cli-jaw 0.1.0

package/skills_ref/pptx/scripts/add_slide.py

@@ -0,0 +1,195 @@
+"""Add a new slide to an unpacked PPTX directory.
+
+Usage: python add_slide.py <unpacked_dir> <source>
+
+The source can be:
+  - A slide file (e.g., slide2.xml) - duplicates the slide
+  - A layout file (e.g., slideLayout2.xml) - creates from layout
+
+Examples:
+    python add_slide.py unpacked/ slide2.xml
+    # Duplicates slide2, creates slide5.xml
+
+    python add_slide.py unpacked/ slideLayout2.xml
+    # Creates slide5.xml from slideLayout2.xml
+
+To see available layouts: ls unpacked/ppt/slideLayouts/
+
+Prints the <p:sldId> element to add to presentation.xml.
+"""
+
+import re
+import shutil
+import sys
+from pathlib import Path
+
+
+def get_next_slide_number(slides_dir: Path) -> int:
+    existing = [int(m.group(1)) for f in slides_dir.glob("slide*.xml")
+                if (m := re.match(r"slide(\d+)\.xml", f.name))]
+    return max(existing) + 1 if existing else 1
+
+
+def create_slide_from_layout(unpacked_dir: Path, layout_file: str) -> None:
+    slides_dir = unpacked_dir / "ppt" / "slides"
+    rels_dir = slides_dir / "_rels"
+    layouts_dir = unpacked_dir / "ppt" / "slideLayouts"
+
+    layout_path = layouts_dir / layout_file
+    if not layout_path.exists():
+        print(f"Error: {layout_path} not found", file=sys.stderr)
+        sys.exit(1)
+
+    next_num = get_next_slide_number(slides_dir)
+    dest = f"slide{next_num}.xml"
+    dest_slide = slides_dir / dest
+    dest_rels = rels_dir / f"{dest}.rels"
+
+    slide_xml = '''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<p:sld xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:p="http://schemas.openxmlformats.org/presentationml/2006/main">
+  <p:cSld>
+    <p:spTree>
+      <p:nvGrpSpPr>
+        <p:cNvPr id="1" name=""/>
+        <p:cNvGrpSpPr/>
+        <p:nvPr/>
+      </p:nvGrpSpPr>
+      <p:grpSpPr>
+        <a:xfrm>
+          <a:off x="0" y="0"/>
+          <a:ext cx="0" cy="0"/>
+          <a:chOff x="0" y="0"/>
+          <a:chExt cx="0" cy="0"/>
+        </a:xfrm>
+      </p:grpSpPr>
+    </p:spTree>
+  </p:cSld>
+  <p:clrMapOvr>
+    <a:masterClrMapping/>
+  </p:clrMapOvr>
+</p:sld>'''
+    dest_slide.write_text(slide_xml, encoding="utf-8")
+
+    rels_dir.mkdir(exist_ok=True)
+    rels_xml = f'''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
+  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slideLayout" Target="../slideLayouts/{layout_file}"/>
+</Relationships>'''
+    dest_rels.write_text(rels_xml, encoding="utf-8")
+
+    _add_to_content_types(unpacked_dir, dest)
+
+    rid = _add_to_presentation_rels(unpacked_dir, dest)
+
+    next_slide_id = _get_next_slide_id(unpacked_dir)
+
+    print(f"Created {dest} from {layout_file}")
+    print(f'Add to presentation.xml <p:sldIdLst>: <p:sldId id="{next_slide_id}" r:id="{rid}"/>')
+
+
+def duplicate_slide(unpacked_dir: Path, source: str) -> None:
+    slides_dir = unpacked_dir / "ppt" / "slides"
+    rels_dir = slides_dir / "_rels"
+
+    source_slide = slides_dir / source
+
+    if not source_slide.exists():
+        print(f"Error: {source_slide} not found", file=sys.stderr)
+        sys.exit(1)
+
+    next_num = get_next_slide_number(slides_dir)
+    dest = f"slide{next_num}.xml"
+    dest_slide = slides_dir / dest
+
+    source_rels = rels_dir / f"{source}.rels"
+    dest_rels = rels_dir / f"{dest}.rels"
+
+    shutil.copy2(source_slide, dest_slide)
+
+    if source_rels.exists():
+        shutil.copy2(source_rels, dest_rels)
+
+        rels_content = dest_rels.read_text(encoding="utf-8")
+        rels_content = re.sub(
+            r'\s*<Relationship[^>]*Type="[^"]*notesSlide"[^>]*/>\s*',
+            "\n",
+            rels_content,
+        )
+        dest_rels.write_text(rels_content, encoding="utf-8")
+
+    _add_to_content_types(unpacked_dir, dest)
+
+    rid = _add_to_presentation_rels(unpacked_dir, dest)
+
+    next_slide_id = _get_next_slide_id(unpacked_dir)
+
+    print(f"Created {dest} from {source}")
+    print(f'Add to presentation.xml <p:sldIdLst>: <p:sldId id="{next_slide_id}" r:id="{rid}"/>')
+
+
+def _add_to_content_types(unpacked_dir: Path, dest: str) -> None:
+    content_types_path = unpacked_dir / "[Content_Types].xml"
+    content_types = content_types_path.read_text(encoding="utf-8")
+
+    new_override = f'<Override PartName="/ppt/slides/{dest}" ContentType="application/vnd.openxmlformats-officedocument.presentationml.slide+xml"/>'
+
+    if f"/ppt/slides/{dest}" not in content_types:
+        content_types = content_types.replace("</Types>", f"  {new_override}\n</Types>")
+        content_types_path.write_text(content_types, encoding="utf-8")
+
+
+def _add_to_presentation_rels(unpacked_dir: Path, dest: str) -> str:
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+    pres_rels = pres_rels_path.read_text(encoding="utf-8")
+
+    rids = [int(m) for m in re.findall(r'Id="rId(\d+)"', pres_rels)]
+    next_rid = max(rids) + 1 if rids else 1
+    rid = f"rId{next_rid}"
+
+    new_rel = f'<Relationship Id="{rid}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide" Target="slides/{dest}"/>'
+
+    if f"slides/{dest}" not in pres_rels:
+        pres_rels = pres_rels.replace("</Relationships>", f"  {new_rel}\n</Relationships>")
+        pres_rels_path.write_text(pres_rels, encoding="utf-8")
+
+    return rid
+
+
+def _get_next_slide_id(unpacked_dir: Path) -> int:
+    pres_path = unpacked_dir / "ppt" / "presentation.xml"
+    pres_content = pres_path.read_text(encoding="utf-8")
+    slide_ids = [int(m) for m in re.findall(r'<p:sldId[^>]*id="(\d+)"', pres_content)]
+    return max(slide_ids) + 1 if slide_ids else 256
+
+
+def parse_source(source: str) -> tuple[str, str | None]:
+    if source.startswith("slideLayout") and source.endswith(".xml"):
+        return ("layout", source)
+
+    return ("slide", None)
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: python add_slide.py <unpacked_dir> <source>", file=sys.stderr)
+        print("", file=sys.stderr)
+        print("Source can be:", file=sys.stderr)
+        print("  slide2.xml        - duplicate an existing slide", file=sys.stderr)
+        print("  slideLayout2.xml  - create from a layout template", file=sys.stderr)
+        print("", file=sys.stderr)
+        print("To see available layouts: ls <unpacked_dir>/ppt/slideLayouts/", file=sys.stderr)
+        sys.exit(1)
+
+    unpacked_dir = Path(sys.argv[1])
+    source = sys.argv[2]
+
+    if not unpacked_dir.exists():
+        print(f"Error: {unpacked_dir} not found", file=sys.stderr)
+        sys.exit(1)
+
+    source_type, layout_file = parse_source(source)
+
+    if source_type == "layout" and layout_file is not None:
+        create_slide_from_layout(unpacked_dir, layout_file)
+    else:
+        duplicate_slide(unpacked_dir, source)

package/skills_ref/pptx/scripts/clean.py

@@ -0,0 +1,286 @@
+"""Remove unreferenced files from an unpacked PPTX directory.
+
+Usage: python clean.py <unpacked_dir>
+
+Example:
+    python clean.py unpacked/
+
+This script removes:
+- Orphaned slides (not in sldIdLst) and their relationships
+- [trash] directory (unreferenced files)
+- Orphaned .rels files for deleted resources
+- Unreferenced media, embeddings, charts, diagrams, drawings, ink files
+- Unreferenced theme files
+- Unreferenced notes slides
+- Content-Type overrides for deleted files
+"""
+
+import sys
+from pathlib import Path
+
+import defusedxml.minidom
+
+
+import re
+
+
+def get_slides_in_sldidlst(unpacked_dir: Path) -> set[str]:
+    pres_path = unpacked_dir / "ppt" / "presentation.xml"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not pres_path.exists() or not pres_rels_path.exists():
+        return set()
+
+    rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+    rid_to_slide = {}
+    for rel in rels_dom.getElementsByTagName("Relationship"):
+        rid = rel.getAttribute("Id")
+        target = rel.getAttribute("Target")
+        rel_type = rel.getAttribute("Type")
+        if "slide" in rel_type and target.startswith("slides/"):
+            rid_to_slide[rid] = target.replace("slides/", "")
+
+    pres_content = pres_path.read_text(encoding="utf-8")
+    referenced_rids = set(re.findall(r'<p:sldId[^>]*r:id="([^"]+)"', pres_content))
+
+    return {rid_to_slide[rid] for rid in referenced_rids if rid in rid_to_slide}
+
+
+def remove_orphaned_slides(unpacked_dir: Path) -> list[str]:
+    slides_dir = unpacked_dir / "ppt" / "slides"
+    slides_rels_dir = slides_dir / "_rels"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not slides_dir.exists():
+        return []
+
+    referenced_slides = get_slides_in_sldidlst(unpacked_dir)
+    removed = []
+
+    for slide_file in slides_dir.glob("slide*.xml"):
+        if slide_file.name not in referenced_slides:
+            rel_path = slide_file.relative_to(unpacked_dir)
+            slide_file.unlink()
+            removed.append(str(rel_path))
+
+            rels_file = slides_rels_dir / f"{slide_file.name}.rels"
+            if rels_file.exists():
+                rels_file.unlink()
+                removed.append(str(rels_file.relative_to(unpacked_dir)))
+
+    if removed and pres_rels_path.exists():
+        rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+        changed = False
+
+        for rel in list(rels_dom.getElementsByTagName("Relationship")):
+            target = rel.getAttribute("Target")
+            if target.startswith("slides/"):
+                slide_name = target.replace("slides/", "")
+                if slide_name not in referenced_slides:
+                    if rel.parentNode:
+                        rel.parentNode.removeChild(rel)
+                        changed = True
+
+        if changed:
+            with open(pres_rels_path, "wb") as f:
+                f.write(rels_dom.toxml(encoding="utf-8"))
+
+    return removed
+
+
+def remove_trash_directory(unpacked_dir: Path) -> list[str]:
+    trash_dir = unpacked_dir / "[trash]"
+    removed = []
+
+    if trash_dir.exists() and trash_dir.is_dir():
+        for file_path in trash_dir.iterdir():
+            if file_path.is_file():
+                rel_path = file_path.relative_to(unpacked_dir)
+                removed.append(str(rel_path))
+                file_path.unlink()
+        trash_dir.rmdir()
+
+    return removed
+
+
+def get_slide_referenced_files(unpacked_dir: Path) -> set:
+    referenced = set()
+    slides_rels_dir = unpacked_dir / "ppt" / "slides" / "_rels"
+
+    if not slides_rels_dir.exists():
+        return referenced
+
+    for rels_file in slides_rels_dir.glob("*.rels"):
+        dom = defusedxml.minidom.parse(str(rels_file))
+        for rel in dom.getElementsByTagName("Relationship"):
+            target = rel.getAttribute("Target")
+            if not target:
+                continue
+            target_path = (rels_file.parent.parent / target).resolve()
+            try:
+                referenced.add(target_path.relative_to(unpacked_dir.resolve()))
+            except ValueError:
+                pass
+
+    return referenced
+
+
+def remove_orphaned_rels_files(unpacked_dir: Path) -> list[str]:
+    resource_dirs = ["charts", "diagrams", "drawings"]
+    removed = []
+    slide_referenced = get_slide_referenced_files(unpacked_dir)
+
+    for dir_name in resource_dirs:
+        rels_dir = unpacked_dir / "ppt" / dir_name / "_rels"
+        if not rels_dir.exists():
+            continue
+
+        for rels_file in rels_dir.glob("*.rels"):
+            resource_file = rels_dir.parent / rels_file.name.replace(".rels", "")
+            try:
+                resource_rel_path = resource_file.resolve().relative_to(unpacked_dir.resolve())
+            except ValueError:
+                continue
+
+            if not resource_file.exists() or resource_rel_path not in slide_referenced:
+                rels_file.unlink()
+                rel_path = rels_file.relative_to(unpacked_dir)
+                removed.append(str(rel_path))
+
+    return removed
+
+
+def get_referenced_files(unpacked_dir: Path) -> set:
+    referenced = set()
+
+    for rels_file in unpacked_dir.rglob("*.rels"):
+        dom = defusedxml.minidom.parse(str(rels_file))
+        for rel in dom.getElementsByTagName("Relationship"):
+            target = rel.getAttribute("Target")
+            if not target:
+                continue
+            target_path = (rels_file.parent.parent / target).resolve()
+            try:
+                referenced.add(target_path.relative_to(unpacked_dir.resolve()))
+            except ValueError:
+                pass
+
+    return referenced
+
+
+def remove_orphaned_files(unpacked_dir: Path, referenced: set) -> list[str]:
+    resource_dirs = ["media", "embeddings", "charts", "diagrams", "tags", "drawings", "ink"]
+    removed = []
+
+    for dir_name in resource_dirs:
+        dir_path = unpacked_dir / "ppt" / dir_name
+        if not dir_path.exists():
+            continue
+
+        for file_path in dir_path.glob("*"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+    theme_dir = unpacked_dir / "ppt" / "theme"
+    if theme_dir.exists():
+        for file_path in theme_dir.glob("theme*.xml"):
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+                theme_rels = theme_dir / "_rels" / f"{file_path.name}.rels"
+                if theme_rels.exists():
+                    theme_rels.unlink()
+                    removed.append(str(theme_rels.relative_to(unpacked_dir)))
+
+    notes_dir = unpacked_dir / "ppt" / "notesSlides"
+    if notes_dir.exists():
+        for file_path in notes_dir.glob("*.xml"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+        notes_rels_dir = notes_dir / "_rels"
+        if notes_rels_dir.exists():
+            for file_path in notes_rels_dir.glob("*.rels"):
+                notes_file = notes_dir / file_path.name.replace(".rels", "")
+                if not notes_file.exists():
+                    file_path.unlink()
+                    removed.append(str(file_path.relative_to(unpacked_dir)))
+
+    return removed
+
+
+def update_content_types(unpacked_dir: Path, removed_files: list[str]) -> None:
+    ct_path = unpacked_dir / "[Content_Types].xml"
+    if not ct_path.exists():
+        return
+
+    dom = defusedxml.minidom.parse(str(ct_path))
+    changed = False
+
+    for override in list(dom.getElementsByTagName("Override")):
+        part_name = override.getAttribute("PartName").lstrip("/")
+        if part_name in removed_files:
+            if override.parentNode:
+                override.parentNode.removeChild(override)
+                changed = True
+
+    if changed:
+        with open(ct_path, "wb") as f:
+            f.write(dom.toxml(encoding="utf-8"))
+
+
+def clean_unused_files(unpacked_dir: Path) -> list[str]:
+    all_removed = []
+
+    slides_removed = remove_orphaned_slides(unpacked_dir)
+    all_removed.extend(slides_removed)
+
+    trash_removed = remove_trash_directory(unpacked_dir)
+    all_removed.extend(trash_removed)
+
+    while True:
+        removed_rels = remove_orphaned_rels_files(unpacked_dir)
+        referenced = get_referenced_files(unpacked_dir)
+        removed_files = remove_orphaned_files(unpacked_dir, referenced)
+
+        total_removed = removed_rels + removed_files
+        if not total_removed:
+            break
+
+        all_removed.extend(total_removed)
+
+    if all_removed:
+        update_content_types(unpacked_dir, all_removed)
+
+    return all_removed
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python clean.py <unpacked_dir>", file=sys.stderr)
+        print("Example: python clean.py unpacked/", file=sys.stderr)
+        sys.exit(1)
+
+    unpacked_dir = Path(sys.argv[1])
+
+    if not unpacked_dir.exists():
+        print(f"Error: {unpacked_dir} not found", file=sys.stderr)
+        sys.exit(1)
+
+    removed = clean_unused_files(unpacked_dir)
+
+    if removed:
+        print(f"Removed {len(removed)} unreferenced files:")
+        for f in removed:
+            print(f"  {f}")
+    else:
+        print("No unreferenced files found")

package/skills_ref/pptx/scripts/office/helpers/merge_runs.py

@@ -0,0 +1,199 @@
+"""Merge adjacent runs with identical formatting in DOCX.
+
+Merges adjacent <w:r> elements that have identical <w:rPr> properties.
+Works on runs in paragraphs and inside tracked changes (<w:ins>, <w:del>).
+
+Also:
+- Removes rsid attributes from runs (revision metadata that doesn't affect rendering)
+- Removes proofErr elements (spell/grammar markers that block merging)
+"""
+
+from pathlib import Path
+
+import defusedxml.minidom
+
+
+def merge_runs(input_dir: str) -> tuple[int, str]:
+    doc_xml = Path(input_dir) / "word" / "document.xml"
+
+    if not doc_xml.exists():
+        return 0, f"Error: {doc_xml} not found"
+
+    try:
+        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
+        root = dom.documentElement
+
+        _remove_elements(root, "proofErr")
+        _strip_run_rsid_attrs(root)
+
+        containers = {run.parentNode for run in _find_elements(root, "r")}
+
+        merge_count = 0
+        for container in containers:
+            merge_count += _merge_runs_in(container)
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Merged {merge_count} runs"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+
+
+def _find_elements(root, tag: str) -> list:
+    results = []
+
+    def traverse(node):
+        if node.nodeType == node.ELEMENT_NODE:
+            name = node.localName or node.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(node)
+            for child in node.childNodes:
+                traverse(child)
+
+    traverse(root)
+    return results
+
+
+def _get_child(parent, tag: str):
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                return child
+    return None
+
+
+def _get_children(parent, tag: str) -> list:
+    results = []
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(child)
+    return results
+
+
+def _is_adjacent(elem1, elem2) -> bool:
+    node = elem1.nextSibling
+    while node:
+        if node == elem2:
+            return True
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+    return False
+
+
+
+
+def _remove_elements(root, tag: str):
+    for elem in _find_elements(root, tag):
+        if elem.parentNode:
+            elem.parentNode.removeChild(elem)
+
+
+def _strip_run_rsid_attrs(root):
+    for run in _find_elements(root, "r"):
+        for attr in list(run.attributes.values()):
+            if "rsid" in attr.name.lower():
+                run.removeAttribute(attr.name)
+
+
+
+
+def _merge_runs_in(container) -> int:
+    merge_count = 0
+    run = _first_child_run(container)
+
+    while run:
+        while True:
+            next_elem = _next_element_sibling(run)
+            if next_elem and _is_run(next_elem) and _can_merge(run, next_elem):
+                _merge_run_content(run, next_elem)
+                container.removeChild(next_elem)
+                merge_count += 1
+            else:
+                break
+
+        _consolidate_text(run)
+        run = _next_sibling_run(run)
+
+    return merge_count
+
+
+def _first_child_run(container):
+    for child in container.childNodes:
+        if child.nodeType == child.ELEMENT_NODE and _is_run(child):
+            return child
+    return None
+
+
+def _next_element_sibling(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _next_sibling_run(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            if _is_run(sibling):
+                return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _is_run(node) -> bool:
+    name = node.localName or node.tagName
+    return name == "r" or name.endswith(":r")
+
+
+def _can_merge(run1, run2) -> bool:
+    rpr1 = _get_child(run1, "rPr")
+    rpr2 = _get_child(run2, "rPr")
+
+    if (rpr1 is None) != (rpr2 is None):
+        return False
+    if rpr1 is None:
+        return True
+    return rpr1.toxml() == rpr2.toxml()  
+
+
+def _merge_run_content(target, source):
+    for child in list(source.childNodes):
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name != "rPr" and not name.endswith(":rPr"):
+                target.appendChild(child)
+
+
+def _consolidate_text(run):
+    t_elements = _get_children(run, "t")
+
+    for i in range(len(t_elements) - 1, 0, -1):
+        curr, prev = t_elements[i], t_elements[i - 1]
+
+        if _is_adjacent(prev, curr):
+            prev_text = prev.firstChild.data if prev.firstChild else ""
+            curr_text = curr.firstChild.data if curr.firstChild else ""
+            merged = prev_text + curr_text
+
+            if prev.firstChild:
+                prev.firstChild.data = merged
+            else:
+                prev.appendChild(run.ownerDocument.createTextNode(merged))
+
+            if merged.startswith(" ") or merged.endswith(" "):
+                prev.setAttribute("xml:space", "preserve")
+            elif prev.hasAttribute("xml:space"):
+                prev.removeAttribute("xml:space")
+
+            run.removeChild(curr)