Skip to content

Commit

Permalink
Comment out potentially unused functions for testing
Browse files Browse the repository at this point in the history
  • Loading branch information
@TCLamnidis
TCLamnidis committed Sep 4, 2024
1 parent ee5ef35 commit 36fb953
Showing 1 changed file with 97 additions and 96 deletions.
193 changes: 97 additions & 96 deletions scripts/delphis-bot_scripts/source_me.sh
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#!/usr/bin/env bash
HELPER_FUNCTION_VERSION='0.2.2dev'
HELPER_FUNCTION_VERSION='0.2.3dev'

## Print coloured messages to stderr
# errecho -r will print in red
Expand Down Expand Up @@ -121,35 +121,6 @@ function pull_by_index() {
echo ${value[${index}]}
}

## Function to check if all items of array X are in array Y, and return any entries exclusive to X.
# all_x_in_y <length_of_list_x> X1 [X2 X3 ...] <length_of_list_y> Y1 [Y2 Y3 ...]
# Returns: A space separated list of exclusive elements in X
function all_x_in_y() {
local length_x
local x
local length_y
local y
local exclusive_entries
local xid

let length_x=${1}
shift 1
x=("${@:1:${length_x}}")
shift ${length_x}
let length_y=${1}
shift 1
y=("${@:1:${length_y}}")
exclusive_entries=()

for xid in ${x[@]}; do
if [[ $(count_instances ${xid} "${y[@]}") == 0 ]]; then
exclusive_entries+=("${xid}")
fi
done

echo "${exclusive_entries[@]}"
}

## Function to return udg treatment based on janno entry
# usage: infer_library_udg 'half;minus;plus' 0
# The second argument (index) is 0-based
Expand Down Expand Up @@ -294,72 +265,102 @@ function dummy_r1_r2_from_ena_fastq() {
echo "${seq_type} ${r1} ${r2}"
}

## Function to create R1 and R2 columns from ena_table fastq_fn entries
# usage: symlink_names_from_ena_fastq <download_path> <output_path> <out_fn_prefix> <fastq_ftp>
# Returns: a space separated list of seq_type R1 R1_symlink R2 R2_symlink
function symlink_names_from_ena_fastq() {
local download_path
local output_path
local out_fn_prefix
local value
local r1
local r1_symlink
local r2
local r2_symlink
local seq_type
local n_entries

download_path="${1}"
output_path="${2}"
out_fn_prefix="${3}"
value="${4}"

## BAMs containing collapsed PE reads will have 3 entries in the ENA (merged, R1 unmerged, R2 unmerged), but we only need the first (merged reads).
n_entries=$(number_of_entries ';' ${value})

r1="${download_path}/$(basename $(pull_by_index ';' ${value} 0))"
r1_symlink="${output_path}/${out_fn_prefix}_R1.fastq.gz"
if [[ ${n_entries} -eq 2 ]]; then
## If there are two entries, then it's PE
r2="${download_path}/$(basename $(pull_by_index ';' ${value} 1))"
r2_symlink="${output_path}/${out_fn_prefix}_R2.fastq.gz"
seq_type="PE"
elif [[ ${n_entries} -eq 1 || ${n_entries} -eq 3 ]]; then
## If there is only one entry, then it's SE. With three, it is a BAM with collapsed reads, so keep only merged reads (treat as SE).
r2="NA"
r2_symlink="NA"
seq_type="SE"
else
errecho -r "Unexpected number of entries in fastq_ftp field: ${value}."
exit 1
fi

echo "${seq_type} ${r1} ${r1_symlink} ${r2} ${r2_symlink}"
}

## Function to create R1 and R2 columns from ena_table fastq_fn entries
# usage: local_r1_r2_from_ena_fastq ${path_to_ena_data} ${fastq_fn}
# Returns: a thrupple of: seq_type R1 R2
function local_r1_r2_from_ena_fastq() {
local data_path
local value
local r1
local r2
local seq_type

data_path=$1
value=$2
r1="${data_path}/${value%%;*}"
r2="${data_path}/${value##*;}"
seq_type="PE"

if [[ "${r2}" == "${r1}" ]]; then
r2="NA"
seq_type="SE"
fi

echo "${seq_type} ${r1} ${r2}"
}
# ## NOTE: The following commands will be removed soon. currently commented out for testing. they are used in poseidon-eager only, and need not be here.
# ## Function to check if all items of array X are in array Y, and return any entries exclusive to X.
# # all_x_in_y <length_of_list_x> X1 [X2 X3 ...] <length_of_list_y> Y1 [Y2 Y3 ...]
# # Returns: A space separated list of exclusive elements in X
# function all_x_in_y() {
# local length_x
# local x
# local length_y
# local y
# local exclusive_entries
# local xid

# let length_x=${1}
# shift 1
# x=("${@:1:${length_x}}")
# shift ${length_x}
# let length_y=${1}
# shift 1
# y=("${@:1:${length_y}}")
# exclusive_entries=()

# for xid in ${x[@]}; do
# if [[ $(count_instances ${xid} "${y[@]}") == 0 ]]; then
# exclusive_entries+=("${xid}")
# fi
# done

# echo "${exclusive_entries[@]}"
# }

# ## Function to create R1 and R2 columns from ena_table fastq_fn entries
# # usage: symlink_names_from_ena_fastq <download_path> <output_path> <out_fn_prefix> <fastq_ftp>
# # Returns: a space separated list of seq_type R1 R1_symlink R2 R2_symlink
# function symlink_names_from_ena_fastq() {
# local download_path
# local output_path
# local out_fn_prefix
# local value
# local r1
# local r1_symlink
# local r2
# local r2_symlink
# local seq_type
# local n_entries

# download_path="${1}"
# output_path="${2}"
# out_fn_prefix="${3}"
# value="${4}"

# ## BAMs containing collapsed PE reads will have 3 entries in the ENA (merged, R1 unmerged, R2 unmerged), but we only need the first (merged reads).
# n_entries=$(number_of_entries ';' ${value})

# r1="${download_path}/$(basename $(pull_by_index ';' ${value} 0))"
# r1_symlink="${output_path}/${out_fn_prefix}_R1.fastq.gz"
# if [[ ${n_entries} -eq 2 ]]; then
# ## If there are two entries, then it's PE
# r2="${download_path}/$(basename $(pull_by_index ';' ${value} 1))"
# r2_symlink="${output_path}/${out_fn_prefix}_R2.fastq.gz"
# seq_type="PE"
# elif [[ ${n_entries} -eq 1 || ${n_entries} -eq 3 ]]; then
# ## If there is only one entry, then it's SE. With three, it is a BAM with collapsed reads, so keep only merged reads (treat as SE).
# r2="NA"
# r2_symlink="NA"
# seq_type="SE"
# else
# errecho -r "Unexpected number of entries in fastq_ftp field: ${value}."
# exit 1
# fi

# echo "${seq_type} ${r1} ${r1_symlink} ${r2} ${r2_symlink}"
# }

# ## Function to create R1 and R2 columns from ena_table fastq_fn entries
# # usage: local_r1_r2_from_ena_fastq ${path_to_ena_data} ${fastq_fn}
# # Returns: a thrupple of: seq_type R1 R2
# function local_r1_r2_from_ena_fastq() {
# local data_path
# local value
# local r1
# local r2
# local seq_type

# data_path=$1
# value=$2
# r1="${data_path}/${value%%;*}"
# r2="${data_path}/${value##*;}"
# seq_type="PE"

# if [[ "${r2}" == "${r1}" ]]; then
# r2="NA"
# seq_type="SE"
# fi

# echo "${seq_type} ${r1} ${r2}"
# }

## Function to infer colour chemistry from an ENA-approved instrument model
# Usage: infer_colour_chemistry ${instrument_platform} ${instrument_model}
Expand Down

0 comments on commit 36fb953

Please sign in to comment.