feat: data quality warning for 3 identical values in nutrition tables (…

…#8109)

* data quality warning for 3 identical values in nutrition tables for major nutriments

* include fiber and sodium

* apply corrections suggested by Stephane

docs/how-to-guides/use-gitpod.md

@@ -55,6 +55,10 @@ on http://openfoodfacts.localhost just as documented in the quickstart guide!
 
 **Remark:** for some Linux distributions, the port 80 is reserved. A workaround is to switch to port 8080: in gitpod, open the .env file and replace the line PRODUCT_OPENER_PORT=80 by PRODUCT_OPENER_PORT=8080, then replace -L 80:localhost:80 by -L 8080:localhost:8080. **Rollback the changes on .env before to make a pull request!***  
 
+**Remark:** the address to connect with ssh can change after few days. If you get a ```Connection closed by ... port 22``` simply go back to https://gitpod.io/workspaces and copy the new address.  
+
+**Remark:** if you load the page after some changes but get a ```502 Bad Gateway``` check again your code. Something may be wrong with it. Eventually, try to comment the part you just coded to see if it works. 
+
 Create an account to be able to edit products.
 
 ## Some commands

lib/ProductOpener/DataQualityFood.pm

@@ -690,6 +690,9 @@ sub check_nutrition_data ($product_ref) {
 		my $nid_non_zero = 0;
 
 		my $total = 0;
+		# variables to check if there are 3 or more duplicates in nutriments
+		my @major_nutriments_values = ();
+		my %nutriments_values_occurences = ();
 
 		if (    (defined $product_ref->{nutriments}{"energy-kcal_value"})
 			and (defined $product_ref->{nutriments}{"energy-kj_value"}))
@@ -758,6 +761,42 @@ sub check_nutrition_data ($product_ref) {
 			if (($nid eq 'fat') or ($nid eq 'carbohydrates') or ($nid eq 'proteins') or ($nid eq 'salt')) {
 				$total += $product_ref->{nutriments}{$nid . "_100g"};
 			}
+
+			# variables to check if there are 3 or more duplicates in nutriments
+			if (
+				(
+					   ($nid eq 'fat_100g')
+					or ($nid eq 'saturated-fat_100g')
+					or ($nid eq 'carbohydrates_100g')
+					or ($nid eq 'sugars_100g')
+					or ($nid eq 'fiber_100g')
+					or ($nid eq 'proteins_100g')
+					or ($nid eq 'salt_100g')
+					or ($nid eq 'sodium_100g')
+				)
+				and ($product_ref->{nutriments}{$nid} > 1)
+				)
+			{
+				push(@major_nutriments_values, $product_ref->{nutriments}{$nid});
+			}
+
+		}
+
+		# create a hash key: nutriment value, value: number of occurence
+		foreach my $nutriment_value (@major_nutriments_values) {
+			if (exists($nutriments_values_occurences{$nutriment_value})) {
+				$nutriments_values_occurences{$nutriment_value}++;
+			}
+			else {
+				$nutriments_values_occurences{$nutriment_value} = 1;
+			}
+		}
+		# raise warning if there are 3 or more duplicates in nutriments
+		foreach my $keys (keys %nutriments_values_occurences) {
+			if ($nutriments_values_occurences{$keys} > 2) {
+				push @{$product_ref->{data_quality_warnings_tags}}, "en:nutrition-3-or-more-values-are-identical";
+				last;
+			}
 		}
 
 		if ($total > 105) {

taxonomies/data_quality.txt

@@ -2647,6 +2647,10 @@ show_on_producers_platform:en:yes
 en:Nutri-Score score from producer does not match calculated score
 description:en:This might be due among other things to incorrect nutrition values, incomplete nutrition values (missing fiber, fruits and vegetables), incorrect fruits and vegetables estimate, incorrect input of diluted/reconstituted values.
 
+<en:Nutrition warnings
+en:Nutrition 3 or more values are identical
+description:en:Someone may have entered wrong data because there are 3 identical values in nutrition table and those values are above 1
+
 <en:Nutrition warnings
 en:Nutrition all values zero
 #description:en:

tests/unit/dataqualityfood.t

@@ -547,6 +547,45 @@ check_quality_and_test_product_has_quality_tag(
 	'en:ingredients-extracted-ingredient-from-picture-with-more-than-100-percent',
 	'percentage should not be above 100, error when extracting the ingredients from the picture', 0
 );
+
+# en:nutrition-3-or-more-values-are-identical
+$product_ref = {
+	nutriments => {
+		"carbohydrates_100g" => 0,
+		"fat_100g" => 0,
+		"proteins_100g" => 0,
+	}
+};
+check_quality_and_test_product_has_quality_tag(
+	$product_ref,
+	'en:nutrition-3-or-more-values-are-identical',
+	'3 or more identical values and above 1 in the nutrition table', 0
+);
+$product_ref = {
+	nutriments => {
+		"carbohydrates_100g" => 1,
+		"fat_100g" => 2,
+		"proteins_100g" => 3,
+	}
+};
+check_quality_and_test_product_has_quality_tag(
+	$product_ref,
+	'en:nutrition-3-or-more-values-are-identical',
+	'3 or more identical values and above 1 in the nutrition table', 0
+);
+$product_ref = {
+	nutriments => {
+		"carbohydrates_100g" => 3,
+		"fat_100g" => 3,
+		"proteins_100g" => 3,
+	}
+};
+check_quality_and_test_product_has_quality_tag(
+	$product_ref,
+	'en:nutrition-3-or-more-values-are-identical',
+	'3 or more identical values and above 1 in the nutrition table', 1
+);
+
 # sum of fructose plus glucose plus maltose plus lactose plus sucrose cannot be greater than sugars
 $product_ref = {nutriments => {}};
 ProductOpener::DataQuality::check_quality($product_ref);
@@ -667,4 +706,5 @@ check_quality_and_test_product_has_quality_tag(
 	'en:nutrition-fructose-plus-glucose-plus-maltose-plus-lactose-plus-sucrose-greater-than-sugars',
 	'sum of fructose plus glucose plus maltose plus lactose plus sucrose cannot be greater than sugars', 0
 );
+
 done_testing();