Cleanup. Text formatting. Fallback picture annotation.

docling_serve/ui/app.py

@@ -16,7 +16,7 @@ from fastapi import (
 from fastapi.responses import HTMLResponse, RedirectResponse, Response
 from fastapi.staticfiles import StaticFiles
 from pydantic import AnyHttpUrl
-from pyjsx import auto_setup
+from pyjsx import auto_setup  # type: ignore
 from starlette.exceptions import HTTPException as StarletteHTTPException
 
 from docling.datamodel.base_models import OutputFormat
@@ -131,7 +131,7 @@ def create_ui_app(process_file, process_url, task_result, task_status_poll) -> F
     ):
         tasks = sorted(orchestrator.tasks.values(), key=lambda t: t.created_at)
 
-        return str(TasksPage(tasks=tasks))
+        return str(TasksPage(tasks))
 
     # Task specific page.
     @ui_app.get("/tasks/{task_id}/", response_class=HTMLResponse)

docling_serve/ui/preview.px

@@ -10,6 +10,7 @@ from docling_core.types.doc.document import (
     DoclingDocument,
     DocItem,
     FloatingItem,
+    Formatting,
     FormulaItem,
     GroupItem,
     GroupLabel,
@@ -20,6 +21,7 @@ from docling_core.types.doc.document import (
     PictureItem,
     ProvenanceItem,
     RefItem,
+    Script,
     SectionHeaderItem,
     TableCell,
     TableItem,
@@ -28,7 +30,7 @@ from docling_core.types.doc.document import (
 )
 from pyjsx import jsx, JSX, JSXComponent
 
-from .svg import circle, clipPath, image, path, rect, text
+from .svg import image, path, rect, text
 
 
 _node_components: dict[str, JSXComponent] = {}
@@ -63,7 +65,7 @@ def NodeComponent(children, node: NodeItem | RefItem, doc: DoclingDocument):
     # Wrap item component with annotations, if any.
     if isinstance(node, DocItem) and (anns := node.get_annotations()):
         element = (
-            <div>
+            <div class="annotated">
                 {element}
                 {[<AnnotationComponent annotation={ann} /> for ann in anns]}
             </div>
@@ -73,7 +75,9 @@ def NodeComponent(children, node: NodeItem | RefItem, doc: DoclingDocument):
     id = node.self_ref[2:]
     element.props["id"] = id
     element.props["onclick"] = "clickId(event)"
-    element.props["class"] = element.props.get("class", "") + f" item {node.content_layer.value}"
+
+    classes = ["item", node.content_layer.value]
+    element.props["class"] = f"{element.props.get("class", "")} {" ".join(classes)}"
 
     return element
 
@@ -203,34 +207,67 @@ def DocPreview(children, doc: DoclingDocument):
     ]
 
 
+def _text_classes(node: TextItem) -> str:
+    classes = [node.label]
+
+    if frmt := node.formatting:
+        formats = {
+            "bold": frmt.bold,
+            "italic": frmt.italic,
+            "underline": frmt.underline,
+            "strikethrough": frmt.strikethrough
+        }
+        classes.extend([cls for cls, active in formats.items() if active])
+        classes.append(frmt.script)
+
+    return " ".join(classes)
+
+
 @component(TextItem)
 def TextComponent(children, node: TextItem, doc: DoclingDocument):
-    return <p class={node.label}>{escape(node.text)}</p>
+    return <p class={_text_classes(node)}>{escape(node.text)}</p>
 
 
 @component(TitleItem)
 def TitleComponent(children, node: TitleItem, doc: DoclingDocument):
-    return <h1>{escape(node.text)}</h1>
+    return <h1 class={_text_classes(node)}>{escape(node.text)}</h1>
 
 
 @component(SectionHeaderItem)
 def SectionHeaderComponent(children, node: SectionHeaderItem, doc: DoclingDocument):
-    return <h4>{escape(node.text)}</h4>
+    return <h4 class={_text_classes(node)}>{escape(node.text)}</h4>
 
 
 @component(ListItem)
 def ListComponent(children, node: ListItem, doc: DoclingDocument):
-    return <li><b>{node.marker}</b> {escape(node.text)}</li>
+    return (
+        <li>
+            <b>{node.marker}</b>
+            <span class={_text_classes(node)}>{escape(node.text)}</span>
+        </li>
+    )
 
 
 @component(CodeItem)
 def CodeComponent(children, node: CodeItem, doc: DoclingDocument):
-    return <figure><code>{escape(node.text or node.orig)}</code></figure>
+    return (
+        <figure>
+            <code class={_text_classes(node)}>
+                {escape(node.text or node.orig)}
+            </code>
+        </figure>
+    )
 
 
 @component(FormulaItem)
 def FormulaComponent(children, node: FormulaItem, doc: DoclingDocument):
-    return <figure><code>{escape(node.text or node.orig)}</code></figure>
+    return (
+        <figure>
+            <code class={_text_classes(node)}>
+                {escape(node.text or node.orig)}
+            </code>
+        </figure>
+    )
 
 
 @component(PictureItem)
@@ -240,25 +277,25 @@ def PictureComponent(children, node: PictureItem, doc: DoclingDocument):
 
 @component(PictureClassificationData)
 def PictureClassificationComponent(children, annotation: PictureClassificationData):
-    classes = annotation.predicted_classes[:5]
     return (
-        <div>
-            {[
-                <div
-                    style={{ "width": f"{cls.confidence * 100}%" }}
-                    title={f"{cls.class_name}: {cls.confidence:.2f}"}
-                >
-                    {f"{cls.class_name.replace("_", " ")} {cls.confidence:.2f}"}
-                </div>
-                for cls in classes
-            ]}
-        </div>
+        <table>
+            <tbody>
+                {[
+                    <tr>
+                        <td>{cls.class_name.replace("_", " ")}</td>
+                        <td>{f"{cls.confidence:.2f}"}</td>
+                    </tr>
+                    for cls in annotation.predicted_classes
+                    if cls.confidence > 0.01
+                ]}
+            </tbody>
+        </table>
     )
 
 
 @component(DescriptionAnnotation)
 def DescriptionAnnotation(children, annotation: DescriptionAnnotation):
-    return <div>{escape(annotation.text)}</div>
+    return <span>{escape(annotation.text)}</span>
 
 
 @component(TableItem)

docling_serve/ui/static/style.css

@@ -1,79 +1,15 @@
 @import "pico.css";
 
-/* Pico configuration. */
-:root {
-  --pico-font-size: 16px;
-}
-
-/* Utilities. */
-.w-4 {
-  width: calc(4 * var(--pico-spacing));
-}
-.w-full {
-  width: 100%;
-}
-.max-w-full {
-  max-width: 100%;
-}
-.mt-1 {
-  margin-top: var(--pico-spacing);
-}
-.mr-auto {
-  margin-right: auto;
-}
-.mb-1 {
-  margin-bottom: var(--pico-spacing);
-}
-.mb-2 {
-  margin-bottom: calc(2 * var(--pico-spacing));
-}
-.flex {
-  display: flex;
-}
-.flex.row {
-  flex-direction: row;
-}
-.flex.col {
-  flex-direction: column;
-}
-.flex-1 {
-  flex: 1 1 0%;
-}
-.flex-auto {
-  flex: 1 1 auto;
-}
-.gap-0 {
-  gap: 0;
-}
-.gap-1 {
-  gap: 0.25rem;
-}
-.gap-2 {
-  gap: 0.5rem;
-}
-.gap-3 {
-  gap: 1rem;
-}
-.hidden {
-  display: none;
-}
-.sticky-footer {
-  position: sticky;
-  bottom: 0;
-  padding-top: var(--pico-spacing);
-  background: var(--pico-background-color);
-}
-
-/* Customization. */
-
 @view-transition {
   navigation: auto;
 }
 
 :root {
+  --pico-font-size: 16px;
+
   --highlight-factor: 0.8;
   --target: hsl(240, 100%, 34%);
-  --mark: hsl(29, 100%, 40%);
+  --mark: hsl(29, 100%, 35%);
 }
 
 @media (prefers-color-scheme: dark) {
@@ -84,6 +20,18 @@
   }
 }
 
+/* Utilities. */
+.hidden {
+  display: none;
+}
+
+.sticky-footer {
+  position: sticky;
+  bottom: 0;
+  padding-top: var(--pico-spacing);
+  background: var(--pico-background-color);
+}
+
 html {
   scroll-behavior: smooth;
 }
@@ -232,6 +180,10 @@ main.preview {
   main.preview:has(.configDarkImg > input:checked) {
     --img-hover-border: white;
 
+    svg.page-image {
+      --mark: hsl(29, 100%, 70%)
+    }
+
     image,
     img {
       filter: invert(1) hue-rotate(180deg) saturate(1.25);
@@ -280,6 +232,38 @@ main.preview {
       visibility: hidden;
     }
 
+    > .item.annotated {
+      display: flex;
+      flex-direction: column;
+      align-items: stretch;
+      gap: 1rem;
+    }
+
+    /* Formatting. */
+    .bold {
+      font-weight: bold;
+    }
+    .italic {
+      font-style: italic;
+    }
+    .underline {
+      text-decoration: underline;
+    }
+    .strikethrough {
+      text-decoration: line-through;
+    }
+    .underline.strikethrough {
+      text-decoration: underline line-through;
+    }
+    .sub {
+      font-size: smaller;
+      vertical-align: sub;
+    }
+    .super {
+      font-size: smaller;
+      vertical-align: super;
+    }
+
     /* Items out of content layer. */
     > .item:not(.body),
     > .item-markers:not(.body) {
@@ -319,34 +303,27 @@ main.preview {
     }
 
     .annotation {
-      margin: 0.5rem 1rem;
-      font-size: 0.9rem;
-      color: var(--mark);
+      margin: 0;
 
       &::before {
-        margin-right: 0.5rem;
         content: attr(data-kind);
         opacity: 0.7;
       }
+
+      &,
+      * {
+        font-size: 0.9rem;
+        color: var(--mark);
+      }
     }
 
-    .annotation[data-kind="description"] {
+    .annotation[data-kind="description"],
+    code.annotation {
       white-space: pre-line;
     }
 
     .annotation[data-kind="classification"] {
-      height: 1.5rem;
-      display: flex;
-      align-items: center;
-
-      > div {
-        padding: 0 0.25rem;
-        background: var(--mark);
-        border: solid 1px var(--pico-background-color);
-        color: var(--pico-background-color);
-        overflow: hidden;
-        text-wrap: nowrap;
-      }
+      width: fit-content;
     }
 
     > .item-markers {
@@ -409,6 +386,8 @@ main.preview {
     }
 
     > svg.page-image {
+      --mark: hsl(29, 100%, 35%);
+
       grid-column: 5;
       position: sticky;
       top: 0.5rem;

docling_serve/ui/svg.py

@@ -1,4 +1,4 @@
-from pyjsx import JSX
+from pyjsx import JSX  # type: ignore
 
 
 def _tag(name: str):
@@ -6,7 +6,7 @@ def _tag(name: str):
         props = " ".join([f'{k}="{v}"' for k, v in args.items()])
 
         if children:
-            child_renders = "".join([f"{c}" for c in children])
+            child_renders = "".join([str(c) for c in children])
             return f"<{name} {props}>{child_renders}</{name}>"
         else:
             return f"<{name} {props} />"
@@ -14,12 +14,7 @@ def _tag(name: str):
     return factory
 
 
-circle = _tag("circle")
-clipPath = _tag("clipPath")
-defs = _tag("defs")
-foreignObject = _tag("foreignobject")
 image = _tag("image")
 path = _tag("path")
 rect = _tag("rect")
 text = _tag("text")
-use = _tag("use")