Estrazione di dati dal catalogo AWS Glue dati per l'analisi delle chiamate di Amazon SDK Chime

call_analytics_metadataha il JSON campo in formato stringa. metadata Usa la funzione json_extract_scalar in Athena per interrogare gli elementi di questa stringa.

SELECT
    json_extract_scalar(metadata,'$.voiceConnectorId') AS "VoiceConnector ID",
    json_extract_scalar(metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(metadata,'$.callId') AS "Call ID",
    json_extract_scalar(metadata,'$.direction') AS Direction,
    json_extract_scalar(metadata,'$.transactionId') AS "Transaction ID"
FROM 
    "GlueDatabaseName"."call_analytics_metadata"

Il campo contiene il call_analytics_metadata campo dei metadati in formato stringa. JSON metadataha un altro oggetto annidato chiamatooneTimeMetadata, questo oggetto contiene SIPRec metadati in formati originali XML e trasformati. JSON Usa la json_extract_scalar funzione in Athena per interrogare gli elementi di questa stringa.

SELECT
    json_extract_scalar(metadata,'$.voiceConnectorId') AS "VoiceConnector ID",
    json_extract_scalar(metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(metadata,'$.callId') AS "Call ID",
    json_extract_scalar(metadata,'$.direction') AS Direction,
    json_extract_scalar(metadata,'$.transactionId') AS "Transaction ID",
    json_extract_scalar(json_extract_scalar(metadata,'$.oneTimeMetadata'),'$.siprecMetadata') AS "siprec Metadata XML",
    json_extract_scalar(json_extract_scalar(metadata,'$.oneTimeMetadata'),'$.siprecMetadataJson') AS "Siprec Metadata JSON",
    json_extract_scalar(json_extract_scalar(metadata,'$.oneTimeMetadata'),'$.inviteHeaders') AS "Invite Headers"
FROM 
    "GlueDatabaseName"."call_analytics_metadata"
WHERE 
    callevent-type = "update";

call_analytics_recording_metadataha il campo dei JSON metadati in formato stringa. Usa la funzione json_extract_scalar in Athena per interrogare gli elementi di questa stringa.

SELECT
    json_extract_scalar(metadata,'$.voiceConnectorId') AS "VoiceConnector ID",
    json_extract_scalar(metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(metadata,'$.callId') AS "Call ID",
    json_extract_scalar(metadata,'$.direction') AS Direction,
    json_extract_scalar(metadata,'$.transactionId') AS "Transaction ID"
FROM 
    "GlueDatabaseName"."call_analytics_recording_metadata"
WHERE 
    detail-subtype = "Recording"

voice_analytics_statusha un campo di dettagli nel tipo di datistruct. L'esempio seguente mostra come interrogare un campo di tipo di struct dati:

SELECT
    detail.transactionId AS "Transaction ID",
    detail.voiceConnectorId AS "VoiceConnector ID",
    detail.siprecmetadata AS "Siprec Metadata",
    detail.inviteheaders AS "Invite Headers",
    detail.streamStartTime AS "Stream Start Time"
FROM 
    "GlueDatabaseName"."voice_analytics_status"

La seguente query di esempio unisce e: call_analytics_metadata voice_analytics_status

SELECT
    a.detail.transactionId AS "Transaction ID",
    a.detail.voiceConnectorId AS "VoiceConnector ID",
    a.detail.siprecmetadata AS "Siprec Metadata",
    a.detail.inviteheaders AS "Invite Headers",
    a.detail.streamStartTime AS "Stream Start Time"
    json_extract_scalar(b.metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(b.metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(b.metadata,'$.callId') AS "Call ID",
    json_extract_scalar(b.metadata,'$.direction') AS Direction
FROM 
    "GlueDatabaseName"."voice_analytics_status" a
INNER JOIN 
    "GlueDatabaseName"."call_analytics_metadata" b
ON a.detail.transactionId = json_extract_scalar(b.metadata,'$.transactionId')

transcribe_call_analytics_post_call ha un campo di trascrizione in formato struct con array annidati. Utilizzate la seguente query per rimuovere l'annidamento degli array:

SELECT 
    jobstatus,
    languagecode,
    IF(CARDINALITY(m.transcript)=0 OR CARDINALITY(m.transcript) IS NULL, NULL, e.transcript.id) AS utteranceId,
    IF(CARDINALITY(m.transcript)=0 OR CARDINALITY(m.transcript) IS NULL, NULL, e.transcript.content) AS transcript,
    accountid,
    channel,
    sessionid,
    contentmetadata.output AS "Redaction"
FROM 
    "GlueDatabaseName"."transcribe_call_analytics_post_call" m
CROSS JOIN UNNEST
    (IF(CARDINALITY(m.transcript)=0, ARRAY[NULL], transcript)) AS e(transcript)

La seguente query unisce transcribe_call_analytics_post_call e call_analytics_metadata:

WITH metadata AS(
  SELECT 
    from_iso8601_timestamp(time) AS "Timestamp",
    date_parse(date_format(from_iso8601_timestamp(time), '%m/%d/%Y %H:%i:%s') , '%m/%d/%Y %H:%i:%s') AS "DateTime",
    date_parse(date_format(from_iso8601_timestamp(time) , '%m/%d/%Y') , '%m/%d/%Y') AS "Date",
    date_format(from_iso8601_timestamp(time) , '%H:%i:%s')  AS "Time",
    mediainsightspipelineid,
    json_extract_scalar(metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(metadata,'$.voiceConnectorId') AS "VoiceConnector ID",
    json_extract_scalar(metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(metadata,'$.callId') AS "Call ID",
    json_extract_scalar(metadata,'$.direction') AS Direction,
    json_extract_scalar(metadata,'$.transactionId') AS "Transaction ID",
    REGEXP_REPLACE(REGEXP_EXTRACT(json_extract_scalar(metadata,'$.oneTimeMetadata.s3RecordingUrl'), '[^/]+(?=\.[^.]+$)'), '\.wav$', '') AS "SessionID"
  FROM 
    "GlueDatabaseName"."call_analytics_metadata"
),
transcript_events AS(
  SELECT 
    jobstatus,
    languagecode,
    IF(CARDINALITY(m.transcript)=0 OR CARDINALITY(m.transcript) IS NULL, NULL, e.transcript.id) AS utteranceId,
    IF(CARDINALITY(m.transcript)=0 OR CARDINALITY(m.transcript) IS NULL, NULL, e.transcript.content) AS transcript,
    accountid,
    channel,
    sessionid,
    contentmetadata.output AS "Redaction"
  FROM 
    "GlueDatabaseName"."transcribe_call_analytics_post_call" m
  CROSS JOIN UNNEST
    (IF(CARDINALITY(m.transcript)=0, ARRAY[NULL], transcript)) AS e(transcript)
)
SELECT 
    jobstatus,
    languagecode,
    a.utteranceId,
    transcript,
    accountid,
    channel,
    a.sessionid,
    "Redaction"
    "Timestamp",
    "DateTime",
    "Date",
    "Time",
    mediainsightspipelineid,
    "To Number",
    "VoiceConnector ID",
    "From Number",
    "Call ID",
    Direction,
    "Transaction ID"
FROM 
    "GlueDatabaseName"."transcribe_call_analytics_post_call" a
LEFT JOIN 
    metadata b
ON 
    a.sessionid = b.SessionID

Il seguente esempio di query si unisce: Voice enhancement call recording URL

SELECT 
    json_extract_scalar(metadata,'$.voiceConnectorId') AS "VoiceConnector ID",
    json_extract_scalar(metadata,'$.fromNumber') AS "From Number",
    json_extract_scalar(metadata,'$.toNumber') AS "To Number",
    json_extract_scalar(metadata,'$.callId') AS "Call ID",
    json_extract_scalar(metadata,'$.direction') AS Direction,
    json_extract_scalar(metadata,'$.transactionId') AS "Transaction ID",
    s3MediaObjectConsoleUrl
FROM
    {GlueDatabaseName}."call_analytics_recording_metadata"
WHERE
    detail-subtype = "VoiceEnhancement"