Kotahi DocMaps API: Match reviews case-insensitive and break on first…

… hyphen break line within public reviews (#249)

* Kotahi DocMaps API: Match reviews case-insensitive

* Ignore text after first hyphen break line when extracting public reviews

data_hub_api/kotahi_docmaps/v1/codecs/evaluation.py

@@ -41,7 +41,7 @@ def extract_elife_assessments_from_email(email_body: Optional[str]) -> Optional[
 
 def extract_elife_public_reviews_from_email(email_body: Optional[str]) -> Optional[str]:
     if email_body:
-        pattern = r'(?s)([pP]ublic [rR]eviews?:?\s*\n.*)-{10,}'
+        pattern = r'(?s)([pP]ublic [rR]eviews?:?\s*\n.*?)-{10,}'
         match = re.search(pattern, email_body)
         if match:
             extracted_text = match.group(1).strip()
@@ -53,7 +53,7 @@ def extract_elife_public_reviews_from_email(email_body: Optional[str]) -> Option
 def extract_public_review_parts(public_reviews: Optional[str]):
     if public_reviews:
         pattern = r'(?=Reviewer #\d+ \(Public Review\):?)'
-        parts = re.split(pattern, public_reviews)
+        parts = re.split(pattern, public_reviews, flags=re.IGNORECASE)
         parts = [part.strip() for part in parts if part.strip()]
         if len(parts) > 1:
             return parts[1:]

tests/unit_tests/kotahi_docmaps/v1/codecs/evaluation_test.py

@@ -63,6 +63,13 @@ def test_should_extract_elife_public_reviews_from_email(self):
         ).strip()
         assert result == PUBLIC_REVIEWS_1.strip()
 
+    def test_should_ignore_text_after_first_hyphen_break(self):
+        result = extract_elife_public_reviews_from_email(
+            EMAIL_BODY_WITH_ELIFE_ASSESSMENT_AND_PUBLIC_REVIEWS_1
+            + '\n----------\nmore text'
+        ).strip()
+        assert result == PUBLIC_REVIEWS_1.strip()
+
     def test_should_return_none_if_there_is_no_public_reviews_available(self):
         assert not extract_elife_public_reviews_from_email(EMAIL_BODY_1)
 
@@ -83,6 +90,10 @@ def test_should_extract_all_public_reviews_individually(self):
         assert result[1] == REVIEW_2.strip()
         assert result[2] == REVIEW_3.strip()
 
+    def test_should_match_case_insensitive(self):
+        result = extract_public_review_parts(PUBLIC_REVIEWS_1.lower())
+        assert result[0] == REVIEW_1.strip().lower()
+
     def test_should_return_none_when_there_is_no_public_reviews(self):
         assert not extract_public_review_parts(None)