(qry).replace("\\", "").replace(
                        ' ', '%20')
        if 'place' in request_qry:
            try:
                query += '&place={0}'.format(request_qry['place'].replace(
                    "\\", ""))
                query = query.replace(' ', '%20')
            except AttributeError:
                for qry in request_qry['place']:
                    query += '&place={0}'.format(qry).replace("\\",
                                                              "").replace(
                                                                  ' ', '%20')
        if 'place.op' in request_qry:
            query += '&place.op={0}'.format(request_qry['place.op'])

        query += '&rows={0}&start={1}'
        exported_cnt = 0.
        for i in xrange(0, num_results, chunk_size):
            req = urllib2.Request(query.replace('{0}',
                                                str(chunk_size)).replace(
                                                    '{1}', str(i)),
                                  headers=headers)
            for n in urllib2.urlopen(req):
                jobs = eval(n.replace('null', '"null"'))['response']['docs']
                if out_format == 'CSV':
                    export_to_csv(jobs, file_name, task_folder, fields)
                elif out_format == 'XML':
                    export_to_xml(jobs, file_name, task_folder)
                elif out_format == 'SHP':
                    export_to_shp(jobs, file_name, task_folder)
                exported_cnt += chunk_size
                if exported_cnt > num_results:
                    status_writer.send_percent(100, 'exported: 100%',
                                               'export_results')
                else:
                    percent_done = exported_cnt / num_results
                    status_writer.send_percent(
                        percent_done,
                        '{0}: {1:.0f}%'.format("exported", percent_done * 100),
                        'export_results')
    else:
        # Voyager Search Portal/Cart UI
        ids = []
        for p in request['params']:
            if 'ids' in p:
                ids = p['ids']
                break
        groups = task_utils.grouper(list(ids), chunk_size, '')
        i = 0
        for group in groups:
            i += len([v for v in group if not v == ''])
            req = urllib2.Request(query + '&ids={0}'.format(','.join(group)),
                                  headers=headers)
            results = urllib2.urlopen(req)
            jobs = eval(results.read())['response']['docs']
            if out_format == 'CSV':
                export_to_csv(jobs, file_name, task_folder, fields)
            elif out_format == 'XML':
                export_to_xml(jobs, file_name, task_folder)
            elif out_format == 'SHP':
                export_to_shp(jobs, file_name, task_folder)
            percent_done = float(i) / num_results
            status_writer.send_percent(
                percent_done, '{0}: {1:.0f}%'.format("exported",
                                                     percent_done * 100),
                'export_results')

    # Zip up outputs.
    if exported_count == 0:
        task_utils.report(os.path.join(request['folder'], '__report.json'),
                          exported_count, 0, errors_count, errors_reasons)
    else:
        task_utils.report(os.path.join(request['folder'], '__report.json'),
                          exported_count, 0, errors_count, errors_reasons)
    zip_file = task_utils.zip_data(task_folder, 'output.zip')
    shutil.move(
        zip_file,
        os.path.join(os.path.dirname(task_folder), os.path.basename(zip_file)))
def execute(request):
    """Copies data to an existing geodatabase or feature dataset.
    :param request: json as a dict.
    """
    added = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request["params"]

    # Get the target workspace location.
    out_gdb = task_utils.get_parameter_value(parameters, "target_workspace", "value")

    # Retrieve the coordinate system code.
    out_coordinate_system = task_utils.get_parameter_value(parameters, "output_projection", "code")
    if not out_coordinate_system == "0":  # Same as Input
        arcpy.env.outputCoordinateSystem = task_utils.get_spatial_reference(out_coordinate_system)

    task_folder = request["folder"]
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    # Check if the geodatabase exists or if it is a feature dataset.
    is_fds = False
    if not os.path.exists(out_gdb):
        if out_gdb.endswith(".gdb"):
            arcpy.CreateFileGDB_management(os.path.dirname(out_gdb), os.path.basename(out_gdb))
            status_writer.send_status(_("Created output workspace: {0}").format(out_gdb))
        elif out_gdb.endswith(".mdb"):
            arcpy.CreatePersonalGDB_management(os.path.dirname(out_gdb), os.path.basename(out_gdb))
            status_writer.send_status(_("Created output workspace: {0}").format(out_gdb))
        elif out_gdb.endswith(".sde"):
            status_writer.send_state(status.STAT_FAILED, _("{0} does not exist").format(out_gdb))
            return
        else:
            # Possible feature dataset.
            is_fds = is_feature_dataset(out_gdb)
            if not is_fds:
                if os.path.dirname(out_gdb).endswith(".gdb"):
                    if not os.path.exists(os.path.dirname(out_gdb)):
                        arcpy.CreateFileGDB_management(
                            os.path.dirname(os.path.dirname(out_gdb)), os.path.basename(os.path.dirname(out_gdb))
                        )
                    arcpy.CreateFeatureDataset_management(os.path.dirname(out_gdb), os.path.basename(out_gdb))
                elif os.path.dirname(out_gdb).endswith(".mdb"):
                    if not os.path.exists(os.path.dirname(out_gdb)):
                        arcpy.CreatePersonalGDB_management(
                            os.path.dirname(os.path.dirname(out_gdb)), os.path.basename(os.path.dirname(out_gdb))
                        )
                    arcpy.CreateFeatureDataset_management(os.path.dirname(out_gdb), os.path.basename(out_gdb))

    status_writer.send_status(_("Setting the output workspace..."))
    arcpy.env.workspace = out_gdb

    headers = {"x-access-token": task_utils.get_security_token(request["owner"])}
    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = "{0}{1}{2}".format(sys.argv[2].split("=")[1], "/select?&wt=json", fl)
    # query = '{0}{1}{2}'.format("http://localhost:8888/solr/v0", '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")
        query += fq
    elif "ids" in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]["ids"]), task_utils.CHUNK_SIZE, "")
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")

    status_writer.send_percent(0.0, _("Starting to process..."), "add_to_geodatabase")
    for group in groups:
        if fq:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )
        elif "ids" in parameters[response_index]:
            results = requests.get(query + "{0}&ids={1}".format(fl, ",".join(group)), headers=headers)
        else:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )

        docs = results.json()["response"]["docs"]
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]["response"]["docs"])
        input_rows = collections.defaultdict(list)
        for doc in docs:
            if "path" not in doc:
                input_rows[doc["title"]].append(doc)
        if input_rows:
            result = add_to_geodatabase(input_rows, out_gdb, is_fds)
            added += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = add_to_geodatabase(input_items, out_gdb, is_fds)
            added += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _("No items to process. Check if items exist."))
            return

    # Update state if necessary.
    if skipped > 0 or errors > 0:
        status_writer.send_state(status.STAT_WARNING, _("{0} results could not be processed").format(skipped + errors))
    task_utils.report(
        os.path.join(task_folder, "__report.json"), added, skipped, errors, errors_reasons, skipped_reasons
    )
示例#19
0
def execute(request):
    """Converts each input dataset to kml (.kmz).
    :param request: json as a dict.
    """
    converted = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Get the boundary box extent for input to KML tools.
    extent = ''
    try:
        try:
            ext = task_utils.get_parameter_value(parameters, 'processing_extent', 'wkt')
            if ext:
                sr = task_utils.get_spatial_reference("4326")
                extent = task_utils.from_wkt(ext, sr)
        except KeyError:
            ext = task_utils.get_parameter_value(parameters, 'processing_extent', 'feature')
            if ext:
                extent = arcpy.Describe(ext).extent
    except KeyError:
        pass

    # Get the output file name.
    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'kml_results'

    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'convert_to_kml')
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
               input_rows[doc['name']].append(doc)
        if input_rows:
            result = convert_to_kml(input_rows, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = convert_to_kml(input_items, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _('No items to process. Check if items exist.'))
            return

    # Zip up kmz files if more than one.
    if converted > 1:
        status_writer.send_status("Converted: {}".format(converted))
        zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
        shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        shutil.copy2(os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', '_thumb.png'), request['folder'])
    elif converted == 1:
        try:
            kml_file = glob.glob(os.path.join(out_workspace, '*.kmz'))[0]
            tmp_lyr = arcpy.KMLToLayer_conversion(kml_file, out_workspace, 'kml_layer')
            task_utils.make_thumbnail(tmp_lyr.getOutput(0), os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            pass
        shutil.move(kml_file, os.path.join(request['folder'], os.path.basename(kml_file)))

    # Update state if necessary.
    if skipped > 0 or errors > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), converted, skipped, errors, errors_reasons, skipped_reasons)
def execute(request):
    """Builds raster pyramids for input raster datasets.
    :param request: json as a dict.
    """
    processed = 0
    skipped = 0
    parameters = request['params']
    resampling_method = task_utils.get_parameter_value(parameters, 'resampling_method', 'value')

    # Advanced options
    compression_method = task_utils.get_parameter_value(parameters, 'compression_method', 'value')
    compression_quality = task_utils.get_parameter_value(parameters, 'compression_quality', 'value')

    # Create the task folder to hold report files.
    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    num_results, response_index = task_utils.get_result_count(parameters)
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
        else:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

        # Begin processing
        status_writer.send_percent(0.0, _('Starting to process...'), 'build_raster_pyramids')
        i = 0.
        for group in groups:
            i += len(group) - group.count('')
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

            input_items = task_utils.get_input_items(results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
            result = build_pyramids(input_items, compression_method, compression_quality, resampling_method)
            processed += result[0]
            skipped += result[1]
            status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'build_raster_pyramids')
    else:
        input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        processed, skipped = build_pyramids(input_items, compression_method, compression_quality, resampling_method, True)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), processed, skipped, skipped_details=skipped_reasons)
示例#21
0
def execute(request):
    """Report duplicate items.
    :param request: json as a dict.
    """
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])
    date_str = str(datetime.date.today())
    report_file = os.path.join(request['folder'], 'Duplicates_{0}.csv'.format(date_str))

    request_owner = request['owner']
    headers = {'x-access-token': task_utils.get_security_token(request_owner)}

    fields = list(task_utils.get_parameter_value(request['params'], 'fields', 'value'))
    required_fields = ("name", "title", "bytes", "id", "format", "absolute_path")
    [fields.remove(f) for f in required_fields if f in fields]

    fields_str = ""
    if fields:
        fields_str = ",".join(fields)

    voyager_instance = sys.argv[2].split('=')[1]
    query = voyager_instance + "/select?q={!func}joindf(md5,md5)&f.md5.facet.mincount=2&f.contentHash.facet.mincount=2&f.schemaHash.facet.mincount=2&sort=md5 desc&start=0&rows=1&fl=id,title,name:[name],format,fullpath:[absolute],absolute_path:[absolute],download:[downloadURL],format_type,bytes,layerURL:[lyrURL],md5,path,name&fq={!frange l=2}{!func}joindf(md5,md5)&wt=json"
    results = requests.get(query, auth=("admin", "admin"), headers=headers)
    result_count = results.json()['response']['numFound']
    if result_count == 0:
        status_writer.send_state(status.STAT_WARNING, "No duplicates found.")
        return
    duplicates = collections.defaultdict(list)
    groups = grouper(range(0, result_count), 25, '')

    url = voyager_instance.split("/solr")[0]
    req = requests.get("{0}/api/rest/i18n/field/format".format(url), headers=headers)
    formats = req.json()['VALUE']['format']

    for group in groups:
        query = "%s/select?q={!func}joindf(md5,md5)&f.md5.facet.mincount=2&f.contentHash.facet.mincount=2&f.schemaHash.facet.mincount=2&sort=md5 desc&start=%s&rows=25&fl=id,title,name:[name],format,fullpath:[absolute],absolute_path:[absolute],download:[downloadURL],format_type,bytes,layerURL:[lyrURL],md5,path,name,%s&fq={!frange l=2}{!func}joindf(md5,md5)&wt=json" % (voyager_instance, group[0], fields_str)
        results = requests.get(query, auth=("admin", "admin"), headers=headers)
        docs = results.json()['response']['docs']

        for doc in docs:
            file_size = 0
            if "bytes" in doc:
                file_size = float(doc['bytes'])

            format_type = ""
            if "format" in doc and not doc["format"] in ("application/vnd.esri.gdb.file.data", "application/vnd.esri.gdb.personal.data"):
                try:
                    format_type = formats[doc["format"]]
                except KeyError:
                    format_type = doc["format"]
            else:
                continue

            file_path = ""
            if "absolute_path" in doc:
                file_path = doc["absolute_path"]

            id = ""
            if "id" in doc:
                id = doc["id"]

            name = ""
            if "name" in doc:
                name = doc["name"]
            elif "title" in doc:
                name = doc["title"]

            field_dict = {"FILE NAME": name, "FILE SIZE": file_size,
                          "FORMAT": format_type, "ID": id, "FILE PATH": file_path}

            extra_fields = {}
            if fields:
                for fld in fields:
                    if fld in doc:
                        extra_fields[fld.upper()] = doc[fld]

            field_dict.update(extra_fields)
            duplicates[doc['md5']].append(field_dict)

    # Find total number of items in the index.
    all_query = "%s/select?disp=default&sort=score desc&place.op=within&start=0&fl=id&voyager.config.id=ace4bb77&wt=json" % (voyager_instance)
    results = requests.get(all_query, auth=("admin", "admin"), headers=headers)
    index_count = results.json()['response']['numFound']

    duplicate_count = 0
    total_file_size = 0
    # Write all the duplicates to the report file.
    with open(report_file, "wb") as f:
        if extra_fields:
            keys = ["MD5", "FILE NAME", "FILE SIZE", "FORMAT", "ID", "FILE PATH"] + extra_fields.keys()
        else:
            keys = ["MD5", "FILE NAME", "FILE SIZE", "FORMAT", "ID", "FILE PATH"]
        writer = csv.DictWriter(f, fieldnames=keys)
        writer.writeheader()
        for md5, values in duplicates.items():
            writer.writerow({})
            val_count = len(values)
            if val_count > 1:
                duplicate_count += val_count - 1
                for val in values:
                    total_file_size += val["FILE SIZE"] * (val_count - 1)
                    val["MD5"] = md5
                    val["FILE SIZE"] = convert_size(val["FILE SIZE"])
                    writer.writerow(val)

    # Report a summary to the report file.
    pct_dups = float(duplicate_count) / index_count
    with open(report_file, "ab") as f:
        writer = csv.DictWriter(f, fieldnames=["DUPLICATE COUNT", "INDEX COUNT", "PERCENT DUPLICATES", "TOTAL DUPLICATE FILE SIZE"])
        writer.writerow({})
        writer.writerow({})
        writer.writeheader()
        writer.writerow({"DUPLICATE COUNT": duplicate_count,
                         "INDEX COUNT": index_count,
                         "PERCENT DUPLICATES": '{:.0f}%'.format(pct_dups * 100),
                         "TOTAL DUPLICATE FILE SIZE": convert_size(total_file_size)})

    status_writer.send_status("DUPLICATE COUNT: {0}".format(duplicate_count))
    status_writer.send_status("INDEX COUNT: {0}".format(index_count))
    status_writer.send_status("PERCENT DUPLICATES: {0}".format('{:.0f}%'.format(pct_dups * 100)))
    status_writer.send_status("TOTAL DUPLICATE FILE SIZE: {0}".format(convert_size(total_file_size)))
    status_writer.send_state(status.STAT_SUCCESS)
示例#22
0
def delete_items(fq_query, q_query, thumbs, metadata, layers, owner):
    """Delete items from the index using the Voyager API."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        # voyager_server = "http://localhost:8888"
        if not q_query and fq_query:
            query = fq_query
            fq = ""
        else:
            query = q_query
            fq = "&fq={0}".format(fq_query)

        url = "{0}/api/rest/index/records?query={1}{2}&items=true&thumbnails={3}&metadata={4}&layers={5}".format(voyager_server, query, fq, thumbs, metadata, layers)
        response = requests.delete(url, headers={'Content-type': 'application/json', 'x-access-token': task_utils.get_security_token(owner)})
        if response.status_code == 200:
            return True, 'Deleted items: {0}'.format(response.json())
        else:
            return False, 'Error deleting items: {0}: {1}'.format('delete_items', response.reason)
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
def execute(request):
    """Replace the workspace path for layer files and map document layers.
    :param request: json as a dict.
    """
    updated = 0
    skipped = 0
    parameters = request['params']
    backup = task_utils.get_parameter_value(parameters, 'create_backup', 'value')
    old_data_source = task_utils.get_parameter_value(parameters, 'old_data_source', 'value').lower()
    new_data_source = task_utils.get_parameter_value(parameters, 'new_data_source', 'value')

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    if not arcpy.Exists(new_data_source):
        status_writer.send_state(status.STAT_FAILED, _('{0} does not exist').format(new_data_source))
        return

    if os.path.splitext(new_data_source)[1] not in ('.gdb', '.mdb', '.sde'):
        new_dataset = os.path.basename(new_data_source)
        dsc = arcpy.Describe(os.path.dirname(new_data_source))
    else:
        dsc = arcpy.Describe(new_data_source)
        new_dataset = ''
    wks_type = 'NONE'
    if dsc.dataType == 'FeatureDataset':
        new_workspace = dsc.path
        wks_type = get_workspace_type(new_workspace)
    elif dsc.dataType == 'Workspace':
        new_workspace = dsc.catalogPath
        wks_type = get_workspace_type(new_workspace)
    elif dsc.dataType == 'Folder':
        dsc = arcpy.Describe(new_data_source)
        new_workspace = dsc.catalogPath
        if new_dataset.endswith('.shp'):
            wks_type = 'SHAPEFILE_WORKSPACE'
            new_dataset = new_dataset.rsplit('.shp')[0]
        else:
            if arcpy.Describe(new_data_source).dataType == 'RasterDataset':
                wks_type = 'RASTER_WORKSPACE'
    elif dsc.dataType == 'CadDrawingDataset':
        new_workspace = dsc.path
        wks_type = 'CAD_WORKSPACE'
    else:
        new_workspace = os.path.dirname(new_data_source)

    num_results, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}'.format(sys.argv[2].split('=')[1], '/select?&wt=json')
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'replace_data_source')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "{0}&rows={1}&start={2}".format(fl, task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers= headers)
        else:
            results = requests.get(query + "{0}&rows={1}&start={2}".format(fl, task_utils.CHUNK_SIZE, group[0]), headers=headers)

        input_items = task_utils.get_input_items(results.json()['response']['docs'], True)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        result = replace_data_source(input_items, old_data_source, new_workspace, new_dataset, wks_type, backup, headers)
        updated += result[0]
        skipped += result[1]
        status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'replace_data_source')

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), updated, skipped, skipped_details=skipped_reasons)
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    extracted = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    output_type = task_utils.get_parameter_value(parameters, 'output_format', 'value')
    task_folder = os.path.join(request['folder'], 'temp')
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)
        if output_type == 'FGDB':
            arcpy.CreateFileGDB_management(task_folder, 'output.gdb')

    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    # query = '{0}{1}{2}'.format("http://localhost:8888/solr/v0", '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    status_writer.send_percent(0.0, _('Starting to process...'), 'locate_xt_arcgis_tool')
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']

        input_items = task_utils.get_input_items(docs)
        if input_items:
            result = extract(input_items, output_type, task_folder)
            extracted += result[0]
            errors += result[1]
            skipped += result[2]
        else:
            status_writer.send_state(status.STAT_FAILED, _('No items to process. Check if items exist.'))
            return

    # Zip up outputs.
    zip_file = task_utils.zip_data(task_folder, 'output.zip')
    shutil.move(zip_file, os.path.join(os.path.dirname(task_folder), os.path.basename(zip_file)))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), extracted, skipped, errors, errors_reasons, skipped_reasons)
def execute(request):
    """Builds raster pyramids for input raster datasets.
    :param request: json as a dict.
    """
    processed = 0
    skipped = 0
    parameters = request['params']
    resampling_method = task_utils.get_parameter_value(parameters, 'resampling_method', 'value')

    # Advanced options
    compression_method = task_utils.get_parameter_value(parameters, 'compression_method', 'value')
    compression_quality = task_utils.get_parameter_value(parameters, 'compression_quality', 'value')

    # Create the task folder to hold report files.
    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    num_results, response_index = task_utils.get_result_count(parameters)
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
        else:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

        # Begin processing
        status_writer.send_percent(0.0, _('Starting to process...'), 'build_raster_pyramids')
        i = 0.
        for group in groups:
            i += len(group) - group.count('')
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), verify=verify_ssl, headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)

            input_items = task_utils.get_input_items(results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
            result = build_pyramids(input_items, compression_method, compression_quality, resampling_method)
            processed += result[0]
            skipped += result[1]
            status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'build_raster_pyramids')
    else:
        input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        processed, skipped = build_pyramids(input_items, compression_method, compression_quality, resampling_method, True)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), processed, skipped, skipped_details=skipped_reasons)
def execute(request):
    """Builds raster pyramids for input raster datasets.
    :param request: json as a dict.
    """
    processed = 0
    skipped = 0
    parameters = request['params']

    # Get the extent for for which to use to calculate statistics.
    extent = ''
    try:
        try:
            ext = task_utils.get_parameter_value(parameters, 'processing_extent', 'wkt')
            if ext:
                sr = task_utils.get_spatial_reference("4326")
                extent = task_utils.from_wkt(ext, sr)
        except KeyError:
            ext = task_utils.get_parameter_value(parameters, 'processing_extent', 'feature')
            if ext:
                extent = arcpy.Describe(ext).extent
    except KeyError:
        pass

    horizontal_skip_factor = task_utils.get_parameter_value(parameters, 'horizontal_skip_factor', 'value')
    vertical_skip_factor = task_utils.get_parameter_value(parameters, 'vertical_skip_factor', 'value')
    ignore_pixel_values = task_utils.get_parameter_value(parameters, 'ignore_pixel_values', 'value')

    # Create the task folder to hold report files.
    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    num_results, response_index = task_utils.get_result_count(parameters)
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
        else:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

        # Begin processing
        status_writer.send_percent(0.0, _('Starting to process...'), 'calculate_raster_statistics')
        i = 0.
        for group in groups:
            i += len(group) - group.count('')
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

            # input_items = task_utils.get_input_items(eval(results.read().replace('false', 'False').replace('true', 'True'))['response']['docs'])
            input_items = task_utils.get_input_items(results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

            result = calculate_raster_statistics(input_items, extent, horizontal_skip_factor, vertical_skip_factor, ignore_pixel_values)
            processed += result[0]
            skipped += result[1]
            status_writer.send_percent(i / num_results, '{0}: {1:.0f}%'.format("Processed", i / num_results * 100), 'calculate_raster_statistics')
    else:
        input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        processed, skipped = calculate_raster_statistics(input_items, extent, horizontal_skip_factor,
                                                         vertical_skip_factor, ignore_pixel_values, True)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), processed, skipped, skipped_details=skipped_reasons)
示例#27
0
def execute(request):
    """Adds a field and calculates it to some value.
    :param request: json as a dict.
    """
    created = 0
    skipped = 0
    errors = 0
    warnings = 0
    global result_count
    parameters = request['params']

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Parameter values
    field_name = task_utils.get_parameter_value(parameters, 'field_name',
                                                'value')
    field_type = task_utils.get_parameter_value(parameters, 'field_type',
                                                'value')
    field_value = task_utils.get_parameter_value(parameters, 'field_value',
                                                 'value')

    # Query the index for results in groups of 25.
    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl + ',links'
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'add_field')
    for group in groups:
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)

        docs = results.json()['response']['docs']
        input_items = []
        for doc in docs:
            if 'path' in doc:
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append((doc['id'], doc['absolute_path'],
                                        links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['id'], doc['absolute_path']))

        result = add_field(input_items, field_name, field_type, field_value)
        created += result[0]
        errors += result[1]
        skipped += result[2]
        warnings += result[3]

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'),
                      created, skipped, errors, errors_reasons,
                      skipped_reasons, warnings, warnings_reasons)
示例#28
0
def create_snapshot(snapshot_name, owner, query=''):
    """TODO ."""
    try:
        voyager_server = sys.argv[2].split('=')[1].split('solr')[0][:-1]
        if query:
            url = "{0}/api/rest/snapshot/export?name={1}&query={2}&format=CORE".format(voyager_server, snapshot_name, query)
        else:
            url = "{0}/api/rest/snapshot/export?name={1}&format=CORE".format(voyager_server, snapshot_name)
        response = requests.post(url, headers={'Content-type': 'application/json', 'x-access-token': task_utils.get_security_token(owner)})
        if response.status_code == 200:
            return True, 'Created snapshot: {0}'.format(response.json()['target']['file'])
        else:
            return False, 'Error creating snapshot: {0}: {1}'.format(snapshot_name, 'Error {0}: {1}'.format(response.status_code, response.reason))
    except requests.HTTPError as http_error:
        return False, http_error
    except requests.exceptions.InvalidURL as url_error:
        return False, url_error
    except requests.RequestException as re:
        return False, re
def execute(request):
    """Package inputs to an Esri map or layer package.
    :param request: json as a dict.
    """
    errors = 0
    skipped = 0
    layers = []
    files = []

    app_folder = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
    parameters = request['params']
    out_format = task_utils.get_parameter_value(parameters, 'output_format',
                                                'value')
    summary = task_utils.get_parameter_value(parameters, 'summary')
    tags = task_utils.get_parameter_value(parameters, 'tags')
    output_file_name = task_utils.get_parameter_value(parameters,
                                                      'output_file_name')
    if not output_file_name:
        output_file_name = 'package_results'

    # Get the clip region as an extent object.
    clip_area = None
    try:
        clip_area_wkt = task_utils.get_parameter_value(parameters,
                                                       'processing_extent',
                                                       'wkt')
        clip_area = task_utils.get_clip_region(clip_area_wkt)
    except (KeyError, ValueError):
        pass

    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    num_results, response_index = task_utils.get_result_count(parameters)
    # if num_results > task_utils.CHUNK_SIZE:
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, num_results),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, num_results),
                                    task_utils.CHUNK_SIZE, '')

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    status_writer.send_status(_('Starting to process...'))
    for group in groups:
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)

        input_items = task_utils.get_input_items(
            results.json()['response']['docs'])
        if not input_items:
            input_items = task_utils.get_input_items(
                parameters[response_index]['response']['docs'])
        layers, files, errors, skipped = get_items(input_items, out_workspace)
    # else:
    #     input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
    #     layers, files, errors, skipped = get_items(input_items, out_workspace)

    if errors == num_results:
        status_writer.send_state(status.STAT_FAILED,
                                 _('No results to package'))
        return

    try:
        if out_format == 'MPK':
            shutil.copyfile(
                os.path.join(app_folder, 'supportfiles', 'MapTemplate.mxd'),
                os.path.join(out_workspace, 'output.mxd'))
            mxd = arcpy.mapping.MapDocument(
                os.path.join(out_workspace, 'output.mxd'))
            if mxd.description == '':
                mxd.description = os.path.basename(mxd.filePath)
            df = arcpy.mapping.ListDataFrames(mxd)[0]
            for layer in layers:
                arcpy.mapping.AddLayer(df, layer)
            mxd.save()
            status_writer.send_status(
                _('Generating {0}. Large input {1} will take longer to process.'
                  .format('MPK', 'results')))
            if arcpy.GetInstallInfo()['Version'] == '10.0':
                arcpy.PackageMap_management(
                    mxd.filePath,
                    os.path.join(os.path.dirname(out_workspace),
                                 '{0}.mpk'.format(output_file_name)),
                    'PRESERVE',
                    extent=clip_area)
            elif arcpy.GetInstallInfo()['Version'] == '10.1':
                arcpy.PackageMap_management(
                    mxd.filePath,
                    os.path.join(os.path.dirname(out_workspace),
                                 '{0}.mpk'.format(output_file_name)),
                    'PRESERVE',
                    extent=clip_area,
                    ArcGISRuntime='RUNTIME',
                    version='10',
                    additional_files=files,
                    summary=summary,
                    tags=tags)
            else:
                arcpy.PackageMap_management(
                    mxd.filePath,
                    os.path.join(os.path.dirname(out_workspace),
                                 '{0}.mpk'.format(output_file_name)),
                    'PRESERVE',
                    extent=clip_area,
                    arcgisruntime='RUNTIME',
                    version='10',
                    additional_files=files,
                    summary=summary,
                    tags=tags)
            #  Create a thumbnail size PNG of the mxd.
            task_utils.make_thumbnail(
                mxd, os.path.join(request['folder'], '_thumb.png'))
        else:
            status_writer.send_status(
                _('Generating {0}. Large input {1} will take longer to process.'
                  .format('LPK', 'results')))
            for layer in layers:
                if layer.description == '':
                    layer.description = layer.name
            if arcpy.GetInstallInfo()['Version'] == '10.0':
                arcpy.PackageLayer_management(
                    layers,
                    os.path.join(os.path.dirname(out_workspace),
                                 '{0}.lpk'.format(output_file_name)),
                    'PRESERVE',
                    extent=clip_area,
                    version='10')
            else:
                arcpy.PackageLayer_management(
                    layers,
                    os.path.join(os.path.dirname(out_workspace),
                                 '{0}.lpk'.format(output_file_name)),
                    'PRESERVE',
                    extent=clip_area,
                    version='10',
                    additional_files=files,
                    summary=summary,
                    tags=tags)
            #  Create a thumbnail size PNG of the mxd.
            task_utils.make_thumbnail(
                layers[0], os.path.join(request['folder'], '_thumb.png'))
    except (RuntimeError, ValueError, arcpy.ExecuteError) as ex:
        status_writer.send_state(status.STAT_FAILED, repr(ex))
        return

    # Update state if necessary.
    if errors > 0 or skipped:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'),
                      num_results - (skipped + errors), skipped, errors,
                      errors_reasons, skipped_reasons)
def execute(request):
    """Mosaics input raster datasets into a new raster dataset or mosaic dataset.
    :param request: json as a dict.
    """
    status_writer = status.Writer()
    parameters = request['params']
    target_workspace = task_utils.get_parameter_value(parameters, 'target_workspace', 'value')
    output_name = task_utils.get_parameter_value(parameters, 'output_dataset_name', 'value')
    out_coordinate_system = task_utils.get_parameter_value(parameters, 'output_projection', 'code')
    # Advanced options
    output_raster_format = task_utils.get_parameter_value(parameters, 'raster_format', 'value')
    compression_method = task_utils.get_parameter_value(parameters, 'compression_method', 'value')
    compression_quality = task_utils.get_parameter_value(parameters, 'compression_quality', 'value')
    arcpy.env.compression = '{0} {1}'.format(compression_method, compression_quality)

    if output_raster_format in ('FileGDB', 'MosaicDataset'):
        if not os.path.splitext(target_workspace)[1] in ('.gdb', '.mdb', '.sde'):
            status_writer.send_state(status.STAT_FAILED, _('Target workspace must be a geodatabase'))
            return

    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    clip_area = None
    if not output_raster_format == 'MosaicDataset':
        # Get the clip region as an extent object.
        try:
            clip_area_wkt = task_utils.get_parameter_value(parameters, 'processing_extent', 'wkt')
            if not clip_area_wkt:
                clip_area_wkt = 'POLYGON ((-180 -90, -180 90, 180 90, 180 -90, -180 -90))'
            if not out_coordinate_system == '0':
                clip_area = task_utils.get_clip_region(clip_area_wkt, out_coordinate_system)
            else:
                clip_area = task_utils.get_clip_region(clip_area_wkt)
        except KeyError:
            pass

    status_writer.send_status(_('Setting the output workspace...'))
    if not os.path.exists(target_workspace):
        status_writer.send_state(status.STAT_FAILED, _('Target workspace does not exist'))
        return
    arcpy.env.workspace = target_workspace

    status_writer.send_status(_('Starting to process...'))
    num_results, response_index = task_utils.get_result_count(parameters)
    raster_items = None
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
        else:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

        headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
        for group in groups:
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

            input_items = task_utils.get_input_items(results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
            raster_items, pixels, bands, skipped = get_items(input_items)
    else:
        input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        raster_items, pixels, bands, skipped = get_items(input_items)

    if not raster_items:
        if skipped == 0:
            status_writer.send_state(status.STAT_FAILED, _('Invalid input types'))
            skipped_reasons['All Items'] = _('Invalid input types')
            task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), num_results, skipped_details=skipped_reasons)
            return
        else:
            status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
            task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), skipped, skipped_details=skipped_reasons)
            return

    # Get most common pixel type.
    pixel_type = pixel_types[max(set(pixels), key=pixels.count)]
    if output_raster_format in ('FileGDB', 'GRID', 'MosaicDataset'):
        output_name = arcpy.ValidateTableName(output_name, target_workspace)
    else:
        output_name = '{0}.{1}'.format(arcpy.ValidateTableName(output_name, target_workspace), output_raster_format.lower())

    if arcpy.Exists(os.path.join(target_workspace, output_name)):
        status_writer.send_state(status.STAT_FAILED, _('Output dataset already exists.'))
        return

    if output_raster_format == 'MosaicDataset':
        try:
            status_writer.send_status(_('Generating {0}. Large input {1} will take longer to process.'.format('Mosaic', 'rasters')))
            if out_coordinate_system == '0':
                out_coordinate_system = raster_items[0]
            else:
                out_coordinate_system = None
            mosaic_ds = arcpy.CreateMosaicDataset_management(target_workspace,
                                                             output_name,
                                                             out_coordinate_system,
                                                             max(bands),
                                                             pixel_type)
            arcpy.AddRastersToMosaicDataset_management(mosaic_ds, 'Raster Dataset', raster_items)
            arcpy.MakeMosaicLayer_management(mosaic_ds, 'mosaic_layer')
            layer_object = arcpy.mapping.Layer('mosaic_layer')
            task_utils.make_thumbnail(layer_object, os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            skipped += 1
            skipped_reasons['All Items'] = arcpy.GetMessages(2)
    else:
        try:
            if len(bands) > 1:
                status_writer.send_state(status.STAT_FAILED, _('Input rasters must have the same number of bands'))
                return
            if out_coordinate_system == '0':
                out_coordinate_system = None
            status_writer.send_status(_('Generating {0}. Large input {1} will take longer to process.'.format('Mosaic', 'rasters')))
            if clip_area:
                ext = '{0} {1} {2} {3}'.format(clip_area.XMin, clip_area.YMin, clip_area.XMax, clip_area.YMax)
                tmp_mosaic = arcpy.MosaicToNewRaster_management(
                    raster_items,
                    target_workspace,
                    'tmpMosaic',
                    out_coordinate_system,
                    pixel_type,
                    number_of_bands=bands.keys()[0]
                )
                status_writer.send_status(_('Clipping...'))
                out_mosaic = arcpy.Clip_management(tmp_mosaic, ext, output_name)
                arcpy.Delete_management(tmp_mosaic)
            else:
                out_mosaic = arcpy.MosaicToNewRaster_management(raster_items,
                                                                target_workspace,
                                                                output_name,
                                                                out_coordinate_system,
                                                                pixel_type,
                                                                number_of_bands=bands.keys()[0],
                                                                mosaic_method='BLEND')
            arcpy.MakeRasterLayer_management(out_mosaic, 'mosaic_layer')
            layer_object = arcpy.mapping.Layer('mosaic_layer')
            task_utils.make_thumbnail(layer_object, os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            skipped += 1
            skipped_reasons['All Items'] = arcpy.GetMessages(2)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), skipped, skipped_details=skipped_reasons)
示例#31
0
def execute(request):
    """Copies files to a target folder.
    :param request: json as a dict.
    """
    extracted = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    output_type = task_utils.get_parameter_value(parameters, 'output_format',
                                                 'value')
    task_folder = os.path.join(request['folder'], 'temp')
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)
        if output_type == 'FGDB':
            arcpy.CreateFileGDB_management(task_folder, 'output.gdb')

    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    # query = '{0}{1}{2}'.format("http://localhost:8888/solr/v0", '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    status_writer.send_percent(0.0, _('Starting to process...'),
                               'locate_xt_arcgis_tool')
    for group in groups:
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)

        docs = results.json()['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']

        input_items = task_utils.get_input_items(docs)
        if input_items:
            result = extract(input_items, output_type, task_folder)
            extracted += result[0]
            errors += result[1]
            skipped += result[2]
        else:
            status_writer.send_state(
                status.STAT_FAILED,
                _('No items to process. Check if items exist.'))
            return

    # Zip up outputs.
    zip_file = task_utils.zip_data(task_folder, 'output.zip')
    shutil.move(
        zip_file,
        os.path.join(os.path.dirname(task_folder), os.path.basename(zip_file)))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'],
                                   '__report.json'), extracted, skipped,
                      errors, errors_reasons, skipped_reasons)
示例#32
0
def execute(request):
    """Converts each input dataset to kml (.kmz).
    :param request: json as a dict.
    """
    converted = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request["params"]

    out_workspace = os.path.join(request["folder"], "temp")
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Get the boundary box extent for input to KML tools.
    extent = ""
    try:
        try:
            ext = task_utils.get_parameter_value(parameters, "processing_extent", "wkt")
            if ext:
                sr = task_utils.get_spatial_reference("4326")
                extent = task_utils.from_wkt(ext, sr)
        except KeyError:
            ext = task_utils.get_parameter_value(parameters, "processing_extent", "feature")
            if ext:
                extent = arcpy.Describe(ext).extent
    except KeyError:
        pass

    # Get the output file name.
    output_file_name = task_utils.get_parameter_value(parameters, "output_file_name", "value")
    if not output_file_name:
        output_file_name = "kml_results"

    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = "{0}{1}{2}".format(sys.argv[2].split("=")[1], "/select?&wt=json", fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")
        query += fq
    elif "ids" in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]["ids"]), task_utils.CHUNK_SIZE, "")
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")

    # Begin processing
    status_writer.send_percent(0.0, _("Starting to process..."), "convert_to_kml")
    headers = {"x-access-token": task_utils.get_security_token(request["owner"])}
    for group in groups:
        if fq:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )
        elif "ids" in parameters[response_index]:
            results = requests.get(query + "{0}&ids={1}".format(fl, ",".join(group)), headers=headers)
        else:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )

        docs = results.json()["response"]["docs"]
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]["response"]["docs"])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if "path" not in doc:
                input_rows[doc["name"]].append(doc)
        if input_rows:
            result = convert_to_kml(input_rows, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = convert_to_kml(input_items, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _("No items to process. Check if items exist."))
            return

    # Zip up kmz files if more than one.
    if converted > 1:
        status_writer.send_status("Converted: {}".format(converted))
        zip_file = task_utils.zip_data(out_workspace, "{0}.zip".format(output_file_name))
        shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        shutil.copy2(
            os.path.join(os.path.dirname(os.path.dirname(__file__)), "supportfiles", "_thumb.png"), request["folder"]
        )
    elif converted == 1:
        try:
            kml_file = glob.glob(os.path.join(out_workspace, "*.kmz"))[0]
            tmp_lyr = arcpy.KMLToLayer_conversion(kml_file, out_workspace, "kml_layer")
            task_utils.make_thumbnail(tmp_lyr.getOutput(0), os.path.join(request["folder"], "_thumb.png"))
        except arcpy.ExecuteError:
            pass
        shutil.move(kml_file, os.path.join(request["folder"], os.path.basename(kml_file)))

    # Update state if necessary.
    if skipped > 0 or errors > 0:
        status_writer.send_state(status.STAT_WARNING, _("{0} results could not be processed").format(errors + skipped))
    task_utils.report(
        os.path.join(request["folder"], "__report.json"), converted, skipped, errors, errors_reasons, skipped_reasons
    )
示例#33
0
def execute(request):
    """Clips selected search results using the clip geometry.
    :param request: json as a dict.
    """
    clipped = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']

    # Retrieve the clip features.
    clip_features = task_utils.get_parameter_value(parameters, 'clip_features', 'value')

    # Retrieve the coordinate system code.
    out_coordinate_system = int(task_utils.get_parameter_value(parameters, 'output_projection', 'code'))

    # Retrieve the output format, create mxd and output file name parameter values.
    out_format = task_utils.get_parameter_value(parameters, 'output_format', 'value')
    create_mxd = task_utils.get_parameter_value(parameters, 'create_mxd', 'value')
    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'clip_results'

    # Create the temporary workspace if clip_feature_class:
    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Set the output coordinate system.
    if not out_coordinate_system == 0:  # Same as Input
        out_sr = task_utils.get_spatial_reference(out_coordinate_system)
        arcpy.env.outputCoordinateSystem = out_sr

    # Set the output workspace.
    status_writer.send_status(_('Setting the output workspace...'))
    if not out_format == 'SHP':
        out_workspace = arcpy.CreateFileGDB_management(out_workspace, 'output.gdb').getOutput(0)
    arcpy.env.workspace = out_workspace

    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl

    # Get the Clip features by id.
    id = clip_features['id']
    clip_query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', "&fl=id,path,fullpath:[absolute],absolute_path:[absolute],[lyrFile],[geo]&q=id:{0}".format(id))
    clip_result = requests.get(clip_query, verify=verify_ssl, headers=headers)
    clipper = clip_result.json()['response']['docs'][0]
    if 'absolute_path' in clipper and not clipper['absolute_path'].startswith('s3'):
        clip_features = clipper['absolute_path']
    elif '[lyrFile]' in clipper:
        clip_features = clipper['[lyrFile]']
    elif '[geo]' in clipper:
        clip_features = arcpy.AsShape(clipper['[geo]']).projectAs(arcpy.SpatialReference(4326))
    elif 'absolute_path' in clipper and clipper['absolute_path'].startswith('s3'):
        base_name = os.path.basename(clipper['path'])
        temp_folder = tempfile.mkdtemp()
        if '[downloadURL]' in clipper:
            download = os.path.join(temp_folder, os.path.basename(clipper['[downloadURL]']))
            response = requests.get(clipper['[downloadURL]'], verify=verify_ssl)
            with open(download, 'wb') as fp:
                fp.write(response.content)
            if download.endswith('.zip'):
                zip = zipfile.ZipFile(download)
                zip.extractall(temp_folder)
                clip_features = os.path.join(temp_folder, base_name)
            else:
                clip_features = download
    else:
        bbox = clipper['bbox'].split()
        extent = arcpy.Extent(*bbox)
        pt_array = arcpy.Array([extent.lowerLeft, extent.upperLeft, extent.upperRight, extent.lowerRight])
        clip_features = arcpy.Polygon(pt_array, 4326)

    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'clip_data')
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), verify=verify_ssl, headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), verify=verify_ssl, headers=headers)

        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
                input_rows[doc['name']].append(doc)
        if input_rows:
            result = clip_data(input_rows, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = clip_data(input_items, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _('No items to process. Check if items exist.'))
            return

    if arcpy.env.workspace.endswith('.gdb'):
        out_workspace = os.path.dirname(arcpy.env.workspace)
    if clipped > 0:
        try:
            if out_format == 'MPK':
                mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                mxd = task_utils.create_mxd(out_workspace, mxd_template, 'output')
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_mpk(out_workspace, mxd, files_to_package)
                shutil.move(os.path.join(out_workspace, 'output.mpk'),
                            os.path.join(os.path.dirname(out_workspace), '{0}.mpk'.format(output_file_name)))
            elif out_format == 'LPK':
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_lpk(out_workspace, output_file_name, files_to_package)
            elif out_format == 'KML':
                task_utils.convert_to_kml(os.path.join(out_workspace, "output.gdb"))
                arcpy.env.workspace = ''
                arcpy.RefreshCatalog(os.path.join(out_workspace, "output.gdb"))
                try:
                    arcpy.Delete_management(os.path.join(out_workspace, "output.gdb"))
                except arcpy.ExecuteError:
                    pass
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
            else:
                if create_mxd:
                    mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                    task_utils.create_mxd(out_workspace, mxd_template, 'output')
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        except arcpy.ExecuteError as ee:
            status_writer.send_state(status.STAT_FAILED, _(ee))
            sys.exit(1)
    else:
        status_writer.send_state(status.STAT_FAILED, _('No output created. Zero inputs were clipped.'))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), clipped, skipped, errors, errors_reasons, skipped_reasons)
示例#34
0
def execute(request):
    """Writes existing metadata for summary, description and tags.
    If overwrite is false, existing metadata is untouched unless any
    field is empty or does not exist, then it is created.

    :param request: json as a dict.
    """
    updated = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']
    summary = task_utils.get_parameter_value(parameters, 'summary', 'value')
    description = task_utils.get_parameter_value(parameters, 'description',
                                                 'value')
    tags = task_utils.get_parameter_value(parameters, 'tags', 'value')
    data_credits = task_utils.get_parameter_value(parameters, 'credits',
                                                  'value')
    constraints = task_utils.get_parameter_value(parameters, 'constraints',
                                                 'value')

    # Handle commas, spaces, and/or new line separators.
    tags = [tag for tag in re.split(' |,|\n', tags) if not tag == '']
    overwrite = task_utils.get_parameter_value(parameters, 'overwrite',
                                               'value')
    if not overwrite:
        overwrite = False
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Stylesheet
    xslt_file = os.path.join(
        arcpy.GetInstallInfo()['InstallDir'],
        'Metadata/Stylesheets/gpTools/exact copy of.xslt')

    # Template metadata file.
    template_xml = os.path.join(os.path.dirname(os.path.dirname(__file__)),
                                'supportfiles', 'metadata_template.xml')

    result_count, response_index = task_utils.get_result_count(parameters)
    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl + ',links'
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'),
                               'write_metadata')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)

        docs = results.json()['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']

        input_items = []
        for doc in docs:
            if 'path' in doc:
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append(
                        (doc['path'], links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['path'], doc['id']))
        result = write_metadata(input_items, template_xml, xslt_file, summary,
                                description, tags, data_credits, constraints,
                                overwrite, headers)
        updated += result[0]
        errors += result[1]
        skipped += result[2]
        status_writer.send_percent(
            i / result_count, '{0}: {1:.0f}%'.format("Processed",
                                                     i / result_count * 100),
            'write_metadata')

    # Report state.
    if skipped > 0 or errors > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped + errors))
    else:
        status_writer.send_state(status.STAT_SUCCESS)
    task_utils.report(os.path.join(request['folder'],
                                   '__report.json'), updated, skipped, errors,
                      errors_reasons, skipped_reasons)
示例#35
0
def execute(request):
    """Writes existing metadata for summary, description and tags.
    If overwrite is false, existing metadata is untouched unless any
    field is empty or does not exist, then it is created.

    :param request: json as a dict.
    """
    updated = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']
    summary = task_utils.get_parameter_value(parameters, 'summary', 'value')
    description = task_utils.get_parameter_value(parameters, 'description', 'value')
    tags = task_utils.get_parameter_value(parameters, 'tags', 'value')
    data_credits = task_utils.get_parameter_value(parameters, 'credits', 'value')
    constraints = task_utils.get_parameter_value(parameters, 'constraints', 'value')

    # Handle commas, spaces, and/or new line separators.
    tags = [tag for tag in re.split(' |,|\n', tags) if not tag == '']
    overwrite = task_utils.get_parameter_value(parameters, 'overwrite', 'value')
    if not overwrite:
        overwrite = False
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Stylesheet
    xslt_file = os.path.join(arcpy.GetInstallInfo()['InstallDir'], 'Metadata/Stylesheets/gpTools/exact copy of.xslt')

    # Template metadata file.
    template_xml = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'metadata_template.xml')

    result_count, response_index = task_utils.get_result_count(parameters)
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl + ',links'
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'), 'write_metadata')
    i = 0.
    for group in groups:
        i += len(group) - group.count('')
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        if not docs:
            docs = parameters[response_index]['response']['docs']

        input_items = []
        for doc in docs:
            if 'path' in doc and os.path.exists(doc['path']):
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append((doc['path'], links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['path'], doc['id']))
            elif 'absolute_path' in doc and os.path.exists(doc['absolute_path']):
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append((doc['absolute_path'], links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['absolute_path'], doc['id']))
            elif '[downloadURL]' in doc:
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append((doc['[downloadURL]'], links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['[downloadURL]'], doc['id']))

        result = write_metadata(input_items, template_xml, xslt_file, summary, description, tags, data_credits, constraints, overwrite, headers)
        updated += result[0]
        errors += result[1]
        skipped += result[2]
        status_writer.send_percent(i / result_count, '{0}: {1:.0f}%'.format("Processed", i / result_count * 100), 'write_metadata')

    # Report state.
    if skipped > 0 or errors > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    else:
        status_writer.send_state(status.STAT_SUCCESS)
    task_utils.report(os.path.join(request['folder'], '__report.json'), updated, skipped, errors, errors_reasons, skipped_reasons)
示例#36
0
def execute(request):
    """Mosaics input raster datasets into a new raster dataset.
    :param request: json as a dict.
    """
    parameters = request['params']
    out_coordinate_system = task_utils.get_parameter_value(parameters, 'output_projection', 'code')
    # Advanced options
    output_raster_format = task_utils.get_parameter_value(parameters, 'raster_format', 'value')
    compression_method = task_utils.get_parameter_value(parameters, 'compression_method', 'value')
    compression_quality = task_utils.get_parameter_value(parameters, 'compression_quality', 'value')
    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'output'
    arcpy.env.compression = '{0} {1}'.format(compression_method, compression_quality)

    clip_area = None
    if not output_raster_format == 'MosaicDataset':
        # Get the clip region as an extent object.
        try:
            clip_area_wkt = task_utils.get_parameter_value(parameters, 'processing_extent', 'wkt')
            if not clip_area_wkt:
                clip_area_wkt = 'POLYGON ((-180 -90, -180 90, 180 90, 180 -90, -180 -90))'
            if not out_coordinate_system == '0':
                clip_area = task_utils.get_clip_region(clip_area_wkt, out_coordinate_system)
            else:
                clip_area = task_utils.get_clip_region(clip_area_wkt)
        except KeyError:
            pass

    status_writer.send_status(_('Setting the output workspace...'))
    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)
    if output_raster_format == 'FileGDB' or output_raster_format == 'MosaicDataset':
        out_workspace = arcpy.CreateFileGDB_management(out_workspace, 'output.gdb').getOutput(0)
    arcpy.env.workspace = out_workspace

    status_writer.send_status(_('Starting to process...'))
    num_results, response_index = task_utils.get_result_count(parameters)
    raster_items = None
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
        else:
            groups = task_utils.grouper(range(0, num_results), task_utils.CHUNK_SIZE, '')

        headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
        for group in groups:
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

            input_items = task_utils.get_input_items(results.json()['response']['docs'])
            if not input_items:
                input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
            raster_items, pixels, bands, skipped = get_items(input_items)
    else:
        input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])
        raster_items, pixels, bands, skipped = get_items(input_items)

    if not raster_items:
        if skipped == 0:
            status_writer.send_state(status.STAT_FAILED, _('Invalid input types'))
            skipped_reasons['All Items'] = _('Invalid input types')
            task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), num_results, skipped_details=skipped_reasons)
            return
        else:
            status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
            task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), skipped, skipped_details=skipped_reasons)
            return

    # Get most common pixel type.
    pixel_type = pixel_types[max(set(pixels), key=pixels.count)]
    if output_raster_format in ('FileGDB', 'GRID', 'MosaicDataset'):
        output_name = arcpy.ValidateTableName('mosaic', out_workspace)
    else:
        output_name = '{0}.{1}'.format(arcpy.ValidateTableName('mosaic', out_workspace)[:9], output_raster_format.lower())
        status_writer.send_status(output_name)

    if output_raster_format == 'MosaicDataset':
        try:
            status_writer.send_status(_('Generating {0}. Large input {1} will take longer to process.'.format('Mosaic', 'rasters')))
            if out_coordinate_system == '0':
                out_coordinate_system = raster_items[0]
            else:
                out_coordinate_system = None
            mosaic_ds = arcpy.CreateMosaicDataset_management(out_workspace,
                                                             output_name,
                                                             out_coordinate_system,
                                                             max(bands),
                                                             pixel_type)
            arcpy.AddRastersToMosaicDataset_management(mosaic_ds, 'Raster Dataset', raster_items)
            arcpy.MakeMosaicLayer_management(mosaic_ds, 'mosaic_layer')
            layer_object = arcpy.mapping.Layer('mosaic_layer')
            task_utils.make_thumbnail(layer_object, os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            status_writer.send_state(status.STAT_FAILED, arcpy.GetMessages(2))
            return
    else:
        try:
            if len(bands) > 1:
                status_writer.send_state(status.STAT_FAILED, _('Input rasters must have the same number of bands'))
                return
            status_writer.send_status(_('Generating {0}. Large input {1} will take longer to process.'.format('Mosaic', 'rasters')))
            if out_coordinate_system == '0':
                out_coordinate_system = None
            if clip_area:
                ext = '{0} {1} {2} {3}'.format(clip_area.XMin, clip_area.YMin, clip_area.XMax, clip_area.YMax)
                tmp_mosaic = arcpy.MosaicToNewRaster_management(
                    raster_items,
                    out_workspace,
                    'tm',
                    out_coordinate_system,
                    pixel_type,
                    number_of_bands=bands.keys()[0]
                )
                status_writer.send_status(_('Clipping...'))
                out_mosaic = arcpy.Clip_management(tmp_mosaic, ext, output_name)
                arcpy.Delete_management(tmp_mosaic)
            else:
                out_mosaic = arcpy.MosaicToNewRaster_management(raster_items,
                                                                out_workspace,
                                                                output_name,
                                                                out_coordinate_system,
                                                                pixel_type, number_of_bands=bands.keys()[0])
            arcpy.MakeRasterLayer_management(out_mosaic, 'mosaic_layer')
            layer_object = arcpy.mapping.Layer('mosaic_layer')
            task_utils.make_thumbnail(layer_object, os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            status_writer.send_state(status.STAT_FAILED, arcpy.GetMessages(2))
            return

    if arcpy.env.workspace.endswith('.gdb'):
        out_workspace = os.path.dirname(arcpy.env.workspace)
    zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
    shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), len(raster_items), skipped, skipped_details=skipped_reasons)
示例#37
0
def execute(request):
    """Adds a field and calculates it to some value.
    :param request: json as a dict.
    """
    created = 0
    skipped = 0
    errors = 0
    warnings = 0
    global result_count
    parameters = request['params']

    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    # Parameter values
    field_name = task_utils.get_parameter_value(parameters, 'field_name', 'value')
    field_type = task_utils.get_parameter_value(parameters, 'field_type', 'value')
    field_value = task_utils.get_parameter_value(parameters, 'field_value', 'value')

    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl + ',links'
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'add_field')
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        docs = results.json()['response']['docs']
        input_items = []
        for doc in docs:
            if 'path' in doc:
                if 'links' in doc:
                    links = eval(doc['links'])
                    input_items.append((doc['id'], doc['path'], links['links'][0]['link'][0]['id']))
                else:
                    input_items.append((doc['id'], doc['path']))

        result = add_field(input_items, field_name, field_type, field_value)
        created += result[0]
        errors += result[1]
        skipped += result[2]
        warnings += result[3]

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(request['folder'], '__report.json'), created, skipped, errors, errors_reasons, skipped_reasons, warnings, warnings_reasons)
示例#38
0
def execute(request):
    """Converts each input dataset to kml (.kmz).
    :param request: json as a dict.
    """
    converted = 0
    skipped = 0
    errors = 0
    global result_count
    parameters = request['params']

    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Get the boundary box extent for input to KML tools.
    extent = ''
    try:
        try:
            ext = task_utils.get_parameter_value(parameters,
                                                 'processing_extent', 'wkt')
            if ext:
                sr = task_utils.get_spatial_reference("4326")
                extent = task_utils.from_wkt(ext, sr)
        except KeyError:
            ext = task_utils.get_parameter_value(parameters,
                                                 'processing_extent',
                                                 'feature')
            if ext:
                extent = arcpy.Describe(ext).extent
    except KeyError:
        pass

    # Get the output file name.
    output_file_name = task_utils.get_parameter_value(parameters,
                                                      'output_file_name',
                                                      'value')
    if not output_file_name:
        output_file_name = 'kml_results'

    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'),
                               'convert_to_kml')
    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    for group in groups:
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                headers=headers)

        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(
                parameters[response_index]['response']['docs'])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
                input_rows[doc['name']].append(doc)
        if input_rows:
            result = convert_to_kml(input_rows, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = convert_to_kml(input_items, out_workspace, extent)
            converted += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(
                status.STAT_FAILED,
                _('No items to process. Check if items exist.'))
            return

    # Zip up kmz files if more than one.
    if converted > 1:
        status_writer.send_status("Converted: {}".format(converted))
        zip_file = task_utils.zip_data(out_workspace,
                                       '{0}.zip'.format(output_file_name))
        shutil.move(
            zip_file,
            os.path.join(os.path.dirname(out_workspace),
                         os.path.basename(zip_file)))
        shutil.copy2(
            os.path.join(os.path.dirname(os.path.dirname(__file__)),
                         'supportfiles', '_thumb.png'), request['folder'])
    elif converted == 1:
        try:
            kml_file = glob.glob(os.path.join(out_workspace, '*.kmz'))[0]
            tmp_lyr = arcpy.KMLToLayer_conversion(kml_file, out_workspace,
                                                  'kml_layer')
            task_utils.make_thumbnail(
                tmp_lyr.getOutput(0),
                os.path.join(request['folder'], '_thumb.png'))
        except arcpy.ExecuteError:
            pass
        shutil.move(
            kml_file,
            os.path.join(request['folder'], os.path.basename(kml_file)))

    # Update state if necessary.
    if skipped > 0 or errors > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'],
                                   '__report.json'), converted, skipped,
                      errors, errors_reasons, skipped_reasons)
示例#39
0
def execute(request):
    """Deletes files.
    :param request: json as a dict.
    """
    deleted = 0
    skipped = 0

    parameters = request['params']
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    num_results, response_index = task_utils.get_result_count(parameters)
    if num_results > task_utils.CHUNK_SIZE:
        # Query the index for results in groups of 25.
        query_index = task_utils.QueryIndex(parameters[response_index])
        fl = query_index.fl
        query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1],
                                   '/select?&wt=json', fl)
        fq = query_index.get_fq()
        if fq:
            groups = task_utils.grouper(range(0, num_results),
                                        task_utils.CHUNK_SIZE, '')
            query += fq
        elif 'ids' in parameters[response_index]:
            groups = task_utils.grouper(
                list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE,
                '')
        else:
            groups = task_utils.grouper(range(0, num_results),
                                        task_utils.CHUNK_SIZE, '')

        status_writer.send_percent(0.0, _('Starting to process...'),
                                   'delete_files')
        i = 0.
        for group in groups:
            i += len(group) - group.count('')
            if fq:
                results = requests.get(query + "&rows={0}&start={1}".format(
                    task_utils.CHUNK_SIZE, group[0]),
                                       headers=headers)
            elif 'ids' in parameters[response_index]:
                results = requests.get(
                    query + '{0}&ids={1}'.format(fl, ','.join(group)),
                    headers=headers)
            else:
                results = requests.get(query + "&rows={0}&start={1}".format(
                    task_utils.CHUNK_SIZE, group[0]),
                                       headers=headers)

            input_items = task_utils.get_input_items(
                results.json()['response']['docs'], True, True)
            if not input_items:
                input_items = task_utils.get_input_items(
                    parameters[response_index]['response']['docs'])

            result = delete_files(input_items)
            deleted += result[0]
            skipped += result[1]
            status_writer.send_percent(
                i / num_results,
                '{0}: {1:.0f}%'.format("Processed",
                                       i / num_results * 100), 'delete_files')
    else:
        input_items = task_utils.get_input_items(
            parameters[response_index]['response']['docs'], True, True)
        deleted, skipped = delete_files(input_items, True)

    # Update state if necessary.
    if skipped > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'),
                      deleted,
                      skipped,
                      skipped_details=skipped_reasons)
示例#40
0
def execute(request):
    """Clips selected search results using the clip geometry.
    :param request: json as a dict.
    """
    clipped = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']

    # Retrieve clip geometry.
    try:
        clip_area = task_utils.get_parameter_value(parameters, 'clip_geometry', 'wkt')
        if not clip_area:
            clip_area = 'POLYGON ((-180 -90, -180 90, 180 90, 180 -90, -180 -90))'
    except KeyError:
        clip_area = 'POLYGON ((-180 -90, -180 90, 180 90, 180 -90, -180 -90))'

    # Retrieve the coordinate system code.
    out_coordinate_system = int(task_utils.get_parameter_value(parameters, 'output_projection', 'code'))

    # Retrieve the output format, create mxd parameter and output file name values.
    out_format = task_utils.get_parameter_value(parameters, 'output_format', 'value')
    create_mxd = task_utils.get_parameter_value(parameters, 'create_mxd', 'value')
    output_file_name = task_utils.get_parameter_value(parameters, 'output_file_name', 'value')
    if not output_file_name:
        output_file_name = 'clip_results'

    # Create the temporary workspace if clip_feature_class:
    out_workspace = os.path.join(request['folder'], 'temp')
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Set the output coordinate system.
    if not out_coordinate_system == 0:  # Same as Input
        out_sr = task_utils.get_spatial_reference(out_coordinate_system)
        arcpy.env.outputCoordinateSystem = out_sr

    # Create the clip polygon geometry object in WGS84 projection.
    gcs_sr = task_utils.get_spatial_reference(4326)
    gcs_clip_poly = task_utils.from_wkt(clip_area, gcs_sr)
    if not gcs_clip_poly.area > 0:
        gcs_clip_poly = task_utils.from_wkt('POLYGON ((-180 -90, -180 90, 180 90, 180 -90, -180 -90))', gcs_sr)

    # Set the output workspace.
    status_writer.send_status(_('Setting the output workspace...'))
    if not out_format == 'SHP':
        out_workspace = arcpy.CreateFileGDB_management(out_workspace, 'output.gdb').getOutput(0)
    arcpy.env.workspace = out_workspace

    # Query the index for results in groups of 25.
    headers = {'x-access-token': task_utils.get_security_token(request['owner'])}
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']), task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, '')

    # Begin processing
    status_writer.send_percent(0.0, _('Starting to process...'), 'clip_data')
    for group in groups:
        if fq:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query + '{0}&ids={1}'.format(fl, ','.join(group)), headers=headers)
        else:
            results = requests.get(query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers)

        # docs = eval(results.read().replace('false', 'False').replace('true', 'True').replace('null', 'None'))['response']['docs']
        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]['response']['docs'])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
               input_rows[doc['name']].append(doc)
        if input_rows:
            result = clip_data(input_rows, out_workspace, out_coordinate_system, gcs_sr, gcs_clip_poly, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = clip_data(input_items, out_workspace, out_coordinate_system, gcs_sr, gcs_clip_poly, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _('No items to process. Check if items exist.'))
            return

    if arcpy.env.workspace.endswith('.gdb'):
        out_workspace = os.path.dirname(arcpy.env.workspace)
    if clipped > 0:
        try:
            if out_format == 'MPK':
                mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                mxd = task_utils.create_mxd(out_workspace, mxd_template, 'output')
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_mpk(out_workspace, mxd, files_to_package)
                shutil.move(os.path.join(out_workspace, 'output.mpk'),
                            os.path.join(os.path.dirname(out_workspace), '{0}.mpk'.format(output_file_name)))
            elif out_format == 'LPK':
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_lpk(out_workspace,output_file_name, files_to_package)
            elif out_format == 'KML':
                task_utils.convert_to_kml(os.path.join(out_workspace, "output.gdb"))
                arcpy.env.workspace = ''
                try:
                    arcpy.Delete_management(os.path.join(out_workspace, "output.gdb"))
                except arcpy.ExecuteError:
                    pass
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
            else:
                if create_mxd:
                    mxd_template = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'supportfiles', 'MapTemplate.mxd')
                    task_utils.create_mxd(out_workspace, mxd_template, 'output')
                zip_file = task_utils.zip_data(out_workspace, '{0}.zip'.format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        except arcpy.ExecuteError as ee:
            status_writer.send_state(status.STAT_FAILED, _(ee))
            sys.exit(1)
    else:
        status_writer.send_state(status.STAT_FAILED, _('No output created. Zero inputs were clipped.'))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _('{0} results could not be processed').format(errors + skipped))
    task_utils.report(os.path.join(request['folder'], '__report.json'), clipped, skipped, errors, errors_reasons, skipped_reasons)
def execute(request):
    """Copies data to an existing geodatabase or feature dataset.
    :param request: json as a dict.
    """
    added = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request['params']

    # Get the target workspace location.
    out_gdb = task_utils.get_parameter_value(parameters, 'target_workspace',
                                             'value')

    # Retrieve the coordinate system code.
    out_coordinate_system = task_utils.get_parameter_value(
        parameters, 'output_projection', 'code')
    if not out_coordinate_system == '0':  # Same as Input
        arcpy.env.outputCoordinateSystem = task_utils.get_spatial_reference(
            out_coordinate_system)

    task_folder = request['folder']
    if not os.path.exists(task_folder):
        os.makedirs(task_folder)

    # Check if the geodatabase exists or if it is a feature dataset.
    is_fds = False
    if not os.path.exists(out_gdb):
        if out_gdb.endswith('.gdb'):
            arcpy.CreateFileGDB_management(os.path.dirname(out_gdb),
                                           os.path.basename(out_gdb))
            status_writer.send_status(
                _('Created output workspace: {0}').format(out_gdb))
        elif out_gdb.endswith('.mdb'):
            arcpy.CreatePersonalGDB_management(os.path.dirname(out_gdb),
                                               os.path.basename(out_gdb))
            status_writer.send_status(
                _('Created output workspace: {0}').format(out_gdb))
        elif out_gdb.endswith('.sde'):
            status_writer.send_state(status.STAT_FAILED,
                                     _('{0} does not exist').format(out_gdb))
            return
        else:
            # Possible feature dataset.
            is_fds = is_feature_dataset(out_gdb)
            if not is_fds:
                if os.path.dirname(out_gdb).endswith('.gdb'):
                    if not os.path.exists(os.path.dirname(out_gdb)):
                        arcpy.CreateFileGDB_management(
                            os.path.dirname(os.path.dirname(out_gdb)),
                            os.path.basename(os.path.dirname(out_gdb)))
                    arcpy.CreateFeatureDataset_management(
                        os.path.dirname(out_gdb), os.path.basename(out_gdb))
                elif os.path.dirname(out_gdb).endswith('.mdb'):
                    if not os.path.exists(os.path.dirname(out_gdb)):
                        arcpy.CreatePersonalGDB_management(
                            os.path.dirname(os.path.dirname(out_gdb)),
                            os.path.basename(os.path.dirname(out_gdb)))
                    arcpy.CreateFeatureDataset_management(
                        os.path.dirname(out_gdb), os.path.basename(out_gdb))

    status_writer.send_status(_('Setting the output workspace...'))
    arcpy.env.workspace = out_gdb

    headers = {
        'x-access-token': task_utils.get_security_token(request['owner'])
    }
    result_count, response_index = task_utils.get_result_count(parameters)
    # Query the index for results in groups of 25.
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl
    query = '{0}{1}{2}'.format(sys.argv[2].split('=')[1], '/select?&wt=json',
                               fl)
    # query = '{0}{1}{2}'.format("http://localhost:8888/solr/v0", '/select?&wt=json', fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')
        query += fq
    elif 'ids' in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]['ids']),
                                    task_utils.CHUNK_SIZE, '')
    else:
        groups = task_utils.grouper(range(0, result_count),
                                    task_utils.CHUNK_SIZE, '')

    status_writer.send_percent(0.0, _('Starting to process...'),
                               'add_to_geodatabase')
    for group in groups:
        if fq:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)
        elif 'ids' in parameters[response_index]:
            results = requests.get(query +
                                   '{0}&ids={1}'.format(fl, ','.join(group)),
                                   verify=verify_ssl,
                                   headers=headers)
        else:
            results = requests.get(
                query +
                "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]),
                verify=verify_ssl,
                headers=headers)

        docs = results.json()['response']['docs']
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(
                parameters[response_index]['response']['docs'])
        input_rows = collections.defaultdict(list)
        for doc in docs:
            if 'path' not in doc:
                input_rows[doc['title']].append(doc)
        if input_rows:
            result = add_to_geodatabase(input_rows, out_gdb, is_fds)
            added += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = add_to_geodatabase(input_items, out_gdb, is_fds)
            added += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(
                status.STAT_FAILED,
                _('No items to process. Check if items exist.'))
            return

    # Update state if necessary.
    if skipped > 0 or errors > 0:
        status_writer.send_state(
            status.STAT_WARNING,
            _('{0} results could not be processed').format(skipped + errors))
    task_utils.report(os.path.join(task_folder, '__report.json'), added,
                      skipped, errors, errors_reasons, skipped_reasons)
def execute(request):
    """Clips selected search results using the clip geometry.
    :param request: json as a dict.
    """
    clipped = 0
    errors = 0
    skipped = 0
    global result_count
    parameters = request["params"]

    # Retrieve the clip features.
    clip_features = task_utils.get_parameter_value(parameters, "clip_features", "value")

    # Retrieve the coordinate system code.
    out_coordinate_system = int(task_utils.get_parameter_value(parameters, "output_projection", "code"))

    # Retrieve the output format, create mxd and output file name parameter values.
    out_format = task_utils.get_parameter_value(parameters, "output_format", "value")
    create_mxd = task_utils.get_parameter_value(parameters, "create_mxd", "value")
    output_file_name = task_utils.get_parameter_value(parameters, "output_file_name", "value")
    if not output_file_name:
        output_file_name = "clip_results"

    # Create the temporary workspace if clip_feature_class:
    out_workspace = os.path.join(request["folder"], "temp")
    if not os.path.exists(out_workspace):
        os.makedirs(out_workspace)

    # Set the output coordinate system.
    if not out_coordinate_system == 0:  # Same as Input
        out_sr = task_utils.get_spatial_reference(out_coordinate_system)
        arcpy.env.outputCoordinateSystem = out_sr

    # Set the output workspace.
    status_writer.send_status(_("Setting the output workspace..."))
    if not out_format == "SHP":
        out_workspace = arcpy.CreateFileGDB_management(out_workspace, "output.gdb").getOutput(0)
    arcpy.env.workspace = out_workspace

    # Query the index for results in groups of 25.
    headers = {"x-access-token": task_utils.get_security_token(request["owner"])}
    result_count, response_index = task_utils.get_result_count(parameters)
    query_index = task_utils.QueryIndex(parameters[response_index])
    fl = query_index.fl

    # Get the Clip features by id.
    id = clip_features["id"]
    clip_query = "{0}{1}{2}".format(
        sys.argv[2].split("=")[1], "/select?&wt=json", "&fl=id,path:[absolute],[lyrFile],[geo]&q=id:{0}".format(id)
    )
    clip_result = requests.get(clip_query, headers=headers)
    clipper = clip_result.json()["response"]["docs"][0]
    if "path" in clipper:
        clip_features = clipper["path"]
    elif "[lyrFile]" in clipper:
        clip_features = clipper["[lyrFile]"]
    elif "[geo]" in clipper:
        clip_features = arcpy.AsShape(clipper["[geo]"]).projectAs(arcpy.SpatialReference(4326))
    else:
        bbox = clipper["bbox"].split()
        extent = arcpy.Extent(*bbox)
        pt_array = arcpy.Array([extent.lowerLeft, extent.upperLeft, extent.upperRight, extent.lowerRight])
        clip_features = arcpy.Polygon(pt_array, 4326)

    query = "{0}{1}{2}".format(sys.argv[2].split("=")[1], "/select?&wt=json", fl)
    fq = query_index.get_fq()
    if fq:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")
        query += fq
    elif "ids" in parameters[response_index]:
        groups = task_utils.grouper(list(parameters[response_index]["ids"]), task_utils.CHUNK_SIZE, "")
    else:
        groups = task_utils.grouper(range(0, result_count), task_utils.CHUNK_SIZE, "")

    status_writer.send_percent(0.0, _("Starting to process..."), "clip_data")
    for group in groups:
        if fq:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )
        elif "ids" in parameters[response_index]:
            results = requests.get(query + "{0}&ids={1}".format(fl, ",".join(group)), headers=headers)
        else:
            results = requests.get(
                query + "&rows={0}&start={1}".format(task_utils.CHUNK_SIZE, group[0]), headers=headers
            )

        # docs = eval(results.read().replace('false', 'False').replace('true', 'True').replace('null', 'None'))['response']['docs']
        docs = results.json()["response"]["docs"]
        input_items = task_utils.get_input_items(docs)
        if not input_items:
            input_items = task_utils.get_input_items(parameters[response_index]["response"]["docs"])

        input_rows = collections.defaultdict(list)
        for doc in docs:
            if "path" not in doc:
                input_rows[doc["name"]].append(doc)
        if input_rows:
            result = clip_data(input_rows, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if input_items:
            result = clip_data(input_items, out_workspace, clip_features, out_format)
            clipped += result[0]
            errors += result[1]
            skipped += result[2]

        if not input_items and not input_rows:
            status_writer.send_state(status.STAT_FAILED, _("No items to process. Check if items exist."))
            return

    if arcpy.env.workspace.endswith(".gdb"):
        out_workspace = os.path.dirname(arcpy.env.workspace)
    if clipped > 0:
        try:
            if out_format == "MPK":
                mxd_template = os.path.join(
                    os.path.dirname(os.path.dirname(__file__)), "supportfiles", "MapTemplate.mxd"
                )
                mxd = task_utils.create_mxd(out_workspace, mxd_template, "output")
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_mpk(out_workspace, mxd, files_to_package)
                shutil.move(
                    os.path.join(out_workspace, "output.mpk"),
                    os.path.join(os.path.dirname(out_workspace), "{0}.mpk".format(output_file_name)),
                )
            elif out_format == "LPK":
                status_writer.send_status(_("Packaging results..."))
                task_utils.create_lpk(out_workspace, output_file_name, files_to_package)
            elif out_format == "KML":
                task_utils.convert_to_kml(os.path.join(out_workspace, "output.gdb"))
                arcpy.env.workspace = ""
                arcpy.RefreshCatalog(os.path.join(out_workspace, "output.gdb"))
                try:
                    arcpy.Delete_management(os.path.join(out_workspace, "output.gdb"))
                except arcpy.ExecuteError:
                    pass
                zip_file = task_utils.zip_data(out_workspace, "{0}.zip".format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
            else:
                if create_mxd:
                    mxd_template = os.path.join(
                        os.path.dirname(os.path.dirname(__file__)), "supportfiles", "MapTemplate.mxd"
                    )
                    task_utils.create_mxd(out_workspace, mxd_template, "output")
                zip_file = task_utils.zip_data(out_workspace, "{0}.zip".format(output_file_name))
                shutil.move(zip_file, os.path.join(os.path.dirname(out_workspace), os.path.basename(zip_file)))
        except arcpy.ExecuteError as ee:
            status_writer.send_state(status.STAT_FAILED, _(ee))
            sys.exit(1)
    else:
        status_writer.send_state(status.STAT_FAILED, _("No output created. Zero inputs were clipped."))

    # Update state if necessary.
    if errors > 0 or skipped > 0:
        status_writer.send_state(status.STAT_WARNING, _("{0} results could not be processed").format(errors + skipped))
    task_utils.report(
        os.path.join(request["folder"], "__report.json"), clipped, skipped, errors, errors_reasons, skipped_reasons
    )
示例#43
0
def execute(request):
    """Report duplicate items.
    :param request: json as a dict.
    """
    if not os.path.exists(request['folder']):
        os.makedirs(request['folder'])
    date_str = str(datetime.date.today())
    report_file = os.path.join(request['folder'], 'Duplicates_{0}.csv'.format(date_str))

    request_owner = request['owner']
    headers = {'x-access-token': task_utils.get_security_token(request_owner)}

    fields = list(task_utils.get_parameter_value(request['params'], 'fields', 'value'))
    required_fields = ("name", "title", "bytes", "id", "format", "absolute_path", "format_category")
    [fields.remove(f) for f in required_fields if f in fields]

    fields_str = ""
    if fields:
        fields_str = ",".join(fields)

    voyager_instance = 'http://localhost:8888/solr/v0' #sys.argv[2].split('=')[1]
    #voyager_instance = 'http://ec2amaz-7h0t5qu.tnc.sdi.org:8888/solr/v0'
    query =  "%s/select?q={!func}joindf(md5,md5)&f.md5.facet.mincount=2&f.contentHash.facet.mincount=2&f.schemaHash.facet.mincount=2&sort=md5 desc&start=0&rows=1&fl=id,title,name:[name],format,fullpath:[absolute],absolute_path:[absolute],format_type,bytes,md5,path,name&fq={!frange l=2}{!func}joindf(md5,md5)&wt=json" % (voyager_instance)
    results = requests.get(query, auth=('admin', 'admin'))
    result_count = results.json()['response']['numFound']
    if result_count == 0:
        status_writer.send_state(status.STAT_WARNING, "No duplicates found.")
        return
    duplicates = collections.defaultdict(list)
    groups = grouper(range(0, result_count), 150, '')

    url = voyager_instance.split("/solr")[0]
    req = requests.get("{0}/api/rest/i18n/field/format".format(url), headers=headers)
    formats = req.json()['VALUE']['format']

    processed_count = 0

    status_writer.send_status("Generating list of documents with children...")
    parent_docs = create_listcount_data_in_doc(voyager_instance, headers)

    increment = task_utils.get_increment(result_count)
    for group in groups:
        query = "%s/select?q={!func}joindf(md5,md5)&f.md5.facet.mincount=2&f.contentHash.facet.mincount=2&f.schemaHash.facet.mincount=2&sort=md5 desc&start=%s&rows=150&fl=md5,id,title,name:[name],format,fullpath:[absolute],absolute_path:[absolute],format_type,format_category,bytes,linkcount_data,linkcount_md5,path,name,%s&fq={!frange l=2}{!func}joindf(md5,md5)&wt=json" % (voyager_instance, group[0], fields_str)
        results = requests.get(query, headers=headers)
        docs = results.json()['response']['docs']
        for doc in docs:
            file_path = ""
            if "absolute_path" in doc:
                file_path = doc["absolute_path"]
                if os.path.splitext(file_path)[1].lower() in ('.cpg', '.ini'):
                    continue

            file_size = 0
            if "bytes" in doc:
                file_size = float(doc['bytes'])

            format_type = ""
            if "format" in doc and not doc["format"] in ("application/vnd.esri.gdb.file.data", "application/vnd.esri.gdb.personal.data"):
                try:
                    format_type = formats[doc["format"]]
                except KeyError:
                    format_type = doc["format"]
            else:
                continue

            format_category = ""
            if "format_category" in doc:
                format_category = doc["format_category"]

            id = ""
            if "id" in doc:
                id = doc["id"]

            name = ""
            if "name" in doc:
                name = doc["name"]
            elif "title" in doc:
                name = doc["title"]

            field_dict = {"FILE NAME": name, "FILE SIZE": file_size, "FORMAT CATEGORY": format_category,
                          "FORMAT": format_type, "ID": id, "FILE PATH": file_path}

            extra_fields = {}
            if fields:
                for fld in fields:
                    if fld in doc:
                        extra_fields[fld.upper()] = doc[fld]

            field_dict.update(extra_fields)
            duplicates[doc['md5']].append(field_dict)
        processed_count += len(group)
        if (processed_count % increment) == 0:
            status_writer.send_percent(processed_count / float(result_count), 'Grouping duplicates by MD5...', 'report_duplicate_files')

    # Find total number of items in the index.
    all_query = "%s/select?&disp=default&sort=score desc&place.op=within&start=0&fl=id&voyager.config.id=ace4bb77&wt=json" % (voyager_instance)
    results = requests.get(all_query, headers=headers)
    index_count = results.json()['response']['numFound']

    duplicate_count = 0
    total_file_size = 0

    # Write all the duplicates to the report file.
    status_writer.send_percent(0, 'Creating the duplicate report and comparing data...', '')
    processed_count = 0
    md5_count = len(duplicates)
    increment = task_utils.get_increment(md5_count)
    with open(report_file, "wb") as f:
        if extra_fields:
            keys = ["MD5", "FILE NAME", "FILE SIZE", "FORMAT", "FORMAT CATEGORY", "ID", "FILE PATH", "MXD COUNT", "LYR COUNT"] + extra_fields.keys()
        else:
            keys = ["MD5", "FILE NAME", "FILE SIZE", "FORMAT", "FORMAT CATEGORY", "ID", "FILE PATH", "MXD COUNT", "LYR COUNT"]
        writer = csv.DictWriter(f, fieldnames=keys)
        writer.writeheader()

        # Loop through each group of MD5 (duplicates).
        for md5, values in duplicates.items():
            try:
                val_count = len(values)
                if val_count > 1:
                    # If the files sizes are all 0 bytes, return them as duplicates.
                    file_size = convert_size(values[0]['FILE SIZE'])
                    for z in values:
                        if not convert_size(z['FILE SIZE']) == file_size:
                            values.remove(z)
                    if len(values) == 1:
                        processed_count += 1
                        continue

                    # Perform data comparison (Feature, Table, File, raster, etc.). If different, don't report and continue.
                    max_severity = compare_data(values)
                    if max_severity > 0:
                        continue

                    writer.writerow({})
                    duplicate_count += val_count - 1
                    for val in values:
                        used_in_mxd = 0
                        used_in_lyr = 0
                        total_file_size += val["FILE SIZE"] * (val_count - 1)
                        val["MD5"] = md5
                        val["FILE SIZE"] = convert_size(val["FILE SIZE"])
                        new_val = {k: change(v, 'utf-8') for (k, v) in val.items()}
                        if new_val["FORMAT CATEGORY"].lower() in ("gis", "cad", "imagery"):
                            for k,v in parent_docs.items():
                                if new_val['ID'] in v:
                                    if k.endswith('.mxd'):
                                        used_in_mxd += 1
                                    elif k.endswith('.lyr'):
                                        used_in_lyr += 1
                        new_val['MXD COUNT'] = used_in_mxd
                        val['MXD COUNT'] = used_in_mxd
                        new_val['LYR COUNT'] = used_in_lyr
                        val['LYR COUNT'] = used_in_lyr
                        try:
                            writer.writerow(new_val)
                        except UnicodeEncodeError:
                            try:
                                new_val = {k: change(v, 'latin-1') for (k, v) in new_val.items()}
                                writer.writerow(new_val)
                            except Exception as we:
                                status_writer.send_status('WRITE ERROR: {0}'.format(repr(we)))
                                pass
                processed_count += 1
            except Exception as ex:
                status_writer.send_status(repr(ex))
                processed_count += 1
                continue
            try:
                if (processed_count % increment) == 0:
                    status_writer.send_percent(processed_count / float(md5_count), 'Creating report and comparing data...', 'report_duplicate_files')
            except Exception:
                status_writer.send_status("error reporting progress.")
                continue
    try:
        # Report a summary to the report file.
        pct_dups = float(duplicate_count) / index_count
        with open(report_file, "ab") as f:
            writer = csv.DictWriter(f, fieldnames=["DUPLICATE COUNT", "INDEX COUNT", "PERCENT DUPLICATES", "TOTAL DUPLICATE FILE SIZE"])
            writer.writerow({})
            writer.writerow({})
            writer.writeheader()
            writer.writerow({"DUPLICATE COUNT": duplicate_count,
                             "INDEX COUNT": index_count,
                             "PERCENT DUPLICATES": '{:.0f}%'.format(pct_dups * 100),
                             "TOTAL DUPLICATE FILE SIZE": convert_size(total_file_size)})

        status_writer.send_status("DUPLICATE COUNT: {0}".format(duplicate_count))
        status_writer.send_status("INDEX COUNT: {0}".format(index_count))
        status_writer.send_status("PERCENT DUPLICATES: {0}".format('{:.0f}%'.format(pct_dups * 100)))
        status_writer.send_status("TOTAL DUPLICATE FILE SIZE: {0}".format(convert_size(total_file_size)))
        status_writer.send_state(status.STAT_SUCCESS)
    except Exception:
        status_writer.send_status("Error writing summary.")