Update v 0.0.6

README.md

@@ -6,7 +6,7 @@ tags:
 - textbox
 - editing
 - color
-title: gradio_highlightedtextbox v0.0.5
+title: gradio_highlightedtextbox v0.0.6
 colorFrom: indigo
 colorTo: green
 sdk: docker

app.py

@@ -4,64 +4,114 @@ from gradio_highlightedtextbox import HighlightedTextbox
 
 
 def convert_tagged_text_to_highlighted_text(
-    tagged_text: str, tag_id: str, tag_open: str, tag_close: str
+    tagged_text: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
 ) -> list[tuple[str, str | None]]:
     return HighlightedTextbox.tagged_text_to_tuples(
         tagged_text, tag_id, tag_open, tag_close
     )
 
 
-with gr.Blocks() as demo:
-    tag_id = gr.Textbox(
-        "Potential issue",
-        label="Tag ID",
-        show_label=True,
-        info="Insert a tag ID to use in the highlighted textbox.",
-    )
-    tag_open = gr.Textbox(
-        "<h>",
-        label="Tag open",
-        show_label=True,
-        info="Insert a tag to mark the beginning of a highlighted section.",
-    )
-    tag_close = gr.Textbox(
-        "</h>",
-        label="Tag close",
-        show_label=True,
-        info="Insert a tag to mark the end of a highlighted section.",
+def convert_highlighted_text_to_tagged_text(
+    highlighted_text: dict[str, str | list[tuple[str, str | None]]],
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
+) -> str:
+    return HighlightedTextbox.tuples_to_tagged_text(
+        highlighted_text["data"], tag_id, tag_open, tag_close
     )
+
+
+initial_text = "It is not something to be ashamed of: it is no different from the <d>personal fears</d> and <tm>dislikes</tm> of other things that <t>manny peopl</t> have."
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Parameters to control the highlighted textbox:")
     with gr.Row():
-        tagged = gr.Textbox(
-            "It is not something to be ashamed of: it is no different from the <h>personal fears</h> and <h>dislikes</h> of other things that <h>very many people</h> have.",
+        tag_id = gr.Dropdown(
+            choices=["Typo", "Terminology", "Disfluency"],
+            value=["Typo", "Terminology", "Disfluency"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag ID",
+            show_label=True,
+            info="Insert one or more tag IDs to use in the highlighted textbox.",
+        )
+        tag_open = gr.Dropdown(
+            choices=["<t>", "<tm>", "<d>"],
+            value=["<t>", "<tm>", "<d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag open",
+            show_label=True,
+            info="Insert one or more tags to mark the beginning of a highlighted section.",
+        )
+        tag_close = gr.Dropdown(
+            choices=["</t>", "</tm>", "</d>"],
+            value=["</t>", "</tm>", "</d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag close",
+            show_label=True,
+            info="Insert one or more tags to mark the end of a highlighted section.",
+        )
+    gr.Markdown("### Example tagged to highlight:")
+    with gr.Row():
+        tagged_t2h = gr.Textbox(
+            initial_text,
             interactive=True,
-            label="Input",
+            label="Tagged Input",
+            show_label=True,
+            info="Tagged text using the format above to mark spans that will be highlighted.",
+        )
+        high_t2h = HighlightedTextbox(
+            convert_tagged_text_to_highlighted_text(
+                tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
+            ),
+            interactive=False,
+            label="Highlighted Output",
+            info="Highlighted textbox intialized from the tagged input.",
+            show_legend=True,
             show_label=True,
-            info="Insert a text with <h>...</h> tags to mark spans that will be highlighted.",
+            legend_label="Legend:",
+            show_legend_label=True,
         )
-        high = HighlightedTextbox(
+    gr.Markdown("### Example highlight to tagged:")
+    with gr.Row():
+        high_h2t = HighlightedTextbox(
+            convert_tagged_text_to_highlighted_text(
+                initial_text, tag_id.value, tag_open.value, tag_close.value
+            ),
             interactive=True,
-            label="Output",
-            info="Highlighted textbox.",
+            label="Highlighted Input",
+            info="Highlighted textbox using the format above to mark spans that will be highlighted.",
             show_legend=True,
             show_label=True,
             legend_label="Legend:",
             show_legend_label=True,
         )
-    button = gr.Button("Submit")
-    button.click(
+        tagged_h2t = gr.Textbox(
+            initial_text,
+            interactive=False,
+            label="Tagged Output",
+            info="Tagged text intialized from the highlighted textbox.",
+            show_label=True,
+        )
+
+    # Functions
+
+    tagged_t2h.input(
         fn=convert_tagged_text_to_highlighted_text,
-        inputs=[tagged, tag_id, tag_open, tag_close],
-        outputs=high,
+        inputs=[tagged_t2h, tag_id, tag_open, tag_close],
+        outputs=high_t2h,
     )
-    # Initialization does not work
-    high = HighlightedTextbox(
-        convert_tagged_text_to_highlighted_text(
-            tagged.value, tag_id.value, tag_open.value, tag_close.value
-        ),
-        interactive=True,
-        label="Does not work",
-        show_label=True,
+    high_h2t.input(
+        fn=convert_highlighted_text_to_tagged_text,
+        inputs=[high_h2t, tag_id, tag_open, tag_close],
+        outputs=tagged_h2t,
     )
 
-
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()

src/README.md

@@ -18,7 +18,10 @@ from gradio_highlightedtextbox import HighlightedTextbox
 
 
 def convert_tagged_text_to_highlighted_text(
-    tagged_text: str, tag_id: str, tag_open: str, tag_close: str
+    tagged_text: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
 ) -> list[tuple[str, str | None]]:
     return HighlightedTextbox.tagged_text_to_tuples(
         tagged_text, tag_id, tag_open, tag_close
@@ -27,64 +30,77 @@ def convert_tagged_text_to_highlighted_text(
 
 def convert_highlighted_text_to_tagged_text(
     highlighted_text: dict[str, str | list[tuple[str, str | None]]],
-    tag_id: str,
-    tag_open: str,
-    tag_close: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
 ) -> str:
     return HighlightedTextbox.tuples_to_tagged_text(
         highlighted_text["data"], tag_id, tag_open, tag_close
     )
 
 
-initial_text = "It is not something to be ashamed of: it is no different from the <h>personal fears</h> and <h>dislikes</h> of other things that <h>very many people</h> have."
+initial_text = "It is not something to be ashamed of: it is no different from the <d>personal fears</d> and <tm>dislikes</tm> of other things that <t>manny peopl</t> have."
 
 with gr.Blocks() as demo:
-    tag_id = gr.Textbox(
-        "Potential issue",
-        label="Tag ID",
-        show_label=True,
-        info="Insert a tag ID to use in the highlighted textbox.",
-    )
-    tag_open = gr.Textbox(
-        "<h>",
-        label="Tag open",
-        show_label=True,
-        info="Insert a tag to mark the beginning of a highlighted section.",
-    )
-    tag_close = gr.Textbox(
-        "</h>",
-        label="Tag close",
-        show_label=True,
-        info="Insert a tag to mark the end of a highlighted section.",
-    )
+    gr.Markdown("### Parameters to control the highlighted textbox:")
+    with gr.Row():
+        tag_id = gr.Dropdown(
+            choices=["Typo", "Terminology", "Disfluency"],
+            value=["Typo", "Terminology", "Disfluency"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag ID",
+            show_label=True,
+            info="Insert one or more tag IDs to use in the highlighted textbox.",
+        )
+        tag_open = gr.Dropdown(
+            choices=["<t>", "<tm>", "<d>"],
+            value=["<t>", "<tm>", "<d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag open",
+            show_label=True,
+            info="Insert one or more tags to mark the beginning of a highlighted section.",
+        )
+        tag_close = gr.Dropdown(
+            choices=["</t>", "</tm>", "</d>"],
+            value=["</t>", "</tm>", "</d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag close",
+            show_label=True,
+            info="Insert one or more tags to mark the end of a highlighted section.",
+        )
+    gr.Markdown("### Example tagged to highlight:")
     with gr.Row():
         tagged_t2h = gr.Textbox(
             initial_text,
             interactive=True,
-            label="Input",
+            label="Tagged Input",
             show_label=True,
-            info="Insert a text with <h>...</h> tags to mark spans that will be highlighted.",
+            info="Tagged text using the format above to mark spans that will be highlighted.",
         )
         high_t2h = HighlightedTextbox(
             convert_tagged_text_to_highlighted_text(
                 tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
             ),
-            interactive=True,
-            label="Output",
-            info="Highlighted textbox.",
+            interactive=False,
+            label="Highlighted Output",
+            info="Highlighted textbox intialized from the tagged input.",
             show_legend=True,
             show_label=True,
             legend_label="Legend:",
             show_legend_label=True,
         )
+    gr.Markdown("### Example highlight to tagged:")
     with gr.Row():
         high_h2t = HighlightedTextbox(
             convert_tagged_text_to_highlighted_text(
-                tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
+                initial_text, tag_id.value, tag_open.value, tag_close.value
             ),
             interactive=True,
-            label="Input",
-            info="The following text will be marked by spans according to its highlights.",
+            label="Highlighted Input",
+            info="Highlighted textbox using the format above to mark spans that will be highlighted.",
             show_legend=True,
             show_label=True,
             legend_label="Legend:",
@@ -92,31 +108,27 @@ with gr.Blocks() as demo:
         )
         tagged_h2t = gr.Textbox(
             initial_text,
-            interactive=True,
-            label="Output",
+            interactive=False,
+            label="Tagged Output",
+            info="Tagged text intialized from the highlighted textbox.",
             show_label=True,
         )
 
     # Functions
 
-    tagged_t2h.change(
+    tagged_t2h.input(
         fn=convert_tagged_text_to_highlighted_text,
         inputs=[tagged_t2h, tag_id, tag_open, tag_close],
         outputs=high_t2h,
     )
-    high_t2h.change(
-        fn=lambda x: x["data"],
-        inputs=high_t2h,
-        outputs=high_h2t,
-    )
-    high_h2t.change(
+    high_h2t.input(
         fn=convert_highlighted_text_to_tagged_text,
         inputs=[high_h2t, tag_id, tag_open, tag_close],
         outputs=tagged_h2t,
     )
 
-
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()
 
 ```
 

src/backend/gradio_highlightedtextbox/highlightedtextbox.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import re
 from typing import Any, Callable
 
 from gradio.components.base import FormComponent
@@ -180,7 +181,7 @@ class HighlightedTextbox(FormComponent):
         return [("Hello", None), ("world", "highlight")]
 
     @classmethod
-    def tagged_text_to_tuples(
+    def tagged_text_to_tuples_single_tag(
         cls, text: str, tag_id: str, tag_open: str = "<h>", tag_close: str = "</h>"
     ) -> list[tuple[str, str | None]]:
         """Parse a text containing tags into a list of tuples in the format accepted by HighlightedTextbox.
@@ -204,43 +205,108 @@ class HighlightedTextbox(FormComponent):
             `list[tuple[str, str | None]]`: List of tuples in the format accepted by HighlightedTextbox.
         """
         # Check that the text is well-formed (i.e. no nested or empty tags)
-        num_tags = text.count(tag_open)
-        if num_tags != text.count(tag_close):
-            raise ValueError(
-                f"Number of open tags ({tag_open}) does not match number of closed tags ({tag_close})."
-            )
-        elif num_tags == 0:
+        num_tags_open = text.count(tag_open)
+        num_tags_close = text.count(tag_close)
+        if num_tags_open == 0 or num_tags_close == 0:
             return [(text, None)]
-        elif num_tags > 0:
+        else:
             out = []
-            pre_tag_text = text[: text.index(tag_open)]
-            if pre_tag_text:
-                out += [(pre_tag_text.strip(), None)]
+            last_end = 0
+            for _ in range(min(num_tags_open, num_tags_close)):
+                start = text.index(tag_open, last_end)
+                end = text.index(tag_close, start)
+                if start > last_end:
+                    out.append((text[last_end:start].strip(), None))
+                out.append((text[start + len(tag_open) : end].strip(), tag_id))
+                last_end = end + len(tag_close)
+            if last_end < len(text):
+                out.append((text[last_end:].strip(), None))
+            return out
 
-            tag_text = text[
-                text.index(tag_open) + len(tag_open) : text.index(tag_close)
-            ]
-            out += [(tag_text.strip(), tag_id)]
-            if num_tags > 1:
-                remaining_text = text[text.index(tag_close) + len(tag_close) :]
-                out += cls.tagged_text_to_tuples(
-                    remaining_text,
-                    tag_id=tag_id,
-                    tag_open=tag_open,
-                    tag_close=tag_close,
-                )
-            else:
-                post_tag_text = text[text.index(tag_close) + len(tag_close) :]
-                if post_tag_text:
-                    out += [(post_tag_text, None)]
+    @classmethod
+    def tagged_text_to_tuples(
+        cls,
+        text: str,
+        tag_ids: str | list[str],
+        tags_open: str | list[str] = "<h>",
+        tags_close: str | list[str] = "</h>",
+    ) -> list[tuple[str, str | None]]:
+        """Parse a text containing tags into a list of tuples in the format accepted by HighlightedTextbox.
+
+        E.g. Hello <h>world</h>! -> [("Hello", None), ("world", <TAG_ID>), ("!", None)]
+
+        Args:
+            text (`str`):
+                Text containing tags that needs to be parsed.
+            tag_ids (`str` or `list[str]`):
+                Label(s) to use for the second element of the tuple.
+            tags_open (`str` or `list[str]`, *optional*, defaults to "<h>"):
+                Tag(s) used to mark the beginning of a highlighted section.
+            tag_close (`str` or `list[str]`, *optional*, defaults to "</h>"):
+                Tag(s) used to mark the end of a highlighted section.
+
+        Raises:
+            ValueError: If the number of tag IDs, open tags and closed tags is not the same.
+
+        Returns:
+            `list[tuple[str, str | None]]`: List of tuples in the format accepted by HighlightedTextbox.
+        """
+        seen_tag_ids = set()
+        seen_tags_open = set()
+        seen_tags_close = set()
+        if not isinstance(tag_ids, list):
+            tag_ids = [tag_ids]
+        if not isinstance(tags_open, list):
+            tags_open = [tags_open]
+        if not isinstance(tags_close, list):
+            tags_close = [tags_close]
+        # Make sure tags are unique
+        tag_ids = [x for x in tag_ids if not (x in seen_tag_ids or seen_tag_ids.add(x))]
+        tags_open = [
+            x for x in tags_open if not (x in seen_tags_open or seen_tags_open.add(x))
+        ]
+        tags_close = [
+            x
+            for x in tags_close
+            if not (x in seen_tags_close or seen_tags_close.add(x))
+        ]
+        if len(tag_ids) != len(tags_open) != len(tags_close):
+            raise ValueError(
+                "The number of tag IDs, open tags and closed tags must be the same."
+            )
+        # Create a dictionary mapping tag open/close pairs to their corresponding tag id
+        tag_dict = {
+            f"{open_tag}(.+?){close_tag}": tag_id
+            for tag_id, open_tag, close_tag in zip(tag_ids, tags_open, tags_close)
+        }
+
+        # Create a regular expression that matches any of the tags
+        tag_regex = re.compile("|".join(tag_dict.keys()))
+
+        out = []
+        last_end = 0
+        for match in tag_regex.finditer(text):
+            # Add the text before the tag to the output
+            if match.start() > last_end:
+                out.append((text[last_end : match.start()].strip(), None))
+            # Add the tag to the output
+            tag_text = match.group(0)
+            for tag, tag_id in tag_dict.items():
+                if re.fullmatch(tag, tag_text):
+                    out.append((re.search(tag, tag_text).group(1), tag_id))
+                    break
+            last_end = match.end()
+        # Add the text after the last tag to the output
+        if last_end < len(text):
+            out.append((text[last_end:].strip(), None))
         return out
 
     @staticmethod
     def tuples_to_tagged_text(
         tuples: list[tuple[str, str | None]],
         tag_ids: str | list[str] = [],
-        tag_open: str = "<h>",
-        tag_close: str = "</h>",
+        tags_open: str | list[str] = "<h>",
+        tags_close: str | list[str] = "</h>",
     ) -> str:
         """Convert a list of tuples in the format accepted by HighlightedTextbox into a text containing tags.
 
@@ -252,16 +318,27 @@ class HighlightedTextbox(FormComponent):
             tag_ids (`str` | `list[str]`):
                 Label(s) to select for the second element of the tuple. All other labels will be ignored
                 (i.e. replaced with None)
-            tag_open (`str`, *optional*, defaults to "<h>"):
-                Tag used to mark the beginning of a highlighted section.
-            tag_close (`str`, *optional*, defaults to "</h>"):
-                Tag used to mark the end of a highlighted section.
+            tags_open (`str`, *optional*, defaults to "<h>"):
+                Tag(s) used to mark the beginning of a highlighted section.
+            tags_close (`str`, *optional*, defaults to "</h>"):
+                Tag(s) used to mark the end of a highlighted section.
 
         Returns:
             `str`: Text containing tags.
         """
-        if isinstance(tag_ids, str):
+        if not isinstance(tag_ids, list):
             tag_ids = [tag_ids]
+        if not isinstance(tags_open, list):
+            tags_open = [tags_open]
+        if not isinstance(tags_close, list):
+            tags_close = [tags_close]
+        if len(tag_ids) != len(tags_open) != len(tags_close):
+            raise ValueError(
+                "The number of tag IDs, open tags and closed tags must be the same."
+            )
+        tuples = [
+            (text, tag_id if tag_id in tag_ids else None) for text, tag_id in tuples
+        ]
         out = ""
         for text, tag_id in tuples:
             space_or_not = (
@@ -269,8 +346,9 @@ class HighlightedTextbox(FormComponent):
                 if text not in [".", "!", "?", ",", ":", ")", "]", ";", "}", """'"""]
                 else ""
             )
-            if tag_id in tag_ids:
-                out += f"{space_or_not}{tag_open}{text.strip()}{tag_close}"
+            if tag_id is not None:
+                tag_id_idx = tag_ids.index(tag_id)
+                out += f"{space_or_not}{tags_open[tag_id_idx]}{text.strip()}{tags_close[tag_id_idx]}"
             else:
                 out += f"{space_or_not}{text.strip()} "
-        return out.strip()
+        return re.sub(" +", " ", out.strip())

src/backend/gradio_highlightedtextbox/highlightedtextbox.pyi

@@ -1,10 +1,16 @@
 from __future__ import annotations
 
+import re
 from typing import Any, Callable
 
 from gradio.components.base import FormComponent
+from gradio.data_classes import GradioRootModel
 from gradio.events import Events
 
+
+class HighlightedTextData(GradioRootModel):
+    root: list[tuple[str, str | None]]
+
 from gradio.events import Dependency
 
 class HighlightedTextbox(FormComponent):
@@ -176,7 +182,7 @@ class HighlightedTextbox(FormComponent):
         return [("Hello", None), ("world", "highlight")]
 
     @classmethod
-    def tagged_text_to_tuples(
+    def tagged_text_to_tuples_single_tag(
         cls, text: str, tag_id: str, tag_open: str = "<h>", tag_close: str = "</h>"
     ) -> list[tuple[str, str | None]]:
         """Parse a text containing tags into a list of tuples in the format accepted by HighlightedTextbox.
@@ -200,43 +206,108 @@ class HighlightedTextbox(FormComponent):
             `list[tuple[str, str | None]]`: List of tuples in the format accepted by HighlightedTextbox.
         """
         # Check that the text is well-formed (i.e. no nested or empty tags)
-        num_tags = text.count(tag_open)
-        if num_tags != text.count(tag_close):
-            raise ValueError(
-                f"Number of open tags ({tag_open}) does not match number of closed tags ({tag_close})."
-            )
-        elif num_tags == 0:
+        num_tags_open = text.count(tag_open)
+        num_tags_close = text.count(tag_close)
+        if num_tags_open == 0 or num_tags_close == 0:
             return [(text, None)]
-        elif num_tags > 0:
+        else:
             out = []
-            pre_tag_text = text[: text.index(tag_open)]
-            if pre_tag_text:
-                out += [(pre_tag_text.strip(), None)]
+            last_end = 0
+            for _ in range(min(num_tags_open, num_tags_close)):
+                start = text.index(tag_open, last_end)
+                end = text.index(tag_close, start)
+                if start > last_end:
+                    out.append((text[last_end:start].strip(), None))
+                out.append((text[start + len(tag_open) : end].strip(), tag_id))
+                last_end = end + len(tag_close)
+            if last_end < len(text):
+                out.append((text[last_end:].strip(), None))
+            return out
 
-            tag_text = text[
-                text.index(tag_open) + len(tag_open) : text.index(tag_close)
-            ]
-            out += [(tag_text.strip(), tag_id)]
-            if num_tags > 1:
-                remaining_text = text[text.index(tag_close) + len(tag_close) :]
-                out += cls.tagged_text_to_tuples(
-                    remaining_text,
-                    tag_id=tag_id,
-                    tag_open=tag_open,
-                    tag_close=tag_close,
-                )
-            else:
-                post_tag_text = text[text.index(tag_close) + len(tag_close) :]
-                if post_tag_text:
-                    out += [(post_tag_text, None)]
+    @classmethod
+    def tagged_text_to_tuples(
+        cls,
+        text: str,
+        tag_ids: str | list[str],
+        tags_open: str | list[str] = "<h>",
+        tags_close: str | list[str] = "</h>",
+    ) -> list[tuple[str, str | None]]:
+        """Parse a text containing tags into a list of tuples in the format accepted by HighlightedTextbox.
+
+        E.g. Hello <h>world</h>! -> [("Hello", None), ("world", <TAG_ID>), ("!", None)]
+
+        Args:
+            text (`str`):
+                Text containing tags that needs to be parsed.
+            tag_ids (`str` or `list[str]`):
+                Label(s) to use for the second element of the tuple.
+            tags_open (`str` or `list[str]`, *optional*, defaults to "<h>"):
+                Tag(s) used to mark the beginning of a highlighted section.
+            tag_close (`str` or `list[str]`, *optional*, defaults to "</h>"):
+                Tag(s) used to mark the end of a highlighted section.
+
+        Raises:
+            ValueError: If the number of tag IDs, open tags and closed tags is not the same.
+
+        Returns:
+            `list[tuple[str, str | None]]`: List of tuples in the format accepted by HighlightedTextbox.
+        """
+        seen_tag_ids = set()
+        seen_tags_open = set()
+        seen_tags_close = set()
+        if not isinstance(tag_ids, list):
+            tag_ids = [tag_ids]
+        if not isinstance(tags_open, list):
+            tags_open = [tags_open]
+        if not isinstance(tags_close, list):
+            tags_close = [tags_close]
+        # Make sure tags are unique
+        tag_ids = [x for x in tag_ids if not (x in seen_tag_ids or seen_tag_ids.add(x))]
+        tags_open = [
+            x for x in tags_open if not (x in seen_tags_open or seen_tags_open.add(x))
+        ]
+        tags_close = [
+            x
+            for x in tags_close
+            if not (x in seen_tags_close or seen_tags_close.add(x))
+        ]
+        if len(tag_ids) != len(tags_open) != len(tags_close):
+            raise ValueError(
+                "The number of tag IDs, open tags and closed tags must be the same."
+            )
+        # Create a dictionary mapping tag open/close pairs to their corresponding tag id
+        tag_dict = {
+            f"{open_tag}(.+?){close_tag}": tag_id
+            for tag_id, open_tag, close_tag in zip(tag_ids, tags_open, tags_close)
+        }
+
+        # Create a regular expression that matches any of the tags
+        tag_regex = re.compile("|".join(tag_dict.keys()))
+
+        out = []
+        last_end = 0
+        for match in tag_regex.finditer(text):
+            # Add the text before the tag to the output
+            if match.start() > last_end:
+                out.append((text[last_end : match.start()].strip(), None))
+            # Add the tag to the output
+            tag_text = match.group(0)
+            for tag, tag_id in tag_dict.items():
+                if re.fullmatch(tag, tag_text):
+                    out.append((re.search(tag, tag_text).group(1), tag_id))
+                    break
+            last_end = match.end()
+        # Add the text after the last tag to the output
+        if last_end < len(text):
+            out.append((text[last_end:].strip(), None))
         return out
 
     @staticmethod
     def tuples_to_tagged_text(
         tuples: list[tuple[str, str | None]],
         tag_ids: str | list[str] = [],
-        tag_open: str = "<h>",
-        tag_close: str = "</h>",
+        tags_open: str | list[str] = "<h>",
+        tags_close: str | list[str] = "</h>",
     ) -> str:
         """Convert a list of tuples in the format accepted by HighlightedTextbox into a text containing tags.
 
@@ -248,16 +319,27 @@ class HighlightedTextbox(FormComponent):
             tag_ids (`str` | `list[str]`):
                 Label(s) to select for the second element of the tuple. All other labels will be ignored
                 (i.e. replaced with None)
-            tag_open (`str`, *optional*, defaults to "<h>"):
-                Tag used to mark the beginning of a highlighted section.
-            tag_close (`str`, *optional*, defaults to "</h>"):
-                Tag used to mark the end of a highlighted section.
+            tags_open (`str`, *optional*, defaults to "<h>"):
+                Tag(s) used to mark the beginning of a highlighted section.
+            tags_close (`str`, *optional*, defaults to "</h>"):
+                Tag(s) used to mark the end of a highlighted section.
 
         Returns:
             `str`: Text containing tags.
         """
-        if isinstance(tag_ids, str):
+        if not isinstance(tag_ids, list):
             tag_ids = [tag_ids]
+        if not isinstance(tags_open, list):
+            tags_open = [tags_open]
+        if not isinstance(tags_close, list):
+            tags_close = [tags_close]
+        if len(tag_ids) != len(tags_open) != len(tags_close):
+            raise ValueError(
+                "The number of tag IDs, open tags and closed tags must be the same."
+            )
+        tuples = [
+            (text, tag_id if tag_id in tag_ids else None) for text, tag_id in tuples
+        ]
         out = ""
         for text, tag_id in tuples:
             space_or_not = (
@@ -265,11 +347,12 @@ class HighlightedTextbox(FormComponent):
                 if text not in [".", "!", "?", ",", ":", ")", "]", ";", "}", """'"""]
                 else ""
             )
-            if tag_id in tag_ids:
-                out += f"{space_or_not}{tag_open}{text.strip()}{tag_close}"
+            if tag_id is not None:
+                tag_id_idx = tag_ids.index(tag_id)
+                out += f"{space_or_not}{tags_open[tag_id_idx]}{text.strip()}{tags_close[tag_id_idx]}"
             else:
                 out += f"{space_or_not}{text.strip()} "
-        return out.strip()
+        return re.sub(" +", " ", out.strip())
 
     
     def change(self,
@@ -522,4 +605,4 @@ class HighlightedTextbox(FormComponent):
             concurrency_id: If set, this is the id of the concurrency group. Events with the same concurrency_id will be limited by the lowest set concurrency_limit.
             show_api: whether to show this event in the "view API" page of the Gradio app, or in the ".view_api()" method of the Gradio clients. Unlike setting api_name to False, setting show_api to False will still allow downstream apps to use this event. If fn is None, show_api will automatically be set to False.
         """
-        ... 
+        ...

src/backend/gradio_highlightedtextbox/templates/component/style.css

@@ -1 +1 @@
-.block.svelte-1t38q2d{position:relative;margin:0;box-shadow:var(--block-shadow);border-width:var(--block-border-width);border-color:var(--block-border-color);border-radius:var(--block-radius);background:var(--block-background-fill);width:100%;line-height:var(--line-sm)}.block.border_focus.svelte-1t38q2d{border-color:var(--color-accent)}.padded.svelte-1t38q2d{padding:var(--block-padding)}.hidden.svelte-1t38q2d{display:none}.hide-container.svelte-1t38q2d{margin:0;box-shadow:none;--block-border-width:0;background:transparent;padding:0;overflow:visible}div.svelte-1hnfib2{margin-bottom:var(--spacing-lg);color:var(--block-info-text-color);font-weight:var(--block-info-text-weight);font-size:var(--block-info-text-size);line-height:var(--line-sm)}span.has-info.svelte-22c38v{margin-bottom:var(--spacing-xs)}span.svelte-22c38v:not(.has-info){margin-bottom:var(--spacing-lg)}span.svelte-22c38v{display:inline-block;position:relative;z-index:var(--layer-4);border:solid var(--block-title-border-width) var(--block-title-border-color);border-radius:var(--block-title-radius);background:var(--block-title-background-fill);padding:var(--block-title-padding);color:var(--block-title-text-color);font-weight:var(--block-title-text-weight);font-size:var(--block-title-text-size);line-height:var(--line-sm)}.hide.svelte-22c38v{margin:0;height:0}label.svelte-9gxdi0{display:inline-flex;align-items:center;z-index:var(--layer-2);box-shadow:var(--block-label-shadow);border:var(--block-label-border-width) solid var(--border-color-primary);border-top:none;border-left:none;border-radius:var(--block-label-radius);background:var(--block-label-background-fill);padding:var(--block-label-padding);pointer-events:none;color:var(--block-label-text-color);font-weight:var(--block-label-text-weight);font-size:var(--block-label-text-size);line-height:var(--line-sm)}.gr-group label.svelte-9gxdi0{border-top-left-radius:0}label.float.svelte-9gxdi0{position:absolute;top:var(--block-label-margin);left:var(--block-label-margin)}label.svelte-9gxdi0:not(.float){position:static;margin-top:var(--block-label-margin);margin-left:var(--block-label-margin)}.hide.svelte-9gxdi0{height:0}span.svelte-9gxdi0{opacity:.8;margin-right:var(--size-2);width:calc(var(--block-label-text-size) - 1px);height:calc(var(--block-label-text-size) - 1px)}.hide-label.svelte-9gxdi0{box-shadow:none;border-width:0;background:transparent;overflow:visible}button.svelte-lpi64a{display:flex;justify-content:center;align-items:center;gap:1px;z-index:var(--layer-2);border-radius:var(--radius-sm);color:var(--block-label-text-color);border:1px solid transparent}button[disabled].svelte-lpi64a{opacity:.5;box-shadow:none}button[disabled].svelte-lpi64a:hover{cursor:not-allowed}.padded.svelte-lpi64a{padding:2px;background:var(--bg-color);box-shadow:var(--shadow-drop);border:1px solid var(--button-secondary-border-color)}button.svelte-lpi64a:hover,button.highlight.svelte-lpi64a{cursor:pointer;color:var(--color-accent)}.padded.svelte-lpi64a:hover{border:2px solid var(--button-secondary-border-color-hover);padding:1px;color:var(--block-label-text-color)}span.svelte-lpi64a{padding:0 1px;font-size:10px}div.svelte-lpi64a{padding:2px;display:flex;align-items:flex-end}.small.svelte-lpi64a{width:14px;height:14px}.large.svelte-lpi64a{width:22px;height:22px}.pending.svelte-lpi64a{animation:svelte-lpi64a-flash .5s infinite}@keyframes svelte-lpi64a-flash{0%{opacity:.5}50%{opacity:1}to{opacity:.5}}.transparent.svelte-lpi64a{background:transparent;border:none;box-shadow:none}.empty.svelte-3w3rth{display:flex;justify-content:center;align-items:center;margin-top:calc(0px - var(--size-6));height:var(--size-full)}.icon.svelte-3w3rth{opacity:.5;height:var(--size-5);color:var(--body-text-color)}.small.svelte-3w3rth{min-height:calc(var(--size-32) - 20px)}.large.svelte-3w3rth{min-height:calc(var(--size-64) - 20px)}.unpadded_box.svelte-3w3rth{margin-top:0}.small_parent.svelte-3w3rth{min-height:100%!important}.dropdown-arrow.svelte-145leq6{fill:currentColor}.wrap.svelte-kzcjhc{display:flex;flex-direction:column;justify-content:center;align-items:center;min-height:var(--size-60);color:var(--block-label-text-color);line-height:var(--line-md);height:100%;padding-top:var(--size-3)}.or.svelte-kzcjhc{color:var(--body-text-color-subdued);display:flex}.icon-wrap.svelte-kzcjhc{width:30px;margin-bottom:var(--spacing-lg)}@media (--screen-md){.wrap.svelte-kzcjhc{font-size:var(--text-lg)}}.hovered.svelte-kzcjhc{color:var(--color-accent)}div.svelte-ipfyu7{border-top:1px solid transparent;display:flex;max-height:100%;justify-content:center;gap:var(--spacing-sm);height:auto;align-items:flex-end;padding-bottom:var(--spacing-xl);color:var(--block-label-text-color);flex-shrink:0;width:95%}.show_border.svelte-ipfyu7{border-top:1px solid var(--block-border-color);margin-top:var(--spacing-xxl);box-shadow:var(--shadow-drop)}.source-selection.svelte-1jp3vgd{display:flex;align-items:center;justify-content:center;border-top:1px solid var(--border-color-primary);width:95%;bottom:0;left:0;right:0;margin-left:auto;margin-right:auto}.icon.svelte-1jp3vgd{width:22px;height:22px;margin:var(--spacing-lg) var(--spacing-xs);padding:var(--spacing-xs);color:var(--neutral-400);border-radius:var(--radius-md)}.selected.svelte-1jp3vgd{color:var(--color-accent)}.icon.svelte-1jp3vgd:hover,.icon.svelte-1jp3vgd:focus{color:var(--color-accent)}label.svelte-1u11ied{display:block;width:100%}button.svelte-1u11ied{display:flex;position:absolute;top:var(--block-label-margin);right:var(--block-label-margin);align-items:center;box-shadow:var(--shadow-drop);border:1px solid var(--color-border-primary);border-top:none;border-right:none;border-radius:var(--block-label-right-radius);background:var(--block-label-background-fill);padding:5px;width:22px;height:22px;overflow:hidden;color:var(--block-label-color);font:var(--font-sans);font-size:var(--button-small-text-size)}.container.svelte-1u11ied{display:flex;flex-direction:column;gap:var(--spacing-sm);padding:var(--block-padding)}.category-legend.svelte-1u11ied{display:flex;flex-wrap:wrap;gap:var(--spacing-sm);color:#000;margin-bottom:var(--spacing-sm)}.category-label.svelte-1u11ied{border-radius:var(--radius-xs);padding-right:var(--size-2);padding-left:var(--size-2);font-weight:var(--weight-semibold)}.legend-description.svelte-1u11ied{background-color:transparent;color:var(--block-title-text-color);padding-left:0;border-radius:var(--radius-xs);font-weight:var(--input-text-weight)}.textfield.svelte-1u11ied{box-sizing:border-box;outline:none!important;box-shadow:var(--input-shadow);padding:var(--input-padding);border-radius:var(--radius-md);background:var(--input-background-fill);background-color:transparent;font-weight:var(--input-text-weight);font-size:var(--input-text-size);width:100%;line-height:var(--line-sm);word-break:break-word;border:var(--input-border-width) solid var(--input-border-color);cursor:text}.textfield.svelte-1u11ied:focus{box-shadow:var(--input-shadow-focus);border-color:var(--input-border-color-focus)}mark{border-radius:3px}svg.svelte-43sxxs.svelte-43sxxs{width:var(--size-20);height:var(--size-20)}svg.svelte-43sxxs path.svelte-43sxxs{fill:var(--loader-color)}div.svelte-43sxxs.svelte-43sxxs{z-index:var(--layer-2)}.margin.svelte-43sxxs.svelte-43sxxs{margin:var(--size-4)}.wrap.svelte-1txqlrd.svelte-1txqlrd{display:flex;flex-direction:column;justify-content:center;align-items:center;z-index:var(--layer-top);transition:opacity .1s ease-in-out;border-radius:var(--block-radius);background:var(--block-background-fill);padding:0 var(--size-6);max-height:var(--size-screen-h);overflow:hidden;pointer-events:none}.wrap.center.svelte-1txqlrd.svelte-1txqlrd{top:0;right:0;left:0}.wrap.default.svelte-1txqlrd.svelte-1txqlrd{top:0;right:0;bottom:0;left:0}.hide.svelte-1txqlrd.svelte-1txqlrd{opacity:0;pointer-events:none}.generating.svelte-1txqlrd.svelte-1txqlrd{animation:svelte-1txqlrd-pulse 2s cubic-bezier(.4,0,.6,1) infinite;border:2px solid var(--color-accent);background:transparent}.translucent.svelte-1txqlrd.svelte-1txqlrd{background:none}@keyframes svelte-1txqlrd-pulse{0%,to{opacity:1}50%{opacity:.5}}.loading.svelte-1txqlrd.svelte-1txqlrd{z-index:var(--layer-2);color:var(--body-text-color)}.eta-bar.svelte-1txqlrd.svelte-1txqlrd{position:absolute;top:0;right:0;bottom:0;left:0;transform-origin:left;opacity:.8;z-index:var(--layer-1);transition:10ms;background:var(--background-fill-secondary)}.progress-bar-wrap.svelte-1txqlrd.svelte-1txqlrd{border:1px solid var(--border-color-primary);background:var(--background-fill-primary);width:55.5%;height:var(--size-4)}.progress-bar.svelte-1txqlrd.svelte-1txqlrd{transform-origin:left;background-color:var(--loader-color);width:var(--size-full);height:var(--size-full)}.progress-level.svelte-1txqlrd.svelte-1txqlrd{display:flex;flex-direction:column;align-items:center;gap:1;z-index:var(--layer-2);width:var(--size-full)}.progress-level-inner.svelte-1txqlrd.svelte-1txqlrd{margin:var(--size-2) auto;color:var(--body-text-color);font-size:var(--text-sm);font-family:var(--font-mono)}.meta-text.svelte-1txqlrd.svelte-1txqlrd{position:absolute;top:0;right:0;z-index:var(--layer-2);padding:var(--size-1) var(--size-2);font-size:var(--text-sm);font-family:var(--font-mono)}.meta-text-center.svelte-1txqlrd.svelte-1txqlrd{display:flex;position:absolute;top:0;right:0;justify-content:center;align-items:center;transform:translateY(var(--size-6));z-index:var(--layer-2);padding:var(--size-1) var(--size-2);font-size:var(--text-sm);font-family:var(--font-mono);text-align:center}.error.svelte-1txqlrd.svelte-1txqlrd{box-shadow:var(--shadow-drop);border:solid 1px var(--error-border-color);border-radius:var(--radius-full);background:var(--error-background-fill);padding-right:var(--size-4);padding-left:var(--size-4);color:var(--error-text-color);font-weight:var(--weight-semibold);font-size:var(--text-lg);line-height:var(--line-lg);font-family:var(--font)}.minimal.svelte-1txqlrd .progress-text.svelte-1txqlrd{background:var(--block-background-fill)}.border.svelte-1txqlrd.svelte-1txqlrd{border:1px solid var(--border-color-primary)}.toast-body.svelte-solcu7{display:flex;position:relative;right:0;left:0;align-items:center;margin:var(--size-6) var(--size-4);margin:auto;border-radius:var(--container-radius);overflow:hidden;pointer-events:auto}.toast-body.error.svelte-solcu7{border:1px solid var(--color-red-700);background:var(--color-red-50)}.dark .toast-body.error.svelte-solcu7{border:1px solid var(--color-red-500);background-color:var(--color-grey-950)}.toast-body.warning.svelte-solcu7{border:1px solid var(--color-yellow-700);background:var(--color-yellow-50)}.dark .toast-body.warning.svelte-solcu7{border:1px solid var(--color-yellow-500);background-color:var(--color-grey-950)}.toast-body.info.svelte-solcu7{border:1px solid var(--color-grey-700);background:var(--color-grey-50)}.dark .toast-body.info.svelte-solcu7{border:1px solid var(--color-grey-500);background-color:var(--color-grey-950)}.toast-title.svelte-solcu7{display:flex;align-items:center;font-weight:var(--weight-bold);font-size:var(--text-lg);line-height:var(--line-sm);text-transform:capitalize}.toast-title.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-title.error.svelte-solcu7{color:var(--color-red-50)}.toast-title.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-title.warning.svelte-solcu7{color:var(--color-yellow-50)}.toast-title.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-title.info.svelte-solcu7{color:var(--color-grey-50)}.toast-close.svelte-solcu7{margin:0 var(--size-3);border-radius:var(--size-3);padding:0px var(--size-1-5);font-size:var(--size-5);line-height:var(--size-5)}.toast-close.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-close.error.svelte-solcu7{color:var(--color-red-500)}.toast-close.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-close.warning.svelte-solcu7{color:var(--color-yellow-500)}.toast-close.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-close.info.svelte-solcu7{color:var(--color-grey-500)}.toast-text.svelte-solcu7{font-size:var(--text-lg)}.toast-text.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-text.error.svelte-solcu7{color:var(--color-red-50)}.toast-text.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-text.warning.svelte-solcu7{color:var(--color-yellow-50)}.toast-text.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-text.info.svelte-solcu7{color:var(--color-grey-50)}.toast-details.svelte-solcu7{margin:var(--size-3) var(--size-3) var(--size-3) 0;width:100%}.toast-icon.svelte-solcu7{display:flex;position:absolute;position:relative;flex-shrink:0;justify-content:center;align-items:center;margin:var(--size-2);border-radius:var(--radius-full);padding:var(--size-1);padding-left:calc(var(--size-1) - 1px);width:35px;height:35px}.toast-icon.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-icon.error.svelte-solcu7{color:var(--color-red-500)}.toast-icon.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-icon.warning.svelte-solcu7{color:var(--color-yellow-500)}.toast-icon.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-icon.info.svelte-solcu7{color:var(--color-grey-500)}@keyframes svelte-solcu7-countdown{0%{transform:scaleX(1)}to{transform:scaleX(0)}}.timer.svelte-solcu7{position:absolute;bottom:0;left:0;transform-origin:0 0;animation:svelte-solcu7-countdown 10s linear forwards;width:100%;height:var(--size-1)}.timer.error.svelte-solcu7{background:var(--color-red-700)}.dark .timer.error.svelte-solcu7{background:var(--color-red-500)}.timer.warning.svelte-solcu7{background:var(--color-yellow-700)}.dark .timer.warning.svelte-solcu7{background:var(--color-yellow-500)}.timer.info.svelte-solcu7{background:var(--color-grey-700)}.dark .timer.info.svelte-solcu7{background:var(--color-grey-500)}.toast-wrap.svelte-gatr8h{display:flex;position:fixed;top:var(--size-4);right:var(--size-4);flex-direction:column;align-items:end;gap:var(--size-2);z-index:var(--layer-top);width:calc(100% - var(--size-8))}@media (--screen-sm){.toast-wrap.svelte-gatr8h{width:calc(var(--size-96) + var(--size-10))}}
+span.has-info.svelte-deja93{margin-bottom:var(--spacing-xs)}span.svelte-deja93:not(.has-info){margin-bottom:var(--spacing-lg)}span.svelte-deja93{display:inline-block;position:relative;z-index:var(--layer-4);border:solid var(--block-title-border-width) var(--block-title-border-color);border-radius:var(--block-title-radius);background:var(--block-title-background-fill);padding:var(--block-title-padding);color:var(--block-title-text-color);font-weight:var(--block-title-text-weight);font-size:var(--block-title-text-size);line-height:var(--line-sm)}.hide.svelte-deja93{margin:0;height:0}.category-legend.svelte-deja93{display:flex;flex-wrap:wrap;gap:var(--spacing-sm);color:#000}.category-label.svelte-deja93{border-radius:var(--radius-xs);padding-right:var(--size-2);padding-left:var(--size-2);font-weight:var(--weight-semibold)}.title-container.svelte-deja93{display:flex}.legend-separator.svelte-deja93{margin:0 var(--spacing-md) 0 var(--spacing-md)}.title-with-highlights-info.svelte-deja93{margin-bottom:var(--spacing-xs);color:var(--block-info-text-color);font-weight:var(--block-info-text-weight);font-size:var(--block-info-text-size);line-height:var(--line-sm)}.dropdown-arrow.svelte-145leq6{fill:currentColor}label.svelte-14ssfqr{display:block;width:100%}button.svelte-14ssfqr{display:flex;position:absolute;top:var(--block-label-margin);right:var(--block-label-margin);align-items:center;box-shadow:var(--shadow-drop);border:1px solid var(--color-border-primary);border-top:none;border-right:none;border-radius:var(--block-label-right-radius);background:var(--block-label-background-fill);padding:5px;width:22px;height:22px;overflow:hidden;color:var(--block-label-color);font:var(--font-sans);font-size:var(--button-small-text-size)}.container.svelte-14ssfqr{display:flex;flex-direction:column;gap:var(--spacing-sm)}.textfield.svelte-14ssfqr{box-sizing:border-box;outline:none!important;box-shadow:var(--input-shadow);padding:var(--input-padding);border-radius:var(--radius-md);background:var(--input-background-fill);background-color:transparent;font-weight:var(--input-text-weight);font-size:var(--input-text-size);width:100%;line-height:var(--line-sm);word-break:break-word;border:var(--input-border-width) solid var(--input-border-color);cursor:text}.textfield.svelte-14ssfqr:focus{box-shadow:var(--input-shadow-focus);border-color:var(--input-border-color-focus)}mark{border-radius:3px}.block.svelte-1t38q2d{position:relative;margin:0;box-shadow:var(--block-shadow);border-width:var(--block-border-width);border-color:var(--block-border-color);border-radius:var(--block-radius);background:var(--block-background-fill);width:100%;line-height:var(--line-sm)}.block.border_focus.svelte-1t38q2d{border-color:var(--color-accent)}.padded.svelte-1t38q2d{padding:var(--block-padding)}.hidden.svelte-1t38q2d{display:none}.hide-container.svelte-1t38q2d{margin:0;box-shadow:none;--block-border-width:0;background:transparent;padding:0;overflow:visible}div.svelte-1hnfib2{margin-bottom:var(--spacing-lg);color:var(--block-info-text-color);font-weight:var(--block-info-text-weight);font-size:var(--block-info-text-size);line-height:var(--line-sm)}span.has-info.svelte-22c38v{margin-bottom:var(--spacing-xs)}span.svelte-22c38v:not(.has-info){margin-bottom:var(--spacing-lg)}span.svelte-22c38v{display:inline-block;position:relative;z-index:var(--layer-4);border:solid var(--block-title-border-width) var(--block-title-border-color);border-radius:var(--block-title-radius);background:var(--block-title-background-fill);padding:var(--block-title-padding);color:var(--block-title-text-color);font-weight:var(--block-title-text-weight);font-size:var(--block-title-text-size);line-height:var(--line-sm)}.hide.svelte-22c38v{margin:0;height:0}label.svelte-9gxdi0{display:inline-flex;align-items:center;z-index:var(--layer-2);box-shadow:var(--block-label-shadow);border:var(--block-label-border-width) solid var(--border-color-primary);border-top:none;border-left:none;border-radius:var(--block-label-radius);background:var(--block-label-background-fill);padding:var(--block-label-padding);pointer-events:none;color:var(--block-label-text-color);font-weight:var(--block-label-text-weight);font-size:var(--block-label-text-size);line-height:var(--line-sm)}.gr-group label.svelte-9gxdi0{border-top-left-radius:0}label.float.svelte-9gxdi0{position:absolute;top:var(--block-label-margin);left:var(--block-label-margin)}label.svelte-9gxdi0:not(.float){position:static;margin-top:var(--block-label-margin);margin-left:var(--block-label-margin)}.hide.svelte-9gxdi0{height:0}span.svelte-9gxdi0{opacity:.8;margin-right:var(--size-2);width:calc(var(--block-label-text-size) - 1px);height:calc(var(--block-label-text-size) - 1px)}.hide-label.svelte-9gxdi0{box-shadow:none;border-width:0;background:transparent;overflow:visible}button.svelte-lpi64a{display:flex;justify-content:center;align-items:center;gap:1px;z-index:var(--layer-2);border-radius:var(--radius-sm);color:var(--block-label-text-color);border:1px solid transparent}button[disabled].svelte-lpi64a{opacity:.5;box-shadow:none}button[disabled].svelte-lpi64a:hover{cursor:not-allowed}.padded.svelte-lpi64a{padding:2px;background:var(--bg-color);box-shadow:var(--shadow-drop);border:1px solid var(--button-secondary-border-color)}button.svelte-lpi64a:hover,button.highlight.svelte-lpi64a{cursor:pointer;color:var(--color-accent)}.padded.svelte-lpi64a:hover{border:2px solid var(--button-secondary-border-color-hover);padding:1px;color:var(--block-label-text-color)}span.svelte-lpi64a{padding:0 1px;font-size:10px}div.svelte-lpi64a{padding:2px;display:flex;align-items:flex-end}.small.svelte-lpi64a{width:14px;height:14px}.large.svelte-lpi64a{width:22px;height:22px}.pending.svelte-lpi64a{animation:svelte-lpi64a-flash .5s infinite}@keyframes svelte-lpi64a-flash{0%{opacity:.5}50%{opacity:1}to{opacity:.5}}.transparent.svelte-lpi64a{background:transparent;border:none;box-shadow:none}.empty.svelte-3w3rth{display:flex;justify-content:center;align-items:center;margin-top:calc(0px - var(--size-6));height:var(--size-full)}.icon.svelte-3w3rth{opacity:.5;height:var(--size-5);color:var(--body-text-color)}.small.svelte-3w3rth{min-height:calc(var(--size-32) - 20px)}.large.svelte-3w3rth{min-height:calc(var(--size-64) - 20px)}.unpadded_box.svelte-3w3rth{margin-top:0}.small_parent.svelte-3w3rth{min-height:100%!important}.wrap.svelte-kzcjhc{display:flex;flex-direction:column;justify-content:center;align-items:center;min-height:var(--size-60);color:var(--block-label-text-color);line-height:var(--line-md);height:100%;padding-top:var(--size-3)}.or.svelte-kzcjhc{color:var(--body-text-color-subdued);display:flex}.icon-wrap.svelte-kzcjhc{width:30px;margin-bottom:var(--spacing-lg)}@media (--screen-md){.wrap.svelte-kzcjhc{font-size:var(--text-lg)}}.hovered.svelte-kzcjhc{color:var(--color-accent)}div.svelte-ipfyu7{border-top:1px solid transparent;display:flex;max-height:100%;justify-content:center;gap:var(--spacing-sm);height:auto;align-items:flex-end;padding-bottom:var(--spacing-xl);color:var(--block-label-text-color);flex-shrink:0;width:95%}.show_border.svelte-ipfyu7{border-top:1px solid var(--block-border-color);margin-top:var(--spacing-xxl);box-shadow:var(--shadow-drop)}.source-selection.svelte-1jp3vgd{display:flex;align-items:center;justify-content:center;border-top:1px solid var(--border-color-primary);width:95%;bottom:0;left:0;right:0;margin-left:auto;margin-right:auto}.icon.svelte-1jp3vgd{width:22px;height:22px;margin:var(--spacing-lg) var(--spacing-xs);padding:var(--spacing-xs);color:var(--neutral-400);border-radius:var(--radius-md)}.selected.svelte-1jp3vgd{color:var(--color-accent)}.icon.svelte-1jp3vgd:hover,.icon.svelte-1jp3vgd:focus{color:var(--color-accent)}svg.svelte-43sxxs.svelte-43sxxs{width:var(--size-20);height:var(--size-20)}svg.svelte-43sxxs path.svelte-43sxxs{fill:var(--loader-color)}div.svelte-43sxxs.svelte-43sxxs{z-index:var(--layer-2)}.margin.svelte-43sxxs.svelte-43sxxs{margin:var(--size-4)}.wrap.svelte-1txqlrd.svelte-1txqlrd{display:flex;flex-direction:column;justify-content:center;align-items:center;z-index:var(--layer-top);transition:opacity .1s ease-in-out;border-radius:var(--block-radius);background:var(--block-background-fill);padding:0 var(--size-6);max-height:var(--size-screen-h);overflow:hidden;pointer-events:none}.wrap.center.svelte-1txqlrd.svelte-1txqlrd{top:0;right:0;left:0}.wrap.default.svelte-1txqlrd.svelte-1txqlrd{top:0;right:0;bottom:0;left:0}.hide.svelte-1txqlrd.svelte-1txqlrd{opacity:0;pointer-events:none}.generating.svelte-1txqlrd.svelte-1txqlrd{animation:svelte-1txqlrd-pulse 2s cubic-bezier(.4,0,.6,1) infinite;border:2px solid var(--color-accent);background:transparent}.translucent.svelte-1txqlrd.svelte-1txqlrd{background:none}@keyframes svelte-1txqlrd-pulse{0%,to{opacity:1}50%{opacity:.5}}.loading.svelte-1txqlrd.svelte-1txqlrd{z-index:var(--layer-2);color:var(--body-text-color)}.eta-bar.svelte-1txqlrd.svelte-1txqlrd{position:absolute;top:0;right:0;bottom:0;left:0;transform-origin:left;opacity:.8;z-index:var(--layer-1);transition:10ms;background:var(--background-fill-secondary)}.progress-bar-wrap.svelte-1txqlrd.svelte-1txqlrd{border:1px solid var(--border-color-primary);background:var(--background-fill-primary);width:55.5%;height:var(--size-4)}.progress-bar.svelte-1txqlrd.svelte-1txqlrd{transform-origin:left;background-color:var(--loader-color);width:var(--size-full);height:var(--size-full)}.progress-level.svelte-1txqlrd.svelte-1txqlrd{display:flex;flex-direction:column;align-items:center;gap:1;z-index:var(--layer-2);width:var(--size-full)}.progress-level-inner.svelte-1txqlrd.svelte-1txqlrd{margin:var(--size-2) auto;color:var(--body-text-color);font-size:var(--text-sm);font-family:var(--font-mono)}.meta-text.svelte-1txqlrd.svelte-1txqlrd{position:absolute;top:0;right:0;z-index:var(--layer-2);padding:var(--size-1) var(--size-2);font-size:var(--text-sm);font-family:var(--font-mono)}.meta-text-center.svelte-1txqlrd.svelte-1txqlrd{display:flex;position:absolute;top:0;right:0;justify-content:center;align-items:center;transform:translateY(var(--size-6));z-index:var(--layer-2);padding:var(--size-1) var(--size-2);font-size:var(--text-sm);font-family:var(--font-mono);text-align:center}.error.svelte-1txqlrd.svelte-1txqlrd{box-shadow:var(--shadow-drop);border:solid 1px var(--error-border-color);border-radius:var(--radius-full);background:var(--error-background-fill);padding-right:var(--size-4);padding-left:var(--size-4);color:var(--error-text-color);font-weight:var(--weight-semibold);font-size:var(--text-lg);line-height:var(--line-lg);font-family:var(--font)}.minimal.svelte-1txqlrd .progress-text.svelte-1txqlrd{background:var(--block-background-fill)}.border.svelte-1txqlrd.svelte-1txqlrd{border:1px solid var(--border-color-primary)}.toast-body.svelte-solcu7{display:flex;position:relative;right:0;left:0;align-items:center;margin:var(--size-6) var(--size-4);margin:auto;border-radius:var(--container-radius);overflow:hidden;pointer-events:auto}.toast-body.error.svelte-solcu7{border:1px solid var(--color-red-700);background:var(--color-red-50)}.dark .toast-body.error.svelte-solcu7{border:1px solid var(--color-red-500);background-color:var(--color-grey-950)}.toast-body.warning.svelte-solcu7{border:1px solid var(--color-yellow-700);background:var(--color-yellow-50)}.dark .toast-body.warning.svelte-solcu7{border:1px solid var(--color-yellow-500);background-color:var(--color-grey-950)}.toast-body.info.svelte-solcu7{border:1px solid var(--color-grey-700);background:var(--color-grey-50)}.dark .toast-body.info.svelte-solcu7{border:1px solid var(--color-grey-500);background-color:var(--color-grey-950)}.toast-title.svelte-solcu7{display:flex;align-items:center;font-weight:var(--weight-bold);font-size:var(--text-lg);line-height:var(--line-sm);text-transform:capitalize}.toast-title.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-title.error.svelte-solcu7{color:var(--color-red-50)}.toast-title.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-title.warning.svelte-solcu7{color:var(--color-yellow-50)}.toast-title.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-title.info.svelte-solcu7{color:var(--color-grey-50)}.toast-close.svelte-solcu7{margin:0 var(--size-3);border-radius:var(--size-3);padding:0px var(--size-1-5);font-size:var(--size-5);line-height:var(--size-5)}.toast-close.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-close.error.svelte-solcu7{color:var(--color-red-500)}.toast-close.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-close.warning.svelte-solcu7{color:var(--color-yellow-500)}.toast-close.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-close.info.svelte-solcu7{color:var(--color-grey-500)}.toast-text.svelte-solcu7{font-size:var(--text-lg)}.toast-text.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-text.error.svelte-solcu7{color:var(--color-red-50)}.toast-text.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-text.warning.svelte-solcu7{color:var(--color-yellow-50)}.toast-text.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-text.info.svelte-solcu7{color:var(--color-grey-50)}.toast-details.svelte-solcu7{margin:var(--size-3) var(--size-3) var(--size-3) 0;width:100%}.toast-icon.svelte-solcu7{display:flex;position:absolute;position:relative;flex-shrink:0;justify-content:center;align-items:center;margin:var(--size-2);border-radius:var(--radius-full);padding:var(--size-1);padding-left:calc(var(--size-1) - 1px);width:35px;height:35px}.toast-icon.error.svelte-solcu7{color:var(--color-red-700)}.dark .toast-icon.error.svelte-solcu7{color:var(--color-red-500)}.toast-icon.warning.svelte-solcu7{color:var(--color-yellow-700)}.dark .toast-icon.warning.svelte-solcu7{color:var(--color-yellow-500)}.toast-icon.info.svelte-solcu7{color:var(--color-grey-700)}.dark .toast-icon.info.svelte-solcu7{color:var(--color-grey-500)}@keyframes svelte-solcu7-countdown{0%{transform:scaleX(1)}to{transform:scaleX(0)}}.timer.svelte-solcu7{position:absolute;bottom:0;left:0;transform-origin:0 0;animation:svelte-solcu7-countdown 10s linear forwards;width:100%;height:var(--size-1)}.timer.error.svelte-solcu7{background:var(--color-red-700)}.dark .timer.error.svelte-solcu7{background:var(--color-red-500)}.timer.warning.svelte-solcu7{background:var(--color-yellow-700)}.dark .timer.warning.svelte-solcu7{background:var(--color-yellow-500)}.timer.info.svelte-solcu7{background:var(--color-grey-700)}.dark .timer.info.svelte-solcu7{background:var(--color-grey-500)}.toast-wrap.svelte-gatr8h{display:flex;position:fixed;top:var(--size-4);right:var(--size-4);flex-direction:column;align-items:end;gap:var(--size-2);z-index:var(--layer-top);width:calc(100% - var(--size-8))}@media (--screen-sm){.toast-wrap.svelte-gatr8h{width:calc(var(--size-96) + var(--size-10))}}

src/demo/app.py

@@ -3,7 +3,10 @@ from gradio_highlightedtextbox import HighlightedTextbox
 
 
 def convert_tagged_text_to_highlighted_text(
-    tagged_text: str, tag_id: str, tag_open: str, tag_close: str
+    tagged_text: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
 ) -> list[tuple[str, str | None]]:
     return HighlightedTextbox.tagged_text_to_tuples(
         tagged_text, tag_id, tag_open, tag_close
@@ -12,64 +15,77 @@ def convert_tagged_text_to_highlighted_text(
 
 def convert_highlighted_text_to_tagged_text(
     highlighted_text: dict[str, str | list[tuple[str, str | None]]],
-    tag_id: str,
-    tag_open: str,
-    tag_close: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
 ) -> str:
     return HighlightedTextbox.tuples_to_tagged_text(
         highlighted_text["data"], tag_id, tag_open, tag_close
     )
 
 
-initial_text = "It is not something to be ashamed of: it is no different from the <h>personal fears</h> and <h>dislikes</h> of other things that <h>very many people</h> have."
+initial_text = "It is not something to be ashamed of: it is no different from the <d>personal fears</d> and <tm>dislikes</tm> of other things that <t>manny peopl</t> have."
 
 with gr.Blocks() as demo:
-    tag_id = gr.Textbox(
-        "Potential issue",
-        label="Tag ID",
-        show_label=True,
-        info="Insert a tag ID to use in the highlighted textbox.",
-    )
-    tag_open = gr.Textbox(
-        "<h>",
-        label="Tag open",
-        show_label=True,
-        info="Insert a tag to mark the beginning of a highlighted section.",
-    )
-    tag_close = gr.Textbox(
-        "</h>",
-        label="Tag close",
-        show_label=True,
-        info="Insert a tag to mark the end of a highlighted section.",
-    )
+    gr.Markdown("### Parameters to control the highlighted textbox:")
+    with gr.Row():
+        tag_id = gr.Dropdown(
+            choices=["Typo", "Terminology", "Disfluency"],
+            value=["Typo", "Terminology", "Disfluency"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag ID",
+            show_label=True,
+            info="Insert one or more tag IDs to use in the highlighted textbox.",
+        )
+        tag_open = gr.Dropdown(
+            choices=["<t>", "<tm>", "<d>"],
+            value=["<t>", "<tm>", "<d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag open",
+            show_label=True,
+            info="Insert one or more tags to mark the beginning of a highlighted section.",
+        )
+        tag_close = gr.Dropdown(
+            choices=["</t>", "</tm>", "</d>"],
+            value=["</t>", "</tm>", "</d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag close",
+            show_label=True,
+            info="Insert one or more tags to mark the end of a highlighted section.",
+        )
+    gr.Markdown("### Example tagged to highlight:")
     with gr.Row():
         tagged_t2h = gr.Textbox(
             initial_text,
             interactive=True,
-            label="Input",
+            label="Tagged Input",
             show_label=True,
-            info="Insert a text with <h>...</h> tags to mark spans that will be highlighted.",
+            info="Tagged text using the format above to mark spans that will be highlighted.",
         )
         high_t2h = HighlightedTextbox(
             convert_tagged_text_to_highlighted_text(
                 tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
             ),
-            interactive=True,
-            label="Output",
-            info="Highlighted textbox.",
+            interactive=False,
+            label="Highlighted Output",
+            info="Highlighted textbox intialized from the tagged input.",
             show_legend=True,
             show_label=True,
             legend_label="Legend:",
             show_legend_label=True,
         )
+    gr.Markdown("### Example highlight to tagged:")
     with gr.Row():
         high_h2t = HighlightedTextbox(
             convert_tagged_text_to_highlighted_text(
-                tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
+                initial_text, tag_id.value, tag_open.value, tag_close.value
             ),
             interactive=True,
-            label="Input",
-            info="The following text will be marked by spans according to its highlights.",
+            label="Highlighted Input",
+            info="Highlighted textbox using the format above to mark spans that will be highlighted.",
             show_legend=True,
             show_label=True,
             legend_label="Legend:",
@@ -77,28 +93,24 @@ with gr.Blocks() as demo:
         )
         tagged_h2t = gr.Textbox(
             initial_text,
-            interactive=True,
-            label="Output",
+            interactive=False,
+            label="Tagged Output",
+            info="Tagged text intialized from the highlighted textbox.",
             show_label=True,
         )
 
     # Functions
 
-    tagged_t2h.change(
+    tagged_t2h.input(
         fn=convert_tagged_text_to_highlighted_text,
         inputs=[tagged_t2h, tag_id, tag_open, tag_close],
         outputs=high_t2h,
     )
-    high_t2h.change(
-        fn=lambda x: x["data"],
-        inputs=high_t2h,
-        outputs=high_h2t,
-    )
-    high_h2t.change(
+    high_h2t.input(
         fn=convert_highlighted_text_to_tagged_text,
         inputs=[high_h2t, tag_id, tag_open, tag_close],
         outputs=tagged_h2t,
     )
 
-
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()

src/demo/css.css

@@ -0,0 +1,157 @@
+html {
+	font-family: Inter;
+	font-size: 16px;
+	font-weight: 400;
+	line-height: 1.5;
+	-webkit-text-size-adjust: 100%;
+	background: #fff;
+	color: #323232;
+	-webkit-font-smoothing: antialiased;
+	-moz-osx-font-smoothing: grayscale;
+	text-rendering: optimizeLegibility;
+}
+
+:root {
+	--space: 1;
+	--vspace: calc(var(--space) * 1rem);
+	--vspace-0: calc(3 * var(--space) * 1rem);
+	--vspace-1: calc(2 * var(--space) * 1rem);
+	--vspace-2: calc(1.5 * var(--space) * 1rem);
+	--vspace-3: calc(0.5 * var(--space) * 1rem);
+}
+
+.app {
+	max-width: 748px !important;
+}
+
+.prose p {
+	margin: var(--vspace) 0;
+	line-height: var(--vspace * 2);
+	font-size: 1rem;
+}
+
+code {
+	font-family: "Inconsolata", sans-serif;
+	font-size: 16px;
+}
+
+h1,
+h1 code {
+	font-weight: 400;
+	line-height: calc(2.5 / var(--space) * var(--vspace));
+}
+
+h1 code {
+	background: none;
+	border: none;
+	letter-spacing: 0.05em;
+	padding-bottom: 5px;
+	position: relative;
+	padding: 0;
+}
+
+h2 {
+	margin: var(--vspace-1) 0 var(--vspace-2) 0;
+	line-height: 1em;
+}
+
+h3,
+h3 code {
+	margin: var(--vspace-1) 0 var(--vspace-2) 0;
+	line-height: 1em;
+}
+
+h4,
+h5,
+h6 {
+	margin: var(--vspace-3) 0 var(--vspace-3) 0;
+	line-height: var(--vspace);
+}
+
+.bigtitle,
+h1,
+h1 code {
+	font-size: calc(8px * 4.5);
+	word-break: break-word;
+}
+
+.title,
+h2,
+h2 code {
+	font-size: calc(8px * 3.375);
+	font-weight: lighter;
+	word-break: break-word;
+	border: none;
+	background: none;
+}
+
+.subheading1,
+h3,
+h3 code {
+	font-size: calc(8px * 1.8);
+	font-weight: 600;
+	border: none;
+	background: none;
+	letter-spacing: 0.1em;
+	text-transform: uppercase;
+}
+
+h2 code {
+	padding: 0;
+	position: relative;
+	letter-spacing: 0.05em;
+}
+
+blockquote {
+	font-size: calc(8px * 1.1667);
+	font-style: italic;
+	line-height: calc(1.1667 * var(--vspace));
+	margin: var(--vspace-2) var(--vspace-2);
+}
+
+.subheading2,
+h4 {
+	font-size: calc(8px * 1.4292);
+	text-transform: uppercase;
+	font-weight: 600;
+}
+
+.subheading3,
+h5 {
+	font-size: calc(8px * 1.2917);
+	line-height: calc(1.2917 * var(--vspace));
+
+	font-weight: lighter;
+	text-transform: uppercase;
+	letter-spacing: 0.15em;
+}
+
+h6 {
+	font-size: calc(8px * 1.1667);
+	font-size: 1.1667em;
+	font-weight: normal;
+	font-style: italic;
+	font-family: "le-monde-livre-classic-byol", serif !important;
+	letter-spacing: 0px !important;
+}
+
+#start .md > *:first-child {
+	margin-top: 0;
+}
+
+h2 + h3 {
+	margin-top: 0;
+}
+
+.md hr {
+	border: none;
+	border-top: 1px solid var(--block-border-color);
+	margin: var(--vspace-2) 0 var(--vspace-2) 0;
+}
+.prose ul {
+	margin: var(--vspace-2) 0 var(--vspace-1) 0;
+}
+
+.gap {
+	gap: 0;
+}

src/demo/space.py

@@ -0,0 +1,237 @@
+
+import gradio as gr
+from app import demo as app
+import os
+
+_docs = {'HighlightedTextbox': {'description': 'Creates a textarea for user to enter string input or display string output where some\nelements are highlighted.\n    (1) "text" whose value is the complete text, and\n    (2) "highlights", which is a list of dictionaries, each of which have the keys:\n        "highlight_type" (consisting of the highlight label),\n        "start" (the character index where the label starts), and\n        "end" (the character index where the label ends).\n    Highlights should not overlap.', 'members': {'__init__': {'value': {'type': 'str | Callable | None', 'default': '""', 'description': 'default text to provide in textbox. If callable, the function will be called whenever the app loads to set the initial value of the component.'}, 'color_map': {'type': 'dict[str, str] | None', 'default': 'None', 'description': 'dictionary mapping labels to colors.'}, 'show_legend': {'type': 'bool', 'default': 'False', 'description': 'if True, will display legend.'}, 'show_legend_label': {'type': 'bool', 'default': 'False', 'description': 'if True, will display legend label.'}, 'legend_label': {'type': 'str', 'default': '""', 'description': 'label to display above legend.'}, 'combine_adjacent': {'type': 'bool', 'default': 'False', 'description': 'if True, will combine adjacent spans with the same label.'}, 'adjacent_separator': {'type': 'str', 'default': '""', 'description': 'separator to use when combining adjacent spans.'}, 'label': {'type': 'str | None', 'default': 'None', 'description': 'component name in interface.'}, 'info': {'type': 'str | None', 'default': 'None', 'description': None}, 'every': {'type': 'float | None', 'default': 'None', 'description': "If `value` is a callable, run the function 'every' number of seconds while the client connection is open. Has no effect otherwise. Queue must be enabled. The event can be accessed (e.g. to cancel it) via this component's .load_event attribute."}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': 'if True, will display label.'}, 'container': {'type': 'bool', 'default': 'True', 'description': 'If True, will place the component in a container - providing some extra padding around the border.'}, 'scale': {'type': 'int | None', 'default': 'None', 'description': 'relative width compared to adjacent Components in a Row. For example, if Component A has scale=2, and Component B has scale=1, A will be twice as wide as B. Should be an integer.'}, 'min_width': {'type': 'int', 'default': '160', 'description': 'minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.'}, 'visible': {'type': 'bool', 'default': 'True', 'description': 'If False, component will be hidden.'}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': 'An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'autofocus': {'type': 'bool', 'default': 'False', 'description': None}, 'autoscroll': {'type': 'bool', 'default': 'True', 'description': 'If True, will automatically scroll to the bottom of the textbox when the value changes, unless the user scrolls up. If False, will not scroll to the bottom of the textbox when the value changes.'}, 'interactive': {'type': 'bool', 'default': 'True', 'description': 'if True, will be rendered as an editable textbox; if False, editing will be disabled. If not provided, this is inferred based on whether the component is used as an input or output.'}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': 'An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'render': {'type': 'bool', 'default': 'True', 'description': 'If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.'}, 'show_copy_button': {'type': 'bool', 'default': 'False', 'description': 'If True, includes a copy button to copy the text in the textbox. Only applies if show_label is True.'}}, 'postprocess': {'y': {'type': 'list[tuple[str, str | None]] | dict | None', 'description': 'List of (word, category) tuples, or a dictionary of two keys: "text", and "highlights", which itself is'}, 'value': {'type': 'list[tuple[str, str | None]] | dict | None', 'description': 'List of (word, category) tuples, or a dictionary of two keys: "text", and "highlights", which itself is'}}, 'preprocess': {'return': {'type': 'dict', 'description': None}, 'value': None}}, 'events': {'change': {'type': None, 'default': None, 'description': 'Triggered when the value of the HighlightedTextbox changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See `.input()` for a listener that is only triggered by user input.'}, 'input': {'type': None, 'default': None, 'description': 'This listener is triggered when the user changes the value of the HighlightedTextbox.'}, 'select': {'type': None, 'default': None, 'description': 'Event listener for when the user selects or deselects the HighlightedTextbox. Uses event data gradio.SelectData to carry `value` referring to the label of the HighlightedTextbox, and `selected` to refer to state of the HighlightedTextbox. See EventData documentation on how to use this event data'}, 'submit': {'type': None, 'default': None, 'description': 'This listener is triggered when the user presses the Enter key while the HighlightedTextbox is focused.'}, 'focus': {'type': None, 'default': None, 'description': 'This listener is triggered when the HighlightedTextbox is focused.'}, 'blur': {'type': None, 'default': None, 'description': 'This listener is triggered when the HighlightedTextbox is unfocused/blurred.'}}}, '__meta__': {'additional_interfaces': {}, 'user_fn_refs': {'HighlightedTextbox': []}}}
+    
+abs_path = os.path.join(os.path.dirname(__file__), "css.css")
+
+with gr.Blocks(
+    css=abs_path,
+    theme=gr.themes.Default(
+        font_mono=[
+            gr.themes.GoogleFont("Inconsolata"),
+            "monospace",
+        ],
+    ),
+) as demo:
+    gr.Markdown(
+"""
+# `gradio_highlightedtextbox`
+
+<div style="display: flex; gap: 7px;">
+<a href="https://pypi.org/project/gradio_highlightedtextbox/" target="_blank"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/gradio_highlightedtextbox"></a>  <a href="https://huggingface.co/spaces/gsarti/gradio_highlightedtextbox/discussions" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/%F0%9F%A4%97%20Discuss-%23097EFF?style=flat&logoColor=black"></a>
+</div>
+
+Editable Gradio textarea supporting highlighting
+""", elem_classes=["md-custom"], header_links=True)
+    app.render()
+    gr.Markdown(
+"""
+## Installation
+
+```bash
+pip install gradio_highlightedtextbox
+```
+
+## Usage
+
+```python
+import gradio as gr
+from gradio_highlightedtextbox import HighlightedTextbox
+
+
+def convert_tagged_text_to_highlighted_text(
+    tagged_text: str,
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
+) -> list[tuple[str, str | None]]:
+    return HighlightedTextbox.tagged_text_to_tuples(
+        tagged_text, tag_id, tag_open, tag_close
+    )
+
+
+def convert_highlighted_text_to_tagged_text(
+    highlighted_text: dict[str, str | list[tuple[str, str | None]]],
+    tag_id: str | list[str],
+    tag_open: str | list[str],
+    tag_close: str | list[str],
+) -> str:
+    return HighlightedTextbox.tuples_to_tagged_text(
+        highlighted_text["data"], tag_id, tag_open, tag_close
+    )
+
+
+initial_text = "It is not something to be ashamed of: it is no different from the <d>personal fears</d> and <tm>dislikes</tm> of other things that <t>manny peopl</t> have."
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Parameters to control the highlighted textbox:")
+    with gr.Row():
+        tag_id = gr.Dropdown(
+            choices=["Typo", "Terminology", "Disfluency"],
+            value=["Typo", "Terminology", "Disfluency"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag ID",
+            show_label=True,
+            info="Insert one or more tag IDs to use in the highlighted textbox.",
+        )
+        tag_open = gr.Dropdown(
+            choices=["<t>", "<tm>", "<d>"],
+            value=["<t>", "<tm>", "<d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag open",
+            show_label=True,
+            info="Insert one or more tags to mark the beginning of a highlighted section.",
+        )
+        tag_close = gr.Dropdown(
+            choices=["</t>", "</tm>", "</d>"],
+            value=["</t>", "</tm>", "</d>"],
+            multiselect=True,
+            allow_custom_value=True,
+            label="Tag close",
+            show_label=True,
+            info="Insert one or more tags to mark the end of a highlighted section.",
+        )
+    gr.Markdown("### Example tagged to highlight:")
+    with gr.Row():
+        tagged_t2h = gr.Textbox(
+            initial_text,
+            interactive=True,
+            label="Tagged Input",
+            show_label=True,
+            info="Tagged text using the format above to mark spans that will be highlighted.",
+        )
+        high_t2h = HighlightedTextbox(
+            convert_tagged_text_to_highlighted_text(
+                tagged_t2h.value, tag_id.value, tag_open.value, tag_close.value
+            ),
+            interactive=False,
+            label="Highlighted Output",
+            info="Highlighted textbox intialized from the tagged input.",
+            show_legend=True,
+            show_label=True,
+            legend_label="Legend:",
+            show_legend_label=True,
+        )
+    gr.Markdown("### Example highlight to tagged:")
+    with gr.Row():
+        high_h2t = HighlightedTextbox(
+            convert_tagged_text_to_highlighted_text(
+                initial_text, tag_id.value, tag_open.value, tag_close.value
+            ),
+            interactive=True,
+            label="Highlighted Input",
+            info="Highlighted textbox using the format above to mark spans that will be highlighted.",
+            show_legend=True,
+            show_label=True,
+            legend_label="Legend:",
+            show_legend_label=True,
+        )
+        tagged_h2t = gr.Textbox(
+            initial_text,
+            interactive=False,
+            label="Tagged Output",
+            info="Tagged text intialized from the highlighted textbox.",
+            show_label=True,
+        )
+
+    # Functions
+
+    tagged_t2h.input(
+        fn=convert_tagged_text_to_highlighted_text,
+        inputs=[tagged_t2h, tag_id, tag_open, tag_close],
+        outputs=high_t2h,
+    )
+    high_h2t.input(
+        fn=convert_highlighted_text_to_tagged_text,
+        inputs=[high_h2t, tag_id, tag_open, tag_close],
+        outputs=tagged_h2t,
+    )
+
+if __name__ == "__main__":
+    demo.launch()
+
+```
+""", elem_classes=["md-custom"], header_links=True)
+
+
+    gr.Markdown("""
+## `HighlightedTextbox`
+
+### Initialization
+""", elem_classes=["md-custom"], header_links=True)
+
+    gr.ParamViewer(value=_docs["HighlightedTextbox"]["members"]["__init__"], linkify=[])
+
+
+    gr.Markdown("### Events")
+    gr.ParamViewer(value=_docs["HighlightedTextbox"]["events"], linkify=['Event'])
+
+
+
+
+    gr.Markdown("""
+
+### User function
+
+The impact on the users predict function varies depending on whether the component is used as an input or output for an event (or both).
+
+- When used as an Input, the component only impacts the input signature of the user function. 
+- When used as an output, the component only impacts the return signature of the user function. 
+
+The code snippet below is accurate in cases where the component is used as both an input and an output.
+
+- **As output:** Should return, list of (word, category) tuples, or a dictionary of two keys: "text", and "highlights", which itself is.
+
+ ```python
+def predict(
+    value: dict
+) -> list[tuple[str, str | None]] | dict | None:
+    return value
+```
+""", elem_classes=["md-custom", "HighlightedTextbox-user-fn"], header_links=True)
+
+
+
+
+    demo.load(None, js=r"""function() {
+    const refs = {};
+    const user_fn_refs = {
+          HighlightedTextbox: [], };
+    requestAnimationFrame(() => {
+
+        Object.entries(user_fn_refs).forEach(([key, refs]) => {
+            if (refs.length > 0) {
+                const el = document.querySelector(`.${key}-user-fn`);
+                if (!el) return;
+                refs.forEach(ref => {
+                    el.innerHTML = el.innerHTML.replace(
+                        new RegExp("\\b"+ref+"\\b", "g"),
+                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
+                    );
+                })
+            }
+        })
+        
+        Object.entries(refs).forEach(([key, refs]) => {
+            if (refs.length > 0) {
+                const el = document.querySelector(`.${key}`);
+                if (!el) return;
+                refs.forEach(ref => {
+                    el.innerHTML = el.innerHTML.replace(
+                        new RegExp("\\b"+ref+"\\b", "g"),
+                        `<a href="#h-${ref.toLowerCase()}">${ref}</a>`
+                    );
+                })
+            }
+        })
+    })
+}
+
+""")
+
+demo.launch()

src/frontend/BlockTitleWithHighlights.svelte

@@ -0,0 +1,106 @@
+<script lang="ts">
+	export let show_label = true;
+    export let show_legend = true;
+    export let show_legend_label = true;
+    export let legend_label: string | undefined = "Highlights:";
+    export let _color_map: Record<string, { primary: string; secondary: string }> = {};
+	export let info: string | undefined = undefined;
+</script>
+
+<div class="title-container">
+    <span
+        class:sr-only={!show_label}
+        class:hide={!show_label}
+        class:has-info={info != null}
+        data-testid="block-info"
+    >
+        <slot />
+    </span>
+    {#if Object.keys(_color_map).length !== 0}
+        <span
+            class="legend-separator"
+            class:hide={!show_legend}
+            class:has-info={info != null}
+        >
+        ·
+        </span>
+        <div
+            class="category-legend"
+            data-testid="highlighted-text:category-legend"
+            class:hide={!show_legend}
+        >
+            <span class:hide={!show_legend_label} class:has-info={info != null}>
+                {legend_label}
+            </span>
+            {#each Object.entries(_color_map) as [category, color], i}
+                <!-- svelte-ignore a11y-no-static-element-interactions -->
+                <div class="category-label" style={"background-color:" + color.secondary}>
+                    {category}
+                </div>
+            {/each}
+        </div>
+    {/if}
+</div>
+{#if info}
+    <div class="title-with-highlights-info">
+        {info}
+    </div>
+{/if}
+
+<style>
+	span.has-info {
+		margin-bottom: var(--spacing-xs);
+	}
+	span:not(.has-info) {
+		margin-bottom: var(--spacing-lg);
+	}
+	span {
+		display: inline-block;
+		position: relative;
+		z-index: var(--layer-4);
+		border: solid var(--block-title-border-width)
+			var(--block-title-border-color);
+		border-radius: var(--block-title-radius);
+		background: var(--block-title-background-fill);
+		padding: var(--block-title-padding);
+		color: var(--block-title-text-color);
+		font-weight: var(--block-title-text-weight);
+		font-size: var(--block-title-text-size);
+		line-height: var(--line-sm);
+	}
+
+	.hide {
+		margin: 0;
+		height: 0;
+	}
+
+    .category-legend {
+		display: flex;
+		flex-wrap: wrap;
+		gap: var(--spacing-sm);
+		color: black;
+	}
+
+	.category-label {
+		border-radius: var(--radius-xs);
+		padding-right: var(--size-2);
+		padding-left: var(--size-2);
+		font-weight: var(--weight-semibold);
+	}
+
+	.title-container {
+        display: flex;
+    }
+
+    .legend-separator {
+        margin: 0 var(--spacing-md) 0 var(--spacing-md);
+    }
+
+    .title-with-highlights-info {
+		margin-bottom: var(--spacing-xs);
+		color: var(--block-info-text-color);
+		font-weight: var(--block-info-text-weight);
+		font-size: var(--block-info-text-size);
+		line-height: var(--line-sm);
+    }
+</style>

src/frontend/HighlightedTextbox.svelte

@@ -4,7 +4,7 @@
 		afterUpdate,
 		createEventDispatcher,
 	} from "svelte";
-	import { BlockTitle } from "@gradio/atoms";
+	import BlockTitleWithHighlights from "./BlockTitleWithHighlights.svelte";
 	import { Copy, Check } from "@gradio/icons";
 	import { fade } from "svelte/transition";
 	import type { SelectData } from "@gradio/utils";
@@ -29,18 +29,18 @@
 	let el_text: string = "";
 	let marked_el_text: string = "";
 	let ctx: CanvasRenderingContext2D;
-	let current_color_map: Record<string, string> = {};
+	let current_color_map: Record<string, string> = !color_map || Object.keys(color_map).length === 0 ? {} : color_map;
 	let _color_map: Record<string, { primary: string; secondary: string }> = {};
 	let copied = false;
 	let timer: ReturnType<typeof setTimeout>;
     let can_scroll: boolean;
 
 	function set_color_map(): void {
-		if (!color_map || Object.keys(color_map).length === 0) {
-			current_color_map = {};
-		}
-		else {
-			current_color_map = color_map;
+		// if a label in the color map is not in the value, remove it from the color map
+		for (let label in current_color_map) {
+			if (!value.map(([_, label]) => label).includes(label)) {
+				delete current_color_map[label];
+			}
 		}
 		if (value.length > 0) {
 			for (let [_, label] of value) {
@@ -54,6 +54,8 @@
 	}
 
 	function set_text_from_value(as_output: boolean): void {
+		console.log(value)
+		console.log(_color_map)
 		if (value.length > 0 && as_output) {
 			el_text = value.map(([text, _]) => text).join(" ");
 			marked_el_text = value.map(([text, category]) => {
@@ -71,10 +73,10 @@
 
 	const dispatch = createEventDispatcher<{
 		change: string;
+		input: string;
 		submit: undefined;
 		blur: undefined;
 		select: SelectData;
-		input: string;
 		focus: undefined;
 	}>();
 
@@ -96,10 +98,7 @@
 	});
 	$: marked_el_text, handle_change();
 
-	// Given a string like Hello <mark class="hl red" style="background-color:#fee2e2">world!</mark>  This is cool.
-	// for marked_el_text and its previous parsed version (value) like [["Hello ", null], ["world!", "red"], [" This is ", null], ["nice", "blue"]],
-	// update value such that it matches marked_el_text (i.e. [["Hello ", null], ["world!", "red"], [" This is cool.", null]])
-	function handle_blur(): void {
+	function set_value_from_marked_span(): void {
 		let new_value: [string, string | null][] = [];
 		let text = "";
 		let category = null;
@@ -169,32 +168,17 @@
 				range.setEnd(nodeAndOffset.node, nodeAndOffset.offset);
 				newSelection.removeAllRanges();
 				newSelection.addRange(range);
-				handle_blur();
 			}
 		}
+		set_value_from_marked_span();
+		dispatch("change", marked_el_text);
 	}
 </script>
 
 <!-- svelte-ignore a11y-no-static-element-interactions -->
 <!-- svelte-ignore a11y-click-events-have-key-events-->
 <label class:container>
-	{#if show_legend}
-		<div
-		class="category-legend"
-		data-testid="highlighted-text:category-legend"
-		>
-			{#if show_legend_label}
-				<div class="legend-description">{legend_label}</div>
-			{/if}
-			{#each Object.entries(_color_map) as [category, color], i}
-				<!-- svelte-ignore a11y-no-static-element-interactions -->
-				<div class="category-label" style={"background-color:" + color.secondary}>
-					{category}
-				</div>
-			{/each}
-		</div>
-	{/if}
-	<BlockTitle {show_label} {info}>{label}</BlockTitle>
+	<BlockTitleWithHighlights {show_label} {info} {show_legend} {show_legend_label} {legend_label} {_color_map}>{label}</BlockTitleWithHighlights>
 	{#if show_copy_button}
 		{#if copied}
 			<button
@@ -228,7 +212,7 @@
             bind:this={el}
             bind:textContent={el_text}
             bind:innerHTML={marked_el_text}
-            on:blur={handle_blur}
+            on:blur
             on:keypress
             on:select
             on:scroll
@@ -269,30 +253,6 @@
 		display: flex;
 		flex-direction: column;
 		gap: var(--spacing-sm);
-		padding: var(--block-padding);
-	}
-
-	.category-legend {
-		display: flex;
-		flex-wrap: wrap;
-		gap: var(--spacing-sm);
-		color: black;
-		margin-bottom: var(--spacing-sm)
-	}
-
-	.category-label {
-		border-radius: var(--radius-xs);
-		padding-right: var(--size-2);
-		padding-left: var(--size-2);
-		font-weight: var(--weight-semibold);
-	}
-
-	.legend-description {
-		background-color: transparent;
-		color: var(--block-title-text-color);
-		padding-left: 0px;
-		border-radius: var(--radius-xs);
-		font-weight: var(--input-text-weight);
 	}
 
 	.textfield {

src/frontend/utils.ts

@@ -107,4 +107,11 @@ export function getNodeAndOffset(root, index) {
 	}
 	var offset = node.textContent.length - (runningTotal - index);
 	return { node: node, offset: offset };
-}
+}
+
+
+export function escapeHtml(unsafe: string): string {
+    return unsafe
+        .replace(/</g, "&lt;")
+        .replace(/>/g, "&gt;")
+}

src/pyproject.toml

@@ -8,7 +8,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "gradio_highlightedtextbox"
-version = "0.0.5"
+version = "0.0.6"
 description = "Editable Gradio textarea supporting highlighting"
 readme = "README.md"
 license = "mit"
@@ -39,7 +39,7 @@ dev = ["build", "twine"]
 space = "https://huggingface.co/spaces/gsarti/gradio_highlightedtextbox"
 
 [tool.hatch.build]
-artifacts = ["/backend/gradio_highlightedtextbox/templates", "*.pyi", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "Users/gsarti/Documents/projects/highlightedtextbox/backend/gradio_highlightedtextbox/templates", "Users/gsarti/Documents/projects/highlightedtextbox/backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates"]
+artifacts = ["/backend/gradio_highlightedtextbox/templates", "*.pyi", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "Users/gsarti/Documents/projects/highlightedtextbox/backend/gradio_highlightedtextbox/templates", "Users/gsarti/Documents/projects/highlightedtextbox/backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates", "backend/gradio_highlightedtextbox/templates"]
 
 [tool.hatch.build.targets.wheel]
 packages = ["/backend/gradio_highlightedtextbox"]