taxonomy: fix taxonomies

taxonomies/categories.txt

@@ -34889,8 +34889,7 @@ nl:Bakmixes, Bakmelanges
 en:Shelf-stable baking mixes
 gpc_category_code:en:10000156
 gpc_category_name:en:Baking/Cooking Mixes (Shelf Stable)
-gpc_category_description:en:Definition: Includes any products that can be described/observed as a quantity of shelf-stable, pre-mixed dough, batter or powder that is specifically intended to produce bread, cakes, biscuits, desserts, or other products. Products may be ready to use (where no additional ingredients need to be added to the mix prior to use) or require the addition of wet ingredients such as water, milk, oil, fat or egg. These products have been treated or packaged in such a way as to extend their consumable life.
-Definition Excludes: Excludes products such as Soups, Frozen or Perishable Baking Mixes, all Part Baked and Baked Products.
+gpc_category_description:en:Definition: Includes any products that can be described/observed as a quantity of shelf-stable, pre-mixed dough, batter or powder that is specifically intended to produce bread, cakes, biscuits, desserts, or other products. Products may be ready to use (where no additional ingredients need to be added to the mix prior to use) or require the addition of wet ingredients such as water, milk, oil, fat or egg. These products have been treated or packaged in such a way as to extend their consumable life. Definition Excludes: Excludes products such as Soups, Frozen or Perishable Baking Mixes, all Part Baked and Baked Products.
 
 <en:Baking Mixes
 en:Refrigerated baking mixes
@@ -35708,7 +35707,6 @@ agribalyse_food_code:en:39212
 ciqual_food_code:en:39212
 ciqual_food_name:en:Rice pudding, refrigerated
 ciqual_food_name:fr:Riz au lait, rayon frais
-intake
 
 <en:Rice puddings
 en:Rice pudding with caramel sauce
@@ -47819,8 +47817,7 @@ intake24_category_code:en:MILK
 en:Refrigerated milks
 gpc_category_code:en:10000025
 gpc_category_name:en:Milk (Perishable)
-gpc_category_description:en:Definition: Includes any products that can be described/observed as unflavoured milk derived from animals, such as cow, goat and buffalo. Products include those, which have been inoculated with live acidophilus and bifidus bacteria, but have been kept at the temperature which is too cool for such bacteria to develop, and have not therefore been fermented and retain the flavour of natural milk. These products must be refrigerated to extend their consumable life.
-Definition Excludes: Specifically excludes all fermented milk (or milk substitute) based beverages. Excludes products such as Frozen and Shelf Stable Milk and all Milk Substitutes and Baby and Infant Specialized Beverage and Formula.
+gpc_category_description:en:Definition: Includes any products that can be described/observed as unflavoured milk derived from animals, such as cow, goat and buffalo. Products include those, which have been inoculated with live acidophilus and bifidus bacteria, but have been kept at the temperature which is too cool for such bacteria to develop, and have not therefore been fermented and retain the flavour of natural milk. These products must be refrigerated to extend their consumable life. Definition Excludes: Specifically excludes all fermented milk (or milk substitute) based beverages. Excludes products such as Frozen and Shelf Stable Milk and all Milk Substitutes and Baby and Infant Specialized Beverage and Formula.
 
 <en:Milks
 en:Milks from Austria, Austrian milks
@@ -61543,7 +61540,6 @@ nl:Vers fruit
 pt:Frutas frescas
 ru:Свежие фрукты
 who_id:en:15
-intake
 
 <en:Fresh fruits
 en:Prepared fresh fruits
@@ -71388,7 +71384,7 @@ es:Capón del Prat
 
 <en:Spanish meat products
 es:Pollo del Prat
-#wikidata:Q772489
+#wikidata:en:Q772489
 
 <en:Spanish meat products
 es:Ternasco de Aragón
@@ -72187,8 +72183,7 @@ gpc_category_description:en:Definition: Includes any products that can be descri
 en:Dough based meals (ready)
 gpc_category_code:en:10000299
 gpc_category_name:en:Dough Based Products / Meals - Ready to Eat - Savoury (Shelf Stable)
-gpc_category_description:en:Definition: Includes any products that can be described/observed as a savoury dough-based ready to eat, prepared/processed product, such as Pasta, Gnocchi or Noodles, with other ingredients, such as meat, dairy, eggs, fish, vegetables and/or seasoning. An optional seasoning/flavour packet may be present. These ingredients form a valuable part of the product, such as tuna and salad in a Tuna Pasta Salad. They may or may not contain a sauce. These products may have a main component which is considered a meal without any additional components. These products do not require cooking prior to consumption, but some products can be eaten hot after reheating. These products have been treated or packaged in such a way as to extend their consumable life. Includes ready to eat shelf stable Ready-Made Meals where a Dough Based Product is the primary ingredient.
-Definition Excludes: Excludes Ready-Made Combination Meals. Specifically excludes pizza, savoury pies, pastries, quiches and bread products.Excludes products such as Perishable Ready to Eat and Not Ready to Eat Dough Based Prepared/Processed Products, Unprepared Pasta and Noodles, Dried Pasta and Noodles.
+gpc_category_description:en:Definition: Includes any products that can be described/observed as a savoury dough-based ready to eat, prepared/processed product, such as Pasta, Gnocchi or Noodles, with other ingredients, such as meat, dairy, eggs, fish, vegetables and/or seasoning. An optional seasoning/flavour packet may be present. These ingredients form a valuable part of the product, such as tuna and salad in a Tuna Pasta Salad. They may or may not contain a sauce. These products may have a main component which is considered a meal without any additional components. These products do not require cooking prior to consumption, but some products can be eaten hot after reheating. These products have been treated or packaged in such a way as to extend their consumable life. Includes ready to eat shelf stable Ready-Made Meals where a Dough Based Product is the primary ingredient. Definition Excludes: Excludes Ready-Made Combination Meals. Specifically excludes pizza, savoury pies, pastries, quiches and bread products.Excludes products such as Perishable Ready to Eat and Not Ready to Eat Dough Based Prepared/Processed Products, Unprepared Pasta and Noodles, Dried Pasta and Noodles.
 
 <en:Variety packs
 <en:Meals
@@ -76780,7 +76775,7 @@ ru:Готовые салаты
 es:Ensalada rusa
 it:Insalata russa
 wikidata:en:Q281278
-e
+
 <en:Prepared salads
 en:Buddha Bowl
 fr:Buddha Bowl
@@ -108267,7 +108262,7 @@ xx:Open Products Facts, OPF
 <en:Open Products Facts
 en:kitchenware
 nl:Keukenproducten, Keukenbenodigdheden
-wikidata:Q1521410
+wikidata:en:Q1521410
 
 <en:Open Products Facts
 en:books
@@ -108277,15 +108272,15 @@ fr:livres
 hr:knjige, knjiga
 ja:本
 nl:Boeken
-wikidata:Q571
+wikidata:en:Q571
 
 <en:Open Products Facts
 en:detergents
 hr:deterdženti, deterdžent
 ja:洗剤
 nl:Detergenten
 tr:Deterjan
-wikidata:Q334637
+wikidata:en:Q334637
 
 # REAL Cigarettes
 <en:Non food products

taxonomies/data_quality.txt

@@ -2269,7 +2269,6 @@ description:en:This ingredient list contains 4 repeated chars, which is very unl
 <en:Ingredients warnings
 en:Ingredients SV - 5 consonants
 description:en:This ingredient list contains 5 consecutive consonants, which is very unlikely in most languages, and might be due to a text extraction (OCR) error
-language:
 
 <en:Ingredients warnings
 en:Ingredients SV - 5 vowels

taxonomies/ingredients.txt

@@ -7125,7 +7125,7 @@ nl:verse kaas
 pt:queijo branco
 sl:sveži sir
 sr:sveži sir
-ciqual_food_code:19501
+ciqual_food_code:en:19501
 ciqual_food_name:en:Quark, plain or fruit (average)
 # en-ca:Fromage blanc
 # en-gb:Fromage blanc
@@ -30877,7 +30877,7 @@ vegan:en:yes
 vegetarian:en:yes
 # openfoodfacts:https://world.openfoodfacts.org/ingredient/corn-syrup 19402 products in 7 languages @2018-09-24
 # probably not a very good proxy, but the closest one in Ciqual
-ciqual_proxy_food_code:31089
+ciqual_proxy_food_code:en:31089
 ciqual_proxy_food_name:en:Syrup, agave
 
 <en:corn syrup
@@ -32936,7 +32936,7 @@ pt:raspas de chocolate
 sv:Choklad bitar, chokladbitar
 # ingredient/fr:morceaux-de-chocolat has 63 products in 4 languages @2019-03-11
 # usage:de:Schokoladenstücke 18% (Kakaomasse, Zucker, Emulgator: Sojalecithin, Vanillepulver)
-ciqual_proxy_food_code:31005
+ciqual_proxy_food_code:en:31005
 ciqual_proxy_food_name:en:Dark chocolate bar, less than 70% cocoa
 
 <en:chocolate
@@ -36770,7 +36770,7 @@ pl:puree z moreli
 pt:pure de damasco
 # in process de:Aprikosenpüree
 # 873 @2021-09-12
-ciqual_proxy_food_code:31037
+ciqual_proxy_food_code:en:31037
 ciqual_proxy_food_name:en:Jam, apricot
 
 <en:Bergeron apricot
@@ -36783,7 +36783,7 @@ es:zumo de albaricoque
 fr:jus d'abricot
 it:succo di albicocca
 pt:suco de damasco
-ciqual_proxy_food_code:2043
+ciqual_proxy_food_code:en:2043
 ciqual_proxy_food_name:en:Apricot nectar
 
 <en:apricot juice
@@ -47796,11 +47796,11 @@ wikidata:en:Q178547
 eurocode_2_group_3:en: 8.10.10
 
 en:Red endive
-ciqual_food_code:20162
+ciqual_food_code:en:20162
 ciqual_food_name:en:Red endive, raw
 
 en:Green endive
-ciqual_food_code:20163
+ciqual_food_code:en:20163
 ciqual_food_name:en:Green endive, raw
 
 # description:en:RADICCHIO is a perennial cultivated form of leaf chicory (Cichorium intybus, Asteraceae) sometimes known as Italian chicory because of its common use in Italian cuisine.
@@ -54629,7 +54629,7 @@ fr:radis blanc, radis d'hiver, radis chinois, daikon
 it:ravanello bianco
 ja:ダイコン, 大根, だいこん
 nl:witte rammenas
-biała rzodkiew, białej rzodkwi, rzodkiew biała
+pl:biała rzodkiew, białej rzodkwi, rzodkiew biała
 
 
 <en:root vegetable
@@ -61742,7 +61742,7 @@ zh:芝麻
 # zh-tw:胡麻
 allergens:en: en:sesame seeds
 wikidata:en:Q2763698
-ciqual_food_code:15010
+ciqual_food_code:en:15010
 ciqual_food_name:en:Sesame seed
 # ingredient/fr:sésame has 1745 products @2018-10-05
 
@@ -64397,7 +64397,7 @@ wo:anet
 zh:蒔蘿
 description:en:dill (anethum graveolens) is an annual herb in the celery family apiaceae. dill is widely grown in eurasia where its leaves and seeds are used as a herb or spice for flavouring food.
 comment:en:the wikidata page mixes the common name and latin name
-ciqual_food_code:11093
+ciqual_food_code:en:11093
 ciqual_food_name:en:Dill, fresh
 # aeb-arab:شبت
 # aeb-latn:ch'ebt

taxonomies/packaging_materials.txt

@@ -437,10 +437,10 @@ hu:PET - Színezet, színes PET
 nl:PET - gekleurd, Gekleurd PET
 pt:PET - colorido
 description:en:Colored PET (polyethylene terephthalate), which requires additional recycling processes
-description:Farbiges PET (Polyethylenterephthalat), das zusätzliche Recyclingprozesse erfordert
+description:de:Farbiges PET (Polyethylenterephthalat), das zusätzliche Recyclingprozesse erfordert
 description:es:PET coloreado (tereftalato de polietileno), que requiere procesos de reciclaje adicionales
 description:fr:PET coloré (polyéthylène téréphtalate), qui nécessite des processus de recyclage supplémentaires
-description:PET colorato (polietilene tereftalato), che richiede ulteriori processi di riciclaggio
+description:it:PET colorato (polietilene tereftalato), che richiede ulteriori processi di riciclaggio
 description:nl:Gekleurd PET (polyethyleentereftalaat), dat extra recyclingprocessen vereist
 description:pt:PET colorido (tereftalato de polietileno), que requer processos de reciclagem adicionais
 #comment:en:This is banned in India, Japan and South Korea
@@ -1875,7 +1875,7 @@ it:Altri Tessili
 nl:Ander textiel
 pt:Outros têxteis
 xx:62 TEX, TEX 62, 63 TEX, TEX 63, 64 TEX, TEX 64, 65 TEX, TEX 65, 66 TEX, TEX 66, 67 TEX, TEX 67, 68 TEX, TEX 68, 69 TEX, TEX 69
-description:Elk textiel (uit draden gemaakt materiaal) dat niet jute of katoen is.
+description:nl:Elk textiel (uit draden gemaakt materiaal) dat niet jute of katoen is.
 
 # Silicates / Verre (sodo-calcique) in data from Les Mousquetaires
 en:Glass
@@ -2990,7 +2990,7 @@ description:en:Tetra Rex®Plant-based is manufactured solely from a combination
 en:Tetra Top
 xx:Tetra Top
 web:en:https://www.tetrapak.com/solutions/packaging/packages/tetra-top
-description:Drink cartons with a large separable top
+description:en:Drink cartons with a large separable top
 
 <en:Tetra Pak
 en:Tetra Stelo Aseptic, Tetra Stelo

taxonomies/packaging_shapes.txt

@@ -1369,7 +1369,7 @@ tr:kamış
 uk:соломинка
 vi:ống hút
 wa:paye
-y:שטרוי
+yi:שטרוי
 zh:吸管
 description:en:A long tube (usually made out of plastic or paper) through which a beverage is drunk via suction
 description:de:Hilfsmittel, mit welchem sich Flüssigkeiten aufsaugen lassen, um sie zu trinken

taxonomies/vitamins.txt

@@ -745,8 +745,8 @@ nl_be:Vitamine K3
 pl:Witamina K3
 pt:Vitamina K3
 ro:Vitamina K3
+sk:Vitamín K3
 zh:维生素K3
-sK3:Vitamín K3
 
 # description:en:Vitamin C, also known as ascorbic acid and L-ascorbic acid, is a vitamin found in food and used as a dietary supplement.
 

tests/unit/expected_test_results/ingredients/fr-epices-irradiees.json

@@ -11,6 +11,7 @@
          "vegetarian" : "yes"
       },
       {
+         "ciqual_food_code" : "15010",
          "id" : "en:sesame",
          "labels" : "en:irradiated",
          "percent_estimate" : 16.6666666666667,
@@ -71,10 +72,9 @@
    "ingredients_with_unspecified_percent_n" : 3,
    "ingredients_with_unspecified_percent_sum" : 100,
    "ingredients_without_ciqual_codes" : [
-      "en:sesame",
       "en:spice"
    ],
-   "ingredients_without_ciqual_codes_n" : 2,
+   "ingredients_without_ciqual_codes_n" : 1,
    "known_ingredients_n" : 6,
    "lc" : "fr",
    "nutriments" : {