Upload 2 files

app.py

@@ -32,8 +32,8 @@ GROUP_ORDER = ["subcategory","gender","number","case","article","proper","degree
 HIDE_CODES = {"subcategory": {"B"}}
 
 UI = {
-    "fo": {"w":"Orð", "t":"Mark", "s":"Vís sum", "m":"Merking"},
-    "en": {"w":"Word","t":"Tag", "s":"Show as", "m":"Meaning"},
+    "fo": {"w":"Orð", "t":"Mark", "s":"Útgreining", "m":"Merking"},
+    "en": {"w":"Word","t":"Tag", "s":"Analysis", "m":"Meaning"},
 }
 
 # Theme color: #89AFA9 (+ close shades)
@@ -47,6 +47,16 @@ CSS = """
 }
 .gr-button-primary:hover, button.primary:hover, .primary:hover{ background:var(--primary-600)!important; }
 a{ color:var(--primary-700)!important; }
+
+/* Dataframe column sizing:
+   - word + tag stay on one line
+   - analysis can wrap only if needed
+*/
+.gr-dataframe table { table-layout: auto !important; width: 100% !important; }
+.gr-dataframe th, .gr-dataframe td { vertical-align: top; }
+.gr-dataframe th:nth-child(1), .gr-dataframe td:nth-child(1) { white-space: nowrap; width: 1%; }
+.gr-dataframe th:nth-child(2), .gr-dataframe td:nth-child(2) { white-space: nowrap; min-width: 8.5rem; }
+.gr-dataframe th:nth-child(3), .gr-dataframe td:nth-child(3) { white-space: normal; }
 """
 
 def simp_tok(s: str):
@@ -178,45 +188,66 @@ def group_code(vec: torch.Tensor, group: str) -> str:
 def clean_label(s: str) -> str:
     s = (s or "").strip()
     s = re.sub(r"\s+", " ", s)
+    # remove leading punctuation/hyphen artifacts
     s = s.strip(" -;,:")
     return s
 
 def visible_summary(vec: torch.Tensor, lang: str) -> str:
     """
-    Vís sum / Show as:
-    - ONLY words/labels, no letters, no hyphens like "X –"
-    - all selected features (stable order)
+    Útgreining / Analysis:
+    - ONLY words/labels (no letters, no hyphens like "X –")
+    - word + tag columns stay single-line; analysis wraps only if needed (CSS)
     """
     lang = "fo" if lang=="fo" else "en"
     raw_tag = vector_to_tag(vec)
     wc = wc_code(vec)
 
-    wc_lbl = label_for(lang, "word_class", wc, wc) or wc
-
-    # Exact override requested earlier:
+    # Special-case: DGd should show ONLY "fyriseting"/"preposition"
     if raw_tag == "DGd":
-        wc_lbl = "Fyriseting" if lang=="fo" else "Preposition"
+        return "fyriseting" if lang == "fo" else "preposition"
+
+    wc_lbl = clean_label(label_for(lang, "word_class", wc, wc) or wc)
 
-    labels = [clean_label(wc_lbl)]
+    labels = []
+
+    # For pronouns: don't start with the main word-class label (subcategories already include it)
+    if wc != "P":
+        if wc_lbl:
+            labels.append(wc_lbl)
 
     for g in GROUP_ORDER:
         c = group_code(vec, g)
         if not c:
             continue
 
+        # Hide "stýrir falli" / "stýrir ikki falli" in Útgreining (but keep them in expanded tags)
+        if wc == "D" and g == "subcategory" and c in {"G", "N"}:
+            continue
+
         lbl = label_for(lang, g, wc, c) or label_for(lang, g, "", c) or ""
         lbl = clean_label(lbl)
         if not lbl:
             continue
 
+        # Extra safety in case the exact phrases come from labels
+        if lang == "fo" and lbl in {"stýrir falli", "stýrir ikki falli"}:
+            continue
+        if lang == "en" and lbl.lower() in {"governs case", "does not govern case"}:
+            continue
+
         if lbl not in labels:
             labels.append(lbl)
 
-    return ", ".join([l for l in labels if l])
+    # If pronoun ended up empty (shouldn't), fall back to word-class label
+    if not labels and wc_lbl:
+        labels = [wc_lbl]
+
+    return ", ".join(labels)
+
 
 def meaning_detail(vec: torch.Tensor, lang: str) -> str:
     """
-    Merking / Meaning:
+    Merking / Meaning (more explicit):
     keeps codes + labels (useful for debugging and linguists)
     """
     lang = "fo" if lang=="fo" else "en"
@@ -263,7 +294,7 @@ CODES_BY_WC = compute_codes_by_wc()
 def build_legend(lang: str) -> str:
     """
     Elaborate overview:
-    Under each word class, show the letter codes actually used in the CURRENT CSV,
+    Under each orðaflokkur / word class, show the letter codes actually used in the CURRENT CSV,
     with labels from tag_labels.json (fallback to code if missing).
     """
     lang = "fo" if lang=="fo" else "en"
@@ -279,6 +310,7 @@ def build_legend(lang: str) -> str:
             if not cs:
                 continue
 
+            # group header
             if lang=="fo":
                 group_name = {
                     "subcategory":"Undirflokkur",
@@ -410,7 +442,7 @@ with gr.Blocks(theme=theme, css=CSS, title="BRAGD-markarin") as demo:
     # Under results + can be changed AFTER tagging (no rerun; just re-render)
     lang = gr.Dropdown(choices=[("Føroyskt","fo"), ("English","en")], value="fo", label="Mál / Language")
 
-    with gr.Accordion("Merking / Meaning", open=False):
+    with gr.Accordion("Útgreinað marking / Expanded tags", open=False):
         out_mean_df = gr.Dataframe(wrap=True, interactive=False, label="")
 
     with gr.Accordion("Markingaryvirlit / Legend", open=False):

tag_labels.json

@@ -150,7 +150,10 @@
         "subcategory": {
           "D": "demonstrative",
           "E": "possessive",
-          "I": "indefinite"
+          "I": "indefinite",
+          "P": "personal pronoun",
+          "Q": "interrogative pronoun",
+          "X": "reflexive pronoun"
         },
         "gender": {
           "M": "masculine",
@@ -179,7 +182,9 @@
         },
         "subcategory": {
           "C": "cardinal number",
-          "O": "Date and other indeclinable number"
+          "O": "Date and other indeclinable number",
+          "P": "percentage",
+          "R": "number preceding other numeral"
         },
         "gender": {
           "M": "masculine",
@@ -331,8 +336,8 @@
         "A": "lýsingarorð",
         "P": "fornavn",
         "N": "talorð",
-        "V": "sagnorð (ikki lýsingarháttur)",
-        "L": "lýsingarháttur",
+        "V": "sagnorð",
+        "L": "tátíðar lýsingarháttur",
         "D": "hjáorð",
         "C": "sambindingarorð",
         "F": "útlendskt orð",
@@ -474,7 +479,10 @@
         "subcategory": {
           "D": "ávísingarfornavn",
           "E": "ognarfornavn",
-          "I": "óbundið fornavn"
+          "I": "óbundið fornavn",
+          "P": "perónsfornavn",
+          "Q": "spurnarfornavn",
+          "X": "afturbent fornavn"
         },
         "gender": {
           "M": "kallkyn",
@@ -503,7 +511,9 @@
         },
         "subcategory": {
           "C": "grundtal",
-          "O": "dagfesting og onnur óbendandi tøl"
+          "O": "dagfesting og onnur óbendandi tøl",
+          "P": "prosent",
+          "R": "nummar sum er framman fyri annað nummar"
         },
         "gender": {
           "M": "kallkyn",
@@ -523,7 +533,7 @@
       },
       "V": {
         "word_class": {
-          "V": "sagnorð (ikki lýsingarháttur)"
+          "V": "sagnorð"
         },
         "mood": {
           "I": "navnháttur",
@@ -552,7 +562,7 @@
       },
       "L": {
         "word_class": {
-          "L": "lýsingarháttur"
+          "L": "tátíðar lýsingarháttur"
         },
         "tense": {
           "P": "nútíð",