Стратегии избежать В спящем режиме LazyInitializationExceptions

Комментарии в коде:

#!/bin/bash

# Scenario 1

echo 'filename    filesize    data_received_dt    tname   createdt
ccaa/01APR2018-revised/ 0   2019-01-17T06:16:59.000Z    sample  2018-03-15T09:51:36.000Z
ccaa/01APR2018/content_01APR2018-00000.csv  115814528   2018-12-05T23:38:10.000Z    live    2018-03-15T09:51:36.000Z
ccaa/01APR2018-revised/content_01APR2018-00001.csv  116584541   2018-12-05T23:38:09.000Z    test    2018-03-15T09:51:36.000Z
ccaa/01JUN2018-revised/content_01JUN2018-00002.csv  117363985   2018-12-05T23:38:09.000Z    sample  2018-03-15T09:51:36.000Z
ccaa/10JUL2018/content_10JUL2018-00002.csv  117363985   2018-12-05T23:38:09.000Z    sample  2018-03-15T09:51:36.000Z
ccaa/21AUG2018-revised/content_21AUG2018-00002.csv  117363985   2018-12-05T23:38:09.000Z    sample  2018-03-15T09:51:36.000Z
' |
# remove first line with headers
tail -n +2 |
# for each line
while 
    IFS=' ' read -r name size received_dt tname create_dt &&
    # stop on empty lines
    [ -n "$name" ]
do

    # get the second directory name from the name
    # this is a smarty way of getting the last second field from the right
    dir=$(<<<"$name" rev | cut -d'/' -f2 | rev)

    # if the 2nd dir doesn't end with -revised, add -revised 
    # (I think this could be just one sed command)
    if ! <<<"$dir" grep -q -- "-revised$"; then
        dir2=$(dirname "$(dirname "$name")")
        dir="${dir}-revised"
        name=$dir2/$dir/$(basename "$name")
    fi

    # extract date data from the dir
    day_from_dir=${dir:0:2}
    month_from_dir="${dir:2:1}$(<<<"${dir:3:2}" tr [:upper:] [:lower:])"
    year_from_dir="20${dir:7:2}"

    # get start and end dates
    start_dt=$(
        LC_ALL=C date \
        --date="${day_from_dir} ${month_from_dir} ${year_from_dir} 00:00:00" \
        +%-d-%b-%g
    )
    end_dt=$start_dt

    # printf ouput
    printf "%s %s %s %s %s %s %s\n" \
        "$name" \
        "$start_dt" \
        "$end_dt" \
        "$size" \
        "$received_dt" \
        "$tname" \
        "$create_dt"

done |
# format the output - left justify and set column names
column -t -s ' ' -o '  ' -N \
    "filename,start_dt,end_dt,filesize,data_received_dt,name,createdt"


# Scenario 2

echo 'filename                        size        date                        tname
ccaa/201802/                    0           2019-01-17T06:16:34.000Z    sample
ccaa/201802/Feb2018000000_0.csv 32602738    2018-09-11T04:05:38.000Z    live
ccaa/201804/Feb2018000001_0.csv 32602738    2018-09-11T04:05:38.000Z    test
ccaa/201805/Feb2018000002_0.csv 32602738    2018-09-11T04:05:38.000Z    sample
ccaa/201806/Feb2018000003_0.csv 32602187    2018-09-11T04:05:38.000Z    sample
' |
tail -n +2 |
while 
    IFS=' ' read -r name size date tname && [ -n "$name" ]
do
    # get the second directory name from the name
    # this is a smarty way of getting the last second field from the right
    dir=$(<<<"$name" rev | cut -d'/' -f2 | rev)

    # extract date from dir
    year=${dir:0:4}
    month=${dir:4:2}
    ts="${year}-${month}-01T00:00:00-00:00"

    # set date format
    start_dt=$(
        LC_ALL=C date \
        --date="$ts" \
        +%-d-%b-%g
    )
    # we want last month day - add 1 month and subtract 1 day
    end_dt=$(
        LC_ALL=C date \
        --date="$ts +1 month -1 day" \
        +%-d-%b-%g
    )

    # and output
    printf "%s %s %s %s %s %s\n" \
        "$name" \
        "$start_dt" \
        "$end_dt" \
        "$size" \
        "$date" \
        "$tname"

done |
column -t -s ' ' -o '  ' -N \
"filename,start_dt,end_dt,size,date,tname"

# Scenario 3 - same as 2 but different naming scheme or smth

echo 'filename                        size        date                        tname
ccaa/201802/                    0           2019-01-17T06:16:34.000Z    sample
ccaa/201802/Feb2018000000_0.csv 32602738    2018-09-11T04:05:38.000Z    live
ccaa/201804/Feb2018000001_0.csv 32602738    2018-09-11T04:05:38.000Z    test
ccaa/201805/Feb2018000002_0.csv 32602738    2018-09-11T04:05:38.000Z    sample
ccaa/201808/Feb2018000003_0.csv 32602187    2018-09-11T04:05:38.000Z    sample
' |
tail -n +2 |
while 
    IFS=' ' read -r name size date tname &&
    [ -n "$name" ]
do
    # get the second directory name from the name
    # this is a smarty way of getting the last second field from the right
    dir=$(<<<"$name" rev | cut -d'/' -f2 | rev)


    #extract date from dir
    year=${dir:0:4}
    month=${dir:4:2}
    ts="${year}-${month}-01T00:00:00-00:00"
    quarter=$(
        LC_ALL=C date \
        --date="$ts" \
        +%q
    )

    #rename the file with the year-Qq
    tmp="$(dirname "$(dirname "$name")")/${year}-Q${quarter}/"
    if ! <<<"$name" grep -q "/$"; then
        name="${tmp}$(basename "$name")"
    fi

    # set date format
    start_dt=$(
        LC_ALL=C date \
        --date="$ts" \
        +%-d-%b-%g
    )
    # we want last month day - add 1 month and subtract 1 day
    end_dt=$(
        LC_ALL=C date \
        --date="$ts  +1 month -1 day" \
        +%-d-%b-%g
    )

    # and output
    printf "%s %s %s %s %s %s\n" \
        "$name" \
        "$start_dt" \
        "$end_dt" \
        "$size" \
        "$date" \
        "$tname"

done |
# add create nice looking table with header names
column -t -s ' ' -o '  ' -N \
"filename,start_dt,end_dt,size,date,tname"

Вывод из jdoodle :

filename                                            start_dt   end_dt     filesize   data_received_dt          name    createdt
ccaa/01APR2018-revised/                             1-Apr-18   1-Apr-18   0          2019-01-17T06:16:59.000Z  sample  2018-03-15T09:51:36.000Z
ccaa/01APR2018-revised/content_01APR2018-00000.csv  1-Apr-18   1-Apr-18   115814528  2018-12-05T23:38:10.000Z  live    2018-03-15T09:51:36.000Z
ccaa/01APR2018-revised/content_01APR2018-00001.csv  1-Apr-18   1-Apr-18   116584541  2018-12-05T23:38:09.000Z  test    2018-03-15T09:51:36.000Z
ccaa/01JUN2018-revised/content_01JUN2018-00002.csv  1-Jun-18   1-Jun-18   117363985  2018-12-05T23:38:09.000Z  sample  2018-03-15T09:51:36.000Z
ccaa/10JUL2018-revised/content_10JUL2018-00002.csv  10-Jul-18  10-Jul-18  117363985  2018-12-05T23:38:09.000Z  sample  2018-03-15T09:51:36.000Z
ccaa/21AUG2018-revised/content_21AUG2018-00002.csv  21-Aug-18  21-Aug-18  117363985  2018-12-05T23:38:09.000Z  sample  2018-03-15T09:51:36.000Z
filename                         start_dt  end_dt     size      date                      tname
ccaa/201802/                     1-Feb-18  28-Feb-18  0         2019-01-17T06:16:34.000Z  sample
ccaa/201802/Feb2018000000_0.csv  1-Feb-18  28-Feb-18  32602738  2018-09-11T04:05:38.000Z  live
ccaa/201804/Feb2018000001_0.csv  1-Apr-18  30-Apr-18  32602738  2018-09-11T04:05:38.000Z  test
ccaa/201805/Feb2018000002_0.csv  1-May-18  31-May-18  32602738  2018-09-11T04:05:38.000Z  sample
ccaa/201806/Feb2018000003_0.csv  1-Jun-18  30-Jun-18  32602187  2018-09-11T04:05:38.000Z  sample
filename                          start_dt  end_dt     size      date                      tname
ccaa/201802/                      1-Feb-18  28-Feb-18  0         2019-01-17T06:16:34.000Z  sample
ccaa/2018-Q1/Feb2018000000_0.csv  1-Feb-18  28-Feb-18  32602738  2018-09-11T04:05:38.000Z  live
ccaa/2018-Q2/Feb2018000001_0.csv  1-Apr-18  30-Apr-18  32602738  2018-09-11T04:05:38.000Z  test
ccaa/2018-Q2/Feb2018000002_0.csv  1-May-18  31-May-18  32602738  2018-09-11T04:05:38.000Z  sample
ccaa/2018-Q3/Feb2018000003_0.csv  1-Aug-18  31-Aug-18  32602187  2018-09-11T04:05:38.000Z  sample

• не используют обратные пометки `для подстановки команд, они надевают не допускают вложения, не читаются и не рекомендуются. Вместо этого используйте $( ... ).