From b0e0182c9bf5588af551a78bd4d24b2e711963f8 Mon Sep 17 00:00:00 2001
From: SuperUser <michael.heerkens@helloprint.com>
Date: Mon, 2 Mar 2026 09:41:03 +0000
Subject: [PATCH] Add xlsx office validate

---
 xlsx/scripts/office/validate.py | 111 ++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)
 create mode 100644 xlsx/scripts/office/validate.py

diff --git a/xlsx/scripts/office/validate.py b/xlsx/scripts/office/validate.py
new file mode 100644
index 0000000..03b01f6
--- /dev/null
+++ b/xlsx/scripts/office/validate.py
@@ -0,0 +1,111 @@
+"""
+Command line tool to validate Office document XML files against XSD schemas and tracked changes.
+
+Usage:
+    python validate.py <path> [--original <original_file>] [--auto-repair] [--author NAME]
+
+The first argument can be either:
+- An unpacked directory containing the Office document XML files
+- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory
+
+Auto-repair fixes:
+- paraId/durableId values that exceed OOXML limits
+- Missing xml:space="preserve" on w:t elements with whitespace
+"""
+
+import argparse
+import sys
+import tempfile
+import zipfile
+from pathlib import Path
+
+from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Validate Office document XML files")
+    parser.add_argument(
+        "path",
+        help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)",
+    )
+    parser.add_argument(
+        "--original",
+        required=False,
+        default=None,
+        help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.",
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Enable verbose output",
+    )
+    parser.add_argument(
+        "--auto-repair",
+        action="store_true",
+        help="Automatically repair common issues (hex IDs, whitespace preservation)",
+    )
+    parser.add_argument(
+        "--author",
+        default="Claude",
+        help="Author name for redlining validation (default: Claude)",
+    )
+    args = parser.parse_args()
+
+    path = Path(args.path)
+    assert path.exists(), f"Error: {path} does not exist"
+
+    original_file = None
+    if args.original:
+        original_file = Path(args.original)
+        assert original_file.is_file(), f"Error: {original_file} is not a file"
+        assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], (
+            f"Error: {original_file} must be a .docx, .pptx, or .xlsx file"
+        )
+
+    file_extension = (original_file or path).suffix.lower()
+    assert file_extension in [".docx", ".pptx", ".xlsx"], (
+        f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file."
+    )
+
+    if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]:
+        temp_dir = tempfile.mkdtemp()
+        with zipfile.ZipFile(path, "r") as zf:
+            zf.extractall(temp_dir)
+        unpacked_dir = Path(temp_dir)
+    else:
+        assert path.is_dir(), f"Error: {path} is not a directory or Office file"
+        unpacked_dir = path
+
+    match file_extension:
+        case ".docx":
+            validators = [
+                DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
+            ]
+            if original_file:
+                validators.append(
+                    RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author)  
+                )
+        case ".pptx":
+            validators = [
+                PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
+            ]
+        case _:
+            print(f"Error: Validation not supported for file type {file_extension}")
+            sys.exit(1)
+
+    if args.auto_repair:
+        total_repairs = sum(v.repair() for v in validators)
+        if total_repairs:
+            print(f"Auto-repaired {total_repairs} issue(s)")
+
+    success = all(v.validate() for v in validators)
+
+    if success:
+        print("All validations PASSED!")
+
+    sys.exit(0 if success else 1)
+
+
+if __name__ == "__main__":
+    main()