extract zenodo doi from readme.rst. Issue 1062 partially solved

src/somef/regular_expressions.py

@@ -711,26 +711,34 @@ def extract_doi_badges(readme_text, repository_metadata: Result, source) -> Resu
         else:
             match = re.search(constants.REGEXP_ZENODO_DOI, readme_text)
             if match:
-                badge_url = match.group(0)
+                # badge_url = match.group(0)
+                badge_url = f"https://doi.org/{match.group(1)}"
         try:
             if badge_url is not None:
-                response = requests.get(badge_url, allow_redirects=True, timeout=10)
-                match = re.search(constants.REGEXP_ZENODO_JSON_LD,
-                    response.text,
-                    re.DOTALL | re.IGNORECASE
-                )
-                if match:
-                    json_ld_text = match.group(1).strip()
-                    try:
-                        json_ld_data = json.loads(json_ld_text)
-                        identifier = json_ld_data.get('identifier')
-                        repository_metadata.add_result(constants.CAT_IDENTIFIER,
-                            {
-                                constants.PROP_TYPE: constants.URL,
-                                constants.PROP_VALUE: identifier,
-                            }, 1, constants.TECHNIQUE_REGULAR_EXPRESSION, source)
-                    except json.JSONDecodeError:
-                        logging.warning("Error parsing Zenodo JSON-LD")
+                if badge_url.startswith("https://doi.org/"):
+                    repository_metadata.add_result(constants.CAT_IDENTIFIER,
+                        {
+                            constants.PROP_TYPE: constants.URL,
+                            constants.PROP_VALUE: badge_url,
+                        }, 1, constants.TECHNIQUE_REGULAR_EXPRESSION, source)
+                else:
+                    response = requests.get(badge_url, allow_redirects=True, timeout=10)
+                    match = re.search(constants.REGEXP_ZENODO_JSON_LD,
+                        response.text,
+                        re.DOTALL | re.IGNORECASE
+                    )
+                    if match:
+                        json_ld_text = match.group(1).strip()
+                        try:
+                            json_ld_data = json.loads(json_ld_text)
+                            identifier = json_ld_data.get('identifier')
+                            repository_metadata.add_result(constants.CAT_IDENTIFIER,
+                                {
+                                    constants.PROP_TYPE: constants.URL,
+                                    constants.PROP_VALUE: identifier,
+                                }, 1, constants.TECHNIQUE_REGULAR_EXPRESSION, source)
+                        except json.JSONDecodeError:
+                            logging.warning("Error parsing Zenodo JSON-LD")
         except requests.RequestException as e:
             logging.warning(f"Error fetching DOI from Zenodo badge: {e}")
     else:

src/somef/test/test_data/README-gammapy.rst

@@ -0,0 +1,103 @@
+.. image:: https://anaconda.org/conda-forge/gammapy/badges/license.svg
+   :target: https://github.com/gammapy/gammapy/blob/main/LICENSE.rst
+   :alt: Licence
+
+.. image:: http://img.shields.io/badge/powered%20by-AstroPy-orange.svg?style=flat
+   :target: http://www.astropy.org/
+
+|
+
+.. image:: https://anaconda.org/conda-forge/gammapy/badges/platforms.svg
+   :target: https://anaconda.org/conda-forge/gammapy
+
+|
+
+.. image:: http://img.shields.io/pypi/v/gammapy.svg?text=version
+   :target: https://pypi.org/project/gammapy/
+   :alt: Latest release
+
+.. image:: https://img.shields.io/pypi/dm/gammapy?label=downloads%20%7C%20pip&logo=PyPI
+   :alt: PyPI - Downloads
+
+.. image:: https://anaconda.org/conda-forge/gammapy/badges/version.svg
+   :target: https://anaconda.org/conda-forge/gammapy
+
+.. image:: https://img.shields.io/conda/dn/conda-forge/gammapy?label=downloads%20%7C%20conda&logo=Conda-Forge
+   :target: https://anaconda.org/conda-forge/gammapy
+
+.. image:: https://img.shields.io/badge/launch-binder-579aca.svg?logo=data:image/png;base64,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
+   :target: https://mybinder.org/v2/gh/gammapy/gammapy-webpage/master?urlpath=lab/tree/notebooks/
+
+|
+
+.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.4701488.svg?style=flat
+   :target: https://doi.org/10.5281/zenodo.4701488
+
+.. image:: https://archive.softwareheritage.org/badge/origin/https://github.com/gammapy/gammapy/
+   :target: https://archive.softwareheritage.org/browse/origin/?origin_url=https://github.com/gammapy/gammapy
+
+|
+
+.. image:: https://img.shields.io/badge/A&A-Published-Green.svg
+   :target: https://doi.org/10.1051/0004-6361/202346488
+
+|
+
+.. image:: https://img.shields.io/badge/Matomo-3152A0?style=for-the-badge&logo=Matomo&logoColor=white
+   :target: https://matomo.org/
+
+Gammapy
+=======
+
+A Python Package for Gamma-ray Astronomy.
+
+Gammapy is an open-source Python package for gamma-ray astronomy built on Numpy, Scipy and Astropy. It is used as core
+library for the Science Analysis tools of the CTAO, recommended by the H.E.S.S.
+collaboration to be used for Science publications, and is already widely used in the analysis of existing gamma-ray
+instruments, such as MAGIC, VERITAS and HAWC.
+
+* Webpage: https://gammapy.org
+* Documentation: https://docs.gammapy.org/
+* Code: https://github.com/gammapy/gammapy
+
+Contributing Code, Documentation, or Feedback
++++++++++++++++++++++++++++++++++++++++++++++
+The Gammapy Project is made both by and for its users, so we welcome and encourage contributions of many kinds. Our
+goal is to keep this a positive, inclusive, successful, and growing community by abiding with the
+`Gammapy Community Code of Conduct <https://gammapy.org/CoC.html>`_.
+
+The Gammapy project uses a mechanism known as a `Developer Certificate of Origin` (DCO). The DCO is a binding statement
+that asserts that you are the creator of your contribution, and that you wish to allow Gammapy to use your work to cite
+you as contributor. More detailed information on contributing to the project or submitting feedback can be found on the
+`Contributing page <https://github.com/gammapy/gammapy/blob/main/CONTRIBUTING.md>`_.
+
+Licence
++++++++
+Gammapy is licensed under a 3-clause BSD style license - see the
+`LICENSE.rst <https://github.com/gammapy/gammapy/blob/main/LICENSE.rst>`_ file.
+
+The Gammapy documentation is licensed under the `CC BY-NC-SA <https://creativecommons.org/licenses/by-nc-sa/4.0/>`_
+license. Examples, recipes, and other code in the documentation are additionally licensed under the
+`BSD 3-Clause "New" or "Revised" <https://opensource.org/license/BSD-3-Clause>`_ license.
+
+Supporting the project
+++++++++++++++++++++++
+The Gammapy project is not sponsored and the development is made by the staff of `the institutes supporting the project
+<https://gammapy.org/team.html#support>`_ over their research time. Any contribution is then encouraged, as punctual or
+regular contributor.
+
+Status shields
+++++++++++++++
+
+(mostly useful for developers)
+
+* .. image:: https://app.codacy.com/project/badge/Grade/9c32a21a915d4a28823f3b44a99a2810
+    :target: https://app.codacy.com/gh/gammapy/gammapy/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade
+    :alt: Codacy
+
+* .. image:: https://github.com/gammapy/gammapy/actions/workflows/ci.yml/badge.svg
+    :target: https://github.com/gammapy/gammapy/actions/workflows/ci.yml
+    :alt: GitHub actions CI
+
+* .. image:: https://codecov.io/gh/gammapy/gammapy/branch/main/graph/badge.svg?style=flat
+    :target: https://codecov.io/gh/gammapy/gammapy

src/somef/test/test_regular_expressions.py

@@ -600,4 +600,20 @@ def test_repo_status_issue_1014(self):
             assert len(status) == 1, f"Should be 1 status, but got {len(status)}"
             extracted_url = status[0]['result']['value']
             expected_url = "https://www.repostatus.org/#active"
-            self.assertEqual(extracted_url, expected_url)
+            self.assertEqual(extracted_url, expected_url)
+
+
+    def test_issue_1062(self):
+        """A Zenodo DOI badge in an rst README yields the exact DOI from the badge,
+        not the latest version's DOI."""
+        with open(test_data_path + "README-gammapy.rst", "r") as data_file:
+            test_text = data_file.read()
+            identifiers = regular_expressions.extract_doi_badges(test_text, Result(),
+                                                test_data_path + "README-gammapy.rst")
+            doi_values = []
+            if "identifier" in identifiers.results:
+                for result in identifiers.results["identifier"]:
+                    if "result" in result and "value" in result["result"]:
+                        doi_values.append(result["result"]["value"])
+            assert doi_values == ["https://doi.org/10.5281/zenodo.4701488"], \
+                f"Expected the exact badge DOI, got {doi_values}"

src/somef/utils/constants.py

@@ -100,7 +100,8 @@
 # Detect zenodo latest doi in readme. 
 ZENODO_API_BASE = "https://zenodo.org/api"
 REGEXP_ZENODO_LATEST_DOI = r':target:\s*(https://zenodo\.org/badge/latestdoi/\d+)'
-REGEXP_ZENODO_DOI = r'https://zenodo\.org/badge/DOI/\d+'
+# REGEXP_ZENODO_DOI = r'https://zenodo\.org/badge/DOI/\d+'
+REGEXP_ZENODO_DOI = r'https://zenodo\.org/badge/DOI/(10\.\d{4,9}/zenodo\.\d+)'
 REGEXP_ZENODO_JSON_LD = r"<script[^>]*type=['\"]application/ld\+json['\"][^>]*>(.*?)</script>"
 
 # Detect copyright information in license files.