pymetadata 0.5.5__tar.gz → 0.5.7__tar.gz

{pymetadata-0.5.5 → pymetadata-0.5.7}/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.5.5"
+current_version = "0.5.7"
 commit = true
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]

{pymetadata-0.5.5 → pymetadata-0.5.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pymetadata
-Version: 0.5.5
+Version: 0.5.7
 Summary: pymetadata are python utilities for working with metadata.
 Author-email: Matthias König <konigmatt@googlemail.com>
 Maintainer-email: Matthias König <konigmatt@googlemail.com>
@@ -53,9 +53,9 @@ metadata in the context of COMBINE standards with source code available from
 
 Features include among others
 
-- [core](src/pymetadata/core)COMBINE archive version 1 support (OMEX)
+- COMBINE archive version 1 support (OMEX)
 - annotation classes and helpers
-- SBO and KISAO ontology enums
+- SBO, KISAO and ECO ontology enums
 
 If you have any questions or issues please [open an issue](https://github.com/matthiaskoenig/pymetadata/issues).
 
@@ -66,8 +66,6 @@ see [omex_example.py](src/pymetadata/examples/omex_example.py).
 # How to cite
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5308801.svg)](https://doi.org/10.5281/zenodo.5308801)
 
-# Contributing
-Contributions are always welcome! Please read the [contributing guidelines](https://github.com/matthiaskoenig/pymetadata/blob/develop/.github/CONTRIBUTING.rst) to get started.
 
 # License
 - Source Code: [MIT](https://opensource.org/license/MIT)
@@ -84,19 +82,6 @@ can be installed via
 pip install pymetadata
 ```
 
-## Develop version
-The latest develop version can be installed via
-```bash
-pip install git+https://github.com/matthiaskoenig/pymetadata.git@develop
-```
-
-Or via cloning the repository and installing via
-```bash
-git clone https://github.com/matthiaskoenig/pymetadata.git
-cd pymetadata
-pip install -e .
-```
-
 # Cache path
 `pymetadata` caches some information for faster retrieval. The cache path is set to
 

{pymetadata-0.5.5 → pymetadata-0.5.7}/README.md

@@ -13,9 +13,9 @@ metadata in the context of COMBINE standards with source code available from
 
 Features include among others
 
-- [core](src/pymetadata/core)COMBINE archive version 1 support (OMEX)
+- COMBINE archive version 1 support (OMEX)
 - annotation classes and helpers
-- SBO and KISAO ontology enums
+- SBO, KISAO and ECO ontology enums
 
 If you have any questions or issues please [open an issue](https://github.com/matthiaskoenig/pymetadata/issues).
 
@@ -26,8 +26,6 @@ see [omex_example.py](src/pymetadata/examples/omex_example.py).
 # How to cite
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5308801.svg)](https://doi.org/10.5281/zenodo.5308801)
 
-# Contributing
-Contributions are always welcome! Please read the [contributing guidelines](https://github.com/matthiaskoenig/pymetadata/blob/develop/.github/CONTRIBUTING.rst) to get started.
 
 # License
 - Source Code: [MIT](https://opensource.org/license/MIT)
@@ -44,19 +42,6 @@ can be installed via
 pip install pymetadata
 ```
 
-## Develop version
-The latest develop version can be installed via
-```bash
-pip install git+https://github.com/matthiaskoenig/pymetadata.git@develop
-```
-
-Or via cloning the repository and installing via
-```bash
-git clone https://github.com/matthiaskoenig/pymetadata.git
-cd pymetadata
-pip install -e .
-```
-
 # Cache path
 `pymetadata` caches some information for faster retrieval. The cache path is set to
 

pymetadata-0.5.7/release-notes/0.5.6.md

@@ -0,0 +1,10 @@
+# Release notes for pymetadata 0.5.6
+![pymetadata](https://github.com/matthiaskoenig/pymetadata/raw/develop/docs/images/favicon/pymetadata-100x100-300dpi.png)
+
+We are pleased to release the next version of pymetadata including the
+following changes:
+
+## Features & fixes
+- bugfix compact ids when id starts with namespace
+
+Your pymetadata team

pymetadata-0.5.7/release-notes/0.5.7.md

@@ -0,0 +1,10 @@
+# Release notes for pymetadata 0.5.7
+![pymetadata](https://github.com/matthiaskoenig/pymetadata/raw/develop/docs/images/favicon/pymetadata-100x100-300dpi.png)
+
+We are pleased to release the next version of pymetadata including the
+following changes:
+
+## Features & fixes
+- bugfix for doi of the form https://identifiers.org/DOI:10.1016/j.jtbi.2004.04.039
+
+Your pymetadata team

{pymetadata-0.5.5 → pymetadata-0.5.7}/src/pymetadata/__init__.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 
 __author__ = "Matthias Koenig"
-__version__ = "0.5.5"
+__version__ = "0.5.7"
 
 
 program_name: str = "pymetadata"

{pymetadata-0.5.5 → pymetadata-0.5.7}/src/pymetadata/core/annotation.py

@@ -22,8 +22,12 @@ from pymetadata.ontologies.ols import ONTOLOGIES, OLSQuery
 OLS_QUERY = OLSQuery(ontologies=ONTOLOGIES)
 
 IDENTIFIERS_ORG_PREFIX: Final = "https://identifiers.org"
-IDENTIFIERS_ORG_PATTERN1: Final = re.compile(r"^https?://identifiers.org/(.+?)/(.+)")
-IDENTIFIERS_ORG_PATTERN2: Final = re.compile(r"^https?://identifiers.org/(.+)")
+IDENTIFIERS_ORG_PATTERN_COMPACT: Final = re.compile(
+    r"^https?://identifiers.org/([a-zA-Z0-9.]+):(.+)"
+)
+IDENTIFIERS_ORG_PATTERN_CLASSIC: Final = re.compile(
+    r"^https?://identifiers.org/([a-zA-Z0-9.]+)/(.+)"
+)
 
 BIOREGISTRY_PREFIX: Final = "https://bioregistry.io"
 BIOREGISTRY_PATTERN: Final = re.compile(r"^https?://bioregistry.io/(.+)")
@@ -62,7 +66,9 @@ class RDFAnnotation:
         "biomodels.sbo": "sbo",
     }
 
-    def __init__(self, qualifier: Union[BQB, BQM], resource: str):
+    def __init__(
+        self, qualifier: Union[BQB, BQM], resource: str, validate: bool = True
+    ):
         """Initialize RDFAnnotation."""
         self.qualifier: Union[BQB, BQM] = qualifier
         self.collection: Optional[str] = None
@@ -87,28 +93,19 @@ class RDFAnnotation:
 
         # handle urls
         if resource.startswith("http"):
-            match1 = IDENTIFIERS_ORG_PATTERN1.match(resource)
-            if match1:
-                # handle identifiers.org pattern
-                self.collection, self.term = match1.group(1), match1.group(2)
+            # tests new compact patterns
+            match_compact = IDENTIFIERS_ORG_PATTERN_COMPACT.match(resource)
+            if match_compact:
+                self.collection = match_compact.group(1).lower()
+                self.term = f"{match_compact.group(1)}:{match_compact.group(2)}"
                 self.provider = ProviderType.IDENTIFIERS_ORG
 
             if not self.collection:
-                # tests new compact patterns
-                match2 = IDENTIFIERS_ORG_PATTERN2.match(resource)
-                if match2:
-                    tokens = match2.group(1).split(":")
-                    if len(tokens) == 2:
-                        self.collection = tokens[0].lower()
-
-                        # check if the namespace is embedded
-                        self.term = match2.group(1)
-                        self.provider = ProviderType.IDENTIFIERS_ORG
-                    else:
-                        logger.warning(
-                            f"Identifiers.org URL does not conform to new"
-                            f"short pattern: {resource}"
-                        )
+                match_classic = IDENTIFIERS_ORG_PATTERN_CLASSIC.match(resource)
+                if match_classic:
+                    self.collection = match_classic.group(1).lower()
+                    self.term = match_classic.group(2)
+                    self.provider = ProviderType.IDENTIFIERS_ORG
 
             if not self.collection:
                 # other urls are directly stored as resources without collection
@@ -119,7 +116,7 @@ class RDFAnnotation:
                     console.print(self.provider)
                 else:
                     self.provider = ProviderType.NONE
-                    logger.warning(
+                    logger.debug(
                         f"{resource} does not conform to "
                         f"http(s)://identifiers.org/collection/id or http(s)://identifiers.org/id or "
                         f"https://bioregistry.io/id .",
@@ -173,7 +170,8 @@ class RDFAnnotation:
         if self.collection in self.replaced_collections:
             self.collection = self.replaced_collections[self.collection]
 
-        self.validate()
+        if validate:
+            self.validate()
 
     @staticmethod
     def shorten_compact_term(term: str, collection: str) -> str:
@@ -184,7 +182,7 @@ class RDFAnnotation:
         namespace = REGISTRY.ns_dict.get(collection, None)
         if namespace and not namespace.namespaceEmbeddedInLui:
             # shorter term
-            if term.lower().startswith(collection):
+            if term.lower().startswith(f"{collection}:"):
                 tokens = term.split(":")
                 term = ":".join(tokens[1:])
 
@@ -242,15 +240,14 @@ class RDFAnnotation:
         m = p.match(term)
         if not m:
             logger.error(
-                f"Term `{term}` did not match pattern "
-                f"`{namespace.pattern}` for collection `{collection}`."
+                f"Term `{term}` did not match pattern `{namespace.pattern}` for collection `{collection}`."
             )
             return False
 
         return True
 
     @staticmethod
-    def check_qualifier(qualifier: Union[BQB, BQM]) -> None:
+    def check_qualifier(qualifier: Union[BQB, BQM]) -> bool:
         """Check that the qualifier is an allowed qualifier.
 
         :param qualifier:
@@ -259,17 +256,23 @@ class RDFAnnotation:
         if not isinstance(qualifier, (BQB, BQM)):
             supported_qualifiers = [e.value for e in BQB] + [e.value for e in BQM]
 
-            raise ValueError(
-                f"qualifier `{qualifier}` is not in supported qualifiers: "
-                f"`{supported_qualifiers}`"
+            logger.error(
+                f"qualifier `{qualifier}` is not in supported qualifiers: '{supported_qualifiers}'."
             )
+            return False
 
-    def validate(self) -> None:
+        return True
+
+    def validate(self) -> bool:
         """Validate annotation."""
+        valid_qualifier: bool = False
         if self.qualifier:
-            self.check_qualifier(self.qualifier)
+            valid_qualifier = self.check_qualifier(self.qualifier)
+        valid_term: bool = True
         if self.collection and self.term:
-            self.check_term(collection=self.collection, term=self.term)
+            valid_term = self.check_term(collection=self.collection, term=self.term)
+
+        return valid_qualifier and valid_term
 
 
 class RDFAnnotationData(RDFAnnotation):
@@ -399,10 +402,18 @@ if __name__ == "__main__":
     for annotation in [
         RDFAnnotation(
             qualifier=BQB.IS_VERSION_OF,
-            resource="https://bioregistry.io/chebi:15996",
+            resource="https://identifiers.org/DOI:10.1016/j.jtbi.2004.04.039",
         ),
         # RDFAnnotation(
         #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="hmdb/HMDB0000122",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="https://bioregistry.io/chebi:15996",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
         #     resource="NCIT:C75913",
         # ),
         # RDFAnnotation(

{pymetadata-0.5.5 → pymetadata-0.5.7}/tests/core/test_annotation.py

@@ -9,6 +9,11 @@ from pymetadata.identifiers.miriam import BQB, BQM
 
 
 rdf_annotation_data = [
+    (
+        BQB.IS,
+        "https://identifiers.org/DOI:10.1016/j.jtbi.2004.04.039",
+        "RDFAnnotation(BQB.IS|doi|10.1016/j.jtbi.2004.04.039|identifiers.org)",
+    ),
     (
         BQB.IS,
         "NCIT:C75913",
@@ -144,6 +149,16 @@ rdf_annotation_data = [
         "https://bioregistry.io/chebi:15996",
         "RDFAnnotation(BQB.IS|None|https://bioregistry.io/chebi:15996|bioregistry.io)",
     ),
+    (
+        BQB.IS,
+        "hmdb/HMDB0000122",
+        "RDFAnnotation(BQB.IS|hmdb|HMDB0000122|identifiers.org)",
+    ),
+    (
+        BQB.IS,
+        "hmdb:HMDB0000122",
+        "RDFAnnotation(BQB.IS|hmdb|HMDB0000122|identifiers.org)",
+    ),
 ]