add first and latest commit dates to table

app.py

@@ -1,4 +1,5 @@
 import json
+from datetime import datetime
 
 import gradio as gr
 import pandas as pd
@@ -10,6 +11,13 @@ def read_json(file_name):
     return json_data
 
 
+def truncate_text(text, max_length=40):
+    if len(text) > max_length:
+        return text[: max_length - 1] + "…"
+    else:
+        return text
+
+
 json_file = "awesome-japanese-nlp-resources-search.json"
 json_data = read_json(json_file)
 data = {
@@ -17,6 +25,8 @@ data = {
     "downloads": [],
     "stars": [],
     "description": [],
+    "first_commit": [],
+    "latest_commit": [],
     "source": [],
     "languages": [],
     "type": [],
@@ -29,6 +39,15 @@ for data_json in json_data:
     source = data_json["source"]
     languages = data_json["languages"]
     repo_type = data_json["model_or_dataset"]
+    first_commit = data_json["first_commit"]
+    if first_commit:
+        first_commit = datetime.strptime(first_commit, "%Y-%m-%d %H:%M:%S")
+        first_commit = first_commit.date()
+
+    latest_commit = data_json["latest_commit"]
+    if latest_commit:
+        latest_commit = datetime.strptime(latest_commit, "%Y-%m-%d %H:%M:%S")
+        latest_commit = latest_commit.date()
 
     if "stargazers_count" in data_json:
         data["stars"].append(data_json["stargazers_count"])
@@ -40,17 +59,19 @@ for data_json in json_data:
     else:
         data["downloads"].append(None)
 
-    data["project_name"].append(f"[{project_name}]({url})")
+    data["project_name"].append(f"[{truncate_text(project_name)}]({url})")
     data["source"].append(source)
     data["description"].append(description)
     data["languages"].append(languages)
     data["type"].append(repo_type)
+    data["first_commit"].append(first_commit)
+    data["latest_commit"].append(latest_commit)
 
 data = pd.DataFrame(data)
 
 
 def show_search_results(
-    language_filter, queries, type_checkbox, source_checkbox
+    language_filter, queries, source_checkbox, show_checkbox
 ):
     queries = queries.lower()
     queries = queries.split()
@@ -67,12 +88,7 @@ def show_search_results(
         )
         df_search = df_search[matches]
 
-    if "Dataset" in type_checkbox:
-        df_search = df_search[df_search["type"] == "dataset"]
-
-    if "Model" in type_checkbox:
-        df_search = df_search[df_search["type"] == "model"]
-
+    # source_checkbox
     if "GitHub" not in source_checkbox:
         df_search = df_search[df_search["source"] != "GitHub"]
         df_search = df_search.drop("stars", axis=1)
@@ -81,6 +97,40 @@ def show_search_results(
         df_search = df_search[df_search["source"] != "Hugging Face"]
         df_search = df_search.drop("downloads", axis=1)
 
+    if "Dataset" in source_checkbox:
+        df_search = df_search[df_search["type"] == "dataset"]
+
+    if "Model" in source_checkbox:
+        df_search = df_search[df_search["type"] == "model"]
+
+    # show_checkbox
+    if "project_name" not in show_checkbox:
+        df_search = df_search.drop("project_name", axis=1)
+
+    if "downloads" not in show_checkbox:
+        df_search = df_search.drop("downloads", axis=1)
+
+    if "stars" not in show_checkbox:
+        df_search = df_search.drop("stars", axis=1)
+
+    if "first_commit" not in show_checkbox:
+        df_search = df_search.drop("first_commit", axis=1)
+
+    if "latest_commit" not in show_checkbox:
+        df_search = df_search.drop("latest_commit", axis=1)
+
+    if "description" not in show_checkbox:
+        df_search = df_search.drop("description", axis=1)
+
+    if "source" not in show_checkbox:
+        df_search = df_search.drop("source", axis=1)
+
+    if "languages" not in show_checkbox:
+        df_search = df_search.drop("languages", axis=1)
+
+    if "type" not in show_checkbox:
+        df_search = df_search.drop("type", axis=1)
+
     for query in queries:
         contained_description = data["description"].str.contains(query)
 
@@ -120,14 +170,30 @@ with gr.Blocks() as demo:
     )
 
     source_checkbox = gr.CheckboxGroup(
-        ["GitHub", "Hugging Face"],
+        ["GitHub", "Hugging Face", "Dataset", "Model"],
         value=["GitHub", "Hugging Face"],
         label="Source",
     )
 
-    type_checkbox = gr.CheckboxGroup(
-        ["Dataset", "Model"],
-        label="Type",
+    show_checkbox = gr.CheckboxGroup(
+        [
+            "project_name",
+            "downloads",
+            "stars",
+            "description",
+            "first_commit",
+            "latest_commit",
+            "source",
+            "type",
+            "languages",
+        ],
+        value=[
+            "project_name",
+            "downloads",
+            "stars",
+            "description",
+        ],
+        label="Display columns in a table",
     )
 
     df = gr.DataFrame(
@@ -142,38 +208,41 @@ with gr.Blocks() as demo:
         inputs=[
             language_selector,
             query,
-            type_checkbox,
             source_checkbox,
+            show_checkbox,
         ],
         outputs=df,
     )
+
     language_selector.change(
         fn=show_search_results,
         inputs=[
             language_selector,
             query,
-            type_checkbox,
             source_checkbox,
+            show_checkbox,
         ],
         outputs=df,
     )
+
     source_checkbox.change(
         fn=show_search_results,
         inputs=[
             language_selector,
             query,
-            type_checkbox,
             source_checkbox,
+            show_checkbox,
         ],
         outputs=df,
     )
-    type_checkbox.change(
+
+    show_checkbox.change(
         fn=show_search_results,
         inputs=[
             language_selector,
             query,
-            type_checkbox,
             source_checkbox,
+            show_checkbox,
         ],
         outputs=df,
     )