fix: tests for cff, add test for doi, move doi and orcid matchers to …

…utils

gimie/parsers/cff.py

@@ -24,6 +24,7 @@
 from gimie import logger
 from gimie.graph.namespaces import SDO, MD4I
 from gimie.parsers.abstract import Parser
+from gimie.utils.uri import is_valid_orcid, valid_doi_match_extractor
 
 
 class CffParser(Parser):
@@ -52,9 +53,7 @@ def parse(self, data: bytes) -> Graph:
             return extracted_cff_triples
         for author in authors:
             orcid = URIRef(author["orcid"])
-            if re.match(
-                r"https:\/\/orcid.org\/\d{4}-\d{4}-\d{4}-\d{4}", str(orcid)
-            ):
+            if is_valid_orcid(orcid):
                 extracted_cff_triples.add(
                     (self.subject, SDO.author, URIRef(orcid))
                 )
@@ -114,9 +113,7 @@ def doi_to_url(doi: str) -> str:
 
     # regex from:
     # https://www.crossref.org/blog/dois-and-matching-regular-expressions
-    doi_match = re.search(
-        r"10.\d{4,9}/[-._;()/:A-Z0-9]+$", doi, flags=re.IGNORECASE
-    )
+    doi_match = valid_doi_match_extractor(doi)
 
     if doi_match is None:
         raise ValueError(f"Not a valid DOI: {doi}")

gimie/utils/uri.py

@@ -18,6 +18,7 @@
 
 from typing import List, Literal
 from urllib.parse import urlparse
+import re
 
 from gimie.graph.namespaces import GIMIE
 
@@ -64,3 +65,62 @@ def generate_uri(ref: str):
     'https://sdsc-ordes.github.io/gimie/abc'
     """
     return str(GIMIE[ref])
+
+
+def is_valid_orcid(orcid):
+    """Check if the input is a valid ORCID according to definition from orcid.org [1]_.
+    .. [1] [https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier](https://support.orcid.org/hc/en-us/articles/360006897674-Structure-of-the-ORCID-Identifier)
+
+    Parameters
+    ----------
+    orcid:
+        The ORCID to validate.
+
+    Returns
+    -------
+    bool:
+        True if the ORCID is valid, False otherwise.
+
+    Examples
+    --------
+    >>> is_valid_orcid("https://orcid.org/0000-0001-2345-6789")
+    True
+    >>> is_valid_orcid("0000-0001-2345-6789")
+    False
+    >>> is_valid_orcid("http://orcid.org/0000-0001-2345-6789")
+    False
+
+    """
+    return bool(
+        re.match(
+            r"(https:\/\/)?orcid.org\/\d{4}-\d{4}-\d{4}-\d{4}", str(orcid)
+        )
+    )
+
+
+def valid_doi_match_extractor(doi):
+    """Extracts doi from the input if it contains a valid DOI according to definition from crossref.org [1]_.
+    .. [1] [https://www.crossref.org/blog/dois-and-matching-regular-expressions](https://www.crossref.org/blog/dois-and-matching-regular-expressions)
+
+    Parameters
+    ----------
+    doi:
+        The DOI to validate.
+
+    Returns
+    -------
+    bool:
+        True if the DOI is valid, False otherwise.
+
+    Examples
+    --------
+    >>> is_valid_doi("10.0000/example.abcd")
+    True
+    >>> is_valid_doi("doi.org/10.0000/example.abcd")
+    False
+    >>> is_valid_doi("https://doi.org/10.0000/example.abcd")
+    False
+    """
+    return re.search(
+        r"10.\d{4,9}/[-._;()/:A-Z0-9]+$", doi, flags=re.IGNORECASE
+    )

tests/test_cff.py

@@ -1,5 +1,7 @@
 from gimie.io import LocalResource
+from gimie.parsers import CffParser
 from gimie.parsers.cff import get_cff_authors
+from rdflib import URIRef
 
 
 def test_parse_cff():
@@ -8,3 +10,76 @@ def test_parse_cff():
         cff_content = f.read()
     authors = get_cff_authors(cff_content)
     assert authors is not None
+
+
+def test_broken_cff():
+    cff_file_emptyish = b"""
+    cff-version: 1.2.0
+    message: "This is a CFF devoid authors or DOI"
+    """
+    cff_file_bad_syntax = b"""
+    cff-version: 1.2.0
+    title: gimie :
+    authors:
+      family-names: Doe
+        given-names: John
+        - family-names: Smith
+    given-names:
+    Jane
+        orcid: 0000-0001-2345-6789
+    """
+    cff_file_broken_orcid = b"""
+    cff-version: 1.2.0
+    title: gimie
+    authors:
+      - family-names: Doe
+        given-names: John
+        orcid: 0000-0001-2345-6789
+      - family-names: Smith
+        given-names: Jane
+        orcid: http://www.orcid.org/0000-0001-2345-6789
+    """
+    cff_file_author_without_orcid = b"""
+    cff-version: 1.2.0
+    title: gimie
+    authors:
+      - family-names: Doe
+        given-names: John
+    """
+
+    # empty graph = \n according to rdflib
+    assert (
+        CffParser(subject=URIRef("https://example.org/"))
+        .parse(data=cff_file_emptyish)
+        .serialize(format="ttl")
+        == "\n"
+    )
+    assert (
+        CffParser(subject=URIRef("https://example.org/"))
+        .parse(data=cff_file_bad_syntax)
+        .serialize(format="ttl")
+        == "\n"
+    )
+    assert (
+        CffParser(subject=URIRef("https://example.org/"))
+        .parse(data=cff_file_broken_orcid)
+        .serialize(format="ttl")
+        == "\n"
+    )
+    assert (
+        CffParser(subject=URIRef("https://example.org/"))
+        .parse(data=cff_file_author_without_orcid)
+        .serialize(format="ttl")
+        == "\n"
+    )
+
+
+def test_doi():
+    cff_file = b"""
+    cff-version: 1.2.0
+    title: gimie
+    doi: 10.5281/zenodo.1234567
+    """
+    assert "https://doi.org/10.5281/zenodo.1234567" in CffParser(
+        subject=URIRef("https://example.org/")
+    ).parse(data=cff_file).serialize(format="ttl")