Skip to content

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

feat(svg_to_pptx): stamp accurate doc properties, optional metadata.json

hugohe3d6f6cdfa97ea
diff --git a/skills/ppt-master/scripts/svg_to_pptx/pptx_builder.py b/skills/ppt-master/scripts/svg_to_pptx/pptx_builder.py
index 42cddb98..55f068cf 100644
--- a/skills/ppt-master/scripts/svg_to_pptx/pptx_builder.py
+++ b/skills/ppt-master/scripts/svg_to_pptx/pptx_builder.py
@@ -12,8 +12,10 @@ import shutil
import tempfile
import zipfile
from concurrent.futures import ProcessPoolExecutor, as_completed
+from datetime import datetime, timezone
from pathlib import Path
from typing import Any
+from xml.sax.saxutils import escape
from pptx import Presentation
from pptx.util import Emu
@@ -327,6 +329,102 @@ def _verify_internal_rels_targets(extract_dir: Path) -> list[str]:
return problems
+def _presentation_format(width: float, height: float) -> str:
+ """Map the slide aspect ratio to PowerPoint's PresentationFormat label.
+ Non-standard ratios (square, portrait, banner crops) report 'Custom'.
+ """
+ if width <= 0 or height <= 0:
+ return 'Custom'
+ ratio = width / height
+ for target, label in (
+ (4 / 3, 'On-screen Show (4:3)'),
+ (16 / 9, 'On-screen Show (16:9)'),
+ (16 / 10, 'On-screen Show (16:10)'),
+ ):
+ if abs(ratio - target) < 0.02:
+ return label
+ return 'Custom'
+
+
+def _stamp_docprops(
+ extract_dir: Path,
+ slide_count: int,
+ pres_format: str,
+ meta: dict[str, Any] | None = None,
+) -> None:
+ """Overwrite the misleading python-pptx default metadata with accurate
+ values. Factual fields (slide count, export timestamp, presentation format,
+ application) are always machine-derived. Authored fields — including the
+ title — come solely from an optional per-project ``metadata.json``
+ (``meta``); whatever it omits stays blank. ``lastModifiedBy`` follows
+ ``creator`` rather than ever carrying the base template's author or a tool
+ name. No field is guessed from slide content: a blank title is preferable
+ to an unreliable heuristic pick.
+ """
+ meta = meta or {}
+
+ def field(key: str, default: str = '') -> str:
+ value = meta.get(key)
+ return value.strip() if isinstance(value, str) and value.strip() else default
+
+ title = field('title')
+ creator = field('creator')
+
+ now = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
+
+ core_path = extract_dir / 'docProps' / 'core.xml'
+ if core_path.exists():
+ core_path.write_text(
+ "<?xml version='1.0' encoding='UTF-8' standalone='yes'?>\n"
+ '<cp:coreProperties '
+ 'xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties" '
+ 'xmlns:dc="http://purl.org/dc/elements/1.1/" '
+ 'xmlns:dcterms="http://purl.org/dc/terms/" '
+ 'xmlns:dcmitype="http://purl.org/dc/dcmitype/" '
+ 'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">'
+ f'<dc:title>{escape(title)}</dc:title>'
+ f'<dc:subject>{escape(field("subject"))}</dc:subject>'
+ f'<dc:creator>{escape(creator)}</dc:creator>'
+ f'<cp:keywords>{escape(field("keywords"))}</cp:keywords>'
+ f'<dc:description>{escape(field("description"))}</dc:description>'
+ f'<dc:language>{escape(field("language"))}</dc:language>'
+ f'<cp:lastModifiedBy>{escape(creator)}</cp:lastModifiedBy>'
+ '<cp:revision>1</cp:revision>'
+ f'<dcterms:created xsi:type="dcterms:W3CDTF">{now}</dcterms:created>'
+ f'<dcterms:modified xsi:type="dcterms:W3CDTF">{now}</dcterms:modified>'
+ f'<cp:category>{escape(field("category"))}</cp:category>'
+ f'<cp:contentStatus>{escape(field("contentStatus"))}</cp:contentStatus>'
+ '</cp:coreProperties>',
+ encoding='utf-8',
+ )
+
+ app_path = extract_dir / 'docProps' / 'app.xml'
+ if app_path.exists():
+ app = app_path.read_text(encoding='utf-8')
+ app = re.sub(r'<Slides>.*?</Slides>', f'<Slides>{slide_count}</Slides>', app)
+ app = re.sub(
+ r'<Company>.*?</Company>',
+ f'<Company>{escape(field("company"))}</Company>',
+ app,
+ )
+ app = re.sub(
+ r'<Manager>.*?</Manager>',
+ f'<Manager>{escape(field("manager"))}</Manager>',
+ app,
+ )
+ app = re.sub(
+ r'<Application>.*?</Application>',
+ '<Application>Microsoft Office PowerPoint</Application>',
+ app,
+ )
+ app = re.sub(
+ r'<PresentationFormat>.*?</PresentationFormat>',
+ f'<PresentationFormat>{escape(pres_format)}</PresentationFormat>',
+ app,
+ )
+ app_path.write_text(app, encoding='utf-8')
+
+
def create_pptx_with_native_svg(
svg_files: list[Path],
output_path: Path,
@@ -352,6 +450,7 @@ def create_pptx_with_native_svg(
workers: int | None = None,
merge_paragraphs: bool = True,
conversion_trace_path: Path | None = None,
+ doc_metadata: dict[str, Any] | None = None,
) -> bool:
"""Create a PPTX file with native SVG.
@@ -849,6 +948,12 @@ def create_pptx_with_native_svg(
'PowerPoint will report the file as corrupt:\n' + details
)
+ # Replace the python-pptx base-template metadata (stale "Steve Canny"
+ # author, 2013 dates, "generated using python-pptx", Slides=0) with
+ # accurate, tool-neutral document properties.
+ pres_format = _presentation_format(width_emu, height_emu)
+ _stamp_docprops(extract_dir, len(svg_files), pres_format, doc_metadata)
+
# Repackage PPTX to a temporary file first. The public output path is
# replaced only after every slide and relationship has succeeded.
temp_output_path = temp_dir / 'result.pptx'
diff --git a/skills/ppt-master/scripts/svg_to_pptx/pptx_cli.py b/skills/ppt-master/scripts/svg_to_pptx/pptx_cli.py
index cb30db77..cb6497a9 100644
--- a/skills/ppt-master/scripts/svg_to_pptx/pptx_cli.py
+++ b/skills/ppt-master/scripts/svg_to_pptx/pptx_cli.py
@@ -3,6 +3,7 @@
from __future__ import annotations
import sys
+import json
import shutil
import argparse
from datetime import datetime
@@ -485,8 +486,26 @@ Recorded narration:
# svg_files is per-product (native vs legacy may now read different
# directories); everything else is shared.
+ # Optional per-project document properties. Absent file → factual fields
+ # are still stamped at export; only the authored fields stay blank.
+ doc_metadata = None
+ metadata_path = project_path / 'metadata.json'
+ if metadata_path.is_file():
+ try:
+ loaded = json.loads(metadata_path.read_text(encoding='utf-8'))
+ except (json.JSONDecodeError, OSError) as exc:
+ print(f" [warn] metadata.json ignored ({exc})", file=sys.stderr)
+ else:
+ if isinstance(loaded, dict):
+ doc_metadata = loaded
+ if verbose:
+ print(f" Document properties: metadata.json ({len(loaded)} field(s))")
+ else:
+ print(" [warn] metadata.json ignored (top level is not an object)", file=sys.stderr)
+
shared_kwargs = dict(
canvas_format=canvas_format,
+ doc_metadata=doc_metadata,
verbose=verbose,
transition=transition,
transition_duration=transition_duration,