mat73-reader 0.1.0__py3-none-any.whl

mat73_reader/__init__.py

@@ -0,0 +1,6 @@
+"""mat73-reader: Read MATLAB v7.3 HDF5 .mat files in Python."""
+
+from mat73_reader.reader import load, inspect
+
+__version__ = "0.1.0"
+__all__ = ["load", "inspect"]

mat73_reader/cli.py

@@ -0,0 +1,108 @@
+"""Command-line interface for mat73-reader."""
+
+import argparse
+import sys
+from pathlib import Path
+
+from mat73_reader.reader import inspect, load
+from mat73_reader.converter import to_csv, to_json
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog="mat73-reader",
+        description="Read and convert MATLAB v7.3 HDF5 .mat files.",
+    )
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    # --- inspect ---
+    inspect_parser = subparsers.add_parser(
+        "inspect",
+        help="List variables in a .mat file with their types and shapes.",
+    )
+    inspect_parser.add_argument("file", type=Path, help="Path to .mat file")
+
+    # --- convert ---
+    convert_parser = subparsers.add_parser(
+        "convert",
+        help="Convert a .mat file to CSV or JSON.",
+    )
+    convert_parser.add_argument("file", type=Path, help="Path to .mat file")
+    convert_parser.add_argument(
+        "--format",
+        choices=["csv", "json"],
+        default="csv",
+        help="Output format (default: csv)",
+    )
+    convert_parser.add_argument(
+        "--output",
+        type=Path,
+        default=None,
+        help="Output path. For CSV: directory. For JSON: file path. "
+        "Defaults to current directory.",
+    )
+    convert_parser.add_argument(
+        "--variable",
+        type=str,
+        default=None,
+        help="Extract only this variable.",
+    )
+
+    args = parser.parse_args()
+
+    if args.command == "inspect":
+        _cmd_inspect(args)
+    elif args.command == "convert":
+        _cmd_convert(args)
+
+
+def _cmd_inspect(args):
+    try:
+        variables = inspect(args.file)
+    except (FileNotFoundError, ValueError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if not variables:
+        print("No variables found.")
+        return
+
+    # Simple tabular output
+    print(f"{'Variable':<30} {'Type':<10} {'Shape/Children'}")
+    print("-" * 70)
+    for var in variables:
+        name = var["name"]
+        vtype = var["type"]
+        if vtype == "dataset":
+            detail = f"{var['shape']}  {var['dtype']}"
+        else:
+            detail = ", ".join(var.get("children", []))
+        print(f"{name:<30} {vtype:<10} {detail}")
+
+
+def _cmd_convert(args):
+    try:
+        if args.variable:
+            raw = load(args.file, variable=args.variable)
+            data = {args.variable: raw}
+        else:
+            data = load(args.file)
+    except (FileNotFoundError, ValueError, KeyError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if args.format == "csv":
+        output_dir = args.output or Path(".")
+        written = to_csv(data, output_dir)
+        for path in written:
+            print(f"Written: {path}")
+        if not written:
+            print("No variables could be converted to CSV.")
+    elif args.format == "json":
+        output_path = args.output or Path(f"{args.file.stem}.json")
+        written = to_json(data, output_path)
+        print(f"Written: {written}")
+
+
+if __name__ == "__main__":
+    main()

mat73_reader/converter.py

@@ -0,0 +1,97 @@
+"""Convert loaded MATLAB v7.3 data to common output formats."""
+
+import json
+from pathlib import Path
+from typing import Any, Union
+
+import numpy as np
+
+
+def to_csv(
+    data: dict,
+    output_dir: Union[str, Path],
+    prefix: str = "",
+) -> list[Path]:
+    """Write loaded .mat data to CSV files.
+
+    Each top-level variable that can be represented as a table
+    gets its own CSV file. Non-tabular data is skipped with a warning.
+
+    Args:
+        data: Dict returned by mat73_reader.load().
+        output_dir: Directory to write CSV files into.
+        prefix: Optional prefix for output filenames.
+
+    Returns:
+        List of paths to written CSV files.
+    """
+    import pandas as pd
+
+    output_dir = Path(output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    written = []
+
+    for name, value in data.items():
+        filename = f"{prefix}{name}.csv" if prefix else f"{name}.csv"
+        out_path = output_dir / filename
+
+        if isinstance(value, pd.DataFrame):
+            value.to_csv(out_path, index=False)
+            written.append(out_path)
+        elif isinstance(value, np.ndarray) and value.ndim <= 2:
+            df = pd.DataFrame(value)
+            df.to_csv(out_path, index=False)
+            written.append(out_path)
+        elif isinstance(value, dict):
+            try:
+                df = pd.DataFrame(value)
+                df.to_csv(out_path, index=False)
+                written.append(out_path)
+            except (ValueError, TypeError):
+                print(f"Skipping '{name}': cannot convert to tabular CSV.")
+        else:
+            print(f"Skipping '{name}': unsupported type {type(value).__name__}.")
+
+    return written
+
+
+def to_json(
+    data: dict,
+    output_path: Union[str, Path],
+    indent: int = 2,
+) -> Path:
+    """Write loaded .mat data to a JSON file.
+
+    Args:
+        data: Dict returned by mat73_reader.load().
+        output_path: Path for the output JSON file.
+        indent: JSON indentation level.
+
+    Returns:
+        Path to the written JSON file.
+    """
+    output_path = Path(output_path)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    serializable = _make_serializable(data)
+    with open(output_path, "w") as f:
+        json.dump(serializable, f, indent=indent)
+
+    return output_path
+
+
+def _make_serializable(obj: Any) -> Any:
+    """Recursively convert numpy types to JSON-serializable Python types."""
+    if isinstance(obj, dict):
+        return {k: _make_serializable(v) for k, v in obj.items()}
+    if isinstance(obj, list):
+        return [_make_serializable(item) for item in obj]
+    if isinstance(obj, np.ndarray):
+        return obj.tolist()
+    if isinstance(obj, (np.integer,)):
+        return int(obj)
+    if isinstance(obj, (np.floating,)):
+        return float(obj)
+    if isinstance(obj, np.bool_):
+        return bool(obj)
+    return obj

mat73_reader/reader.py

@@ -0,0 +1,402 @@
+"""Core reader for MATLAB v7.3 HDF5 .mat files."""
+
+from pathlib import Path
+from typing import Any, Optional, Union
+
+import h5py
+import numpy as np
+
+# MATLAB MCOS (MATLAB Class Object System) class marker.
+# Table objects in v7.3 files store a (1,6) uint32 header where
+# the first element is this value.
+_MCOS_CLASS_MARKER = 0xDD000000
+
+# Number of MCOS ref slots per table instance.
+# Each table occupies a fixed block of consecutive entries in the
+# #subsystem#/MCOS reference array:
+#   +0: (ncols, 1) object refs -> column data arrays
+#   +1: (1,1) float64 = ndims
+#   +2: (1,1) float64 = nrows
+#   +3: (2,) uint64   = segment info
+#   +4: (1,1) float64 = nvars (ncols)
+#   +5: (ncols, 1) object refs -> column name strings (uint16)
+#   +6: Group = table properties (DimensionNames, VariableUnits, etc.)
+_MCOS_BLOCK_SIZE = 7
+
+# Offset of the first table block within the MCOS refs array.
+_MCOS_BLOCK_BASE = 2
+
+
+def load(
+    filepath: Union[str, Path],
+    variable: Optional[str] = None,
+    as_dataframe: bool = False,
+) -> Union[dict, Any]:
+    """Load a MATLAB v7.3 HDF5 .mat file.
+
+    Supports standard arrays, structs, cell arrays, char arrays,
+    and MATLAB table objects (which most Python tools cannot read).
+
+    Args:
+        filepath: Path to the .mat file.
+        variable: If provided, return only this top-level variable.
+            If None, return all variables as a dict.
+        as_dataframe: If True, attempt to convert array results to
+            pandas DataFrames. MATLAB tables are always returned as
+            DataFrames regardless of this flag.
+
+    Returns:
+        A dict mapping variable names to their values, or a single
+        value if `variable` is specified.
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        ValueError: If the file is not a valid HDF5 .mat file.
+        KeyError: If the requested variable does not exist.
+    """
+    filepath = Path(filepath)
+    if not filepath.exists():
+        raise FileNotFoundError(f"File not found: {filepath}")
+
+    if not _is_mat73(filepath):
+        raise ValueError(
+            f"Not a MATLAB v7.3 HDF5 file: {filepath}. "
+            "For older .mat formats, use scipy.io.loadmat()."
+        )
+
+    with h5py.File(filepath, "r") as f:
+        # Pre-load the MCOS reference array if it exists.
+        # This is needed to resolve MATLAB table objects.
+        mcos_refs = _load_mcos_refs(f)
+
+        if variable is not None:
+            if variable not in f:
+                available = [
+                    k for k in f.keys()
+                    if k not in ("#refs#", "#subsystem#")
+                ]
+                raise KeyError(
+                    f"Variable '{variable}' not found. "
+                    f"Available: {available}"
+                )
+            result = _read_item(f[variable], f, mcos_refs)
+            if as_dataframe:
+                result = _try_to_dataframe(result, variable)
+            return result
+
+        data = {}
+        for key in f.keys():
+            if key in ("#refs#", "#subsystem#"):
+                continue
+            data[key] = _read_item(f[key], f, mcos_refs)
+
+        if as_dataframe:
+            data = {k: _try_to_dataframe(v, k) for k, v in data.items()}
+
+        return data
+
+
+def inspect(filepath: Union[str, Path]) -> list[dict]:
+    """Inspect the contents of a MATLAB v7.3 HDF5 .mat file.
+
+    Returns a list of dicts describing each top-level variable:
+    name, type, shape, and dtype (for arrays).
+
+    Args:
+        filepath: Path to the .mat file.
+
+    Returns:
+        List of variable info dicts.
+    """
+    filepath = Path(filepath)
+    if not filepath.exists():
+        raise FileNotFoundError(f"File not found: {filepath}")
+
+    if not _is_mat73(filepath):
+        raise ValueError(
+            f"Not a MATLAB v7.3 HDF5 file: {filepath}. "
+            "For older .mat formats, use scipy.io.loadmat()."
+        )
+
+    variables = []
+    with h5py.File(filepath, "r") as f:
+        for key in f.keys():
+            if key in ("#refs#", "#subsystem#"):
+                continue
+            item = f[key]
+            info = {"name": key}
+            if isinstance(item, h5py.Dataset):
+                info["type"] = "dataset"
+                info["shape"] = item.shape
+                info["dtype"] = str(item.dtype)
+            elif isinstance(item, h5py.Group):
+                info["type"] = "group"
+                info["children"] = [k for k in item.keys()]
+            variables.append(info)
+
+    return variables
+
+
+# ---------------------------------------------------------------------------
+# MCOS table support
+# ---------------------------------------------------------------------------
+
+def _load_mcos_refs(f: h5py.File) -> Optional[np.ndarray]:
+    """Load the MCOS reference array if the file has one.
+
+    The #subsystem#/MCOS dataset is an object reference array that
+    MATLAB uses to store class instance data, including table columns
+    and metadata. We load it once and pass it through the read pipeline
+    so table objects can be resolved.
+    """
+    try:
+        mcos = f["#subsystem#"]["MCOS"]
+        return mcos[()]
+    except (KeyError, Exception):
+        return None
+
+
+def _is_mcos_table_header(dataset: h5py.Dataset) -> bool:
+    """Check if a dataset is a MATLAB MCOS table header.
+
+    MATLAB table objects are stored as (1,6) uint32 arrays where
+    the first element is the MCOS class marker 0xDD000000.
+    """
+    if dataset.shape != (1, 6):
+        return False
+    if dataset.dtype != np.dtype("uint32"):
+        return False
+    first_val = dataset[0, 0]
+    return int(first_val) == _MCOS_CLASS_MARKER
+
+
+def _read_mcos_table(
+    dataset: h5py.Dataset,
+    root: h5py.File,
+    mcos_refs: np.ndarray,
+) -> Any:
+    """Decode a MATLAB table object into a pandas DataFrame.
+
+    The (1,6) uint32 header encodes:
+        [0]: 0xDD000000  (MCOS class marker)
+        [1]: class definition index (same for all tables in a file)
+        [2]: reserved
+        [3]: reserved
+        [4]: instance index (1-based, determines which MCOS block)
+        [5]: reserved
+
+    The instance index maps to a block of 7 consecutive entries in
+    the MCOS reference array starting at offset:
+        mcos_ref_index = _MCOS_BLOCK_BASE + (instance - 1) * _MCOS_BLOCK_SIZE
+    """
+    import pandas as pd
+
+    header = dataset[()].ravel()
+    instance = int(header[4])
+    block_start = _MCOS_BLOCK_BASE + (instance - 1) * _MCOS_BLOCK_SIZE
+
+    refs_flat = mcos_refs.ravel()
+
+    # Safety check
+    if block_start + _MCOS_BLOCK_SIZE > len(refs_flat):
+        return None
+
+    # +0: column data references (ncols, 1)
+    data_ref_array = root[refs_flat[block_start]]
+    ncols = data_ref_array.shape[0]
+
+    # +5: column name references (ncols, 1)
+    name_ref_array = root[refs_flat[block_start + 5]]
+
+    # Read column names
+    col_names = []
+    for i in range(ncols):
+        ref = name_ref_array[i, 0]
+        name_ds = root[ref]
+        if name_ds.dtype == np.uint16:
+            col_names.append(_decode_chars(name_ds[()]))
+        else:
+            col_names.append(f"col_{i}")
+
+    # Read column data
+    columns = {}
+    for i, name in enumerate(col_names):
+        ref = data_ref_array[i, 0]
+        col_ds = root[ref]
+
+        if col_ds.dtype == np.float64:
+            columns[name] = col_ds[()].ravel()
+        elif col_ds.dtype == np.uint16:
+            columns[name] = _decode_chars(col_ds[()])
+        elif col_ds.dtype == h5py.ref_dtype:
+            # Column of object references (e.g., cell array column)
+            col_data = []
+            for j in range(col_ds.shape[0] if col_ds.ndim == 1 else col_ds.shape[1]):
+                r = col_ds[0, j] if col_ds.ndim == 2 else col_ds[j]
+                try:
+                    inner = root[r]
+                    if isinstance(inner, h5py.Dataset):
+                        if inner.dtype == np.uint16:
+                            col_data.append(_decode_chars(inner[()]))
+                        elif inner.dtype == np.float64:
+                            val = inner[()].ravel()
+                            col_data.append(
+                                val[0] if val.size == 1 else val
+                            )
+                        else:
+                            col_data.append(inner[()])
+                    else:
+                        col_data.append(None)
+                except Exception:
+                    col_data.append(None)
+            columns[name] = col_data
+        elif col_ds.dtype in (np.int64, np.int32, np.uint64, np.uint32):
+            columns[name] = col_ds[()].ravel()
+        else:
+            # Fallback: try to read raw
+            columns[name] = col_ds[()].ravel()
+
+    # Build DataFrame, handling ragged columns gracefully
+    try:
+        return pd.DataFrame(columns)
+    except ValueError:
+        # Columns may have different lengths (shouldn't happen for valid
+        # tables, but handle defensively)
+        max_len = max(
+            (len(v) if hasattr(v, '__len__') and not isinstance(v, str) else 1)
+            for v in columns.values()
+        )
+        padded = {}
+        for k, v in columns.items():
+            if isinstance(v, str):
+                padded[k] = [v] * max_len
+            elif hasattr(v, '__len__'):
+                arr = list(v)
+                arr.extend([None] * (max_len - len(arr)))
+                padded[k] = arr
+            else:
+                padded[k] = [v] * max_len
+        return pd.DataFrame(padded)
+
+
+# ---------------------------------------------------------------------------
+# Core reading functions
+# ---------------------------------------------------------------------------
+
+def _is_mat73(filepath: Path) -> bool:
+    """Check if a file is a valid HDF5-based MATLAB v7.3 file."""
+    try:
+        return h5py.is_hdf5(str(filepath))
+    except Exception:
+        return False
+
+
+def _read_item(
+    item: Any,
+    root: h5py.File,
+    mcos_refs: Optional[np.ndarray] = None,
+) -> Any:
+    """Recursively read an HDF5 item into a Python object.
+
+    Handles datasets, groups (structs), object references,
+    cell arrays, char arrays, and MATLAB table objects.
+    """
+    if isinstance(item, h5py.Dataset):
+        return _read_dataset(item, root, mcos_refs)
+    elif isinstance(item, h5py.Group):
+        return _read_group(item, root, mcos_refs)
+    return item
+
+
+def _read_dataset(
+    dataset: h5py.Dataset,
+    root: h5py.File,
+    mcos_refs: Optional[np.ndarray] = None,
+) -> Any:
+    """Read an HDF5 dataset, handling MATLAB-specific encodings."""
+    # Check for MATLAB table objects first
+    if mcos_refs is not None and _is_mcos_table_header(dataset):
+        return _read_mcos_table(dataset, root, mcos_refs)
+
+    data = dataset[()]
+
+    # MATLAB stores strings as uint16 arrays
+    if dataset.dtype == np.dtype("uint16"):
+        return _decode_chars(data)
+
+    # Object references (e.g., cell arrays)
+    if dataset.dtype == h5py.ref_dtype:
+        return _read_references(data, root, mcos_refs)
+
+    # Squeeze single-element arrays to scalars
+    if isinstance(data, np.ndarray):
+        if data.ndim == 0:
+            return data.item()
+        if data.shape == (1, 1):
+            return data[0, 0]
+        # MATLAB stores arrays in column-major (Fortran) order
+        # Transpose 2D arrays to match expected row-major layout
+        if data.ndim == 2:
+            return data.T
+
+    return data
+
+
+def _read_group(
+    group: h5py.Group,
+    root: h5py.File,
+    mcos_refs: Optional[np.ndarray] = None,
+) -> dict:
+    """Read an HDF5 group as a dict (MATLAB struct)."""
+    result = {}
+    for key in group.keys():
+        result[key] = _read_item(group[key], root, mcos_refs)
+    return result
+
+
+def _read_references(
+    data: np.ndarray,
+    root: h5py.File,
+    mcos_refs: Optional[np.ndarray] = None,
+) -> list:
+    """Resolve an array of HDF5 object references."""
+    refs = []
+    flat = data.flat
+    for ref in flat:
+        if isinstance(ref, h5py.Reference):
+            try:
+                dereferenced = root[ref]
+                refs.append(_read_item(dereferenced, root, mcos_refs))
+            except Exception:
+                refs.append(None)
+        else:
+            refs.append(ref)
+    return refs
+
+
+def _decode_chars(data: np.ndarray) -> str:
+    """Decode MATLAB char arrays stored as uint16."""
+    if data.ndim == 0:
+        return chr(int(data))
+    flat = data.flatten()
+    return "".join(chr(c) for c in flat)
+
+
+def _try_to_dataframe(value: Any, name: str) -> Any:
+    """Attempt to convert a value to a pandas DataFrame."""
+    import pandas as pd
+
+    # MATLAB tables are already DataFrames
+    if isinstance(value, pd.DataFrame):
+        return value
+
+    if isinstance(value, np.ndarray) and value.ndim == 2:
+        return pd.DataFrame(value)
+    if isinstance(value, dict):
+        # Try to build a DataFrame from a struct where each field
+        # is an array of the same length (common MATLAB table pattern)
+        try:
+            return pd.DataFrame(value)
+        except (ValueError, TypeError):
+            return value
+    return value

mat73_reader-0.1.0.dist-info/METADATA

@@ -0,0 +1,213 @@
+Metadata-Version: 2.4
+Name: mat73-reader
+Version: 0.1.0
+Summary: Read MATLAB v7.3 HDF5 .mat files that scipy.io.loadmat cannot handle.
+Author-email: William Garrow <williamgarrow@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: hdf5,mat73,matlab,scientific-data,scipy
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.9
+Requires-Dist: h5py>=3.0
+Requires-Dist: numpy>=1.20
+Requires-Dist: pandas>=1.3
+Provides-Extra: dev
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# mat73-reader
+
+Read MATLAB v7.3 HDF5 `.mat` files in Python. **including MATLAB table objects** that other tools cannot decode.
+
+## The MATLAB Table Problem
+
+MATLAB v7.3 stores table objects using an undocumented internal system called MCOS (MATLAB Class Object System). Every existing Python tool (`scipy.io.loadmat()`, `mat73`, `hdf5storage`) fails on them:
+
+```python
+# scipy can't even open v7.3 files
+>>> scipy.io.loadmat("experiment.mat")
+NotImplementedError: Please use HDF reader for matlab v7.3 files
+
+# mat73 opens the file but returns None for every table
+>>> import mat73
+>>> data = mat73.loadmat("experiment.mat")
+ERROR: MATLAB type not supported: table, (uint32)   # x 800
+>>> data["task"]["gaze"][0]
+None
+```
+
+Tables are used extensively in neuroscience, signal processing, cognitive science, biomechanics, and clinical research datasets. If your `.mat` file contains tables, **mat73-reader is currently the only Python tool that can read them.**
+
+```python
+>>> from mat73_reader import load
+>>> data = load("experiment.mat")
+>>> data["task"]["gaze"][0]
+      gaze_timestamp  world_index  confidence  norm_pos_x  norm_pos_y  ...
+0        5410.551714          0.0    0.999499    0.446264    0.846886  ...
+1        5410.555834          0.0    0.999653    0.446534    0.847007  ...
+2        5410.559773          0.0    0.999648    0.446660    0.846410  ...
+...
+[8205 rows x 21 columns]
+```
+
+## How It Works
+
+When other tools encounter a MATLAB table, they see a `(1,6) uint32` header and stop. mat73-reader decodes the MCOS block structure to follow the reference chain to the actual data:
+
+```mermaid
+graph TD
+    subgraph "What other tools see"
+        A["Table Header<br/>(1,6) uint32<br/>0xDD000000 ..."] -->|"???"| B["None"]
+    end
+
+    subgraph "What mat73-reader decodes"
+        H["Table Header<br/>(1,6) uint32"] -->|"instance index"| M["MCOS Reference Array<br/>#subsystem#/MCOS"]
+        M -->|"block offset + 0"| D["Column Data Refs<br/>(ncols, 1) object"]
+        M -->|"block offset + 5"| N["Column Name Refs<br/>(ncols, 1) object"]
+        D -->|"dereference"| D1["timestamp<br/>float64 (1, N)"]
+        D -->|"dereference"| D2["confidence<br/>float64 (1, N)"]
+        D -->|"dereference"| D3["...<br/>float64 (1, N)"]
+        N -->|"dereference"| N1["'gaze_timestamp'<br/>uint16 chars"]
+        N -->|"dereference"| N2["'confidence'<br/>uint16 chars"]
+        N -->|"dereference"| N3["'...'<br/>uint16 chars"]
+        D1 & D2 & D3 & N1 & N2 & N3 -->|"assemble"| DF["pandas DataFrame"]
+    end
+
+    style B fill:#ff6b6b,color:#fff
+    style DF fill:#51cf66,color:#fff
+```
+
+Each table instance occupies a fixed block of 7 consecutive entries in the MCOS reference array:
+
+```
+Block layout (7 slots per table):
+  +0  (ncols, 1) object refs   --> column data arrays (float64, int, etc.)
+  +1  (1, 1) float64           --> ndims
+  +2  (1, 1) float64           --> nrows
+  +3  (2,) uint64              --> segment info
+  +4  (1, 1) float64           --> nvars (number of columns)
+  +5  (ncols, 1) object refs   --> column name strings (uint16-encoded)
+  +6  Group                    --> table properties (units, descriptions, etc.)
+```
+
+The instance index from the table header maps to a block offset:
+
+```
+block_start = 2 + (instance - 1) * 7
+```
+
+This structure is not documented by MathWorks. It was reverse-engineered by analyzing real-world scientific datasets.
+
+## Real-World Validation
+
+mat73-reader has been validated against the [COLET dataset](https://zenodo.org/records/7766785) (Cognitive workLoad Estimation via Eye-Tracking), a 3.8 GB MATLAB v7.3 file containing:
+
+- 47 subjects, 4 tasks per subject
+- 4 data fields per task (gaze, pupil, blinks, annotation)
+- **752 MATLAB table objects** total
+- Over 14,000 individual data arrays
+
+Every table was successfully decoded into a pandas DataFrame with correct column names and data types. Other Python tools return `None` for all 752 tables.
+
+## Installation
+
+```bash
+pip install mat73-reader
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/WilliamGarrow/mat73-reader.git
+cd mat73-reader
+pip install -e ".[dev]"
+```
+
+## Usage
+
+### Python API
+
+```python
+from mat73_reader import load, inspect
+
+# Inspect file contents without loading data
+variables = inspect("experiment.mat")
+for var in variables:
+    print(var)
+
+# Load everything
+data = load("experiment.mat")
+
+# Load a specific top-level variable
+results = load("experiment.mat", variable="results")
+
+# Force all compatible arrays to pandas DataFrames
+data = load("experiment.mat", as_dataframe=True)
+```
+
+MATLAB tables are always returned as DataFrames automatically, no flags needed.
+
+### Command Line
+
+```bash
+# List variables, types, and shapes
+mat73-reader inspect experiment.mat
+
+# Convert to CSV (one file per variable)
+mat73-reader convert experiment.mat --format csv --output ./csv_output/
+
+# Convert to JSON
+mat73-reader convert experiment.mat --format json --output experiment.json
+
+# Convert a single variable
+mat73-reader convert experiment.mat --variable gaze_data --format csv
+```
+
+## What It Handles
+
+| MATLAB Type | Python Type | Notes |
+|------------|-------------|-------|
+| **Table objects** | **`pandas.DataFrame`** | **Column names and data types preserved** |
+| Numeric arrays | `numpy.ndarray` | Transposed to row-major order |
+| Structs | `dict` | Nested to arbitrary depth |
+| Cell arrays | `list` | HDF5 object references resolved |
+| Char arrays | `str` | Decoded from uint16 |
+| Scalars | Python `int`/`float` | Single-element arrays squeezed |
+
+## When to Use This vs. Other Tools
+
+| Scenario | Tool |
+|----------|------|
+| `.mat` v5 or earlier (no tables) | `scipy.io.loadmat()` |
+| `.mat` v7.3 with arrays and structs only | `mat73` or **mat73-reader** |
+| `.mat` v7.3 with **table objects** | **mat73-reader** (only option in Python) |
+| Not sure what format you have | Try `mat73-reader` first; it will tell you if it's not v7.3 |
+
+## Development
+
+```bash
+git clone https://github.com/WilliamGarrow/mat73-reader.git
+cd mat73-reader
+python -m venv .venv
+source .venv/bin/activate
+pip install -e ".[dev]"
+pytest
+```
+
+### Test Suite
+
+38 tests covering:
+- Standard v7.3 reading (arrays, structs, cell arrays, char arrays, scalars)
+- MCOS table header detection (positive and negative cases)
+- Single and multi-table decoding with synthetic fixtures
+- Column name extraction and data value verification
+- Edge cases (non-table uint32 arrays, missing variables, invalid files)
+
+## License
+
+Apache 2.0. See [LICENSE](LICENSE) for details.

mat73_reader-0.1.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+mat73_reader/__init__.py,sha256=KHaNaOkshxbEYycuLeOPx-ig3ggkKu6UYNQzQtsXQ-4,164
+mat73_reader/cli.py,sha256=BXA3yBqD5_TWa5YVQyuoQp8HA9R-V76Yn6KwDsaz8M4,3052
+mat73_reader/converter.py,sha256=dxKEped_JZ9ELI9BFGE1CfOV5CS4Q7a82PoOtge0LII,2864
+mat73_reader/reader.py,sha256=0-MuCxqsx-bULtAoInlG7BszS92djpPswzx-D8PPOCg,13082
+mat73_reader-0.1.0.dist-info/METADATA,sha256=81D9HeZQS7zkhgBYvophLKCBzQ-S8WCxUu69oYHUUOE,7314
+mat73_reader-0.1.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+mat73_reader-0.1.0.dist-info/entry_points.txt,sha256=_g3IHPl5X6dgH3hib5MORe7q0o9Cuh2Jg3P5JeVWleQ,55
+mat73_reader-0.1.0.dist-info/licenses/LICENSE,sha256=OMUDZnvIFu9yLKN2HgPTsMmNUvEoVg7unVEm_YWtUpE,10765
+mat73_reader-0.1.0.dist-info/RECORD,,

mat73_reader-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.29.0
+Root-Is-Purelib: true
+Tag: py3-none-any

mat73_reader-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+mat73-reader = mat73_reader.cli:main

mat73_reader-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 William Garrow
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.