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: route document URLs to their converter; bullet glyphs never make PDF headings; polygon carries a filter

hugohe30b593d6d803b
diff --git a/skills/ppt-master/scripts/source_to_md/pdf_to_md.py b/skills/ppt-master/scripts/source_to_md/pdf_to_md.py
index b07eb859..5a705e13 100644
--- a/skills/ppt-master/scripts/source_to_md/pdf_to_md.py
+++ b/skills/ppt-master/scripts/source_to_md/pdf_to_md.py
@@ -132,6 +132,10 @@ def get_heading_level(size: float, size_map: dict, text: str = "",
if len(text) > 80:
return 0
+ # Exclusion: a bullet-led line is a list item, whatever its glyph size
+ if text[:1] in _BULLET_GLYPHS:
+ return 0
+
# Exclusion: complete sentences ending with punctuation
sentence_endings = '.。!!??'
if text and text[-1] in sentence_endings:
@@ -184,12 +188,23 @@ def format_span_text(text: str, flags: int) -> str:
return text
+# Bullet glyphs a PDF sets as their own span; ``·`` (U+00B7) is common in
+# fact sheets, and a stray control character often follows the glyph.
+_BULLET_GLYPHS = '•●○◦▪▸►·‧∙・'
+
+
+def is_bullet_glyph_span(text: str) -> bool:
+ """Return whether a span holds only a bullet glyph (plus spaces / control characters)."""
+ stripped = re.sub(r'[\s\x00-\x1f]+', '', text)
+ return len(stripped) == 1 and stripped in _BULLET_GLYPHS
+
+
def detect_list_item(text: str) -> tuple:
"""Detect if the text is a list item. Returns (is_list, list_type, content)."""
text = text.strip()
ul_patterns = [
- (r'^[•●○◦▪▸►]\s*', '-'),
+ (rf'^[{_BULLET_GLYPHS}][\s\x00-\x1f]*', '-'),
(r'^[-–—]\s+', '-'),
(r'^\*\s+', '-'),
]
@@ -1474,6 +1489,12 @@ def extract_pdf_to_markdown(
span_size = span["size"]
span_flags = span["flags"]
+ # A bullet glyph set in its own larger span must not
+ # promote the line to a heading; it is a list marker.
+ if is_bullet_glyph_span(span_text):
+ formatted_spans.append(span_text)
+ continue
+
line_size = max(line_size, span_size)
line_flags |= span_flags
span_count += 1
@@ -1503,6 +1524,8 @@ def extract_pdf_to_markdown(
heading_level = get_heading_level(line_size, size_map, line_text, line_flags)
is_list, list_type, list_content = detect_list_item(line_text)
+ if is_list and not list_content.split(' ', 1)[-1].strip():
+ continue
if heading_level > 0:
prefix = '#' * heading_level + ' '
diff --git a/skills/ppt-master/scripts/source_to_md/web_to_md.py b/skills/ppt-master/scripts/source_to_md/web_to_md.py
index 58b76894..2c85e5b8 100644
--- a/skills/ppt-master/scripts/source_to_md/web_to_md.py
+++ b/skills/ppt-master/scripts/source_to_md/web_to_md.py
@@ -37,6 +37,7 @@ import json
import os
import re
import socket
+import subprocess
import sys
import time
from pathlib import Path
@@ -47,6 +48,14 @@ if str(_SCRIPTS_DIR) not in sys.path:
sys.path.insert(0, str(_SCRIPTS_DIR))
from console_encoding import configure_utf8_stdio # noqa: E402
+from _dispatcher import ( # noqa: E402
+ DOC_SUFFIXES,
+ EXCEL_SUFFIXES,
+ LEGACY_EXCEL_SUFFIXES,
+ PDF_SUFFIXES,
+ PRESENTATION_SUFFIXES,
+ build_conversion_command,
+)
from _conversion_profile import ( # noqa: E402
profile_path_for,
write_conversion_profile_best_effort,
@@ -272,15 +281,8 @@ CONFIG = {
}
-def fetch_url(url: str) -> tuple[str, str]:
- """Fetch a web page with explicit headers and encoding detection.
-
- Args:
- url: Target URL.
-
- Returns:
- The response body as text and the final URL after redirects.
- """
+def fetch_response(url: str):
+ """Fetch a URL with explicit headers and return the raw HTTP response."""
headers = {
"User-Agent": CONFIG["user_agent"],
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
@@ -291,12 +293,17 @@ def fetch_url(url: str) -> tuple[str, str]:
response = _http_get(url, headers=headers,
timeout=CONFIG["timeout"], verify=not CONFIG["insecure"])
response.raise_for_status()
-
- return _decode_response_text(response), response.url
+ return response
except Exception as e:
raise Exception(f"Failed to fetch {url}: {str(e)}")
+def fetch_url(url: str) -> tuple[str, str]:
+ """Fetch a web page as decoded text plus the final URL after redirects."""
+ response = fetch_response(url)
+ return _decode_response_text(response), response.url
+
+
def clean_title(title: str) -> str:
"""Remove common site suffixes from a title."""
if not title:
@@ -955,6 +962,64 @@ def _save_plain_text_document(
return True, url, None, output_path
+_DOCUMENT_CONTENT_TYPES = {
+ "application/pdf": ".pdf",
+ "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
+ "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+ "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
+ "application/msword": ".doc",
+ "application/vnd.ms-excel": ".xls",
+ "application/epub+zip": ".epub",
+}
+_DOCUMENT_URL_SUFFIXES = frozenset(
+ PDF_SUFFIXES | EXCEL_SUFFIXES | LEGACY_EXCEL_SUFFIXES | PRESENTATION_SUFFIXES
+ | (DOC_SUFFIXES - {".html", ".htm"})
+)
+
+
+def remote_document_suffix(url: str, content_type: str, head: bytes) -> str | None:
+ """Return the file suffix when a fetched URL is a document, not an HTML page.
+
+ A ``.pdf`` URL (or a suffix-less download that answers ``application/pdf``)
+ has no HTML body; the HTML extractor would fail on it. The body magic and
+ the Content-Type decide first, then the URL suffix, unless the server
+ explicitly answered with HTML (a viewer page at a document-looking URL).
+ """
+ if head.startswith(b"%PDF-"):
+ return ".pdf"
+ ctype = content_type.split(";")[0].strip().lower()
+ if ctype in _DOCUMENT_CONTENT_TYPES:
+ return _DOCUMENT_CONTENT_TYPES[ctype]
+ if ctype.startswith("text/html") or ctype == "application/xhtml+xml":
+ return None
+ suffix = os.path.splitext(urlparse(url).path)[1].lower()
+ return suffix if suffix in _DOCUMENT_URL_SUFFIXES else None
+
+
+def _convert_remote_document(
+ url: str, body: bytes, suffix: str, output_file: str | None,
+) -> tuple[bool, str, str | None, str | None]:
+ """Save a downloaded document beside its Markdown and run its own converter."""
+ stem = os.path.splitext(os.path.basename(urlparse(url).path))[0]
+ output_path = output_file or os.path.join(
+ CONFIG["output_dir"], f"{derive_base_name(stem, url)}.md",
+ )
+ output_dirname = os.path.dirname(output_path) or "."
+ os.makedirs(output_dirname, exist_ok=True)
+ base_name = os.path.splitext(os.path.basename(output_path))[0]
+ local_path = os.path.join(output_dirname, f"{base_name}{suffix}")
+ with open(local_path, "wb") as f:
+ f.write(body)
+ print(f" [OK] Document: {len(body)} bytes saved to {local_path}")
+
+ route = build_conversion_command(local_path, output_path)
+ print(f" [>>] {route.script_name} {local_path}")
+ rc = subprocess.run(route.command).returncode
+ if rc != 0 or not os.path.isfile(output_path):
+ return False, url, f"{route.script_name} exited with {rc}", None
+ return True, url, None, output_path
+
+
def process_url(
url: str,
output_file: str | None = None,
@@ -969,7 +1034,12 @@ def process_url(
"""
print(f"\n[Fetching] {url}")
try:
- html, page_url = fetch_url(url)
+ response = fetch_response(url)
+ suffix = remote_document_suffix(
+ url, response.headers.get("Content-Type", ""), response.content[:8])
+ if suffix:
+ return _convert_remote_document(url, response.content, suffix, output_file)
+ html, page_url = _decode_response_text(response), response.url
if is_plain_text_document(url, html):
return _save_plain_text_document(url, html, output_file)
soup = BeautifulSoup(html, 'html.parser')
diff --git a/skills/ppt-master/scripts/svg_to_pptx/drawingml/elements.py b/skills/ppt-master/scripts/svg_to_pptx/drawingml/elements.py
index 8fa6cece..d25ade5b 100644
--- a/skills/ppt-master/scripts/svg_to_pptx/drawingml/elements.py
+++ b/skills/ppt-master/scripts/svg_to_pptx/drawingml/elements.py
@@ -1909,6 +1909,14 @@ def convert_polygon(elem: ET.Element, ctx: ConvertContext) -> ShapeResult | None
fill = build_fill_xml(elem, ctx, fill_op)
stroke = build_stroke_xml(elem, ctx, stroke_op)
+ effect = ''
+ filt_id = get_effective_filter_id(elem, ctx)
+ if filt_id and filt_id in ctx.defs:
+ effect = build_effect_xml(
+ ctx.defs[filt_id],
+ get_element_opacity(elem, ctx),
+ )
+
shape_id = _claim_element_shape_id(elem, ctx)
xfrm_attr = ''
off_x = px_to_emu(min_x)
@@ -1931,7 +1939,7 @@ def convert_polygon(elem: ET.Element, ctx: ConvertContext) -> ShapeResult | None
ctx,
shape_id, f'Polygon {shape_id}',
off_x, off_y, w_emu, h_emu,
- geom, fill, stroke, xfrm_attr=xfrm_attr,
+ geom, fill, stroke, effect, xfrm_attr=xfrm_attr,
),
bounds_emu=bounds_emu,
)
diff --git a/skills/ppt-master/scripts/svg_to_pptx/drawingml/utils.py b/skills/ppt-master/scripts/svg_to_pptx/drawingml/utils.py
index 05182d47..74d3a72a 100644
--- a/skills/ppt-master/scripts/svg_to_pptx/drawingml/utils.py
+++ b/skills/ppt-master/scripts/svg_to_pptx/drawingml/utils.py
@@ -263,6 +263,7 @@ PROJECT_FILTER_PUBLIC_TARGETS = frozenset({
'circle',
'image',
'path',
+ 'polygon',
'text',
})
_PROJECT_MARKER_NUMBER_TOKEN = (
@@ -2821,7 +2822,7 @@ def project_filter_errors(root: ET.Element) -> list[str]:
):
errors.add(
f'{label} cannot use filter; supported native targets are '
- 'rect, circle, image, path, text, a validated compact authored-'
+ 'rect, circle, image, path, polygon, text, a validated compact authored-'
'preset shape, and an exact registered carrier group'
)
if tag == 'image' and elem.get('clip-path') is not None:
diff --git a/skills/ppt-master/scripts/svg_to_pptx/pptx_package/builder.py b/skills/ppt-master/scripts/svg_to_pptx/pptx_package/builder.py
index 7080ec06..a6ca7368 100644
--- a/skills/ppt-master/scripts/svg_to_pptx/pptx_package/builder.py
+++ b/skills/ppt-master/scripts/svg_to_pptx/pptx_package/builder.py
@@ -166,6 +166,26 @@ THEME_REL_TYPE = (
)
THEME_CONTENT_TYPE = "application/vnd.openxmlformats-officedocument.theme+xml"
PML_NS = "http://schemas.openxmlformats.org/presentationml/2006/main"
+
+# ST_SlideSizeType tokens for the standard screen ratios; every other canvas
+# (portrait story, banner, print) is ``custom``. python-pptx's default
+# template says ``screen4x3`` whatever cx/cy are set to afterwards.
+_SLIDE_SIZE_TYPES = ((4, 3, "screen4x3"), (16, 9, "screen16x9"), (16, 10, "screen16x10"))
+
+
+def _slide_size_type(width_emu: int, height_emu: int) -> str:
+ """Return the ``p:sldSz type`` token matching a slide size."""
+ for ratio_w, ratio_h, token in _SLIDE_SIZE_TYPES:
+ if abs(width_emu * ratio_h - height_emu * ratio_w) <= max(width_emu, height_emu) // 200:
+ return token
+ return "custom"
+
+
+def _set_slide_size_type(presentation, width_emu: int, height_emu: int) -> None:
+ """Make the ``type`` token agree with the cx/cy the exporter just set."""
+ slide_size = presentation.element.find(f"{{{PML_NS}}}sldSz")
+ if slide_size is not None:
+ slide_size.set("type", _slide_size_type(width_emu, height_emu))
DML_NS = "http://schemas.openxmlformats.org/drawingml/2006/main"
REL_NS = "http://schemas.openxmlformats.org/officeDocument/2006/relationships"
P14_NS = "http://schemas.microsoft.com/office/powerpoint/2010/main"
@@ -6852,6 +6872,7 @@ def create_pptx_with_native_svg(
prs = Presentation()
prs.slide_width = width_emu
prs.slide_height = height_emu
+ _set_slide_size_type(prs, width_emu, height_emu)
blank_layout = prs.slide_layouts[6]
for _ in svg_files:
diff --git a/skills/ppt-master/scripts/tests/test_dogfood_leaves_fixes.py b/skills/ppt-master/scripts/tests/test_dogfood_leaves_fixes.py
new file mode 100644
index 00000000..3fa2c7fd
--- /dev/null
+++ b/skills/ppt-master/scripts/tests/test_dogfood_leaves_fixes.py
@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+"""Regression tests for the fixes reported by the Why Leaves Turn dogfood run.
+
+Document URLs route to their own converter, bullet glyphs never promote a PDF
+line to a heading, ``<polygon>`` carries a filter, and the exported slide size
+type token follows the canvas.
+"""
+
+from __future__ import annotations
+
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from xml.etree import ElementTree as ET
+
+SCRIPTS_DIR = Path(__file__).resolve().parents[1]
+if str(SCRIPTS_DIR) not in sys.path:
+ sys.path.insert(0, str(SCRIPTS_DIR))
+BACKEND_DIR = SCRIPTS_DIR / "source_to_md"
+if str(BACKEND_DIR) not in sys.path:
+ sys.path.insert(0, str(BACKEND_DIR))
+
+import pdf_to_md # noqa: E402
+import web_to_md # noqa: E402
+from svg_to_pptx.drawingml.converter import convert_svg_to_slide_shapes # noqa: E402
+from svg_to_pptx.drawingml.utils import project_filter_errors # noqa: E402
+from svg_to_pptx.pptx_package.builder import _slide_size_type # noqa: E402
+
+PDF_URL = "https://www.example.gov/content/pkg/report/pdf/report.pdf"
+
+
+class RemoteDocumentSuffixTests(unittest.TestCase):
+ def test_pdf_url_with_pdf_content_type(self) -> None:
+ self.assertEqual(
+ web_to_md.remote_document_suffix(PDF_URL, "application/pdf", b"%PDF-1.4"), ".pdf")
+
+ def test_suffixless_download_answering_pdf(self) -> None:
+ self.assertEqual(
+ web_to_md.remote_document_suffix(
+ "https://example.org/download?id=7", "application/pdf; charset=binary", b"%PDF-1.7"),
+ ".pdf")
+
+ def test_body_magic_wins_over_wrong_content_type(self) -> None:
+ self.assertEqual(
+ web_to_md.remote_document_suffix(
+ "https://example.org/files/report", "application/octet-stream", b"%PDF-1.7"),
+ ".pdf")
+
+ def test_docx_url_by_suffix(self) -> None:
+ self.assertEqual(
+ web_to_md.remote_document_suffix(
+ "https://example.org/a/brief.docx", "application/octet-stream", b"PK\x03\x04"),
+ ".docx")
+
+ def test_html_viewer_at_document_url_stays_web(self) -> None:
+ self.assertIsNone(
+ web_to_md.remote_document_suffix(PDF_URL, "text/html; charset=utf-8", b"<!doctyp"))
+
+ def test_ordinary_page_is_not_a_document(self) -> None:
+ self.assertIsNone(
+ web_to_md.remote_document_suffix(
+ "https://example.org/article", "text/html", b"<html>"))
+ self.assertIsNone(
+ web_to_md.remote_document_suffix(
+ "https://example.org/page.html", "", b"<html>"))
+
+
+class PdfBulletTests(unittest.TestCase):
+ def test_middot_bullet_is_a_list_item(self) -> None:
+ is_list, kind, content = pdf_to_md.detect_list_item("·\x01 Oaks turn red, brown, or russet;")
+ self.assertTrue(is_list)
+ self.assertEqual(kind, "ul")
+ self.assertEqual(content, "- Oaks turn red, brown, or russet;")
+
+ def test_bullet_led_line_is_never_a_heading(self) -> None:
+ size_map = {"body": 12.1, "h1": 13.6}
+ self.assertEqual(pdf_to_md.get_heading_level(13.6, size_map, "· Oaks turn red", 4), 0)
+ self.assertEqual(pdf_to_md.get_heading_level(13.6, size_map, "Autumn colours", 16), 1)
+
+ def test_bullet_glyph_span_detection(self) -> None:
+ self.assertTrue(pdf_to_md.is_bullet_glyph_span("· "))
+ self.assertTrue(pdf_to_md.is_bullet_glyph_span("•"))
+ self.assertTrue(pdf_to_md.is_bullet_glyph_span("·\x01"))
+ self.assertFalse(pdf_to_md.is_bullet_glyph_span("Oaks"))
+ self.assertFalse(pdf_to_md.is_bullet_glyph_span("· Oaks"))
+
+
+class PolygonFilterTests(unittest.TestCase):
+ SVG = (
+ '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1280 720">'
+ '<defs><filter id="paperShadow"><feDropShadow dx="0" dy="6" stdDeviation="6" '
+ 'flood-color="#000000" flood-opacity="0.25"/></filter></defs>'
+ '<polygon id="sheet" points="100,100 400,120 380,400 90,380" fill="#E8D9C4" '
+ 'filter="url(#paperShadow)"/>'
+ '</svg>'
+ )
+
+ def test_polygon_is_a_public_filter_target(self) -> None:
+ errors = project_filter_errors(ET.fromstring(self.SVG))
+ self.assertEqual([e for e in errors if "cannot use filter" in e], [])
+
+ def test_polygon_exports_its_shadow(self) -> None:
+ with tempfile.TemporaryDirectory() as tmp:
+ root = Path(tmp)
+ svg_path = root / "page.svg"
+ svg_path.write_text(self.SVG, encoding="utf-8")
+ xml, *_rest = convert_svg_to_slide_shapes(svg_path, resource_root=root)
+ self.assertIn("<a:outerShdw", xml)
+ self.assertIn("Polygon", xml)
+
+
+class SlideSizeTypeTests(unittest.TestCase):
+ def test_standard_ratios_keep_their_token(self) -> None:
+ self.assertEqual(_slide_size_type(12192000, 6858000), "screen16x9")
+ self.assertEqual(_slide_size_type(9144000, 6858000), "screen4x3")
+ self.assertEqual(_slide_size_type(10287000, 18288000), "custom")
+ self.assertEqual(_slide_size_type(11811000, 16706000), "custom")
+
+
+if __name__ == "__main__":
+ unittest.main()
diff --git a/skills/ppt-master/scripts/text_measure.py b/skills/ppt-master/scripts/text_measure.py
index 13ed505b..1e9b2acf 100644
--- a/skills/ppt-master/scripts/text_measure.py
+++ b/skills/ppt-master/scripts/text_measure.py
@@ -602,6 +602,12 @@ def _render_calibration_table(payload: dict[str, object], *, include_outline: bo
'while authoring (an expanded title, a longer label) is re-estimated '
'with the rates — the outline column does not cover it.'
)
+ lines.append(
+ '[NOTE] rates ignore letter-spacing and average a mixed-case sample: '
+ 'a tracked role (a kicker with letter-spacing) or a display-size line '
+ '(a cover title) is sized per string with measure --letter-spacing, '
+ 'not from the table.'
+ )
lines.append(
'[NOTE] measure and wrap take one --weight for the whole string: a line '
'with a bold run (an inline emphasis lead) is measured piecewise per '
@@ -658,6 +664,11 @@ def _run_calibrate(args: argparse.Namespace) -> int:
weights=weights,
)
payload['notes'] = _fallback_notes(roles, fallbacks)
+ if args.outline and not (project_path / 'design_spec.md').is_file():
+ payload['notes'].append(
+ 'no design_spec.md in this project (Quick writes none), so the '
+ '--outline column has no §IX source and stays empty'
+ )
bold_roles = sorted(name for name, weight in weights.items() if weight == 'bold')
payload['notes'].append(
'rates for ' + ', '.join(bold_roles) + ' are measured at bold weight'