feat: cff to doi parser (#107)

* chore: update py version to match pkg description

* feat(parsers): add cff->doi parser

* refactor: register cff parser

* test(cff): add doctests for cff->doi parsing

* fix(cff): combine re flags with OR

* fix(parsers): use .decode() for bytes->str

* fix: restrict cff parsing to root dir

gimie/parsers/__init__.py

@@ -22,6 +22,7 @@
 from gimie.io import Resource
 from gimie.parsers.abstract import Parser
 from gimie.parsers.license import LicenseParser, is_license_filename
+from gimie.parsers.cff import CffParser
 
 
 class ParserInfo(NamedTuple):
@@ -31,6 +32,7 @@ class ParserInfo(NamedTuple):
 
 PARSERS = {
     "license": ParserInfo(default=True, type=LicenseParser),
+    "cff": ParserInfo(default=True, type=CffParser),
 }
 
 
@@ -69,9 +71,11 @@ def select_parser(
     parsers:
         A set of parser names. If None, use the default collection.
     """
-    # Only parse licenses in the root directory
+    # Only parse licenses and citations in the root directory
     if is_license_filename(path.name) and len(path.parts) == 1:
         name = "license"
+    elif path.name == "CITATION.cff" and len(path.parts) == 1:
+        name = "cff"
     else:
         return None
 

gimie/parsers/cff.py

@@ -0,0 +1,72 @@
+# Gimie
+# Copyright 2022 - Swiss Data Science Center (SDSC)
+# A partnership between École Polytechnique Fédérale de Lausanne (EPFL) and
+# Eidgenössische Technische Hochschule Zürich (ETHZ).
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from io import BytesIO
+import re
+from typing import List, Optional, Set
+
+from rdflib.term import URIRef
+
+from gimie.graph.namespaces import SDO
+from gimie.parsers.abstract import Parser, Property
+
+
+class CffParser(Parser):
+    """Parse cff file to extract the doi into schema:citation <doi>."""
+
+    def __init__(self):
+        super().__init__()
+
+    def parse(self, data: bytes) -> Set[Property]:
+        """Extracts a DOI link from a CFF file and returns a
+        set with a single tuple <schema:citation> <doi>.
+        If no DOI is found, an empty set is returned.
+        """
+        props = set()
+        doi = get_cff_doi(data)
+
+        if doi:
+            props.add((SDO.citation, URIRef(doi)))
+        return props
+
+
+def get_cff_doi(data: bytes) -> Optional[str]:
+    """Given a CFF file, returns the DOI, if any.
+
+    Parameters
+    ----------
+    data:
+        The cff file body as bytes.
+
+    Examples
+    --------
+    >>> get_cff_doi(bytes("doi:   10.5281/zenodo.1234", encoding="utf8"))
+    '10.5281/zenodo.1234'
+    >>> get_cff_doi(bytes("abc: def", encoding="utf8"))
+
+    """
+
+    matches = re.search(
+        r"^doi: *(.*)$",
+        data.decode(),
+        flags=re.IGNORECASE | re.MULTILINE,
+    )
+    try:
+        doi = matches.groups()[0]
+    except AttributeError:
+        doi = None
+
+    return doi

gimie/parsers/license/__init__.py

@@ -66,7 +66,7 @@ def match_license(data: bytes, min_similarity: float = 0.9) -> Optional[str]:
     """
     # Compute tfidf vector for input license
     vectorizer = load_tfidf_vectorizer()
-    input_vec = vectorizer.transform([str(data)])
+    input_vec = vectorizer.transform([data.decode()])
 
     # Load ids and tfidf vectors for spdx licenses
     spdx_licenses = load_spdx_ids()

pyproject.toml

@@ -24,7 +24,7 @@ classifiers = [
 # Dependency management
 
 [tool.poetry.dependencies]
-python = ">=3.9,<=3.11"
+python = ">=3.9,<=3.12"
 gitpython = ">=3.1.35"
 PyDriller = "^2.5"
 pyshacl = "^0.20.0"