Upload app.py with huggingface_hub

app.py

@@ -54,7 +54,8 @@ def convert(text: str, num_candidates: int = 3, structured_fallback: bool = True
 
     PASITA samples the document several times, every candidate is post-processed and
     scored for number fidelity, content coverage and GFM validity, and the best one is
-    returned. Inputs detected as HTML or delimited data are converted deterministically.
+    returned. Inputs detected as HTML or delimited data are converted deterministically,
+    and a run that loses source numbers falls back to a faithful passthrough of the input.
 
     Args:
         text: The document to convert, for example OCR output, pasted HTML, meeting notes or a report.
@@ -93,9 +94,14 @@ def convert(text: str, num_candidates: int = 3, structured_fallback: bool = True
     metrics = result["metrics"]
     numbers = f"{metrics['numbers_matched']}/{metrics['numbers_in']} NUMBERS"
     overlap = f"{metrics['content_overlap']:.0%} CONTENT"
-    source = "HTML/TABLE CONVERTER" if result.get("strategy", {}).get("mode") == "structured" else "PASITA + RERANK"
+    routes = {
+        "model": "PASITA + RERANK",
+        "structured": "HTML/TABLE CONVERTER",
+        "passthrough": "SOURCE PASSTHROUGH",
+    }
+    source_label = routes.get(result.get("route"), "PASITA + RERANK")
     taken = result["seconds"] if result["seconds"] else time.perf_counter() - started
-    detail = f"{source} / {numbers} / {overlap} / {taken:.1f}S"
+    detail = f"{source_label} / {numbers} / {overlap} / {taken:.1f}S"
     return result["markdown"], result["markdown"], _status("DONE", "ready", detail)
 
 
@@ -103,6 +109,21 @@ def reset() -> tuple[str, str, str, str]:
     return EMPTY_MD, "", _status("READY"), _counter("")
 
 
+BUSY_JS = """(text, num_candidates, structured_fallback, md, source, status) => {
+  const n = Number(num_candidates) || 1;
+  const label = n > 1 ? 'PASITA ' + n + ' SAMPLES / RERANK' : 'PASITA SAMPLE / RERANK';
+  return [md, source,
+    '<div class="p-status busy"><span class="p-dot"></span><span class="p-text">CONVERTING</span><span class="p-detail">' + label + '</span></div>'];
+}"""
+
+COUNTER_JS = """(text) => {
+  const t = (text || '').trim();
+  const words = t ? t.split(/\\s+/).length : 0;
+  const chars = (text || '').length;
+  return '<span class="p-label">PLAIN TEXT</span><span class="p-count">' + chars.toLocaleString() + ' CHARS / ' + words.toLocaleString() + ' WORDS</span>';
+}"""
+
+
 HEADER = f"""
 <header class="p-head">
   <div class="p-brand">
@@ -228,7 +249,7 @@ body, .gradio-container {
   -webkit-font-smoothing: antialiased;
 }
 .gradio-container { max-width: 1240px !important; margin: 0 auto; padding: 0 20px 26px; }
-footer { display: none !important; }
+footer[aria-label="Gradio footer navigation"] { display: none !important; }
 :focus-visible { outline: 2px solid var(--cool) !important; outline-offset: 2px; }
 
 .p-head {
@@ -284,29 +305,33 @@ footer { display: none !important; }
 #p-clear { flex: 1; background: transparent !important; color: var(--muted) !important; border: 1px solid var(--hair) !important; }
 #p-clear:hover { color: var(--ink) !important; border-color: rgba(255,255,255,0.3) !important; }
 
-#p-examples table { border-collapse: separate; border-spacing: 6px; }
-#p-examples button {
+#p-examples .label { font-family: var(--font-mono) !important; font-size: 0.66rem !important; letter-spacing: 0.14em; text-transform: uppercase; color: var(--muted) !important; }
+#p-examples .label svg { display: none; }
+#p-examples .gallery-item {
   background: var(--panel) !important; border: 1px solid var(--hair) !important; border-radius: 999px !important;
-  color: var(--muted) !important; font-size: 12px !important; min-height: 40px; padding: 8px 14px !important;
+  color: var(--muted) !important; font-size: 12px !important; min-height: 44px; padding: 8px 14px !important;
   text-align: left; transition: background .2s ease, color .2s ease, border-color .2s ease;
 }
-#p-examples button:hover { border-color: rgba(255,255,255,0.3) !important; color: var(--ink) !important; background: var(--panel-hover) !important; }
-#p-examples label { font-family: var(--font-mono) !important; font-size: 0.66rem !important; letter-spacing: 0.14em; text-transform: uppercase; color: var(--muted) !important; }
+#p-examples .gallery-item:hover { border-color: rgba(255,255,255,0.3) !important; color: var(--ink) !important; background: var(--panel-hover) !important; }
 
-#p-tabs .tab-nav {
+#p-tabs .tab-container[role="tablist"] {
   display: inline-flex; gap: 4px; background: var(--panel); border: 1px solid var(--hair);
   border-radius: 100px; padding: 3px; margin-bottom: 12px;
 }
-#p-tabs .tab-nav button {
+#p-tabs .tab-container[role="tablist"] button {
   appearance: none; border: 0 !important; background: transparent !important; border-radius: 100px !important;
   padding: 7px 14px !important; font-family: var(--font-mono) !important; font-size: 10.5px !important;
   letter-spacing: 0.1em; text-transform: uppercase; color: var(--muted) !important;
 }
-#p-tabs .tab-nav button.selected, #p-tabs .tab-nav button[aria-selected="true"] {
+#p-tabs .tab-container[role="tablist"] button.selected,
+#p-tabs .tab-container[role="tablist"] button[aria-selected="true"] {
   background: rgba(255,255,255,0.08) !important; color: var(--warm) !important;
 }
+#p-tabs .tab-container::after,
+#p-tabs .tab-container button.selected::after { content: none !important; }
 
 #p-rendered { min-height: 360px; font-size: 0.95rem; line-height: 1.72; color: var(--ink); }
+#p-rendered .prose { font-size: 0.95rem; line-height: 1.72; }
 #p-rendered h1, #p-rendered h2, #p-rendered h3, #p-rendered h4 { color: #fff; font-weight: 600; line-height: 1.25; margin: 1.25em 0 0.55em; }
 #p-rendered h1 { font-size: 1.5em; }
 #p-rendered h2 { font-size: 1.28em; }
@@ -330,9 +355,14 @@ footer { display: none !important; }
   background: var(--obsidian) !important; border: 1px solid var(--hair-soft) !important;
   border-radius: 12px !important; font-family: var(--font-mono) !important; min-height: 360px;
 }
+#p-source label[data-testid="block-label"] { display: none; }
+#p-source .cm-editor { background: transparent !important; }
+#p-source .cm-content, #p-source .cm-scroller { color: var(--ink) !important; caret-color: var(--warm) !important; }
+#p-source .cm-gutters { background: transparent !important; color: var(--muted-2) !important; border-right: 1px solid var(--hair-soft) !important; }
 
 #p-settings { background: transparent !important; border: 1px solid var(--hair-soft) !important; border-radius: 12px !important; margin-top: 4px; }
-#p-settings summary, #p-settings > .label-wrap { font-family: var(--font-mono) !important; font-size: 0.68rem !important; letter-spacing: 0.12em; text-transform: uppercase; color: var(--muted) !important; }
+#p-settings > .label-wrap { font-family: var(--font-mono) !important; font-size: 0.68rem !important; letter-spacing: 0.12em; text-transform: uppercase; color: var(--muted) !important; }
+#p-settings > .label-wrap .icon { color: var(--muted-2) !important; }
 #p-settings .p-label { margin-bottom: 4px; }
 
 .p-foot {
@@ -376,9 +406,9 @@ with gr.Blocks(title="PASITA: plain text to Markdown") as demo:
             text_in = gr.Textbox(
                 show_label=False,
                 container=False,
-                placeholder="Paste OCR output, pasted HTML, meeting notes, a report or an article...",
+                placeholder="Paste OCR output, pasted HTML, meeting notes, a report or an article... (SHIFT + ENTER to convert)",
                 lines=18,
-                max_lines=36,
+                max_lines=32,
                 elem_id="p-text",
             )
             with gr.Accordion("SETTINGS", open=False, elem_id="p-settings"):
@@ -397,13 +427,17 @@ with gr.Blocks(title="PASITA: plain text to Markdown") as demo:
                 clear = gr.Button("CLEAR", elem_id="p-clear")
         with gr.Column(scale=1, min_width=320, elem_classes=["p-panel"]):
             with gr.Tabs(elem_id="p-tabs"):
-                with gr.Tab("RENDERED"):
-                    md_out = gr.Markdown(EMPTY_MD, buttons=["copy"], elem_id="p-rendered")
-                with gr.Tab("SOURCE"):
-                    source = gr.Code(value="", language="markdown", buttons=["copy"], wrap_lines=True, elem_id="p-source")
+                with gr.Tab("RENDERED", elem_id="p-tab-rendered"):
+                    md_out = gr.Markdown(EMPTY_MD, buttons=["copy"], height=520, elem_id="p-rendered")
+                with gr.Tab("SOURCE", elem_id="p-tab-source"):
+                    source = gr.Code(
+                        value="", language="markdown", buttons=["copy", "download"],
+                        wrap_lines=True, lines=24, max_lines=24, elem_id="p-source",
+                    )
 
     gr.Examples(
         examples=EXAMPLES,
+        example_labels=["ES REPORT", "EN MEETING", "HTML", "CSV"],
         inputs=[text_in],
         outputs=[md_out, source, status],
         fn=convert,
@@ -415,10 +449,24 @@ with gr.Blocks(title="PASITA: plain text to Markdown") as demo:
     )
     gr.HTML(FOOTER)
 
-    run.click(convert, inputs=[text_in, candidates, structured], outputs=[md_out, source, status], api_name="convert")
-    text_in.submit(convert, inputs=[text_in, candidates, structured], outputs=[md_out, source, status], api_name=False)
-    text_in.change(_counter, inputs=[text_in], outputs=[label_in], api_name=False)
-    clear.click(reset, inputs=None, outputs=[md_out, source, status, label_in], api_name=False)
+    run.click(
+        convert,
+        inputs=[text_in, candidates, structured],
+        outputs=[md_out, source, status],
+        api_name="convert",
+        js=BUSY_JS,
+        show_progress="minimal",
+    )
+    text_in.submit(
+        convert,
+        inputs=[text_in, candidates, structured],
+        outputs=[md_out, source, status],
+        api_visibility="undocumented",
+        js=BUSY_JS,
+        show_progress="minimal",
+    )
+    text_in.change(None, inputs=[text_in], outputs=[label_in], js=COUNTER_JS, api_visibility="undocumented")
+    clear.click(reset, inputs=None, outputs=[md_out, source, status, label_in], api_visibility="undocumented")
 
 demo.queue()
 demo.launch(theme=theme, css=CSS, mcp_server=True)