Add application file

app.py

@@ -0,0 +1,61 @@
+import gradio as gr
+from reference_string_parsing import *
+from description import *
+
+
+
+with gr.Blocks(css="#htext span {white-space: pre-line}") as demo:
+    gr.Markdown("# Gradio Demo for SciAssist")
+    with gr.Tabs():
+        with gr.TabItem("Reference String Parsing"):
+            with gr.Box():
+                gr.Markdown(rsp_str_md)
+                with gr.Row():
+                    with gr.Column():
+                        rsp_str = gr.Textbox(label="Input String")
+                        rsp_str_dehyphen = gr.Checkbox(label="dehyphen")
+                        with gr.Row():
+                            rsp_str_btn = gr.Button("Parse")
+                    rsp_str_output = gr.HighlightedText(
+                        elem_id="htext",
+                        label="The Result of Parsing",
+                        combine_adjacent=True,
+                        adjacent_separator=" ",
+                    )
+                rsp_str_examples = gr.Examples(examples=[[
+                                                         "Waleed Ammar, Matthew E. Peters, Chandra Bhagavat- ula, and Russell Power. 2017. The ai2 system at semeval-2017 task 10 (scienceie): semi-supervised end-to-end entity and relation extraction. In ACL workshop (SemEval).",
+                                                         True],
+                                                     [
+                                                         "Isabelle Augenstein, Mrinal Das, Sebastian Riedel, Lakshmi Vikraman, and Andrew D. McCallum. 2017. Semeval 2017 task 10 (scienceie): Extracting keyphrases and relations from scientific publications. In ACL workshop (SemEval).",
+                                                         False]], inputs=[rsp_str, rsp_str_dehyphen])
+            with gr.Box():
+                gr.Markdown(rsp_file_md)
+                with gr.Row():
+                    with gr.Column():
+                        rsp_file = gr.File()
+                        rsp_file_dehyphen = gr.Checkbox(label="dehyphen")
+                        with gr.Row():
+                            rsp_file_btn = gr.Button("Parse")
+
+                    rsp_file_output = gr.HighlightedText(
+                        elem_id="htext",
+                        label="The Result of Parsing",
+                        combine_adjacent=True,
+                        adjacent_separator=" ",
+                    )
+
+        with gr.TabItem("Source Code"):
+            gr.Markdown(value=gradio_code)
+
+    rsp_file_btn.click(
+        fn=rsp_for_file,
+        inputs=[rsp_file, rsp_file_dehyphen],
+        outputs=rsp_file_output
+    )
+    rsp_str_btn.click(
+        fn=rsp_for_str,
+        inputs=[rsp_str, rsp_str_dehyphen],
+        outputs=rsp_str_output
+    )
+
+demo.launch(share=True)

description.py

@@ -0,0 +1,57 @@
+gradio_code = '''
+If you'd like to generate a demo like this on your own, please go for [**our GitHub repo**](https://github.com/WING-NUS/SciAssist) 
+and try the following codes.
+
+This is the command we actually run:
+```python
+
+from typing import List, Tuple
+from SciAssist import ReferenceStringParsing
+
+rsp_pipeline = ReferenceStringParsing()
+
+
+def rsp_for_str(input, dehyphen=False) -> List[Tuple[str, str]]:
+    results = rsp_pipeline.predict(input, type="str", dehyphen=dehyphen)
+    output = []
+    for res in results:
+        for token, tag in zip(res["tokens"], res["tags"]):
+            output.append((token, tag))
+        output.append(("\n\n", None))
+    return output
+
+
+def rsp_for_file(input, dehyphen=False) -> List[Tuple[str, str]]:
+    if input == None:
+        return None
+    filename = input.name
+    # Identify the format of input and parse reference strings
+    if filename[-4:] == ".txt":
+        results = rsp_pipeline.predict(filename, type="txt", dehyphen=dehyphen)
+    elif filename[-4:] == ".pdf":
+        results = rsp_pipeline.predict(filename, dehyphen=dehyphen)
+    else:
+        return [("File Format Error !", None)]
+    # Prepare for the input gradio.HighlightedText accepts.
+    output = []
+    for res in results:
+        for token, tag in zip(res["tokens"], res["tags"]):
+            output.append((token, tag))
+        output.append(("\n\n", None))
+    return output
+
+```
+'''
+
+rsp_str_md = '''
+    To **test on strings**, simply input one or more strings.
+'''
+
+rsp_file_md = '''
+To **test on a file**, the input can be either:
+
+- A txt file which contains a reference string in each line.
+- A pdf file which contains a whole scientific document without any processing (including title, author...). 
+
+'''
+

reference_string_parsing.py

@@ -0,0 +1,34 @@
+from typing import List, Tuple
+from SciAssist import ReferenceStringParsing
+
+rsp_pipeline = ReferenceStringParsing()
+
+
+def rsp_for_str(input, dehyphen=False) -> List[Tuple[str, str]]:
+    results = rsp_pipeline.predict(input, type="str", dehyphen=dehyphen)
+    output = []
+    for res in results:
+        for token, tag in zip(res["tokens"], res["tags"]):
+            output.append((token, tag))
+        output.append(("\n\n", None))
+    return output
+
+
+def rsp_for_file(input, dehyphen=False) -> List[Tuple[str, str]]:
+    if input == None:
+        return None
+    filename = input.name
+    # Identify the format of input and parse reference strings
+    if filename[-4:] == ".txt":
+        results = rsp_pipeline.predict(filename, type="txt", dehyphen=dehyphen)
+    elif filename[-4:] == ".pdf":
+        results = rsp_pipeline.predict(filename, dehyphen=dehyphen)
+    else:
+        return [("File Format Error !", None)]
+    # Prepare for the input gradio.HighlightedText accepts.
+    output = []
+    for res in results:
+        for token, tag in zip(res["tokens"], res["tags"]):
+            output.append((token, tag))
+        output.append(("\n\n", None))
+    return output

requirements.txt

@@ -0,0 +1 @@
+SciAssist==0.0.11