fix(api): reduce code redundancies, update tests

Sefaria · Jul 10, 2024 · da70c51 · da70c51
1 parent 676a1fb
commit da70c51
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 11 deletions.
diff --git a/sefaria/model/tests/text_test.py b/sefaria/model/tests/text_test.py
@@ -817,7 +817,7 @@ def test_remove_html():
     pasuk_with_html = "</big>בּ<big>ְרֵאשִׁ֖ית בָּרָ֣א אֱלֹהִ֑ים אֵ֥ת הַשָּׁמַ֖יִם וְאֵ֥ת הָאָֽרֶץ"
     pasuk_without_html = "בְּרֵאשִׁ֖ית בָּרָ֣א אֱלֹהִ֑ים אֵ֥ת הַשָּׁמַ֖יִם וְאֵ֥ת הָאָֽרֶץ"
 
-    pasuk_with_br = "Happy is the <big>man</big> who has not followed the counsel of the wicked,<br>or taken the path of sinners,<br>or joined the company of the insolent;"
+    pasuk_with_br = "Happy is the <big>man</big> who has not followed the counsel of the wicked,<br/>or taken the path of sinners,<br/>or joined the company of the insolent;"
     pasuk_without_br = "Happy is the man who has not followed the counsel of the wicked, or taken the path of sinners, or joined the company of the insolent;"
 
     assert model.TextChunk.remove_html(pasuk_with_html) == pasuk_without_html

diff --git a/sefaria/model/text.py b/sefaria/model/text.py
@@ -1171,22 +1171,21 @@ def sanitize_text(cls, t):
 
     @staticmethod
     def remove_html(t):
+
+        def conditional_replace(match):
+            tag = match.group()
+            if tag == "<br/>":
+                return " "
+            return ""
+
         if isinstance(t, list):
             for i, v in enumerate(t):
                 if isinstance(v, str):
-                    tags = re.findall('<[^>]+>', t[i])
-                    for tag in tags:
-                        if tag == "<br>":
-                            t[i] = re.sub("<br>", " ", v)
-                    t[i] = re.sub('<[^>]+>', "", v)
+                    t[i] = re.sub('<[^>]+>', conditional_replace, v)
                 else:
                     t[i] = AbstractTextRecord.remove_html(v)
         elif isinstance(t, str):
-            tags = re.findall('<[^>]+>', t)
-            for tag in tags:
-                if tag == "<br>":
-                    t = re.sub("<br>", " ", t)
-            t = re.sub('<[^>]+>', "", t)
+            t = re.sub('<[^>]+>', conditional_replace, t)
         else:
             return False
         return t