Merge pull request #118 from Materials-Data-Science-and-Informatics/fix/author_list

Fix/author list

Author: mustafasoylu

.somesy.toml

@@ -1,6 +1,6 @@
 [project]
 name = "somesy"
-version = "0.7.2"
+version = "0.7.3"
 description = "A CLI tool for synchronizing software project metadata."
 keywords = ["metadata", "FAIR"]
 license = "MIT"
@@ -12,7 +12,7 @@ documentation = "https://materials-data-science-and-informatics.github.io/somesy
 family-names = "Soylu"
 given-names = "Mustafa"
 email = "m.soylu@fz-juelich.de"
-orcid = "https://orcid.org/0000-0003-2637-0432"
+orcid = "0000-0003-2637-0432"
 
 contribution = "Main developer, maintainer and tester."
 contribution_begin = "2023-03-01"
@@ -25,7 +25,7 @@ maintainer = true
 family-names = "Pirogov"
 given-names = "Anton"
 email = "a.pirogov@fz-juelich.de"
-orcid = "https://orcid.org/0000-0002-5077-7497"
+orcid = "0000-0002-5077-7497"
 
 contribution = "Concepts, tool development and enhancement, documentation."
 contribution_begin = "2023-03-01"
@@ -38,7 +38,7 @@ author = true
 family-names = "Bröder"
 given-names = "Jens"
 email = "j.broeder@fz-juelich.de"
-orcid = "https://orcid.org/0000-0001-7939-226X"
+orcid = "0000-0001-7939-226X"
 
 contribution = "Discussions and suggestions concerning metadata standards and usability."
 contribution_begin = "2023-03-01"
@@ -49,7 +49,7 @@ contribution_types = ["ideas"]
 family-names = "Hofmann"
 given-names = "Volker"
 email = "v.hofmann@fz-juelich.de"
-orcid = "https://orcid.org/0000-0002-5149-603X"
+orcid = "0000-0002-5149-603X"
 
 contribution = "Discussions and suggestions concerning tool scope and usability."
 contribution_begin = "2023-06-01"
@@ -62,7 +62,7 @@ publication_author = true
 family-names = "Sandfeld"
 given-names = "Stefan"
 email = "s.sandfeld@fz-juelich.de"
-orcid = "https://orcid.org/0000-0001-9560-4728"
+orcid = "0000-0001-9560-4728"
 
 contribution_types = ["fundingFinding"]
 

CHANGELOG.md

@@ -4,6 +4,14 @@ Here we provide notes that summarize the most important changes in each released
 
 Please consult the changelog to inform yourself about breaking changes and security issues.
 
+## [v0.7.3](https://github.com/Materials-Data-Science-and-Informatics/somesy/tree/v0.7.3) <small>(2025-03-14)</small> { id="0.7.3" }
+
+- accept orcid id as string without url
+- support multiline description in somesy input and outputs that enables multiline strings
+- dont save same person in available output formats
+- better toml inline table formatting
+- support only orcid id string (without the url)
+
 ## [v0.7.2](https://github.com/Materials-Data-Science-and-Informatics/somesy/tree/v0.7.2) <small>(2025-03-10)</small> { id="0.7.2" }
 
 - fix CITATION.CFF formatting

CITATION.cff

@@ -3,7 +3,7 @@ type: software
 message: If you use this software, please cite it using this metadata.
 
 title: somesy
-version: 0.7.2
+version: 0.7.3
 abstract: A CLI tool for synchronizing software project metadata.
 url: https://materials-data-science-and-informatics.github.io/somesy
 repository-code: https://github.com/Materials-Data-Science-and-Informatics/somesy

codemeta.json

@@ -27,7 +27,7 @@
   ],
   "name": "somesy",
   "description": "A CLI tool for synchronizing software project metadata.",
-  "version": "0.7.2",
+  "version": "0.7.3",
   "keywords": [
     "metadata",
     "FAIR"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "somesy"
-version = "0.7.2"
+version = "0.7.3"
 description = "A CLI tool for synchronizing software project metadata."
 readme = "README.md"
 keywords = [
@@ -33,15 +33,15 @@ dependencies = [
 ]
 
 authors = [
-    {name = "Mustafa Soylu",email = "m.soylu@fz-juelich.de"},
-    {name = "Anton Pirogov",email = "a.pirogov@fz-juelich.de"},
+    {name = "Mustafa Soylu", email = "m.soylu@fz-juelich.de"},
+    {name = "Anton Pirogov", email = "a.pirogov@fz-juelich.de"},
 ]
 maintainers = [
-    {name = "Mustafa Soylu",email = "m.soylu@fz-juelich.de"},
+    {name = "Mustafa Soylu", email = "m.soylu@fz-juelich.de"},
 ]
 
-
-license = {text = "MIT"}
+[project.license]
+text = "MIT"
 
 [project.urls]
 homepage = "https://materials-data-science-and-informatics.github.io/somesy"

src/somesy/cff/writer.py

@@ -6,6 +6,7 @@
 
 from cffconvert.cli.create_citation import create_citation
 from ruamel.yaml import YAML
+from ruamel.yaml.scalarstring import LiteralScalarString
 
 from somesy.core.models import Entity, Person, ProjectMetadata
 from somesy.core.writer import FieldKeyMapping, IgnoreKey, ProjectMetadataWriter
@@ -71,6 +72,14 @@ def _validate(self) -> None:
     def save(self, path: Optional[Path] = None) -> None:
         """Save the CFF object to a file."""
         path = path or self.path
+
+        # if description have new line characters, it should be saved as multiline string
+        if "abstract" in self._data:
+            if "\n" in self._data["abstract"]:
+                self._data["abstract"] = LiteralScalarString(self._data["abstract"])
+        else:
+            self._data["abstract"] = str(self.description)
+
         self._yaml.dump(self._data, path)
 
     def _sync_authors(self, metadata: ProjectMetadata) -> None:

src/somesy/core/models.py

@@ -560,6 +560,17 @@ class Person(ContributorBaseModel):
 
     # helper methods
 
+    @field_validator("orcid", mode="before")
+    @classmethod
+    def orcid_from_string(cls, orcid: str) -> Optional[HttpUrlStr]:
+        """Convert orcid id string to HttpUrlStr."""
+        # orcid regex without https://orcid.org/ prefix
+        orcid_regex = r"^[0-9]{4}-[0-9]{4}-[0-9]{4}-[0-9]{3}[0-9X]$"
+        if orcid is not None and isinstance(orcid, str):
+            if re.match(orcid_regex, orcid):
+                return f"https://orcid.org/{orcid}"
+        return orcid
+
     @property
     def full_name(self) -> str:
         """Return the full name of the person."""

src/somesy/core/writer.py

@@ -251,11 +251,27 @@ def _sync_person_list(
 
         """
         old_people: List[Union[Person, Entity]] = self._parse_people(old)
-        if old_people is None or len(old_people) == 0:
-            return new
-        if new is None or len(new) == 0:
-            return old_people
-        return self._merge_person_metadata(old_people, new)
+
+        # check if people are unique
+        def filter_unique(
+            people: List[Union[Person, Entity]],
+        ) -> List[Union[Person, Entity]]:
+            """Filter out duplicate people from a list."""
+            if people is None or len(people) == 0:
+                return []
+
+            unique_people: List[Union[Person, Entity]] = []
+            # use same_person method to check if people are unique
+            for person in people:
+                if not any(person.same_person(p) for p in unique_people):
+                    unique_people.append(person)
+
+            return unique_people
+
+        old_people_unique = filter_unique(old_people)
+        new_people_unique = filter_unique(new)
+
+        return self._merge_person_metadata(old_people_unique, new_people_unique)
 
     def _sync_authors(self, metadata: ProjectMetadata) -> None:
         """Sync output file authors with authors from metadata.

src/somesy/fortran/writer.py

@@ -91,6 +91,31 @@ def _validate(self) -> None:
     def save(self, path: Optional[Path] = None) -> None:
         """Save the fpm file."""
         path = path or self.path
+        if "description" in self._data:
+            if "\n" in self._data["description"]:
+                self._data["description"] = tomlkit.string(
+                    self._data["description"], multiline=True
+                )
+
+        # Handle arrays with proper formatting
+        for key, value in self._data.items():
+            if isinstance(value, list):
+                array = tomlkit.array()
+                array.extend(value)
+                array.multiline(True)
+                # Ensure whitespace after commas in inline tables
+                for item in array:
+                    if isinstance(item, tomlkit.items.InlineTable):
+                        # Rebuild the inline table with desired formatting
+                        formatted_item = tomlkit.inline_table()
+                        for k, v in item.value.items():
+                            formatted_item[k] = v
+                        formatted_item.trivia.trail = " "  # Add space after each comma
+                        array[array.index(item)] = formatted_item
+                self._data[key] = array
+            else:
+                self._data[key] = value
+
         with open(path, "w") as f:
             tomlkit.dump(self._data, f)
 

src/somesy/julia/writer.py

@@ -55,6 +55,31 @@ def _validate(self) -> None:
     def save(self, path: Optional[Path] = None) -> None:
         """Save the julia file."""
         path = path or self.path
+        if "description" in self._data:
+            if "\n" in self._data["description"]:
+                self._data["description"] = tomlkit.string(
+                    self._data["description"], multiline=True
+                )
+
+        # Handle arrays with proper formatting
+        for key, value in self._data.items():
+            if isinstance(value, list):
+                array = tomlkit.array()
+                array.extend(value)
+                array.multiline(True)
+                # Ensure whitespace after commas in inline tables
+                for item in array:
+                    if isinstance(item, tomlkit.items.InlineTable):
+                        # Rebuild the inline table with desired formatting
+                        formatted_item = tomlkit.inline_table()
+                        for k, v in item.value.items():
+                            formatted_item[k] = v
+                        formatted_item.trivia.trail = " "  # Add space after each comma
+                        array[array.index(item)] = formatted_item
+                self._data[key] = array
+            else:
+                self._data[key] = value
+
         with open(path, "w") as f:
             tomlkit.dump(self._data, f)