Add Read_SDMX method

src/pysdmx/io/__init__.py

@@ -1 +1,5 @@
 """IO module for SDMX data."""
+
+from pysdmx.io.reader import read_sdmx
+
+__all__ = ["read_sdmx"]

src/pysdmx/io/csv/sdmx20/__init__.py

@@ -1,6 +1,6 @@
 """SDMX 2.0 CSV reader and writer."""
 
-from pysdmx.model.message import ActionType
+from pysdmx.model.dataset import ActionType
 
 SDMX_CSV_ACTION_MAPPER = {
     ActionType.Append: "A",

src/pysdmx/io/csv/sdmx20/reader/__init__.py

@@ -7,7 +7,7 @@
 
 from pysdmx.errors import Invalid
 from pysdmx.io.pd import PandasDataset
-from pysdmx.model.message import ActionType
+from pysdmx.model.dataset import ActionType
 
 ACTION_SDMX_CSV_MAPPER_READING = {
     "A": ActionType.Append,

src/pysdmx/io/input_processor.py

@@ -1,11 +1,14 @@
 """Processes the input that comes into read_sdmx function."""
 
-from io import BytesIO, TextIOWrapper
+import os.path
+from io import BytesIO, StringIO, TextIOWrapper
 from json import JSONDecodeError, loads
 from os import PathLike
 from pathlib import Path
 from typing import Tuple, Union
 
+import pandas as pd
+
 from pysdmx.errors import Invalid
 
 
@@ -17,6 +20,27 @@ def __check_xml(infile: str) -> bool:
     return infile[:5] == "<?xml"
 
 
+def __check_csv(infile: str) -> bool:
+    try:
+        pd.read_csv(StringIO(infile), nrows=2)
+        if (
+            len(infile.splitlines()) > 1
+            or infile.splitlines()[0].count(",") > 1
+        ):
+            return True
+    except Exception:
+        return False
+    return False
+
+
+def __check_json(infile: str) -> bool:
+    try:
+        loads(infile)
+        return True
+    except JSONDecodeError:
+        return False
+
+
 def process_string_to_read(
     infile: Union[str, Path, BytesIO],
 ) -> Tuple[str, str]:
@@ -31,6 +55,8 @@ def process_string_to_read(
     Raises:
         Invalid: If the input cannot be parsed as SDMX.
     """
+    if isinstance(infile, str) and os.path.exists(infile):
+        infile = Path(infile)
     # Read file as string
     if isinstance(infile, (Path, PathLike)):
         with open(infile, "r", encoding="utf-8-sig", errors="replace") as f:
@@ -51,16 +77,17 @@ def process_string_to_read(
     out_str = __remove_bom(out_str)
 
     # Check if string is a valid JSON
-    try:
-        loads(out_str)
+    if __check_json(out_str):
         return out_str, "json"
-    except JSONDecodeError:
-        pass
 
     # Check if string is a valid XML
     if __check_xml(out_str):
         return out_str, "xml"
 
+    # Check if string is a valid CSV
+    if __check_csv(out_str):
+        return out_str, "csv"
+
     raise Invalid(
         "Validation Error", f"Cannot parse input as SDMX. Found {infile}"
     )

src/pysdmx/io/reader.py

@@ -0,0 +1,112 @@
+"""SDMX All formats reader module."""
+
+from enum import Enum
+from io import BytesIO
+from pathlib import Path
+from typing import Union
+
+from pysdmx.errors import Invalid
+from pysdmx.io.input_processor import process_string_to_read
+from pysdmx.model.dataset import Dataset
+from pysdmx.model.message import Message
+
+
+class ReadFormat(Enum):
+    """Enumeration of supported SDMX read formats."""
+
+    SDMX_ML_2_1 = "SDMX-ML 2.1"
+    # SDMX_JSON_2 = "SDMX-JSON 2.0.0"
+    # FUSION_JSON = "FusionJSON"
+    SDMX_CSV_1_0 = "SDMX-CSV 1.0"
+    SDMX_CSV_2_0 = "SDMX-CSV 2.0"
+
+    def check_extension(self, extension: str) -> bool:
+        """Check if the extension is valid for the format.
+
+        Args:
+            extension: The file extension.
+
+        Returns:
+            bool: True if the extension is valid, False otherwise
+        """
+        if self == ReadFormat.SDMX_ML_2_1 and extension == "xml":
+            return True
+        # if self == ReadFormat.SDMX_JSON_2 and extension == "json":
+        #     return True
+        # if self == ReadFormat.FUSION_JSON and extension == "json":
+        #     return True
+        if self == ReadFormat.SDMX_CSV_1_0 and extension == "csv":
+            return True
+        return bool(self == ReadFormat.SDMX_CSV_2_0 and extension == "csv")
+
+    def __str__(self) -> str:
+        """Return the string representation of the format."""
+        return self.value
+
+
+def read_sdmx(
+    infile: Union[str, Path, BytesIO],
+    format: ReadFormat,
+    validate: bool = True,
+    use_dataset_id: bool = False,
+) -> Message:
+    """Reads any sdmx file or buffer and returns a dictionary.
+
+    Supported metadata formats are:
+    - SDMX-ML 2.1
+    - SDMX JSON 2.0.0
+    - FusionJSON
+
+    Supported data formats are:
+    - SDMX-ML 2.1
+    - SDMX-CSV 1.0
+    - SDMX-CSV 2.0
+
+    Args:
+        infile: Path to file (pathlib.Path), URL, or string.
+        format: Enumerated format of the SDMX file.
+        use_dataset_id: Whether to use the dataset ID as
+            the key in the resulting dictionary (only for SDMX-ML).
+        validate: Validate the input file (only for SDMX-ML).
+
+    Returns:
+        A dictionary containing the parsed SDMX data or metadata.
+
+    Raises:
+        Invalid: If the file is empty or the format is not supported.
+    """
+    input_str, ext = process_string_to_read(infile)
+    if not format.check_extension(ext):
+        raise Invalid(f"Invalid format {format} for extension {ext}.")
+
+    elif format == ReadFormat.SDMX_ML_2_1:
+        # SDMX-ML 2.1
+        from pysdmx.io.xml.sdmx21.reader import read_xml
+
+        result = read_xml(
+            input_str, validate=validate, use_dataset_id=use_dataset_id
+        )
+    elif format == ReadFormat.SDMX_CSV_1_0:
+        # SDMX-CSV 1.0
+        from pysdmx.io.csv.sdmx10.reader import read
+
+        result = read(input_str)
+    else:
+        # SDMX-CSV 2.0
+        from pysdmx.io.csv.sdmx20.reader import read
+
+        result = read(input_str)
+
+    if len(result) == 0:
+        raise Invalid("Empty SDMX Message")
+
+    # TODO: Add here the Schema download for Datasets, based on structure
+
+    # Returning a Message class
+    if format in (ReadFormat.SDMX_CSV_1_0, ReadFormat.SDMX_CSV_2_0):
+        return Message(data=result)
+
+    first_value = next(iter(result.values()))
+    if isinstance(first_value, Dataset):
+        return Message(data=result)
+    return Message(structures=result)

src/pysdmx/io/xml/sdmx21/reader/__utils.py

@@ -98,7 +98,7 @@
 AGENCIES = "AgencyScheme"
 ORGS = "OrganisationSchemes"
 CLS = "Codelists"
-CONCEPTS = "ConceptSchemes"
+CONCEPTS = "Concepts"
 CS = "ConceptScheme"
 CODE = "Code"
 DFW = "Dataflow"
@@ -124,17 +124,3 @@
     "endTime": "end_time",
     "isSequence": "is_sequence",
 }
-
-
-def unique_id(agencyID: str, id_: str, version: str) -> str:
-    """Create a unique ID for an object.
-
-    Args:
-        agencyID: The agency ID
-        id_: The ID of the object
-        version: The version of the object
-
-    Returns:
-        A string with the unique ID
-    """
-    return f"{agencyID}:{id_}({version})"