match new kaikki jsonl filenames (#90)

.gitignore

@@ -1,4 +1,5 @@
 *.json
+*.jsonl
 !tag_bank_term.json
 !tag_bank_ipa.json
 !parts_of_speech.json

2-extract-language.py

@@ -4,8 +4,8 @@
 source_iso = os.environ.get("source_iso")
 target_iso = os.environ.get("target_iso")
 
-input_file = f"data/kaikki/{target_iso}-extract.json"
-output_file = f"data/kaikki/{source_iso}-{target_iso}-extract.json"
+input_file = f"data/kaikki/{target_iso}-extract.jsonl"
+output_file = f"data/kaikki/{source_iso}-{target_iso}-extract.jsonl"
 
 print(f"Reading {input_file} and writing {output_file}...")
 

auto.sh

@@ -97,19 +97,19 @@ for target_lang in "${languages[@]}"; do
     # Step 3: Download JSON data if it doesn't exist
     if [ "$target_language" = "English" ]; then
       language_no_special_chars=$(echo "$language" | tr -d '[:space:]-') #Serbo-Croatian, Ancient Greek and such cases
-      filename="kaikki.org-dictionary-$language_no_special_chars.json"
+      filename="kaikki.org-dictionary-$language_no_special_chars.jsonl"
       filepath="data/kaikki/$filename"
 
 
       if [ ! -f "$filepath" ] || [ "$redownload" = true ]; then
-        url="kaikki.org/dictionary/$language/$filename"
+        url="https://kaikki.org/dictionary/$language/$filename"
         echo "Downloading $filename from $url"
         wget "$url" -O "$filepath"
       else
         echo "Kaikki dict already exists. Skipping download."
       fi
     else
-      target_extract="$target_iso-extract.json"
+      target_extract="$target_iso-extract.jsonl"
       target_extract_path="data/kaikki/$target_extract"
 
       if [ ! -f "$target_extract_path" ] || [ "$redownload" = true ] && [ "$downloaded_target_extract" = false ]; then
@@ -123,7 +123,7 @@ for target_lang in "${languages[@]}"; do
         echo "Kaikki dict already exists. Skipping download."
       fi
 
-      filename="$source_iso-$target_iso-extract.json"
+      filename="$source_iso-$target_iso-extract.jsonl"
       filepath="data/kaikki/$filename"
 
       if [ ! -f "$filepath" ]; then