Fix misalignment in SQuAD

datasets/squad/README.md

@@ -1,4 +1,5 @@
 ---
+pretty_name: SQuAD
 annotations_creators:
 - crowdsourced
 language_creators:

datasets/squad/squad.py

@@ -120,15 +120,15 @@ def _generate_examples(self, filepath):
         with open(filepath, encoding="utf-8") as f:
             squad = json.load(f)
             for article in squad["data"]:
-                title = article.get("title", "").strip()
+                title = article.get("title", "")
                 for paragraph in article["paragraphs"]:
-                    context = paragraph["context"].strip()
+                    context = paragraph["context"]  # do not strip leading blank spaces GH-2585
                     for qa in paragraph["qas"]:
-                        question = qa["question"].strip()
+                        question = qa["question"]
                         id_ = qa["id"]
 
                         answer_starts = [answer["answer_start"] for answer in qa["answers"]]
-                        answers = [answer["text"].strip() for answer in qa["answers"]]
+                        answers = [answer["text"] for answer in qa["answers"]]
 
                         # Features currently used are "context", "question", and "answers".
                         # Others are extracted here for the ease of future expansions.

datasets/squad_v2/README.md

@@ -1,4 +1,5 @@
 ---
+pretty_name: SQuAD2.0
 annotations_creators:
 - crowdsourced
 language_creators:

datasets/squad_v2/squad_v2.py

@@ -109,15 +109,15 @@ def _generate_examples(self, filepath):
         with open(filepath, encoding="utf-8") as f:
             squad = json.load(f)
             for example in squad["data"]:
-                title = example.get("title", "").strip()
+                title = example.get("title", "")
                 for paragraph in example["paragraphs"]:
-                    context = paragraph["context"].strip()
+                    context = paragraph["context"]  # do not strip leading blank spaces GH-2585
                     for qa in paragraph["qas"]:
-                        question = qa["question"].strip()
+                        question = qa["question"]
                         id_ = qa["id"]
 
                         answer_starts = [answer["answer_start"] for answer in qa["answers"]]
-                        answers = [answer["text"].strip() for answer in qa["answers"]]
+                        answers = [answer["text"] for answer in qa["answers"]]
 
                         # Features currently used are "context", "question", and "answers".
                         # Others are extracted here for the ease of future expansions.