@farazirfan/costar-server-executor 1.7.37 → 1.7.39

package/skills/pptx/scripts/ooxml/scripts/validation/pptx.py

@@ -0,0 +1,315 @@
+"""
+Validator for PowerPoint presentation XML files against XSD schemas.
+"""
+
+import re
+
+from .base import BaseSchemaValidator
+
+
+class PPTXSchemaValidator(BaseSchemaValidator):
+    """Validator for PowerPoint presentation XML files against XSD schemas."""
+
+    # PowerPoint presentation namespace
+    PRESENTATIONML_NAMESPACE = (
+        "http://schemas.openxmlformats.org/presentationml/2006/main"
+    )
+
+    # PowerPoint-specific element to relationship type mappings
+    ELEMENT_RELATIONSHIP_TYPES = {
+        "sldid": "slide",
+        "sldmasterid": "slidemaster",
+        "notesmasterid": "notesmaster",
+        "sldlayoutid": "slidelayout",
+        "themeid": "theme",
+        "tablestyleid": "tablestyles",
+    }
+
+    def validate(self):
+        """Run all validation checks and return True if all pass."""
+        # Test 0: XML well-formedness
+        if not self.validate_xml():
+            return False
+
+        # Test 1: Namespace declarations
+        all_valid = True
+        if not self.validate_namespaces():
+            all_valid = False
+
+        # Test 2: Unique IDs
+        if not self.validate_unique_ids():
+            all_valid = False
+
+        # Test 3: UUID ID validation
+        if not self.validate_uuid_ids():
+            all_valid = False
+
+        # Test 4: Relationship and file reference validation
+        if not self.validate_file_references():
+            all_valid = False
+
+        # Test 5: Slide layout ID validation
+        if not self.validate_slide_layout_ids():
+            all_valid = False
+
+        # Test 6: Content type declarations
+        if not self.validate_content_types():
+            all_valid = False
+
+        # Test 7: XSD schema validation
+        if not self.validate_against_xsd():
+            all_valid = False
+
+        # Test 8: Notes slide reference validation
+        if not self.validate_notes_slide_references():
+            all_valid = False
+
+        # Test 9: Relationship ID reference validation
+        if not self.validate_all_relationship_ids():
+            all_valid = False
+
+        # Test 10: Duplicate slide layout references validation
+        if not self.validate_no_duplicate_slide_layouts():
+            all_valid = False
+
+        return all_valid
+
+    def validate_uuid_ids(self):
+        """Validate that ID attributes that look like UUIDs contain only hex values."""
+        import lxml.etree
+
+        errors = []
+        # UUID pattern: 8-4-4-4-12 hex digits with optional braces/hyphens
+        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()
+
+                # Check all elements for ID attributes
+                for elem in root.iter():
+                    for attr, value in elem.attrib.items():
+                        # Check if this is an ID attribute
+                        attr_name = attr.split("}")[-1].lower()
+                        if attr_name == "id" or attr_name.endswith("id"):
+                            # Check if value looks like a UUID (has the right length and pattern structure)
+                            if self._looks_like_uuid(value):
+                                # Validate that it contains only hex characters in the right positions
+                                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):
+        """Check if a value has the general structure of a UUID."""
+        # Remove common UUID delimiters
+        clean_value = value.strip("{}()").replace("-", "")
+        # Check if it's 32 hex-like characters (could include invalid hex chars)
+        return len(clean_value) == 32 and all(c.isalnum() for c in clean_value)
+
+    def validate_slide_layout_ids(self):
+        """Validate that sldLayoutId elements in slide masters reference valid slide layouts."""
+        import lxml.etree
+
+        errors = []
+
+        # Find all slide master files
+        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:
+                # Parse the slide master file
+                root = lxml.etree.parse(str(slide_master)).getroot()
+
+                # Find the corresponding _rels file for this slide master
+                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
+
+                # Parse the relationships file
+                rels_root = lxml.etree.parse(str(rels_file)).getroot()
+
+                # Build a set of valid relationship IDs that point to slide layouts
+                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"))
+
+                # Find all sldLayoutId elements in the slide master
+                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):
+        """Validate that each slide has exactly one slideLayout reference."""
+        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()
+
+                # Find all slideLayout relationships
+                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):
+        """Validate that each notesSlide file is referenced by only one slide."""
+        import lxml.etree
+
+        errors = []
+        notes_slide_references = {}  # Track which slides reference each notesSlide
+
+        # Find all slide relationship files
+        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:
+                # Parse the relationships file
+                root = lxml.etree.parse(str(rels_file)).getroot()
+
+                # Find all notesSlide relationships
+                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:
+                            # Normalize the target path to handle relative paths
+                            normalized_target = target.replace("../", "")
+
+                            # Track which slide references this notesSlide
+                            slide_name = rels_file.stem.replace(
+                                ".xml", ""
+                            )  # e.g., "slide1"
+
+                            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}"
+                )
+
+        # Check for duplicate references
+        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.")

package/skills/pptx/scripts/ooxml/scripts/validation/redlining.py

@@ -0,0 +1,284 @@
+"""
+Validator for tracked changes in Word documents.
+"""
+
+import subprocess
+import tempfile
+import zipfile
+from pathlib import Path
+
+
+class RedliningValidator:
+    """Validator for tracked changes in Word documents."""
+
+    def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"):
+        self.unpacked_dir = Path(unpacked_dir)
+        self.original_docx = Path(original_docx)
+        self.verbose = verbose
+        self.author = author
+        self.namespaces = {
+            "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+        }
+
+    def repair(self) -> int:
+        """No auto-repairs for redlining validation. Returns 0."""
+        return 0
+
+    def validate(self):
+        """Main validation method that returns True if valid, False otherwise."""
+        # Verify unpacked directory exists and has correct structure
+        modified_file = self.unpacked_dir / "word" / "document.xml"
+        if not modified_file.exists():
+            print(f"FAILED - Modified document.xml not found at {modified_file}")
+            return False
+
+        # First, check if there are any tracked changes by the author to validate
+        try:
+            import xml.etree.ElementTree as ET
+
+            tree = ET.parse(modified_file)
+            root = tree.getroot()
+
+            # Check for w:del or w:ins tags by the specified author
+            del_elements = root.findall(".//w:del", self.namespaces)
+            ins_elements = root.findall(".//w:ins", self.namespaces)
+
+            # Filter to only include changes by the specified author
+            author_del_elements = [
+                elem
+                for elem in del_elements
+                if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
+            ]
+            author_ins_elements = [
+                elem
+                for elem in ins_elements
+                if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
+            ]
+
+            # Redlining validation is only needed if tracked changes by the author have been used.
+            if not author_del_elements and not author_ins_elements:
+                if self.verbose:
+                    print(f"PASSED - No tracked changes by {self.author} found.")
+                return True
+
+        except Exception:
+            # If we can't parse the XML, continue with full validation
+            pass
+
+        # Create temporary directory for unpacking original docx
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_path = Path(temp_dir)
+
+            # Unpack original docx
+            try:
+                with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
+                    zip_ref.extractall(temp_path)
+            except Exception as e:
+                print(f"FAILED - Error unpacking original docx: {e}")
+                return False
+
+            original_file = temp_path / "word" / "document.xml"
+            if not original_file.exists():
+                print(
+                    f"FAILED - Original document.xml not found in {self.original_docx}"
+                )
+                return False
+
+            # Parse both XML files using xml.etree.ElementTree for redlining validation
+            try:
+                import xml.etree.ElementTree as ET
+
+                modified_tree = ET.parse(modified_file)
+                modified_root = modified_tree.getroot()
+                original_tree = ET.parse(original_file)
+                original_root = original_tree.getroot()
+            except ET.ParseError as e:
+                print(f"FAILED - Error parsing XML files: {e}")
+                return False
+
+            # Remove the author's tracked changes from both documents
+            self._remove_author_tracked_changes(original_root)
+            self._remove_author_tracked_changes(modified_root)
+
+            # Extract and compare text content
+            modified_text = self._extract_text_content(modified_root)
+            original_text = self._extract_text_content(original_root)
+
+            if modified_text != original_text:
+                # Show detailed character-level differences for each paragraph
+                error_message = self._generate_detailed_diff(
+                    original_text, modified_text
+                )
+                print(error_message)
+                return False
+
+            if self.verbose:
+                print(f"PASSED - All changes by {self.author} are properly tracked")
+            return True
+
+    def _generate_detailed_diff(self, original_text, modified_text):
+        """Generate detailed word-level differences using git word diff."""
+        error_parts = [
+            f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes",
+            "",
+            "Likely causes:",
+            "  1. Modified text inside another author's <w:ins> or <w:del> tags",
+            "  2. Made edits without proper tracked changes",
+            "  3. Didn't nest <w:del> inside <w:ins> when deleting another's insertion",
+            "",
+            "For pre-redlined documents, use correct patterns:",
+            "  - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
+            "  - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
+            "",
+        ]
+
+        # Show git word diff
+        git_diff = self._get_git_word_diff(original_text, modified_text)
+        if git_diff:
+            error_parts.extend(["Differences:", "============", git_diff])
+        else:
+            error_parts.append("Unable to generate word diff (git not available)")
+
+        return "\n".join(error_parts)
+
+    def _get_git_word_diff(self, original_text, modified_text):
+        """Generate word diff using git with character-level precision."""
+        try:
+            with tempfile.TemporaryDirectory() as temp_dir:
+                temp_path = Path(temp_dir)
+
+                # Create two files
+                original_file = temp_path / "original.txt"
+                modified_file = temp_path / "modified.txt"
+
+                original_file.write_text(original_text, encoding="utf-8")
+                modified_file.write_text(modified_text, encoding="utf-8")
+
+                # Try character-level diff first for precise differences
+                result = subprocess.run(
+                    [
+                        "git",
+                        "diff",
+                        "--word-diff=plain",
+                        "--word-diff-regex=.",  # Character-by-character diff
+                        "-U0",  # Zero lines of context - show only changed lines
+                        "--no-index",
+                        str(original_file),
+                        str(modified_file),
+                    ],
+                    capture_output=True,
+                    text=True,
+                )
+
+                if result.stdout.strip():
+                    # Clean up the output - remove git diff header lines
+                    lines = result.stdout.split("\n")
+                    # Skip the header lines (diff --git, index, +++, ---, @@)
+                    content_lines = []
+                    in_content = False
+                    for line in lines:
+                        if line.startswith("@@"):
+                            in_content = True
+                            continue
+                        if in_content and line.strip():
+                            content_lines.append(line)
+
+                    if content_lines:
+                        return "\n".join(content_lines)
+
+                # Fallback to word-level diff if character-level is too verbose
+                result = subprocess.run(
+                    [
+                        "git",
+                        "diff",
+                        "--word-diff=plain",
+                        "-U0",  # Zero lines of context
+                        "--no-index",
+                        str(original_file),
+                        str(modified_file),
+                    ],
+                    capture_output=True,
+                    text=True,
+                )
+
+                if result.stdout.strip():
+                    lines = result.stdout.split("\n")
+                    content_lines = []
+                    in_content = False
+                    for line in lines:
+                        if line.startswith("@@"):
+                            in_content = True
+                            continue
+                        if in_content and line.strip():
+                            content_lines.append(line)
+                    return "\n".join(content_lines)
+
+        except (subprocess.CalledProcessError, FileNotFoundError, Exception):
+            # Git not available or other error, return None to use fallback
+            pass
+
+        return None
+
+    def _remove_author_tracked_changes(self, root):
+        """Remove tracked changes authored by the specified author from the XML root."""
+        ins_tag = f"{{{self.namespaces['w']}}}ins"
+        del_tag = f"{{{self.namespaces['w']}}}del"
+        author_attr = f"{{{self.namespaces['w']}}}author"
+
+        # Remove w:ins elements
+        for parent in root.iter():
+            to_remove = []
+            for child in parent:
+                if child.tag == ins_tag and child.get(author_attr) == self.author:
+                    to_remove.append(child)
+            for elem in to_remove:
+                parent.remove(elem)
+
+        # Unwrap content in w:del elements where author matches
+        deltext_tag = f"{{{self.namespaces['w']}}}delText"
+        t_tag = f"{{{self.namespaces['w']}}}t"
+
+        for parent in root.iter():
+            to_process = []
+            for child in parent:
+                if child.tag == del_tag and child.get(author_attr) == self.author:
+                    to_process.append((child, list(parent).index(child)))
+
+            # Process in reverse order to maintain indices
+            for del_elem, del_index in reversed(to_process):
+                # Convert w:delText to w:t before moving
+                for elem in del_elem.iter():
+                    if elem.tag == deltext_tag:
+                        elem.tag = t_tag
+
+                # Move all children of w:del to its parent before removing w:del
+                for child in reversed(list(del_elem)):
+                    parent.insert(del_index, child)
+                parent.remove(del_elem)
+
+    def _extract_text_content(self, root):
+        """Extract text content from Word XML, preserving paragraph structure.
+
+        Empty paragraphs are skipped to avoid false positives when tracked
+        insertions add only structural elements without text content.
+        """
+        p_tag = f"{{{self.namespaces['w']}}}p"
+        t_tag = f"{{{self.namespaces['w']}}}t"
+
+        paragraphs = []
+        for p_elem in root.findall(f".//{p_tag}"):
+            # Get all text elements within this paragraph
+            text_parts = []
+            for t_elem in p_elem.findall(f".//{t_tag}"):
+                if t_elem.text:
+                    text_parts.append(t_elem.text)
+            paragraph_text = "".join(text_parts)
+            # Skip empty paragraphs - they don't affect content validation
+            if paragraph_text:
+                paragraphs.append(paragraph_text)
+
+        return "\n".join(paragraphs)
+
+
+if __name__ == "__main__":
+    raise RuntimeError("This module should not be run directly.")