edjas 0.5.1__py3-none-any.whl

edjas/__init__.py

@@ -0,0 +1,35 @@
+import argparse
+import json
+import sys
+
+from importlib.metadata import PackageNotFoundError, version
+
+from .read_params import read_file
+
+try:
+    __version__ = version("edjas")
+except PackageNotFoundError:  # not installed (e.g. running from a source checkout)
+    __version__ = "0.0.0+unknown"
+
+__all__ = ["read_file", "__version__"]
+
+def main(argv=None):
+    parser = argparse.ArgumentParser(
+        prog="edjas",
+        description="Extract data in JSON from any spreadsheet.",
+    )
+    parser.add_argument("file", help="path to the spreadsheet to read")
+    parser.add_argument(
+        "-r",
+        "--range",
+        default="Parameters",
+        help="named range to use as the starting point (default: Parameters)",
+    )
+    parser.add_argument(
+        "--version",
+        action="version",
+        version=f"%(prog)s {__version__}",
+    )
+    args = parser.parse_args(argv)
+    json.dump(read_file(args.file, args.range), sys.stdout)
+    sys.stdout.write("\n")

edjas/find_first.py

@@ -0,0 +1,49 @@
+from openpyxl import Workbook
+from openpyxl.cell import Cell
+from openpyxl.worksheet.worksheet import Worksheet
+
+
+def column(sheet: Worksheet) -> Cell:
+    """
+    Return the first cell of the first non-blank column in the sheet.
+
+    Args:
+        sheet (openpyxl.worksheet.worksheet.Worksheet): The worksheet to search.
+
+    Returns:
+        openpyxl.cell.Cell: The first non-blank cell scanning column by column,
+        or None if every cell is blank.
+    """
+    for col in sheet.iter_cols():
+        for cell in col:
+            if cell is not None and cell.value:  # Check if the cell is not empty
+                return cell
+
+def row(sheet: Worksheet) -> Cell:
+    """
+    Return the first cell of the first non-blank row in the sheet.
+
+    Args:
+        sheet (openpyxl.worksheet.worksheet.Worksheet): The worksheet to search.
+
+    Returns:
+        openpyxl.cell.Cell: The first non-blank cell scanning row by row,
+        or None if every cell is blank.
+    """
+    for row in sheet.iter_rows():
+        for cell  in row:
+            if cell is not None and cell.value:  # Check if the cell is not empty
+                return cell
+
+def top_left(sheet: Worksheet) -> Cell:
+    """
+    Return the top-left cell of the sheet's used data range.
+
+    Args:
+        sheet (openpyxl.worksheet.worksheet.Worksheet): The worksheet to search.
+
+    Returns:
+        openpyxl.cell.Cell: The cell at the top-left corner of the used range.
+    """
+    data_range = sheet.calculate_dimension()
+    return sheet[data_range][0][0]

edjas/read_params.py

@@ -0,0 +1,74 @@
+import sys
+
+import openpyxl
+
+def extract_values(sheet, range_spec, flatten=True):
+    result = []
+    for row in sheet[range_spec]:
+        result.append([c.value for c in row])
+    if not flatten:
+        return result
+    if len(result) == 1:
+        return result[0]
+    elif len(result[0]) == 1:
+        return [r[0] for r in result]
+    else:
+        return result
+
+def range_values(wb, range_spec, flatten=True):
+    if range_spec in wb.defined_names:
+        range_spec = wb.defined_names[range_spec].attr_text
+    if "!" in range_spec:
+        sheet_name, cell_refs = range_spec.split("!")
+        sheet = wb[sheet_name]
+    else:
+        sheet = wb.active
+        cell_refs = range_spec
+    return extract_values(sheet, cell_refs, flatten=flatten)
+
+def range_to_dict(workbook, range_spec):
+    # Get the rows in the given range
+    rows = range_values(workbook, range_spec, flatten=False)
+    if len(rows[0]) != 2:
+        raise ValueError(f"Range spec {range_spec} should have two columns")
+    # Initialize the result dictionary
+    result = {}
+    i = 0
+    for key, value in rows:
+        # Skip empty rows, but complain about floating values
+        if key is None:
+            if value is None:
+                continue
+            else:
+                raise ValueError("Empty key not expected on value {value!r} - programming error?")
+        # Check if the value is a range name enclosed in braces: dictionary
+        if type(value) is str:
+            if value.startswith("{") and value.endswith("}"):
+                # Extract the named range name (e.g., "SubParameters" from "{SubParameters}")
+                ref_range_spec = value[1:-1]
+                # Recursively process the referenced named range
+                result[key] = range_to_dict(workbook, ref_range_spec)
+            # Otherwise "[range]" references a list or matrix.
+            elif value.startswith("[") and value.endswith("]"):
+                ref_range_spec = value[1:-1]
+                result[key] = range_values(workbook, ref_range_spec)
+            else:
+                result[key] = value
+        else:
+            # Single value
+            result[key] = value
+    return result
+
+def read_file(file_name, range_name="Parameters"):
+    # Load the Excel workbook
+    workbook = openpyxl.load_workbook(file_name, data_only=False)
+    return range_to_dict(workbook, range_name)
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        sys.exit("Requires spreadsheet arguments")
+    if len(sys.argv) > 3:
+        sys.exit("Sorry, only handling one or two arguments for now")
+    from pprint import pprint
+    data = read_file(*sys.argv[1:])
+    pprint(data)

edjas-0.5.1.dist-info/METADATA

@@ -0,0 +1,71 @@
+Metadata-Version: 2.4
+Name: edjas
+Version: 0.5.1
+Summary: Extract data in JSON from any spreadsheet
+Author-email: Steve Holden <steve@holdenweb.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: data-extraction,excel,json,openpyxl,reporting,spreadsheet,xlsx
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Office/Business :: Financial :: Spreadsheet
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.12
+Requires-Dist: openpyxl<4.0.0,>=3.1.5
+Description-Content-Type: text/markdown
+
+# EDJAS: Extract Data in JSON from Any Spreadsheet
+
+- Sources at https://github.com/holdenweb/edjas
+
+This project is an attempt to help organisations that insist on managing
+their businesses, or major aspects thereof, using spreadsheets.
+Many articles have been written on the limitations of spreadsheet technology.
+If you have any doubts then look at the "The Problem with Spreadsheets"
+section of this [LinkedIn
+article](https://www.linkedin.com/pulse/spreadsheets-inadequate-effective-management--gjsse/).
+Some large organisations are now
+[providing advice](https://www.gov.uk/guidance/creating-and-sharing-spreadsheets)
+— although in many cases better advice might be:
+_stop using spreadsheets for that_!
+
+Rather than try to change the way people do business (imagine "If I Ruled the
+World" playing softly in the background), EDJAS is intended to help people extract
+that locked-up data more effectively, in simple and easy-to-understand ways
+that don't affect existing workflows.
+
+It lets you add data specifications to any existing spreadsheet by creating
+named ranges in the spreadsheet. By default EDJAS will look for a range
+name `Parameters` as its starting point, although this can be overridden on the command line.
+This range should be precisely two columns wide, and EDJAS
+treats the left-hand column as names and the right-hand column as values.
+Normally, the values are used literally after extraction from the spreadsheet.
+Two formats for the value are given special treatment.
+
+  - `[range-name]`: the named range is exported as a JSON list or, if  it's two-dimensional a list of row lists.
+  - `{range_name}`: The named range, which must be two columns wide, becomes a JSON object where the left-hand column specifies
+    the names and the right-hand column specifies the values.
+
+The parameter details are used to extract data from the spreadsheet, which is then sent to standard output as JSON.
+
+![Parameter specifications in EDJAS](images/parameters.png "Parameter specifications in EDJAS")
+
+In the example shown, the `version` key has a dict value, and in that dict the `number` key has a value of "1.0.2".
+The version number can therefore be referenced in the JSON output as `version.number`. The output from this example is shown below.
+
+
+![Parameter data extracted from a spreadsheet](images/json.png "The parameter data")
+
+A demonstration of the system can be found at [https://github.com/holdenweb/edjas-demo](https://github.com/holdenweb/edjas-demo).
+
+This is particularly useful for audiences that have an interest in only a
+limited number of features from a possibly quite large spreadsheet.
+More generally, JSON is such a widely used format that spreadsheet data can
+be re-used in a wide range of systems as appropriate.

edjas-0.5.1.dist-info/RECORD

@@ -0,0 +1,8 @@
+edjas/__init__.py,sha256=HGHNJ0IH45E5WiQGJ-wfWN4JVRzWql_xSqgB4uf1u98,977
+edjas/find_first.py,sha256=t7zJQUobjhqYkj3Ahl1XQeff38jHrHr1HTRqMzWFJFY,1525
+edjas/read_params.py,sha256=4LP6JAbNt-Y1RRTun3Tr0Ex5EzaE4XrXSPvXNvxq69M,2660
+edjas-0.5.1.dist-info/METADATA,sha256=mz51Sym-A-r7o5sMjMs469DGqbSL89Mibx77kB8Q4mw,3711
+edjas-0.5.1.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+edjas-0.5.1.dist-info/entry_points.txt,sha256=J1HXWdLo-WZ0TLUgEk16uDxFUZ8kvvB6Q5z_1fYXomA,37
+edjas-0.5.1.dist-info/licenses/LICENSE,sha256=YdiT5URXWh-yGtoqz8kfS199rVB7_lBvivJfuRyOfTc,1074
+edjas-0.5.1.dist-info/RECORD,,

edjas-0.5.1.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

edjas-0.5.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+edjas = edjas:main

edjas-0.5.1.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025-2026 Steve Holden
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.