From b18b8da680b9f065a2ee3c00986c8d86ada81a51 Mon Sep 17 00:00:00 2001
From: Rossi-Luciano <luciano.rossi.lucross@gmail.com>
Date: Fri, 3 Jul 2026 22:28:47 -0300
Subject: [PATCH] feat(pubmed): implementar CopyrightInformation e CoiStatement
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Substitui os stubs vazios de xml_pubmed_copyright_information e
xml_pubmed_coi_statement por implementações reais, via xpath direto
(sem model dedicado, seguindo o padrão já usado em
xml_pubmed_title_reference_list):

- CopyrightInformation: .//permissions/copyright-statement
- CoiStatement: .//fn[@fn-type="coi-statement"]/p, ignorando o
  <label> (ex. "Conflito de Interesses"), que é só cabeçalho de
  seção, não parte do conteúdo do statement.

Usa node_plain_text (já usado em article_contribs.py) para extrair o
texto sem subtags.

Refs #1226, #1238
---
 packtools/sps/formats/pubmed.py  |  37 +++++++---
 tests/sps/formats/test_pubmed.py | 115 +++++++++++++++++++++++++++++++
 2 files changed, 144 insertions(+), 8 deletions(-)

diff --git a/packtools/sps/formats/pubmed.py b/packtools/sps/formats/pubmed.py
index f99b2651d..60b876799 100644
--- a/packtools/sps/formats/pubmed.py
+++ b/packtools/sps/formats/pubmed.py
@@ -14,6 +14,7 @@
     journal_meta,
     kwd_group,
 )
+from packtools.sps.utils.xml_utils import node_plain_text
 
 
 def xml_pubmed_article_pipe():
@@ -508,18 +509,38 @@ def xml_pubmed_history(xml_pubmed, xml_tree):
     xml_pubmed.append(history)
 
 
+def get_copyright_information(xml_tree):
+    copyright_statement = xml_tree.find(".//permissions/copyright-statement")
+    return node_plain_text(copyright_statement) or None
+
+
 def xml_pubmed_copyright_information(xml_pubmed, xml_tree):
-    ...
-    # TODO
-    # The Copyright information associated with this article.
-    # There is no example of using this value in the files.
+    """
+    <CopyrightInformation>Copyright © 2023 The Authors</CopyrightInformation>
+    """
+    copyright_information = get_copyright_information(xml_tree)
+    if copyright_information:
+        el = ET.Element("CopyrightInformation")
+        el.text = copyright_information
+        xml_pubmed.append(el)
+
+
+def get_coi_statement(xml_tree):
+    fn_node = xml_tree.find('.//fn[@fn-type="coi-statement"]')
+    if fn_node is None:
+        return None
+    return node_plain_text(fn_node.find("p")) or node_plain_text(fn_node) or None
 
 
 def xml_pubmed_coi_statement(xml_pubmed, xml_tree):
-    ...
-    # TODO
-    # The Conflict of Interest statement associated with this article.
-    # There is no example of using this value in the files.
+    """
+    <CoiStatement>Não há conflito de interesse entre os autores do artigo.</CoiStatement>
+    """
+    coi_statement = get_coi_statement(xml_tree)
+    if coi_statement:
+        el = ET.Element("CoiStatement")
+        el.text = coi_statement
+        xml_pubmed.append(el)
 
 
 def get_keywords(xml_tree):
diff --git a/tests/sps/formats/test_pubmed.py b/tests/sps/formats/test_pubmed.py
index a8afad598..fba999b66 100644
--- a/tests/sps/formats/test_pubmed.py
+++ b/tests/sps/formats/test_pubmed.py
@@ -19,6 +19,8 @@
     xml_pubmed_publication_type,
     xml_pubmed_article_id,
     xml_pubmed_history,
+    xml_pubmed_copyright_information,
+    xml_pubmed_coi_statement,
     xml_pubmed_vernacular_title_pipe,
     xml_pubmed_object_list,
     xml_pubmed_title_reference_list,
@@ -1243,6 +1245,119 @@ def test_xml_pubmed_history(self):
 
         self.assertEqual(obtained, expected)
 
+    def test_xml_pubmed_copyright_information(self):
+        expected = (
+            '<Article>'
+            '<CopyrightInformation>Copyright © 2023 The Authors</CopyrightInformation>'
+            '</Article>'
+        )
+        xml_pubmed = ET.fromstring(
+            '<Article/>'
+        )
+        xml_tree = ET.fromstring(
+            '<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
+            'xmlns:xlink="http://www.w3.org/1999/xlink" '
+            'article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="en">'
+            '<front>'
+            '<article-meta>'
+            '<permissions>'
+            '<copyright-statement>Copyright © 2023 The Authors</copyright-statement>'
+            '</permissions>'
+            '</article-meta>'
+            '</front>'
+            '</article>'
+        )
+
+        xml_pubmed_copyright_information(xml_pubmed, xml_tree)
+
+        obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")
+
+        self.assertEqual(obtained, expected)
+
+    def test_xml_pubmed_copyright_information_without_statement(self):
+        expected = (
+            '<Article/>'
+        )
+        xml_pubmed = ET.fromstring(
+            '<Article/>'
+        )
+        xml_tree = ET.fromstring(
+            '<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
+            'xmlns:xlink="http://www.w3.org/1999/xlink" '
+            'article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="en">'
+            '<front>'
+            '<article-meta>'
+            '<permissions>'
+            '</permissions>'
+            '</article-meta>'
+            '</front>'
+            '</article>'
+        )
+
+        xml_pubmed_copyright_information(xml_pubmed, xml_tree)
+
+        obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")
+
+        self.assertEqual(obtained, expected)
+
+    def test_xml_pubmed_coi_statement(self):
+        expected = (
+            '<Article>'
+            '<CoiStatement>Não há conflito de interesse entre os autores do artigo.</CoiStatement>'
+            '</Article>'
+        )
+        xml_pubmed = ET.fromstring(
+            '<Article/>'
+        )
+        xml_tree = ET.fromstring(
+            '<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
+            'xmlns:xlink="http://www.w3.org/1999/xlink" '
+            'article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="pt">'
+            '<front>'
+            '<article-meta>'
+            '<author-notes>'
+            '<fn fn-type="coi-statement">'
+            '<label>Conflito de Interesses</label>'
+            '<p>Não há conflito de interesse entre os autores do artigo.</p>'
+            '</fn>'
+            '</author-notes>'
+            '</article-meta>'
+            '</front>'
+            '</article>'
+        )
+
+        xml_pubmed_coi_statement(xml_pubmed, xml_tree)
+
+        obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")
+
+        self.assertEqual(obtained, expected)
+
+    def test_xml_pubmed_coi_statement_without_fn(self):
+        expected = (
+            '<Article/>'
+        )
+        xml_pubmed = ET.fromstring(
+            '<Article/>'
+        )
+        xml_tree = ET.fromstring(
+            '<article xmlns:mml="http://www.w3.org/1998/Math/MathML" '
+            'xmlns:xlink="http://www.w3.org/1999/xlink" '
+            'article-type="research-article" dtd-version="1.1" specific-use="sps-1.9" xml:lang="en">'
+            '<front>'
+            '<article-meta>'
+            '<author-notes>'
+            '</author-notes>'
+            '</article-meta>'
+            '</front>'
+            '</article>'
+        )
+
+        xml_pubmed_coi_statement(xml_pubmed, xml_tree)
+
+        obtained = ET.tostring(xml_pubmed, encoding="utf-8").decode("utf-8")
+
+        self.assertEqual(obtained, expected)
+
     def test_xml_pubmed_object_list_keyword(self):
         expected = (
             '<Article>'