From c1f56c61e82e504ef662bb10bea725f7c287a8be Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Wed, 24 Nov 2021 18:33:06 +0100
Subject: [PATCH] Add a function to pull start and end datetimes.

---
 src/data/streams/aware_postgresql/container.R | 45 ++++++++++++++++++-
 1 file changed, 44 insertions(+), 1 deletion(-)

diff --git a/src/data/streams/aware_postgresql/container.R b/src/data/streams/aware_postgresql/container.R
index 30e8e5ac..8f4c6a06 100644
--- a/src/data/streams/aware_postgresql/container.R
+++ b/src/data/streams/aware_postgresql/container.R
@@ -134,7 +134,7 @@ pull_participants_ids <- function(stream_parameters, usernames, participants_con
 }
 
 #' @description
-#' Gets participants' IDs for specified usernames.
+#' Gets participants' IDs for specified participant IDs
 #'
 #' @param stream_parameters The PHONE_DATA_STREAMS key in config.yaml. If you need specific parameters add them there.
 #' @param participants_ids A vector of numeric participant IDs
@@ -142,6 +142,7 @@ pull_participants_ids <- function(stream_parameters, usernames, participants_con
 #' @return A dataframe with a row matching each distinct device ID with a participant ID
 
 pull_participants_device_ids <- function(stream_parameters, participants_ids, device_id_container) {
+  dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
 
   query_device_id <- tbl(dbEngine, device_id_container) %>% 
     filter(participant_id %in% !!participants_ids) %>% 
@@ -160,4 +161,46 @@ pull_participants_device_ids <- function(stream_parameters, participants_ids, de
   return(device_ids)
 }
 
+#' @description
+#' Gets start and end datetimes for specified participant IDs.
+#'
+#' @param stream_parameters The PHONE_DATA_STREAMS key in config.yaml. If you need specific parameters add them there.
+#' @param participants_ids A vector of numeric participant IDs
+#' @param start_end_date_container The name of the database table which will be used to determine when a participant started and ended their participation. Briefing and debriefing EMAs can be meaningfully used here.
+#' @return A dataframe relating participant IDs with their start and end datetimes.
+
+pull_participants_start_end_dates <- function(stream_parameters, participants_ids, start_end_date_container) {
+  dbEngine <- get_db_engine(stream_parameters$DATABASE_GROUP)
+
+  query_timestamps <- tbl(dbEngine, start_end_date_container) %>% 
+    filter(
+      participant_id %in% !!participant_data$id,
+      double_esm_user_answer_timestamp > 0
+    ) %>% 
+    group_by(participant_id) %>% 
+    summarise(
+      timestamp_min = min(double_esm_user_answer_timestamp, na.rm = TRUE),
+      timestamp_max = max(double_esm_user_answer_timestamp, na.rm = TRUE)
+    ) %>% 
+    select(participant_id, timestamp_min, timestamp_max)
+  
+  message(paste0("Executing the following query to get the starting and ending datetimes: \n", sql_render(query_timestamps)))
+  
+  start_end_timestamps <- query_timestamps %>% collect()
+  
+  if(nrow(start_end_timestamps) == 0)
+    warning(paste("We could not find datetimes for requested participant IDs (", participants_ids,  ") in ", device_id_container))
+
+  start_end_times <- start_end_timestamps %>% 
+    mutate(    
+      datetime_start = as_datetime(timestamp_min/1000, tz = "UTC"),
+      datetime_end = as_datetime(timestamp_max/1000, tz = "UTC")
+    ) %>% 
+    select(-c(timestamp_min, timestamp_max))
+  
+  dbDisconnect(dbEngine)
+  
+  return(start_end_times)
+}
+