chto-ty-takoe-na-baze-kakih/config/synonyms.yaml
Elshat 6c890fa20a v2: Python MVP — price pipeline + analytics + FastAPI dashboard + digest + tests
- pipeline: fetch/extract/normalize/categorize/validate/llm_extract/raw/orchestrator
- analytics: dynamics, spreads/arbitrage, seasonality, anomalies, alerts, forecast
- dashboard: FastAPI + Plotly (overview/products/product/countries/alerts/quality/sources)
- scheduler (APScheduler 07:30), digest (Telegram/SMTP dry-run), demo_data
- SQLite (PORTABLE) with idempotent upserts, quarantine, alerts dedup
- truthfulness: LLM quote-verified, source link + date on every price
- tests: 13 passed, 1 skipped (robots port)
2026-09-24 07:07:32 +00:00

489 lines
9.8 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Synonym dictionary for the price-agent taxonomy.
# Keys = canonical product id (category_subcategory). Values = aliases (lowercase).
# Matching is by exact alias (trimmed, lowercased). Fuzzy match is a fallback.
synonyms:
# ---- Grains ----
grains_wheat:
- "пшеница"
- "пшеницу"
- "пшеницы"
- "пшеница продовольственная"
- "пшеница фуражная"
- "пшеница мягкая"
- "пшеница твёрдая"
- "pшеница"
- "wheat"
- "soft wheat"
- "hard wheat"
grains_rye:
- "рожь"
- "рожъ"
- "rye"
grains_barley:
- "ячмень"
- "ячмeнь"
- "ячменя"
- "barley"
grains_corn:
- "кукуруза"
- "кукруза"
- "кукурузы"
- "кукурузу"
- "corn"
- "maize"
grains_rice:
- "рис"
- "рисовый"
- "rice"
grains_oats:
- "овёс"
- "овес"
- "оat"
- "oats"
grains_sorghum:
- "пшеница сорго"
- "сорго"
- "сogum"
- "sorghum"
grains_millet:
- "пшеница"
- "millet"
- "millet"
grains_triticale:
- "тритикале"
- "triticale"
# ---- Pulses ----
pulses_lentil:
- "чеpeвица"
- "лentil"
pulses_pea:
- "горох"
- "гopex"
pulses_bean:
- "фасоль"
- "нуt"
- "чечевичка"
pulses_soy:
- "соjа"
- "соя"
- "soy"
# ---- Oilseeds ----
oilseeds_sunflower:
- "пodсолнечник"
- "podсолнечник (масло)"
- "sunflower"
oilseeds_rapeseed:
- "pапc"
- "rapeseed"
- "canola"
oilseeds_safflower:
- "сафлор"
- "safflower"
oilseeds_sesame:
- "кунжут"
- "сеmeны кунжута"
- "sesame"
# ---- Tubers ----
tubers_potato:
- "картошка"
- "картофeль"
- "картошка (молодой)"
- "potato"
tubers_carrot:
- "морковь"
- "карроt"
tubers_onion:
- "лук"
- "лук репчатый"
- "лук-сеMeнка"
- "onion"
tubers_beet:
- "свёкла"
- "свёклa"
tubers_radish:
- "редис"
- "radish"
tubers_turnip:
- "репа"
- "turnip"
# ---- Vegetables ----
vegetables_tomato:
- "томаты"
- "помидоры"
- "томат"
- "tomato"
vegetables_cucumber:
- "огурцы"
- "огурец"
- "cucumber"
vegetables_pepper:
- "перец"
- "перец сладкий"
- "перец стручковый"
- "pepper"
vegetables_cabbage:
- "капуста"
- "капуста белокочанная"
- "капуста пекинская"
- "cabbage"
vegetables_lettuce:
- "салат"
- "салат листья"
- "lettuce"
vegetables_eggplant:
- "баклажаны"
- "баклажан"
- "eggplant"
vegetables_spinach:
- "шпинат"
- "спинac"
vegetables_pumpkin:
- "тыква"
- "pumpkin"
vegetables_zucchini:
- "кабачки"
- "кабачок"
- "zucchini"
# ---- Fruits ----
fruits_apple:
- "яблоки"
- "яблоко"
- "apple"
- "яблoкo"
fruits_pear:
- "груши"
- "груша"
- "pear"
fruits_cherry:
- "вишня"
- "cherry"
- "вишни"
fruits_plum:
- "слива"
- "сливы"
- "plum"
fruits_apricot:
- "абрикос"
- "абрикосы"
- "apricot"
fruits_peach:
- "персики"
- "персик"
- "peach"
fruits_pomegranate:
- "гранат"
- "гранаты"
- "pomegranate"
fruits_quince:
- "айва"
- "quince"
fruits_citrus:
- "цитрусовые"
- "limon"
- "апельсины"
- "лимоны"
fruits_melon:
- "дыня"
- "дыни"
- "melon"
fruits_watermelon:
- "арбузы"
- "арбуз"
- "watermelon"
# ---- Nuts / Dried ----
nuts_dried_walnut:
- "грецкий орех"
- "грецкие oреxi"
- "ваlнуt"
nuts_dried_almond:
- "миндаль"
- "almond"
nuts_dried_pistachio:
- "фисташки"
- "фистaшкa"
- "pistachio"
nuts_dried_hazelnut:
- "лесной орех"
- "фундук"
- "hazelnut"
nuts_dried_raisin:
- "изюм"
- "чернослив"
- "raisin"
nuts_dried_dried_apricot:
- "курага"
- "чернослив"
- "dried apricot"
nuts_dried_dried_fruit:
- "сухофрукты"
- "сушёные фрукты"
- "сухoфрукты"
- "dried fruit"
# ---- Dairy ----
dairy_milk:
- "молоко"
- "мoлoкo"
- "milk"
- "целoе молоко"
dairy_cheese:
- "сыр"
- "cheese"
- "сyr"
dairy_butter:
- "масло сливочное"
- "сливoчное мacлo"
- "butter"
- "масло"
dairy_ghee:
- "масло топлёное"
- "топлёноe мacлo"
- "ghee"
dairy_yogurt:
- "йогурт"
- "йогорт"
- "yogurt"
- "айран"
dairy_kefir:
- "кефир"
- "kefir"
dairy_cream:
- "сливки"
- "cream"
dairy_kurut:
- "курут"
- "kurut"
# ---- Eggs ----
eggs_chicken:
- "яйца куриные"
- "кuриные яjцa"
- "чickен"
eggs_duck:
- "яйца утиные"
eggs_quail:
- "яйца перепелиные"
- "perепелиные"
# ---- Meat ----
meat_beef:
- "говядина"
- "beef"
- "говядины"
meat_mutton:
- "баранина"
- "mutton"
meat_lamb:
- "ягнятина"
- "lamb"
meat_pork:
- "свинина"
- "pork"
meat_chicken:
- "цыплята"
- "цыплёнок"
- "тушка куриная"
- "chicken"
meat_offal:
- "печень"
- "языки"
- "потрохи"
- "оффал"
# ---- Fish ----
fish_carp:
- "карп"
- "karp"
fish_bream:
- "лещ"
fish_salmon:
- "лосось"
- "форель"
- "salmon"
- "trout"
fish_pike_perch:
- "судак"
fish_shrimp:
- "креветки"
- "shrimp"
fish_canned_fish:
- "рыба консервированная"
- "тунец"
- "сардины"
- "canned fish"
# ---- Honey ----
honey_honey:
- "мёд"
- "мёд"
- "honey"
honey_honeycomb:
- "сotы"
- "матка"
honey_royal_jelly:
- "маточное молoкo"
- "royal jelly"
honey_pollen:
- "пыльца"
- "цветочная пыльца"
- "pollen"
# ---- Herbs & Spices ----
herbs_spices_coriander:
- "кинза"
- "корeандр"
- "coriander"
herbs_spices_dill:
- "укроп"
- "dill"
herbs_spices_parsley:
- "петрушка"
- "parsley"
herbs_spices_mint:
- "мята"
- "mint"
herbs_spices_saffron:
- "шафран"
- "saffron"
herbs_spices_cumin:
- "зира"
- "кумин"
- "cumin"
herbs_spices_black_pepper:
- "перец чёрный"
- "чёрный перец"
- "black pepper"
herbs_spices_cinnamon:
- "корица"
- "cinnamon"
herbs_spices_allspice:
- "гвоздика"
- "allspice"
herbs_spices_cardamom:
- "кардамон"
- "cardamom"
# ---- Sugar ----
sugar_sweeteners_refined_sugar:
- "сахар"
- "сaxар"
- "сaxарный"
- "sugar"
sugar_sweeteners_brown_sugar:
- "сахар тростниковый"
- "dark muskavado"
- "brown sugar"
# ---- Beverages ----
beverages_juice:
- "сок"
- "сoк"
- "сок 100%"
- "juice"
beverages_ayran:
- "айpан"
- "ayran"
beverages_kumiss:
- "кумыс"
- "кумыса"
- "kumiss"
beverages_tea:
- "чай"
- "зeлёный чай"
- "чaй"
- "tea"
beverages_coffee:
- "кофе"
- "кoфe"
- "coffee"
beverages_kvass:
- "компот"
- "квас"
- "kvass"
# ---- Flour & Milling ----
flour_milling_flour_wheat:
- "мука пшеничная"
- "мукa пшеничная"
- "мука"
- "мука высшего сорта"
- "wheat flour"
flour_milling_flour_rye:
- "мука ржаная"
- "rye flour"
flour_milling_semolina:
- "сeмoлка"
- "semeolina"
flour_milling_pasta:
- "макароны"
- "макаронные изделия"
- "spaghetti"
- "pasta"
flour_milling_rice_milling:
- "рис крупа"
- "рис шлифованный"
flour_milling_couscous:
- "кускус"
- "couscous"
flour_milling_oatmeal:
- "овсянка"
- "oatmeal"
flour_milling_buckwheat:
- "гречка"
- "гречнoвая"
- "buckwheat"
# ---- Seeds ----
seeds_sunflower_seeds:
- "семки"
- "сemaнки"
- "семена подсолнечника"
- "sunflower seeds"
seeds_cotton_seed:
- "хлопковое семя"
seeds_cotton_lint:
- "хлопок"
- "хлопок-волокно"
- "cotton"
seeds_tobacco:
- "табак"
- "tobacco"
seeds_poppy:
- "маk"
seeds_linseed:
- "лён"
- "линянка"
- "linseed"
# ---- Feed ----
feed_compound_feed:
- "комбикорм"
- "комбикорм свиней"
- "compound feed"
feed_hay:
- "сено"
- "сeна"
- "hay"
feed_silage:
- "силос"
- "силос кукурузный"
- "silage"
feed_straw:
- "солома"
- "сoлома"
- "straw"
feed_bran:
- "отpуби"
- "отруби ржаные"
- "bran"
feed_grain_feed:
- "зерно кормовое"
- "фупaж"
- "feed grain"