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

fix(beautify): keep chart titles in the frozen inventory and its verifier

hugohe3694bdacac7e6
diff --git a/skills/ppt-master/scripts/beautify_inventory.py b/skills/ppt-master/scripts/beautify_inventory.py
index bf439669..0f26e551 100644
--- a/skills/ppt-master/scripts/beautify_inventory.py
+++ b/skills/ppt-master/scripts/beautify_inventory.py
@@ -113,6 +113,7 @@ def build_inventory(slide_library: dict, images_by_slide: dict[int, list[dict]])
{
"chart_id": c.get("chart_id"),
"chart_type": c.get("chart_type"),
+ "title": c.get("title", ""),
"category_count": c.get("category_count"),
"series_count": c.get("series_count"),
"categories": c.get("categories", []), # frozen data
@@ -240,6 +241,8 @@ def _frozen_strings(slide: dict) -> list[str]:
for row in table.get("cells", []):
strings.extend(cell for cell in row if cell and cell.strip())
for chart in slide.get("charts", []):
+ if chart.get("title"):
+ strings.append(chart["title"])
strings.extend(str(c) for c in chart.get("categories", []) if str(c).strip())
strings.extend(str(series.get("name")) for series in chart.get("series", []) if series.get("name"))
for diagram in slide.get("diagrams", []):
@@ -259,6 +262,7 @@ def _exported_text_by_slide(pptx_path: Path) -> dict[int, str]:
for row in table.get("rows", []):
parts.extend(cell.get("text", "") for cell in row.get("cells", []))
for chart in slide.get("charts", []):
+ parts.append(chart.get("title", ""))
parts.extend(str(c) for c in chart.get("categories", []))
parts.extend(str(series.get("name", "")) for series in chart.get("series", []))
for diagram in slide.get("diagrams", []):
diff --git a/skills/ppt-master/scripts/docs/conversion.md b/skills/ppt-master/scripts/docs/conversion.md
index bede0342..89c877c2 100644
--- a/skills/ppt-master/scripts/docs/conversion.md
+++ b/skills/ppt-master/scripts/docs/conversion.md
@@ -266,7 +266,7 @@ python3 scripts/pptx_intake.py deck.pptx -o projects/demo/analysis
Outputs (per source deck, prefixed by file stem):
- `<stem>.identity.json` — canvas size/aspect, theme palette/fonts, observed colors/fonts
-- `<stem>.slide_library.json` — text slots, geometry, native tables, native chart display caches, and SmartArt nodes/connections
+- `<stem>.slide_library.json` — text slots, geometry, native tables, native chart titles/display caches, and SmartArt nodes/connections. Chart titles include rich text and linked-string caches; Beautify carries them into its frozen inventory and verifies their presence in the exported deck.
- `source_profile.json` — the single multi-deck index: a compact Strategist-facing digest per deck (over identity, tables, charts, SmartArt, and page types) under `decks[]`, with prefixed artifact pointers
`project_manager.py import-sources` runs this automatically for PPTX/PPTM/PPSX/PPSM/POTX/POTM inputs and stores the bundle directly under `analysis/`. Multi-deck per project: each deck uses its archived stem, including any collision suffix, for `<stem>.*` artifacts and its `decks[]` entry in the shared `source_profile.json` index. Re-running intake for an existing archived stem replaces its entry. The beautify profile stays single-deck and reads one chosen deck's `<stem>.*` artifacts.
diff --git a/skills/ppt-master/scripts/pptx_ooxml/chart_read.py b/skills/ppt-master/scripts/pptx_ooxml/chart_read.py
index 59047be7..c4653558 100644
--- a/skills/ppt-master/scripts/pptx_ooxml/chart_read.py
+++ b/skills/ppt-master/scripts/pptx_ooxml/chart_read.py
@@ -9,7 +9,7 @@ from __future__ import annotations
from typing import Any
from xml.etree import ElementTree as ET
-from .ooxml import NS
+from .ooxml import NS, _paragraph_texts
def empty_chart_data() -> dict[str, Any]:
@@ -19,6 +19,7 @@ def empty_chart_data() -> dict[str, Any]:
"series_count": 0,
"categories": [],
"series": [],
+ "title": "",
}
@@ -74,10 +75,18 @@ def _series_name(series: ET.Element, fallback: str) -> str:
def read_chart_data(chart_root: ET.Element) -> dict[str, Any]:
- """Return a compact summary of chart type, categories, series, and values."""
+ """Return the chart title, type, categories, series, and values."""
+ title_node = chart_root.find("c:chart/c:title/c:tx", NS)
+ title = ""
+ if title_node is not None:
+ rich = title_node.find("c:rich", NS)
+ title = (
+ "\n".join(_paragraph_texts(rich))
+ if rich is not None else "\n".join(map(str, _cache_values(title_node)))
+ )
chart_types = _chart_types_with_series(chart_root)
if not chart_types:
- return empty_chart_data()
+ return {**empty_chart_data(), "title": title}
first_series = chart_types[0].find("c:ser", NS)
categories = _cache_values(first_series.find("c:cat", NS)) if first_series is not None else []
@@ -106,4 +115,5 @@ def read_chart_data(chart_root: ET.Element) -> dict[str, Any]:
"series_count": len(series_payload),
"categories": categories,
"series": series_payload,
+ "title": title,
}
diff --git a/skills/ppt-master/scripts/tests/test_beautify_chart_title_survival.py b/skills/ppt-master/scripts/tests/test_beautify_chart_title_survival.py
new file mode 100644
index 00000000..fd8f301b
--- /dev/null
+++ b/skills/ppt-master/scripts/tests/test_beautify_chart_title_survival.py
@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""Keep visible chart titles across PPTX intake and Beautify verification.
+
+Usage:
+ python3 -m unittest tests.test_beautify_chart_title_survival
+
+Dependencies:
+ python-pptx and the script runtime dependencies.
+"""
+
+from __future__ import annotations
+
+import contextlib
+import io
+import json
+from pathlib import Path
+import sys
+import tempfile
+import unittest
+import zipfile
+from xml.etree import ElementTree as ET
+
+from pptx import Presentation
+from pptx.chart.data import ChartData
+from pptx.enum.chart import XL_CHART_TYPE
+from pptx.util import Inches
+
+SCRIPTS = Path(__file__).resolve().parents[1]
+if str(SCRIPTS) not in sys.path:
+ sys.path.insert(0, str(SCRIPTS))
+
+import beautify_inventory # noqa: E402
+import pptx_intake # noqa: E402
+
+NS = {
+ "a": "http://schemas.openxmlformats.org/drawingml/2006/main",
+ "c": "http://schemas.openxmlformats.org/drawingml/2006/chart",
+}
+
+
+class BeautifyChartTitleSurvivalTests(unittest.TestCase):
+ def setUp(self) -> None:
+ temporary = tempfile.TemporaryDirectory()
+ self.addCleanup(temporary.cleanup)
+ self.root = Path(temporary.name)
+ self.source = self.root / "source.pptx"
+ presentation = Presentation()
+ slide = presentation.slides.add_slide(presentation.slide_layouts[6])
+ data = ChartData()
+ data.categories = ["CATEGORY_MARKER"]
+ data.add_series("SERIES_MARKER", [271])
+ chart = slide.shapes.add_chart(
+ XL_CHART_TYPE.COLUMN_CLUSTERED,
+ Inches(1), Inches(1), Inches(8), Inches(5), data,
+ ).chart
+ chart.has_title = True
+ chart.chart_title.text_frame.text = "TITLE_MARKER\n第二行 & <exact>"
+ presentation.save(self.source)
+
+ def _intake(self) -> tuple[Path, dict]:
+ analysis = self.root / "analysis"
+ inventory = analysis / "inventory.json"
+ with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(io.StringIO()):
+ self.assertEqual(pptx_intake.main([str(self.source), "-o", str(analysis)]), 0)
+ self.assertEqual(beautify_inventory.main([
+ str(analysis / "source.slide_library.json"), "-o", str(inventory),
+ ]), 0)
+ return inventory, json.loads(inventory.read_text(encoding="utf-8"))
+
+ def _mutate_chart(self, mutation) -> None:
+ with zipfile.ZipFile(self.source) as archive:
+ entries = {name: archive.read(name) for name in archive.namelist()}
+ chart = ET.fromstring(entries["ppt/charts/chart1.xml"])
+ mutation(chart)
+ entries["ppt/charts/chart1.xml"] = ET.tostring(chart, encoding="utf-8")
+ with zipfile.ZipFile(self.source, "w") as archive:
+ for name, payload in entries.items():
+ archive.writestr(name, payload)
+
+ def test_rich_title_survives_intake_and_missing_title_fails_verification(self) -> None:
+ inventory, payload = self._intake()
+ title = "TITLE_MARKER\n第二行 & <exact>"
+ self.assertEqual(payload["slides"][0]["charts"][0]["title"], title)
+ with contextlib.redirect_stdout(io.StringIO()):
+ self.assertEqual(beautify_inventory.main([
+ str(inventory), "--verify", str(self.source),
+ ]), 0)
+ presentation = Presentation(self.source)
+ presentation.slides[0].shapes[0].chart.has_title = False
+ missing_title = self.root / "missing-title.pptx"
+ presentation.save(missing_title)
+ output = io.StringIO()
+ with contextlib.redirect_stdout(output):
+ self.assertEqual(beautify_inventory.main([
+ str(inventory), "--verify", str(missing_title),
+ ]), 1)
+ self.assertIn("TITLE_MARKER", output.getvalue())
+
+ def test_linked_title_cache_survives_intake(self) -> None:
+ def linked_title(root):
+ tx = root.find("c:chart/c:title/c:tx", NS)
+ tx.clear()
+ ref = ET.SubElement(tx, f"{{{NS['c']}}}strRef")
+ ET.SubElement(ref, f"{{{NS['c']}}}f").text = "Sheet1!$A$1"
+ cache = ET.SubElement(ref, f"{{{NS['c']}}}strCache")
+ ET.SubElement(cache, f"{{{NS['c']}}}ptCount", {"val": "1"})
+ point = ET.SubElement(cache, f"{{{NS['c']}}}pt", {"idx": "0"})
+ ET.SubElement(point, f"{{{NS['c']}}}v").text = "LINKED_TITLE_MARKER"
+
+ self._mutate_chart(linked_title)
+ _path, payload = self._intake()
+ self.assertEqual(payload["slides"][0]["charts"][0]["title"], "LINKED_TITLE_MARKER")
+
+ def test_title_survives_chart_without_series(self) -> None:
+ def remove_series(root):
+ for plot in root.findall("c:chart/c:plotArea/*", NS):
+ for series in plot.findall("c:ser", NS):
+ plot.remove(series)
+
+ self._mutate_chart(remove_series)
+ _path, payload = self._intake()
+ chart = payload["slides"][0]["charts"][0]
+ self.assertIn("TITLE_MARKER", chart["title"])
+ self.assertEqual(chart["series"], [])