Removed empty fields from words.toml

added words.toml schema
replaced custom validation script with the Taplo CLI
removed the python extension recommendation

.github/workflows/validate_toml.yml

@@ -13,20 +13,12 @@ permissions:
 jobs:
   validate:
     runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: .github/workflows/
     steps:
       - name: Checkout
         uses: actions/checkout@v3
 
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.11"
+      - name: Validate translations
+        run: npx --yes @taplo/cli check --schema https://raw.githubusercontent.com/lipu-linku/sona/${{vars.GITHUB_SHA || 'main'}}/schemas/translation.schema.json ./translations/*.toml
 
-      - name: Install Dependencies
-        run: python -m pip install --upgrade pip setuptools wheel jsonschema
-
-      - name: Validate Files
-        run: python validate_toml.py
+      - name: Validate words.toml
+        run: npx --yes @taplo/cli check --schema https://raw.githubusercontent.com/lipu-linku/sona/${{vars.GITHUB_SHA || 'main'}}/schemas/words.schema.json ./words.toml

.vscode/extensions.json

@@ -1,6 +1,5 @@
 {
   "recommendations": [
     "tamasfe.even-better-toml",
-    "ms-python.python"
   ]
 }

schemas/words.schema.json

@@ -0,0 +1,155 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://linku.la/sona/schemas/words.schema.json",
+  "title": "sona words.toml file",
+  "description": "General info on a Toki Pona word",
+  "type": "object",
+  "additionalProperties": {
+    "type": "object",
+    "properties": {
+      "author_verbatim": {
+        "description": "The author's original definition, taken verbatim in their words",
+        "type": "string"
+      },
+      "author_verbatim_source": {
+        "description": "Where the author's original definition is located (usually Discord)",
+        "type": "string"
+      },
+      "book": {
+        "description": "Which official Toki Pona book was this word featured in, if any.",
+        "type": "string",
+        "enum": ["pu", "ku suli", "ku lili", "none"]
+      },
+      "coined_era": {
+        "description": "When this word was coined (relative to the publication dates of the official Toki Pona books)",
+        "type": "string"
+      },
+      "coined_year": {
+        "description": "The exact year when this word was coined (if known)",
+        "type": "number",
+        "minimum": 2000
+      },
+      "creator": {
+        "description": "The person who created this word (if known)",
+        "type": "string"
+      },
+      "ku_data": {
+        "description": "The usage data of the word as described in ku (the official Toki Pona dictionary), formatted as a map between a meaning and its frequency index (0 to 5)",
+        "additionalProperties": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 5
+        },
+        "type": "object"
+      },
+      "see_also": {
+        "description": "A list of related words",
+        "type": "array",
+        "items": {
+          "type": "string"
+        }
+      },
+      "sitelen_emosi": {
+        "description": "The sitelen emosi representation of this word, a script for writing Toki Pona using emoji",
+        "type": "string",
+        "pattern": "(\u00a9|\u00ae|[\u2000-\u3300]|\ud83c[\ud000-\udfff]|\ud83d[\ud000-\udfff]|\ud83e[\ud000-\udfff])"
+      },
+      "sitelen_pona": {
+        "description": "A list of sitelen Lasina representations of this word, to be converted into sitelen pona glyphs",
+        "type": "array",
+        "items": {
+          "type": "string"
+        }
+      },
+      "sitelen_sitelen": {
+        "description": "A URL pointing to an image of this word's sitelen sitelen hieroglyphic block",
+        "type": "string",
+        "format": "uri"
+      },
+      "source_language": {
+        "description": "The language this word originated from",
+        "type": "string"
+      },
+      "ucsur": {
+        "description": "The word's UCSUR codepoint",
+        "type": "string",
+        "pattern": "U\\+[\\da-fA-F]{4,6}"
+      },
+      "usage_category": {
+        "description": "The word's usage category, according to a survey performed by the Linku Project",
+        "type": "string",
+        "enum": ["core", "widespread", "common", "uncommon", "rare", "obscure"]
+      },
+      "word": {
+        "description": "The word's actual text, in case of a word with multiple definitions",
+        "type": "string"
+      },
+      "audio": {
+        "description": "Audio files of the words pronounced out loud",
+        "type": "object",
+        "properties": {
+          "jan_lakuse": {
+            "type": "string",
+            "description": "jan Lakuse's pronounciation of the word, made for jan Sonja's Memrise course: https://archive.org/details/toki-pona-audio-by-jan-lakuse",
+            "format": "uri"
+          },
+          "kala_asi": {
+            "type": "string",
+            "description": "kala Asi's pronounciation of the word, made for the Linku Project",
+            "format": "uri"
+          }
+        }
+      },
+      "luka_pona": {
+        "description": "Video clips of the word being signed in Luka Pona, a Toki Pona sign language",
+        "type": "object",
+        "properties": {
+          "mp4": {
+            "description": "The video clip in MP4 format",
+            "type": "string",
+            "format": "uri"
+          },
+          "gif": {
+            "description": "The video clip as a GIF",
+            "type": "string",
+            "format": "uri"
+          }
+        },
+        "required": ["mp4", "gif"]
+      },
+      "pu_verbatim": {
+        "description": "The original definition of the word, as described in the book The Language Of Good (pu). May be inaccurate or outdated",
+        "type": "object",
+        "properties": {
+          "en": {
+            "description": "The original definition in the English version of pu",
+            "type": "string"
+          },
+          "fr": {
+            "description": "The original definition in the French version of pu",
+            "type": "string"
+          },
+          "de": {
+            "description": "The original definition in the German version of pu",
+            "type": "string"
+          },
+          "eo": {
+            "description": "The original definition in the Esperanto version of pu",
+            "type": "string"
+          }
+        },
+        "required": ["en", "fr", "de", "eo"]
+      },
+      "recognition": {
+        "description": "The percentage of people in the Toki Pona community who recognize this word, according to surveys performed by the Linku Project",
+        "type": "object",
+        "patternProperties": {
+          "\\d{4}-\\d{2}": {
+            "type": "number"
+          }
+        }
+      }
+    },
+    "required": ["word", "usage_category", "book", "recognition"]
+  }
+}