fix dup logo

pov-doc/SKILL.md

@@ -142,6 +142,4 @@ Review the markdown examples to match tone, structure, and formatting convention
 
 ## Output
 
-Write the generated markdown document to `~/notes/Inbox/` with the filename format `[Customer Name] POC Criteria.md`.
+Write both the generated markdown and the rendered .odt to `~/notes/Inbox/agent/`. Use the filename format `[Customer Name] POC Criteria.md` and `[Customer Name] POC Criteria.odt`.
-
-After rendering, the .odt file should be placed alongside the markdown or in the same location the user specifies.

pov-doc/scripts/render_poc.py

@@ -27,6 +27,7 @@ import re
 import subprocess
 import sys
 import tempfile
+import zipfile
 from pathlib import Path
 
 
@@ -44,9 +45,11 @@ def find_reference_doc() -> Path:
     # Fallback: look for the El Paso doc and warn
     alt = skill_dir / "examples" / "City of El Paso POC Criteria.odt"
     if alt.exists():
-        print("Warning: using City of El Paso reference (may carry over logos). "
+        print(
+            "Warning: using City of El Paso reference (may carry over logos). "
             "Run create_reference_template() to generate a clean template.",
-              file=sys.stderr)
+            file=sys.stderr,
+        )
         return alt
     return None
 
@@ -60,13 +63,16 @@ def find_verkada_logo() -> Path:
     return None
 
 
-def resize_logo_if_needed(input_path: str, max_width_inches: float = 2.75, dpi: int = 150) -> str:
+def resize_logo_if_needed(
+    input_path: str, max_width_inches: float = 2.75, dpi: int = 150
+) -> str:
     """
     Resize a logo image if it exceeds the target width for print.
     Returns the path to the (possibly new) resized image.
     """
     try:
         from PIL import Image
+
         img = Image.open(input_path)
         width_px, height_px = img.size
         max_width_px = int(max_width_inches * dpi)
@@ -103,8 +109,8 @@ def process_markdown(
 
     # Replace customer logo placeholder (match any logo comment that is NOT Verkada)
     md_content = re.sub(
-        r'<!--\s*Image goes here:(?!.*?Verkada).*?logo.*?-->\s*\n?',
+        r"<!--\s*Image goes here:(?!.*?Verkada).*?logo.*?-->\s*\n?",
-        f'![Customer Logo]({customer_logo_path})\n\n',
+        f"![Customer Logo]({customer_logo_path})\n\n",
         md_content,
         flags=re.IGNORECASE,
     )
@@ -112,16 +118,16 @@ def process_markdown(
     # Replace Verkada logo placeholder
     if verkada_logo_path:
         md_content = re.sub(
-            r'<!--\s*Image goes here:.*?Verkada.*?logo.*?-->\s*\n?',
+            r"<!--\s*Image goes here:.*?Verkada.*?logo.*?-->\s*\n?",
-            f'![Verkada Logo]({verkada_logo_path})\n',
+            f"![Verkada Logo]({verkada_logo_path})\n",
             md_content,
             flags=re.IGNORECASE,
         )
     else:
         # Remove the Verkada logo placeholder entirely
         md_content = re.sub(
-            r'<!--\s*Image goes here:.*?Verkada.*?logo.*?-->\s*\n?',
+            r"<!--\s*Image goes here:.*?Verkada.*?logo.*?-->\s*\n?",
-            '',
+            "",
             md_content,
             flags=re.IGNORECASE,
         )
@@ -143,10 +149,14 @@ def convert_with_pandoc(md_path: str, output_path: str, reference_doc: str) -> b
     cmd = [
         "pandoc",
         md_path,
-        "-o", output_path,
+        "-o",
-        "--from", "markdown",
+        output_path,
-        "--to", "odt",
+        "--from",
-        "--reference-doc", reference_doc,
+        "markdown",
+        "--to",
+        "odt",
+        "--reference-doc",
+        reference_doc,
     ]
 
     try:
@@ -156,23 +166,108 @@ def convert_with_pandoc(md_path: str, output_path: str, reference_doc: str) -> b
             return False
         return True
     except FileNotFoundError:
-        print("Error: pandoc not found. Install it with your package manager.", file=sys.stderr)
+        print(
+            "Error: pandoc not found. Install it with your package manager.",
+            file=sys.stderr,
+        )
         return False
     except subprocess.TimeoutExpired:
         print("Error: pandoc timed out", file=sys.stderr)
         return False
 
 
+def _remove_elements_from_xml(
+    data: bytes, xpath_to_remove: list[tuple[str, dict]]
+) -> bytes:
+    """Remove elements matching the given xpath patterns from ODT XML data."""
+    import xml.etree.ElementTree as ET
+
+    tree = ET.fromstring(data)
+    changed = False
+    for xpath, ns in xpath_to_remove:
+        for el in tree.findall(xpath, ns):
+            for parent in tree.iter():
+                if el in list(parent):
+                    parent.remove(el)
+                    changed = True
+                    break
+    if changed:
+        return ET.tostring(tree, encoding="unicode", xml_declaration=True).encode(
+            "utf-8"
+        )
+    return data
+
+
+def _odt_ns() -> dict:
+    return {
+        "text": "urn:oasis:names:tc:opendocument:xmlns:text:1.0",
+        "office": "urn:oasis:names:tc:opendocument:xmlns:office:1.0",
+        "style": "urn:oasis:names:tc:opendocument:xmlns:style:1.0",
+        "draw": "urn:oasis:names:tc:opendocument:xmlns:drawing:1.0",
+    }
+
+
+def remove_heading_bookmarks(odt_path: str) -> None:
+    """Remove bookmark-start and bookmark-end elements from the ODT content.xml."""
+    ns = _odt_ns()
+    bookmarks_xpath = [
+        (".//text:bookmark", ns),
+        (".//text:bookmark-start", ns),
+        (".//text:bookmark-end", ns),
+    ]
+
+    tmp_path = odt_path + ".tmp"
+    with zipfile.ZipFile(odt_path, "r") as zin:
+        with zipfile.ZipFile(tmp_path, "w", zipfile.ZIP_DEFLATED) as zout:
+            for item in zin.infolist():
+                data = zin.read(item.filename)
+                if item.filename == "content.xml":
+                    data = _remove_elements_from_xml(data, bookmarks_xpath)
+                zout.writestr(item, data)
+
+    os.replace(tmp_path, odt_path)
+
+
+def remove_header_images(odt_path: str) -> None:
+    """Remove draw:frame elements from the header in styles.xml to strip reference doc logos."""
+    ns = _odt_ns()
+    frames_xpath = [
+        (".//style:header//draw:frame", ns),
+        (".//style:footer//draw:frame", ns),
+    ]
+
+    tmp_path = odt_path + ".tmp"
+    with zipfile.ZipFile(odt_path, "r") as zin:
+        with zipfile.ZipFile(tmp_path, "w", zipfile.ZIP_DEFLATED) as zout:
+            for item in zin.infolist():
+                data = zin.read(item.filename)
+                if item.filename == "styles.xml":
+                    data = _remove_elements_from_xml(data, frames_xpath)
+                zout.writestr(item, data)
+
+    os.replace(tmp_path, odt_path)
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Render a Verkada POC Criteria markdown document as a formatted .odt file."
     )
-    parser.add_argument("--input", "-i", required=True, help="Path to the POC Criteria markdown file")
+    parser.add_argument(
-    parser.add_argument("--customer-logo", required=True, help="Path to the customer logo image")
+        "--input", "-i", required=True, help="Path to the POC Criteria markdown file"
-    parser.add_argument("--verkada-logo", help="Path to the Verkada logo image (optional)")
+    )
-    parser.add_argument("--mission", help="Customer mission statement (replaces existing)")
+    parser.add_argument(
+        "--customer-logo", required=True, help="Path to the customer logo image"
+    )
+    parser.add_argument(
+        "--verkada-logo", help="Path to the Verkada logo image (optional)"
+    )
+    parser.add_argument(
+        "--mission", help="Customer mission statement (replaces existing)"
+    )
     parser.add_argument("--reference-doc", help="Path to reference .odt for formatting")
-    parser.add_argument("--output", "-o", help="Output .odt path (default: same as input with .odt)")
+    parser.add_argument(
+        "--output", "-o", help="Output .odt path (default: same as input with .odt)"
+    )
 
     args = parser.parse_args()
 
@@ -190,9 +285,11 @@ def main():
     # Find reference doc
     reference_doc = args.reference_doc or find_reference_doc()
     if not reference_doc or not Path(reference_doc).exists():
-        print("Error: reference document not found. Provide --reference-doc or place the "
+        print(
+            "Error: reference document not found. Provide --reference-doc or place the "
             "City of El Paso POC Criteria.odt in the skill's examples directory.",
-              file=sys.stderr)
+            file=sys.stderr,
+        )
         sys.exit(1)
 
     # Find Verkada logo
@@ -235,6 +332,8 @@ def main():
         success = convert_with_pandoc(temp_md, output_path, reference_doc)
 
         if success:
+            remove_heading_bookmarks(output_path)
+            remove_header_images(output_path)
             out_size = os.path.getsize(output_path)
             print(f"Done: {output_path} ({out_size:,} bytes)")
         else: