On duplicates in the new logbooks

library(tidyverse)
library(mar)
# Functions --------------------------------------------------------------------
lb_trip_new <- function(con) {
  tbl_mar(con, "adb.trip_v") |> 
    select(trip_id, 
           vid = vessel_no,
           T1 = departure,
           hid1 = departure_port_no,
           T2 = landing,
           hid2 = landing_port_no,
           source)
}
lb_station_new0 <- function(con) {
  tbl_mar(con, "adb.station_v") |> 
    select(trip_id,
           station_id,
           gid = gear_no,
           t1 = fishing_start,
           t2 = fishing_end,
           lon = longitude,
           lat = latitude,
           lon2 = longitude_end,
           lat2 = latitude_end,
           z1 = depth,
           z2 = depth_end,
           tow_start,
           everything())
}
lb_base_new <- function(con) {
  lb_trip_new(con) |> 
    inner_join(lb_station_new0(con) |> 
                 select(trip_id:tow_start),
               by = "trip_id") |> 
    select(vid, gid, t1:tow_start, everything()) |> 
    mutate(whack = case_when(between(lon, 10, 30) & between(lat, 62.5, 67.6) ~ "mirror",
                             between(lon, -3, 3) & gid != 7 ~ "ghost",
                             .default = "ok"),
           lon = ifelse(whack == "mirror",
                        -lon,
                        lon),
           lon2 = ifelse(whack == "mirror",
                         -lon2,
                         lon2))
}
lb_catch_new <- function(con) {
  tbl_mar(con, "adb.catch") |> 
    mutate(catch = case_when(condition == "GUTT" ~ quantity / 0.8,
                             condition == "UNGU" ~ quantity,
                             .default = NA)) |> 
    select(station_id = fishing_station_id,
           sid = species_no, 
           catch, 
           weight, 
           quantity, 
           condition, 
           catch_type = source_type)
}


con <- connect_mar()
trips <- 
  lb_trip_new(con) |> 
  collect() |> 
  group_by(vid, T1, T2) |> 
  mutate(replicates = n(),
         source = n_distinct(source)) |> 
  ungroup()

The total number of records in the trip table is 257579 while the number of distinct vessel, departure and arrivals are 254111, a diference of some 3468 records.