Upload app.py

app.py

@@ -670,23 +670,41 @@ def _write_tsv(df: pd.DataFrame, filename: str) -> str:
     return path
 
 def build_download_main(rows_state) -> str:
-    """TSV with 2 columns: Faroese analysis, then English analysis."""
-    fo_vals, en_vals = [], []
+    """TSV with 4 columns:
+    Orð, Mark, Útgreining (FO), Analysis (EN)
+    """
+    words, tags, fo_vals, en_vals = [], [], [], []
     for r in (rows_state or []):
         vec = torch.tensor(r["vec"])
+        tag = vector_to_tag(vec)
+        words.append(r["word"])
+        tags.append(tag)
         fo_vals.append(analysis_text(vec, "fo"))
         en_vals.append(analysis_text(vec, "en"))
-    df = pd.DataFrame({UI["fo"]["s"]: fo_vals, UI["en"]["s"]: en_vals})
+
+    df = pd.DataFrame({
+        UI["fo"]["w"]: words,
+        UI["fo"]["t"]: tags,
+        UI["fo"]["s"]: fo_vals,
+        UI["en"]["s"]: en_vals,
+    })
     return _write_tsv(df, "Markað.tsv")
 
 def build_download_expanded(rows_state, lang: str) -> str:
-    """TSV with the Expanded tags column in the currently selected UI language."""
+    """TSV with 3 columns: Word/Orð, Tag/Mark, and Expanded tags in the UI language."""
     lang = "fo" if lang == "fo" else "en"
-    vals = []
+    words, tags, vals = [], [], []
     for r in (rows_state or []):
         vec = torch.tensor(r["vec"])
+        tag = vector_to_tag(vec)
+        words.append(r["word"])
+        tags.append(tag)
         vals.append(expanded_text(vec, lang))
-    df = pd.DataFrame({UI[lang]["m"]: vals})
+    df = pd.DataFrame({
+        UI[lang]["w"]: words,
+        UI[lang]["t"]: tags,
+        UI[lang]["m"]: vals,
+    })
     return _write_tsv(df, "Markað_útgreinað.tsv")
 
 with gr.Blocks(css=CSS, title="Marka") as demo: