update

src/application/content_detection.py

@@ -507,15 +507,14 @@ class NewsVerification:
             score = self.text_prediction_score[0]
 
         # Format displayed url
-
-        short_url = self.shorten_url(url, max_length)
-        source_text_url = f"""<a href="{url}">{short_url}</a>"""
+        source_text_url = f"""<a href="{url}">{url}</a>"""
 
         # Format displayed entity count
         entity_count_text = self.get_entity_count_text(entity_count)
 
         border_top = "border-top: 1px solid transparent;"
         border_bottom = "border-bottom: 1px solid transparent;"
+        word_break = "word-break: break-all;"
         if first_url_row is True:
             # First & Last the group: no transparent
             if last_url_row is True:
@@ -526,7 +525,7 @@ class NewsVerification:
     <td rowspan="{span_row}">{label}<br>
     ({score * 100:.2f}%)<br><br>
     {entity_count_text}</td>
-    <td rowspan="{span_row}">{source_text_url}</td>
+    <td rowspan="{span_row}"; style="{word_break}";>{source_text_url}</td>
 </tr>
 """
             # First row of the group: transparent bottom border
@@ -537,7 +536,7 @@ class NewsVerification:
     <td rowspan="{span_row}">{label}<br>
     ({score * 100:.2f}%)<br><br>
     {entity_count_text}</td>
-    <td rowspan="{span_row}">{source_text_url}</td>
+    <td rowspan="{span_row}"; style="{word_break}";>{source_text_url}</td>
 </tr>
 """
         else:
@@ -565,15 +564,18 @@ class NewsVerification:
             or self.image_referent_url != ""
         ):
             source_image = f"""<img src="{self.image_referent_url}" width="100" height="150">"""  # noqa: E501
-            short_url = self.shorten_url(self.image_referent_url, max_length)
-            source_image_url = (
-                f"""<a href="{self.image_referent_url}">{short_url}</a>"""
-            )
+            source_image_url = f"""<a href="{self.image_referent_url}">{self.image_referent_url}</a>"""  # noqa: E501
         else:
             source_image = "Image not found"
             source_image_url = ""
 
-        return f"""<tr><td>input image</td><td>{source_image}</td><td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td><td>{source_image_url}</td></tr>"""  # noqa: E501
+        word_break = "word-break: break-all;"
+        return f"""
+    <tr>
+        <td>input image</td>
+        <td>{source_image}</td>
+        <td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td>
+        <td style="{word_break}";>{source_image_url}</td></tr>"""
 
     def create_ordinary_user_table(self):
         rows = []
@@ -585,7 +587,7 @@ class NewsVerification:
         return f"""
 <h5>Comparison between input news and source news:</h5>
 <table border="1" style="width:100%; text-align:left;">
-<col style="width: 170px;">
+<col style="width: 340px;">
 <col style="width: 30px;">
 <col style="width: 75px;">
     <thead>
@@ -614,15 +616,15 @@ class NewsVerification:
             url = row["url"]
             if url not in urls:
                 urls.append(url)
-                short_url = self.shorten_url(url, max_length)
-                source_text_urls += f"""<a href="{url}">{short_url}</a><br>"""
+                source_text_urls += f"""<a href="{url}">{url}</a><br>"""
 
+        word_break = "word-break: break-all;"
         return f"""
                 <tr>
                     <td>{input_sentences}</td>
                     <td>{self.text_prediction_label[0]}<br>
                     ({self.text_prediction_score[0] * 100:.2f}%)</td>
-                    <td>{source_text_urls}</td>
+                    <td style="{word_break}";>{source_text_urls}</td>
                 </tr>
                 """
 
@@ -632,15 +634,12 @@ class NewsVerification:
             self.image_referent_url is not None
             or self.image_referent_url != ""
         ):
-            short_url = self.shorten_url(self.image_referent_url, max_length)
-            source_image_url = (
-                f"""<a href="{self.image_referent_url}">{short_url}</a>"""
-            )
+            source_image_url = f"""<a href="{self.image_referent_url}">{self.image_referent_url}</a>"""  # noqa: E501
         else:
-            # source_image = "Image not found"
             source_image_url = ""
 
-        return f"""<tr><td>input image</td><td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td><td>{source_image_url}</td></tr>"""  # noqa: E501
+        word_break = "word-break: break-all;"
+        return f"""<tr><td>input image</td><td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td><td style="{word_break}";>{source_image_url}</td></tr>"""  # noqa: E501
 
     def create_governor_table(self):
         rows = []
@@ -764,14 +763,13 @@ class NewsVerification:
             url = row[0]["url"]
             if url not in urls:
                 urls.append(url)
-                short_url = self.shorten_url(url, max_length)
-                source_text_urls += f"""<a href="{url}">{short_url}</a><br>"""
+                source_text_urls += f"""<a href="{url}">{url}</a><br><br>"""
                 sentence_count += 1
                 if row[3] is not None:
                     entity_count.append(len(row[3]))
 
         entity_count_text = self.get_entity_count_text(sum(entity_count))
-
+        word_break = "word-break: break-all;"
         return f"""
 <tr>
     <td>{input_sentences}</td>
@@ -779,7 +777,7 @@ class NewsVerification:
     <td>{self.text_prediction_label[0]}<br>
         ({self.text_prediction_score[0] * 100:.2f}%)<br><br>
         {entity_count_text}</td>
-    <td>{source_text_urls}</td>
+    <td style="{word_break}";>{source_text_urls}</td>
 </tr>
                 """
 
@@ -789,15 +787,13 @@ class NewsVerification:
             or self.image_referent_url != ""
         ):
             source_image = f"""<img src="{self.image_referent_url}" width="100" height="150">"""  # noqa: E501
-            short_url = self.shorten_url(self.image_referent_url, max_length)
-            source_image_url = (
-                f"""<a href="{self.image_referent_url}">{short_url}</a>"""
-            )
+            source_image_url = f"""<a href="{self.image_referent_url}">{self.image_referent_url}</a>"""  # noqa: E501
         else:
             source_image = "Image not found"
             source_image_url = ""
 
-        return f"""<tr><td>input image</td><td>{source_image}</td><td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td><td>{source_image_url}</td></tr>"""  # noqa: E501
+        word_break = "word-break: break-all;"
+        return f"""<tr><td>input image</td><td>{source_image}</td><td>{self.image_prediction_label}<br>({self.image_prediction_score:.2f}%)</td><td style="{word_break}";>{source_image_url}</td></tr>"""  # noqa: E501
 
     def get_entity_count_text(self, entity_count):
         if entity_count <= 0:
@@ -808,16 +804,6 @@ class NewsVerification:
             entity_count_text = "with altered entities"
         return entity_count_text
 
-    def shorten_url(self, url, max_length=30):
-        if url is None:
-            return ""
-
-        if len(url) > max_length:
-            short_url = url[:max_length] + "..."
-        else:
-            short_url = url
-        return short_url
-
     def color_text(self, text, colored_idx, highlighted_idx):
         paragraph = ""
         words = text.split()

test.py

@@ -1,2 +1,14 @@
-my_list = [0, 0]
-print(my_list[-2])
+import pandas as pd
+
+# Assuming your CSV file is named 'data.csv'
+try:
+    df = pd.read_csv('data/bbc_news_4o_mini.csv')
+    # df = pd.read_csv('data/MAGE_4o_mini.csv')
+    
+    print(df.columns)  # header names
+    print(len(df))
+
+except FileNotFoundError:
+    print("Error: data.csv not found")
+except Exception as e:
+    print(f"An error occurred: {e}")