add replace_curie function

Author: mfenner

commonmeta/__init__.py

@@ -10,7 +10,7 @@
 """
 
 __title__ = "commonmeta-py"
-__version__ = "0.74"
+__version__ = "0.75"
 __author__ = "Martin Fenner"
 __license__ = "MIT"
 

commonmeta/utils.py

@@ -1116,16 +1116,33 @@ def extract_curie(string: Optional[str]) -> Optional[str]:
     """Extract CURIE"""
     if string is None:
         return None
-    match = re.search(r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    match = re.search(
+        r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string
+    )
     if match is None:
         return None
     return doi_as_url(match.group(2))
 
-    
+
+def replace_curie(string: Optional[str]) -> Optional[str]:
+    """Replace CURIE with DOI expressed as URL"""
+    if string is None:
+        return None
+    match = re.sub(
+        r"((?:doi|DOI):\s?([\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", r'https://doi.org/\2', string
+    )
+    if match is None:
+        return None
+    return match
+
+
 def extract_url(string: str) -> list:
     """Extract urls from string, including markdown and html."""
 
-    match = re.search(r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    match = re.search(
+        r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))",
+        string,
+    )
     if match is None:
         return None
     return normalize_url(match.group(1))
@@ -1134,7 +1151,10 @@ def extract_url(string: str) -> list:
 def extract_urls(string: str) -> list:
     """Extract urls from string, including markdown and html."""
 
-    urls = re.findall(r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))", string)
+    urls = re.findall(
+        r"((?:http|https):\/\/(?:[\w_-]+(?:(?:\.[\w_-]+)+))(?:[\w.,@?^=%&:\/~+#-]*[\w@?^=%&\/~+#-]))",
+        string,
+    )
     return py_.uniq(urls)
 
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "commonmeta-py"
-version = "0.74"
+version = "0.75"
 description = "Library for conversions to/from the Commonmeta scholarly metadata format"
 authors = [{ name = "Martin Fenner", email = "[email protected]" }]
 requires-python = ">=3.9,<4.0"

tests/test-utils.py

@@ -40,6 +40,7 @@
     github_as_repo_url,
     from_curie,
     extract_curie,
+    replace_curie,
     get_language,
     validate_url,
     format_name_identifier,
@@ -815,6 +816,7 @@ def test_from_curie():
         "ISNI:0000000121099845"
     )
 
+
 def test_extract_curie():
     """extract_curie"""
     string = """Melstrom, Keegan M., Michael D. D’Emic, Daniel Chure and Jeffrey A.
@@ -835,14 +837,31 @@ def test_extract_curie_doi_space():
     assert "https://doi.org/10.1080/02724634.2016.1111898" == extract_curie(string)
 
 
+def test_replace_curie():
+    """replace_curie"""
+    string = """Melstrom, Keegan M., Michael D. D’Emic, Daniel Chure and Jeffrey A.
+Wilson. 2016. A juvenile sauropod dinosaur from the Late Jurassic of
+Utah, USA, presents further evidence of an avian style air-sac
+system. Journal of Vertebrate Paleontology 36(4):e1111898. doi:10.1080/02724634.2016.1111898"""
+    assert """Melstrom, Keegan M., Michael D. D’Emic, Daniel Chure and Jeffrey A.
+Wilson. 2016. A juvenile sauropod dinosaur from the Late Jurassic of
+Utah, USA, presents further evidence of an avian style air-sac
+system. Journal of Vertebrate Paleontology 36(4):e1111898. https://doi.org/10.1080/02724634.2016.1111898""" == replace_curie(string)
+
+
 def test_extract_urls():
     """extract_urls"""
     string = """Zauner, H. (2025, January 9). Sex chromosome madness in the iconic echidna. GigaBlog. https://doi.org/10.59350/9509z-ns663
 
 Willighagen, E. (2024, December 30). FAIR blog-to-blog citations. Chem-Bla-Ics. https://doi.org/10.59350/er1mn-m5q69
 
 Marcum, C. S. (2024, August 27). Drinking from the Firehose? Write More and Publish Less. Upstream. https://doi.org/10.54900/r8zwg-62003"""
-    assert ['https://doi.org/10.59350/9509z-ns663','https://doi.org/10.59350/er1mn-m5q69','https://doi.org/10.54900/r8zwg-62003',] == extract_urls(string)
+    assert [
+        "https://doi.org/10.59350/9509z-ns663",
+        "https://doi.org/10.59350/er1mn-m5q69",
+        "https://doi.org/10.54900/r8zwg-62003",
+    ] == extract_urls(string)
+
 
 def test_extract_urls_markdown():
     """extract_urls markdown"""
@@ -854,12 +873,21 @@ def test_extract_urls_markdown():
 
 Marcum, C. S. (2024, August 27). Drinking from the Firehose? Write More
 and Publish Less. *Upstream*. <https://doi.org/10.54900/r8zwg-62003>"""
-    assert ['https://doi.org/10.59350/9509z-ns663', 'https://doi.org/10.59350/er1mn-m5q69', 'https://doi.org/10.54900/r8zwg-62003'] == extract_urls(string)
+    assert [
+        "https://doi.org/10.59350/9509z-ns663",
+        "https://doi.org/10.59350/er1mn-m5q69",
+        "https://doi.org/10.54900/r8zwg-62003",
+    ] == extract_urls(string)
+
 
 def test_extract_urls_html():
     """extract_urls html"""
     string = """<p>Zauner, H. (2025, January 9). Sex chromosome madness in the iconic echidna. <em>GigaBlog</em>. <a href="https://doi.org/10.59350/9509z-ns663">https://doi.org/10.59350/9509z-ns663</a></p><p>Willighagen, E. (2024, December 30). FAIR blog-to-blog citations. <em>Chem-Bla-Ics</em>. <a href="https://doi.org/10.59350/er1mn-m5q69">https://doi.org/10.59350/er1mn-m5q69</a></p><p>Marcum, C. S. (2024, August 27). Drinking from the Firehose? Write More and Publish Less. <em>Upstream</em>. <a href="https://doi.org/10.54900/r8zwg-62003">https://doi.org/10.54900/r8zwg-62003</a></p>"""
-    assert ['https://doi.org/10.59350/9509z-ns663', 'https://doi.org/10.59350/er1mn-m5q69', 'https://doi.org/10.54900/r8zwg-62003'] == extract_urls(string)
+    assert [
+        "https://doi.org/10.59350/9509z-ns663",
+        "https://doi.org/10.59350/er1mn-m5q69",
+        "https://doi.org/10.54900/r8zwg-62003",
+    ] == extract_urls(string)
 
 
 def test_id_from_url():