Adds multi format reader

docs/learn/nexus-rules.md

@@ -40,4 +40,4 @@ Aside from these general rules, there are a number of special rules for NeXus na
 
 - There is also a set of reserved suffixes that are used to give additional information for a group or field. For the full list, see [Rules for Storing Data Items in NeXus Files](https://manual.nexusformat.org/datarules.html), section "Reserved suffixes".
 
-- Additionally to namefitting, data annotation can use further information. For example, in case of NXdata, the axes listed among the `@axes` shall fit to any instances of `AXISNAME` and data objects listed in `@signal` or `@auxiliary_signals` shall fit to instances of `DATA`. Such rules are typically given in the base classes (e.g., see [here](https://manual.nexusformat.org/classes/base_classes/NXdata.html#index-0) for NXdata). Any tool that makes use of the base classes should implement these special rules in its validation procedure. As an example, pynxtools has a special [function for handling NXdata](https://github.com/FAIRmat-NFDI/pynxtools/blob/474fe823112b8ee1e7b42ac80bb7408fdde22bd5/src/pynxtools/dataconverter/validation.py#L220).
+- Additionally to namefitting, data annotation can use further information. For example, in case of NXdata, the axes listed among the `@axes` shall fit to any instances of `AXISNAME` and data objects listed in `@signal` or `@auxiliary_signals` shall fit to instances of `DATA`. Such rules are typically given in the base classes (e.g., see [here](https://manual.nexusformat.org/classes/base_classes/NXdata.html#index-0) for NXdata). Any tool that makes use of the base classes should implement these special rules in its validation procedure. As an example, pynxtools has a special [function for handling NXdata](https://github.com/FAIRmat-NFDI/pynxtools/blob/474fe823112b8ee1e7b42ac80bb7408fdde22bd5/src/pynxtools/dataconverter/validation.py#L220).

src/pynxtools/__init__.py

@@ -16,13 +16,36 @@
 # limitations under the License.
 #
 
+import logging
 import os
 import re
 from datetime import datetime
 
 from pynxtools._build_wrapper import get_vcs_version
 from pynxtools.definitions.dev_tools.globals.nxdl import get_nxdl_version
 
+LOGGER_LEVELS_TO_HIGHLIGHT = (logging.WARNING, logging.ERROR)
+
+
+class CustomFormatter(logging.Formatter):
+    """Formatter that specifically highlights errors and warnings."""
+
+    def format(self, record):
+        if not getattr(record, "prefixed", False):
+            if record.levelno in LOGGER_LEVELS_TO_HIGHLIGHT:
+                record.msg = f"{record.levelname}: {record.msg}"
+            # Mark the record as prefixed
+            record.prefixed = True
+        return super().format(record)
+
+
+logger = logging.getLogger("pynxtools")
+handler = logging.StreamHandler()
+formatter = CustomFormatter("%(message)s")
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+logger.setLevel(logging.INFO)
+
 MAIN_BRANCH_NAME = "fairmat"
 
 

src/pynxtools/dataconverter/convert.py

@@ -40,9 +40,7 @@
 from pynxtools.dataconverter.validation import validate_dict_against
 from pynxtools.dataconverter.writer import Writer
 
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.INFO)
-logger.addHandler(logging.StreamHandler())
+logger = logging.getLogger("pynxtools")
 
 
 if sys.version_info >= (3, 10):
@@ -337,7 +335,12 @@ def main_cli():
     "--mapping",
     help="Takes a <name>.mapping.json file and converts data from given input files.",
 )
-
+@click.option(
+    "-c",
+    "--config",
+    type=click.Path(exists=True, dir_okay=False, file_okay=True, readable=True),
+    help="A json config file for the reader",
+)
 # pylint: disable=too-many-arguments
 def convert_cli(
     files: Tuple[str, ...],
@@ -349,6 +352,7 @@ def convert_cli(
     ignore_undocumented: bool,
     skip_verify: bool,
     mapping: str,
+    config: str,
     fail: bool,
 ):
     """This command allows you to use the converter functionality of the dataconverter."""
@@ -394,6 +398,7 @@ def convert_cli(
             nxdl,
             output,
             skip_verify,
+            config_file=config,
             ignore_undocumented=ignore_undocumented,
             fail=fail,
         )

src/pynxtools/dataconverter/helpers.py

@@ -42,8 +42,7 @@
     get_required_string as nexus_get_required_string,
 )
 
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.INFO)
+logger = logging.getLogger("pynxtools")
 
 
 class ValidationProblem(Enum):
@@ -874,13 +873,13 @@ def write_nexus_def_to_entry(data, entry_name: str, nxdl_def: str):
     def update_and_warn(key: str, value: str, overwrite=False):
         if key in data and data[key] is not None and data[key] != value:
             report = (
-                f"This is overwritten by the actually used value '{value}'"
+                f"This is overwritten by the actually used value '{data[key]}'"
                 if overwrite
-                else f"The provided version '{value}' is kept. We assume you know what you are doing."
+                else f"The provided version '{data[key]}' is kept. We assume you know what you are doing."
             )
             logger.log(
                 logging.WARNING if overwrite else logging.INFO,
-                f"The entry '{key}' (value: {data[key]}) should not be changed by "
+                f"The entry '{key}' (value: {value}) should not be changed by "
                 f"the reader. {report}",
             )
         if overwrite or data.get(key) is None:

src/pynxtools/dataconverter/readers/base/reader.py

@@ -18,7 +18,7 @@
 """The abstract class off of which to implement readers."""
 
 from abc import ABC, abstractmethod
-from typing import Tuple, Any
+from typing import Any, Tuple
 
 
 class BaseReader(ABC):

src/pynxtools/dataconverter/readers/example/reader.py

@@ -40,6 +40,7 @@ def read(
         template: dict = None,
         file_paths: Tuple[str] = None,
         objects: Tuple[Any] = None,
+        **_,
     ) -> dict:
         """Reads data from given file and returns a filled template dictionary"""
         data: dict = {}