Files
Jason Woltje f5792c40be feat: Complete fleet — 94 skills across 10+ domains
Pulled ALL skills from 15 source repositories:
- anthropics/skills: 16 (docs, design, MCP, testing)
- obra/superpowers: 14 (TDD, debugging, agents, planning)
- coreyhaines31/marketingskills: 25 (marketing, CRO, SEO, growth)
- better-auth/skills: 5 (auth patterns)
- vercel-labs/agent-skills: 5 (React, design, Vercel)
- antfu/skills: 16 (Vue, Vite, Vitest, pnpm, Turborepo)
- Plus 13 individual skills from various repos

Mosaic Stack is not limited to coding — the Orchestrator and
subagents serve coding, business, design, marketing, writing,
logistics, analysis, and more.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 16:27:42 -06:00

276 lines
9.6 KiB
Python

"""
Validator for PowerPoint presentation XML files against XSD schemas.
"""
import re
from .base import BaseSchemaValidator
class PPTXSchemaValidator(BaseSchemaValidator):
PRESENTATIONML_NAMESPACE = (
"http://schemas.openxmlformats.org/presentationml/2006/main"
)
ELEMENT_RELATIONSHIP_TYPES = {
"sldid": "slide",
"sldmasterid": "slidemaster",
"notesmasterid": "notesmaster",
"sldlayoutid": "slidelayout",
"themeid": "theme",
"tablestyleid": "tablestyles",
}
def validate(self):
if not self.validate_xml():
return False
all_valid = True
if not self.validate_namespaces():
all_valid = False
if not self.validate_unique_ids():
all_valid = False
if not self.validate_uuid_ids():
all_valid = False
if not self.validate_file_references():
all_valid = False
if not self.validate_slide_layout_ids():
all_valid = False
if not self.validate_content_types():
all_valid = False
if not self.validate_against_xsd():
all_valid = False
if not self.validate_notes_slide_references():
all_valid = False
if not self.validate_all_relationship_ids():
all_valid = False
if not self.validate_no_duplicate_slide_layouts():
all_valid = False
return all_valid
def validate_uuid_ids(self):
import lxml.etree
errors = []
uuid_pattern = re.compile(
r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$"
)
for xml_file in self.xml_files:
try:
root = lxml.etree.parse(str(xml_file)).getroot()
for elem in root.iter():
for attr, value in elem.attrib.items():
attr_name = attr.split("}")[-1].lower()
if attr_name == "id" or attr_name.endswith("id"):
if self._looks_like_uuid(value):
if not uuid_pattern.match(value):
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: "
f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} UUID ID validation errors:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All UUID-like IDs contain valid hex values")
return True
def _looks_like_uuid(self, value):
clean_value = value.strip("{}()").replace("-", "")
return len(clean_value) == 32 and all(c.isalnum() for c in clean_value)
def validate_slide_layout_ids(self):
import lxml.etree
errors = []
slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml"))
if not slide_masters:
if self.verbose:
print("PASSED - No slide masters found")
return True
for slide_master in slide_masters:
try:
root = lxml.etree.parse(str(slide_master)).getroot()
rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels"
if not rels_file.exists():
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: "
f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}"
)
continue
rels_root = lxml.etree.parse(str(rels_file)).getroot()
valid_layout_rids = set()
for rel in rels_root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
):
rel_type = rel.get("Type", "")
if "slideLayout" in rel_type:
valid_layout_rids.add(rel.get("Id"))
for sld_layout_id in root.findall(
f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId"
):
r_id = sld_layout_id.get(
f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id"
)
layout_id = sld_layout_id.get("id")
if r_id and r_id not in valid_layout_rids:
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: "
f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' "
f"references r:id='{r_id}' which is not found in slide layout relationships"
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print(f"FAILED - Found {len(errors)} slide layout ID validation errors:")
for error in errors:
print(error)
print(
"Remove invalid references or add missing slide layouts to the relationships file."
)
return False
else:
if self.verbose:
print("PASSED - All slide layout IDs reference valid slide layouts")
return True
def validate_no_duplicate_slide_layouts(self):
import lxml.etree
errors = []
slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
for rels_file in slide_rels_files:
try:
root = lxml.etree.parse(str(rels_file)).getroot()
layout_rels = [
rel
for rel in root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
)
if "slideLayout" in rel.get("Type", "")
]
if len(layout_rels) > 1:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references"
)
except Exception as e:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
if errors:
print("FAILED - Found slides with duplicate slideLayout references:")
for error in errors:
print(error)
return False
else:
if self.verbose:
print("PASSED - All slides have exactly one slideLayout reference")
return True
def validate_notes_slide_references(self):
import lxml.etree
errors = []
notes_slide_references = {}
slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
if not slide_rels_files:
if self.verbose:
print("PASSED - No slide relationship files found")
return True
for rels_file in slide_rels_files:
try:
root = lxml.etree.parse(str(rels_file)).getroot()
for rel in root.findall(
f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
):
rel_type = rel.get("Type", "")
if "notesSlide" in rel_type:
target = rel.get("Target", "")
if target:
normalized_target = target.replace("../", "")
slide_name = rels_file.stem.replace(
".xml", ""
)
if normalized_target not in notes_slide_references:
notes_slide_references[normalized_target] = []
notes_slide_references[normalized_target].append(
(slide_name, rels_file)
)
except (lxml.etree.XMLSyntaxError, Exception) as e:
errors.append(
f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
)
for target, references in notes_slide_references.items():
if len(references) > 1:
slide_names = [ref[0] for ref in references]
errors.append(
f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}"
)
for slide_name, rels_file in references:
errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}")
if errors:
print(
f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:"
)
for error in errors:
print(error)
print("Each slide may optionally have its own slide file.")
return False
else:
if self.verbose:
print("PASSED - All notes slide references are unique")
return True
if __name__ == "__main__":
raise RuntimeError("This module should not be run directly.")