@synsci/cli-darwin-x64-baseline 1.1.76 → 1.1.78

package/bin/skills/document-skills/pptx/ooxml/scripts/validation/redlining.py

@@ -0,0 +1,279 @@
+"""
+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):
+        self.unpacked_dir = Path(unpacked_dir)
+        self.original_docx = Path(original_docx)
+        self.verbose = verbose
+        self.namespaces = {
+            "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+        }
+
+    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 Scientific-Writer 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 authored by Scientific-Writer
+            del_elements = root.findall(".//w:del", self.namespaces)
+            ins_elements = root.findall(".//w:ins", self.namespaces)
+
+            # Filter to only include changes by Scientific-Writer
+            sw_del_elements = [
+                elem
+                for elem in del_elements
+                if elem.get(f"{{{self.namespaces['w']}}}author") == "Scientific-Writer"
+            ]
+            sw_ins_elements = [
+                elem
+                for elem in ins_elements
+                if elem.get(f"{{{self.namespaces['w']}}}author") == "Scientific-Writer"
+            ]
+
+            # Redlining validation is only needed if tracked changes by Scientific-Writer have been used.
+            if not sw_del_elements and not sw_ins_elements:
+                if self.verbose:
+                    print("PASSED - No tracked changes by Scientific-Writer 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 Scientific-Writer's tracked changes from both documents
+            self._remove_sw_tracked_changes(original_root)
+            self._remove_sw_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("PASSED - All changes by Scientific-Writer 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 = [
+            "FAILED - Document text doesn't match after removing Scientific-Writer'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_sw_tracked_changes(self, root):
+        """Remove tracked changes authored by Scientific-Writer 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) == "Scientific-Writer":
+                    to_remove.append(child)
+            for elem in to_remove:
+                parent.remove(elem)
+
+        # Unwrap content in w:del elements where author is "Scientific-Writer"
+        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) == "Scientific-Writer":
+                    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.")

package/bin/skills/document-skills/pptx/ooxml.md

@@ -0,0 +1,427 @@
+# Office Open XML Technical Reference for PowerPoint
+
+**Important: Read this entire document before starting.** Critical XML schema rules and formatting requirements are covered throughout. Incorrect implementation can create invalid PPTX files that PowerPoint cannot open.
+
+## Technical Guidelines
+
+### Schema Compliance
+- **Element ordering in `<p:txBody>`**: `<a:bodyPr>`, `<a:lstStyle>`, `<a:p>`
+- **Whitespace**: Add `xml:space='preserve'` to `<a:t>` elements with leading/trailing spaces
+- **Unicode**: Escape characters in ASCII content: `"` becomes `&#8220;`
+- **Images**: Add to `ppt/media/`, reference in slide XML, set dimensions to fit slide bounds
+- **Relationships**: Update `ppt/slides/_rels/slideN.xml.rels` for each slide's resources
+- **Dirty attribute**: Add `dirty="0"` to `<a:rPr>` and `<a:endParaRPr>` elements to indicate clean state
+
+## Presentation Structure
+
+### Basic Slide Structure
+```xml
+<!-- ppt/slides/slide1.xml -->
+<p:sld>
+  <p:cSld>
+    <p:spTree>
+      <p:nvGrpSpPr>...</p:nvGrpSpPr>
+      <p:grpSpPr>...</p:grpSpPr>
+      <!-- Shapes go here -->
+    </p:spTree>
+  </p:cSld>
+</p:sld>
+```
+
+### Text Box / Shape with Text
+```xml
+<p:sp>
+  <p:nvSpPr>
+    <p:cNvPr id="2" name="Title"/>
+    <p:cNvSpPr>
+      <a:spLocks noGrp="1"/>
+    </p:cNvSpPr>
+    <p:nvPr>
+      <p:ph type="ctrTitle"/>
+    </p:nvPr>
+  </p:nvSpPr>
+  <p:spPr>
+    <a:xfrm>
+      <a:off x="838200" y="365125"/>
+      <a:ext cx="7772400" cy="1470025"/>
+    </a:xfrm>
+  </p:spPr>
+  <p:txBody>
+    <a:bodyPr/>
+    <a:lstStyle/>
+    <a:p>
+      <a:r>
+        <a:t>Slide Title</a:t>
+      </a:r>
+    </a:p>
+  </p:txBody>
+</p:sp>
+```
+
+### Text Formatting
+```xml
+<!-- Bold -->
+<a:r>
+  <a:rPr b="1"/>
+  <a:t>Bold Text</a:t>
+</a:r>
+
+<!-- Italic -->
+<a:r>
+  <a:rPr i="1"/>
+  <a:t>Italic Text</a:t>
+</a:r>
+
+<!-- Underline -->
+<a:r>
+  <a:rPr u="sng"/>
+  <a:t>Underlined</a:t>
+</a:r>
+
+<!-- Highlight -->
+<a:r>
+  <a:rPr>
+    <a:highlight>
+      <a:srgbClr val="FFFF00"/>
+    </a:highlight>
+  </a:rPr>
+  <a:t>Highlighted Text</a:t>
+</a:r>
+
+<!-- Font and Size -->
+<a:r>
+  <a:rPr sz="2400" typeface="Arial">
+    <a:solidFill>
+      <a:srgbClr val="FF0000"/>
+    </a:solidFill>
+  </a:rPr>
+  <a:t>Colored Arial 24pt</a:t>
+</a:r>
+
+<!-- Complete formatting example -->
+<a:r>
+  <a:rPr lang="en-US" sz="1400" b="1" dirty="0">
+    <a:solidFill>
+      <a:srgbClr val="FAFAFA"/>
+    </a:solidFill>
+  </a:rPr>
+  <a:t>Formatted text</a:t>
+</a:r>
+```
+
+### Lists
+```xml
+<!-- Bullet list -->
+<a:p>
+  <a:pPr lvl="0">
+    <a:buChar char="•"/>
+  </a:pPr>
+  <a:r>
+    <a:t>First bullet point</a:t>
+  </a:r>
+</a:p>
+
+<!-- Numbered list -->
+<a:p>
+  <a:pPr lvl="0">
+    <a:buAutoNum type="arabicPeriod"/>
+  </a:pPr>
+  <a:r>
+    <a:t>First numbered item</a:t>
+  </a:r>
+</a:p>
+
+<!-- Second level indent -->
+<a:p>
+  <a:pPr lvl="1">
+    <a:buChar char="•"/>
+  </a:pPr>
+  <a:r>
+    <a:t>Indented bullet</a:t>
+  </a:r>
+</a:p>
+```
+
+### Shapes
+```xml
+<!-- Rectangle -->
+<p:sp>
+  <p:nvSpPr>
+    <p:cNvPr id="3" name="Rectangle"/>
+    <p:cNvSpPr/>
+    <p:nvPr/>
+  </p:nvSpPr>
+  <p:spPr>
+    <a:xfrm>
+      <a:off x="1000000" y="1000000"/>
+      <a:ext cx="3000000" cy="2000000"/>
+    </a:xfrm>
+    <a:prstGeom prst="rect">
+      <a:avLst/>
+    </a:prstGeom>
+    <a:solidFill>
+      <a:srgbClr val="FF0000"/>
+    </a:solidFill>
+    <a:ln w="25400">
+      <a:solidFill>
+        <a:srgbClr val="000000"/>
+      </a:solidFill>
+    </a:ln>
+  </p:spPr>
+</p:sp>
+
+<!-- Rounded Rectangle -->
+<p:sp>
+  <p:spPr>
+    <a:prstGeom prst="roundRect">
+      <a:avLst/>
+    </a:prstGeom>
+  </p:spPr>
+</p:sp>
+
+<!-- Circle/Ellipse -->
+<p:sp>
+  <p:spPr>
+    <a:prstGeom prst="ellipse">
+      <a:avLst/>
+    </a:prstGeom>
+  </p:spPr>
+</p:sp>
+```
+
+### Images
+```xml
+<p:pic>
+  <p:nvPicPr>
+    <p:cNvPr id="4" name="Picture">
+      <a:hlinkClick r:id="" action="ppaction://media"/>
+    </p:cNvPr>
+    <p:cNvPicPr>
+      <a:picLocks noChangeAspect="1"/>
+    </p:cNvPicPr>
+    <p:nvPr/>
+  </p:nvPicPr>
+  <p:blipFill>
+    <a:blip r:embed="rId2"/>
+    <a:stretch>
+      <a:fillRect/>
+    </a:stretch>
+  </p:blipFill>
+  <p:spPr>
+    <a:xfrm>
+      <a:off x="1000000" y="1000000"/>
+      <a:ext cx="3000000" cy="2000000"/>
+    </a:xfrm>
+    <a:prstGeom prst="rect">
+      <a:avLst/>
+    </a:prstGeom>
+  </p:spPr>
+</p:pic>
+```
+
+### Tables
+```xml
+<p:graphicFrame>
+  <p:nvGraphicFramePr>
+    <p:cNvPr id="5" name="Table"/>
+    <p:cNvGraphicFramePr>
+      <a:graphicFrameLocks noGrp="1"/>
+    </p:cNvGraphicFramePr>
+    <p:nvPr/>
+  </p:nvGraphicFramePr>
+  <p:xfrm>
+    <a:off x="1000000" y="1000000"/>
+    <a:ext cx="6000000" cy="2000000"/>
+  </p:xfrm>
+  <a:graphic>
+    <a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/table">
+      <a:tbl>
+        <a:tblGrid>
+          <a:gridCol w="3000000"/>
+          <a:gridCol w="3000000"/>
+        </a:tblGrid>
+        <a:tr h="500000">
+          <a:tc>
+            <a:txBody>
+              <a:bodyPr/>
+              <a:lstStyle/>
+              <a:p>
+                <a:r>
+                  <a:t>Cell 1</a:t>
+                </a:r>
+              </a:p>
+            </a:txBody>
+          </a:tc>
+          <a:tc>
+            <a:txBody>
+              <a:bodyPr/>
+              <a:lstStyle/>
+              <a:p>
+                <a:r>
+                  <a:t>Cell 2</a:t>
+                </a:r>
+              </a:p>
+            </a:txBody>
+          </a:tc>
+        </a:tr>
+      </a:tbl>
+    </a:graphicData>
+  </a:graphic>
+</p:graphicFrame>
+```
+
+### Slide Layouts
+
+```xml
+<!-- Title Slide Layout -->
+<p:sp>
+  <p:nvSpPr>
+    <p:nvPr>
+      <p:ph type="ctrTitle"/>
+    </p:nvPr>
+  </p:nvSpPr>
+  <!-- Title content -->
+</p:sp>
+
+<p:sp>
+  <p:nvSpPr>
+    <p:nvPr>
+      <p:ph type="subTitle" idx="1"/>
+    </p:nvPr>
+  </p:nvSpPr>
+  <!-- Subtitle content -->
+</p:sp>
+
+<!-- Content Slide Layout -->
+<p:sp>
+  <p:nvSpPr>
+    <p:nvPr>
+      <p:ph type="title"/>
+    </p:nvPr>
+  </p:nvSpPr>
+  <!-- Slide title -->
+</p:sp>
+
+<p:sp>
+  <p:nvSpPr>
+    <p:nvPr>
+      <p:ph type="body" idx="1"/>
+    </p:nvPr>
+  </p:nvSpPr>
+  <!-- Content body -->
+</p:sp>
+```
+
+## File Updates
+
+When adding content, update these files:
+
+**`ppt/_rels/presentation.xml.rels`:**
+```xml
+<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/slide1.xml"/>
+<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slideMaster" Target="slideMasters/slideMaster1.xml"/>
+```
+
+**`ppt/slides/_rels/slide1.xml.rels`:**
+```xml
+<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slideLayout" Target="../slideLayouts/slideLayout1.xml"/>
+<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/image" Target="../media/image1.png"/>
+```
+
+**`[Content_Types].xml`:**
+```xml
+<Default Extension="png" ContentType="image/png"/>
+<Default Extension="jpg" ContentType="image/jpeg"/>
+<Override PartName="/ppt/slides/slide1.xml" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>
+```
+
+**`ppt/presentation.xml`:**
+```xml
+<p:sldIdLst>
+  <p:sldId id="256" r:id="rId1"/>
+  <p:sldId id="257" r:id="rId2"/>
+</p:sldIdLst>
+```
+
+**`docProps/app.xml`:** Update slide count and statistics
+```xml
+<Slides>2</Slides>
+<Paragraphs>10</Paragraphs>
+<Words>50</Words>
+```
+
+## Slide Operations
+
+### Adding a New Slide
+When adding a slide to the end of the presentation:
+
+1. **Create the slide file** (`ppt/slides/slideN.xml`)
+2. **Update `[Content_Types].xml`**: Add Override for the new slide
+3. **Update `ppt/_rels/presentation.xml.rels`**: Add relationship for the new slide
+4. **Update `ppt/presentation.xml`**: Add slide ID to `<p:sldIdLst>`
+5. **Create slide relationships** (`ppt/slides/_rels/slideN.xml.rels`) if needed
+6. **Update `docProps/app.xml`**: Increment slide count and update statistics (if present)
+
+### Duplicating a Slide
+1. Copy the source slide XML file with a new name
+2. Update all IDs in the new slide to be unique
+3. Follow the "Adding a New Slide" steps above
+4. **CRITICAL**: Remove or update any notes slide references in `_rels` files
+5. Remove references to unused media files
+
+### Reordering Slides
+1. **Update `ppt/presentation.xml`**: Reorder `<p:sldId>` elements in `<p:sldIdLst>`
+2. The order of `<p:sldId>` elements determines slide order
+3. Keep slide IDs and relationship IDs unchanged
+
+Example:
+```xml
+<!-- Original order -->
+<p:sldIdLst>
+  <p:sldId id="256" r:id="rId2"/>
+  <p:sldId id="257" r:id="rId3"/>
+  <p:sldId id="258" r:id="rId4"/>
+</p:sldIdLst>
+
+<!-- After moving slide 3 to position 2 -->
+<p:sldIdLst>
+  <p:sldId id="256" r:id="rId2"/>
+  <p:sldId id="258" r:id="rId4"/>
+  <p:sldId id="257" r:id="rId3"/>
+</p:sldIdLst>
+```
+
+### Deleting a Slide
+1. **Remove from `ppt/presentation.xml`**: Delete the `<p:sldId>` entry
+2. **Remove from `ppt/_rels/presentation.xml.rels`**: Delete the relationship
+3. **Remove from `[Content_Types].xml`**: Delete the Override entry
+4. **Delete files**: Remove `ppt/slides/slideN.xml` and `ppt/slides/_rels/slideN.xml.rels`
+5. **Update `docProps/app.xml`**: Decrement slide count and update statistics
+6. **Clean up unused media**: Remove orphaned images from `ppt/media/`
+
+Note: Don't renumber remaining slides - keep their original IDs and filenames.
+
+
+## Common Errors to Avoid
+
+- **Encodings**: Escape unicode characters in ASCII content: `"` becomes `&#8220;`
+- **Images**: Add to `ppt/media/` and update relationship files
+- **Lists**: Omit bullets from list headers
+- **IDs**: Use valid hexadecimal values for UUIDs
+- **Themes**: Check all themes in `theme` directory for colors
+
+## Validation Checklist for Template-Based Presentations
+
+### Before Packing, Always:
+- **Clean unused resources**: Remove unreferenced media, fonts, and notes directories
+- **Fix Content_Types.xml**: Declare ALL slides, layouts, and themes present in the package
+- **Fix relationship IDs**: 
+   - Remove font embed references if not using embedded fonts
+- **Remove broken references**: Check all `_rels` files for references to deleted resources
+
+### Common Template Duplication Pitfalls:
+- Multiple slides referencing the same notes slide after duplication
+- Image/media references from template slides that no longer exist
+- Font embedding references when fonts aren't included
+- Missing slideLayout declarations for layouts 12-25
+- docProps directory may not unpack - this is optional