From a7e88c8be7a09be811eb86b7775508670c7aafa9 Mon Sep 17 00:00:00 2001
From: Nils Herrmann <88451442+nils-herrmann@users.noreply.github.com>
Date: Fri, 30 Aug 2024 10:52:33 +0200
Subject: [PATCH] Drop all_paragraph from parse_pubmed_paragraph() (close #147)

---
 pubmed_parser/pubmed_oa_parser.py | 13 +++----------
 tests/test_pubmed_oa_parser.py    |  2 +-
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/pubmed_parser/pubmed_oa_parser.py b/pubmed_parser/pubmed_oa_parser.py
index 33dc22f..9e3cfe3 100644
--- a/pubmed_parser/pubmed_oa_parser.py
+++ b/pubmed_parser/pubmed_oa_parser.py
@@ -367,7 +367,7 @@ def parse_pubmed_references(path):
     return dict_refs
 
 
-def parse_pubmed_paragraph(path, all_paragraph=False):
+def parse_pubmed_paragraph(path):
     """
     Give path to a given PubMed OA file, parse and return
     a dictionary of all paragraphs, section that it belongs to,
@@ -377,13 +377,6 @@ def parse_pubmed_paragraph(path, all_paragraph=False):
     ----------
     path: str
         A string to an XML path.
-    all_paragraph: bool
-        By default, this function will only append a paragraph if there is at least
-        one reference made in a paragraph (to aviod noisy parsed text).
-        A boolean indicating if you want to include paragraph with no references made or not
-        if True, include all paragraphs
-        if False, include only paragraphs that have references
-        default: False
 
     Return
     ------
@@ -421,8 +414,8 @@ def parse_pubmed_paragraph(path, all_paragraph=False):
             "section": section,
             "text": paragraph_text,
         }
-        if len(ref_ids) >= 1 or all_paragraph:
-            dict_pars.append(dict_par)
+
+        dict_pars.append(dict_par)
 
     return dict_pars
 
diff --git a/tests/test_pubmed_oa_parser.py b/tests/test_pubmed_oa_parser.py
index 577622f..b9c834e 100644
--- a/tests/test_pubmed_oa_parser.py
+++ b/tests/test_pubmed_oa_parser.py
@@ -60,7 +60,7 @@ def test_parse_pubmed_paragraph():
     paragraphs = pp.parse_pubmed_paragraph(pubmed_xml_3460867)
     assert isinstance(paragraphs, list)
     assert isinstance(paragraphs[0], dict)
-    assert len(paragraphs) == 29, "Expected number of paragraphs to be 29"
+    assert len(paragraphs) == 58, "Expected number of paragraphs to be 58"
     assert (
         len(paragraphs[0]["reference_ids"]) == 11
     ), "Expected number of references in the first paragraph to be 11"