From a20deff4c75486a4b12200f870160f1e7bee0fff Mon Sep 17 00:00:00 2001
From: Pieter Verschaffelt <pieter.verschaffelt@ugent.be>
Date: Thu, 10 Aug 2023 10:49:49 +0200
Subject: [PATCH] Add cutoff parameter for pept2filtered endpoint

---
 app/controllers/mpa_controller.rb  | 10 +++++++++-
 config/database.yml                |  1 +
 config/environments/development.rb |  3 ++-
 config/environments/production.rb  |  3 +++
 4 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/app/controllers/mpa_controller.rb b/app/controllers/mpa_controller.rb
index a43e2c2..1c29a9b 100644
--- a/app/controllers/mpa_controller.rb
+++ b/app/controllers/mpa_controller.rb
@@ -44,6 +44,7 @@ def pept2data
 
   def pept2filtered
     peptides = params[:peptides] || []
+    cutoff = params[:cutoff] || 1000
     # missed = params[:missed] || false
     taxa_filter_ids = (params[:taxa] || []).map(&:to_i)
 
@@ -52,11 +53,18 @@ def pept2filtered
     @seq_entries = {}
     uniprot_ids = []
 
+    peptides_under_cutoff = Sequence
+      .joins(:peptides)
+      .where(sequence: peptides)
+      .group('sequences.id')
+      .having('count(peptides.id) < ?', cutoff)
+      .pluck(:sequence)
+
     taxa_filter_ids.each_slice(5000) do |taxa_slice|
       sequence_subset = Sequence
                         .joins(peptides: [:uniprot_entry])
                         .includes(peptides: [:uniprot_entry])
-                        .where(sequence: peptides)
+                        .where(sequence: peptides_under_cutoff)
                         .where(uniprot_entry: { taxon_id: taxa_slice })
                         .uniq
 
diff --git a/config/database.yml b/config/database.yml
index 1c32715..06f9ee6 100644
--- a/config/database.yml
+++ b/config/database.yml
@@ -6,6 +6,7 @@ default: &default
 
 development:
   <<: *default
+  username: unipept
   database: unipept
   # setup local port forwarding for this to work
   host: 127.0.0.1
diff --git a/config/environments/development.rb b/config/environments/development.rb
index eeb99ac..85ef47c 100644
--- a/config/environments/development.rb
+++ b/config/environments/development.rb
@@ -53,8 +53,9 @@
   config.active_record.migration_error = :page_load
 
   # Highlight code that triggered database queries in logs.
-  config.active_record.verbose_query_logs = true
+  # config.active_record.verbose_query_logs = true
 
+  # config.log_level = :info
 
   # Raises error for missing translations.
   # config.i18n.raise_on_missing_translations = true
diff --git a/config/environments/production.rb b/config/environments/production.rb
index dbbe0ea..04dee56 100644
--- a/config/environments/production.rb
+++ b/config/environments/production.rb
@@ -71,6 +71,9 @@
   # Use default logging formatter so that PID and timestamp are not suppressed.
   config.log_formatter = ::Logger::Formatter.new
 
+  # Do not log SQL queries in production mode (this can cause the server to go out of disk space).
+  config.log_level = :info
+
   # Use a different logger for distributed setups.
   # require "syslog/logger"
   # config.logger = ActiveSupport::TaggedLogging.new(Syslog::Logger.new "app-name")