ghga-transpiler 1.2.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

ghga_transpiler/__init__.py

@@ -15,4 +15,13 @@
 
 """Short description of package"""  # Please adapt to package
 
-__version__ = "1.2.0"
+from importlib.metadata import version
+
+from openpyxl.xml import DEFUSEDXML
+
+__version__ = version(__package__)
+
+if not DEFUSEDXML:
+    raise RuntimeError(
+        "The 'defusedxml' package must be present to safely run ghga-transpiler."
+    )

ghga_transpiler/cli.py

@@ -13,21 +13,27 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-""" CLI-specific wrappers around core functions."""
+"""CLI-specific wrappers around core functions."""
 import sys
 from pathlib import Path
 from typing import Optional
 
 import typer
 
-from ghga_transpiler import io
-
+from . import __version__, io
 from .config.exceptions import UnknownVersionError
-from .core import convert_workbook
+from .core import InvalidSematicVersion, convert_workbook
 
 cli = typer.Typer()
 
 
+def version_callback(value: bool):
+    """Prints the package version"""
+    if value:
+        print(__version__)
+        raise typer.Exit()
+
+
 @cli.command()
 def transpile(
     spread_sheet: Path = typer.Argument(
@@ -43,15 +49,24 @@ def transpile(
     force: bool = typer.Option(
         False, "--force", "-f", help="Override output file if it exists."
     ),
+    version: bool = typer.Option(
+        False,
+        "--version",
+        "-v",
+        callback=version_callback,
+        is_eager=True,
+        help="Print package version",
+    ),
 ):
     """ghga-transpiler is a command line utility to transpile the official GHGA
     metadata XLSX workbooks to JSON. Please note that ghga-transpiler does not
     validate that the provided metadata is compliant with the GHGA Metadata
     Schema. This can be achieved by running ghga-validator on the JSON data
-    generated by the ghga-transpiler."""
+    generated by the ghga-transpiler.
+    """
     try:
         ghga_workbook = io.read_workbook(spread_sheet)
-    except (SyntaxError, UnknownVersionError) as exc:
+    except (SyntaxError, UnknownVersionError, InvalidSematicVersion) as exc:
         sys.exit(f"Unable to parse input file '{spread_sheet}': {exc}")
 
     converted = convert_workbook(ghga_workbook)

ghga_transpiler/config/config.py

@@ -21,7 +21,7 @@ from importlib import resources
 from typing import Callable, Optional
 
 import yaml
-from pydantic import BaseModel, root_validator
+from pydantic import BaseModel, model_validator
 
 from .exceptions import DuplicatedName, UnknownVersionError
 
@@ -40,11 +40,11 @@ class WorksheetSettings(BaseModel):
     """A data model for the per-worksheet settings of a transpiler config"""
 
     name: str
-    header_row: Optional[int]
-    start_row: Optional[int]
-    start_column: Optional[int]
-    end_column: Optional[int]
-    transformations: Optional[dict[str, Callable]]
+    header_row: Optional[int] = None
+    start_row: Optional[int] = None
+    start_column: Optional[int] = None
+    end_column: Optional[int] = None
+    transformations: Optional[dict[str, Callable]] = None
 
 
 class Worksheet(BaseModel):
@@ -61,21 +61,21 @@ class Config(BaseModel):
     default_settings: DefaultSettings
     worksheets: list[Worksheet]
 
-    @root_validator(pre=False)
-    def get_param(cls, values):  # pylint: disable=no-self-argument
+    @model_validator(mode="after")
+    def get_param(cls, values):  # noqa
         """Function to manage parameters of global and worksheet specific configuration"""
-        for sheet in values.get("worksheets"):
-            for key in values.get("default_settings").__dict__:
+        for sheet in values.worksheets:
+            for key in values.default_settings.__dict__:
                 if getattr(sheet.settings, key) is None:
-                    val = getattr(values.get("default_settings"), key)
+                    val = getattr(values.default_settings, key)
                     setattr(sheet.settings, key, val)
         return values
 
-    @root_validator(pre=False)
-    def check_name(cls, values):  # pylint: disable=no-self-argument
+    @model_validator(mode="after")
+    def check_name(cls, values):  # noqa
         """Function to ensure that each worksheets has a unique sheet_name and name attributes."""
         # Check for duplicate attribute names
-        attrs_counter = Counter(ws.settings.name for ws in values["worksheets"])
+        attrs_counter = Counter(ws.settings.name for ws in values.worksheets)
         dup_attrs = [name for name, count in attrs_counter.items() if count > 1]
         if dup_attrs:
             raise DuplicatedName(
@@ -83,7 +83,7 @@ class Config(BaseModel):
             )
 
         # Check for duplicate worksheet names
-        attrs_counter = Counter(ws.sheet_name for ws in values["worksheets"])
+        attrs_counter = Counter(ws.sheet_name for ws in values.worksheets)
         dup_ws_names = [name for name, count in attrs_counter.items() if count > 1]
         if dup_ws_names:
             raise DuplicatedName(
@@ -94,11 +94,10 @@ class Config(BaseModel):
 
 def load_config(version: str, package: resources.Package) -> Config:
     """Reads configuration yaml file from default location and creates a Config object"""
-
     config_resource = resources.files(package).joinpath(f"{version}.yaml")
     try:
         config_str = config_resource.read_text(encoding="utf8")
     except FileNotFoundError:
         # pylint: disable=raise-missing-from
-        raise UnknownVersionError(f"Unknown metadata version: {version}")
-    return Config.parse_obj(yaml.load(config_str, yaml.Loader))  # nosec
+        raise UnknownVersionError(f"Unknown metadata version: {version}") from None
+    return Config.model_validate(yaml.load(config_str, yaml.Loader))  # noqa # nosec

ghga_transpiler/core.py

@@ -15,16 +15,17 @@
 #
 
 """This module contains functionalities for processing excel sheets into json object."""
-import re
 from importlib import resources
 from typing import Callable, Optional, Union
 
+import semver
 from openpyxl import Workbook
 
-from ghga_transpiler import config
+from . import config
 
-# pylint: disable=line-too-long
-SEMVER_REGEX = r"^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)(?:-((?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+([0-9a-zA-Z-]+(?:\.[0-9a-zA-Z-]+)*))?$"
+
+class InvalidSematicVersion(Exception):
+    """Raised when a version string is invalid."""
 
 
 class GHGAWorkbook:
@@ -33,20 +34,28 @@ class GHGAWorkbook:
     def __init__(self, workbook: Workbook, configs_package: resources.Package):
         """Create a new GHGAWorkbook object from an XLSX workbook"""
         self.workbook = workbook
-        self.version = GHGAWorkbook._get_version(workbook)
-        self.config = config.load_config(self.version, configs_package)
+        self.wb_version = GHGAWorkbook._get_version(workbook)
+        self.config = config.load_config(self.major_minor_version, configs_package)
 
     @staticmethod
     def _get_version(workbook):
         """Function to get workbook version from the worksheet _properties"""
         if "__properties" in workbook.sheetnames:
-            version = str(workbook["__properties"].cell(1, 1).value)
-            if re.fullmatch(SEMVER_REGEX, version):
-                return version
+            try:
+                return semver.Version.parse(workbook["__properties"].cell(1, 1).value)
+            except ValueError:
+                raise InvalidSematicVersion(
+                    "Unable to extract metadata model version from the provided workbook (not a valid semantic version)."
+                ) from None
         raise SyntaxError(
-            "Unable to extract metadata version from the provided workbook."
+            "Unable to extract metadata model version from the provided workbook (missing)."
         )
 
+    @property
+    def major_minor_version(self):
+        """Returns only major and minor version numbers"""
+        return f"{self.wb_version.major}.{self.wb_version.minor}"
+
 
 def get_worksheet_rows(
     worksheet,
@@ -81,7 +90,8 @@ def get_header(
 
 def convert_rows(header, rows) -> list[dict]:
     """Function to return list of dictionaries, rows as worksheet row values and
-    column names as keys"""
+    column names as keys
+    """
     return [
         {
             key: value

ghga_transpiler/io.py

@@ -24,15 +24,13 @@ from typing import Optional, TextIO
 
 from openpyxl import load_workbook
 
-from ghga_transpiler.core import GHGAWorkbook
+from .core import GHGAWorkbook
 
 
 def read_workbook(
     path: Path, configs_package: resources.Package = "ghga_transpiler.configs"
 ) -> GHGAWorkbook:
-    """
-    Function to read-in a workbook
-    """
+    """Function to read-in a workbook"""
     return GHGAWorkbook(load_workbook(path), configs_package=configs_package)
 
 
@@ -43,7 +41,8 @@ def _write_json(data: dict, file: TextIO):
 
 def write_json(data: dict, path: Optional[Path], force: bool) -> None:
     """Write the data provided as a dictionary to the specified output path or
-    to stdout if the path is None."""
+    to stdout if the path is None.
+    """
     if path is None:
         _write_json(data, sys.stdout)
     elif path.exists() and not force:

ghga_transpiler/transformations.py

@@ -38,7 +38,28 @@ def to_attributes() -> Callable:
         return dict(zip(("key", "value"), splitted))
 
     def split_mult(value: str) -> list[dict]:
-        """Function to convert string to attributes"""
+        """Converts string to attributes"""
         return [split_one(elem) for elem in split_by_semicolon(value)]
 
     return split_mult
+
+
+def snake_case(cv: str) -> str:
+    """Converts format of a string to SNAKE_CASE"""
+    return cv.replace(" ", "_").upper()
+
+
+def to_snake_case() -> Callable:
+    """Returns a function that converts a string to SNAKE_CASE"""
+    return snake_case
+
+
+def snake_case_list(value: str) -> list[str]:
+    """Combines the functions to split_by_semicolon and convert_to_snake_case"""
+    list_to_convert = split_by_semicolon(value)
+    return [snake_case(elem) for elem in list_to_convert]
+
+
+def to_snake_case_list() -> Callable:
+    """Returns a function that converts a semicolon separated string into a list of snake-cased strings"""
+    return snake_case_list

{ghga_transpiler-1.2.0.dist-info → ghga_transpiler-2.0.0.dist-info}/METADATA

@@ -1,33 +1,36 @@
 Metadata-Version: 2.1
 Name: ghga-transpiler
-Version: 1.2.0
-Summary: GHGA-Transpiler - GHGA metadata XLSX to JSON transpilation
-Home-page: https://github.com/ghga-de/ghga-transpiler
-Author: German Human Genome Phenome Archive (GHGA)
-Author-email: contact@ghga.de
+Version: 2.0.0
+Summary: GHGA-Transpiler - excel to JSON converter
+Author-email: "German Human Genome Phenome Archive (GHGA)" <contact@ghga.de>
 License: Apache 2.0
+Project-URL: Repository, https://github.com/ghga-de/ghga-transpiler
+Classifier: Development Status :: 1 - Planning
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Topic :: Internet :: WWW/HTTP :: HTTP Servers
-Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Intended Audience :: Developers
 Requires-Python: >=3.9
-Description-Content-Type: text/markdown; charset=UTF-8
+Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: typer (==0.7.0)
-Requires-Dist: pydantic (==1.10.6)
-Requires-Dist: openpyxl (==3.1.2)
-Requires-Dist: defusedxml (==0.7.1)
-Requires-Dist: PyYAML (==6.0)
-Provides-Extra: all
+Requires-Dist: typer ~=0.9.0
+Requires-Dist: openpyxl ==3.*,>=3.1.2
+Requires-Dist: defusedxml ==0.*,>=0.7
+Requires-Dist: pydantic <3,>=2
+Requires-Dist: PyYAML ~=6.0
+Requires-Dist: semver ==3.*
 
 
-[![tests](https://github.com/ghga-de/ghga-transpiler/actions/workflows/unit_and_int_tests.yaml/badge.svg)](https://github.com/ghga-de/ghga-transpiler/actions/workflows/unit_and_int_tests.yaml)
+[![tests](https://github.com/ghga-de/ghga-transpiler/actions/workflows/tests.yaml/badge.svg)](https://github.com/ghga-de/ghga-transpiler/actions/workflows/unit_and_int_tests.yaml)
 [![Coverage Status](https://coveralls.io/repos/github/ghga-de/ghga-transpiler/badge.svg?branch=main)](https://coveralls.io/github/ghga-de/ghga-transpiler?branch=main)
 
 # Ghga Transpiler
 
-GHGA-Transpiler - GHGA metadata XLSX to JSON transpilation
+GHGA-Transpiler - excel to JSON converter
 
 ## Description
 

ghga_transpiler-2.0.0.dist-info/RECORD

@@ -0,0 +1,16 @@
+ghga_transpiler/__init__.py,sha256=5TNi3CUUdk2qXfeDjKHtqG5zre2GuLv9YAFOydRAE4k,993
+ghga_transpiler/__main__.py,sha256=NgajDXhJ36WPA6MR5Rb44Qqmogie16_kr0HRL-umGxc,848
+ghga_transpiler/cli.py,sha256=haVokV0xVTRET1oQZw0B_4r3V-kEUcypbrLEACPLWBs,2522
+ghga_transpiler/core.py,sha256=L-L3BkU8PfuBUWq9scA-o065rMhMKlNHqtDqg2ZwkPo,5246
+ghga_transpiler/io.py,sha256=MJwXmFC2xsgq7exlG623pnKhCxiJ-EBI9uIV0G46frU,1783
+ghga_transpiler/transformations.py,sha256=up9Yday5Hg-ECKvfzmqcvv8XlevnYz5mufwbZuK3Lm4,2214
+ghga_transpiler/config/__init__.py,sha256=IKlzAd82ta9a0_aEps3f4I3GLRSJeyV1QImFcHvBLE0,818
+ghga_transpiler/config/config.py,sha256=3N3ozWlqIdtBNlNZI5dPjDunGGxlF7-APplgzx9MSn0,3807
+ghga_transpiler/config/exceptions.py,sha256=_A8wMX9t0YkLw4tk2IhOVdKoGoZxP2pXsEaZwrgkXhw,1091
+ghga_transpiler/configs/__init__.py,sha256=uGpTS9l2diw93p053atk09DuObDZ7eDZJoADCmuYX0g,687
+ghga_transpiler-2.0.0.dist-info/LICENSE,sha256=a2nPPnhGY9QGdkfGrseHGDVj62fh8o5DoHsUpQp3GzA,11452
+ghga_transpiler-2.0.0.dist-info/METADATA,sha256=n2ziI2Q_Kyhzk03xwGq9_EoCSHpAPtls4S7a44XuYjk,4460
+ghga_transpiler-2.0.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+ghga_transpiler-2.0.0.dist-info/entry_points.txt,sha256=Fr_VQJynZZl95NXjrQW2gE0bCocgjKVNEZQpaLls8po,65
+ghga_transpiler-2.0.0.dist-info/top_level.txt,sha256=TksRpDO3Y4mvK-B09UhQU3ceZpG19fljNlVDGTfjg8o,16
+ghga_transpiler-2.0.0.dist-info/RECORD,,

{ghga_transpiler-1.2.0.dist-info → ghga_transpiler-2.0.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.0)
+Generator: bdist_wheel (0.42.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{ghga_transpiler-1.2.0.dist-info → ghga_transpiler-2.0.0.dist-info}/top_level.txt

@@ -1,3 +1 @@
 ghga_transpiler
-scripts
-tests

ghga_transpiler/configs/0.10.0.yaml

@@ -1,109 +0,0 @@
-ghga_metadata_version: 0.10.0
-default_settings:
-  header_row: 1
-  start_row: 7
-  start_column: 1
-  transformations:
-    attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-worksheets:
-  - settings:
-      end_column: 6
-      name: analyses
-    sheet_name: Analysis
-  - settings:
-      end_column: 8
-      name: analysis_process_output_files
-    sheet_name: AnalysisProcessOutputFile
-  - settings:
-      end_column: 5
-      name: analysis_processes
-      transformations:
-        study_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sample_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sequencing_process_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: AnalysisProcess
-  - settings:
-      end_column: 9
-      name: biospecimens
-    sheet_name: Biospecimen
-  - settings:
-      end_column: 9
-      name: conditions
-    sheet_name: Condition
-  - settings:
-      end_column: 3
-      name: data_access_committees
-    sheet_name: DataAccessCommittee
-  - settings:
-      end_column: 8
-      name: data_access_policies
-      transformations:
-        data_use_modifiers: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: DataAccessPolicy
-  - settings:
-      end_column: 5
-      name: datasets
-      transformations:
-        types: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Dataset
-  - settings:
-      end_column: 8
-      name: individuals
-      transformations:
-        ancestries: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        phenotypic_features: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Individual
-  - settings:
-      end_column: 14
-      name: library_preparation_protocols
-      transformations:
-        target_regions: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    sheet_name: LibraryPreparationProtocol
-  - settings:
-      end_column: 9
-      name: publications
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Publication
-  - settings:
-      end_column: 8
-      name: sample_files
-    sheet_name: SampleFile
-  - settings:
-      end_column: 10
-      name: samples
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Sample
-  - settings:
-      end_column: 7
-      name: sequencing_experiments
-    sheet_name: SequencingExperiment
-  - settings:
-      end_column: 8
-      name: sequencing_process_files
-    sheet_name: SequencingProcessFile
-  - settings:
-      end_column: 10
-      name: sequencing_processes
-    sheet_name: SequencingProcess
-  - settings:
-      end_column: 20
-      name: sequencing_protocols
-    sheet_name: SequencingProtocol
-  - settings:
-      end_column: 6
-      name: studies
-      transformations:
-        affiliations: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    sheet_name: Study
-  - settings:
-      end_column: 8
-      name: study_files
-    sheet_name: StudyFile
-  - settings:
-      end_column: 4
-      name: trios
-    sheet_name: Trio

ghga_transpiler/configs/1.0.0.yaml

@@ -1,109 +0,0 @@
-ghga_metadata_version: 1.0.0
-default_settings:
-  header_row: 1
-  start_row: 7
-  start_column: 1
-  transformations:
-    attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-worksheets:
-  - settings:
-      end_column: 6
-      name: analyses
-    sheet_name: Analysis
-  - settings:
-      end_column: 9
-      name: analysis_process_output_files
-    sheet_name: AnalysisProcessOutputFile
-  - settings:
-      end_column: 5
-      name: analysis_processes
-      transformations:
-        study_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sample_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        sequencing_process_input_files: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: AnalysisProcess
-  - settings:
-      end_column: 10
-      name: biospecimens
-    sheet_name: Biospecimen
-  - settings:
-      end_column: 9
-      name: conditions
-    sheet_name: Condition
-  - settings:
-      end_column: 3
-      name: data_access_committees
-    sheet_name: DataAccessCommittee
-  - settings:
-      end_column: 8
-      name: data_access_policies
-      transformations:
-        data_use_modifiers: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: DataAccessPolicy
-  - settings:
-      end_column: 5
-      name: datasets
-      transformations:
-        types: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Dataset
-  - settings:
-      end_column: 6
-      name: individuals
-      transformations:
-        ancestries: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        phenotypic_features: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Individual
-  - settings:
-      end_column: 14
-      name: library_preparation_protocols
-      transformations:
-        target_regions: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    sheet_name: LibraryPreparationProtocol
-  - settings:
-      end_column: 9
-      name: publications
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Publication
-  - settings:
-      end_column: 9
-      name: sample_files
-    sheet_name: SampleFile
-  - settings:
-      end_column: 10
-      name: samples
-      transformations:
-        xref: !!python/object/apply:ghga_transpiler.transformations.to_list []
-    sheet_name: Sample
-  - settings:
-      end_column: 7
-      name: sequencing_experiments
-    sheet_name: SequencingExperiment
-  - settings:
-      end_column: 9
-      name: sequencing_process_files
-    sheet_name: SequencingProcessFile
-  - settings:
-      end_column: 12
-      name: sequencing_processes
-    sheet_name: SequencingProcess
-  - settings:
-      end_column: 17
-      name: sequencing_protocols
-    sheet_name: SequencingProtocol
-  - settings:
-      end_column: 6
-      name: studies
-      transformations:
-        affiliations: !!python/object/apply:ghga_transpiler.transformations.to_list []
-        attributes: !!python/object/apply:ghga_transpiler.transformations.to_attributes []
-    sheet_name: Study
-  - settings:
-      end_column: 9
-      name: study_files
-    sheet_name: StudyFile
-  - settings:
-      end_column: 4
-      name: trios
-    sheet_name: Trio