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(import-sources): give same-stem sources distinct archive stems

hugohe3ca04346de145
diff --git a/skills/ppt-master/scripts/docs/conversion.md b/skills/ppt-master/scripts/docs/conversion.md
index a02498ce..e175611c 100644
--- a/skills/ppt-master/scripts/docs/conversion.md
+++ b/skills/ppt-master/scripts/docs/conversion.md
@@ -84,8 +84,13 @@ Useful options:
refuses an existing file except its own Markdown/text passthrough.
For multi-source project intake, use `project_manager.py import-sources` with
-all source paths / URLs. For local files, the default is to keep generated
-Markdown and profile outputs beside the original source.
+all source paths / URLs. Same-stem convertible sources receive distinct
+archive names such as `budget_2.xlsm`, so their Markdown, profiles, assets, and
+PPTX intake artifacts stay separate. Pre-existing Markdown and explicitly
+supplied same-stem Markdown still suppress automatic conversion; PPTX intake
+remains separate for each archived deck. See
+[`project.md`](project.md). For standalone local conversion, the default is to
+keep generated Markdown and profiles beside the original source.
`source_to_md.py` and the backend converters support single files, explicit
multi-file inputs, and non-recursive directory inputs.
@@ -260,7 +265,7 @@ Outputs (per source deck, prefixed by file stem):
- `<stem>.slide_library.json` — text slots, geometry, native tables, native chart display caches, and SmartArt nodes/connections
- `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: importing several PPTX files gives each its own `<stem>.*` artifacts and a `decks[]` entry in the shared `source_profile.json` index (re-importing the same stem replaces its entry). The beautify profile stays single-deck and reads one chosen deck's `<stem>.*` artifacts.
+`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.
Usage boundary:
- Standard generation uses these fields as facts and recommendation candidates; it does not inherit source slide coordinates or page order by default.
diff --git a/skills/ppt-master/scripts/docs/project.md b/skills/ppt-master/scripts/docs/project.md
index 76b101f0..7f3402c8 100644
--- a/skills/ppt-master/scripts/docs/project.md
+++ b/skills/ppt-master/scripts/docs/project.md
@@ -58,6 +58,11 @@ Notes:
pass the source file/directory once when generated Markdown lives beside the
original source. If Step 1 used `-o` to write Markdown elsewhere, pass both
the original source path/directory and the Markdown output path/directory.
+- Distinct same-stem convertible sources in one `import-sources` call
+ receive archive suffixes (`budget.xlsm` → `budget_2.xlsm`). Markdown, conversion
+ profiles, `_files/` assets, and PPTX analysis follow the archived stem.
+ Pre-existing Markdown and explicitly supplied same-stem Markdown still
+ suppress automatic conversion; PPTX intake still keeps each deck separate.
- A projects-local supplied source directory left strictly empty after import
(or empty from the start) is removed; every directory outside `projects/`
remains untouched. `--copy` never removes directories.
@@ -101,8 +106,9 @@ Notes:
- PPTX-family inputs are enriched automatically under `analysis/` with
per-deck `<stem>.identity.json` / `<stem>.slide_library.json` plus the shared
multi-deck index `source_profile.json` (`decks[]`).
- Multi-deck per project: several PPTX imports each get their own `<stem>.*`
- artifacts and a `decks[]` entry; re-importing the same stem replaces its entry.
+ Multi-deck per project: `<stem>` is the archived stem, including any collision
+ suffix. Each deck gets its own artifacts and `decks[]` entry; re-running
+ intake for an existing archived stem replaces its entry.
### On-demand page execution view
diff --git a/skills/ppt-master/scripts/project_management/cli.py b/skills/ppt-master/scripts/project_management/cli.py
index 53e555e0..8a269069 100644
--- a/skills/ppt-master/scripts/project_management/cli.py
+++ b/skills/ppt-master/scripts/project_management/cli.py
@@ -820,6 +820,8 @@ class ProjectManager:
raise ValueError("At least one source path or URL is required")
sources_dir = self._source_dir(project_dir)
+ existing_markdown = {path.resolve() for path in sources_dir.glob("*.md")}
+ reserved_markdown: set[Path] = set()
summary: dict[str, list[str]] = {
"archived": [],
"url_records": [],
@@ -998,12 +1000,48 @@ class ProjectManager:
summary["notes"].append(note)
continue
+ archive_target = sources_dir / source_path.name
+ if source_path.resolve() != archive_target.resolve():
+ archive_target = self._ensure_unique_path(archive_target)
+ canonical_markdown_path = archive_target.with_suffix(".md")
+ has_explicit_markdown = archive_target.stem in explicit_markdown_stems
+ if suffix in PDF_SUFFIXES | PRESENTATION_SUFFIXES | EXCEL_SUFFIXES | DOC_SUFFIXES:
+ markdown_target = canonical_markdown_path
+ keep_markdown = (
+ has_explicit_markdown or markdown_target.resolve() in existing_markdown
+ )
+ if not keep_markdown or markdown_target.resolve() in reserved_markdown:
+ # Reserve the source stem before conversion, including failed
+ # conversions that may already have written intake or assets.
+ stem = archive_target.stem
+ counter = 2
+ while (
+ markdown_target.resolve() in reserved_markdown
+ or markdown_target.exists()
+ or archive_target.stem in explicit_markdown_stems
+ or (archive_target.exists() and archive_target.resolve() != source_path.resolve())
+ or markdown_target.with_suffix(".conversion_profile.json").exists()
+ or (sources_dir / f"{archive_target.stem}_files").exists()
+ or (project_dir / "analysis" / f"{archive_target.stem}.identity.json").exists()
+ or (project_dir / "analysis" / f"{archive_target.stem}.slide_library.json").exists()
+ ):
+ archive_target = archive_target.with_name(f"{stem}_{counter}{source_path.suffix}")
+ markdown_target = archive_target.with_suffix(".md")
+ counter += 1
+ # PPTX intake still writes analysis when Markdown is reused.
+ reserved_markdown.add(markdown_target.resolve())
+ if not keep_markdown:
+ canonical_markdown_path = markdown_target
archived_path = self._copy_or_move_file(
source_path,
- sources_dir / source_path.name,
+ archive_target,
move=effective_move,
)
summary["archived"].append(str(archived_path))
+ if archived_path.name != source_path.name:
+ summary["notes"].append(
+ f"{item}: archived as {archived_path.name} to avoid a filename or source-stem collision"
+ )
if suffix in BITMAP_IMAGE_SUFFIXES:
images_dir = project_dir / "images"
@@ -1017,8 +1055,7 @@ class ProjectManager:
"to avoid a filename collision"
)
elif suffix in PDF_SUFFIXES:
- canonical_markdown_path = sources_dir / f"{archived_path.stem}.md"
- if archived_path.stem in explicit_markdown_stems:
+ if has_explicit_markdown:
summary["notes"].append(
f"{item}: skipped PDF auto-conversion because a same-stem Markdown source was provided"
)
@@ -1040,7 +1077,6 @@ class ProjectManager:
except Exception as exc: # pragma: no cover - summary path
summary["skipped"].append(f"{item}: PDF conversion failed ({exc})")
elif suffix in PRESENTATION_SUFFIXES:
- canonical_markdown_path = sources_dir / f"{archived_path.stem}.md"
try:
intake_dir = self._import_pptx_intake(archived_path, project_dir)
intake_str = str(intake_dir)
@@ -1048,7 +1084,7 @@ class ProjectManager:
summary["analysis"].append(intake_str)
except Exception as exc: # pragma: no cover - summary path
summary["notes"].append(f"{item}: PPTX intake analysis failed ({exc})")
- if archived_path.stem in explicit_markdown_stems:
+ if has_explicit_markdown:
summary["notes"].append(
f"{item}: skipped presentation auto-conversion because a same-stem Markdown source was provided"
)
@@ -1070,8 +1106,7 @@ class ProjectManager:
except Exception as exc: # pragma: no cover - summary path
summary["skipped"].append(f"{item}: presentation conversion failed ({exc})")
elif suffix in EXCEL_SUFFIXES:
- canonical_markdown_path = sources_dir / f"{archived_path.stem}.md"
- if archived_path.stem in explicit_markdown_stems:
+ if has_explicit_markdown:
summary["notes"].append(
f"{item}: skipped Excel auto-conversion because a same-stem Markdown source was provided"
)
@@ -1102,8 +1137,7 @@ class ProjectManager:
f"{item}: archived as a plain-text table source; no Markdown conversion needed"
)
elif suffix in DOC_SUFFIXES:
- canonical_markdown_path = sources_dir / f"{archived_path.stem}.md"
- if archived_path.stem in explicit_markdown_stems:
+ if has_explicit_markdown:
summary["notes"].append(
f"{item}: skipped document auto-conversion because a same-stem Markdown source was provided"
)
diff --git a/skills/ppt-master/scripts/tests/test_audit_r3_sources.py b/skills/ppt-master/scripts/tests/test_audit_r3_sources.py
index 476cd907..1c02319c 100644
--- a/skills/ppt-master/scripts/tests/test_audit_r3_sources.py
+++ b/skills/ppt-master/scripts/tests/test_audit_r3_sources.py
@@ -13,6 +13,7 @@ Dependencies:
from __future__ import annotations
import contextlib
+import base64
import io
import json
import socket
@@ -412,6 +413,226 @@ class ArchivedProjectImportTests(unittest.TestCase):
)
+class SameStemProjectImportTests(unittest.TestCase):
+ def setUp(self) -> None:
+ self.temporary = tempfile.TemporaryDirectory()
+ self.addCleanup(self.temporary.cleanup)
+ self.root = Path(self.temporary.name)
+ self.manager = project_cli.ProjectManager(base_dir=self.root / "projects")
+
+ def _project(self, name="target") -> Path:
+ with contextlib.redirect_stdout(io.StringIO()):
+ return Path(self.manager.init_project(name, quick_generate=True))
+
+ def _workbooks(self, root: Path) -> list[Path]:
+ from openpyxl import Workbook
+
+ root.mkdir(parents=True)
+ sources = []
+ for suffix, total in ((".xlsx", 20000), (".xlsm", 22500)):
+ workbook = Workbook()
+ workbook.active.append(["Category", "Amount"])
+ workbook.active.append(["Total", total])
+ source = root / f"budget{suffix}"
+ workbook.save(source)
+ workbook.close()
+ sources.append(source)
+ return sources
+
+ def _import(self, project: Path, sources: list[Path]) -> dict:
+ with contextlib.redirect_stdout(io.StringIO()):
+ return self.manager.import_sources(str(project), list(map(str, sources)), copy=True)
+
+ def _assert_conversions(self, project: Path, summary: dict, labels: list[str]) -> None:
+ self.assertEqual(summary["skipped"], [])
+ self.assertEqual(len(summary["markdown"]), len(labels))
+ self.assertEqual(len(set(summary["markdown"])), len(labels))
+ for raw_path, markdown_path, label in zip(summary["archived"], summary["markdown"], labels):
+ source = Path(raw_path)
+ markdown = Path(markdown_path)
+ self.assertEqual(source.stem, markdown.stem)
+ content = markdown.read_text(encoding="utf-8").replace(r"\-", "-")
+ self.assertIn(label, content)
+ for other_label in labels:
+ if other_label != label:
+ self.assertNotIn(other_label, content)
+ profile = json.loads(profile_path_for(markdown).read_text(encoding="utf-8"))
+ self.assertEqual(profile["source"]["name"], source.name)
+ self.assertEqual(profile["outputs"]["markdown"], markdown.name)
+
+ def test_same_stem_workbooks_each_convert_with_matching_archived_names(self) -> None:
+ for reverse in (False, True):
+ with self.subTest(reverse=reverse):
+ sources = self._workbooks(self.root / f"inputs_{reverse}")
+ labels = ["20000", "22500"]
+ if reverse:
+ sources.reverse()
+ labels.reverse()
+ originals = {source: source.read_bytes() for source in sources}
+ project = self._project(f"target_{reverse}")
+ summary = self._import(project, sources)
+ self._assert_conversions(project, summary, labels)
+ self.assertEqual([Path(path).name for path in summary["markdown"]],
+ ["budget.md", "budget_2.md"])
+ for source, archived in zip(sources, summary["archived"]):
+ self.assertEqual(Path(archived).read_bytes(), originals[source])
+ self.assertEqual(source.read_bytes(), originals[source])
+
+ def test_document_and_presentation_assets_and_intake_keep_each_source(self) -> None:
+ from docx import Document
+ from PIL import Image
+ from pptx import Presentation
+ from pptx.util import Inches
+
+ for kind in ("document", "presentation"):
+ with self.subTest(kind=kind):
+ inputs = self.root / kind
+ inputs.mkdir()
+ sources = []
+ expected_images = []
+ labels = ["FIRST-SOURCE-20000", "SECOND-SOURCE-22500"]
+ for index, color in enumerate(("red", "blue")):
+ buffer = io.BytesIO()
+ Image.new("RGB", (16, 16), color).save(buffer, format="PNG")
+ raw = buffer.getvalue()
+ expected_images.append(raw)
+ if kind == "document":
+ source = inputs / ("report.docx" if index == 0 else "report.html")
+ if index == 0:
+ document = Document()
+ document.add_paragraph(labels[index])
+ document.add_picture(io.BytesIO(raw))
+ document.save(source)
+ else:
+ encoded = base64.b64encode(raw).decode("ascii")
+ source.write_text(
+ f'<p>{labels[index]}</p><img src="data:image/png;base64,{encoded}">',
+ encoding="utf-8",
+ )
+ else:
+ source = inputs / ("deck.pptx" if index == 0 else "deck.potx")
+ presentation = Presentation()
+ slide = presentation.slides.add_slide(presentation.slide_layouts[6])
+ slide.shapes.add_textbox(Inches(1), Inches(1), Inches(5), Inches(1)).text = labels[index]
+ slide.shapes.add_picture(io.BytesIO(raw), Inches(1), Inches(2))
+ presentation.save(source)
+ sources.append(source)
+ project = self._project(kind)
+ summary = self._import(project, sources)
+ self._assert_conversions(project, summary, labels)
+ stems = {Path(path).stem for path in summary["archived"]}
+ manifest = json.loads((project / "images/image_manifest.json").read_text(encoding="utf-8"))
+ self.assertEqual({row["source_namespace"] for row in manifest}, stems)
+ self.assertEqual({(project / "images" / row["filename"]).read_bytes() for row in manifest},
+ set(expected_images))
+ for source, raw in zip(summary["archived"], expected_images):
+ assets = project / "sources" / f"{Path(source).stem}_files"
+ self.assertEqual(len(list(assets.glob("*.png"))), 1)
+ self.assertEqual(next(assets.glob("*.png")).read_bytes(), raw)
+ if kind == "presentation":
+ index = json.loads((project / "analysis/source_profile.json").read_text(encoding="utf-8"))
+ self.assertEqual(index["deck_count"], 2)
+ self.assertEqual({deck["stem"] for deck in index["decks"]}, stems)
+ self.assertEqual({deck["source_pptx"] for deck in index["decks"]}, set(summary["archived"]))
+ for stem, label in zip(("deck", "deck_2"), labels):
+ self.assertTrue((project / "analysis" / f"{stem}.identity.json").is_file())
+ library = project / "analysis" / f"{stem}.slide_library.json"
+ self.assertIn(label, library.read_text(encoding="utf-8"))
+
+ def test_reused_markdown_does_not_merge_same_stem_presentation_intake(self) -> None:
+ from pptx import Presentation
+ from pptx.util import Inches
+
+ for explicit in (False, True):
+ with self.subTest(explicit=explicit):
+ inputs = self.root / f"companion_{explicit}"
+ inputs.mkdir()
+ sources = []
+ labels = ["FIRST-SOURCE-20000", "SECOND-SOURCE-22500"]
+ for suffix, label in zip((".pptx", ".potx"), labels):
+ presentation = Presentation()
+ slide = presentation.slides.add_slide(presentation.slide_layouts[6])
+ slide.shapes.add_textbox(Inches(1), Inches(1), Inches(5), Inches(1)).text = label
+ source = inputs / f"deck{suffix}"
+ presentation.save(source)
+ sources.append(source)
+ project = self._project(f"companion_{explicit}")
+ (project / "sources").mkdir()
+ markdown = (inputs if explicit else project / "sources") / "deck.md"
+ markdown.write_text("# Authoritative Markdown\n", encoding="utf-8")
+ summary = self._import(project, [*sources, markdown] if explicit else sources)
+ self.assertEqual(summary["skipped"], [])
+ self.assertEqual([Path(path).name for path in summary["archived"][:2]],
+ ["deck.pptx", "deck_2.potx"])
+ self.assertEqual((project / "sources/deck.md").read_text(encoding="utf-8"),
+ "# Authoritative Markdown\n")
+ self.assertEqual(list((project / "sources").glob("*.conversion_profile.json")), [])
+ self.assertEqual(sum("skipped presentation auto-conversion" in note
+ for note in summary["notes"]), 2)
+ index = json.loads((project / "analysis/source_profile.json").read_text(encoding="utf-8"))
+ self.assertEqual(index["deck_count"], 2)
+ self.assertEqual({deck["stem"] for deck in index["decks"]}, {"deck", "deck_2"})
+ self.assertEqual({deck["source_pptx"] for deck in index["decks"]},
+ set(summary["archived"][:2]))
+ for stem, label, other_label in zip(("deck", "deck_2"), labels, reversed(labels)):
+ self.assertTrue((project / "analysis" / f"{stem}.identity.json").is_file())
+ library = (project / "analysis" / f"{stem}.slide_library.json").read_text(encoding="utf-8")
+ self.assertIn(label, library)
+ self.assertNotIn(other_label, library)
+
+ def test_explicit_markdown_still_suppresses_both_conversions(self) -> None:
+ for markdown_first in (False, True):
+ with self.subTest(markdown_first=markdown_first):
+ sources = self._workbooks(self.root / f"explicit_{markdown_first}")
+ markdown = sources[0].with_suffix(".md")
+ markdown.write_text("# Authoritative Markdown\n", encoding="utf-8")
+ inputs = [markdown, *sources] if markdown_first else [*sources, markdown]
+ project = self._project(f"explicit_{markdown_first}")
+ summary = self._import(project, inputs)
+ self.assertEqual(summary["skipped"], [])
+ self.assertEqual((project / "sources/budget.md").read_text(encoding="utf-8"),
+ "# Authoritative Markdown\n")
+ self.assertEqual(list((project / "sources").glob("*.conversion_profile.json")), [])
+ self.assertEqual(sum("same-stem Markdown source was provided" in note
+ for note in summary["notes"]), 2)
+
+ def test_markdown_existing_before_import_is_reused(self) -> None:
+ sources = self._workbooks(self.root / "existing")
+ project = self._project()
+ (project / "sources").mkdir()
+ markdown = project / "sources/budget.md"
+ markdown.write_text("# Previous conversion\n", encoding="utf-8")
+ summary = self._import(project, sources)
+ self.assertEqual(summary["markdown"], [str(markdown), str(markdown)])
+ self.assertEqual(markdown.read_text(encoding="utf-8"), "# Previous conversion\n")
+ self.assertEqual(sum("budget.md already exists" in note for note in summary["notes"]), 2)
+ self.assertEqual(list((project / "sources").glob("*.conversion_profile.json")), [])
+
+ def test_generated_suffix_avoids_existing_markdown_and_source_names(self) -> None:
+ sources = self._workbooks(self.root / "suffixes")
+ project = self._project()
+ (project / "sources").mkdir()
+ existing = project / "sources/budget_2.md"
+ existing.write_text("# Unrelated existing source\n", encoding="utf-8")
+ occupied = project / "sources/budget_3.xlsm"
+ occupied.write_bytes(b"archived original")
+ summary = self._import(project, sources)
+ self._assert_conversions(project, summary, ["20000", "22500"])
+ self.assertEqual([Path(path).name for path in summary["markdown"]],
+ ["budget.md", "budget_4.md"])
+ self.assertEqual(existing.read_text(encoding="utf-8"), "# Unrelated existing source\n")
+ self.assertEqual(occupied.read_bytes(), b"archived original")
+
+ def test_failed_conversion_still_reserves_its_source_stem(self) -> None:
+ sources = self._workbooks(self.root / "failure")
+ sources[0].write_bytes(b"invalid workbook")
+ project = self._project()
+ summary = self._import(project, sources)
+ self.assertEqual(len(summary["skipped"]), 1)
+ self.assertEqual([Path(path).name for path in summary["markdown"]], ["budget_2.md"])
+ self.assertIn("22500", Path(summary["markdown"][0]).read_text(encoding="utf-8"))
+
+
class _CurlHeaders(dict):
"""Represent repeated curl headers without importing optional curl_cffi."""