anymous 1.2.7 → 1.3.0

package/skills/docx/scripts/comment.py

@@ -0,0 +1,368 @@
+"""Add comments to a DOCX document.
+
+Accepts either an unpacked directory OR a .docx/.dotx file directly.
+
+Usage:
+    # Against an unpacked directory (writes satellite files in place)
+    python comment.py unpacked/ "Comment text"
+    python comment.py unpacked/ "Reply text" --parent 0
+
+    # Against a .docx directly (extracts, writes satellite files, rezips)
+    python comment.py contract.docx "This cap is too low" -o annotated.docx
+    python comment.py contract.docx "Comment" --id 5      # explicit ID
+
+The comment ID is auto-assigned (max existing + 1) unless --id is given.
+Plain text is XML-escaped automatically; if you pass already-escaped text
+(e.g. &, ’) use --raw to skip escaping.
+
+After running, add markers to word/document.xml so the comment is visible:
+  <w:commentRangeStart w:id="N"/>
+  ... commented content ...
+  <w:commentRangeEnd w:id="N"/>
+  <w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="N"/></w:r>
+"""
+
+import argparse
+import random
+import shutil
+import sys
+import tempfile
+import zipfile
+from datetime import datetime, timezone
+from pathlib import Path
+
+import defusedxml.minidom
+from xml.parsers.expat import ExpatError
+from xml.sax.saxutils import escape as xml_escape
+
+from office.helpers import opc_target, rezip as _rezip, safe_extract as _safe_extract
+
+TEMPLATE_DIR = Path(__file__).parent / "templates"
+NS = {
+    "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main",
+    "w14": "http://schemas.microsoft.com/office/word/2010/wordml",
+    "w15": "http://schemas.microsoft.com/office/word/2012/wordml",
+    "w16cid": "http://schemas.microsoft.com/office/word/2016/wordml/cid",
+    "w16cex": "http://schemas.microsoft.com/office/word/2018/wordml/cex",
+}
+
+COMMENT_XML = """\
+<w:comment w:id="{id}" w:author="{author}" w:date="{date}" w:initials="{initials}">
+  <w:p w14:paraId="{para_id}" w14:textId="77777777">
+    <w:r>
+      <w:rPr><w:rStyle w:val="CommentReference"/></w:rPr>
+      <w:annotationRef/>
+    </w:r>
+    <w:r>
+      <w:rPr>
+        <w:color w:val="000000"/>
+        <w:sz w:val="20"/>
+        <w:szCs w:val="20"/>
+      </w:rPr>
+      <w:t xml:space="preserve">{text}</w:t>
+    </w:r>
+  </w:p>
+</w:comment>"""
+
+COMMENT_MARKER_TEMPLATE = """
+Add to word/document.xml (markers must be direct children of w:p, never inside w:r):
+  <w:commentRangeStart w:id="{cid}"/>
+  <w:r>...</w:r>
+  <w:commentRangeEnd w:id="{cid}"/>
+  <w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="{cid}"/></w:r>"""
+
+REPLY_MARKER_TEMPLATE = """
+Nest markers inside parent {pid}'s markers (direct children of w:p, never inside w:r):
+  <w:commentRangeStart w:id="{pid}"/><w:commentRangeStart w:id="{cid}"/>
+  <w:r>...</w:r>
+  <w:commentRangeEnd w:id="{cid}"/><w:commentRangeEnd w:id="{pid}"/>
+  <w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="{pid}"/></w:r>
+  <w:r><w:rPr><w:rStyle w:val="CommentReference"/></w:rPr><w:commentReference w:id="{cid}"/></w:r>"""
+
+SMART_QUOTE_ENTITIES = {
+    "“": "&#x201C;",
+    "”": "&#x201D;",
+    "‘": "&#x2018;",
+    "’": "&#x2019;",
+}
+
+
+def _generate_hex_id() -> str:
+    return f"{random.randint(0, 0x7FFFFFFE):08X}"
+
+
+def _encode_smart_quotes(text: str) -> str:
+    for char, entity in SMART_QUOTE_ENTITIES.items():
+        text = text.replace(char, entity)
+    return text
+
+
+def _append_xml(xml_path: Path, root_tag: str, content: str) -> None:
+    dom = defusedxml.minidom.parseString(xml_path.read_text(encoding="utf-8"))
+    root = dom.getElementsByTagName(root_tag)[0]
+    ns_attrs = " ".join(f'xmlns:{k}="{v}"' for k, v in NS.items())
+    wrapper_dom = defusedxml.minidom.parseString(f"<root {ns_attrs}>{content}</root>")
+    for child in wrapper_dom.documentElement.childNodes:  
+        if child.nodeType == child.ELEMENT_NODE:
+            root.appendChild(dom.importNode(child, True))
+    output = _encode_smart_quotes(dom.toxml(encoding="UTF-8").decode("utf-8"))
+    xml_path.write_text(output, encoding="utf-8")
+
+
+def _find_para_id(comments_path: Path, comment_id: int) -> str | None:
+    dom = defusedxml.minidom.parseString(comments_path.read_text(encoding="utf-8"))
+    for c in dom.getElementsByTagName("w:comment"):
+        if c.getAttribute("w:id") == str(comment_id):
+            for p in c.getElementsByTagName("w:p"):
+                if pid := p.getAttribute("w14:paraId"):
+                    return pid
+    return None
+
+
+def _next_comment_id(comments_path: Path) -> int:
+    if not comments_path.exists():
+        return 0
+    dom = defusedxml.minidom.parseString(comments_path.read_text(encoding="utf-8"))
+    ids = []
+    for c in dom.getElementsByTagName("w:comment"):
+        try:
+            ids.append(int(c.getAttribute("w:id")))
+        except ValueError:
+            pass
+    return (max(ids) + 1) if ids else 0
+
+
+def _get_next_rid(rels_path: Path) -> int:
+    dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8"))
+    max_rid = 0
+    for rel in dom.getElementsByTagName("Relationship"):
+        rid = rel.getAttribute("Id")
+        if rid and rid.startswith("rId"):
+            try:
+                max_rid = max(max_rid, int(rid[3:]))
+            except ValueError:
+                pass
+    return max_rid + 1
+
+
+def _has_relationship(rels_path: Path, target: str) -> bool:
+    dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8"))
+    return any(
+        rel.getAttribute("Target") == target
+        for rel in dom.getElementsByTagName("Relationship")
+    )
+
+
+def _has_content_type(ct_path: Path, part_name: str) -> bool:
+    dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8"))
+    return any(
+        o.getAttribute("PartName") == part_name
+        for o in dom.getElementsByTagName("Override")
+    )
+
+
+_COMMENT_RELS = [
+    ("http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments", "comments.xml"),
+    ("http://schemas.microsoft.com/office/2011/relationships/commentsExtended", "commentsExtended.xml"),
+    ("http://schemas.microsoft.com/office/2016/09/relationships/commentsIds", "commentsIds.xml"),
+    ("http://schemas.microsoft.com/office/2018/08/relationships/commentsExtensible", "commentsExtensible.xml"),
+]
+_COMMENT_OVERRIDES = [
+    ("/word/comments.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml"),
+    ("/word/commentsExtended.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtended+xml"),
+    ("/word/commentsIds.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsIds+xml"),
+    ("/word/commentsExtensible.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtensible+xml"),
+]
+
+
+def _ensure_comment_relationships(unpacked_dir: Path) -> None:
+    rels_path = unpacked_dir / "word" / "_rels" / "document.xml.rels"
+    if not rels_path.exists():
+        return
+    dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8"))
+    root = dom.documentElement
+    comment_types = {rel_type for rel_type, _ in _COMMENT_RELS}
+    existing = set()
+    for rel in dom.getElementsByTagName("Relationship"):
+        if rel.getAttribute("Type") not in comment_types:
+            continue
+        part = opc_target(
+            rel.getAttribute("Target"),
+            "word/document.xml",
+            rel.getAttribute("TargetMode"),
+        )
+        if part is not None:
+            existing.add(part)
+    next_rid = _get_next_rid(rels_path)
+    changed = False
+    for rel_type, target in _COMMENT_RELS:
+        if opc_target(target, "word/document.xml") in existing:
+            continue
+        rel = dom.createElement("Relationship")
+        rel.setAttribute("Id", f"rId{next_rid}")
+        rel.setAttribute("Type", rel_type)
+        rel.setAttribute("Target", target)
+        root.appendChild(rel)  
+        next_rid += 1
+        changed = True
+    if changed:
+        rels_path.write_bytes(dom.toxml(encoding="UTF-8"))
+
+
+def _ensure_comment_content_types(unpacked_dir: Path) -> None:
+    ct_path = unpacked_dir / "[Content_Types].xml"
+    if not ct_path.exists():
+        return
+    dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8"))
+    root = dom.documentElement
+    existing = {
+        o.getAttribute("PartName")
+        for o in dom.getElementsByTagName("Override")
+    }
+    changed = False
+    for part_name, content_type in _COMMENT_OVERRIDES:
+        if part_name in existing:
+            continue
+        override = dom.createElement("Override")
+        override.setAttribute("PartName", part_name)
+        override.setAttribute("ContentType", content_type)
+        root.appendChild(override)  
+        changed = True
+    if changed:
+        ct_path.write_bytes(dom.toxml(encoding="UTF-8"))
+
+
+def add_comment(
+    unpacked_dir: Path | str,
+    text: str,
+    comment_id: int | None = None,
+    author: str = "Claude",
+    initials: str = "C",
+    parent_id: int | None = None,
+    raw: bool = False,
+) -> tuple[int, str, str]:
+    unpacked_dir = Path(unpacked_dir)
+    if not raw:
+        text = xml_escape(text)
+    author = xml_escape(author, {'"': "&quot;"})
+    initials = xml_escape(initials, {'"': "&quot;"})
+    word = unpacked_dir / "word"
+    if not word.exists():
+        raise FileNotFoundError(f"{word} not found (not an unpacked .docx?)")
+
+    comments = word / "comments.xml"
+    if comment_id is None:
+        comment_id = _next_comment_id(comments)
+
+    parent_para = None
+    if parent_id is not None:
+        parent_para = _find_para_id(comments, parent_id) if comments.exists() else None
+        if not parent_para:
+            raise ValueError(f"parent comment {parent_id} not found")
+
+    para_id, durable_id = _generate_hex_id(), _generate_hex_id()
+    ts = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
+
+    if not comments.exists():
+        shutil.copy(TEMPLATE_DIR / "comments.xml", comments)
+    _ensure_comment_relationships(unpacked_dir)
+    _ensure_comment_content_types(unpacked_dir)
+    _append_xml(
+        comments,
+        "w:comments",
+        COMMENT_XML.format(
+            id=comment_id, author=author, date=ts, initials=initials,
+            para_id=para_id, text=text,
+        ),
+    )
+
+    ext = word / "commentsExtended.xml"
+    if not ext.exists():
+        shutil.copy(TEMPLATE_DIR / "commentsExtended.xml", ext)
+    if parent_para is not None:
+        _append_xml(
+            ext, "w15:commentsEx",
+            f'<w15:commentEx w15:paraId="{para_id}" w15:paraIdParent="{parent_para}" w15:done="0"/>',
+        )
+    else:
+        _append_xml(
+            ext, "w15:commentsEx",
+            f'<w15:commentEx w15:paraId="{para_id}" w15:done="0"/>',
+        )
+
+    ids = word / "commentsIds.xml"
+    if not ids.exists():
+        shutil.copy(TEMPLATE_DIR / "commentsIds.xml", ids)
+    _append_xml(
+        ids, "w16cid:commentsIds",
+        f'<w16cid:commentId w16cid:paraId="{para_id}" w16cid:durableId="{durable_id}"/>',
+    )
+
+    extensible = word / "commentsExtensible.xml"
+    if not extensible.exists():
+        shutil.copy(TEMPLATE_DIR / "commentsExtensible.xml", extensible)
+    _append_xml(
+        extensible, "w16cex:commentsExtensible",
+        f'<w16cex:commentExtensible w16cex:durableId="{durable_id}" w16cex:dateUtc="{ts}"/>',
+    )
+
+    action = "reply" if parent_id is not None else "comment"
+    return comment_id, para_id, f"Added {action} id={comment_id} (paraId={para_id})"
+
+
+def main() -> None:
+    p = argparse.ArgumentParser(description="Add a comment to a DOCX (directory or .docx file).")
+    p.add_argument("input", help="Unpacked DOCX directory OR a .docx/.dotx file")
+    p.add_argument("text", help="Comment text (plain text; XML-escaped automatically)")
+    p.add_argument("--raw", action="store_true",
+                   help="Treat text as pre-escaped XML (skip automatic escaping)")
+    p.add_argument("--id", type=int, dest="comment_id",
+                   help="Comment ID (default: auto-assign as max existing + 1)")
+    p.add_argument("--author", default="Claude", help="Author name")
+    p.add_argument("--initials", default="C", help="Author initials")
+    p.add_argument("--parent", type=int, help="Parent comment ID (makes this a reply)")
+    p.add_argument("-o", "--output",
+                   help="Output .docx path (only used when input is a .docx; default: overwrite input)")
+    args = p.parse_args()
+
+    src = Path(args.input)
+
+    try:
+        if src.is_dir():
+            if args.output:
+                print("Warning: --output ignored for directory input", file=sys.stderr)
+            cid, _, msg = add_comment(
+                src, args.text, comment_id=args.comment_id,
+                author=args.author, initials=args.initials,
+                parent_id=args.parent, raw=args.raw,
+            )
+            print(msg)
+        elif src.is_file() and src.suffix.lower() in (".docx", ".dotx"):
+            out = Path(args.output) if args.output else src
+            with tempfile.TemporaryDirectory() as tmp:
+                tmp_path = Path(tmp)
+                with zipfile.ZipFile(src) as zf:
+                    _safe_extract(zf, tmp_path)
+                cid, _, msg = add_comment(
+                    tmp_path, args.text, comment_id=args.comment_id,
+                    author=args.author, initials=args.initials,
+                    parent_id=args.parent, raw=args.raw,
+                )
+                _rezip(tmp_path, out)
+            print(msg)
+            print(f"Wrote {out} (comment defined; add markers to word/document.xml to make it visible)")
+        else:
+            print(f"Error: {src} is neither a directory nor a .docx/.dotx file", file=sys.stderr)
+            sys.exit(1)
+    except (FileNotFoundError, ValueError, zipfile.BadZipFile, ExpatError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if args.parent is not None:
+        print(REPLY_MARKER_TEMPLATE.format(pid=args.parent, cid=cid))
+    else:
+        print(COMMENT_MARKER_TEMPLATE.format(cid=cid))
+
+
+if __name__ == "__main__":
+    main()

package/skills/docx/scripts/merge_runs.py

@@ -0,0 +1,310 @@
+"""Merge adjacent identically-formatted runs in a DOCX.
+
+Word fragments paragraph text across many <w:r> elements (revision ids,
+spell-check markers, editing history), which makes find-and-replace on
+word/document.xml unreliable — the string you're looking for is split
+across runs. This coalesces adjacent runs whose formatting (<w:rPr>) is
+identical, strips rsid attributes and proofErr markers, and consolidates the
+text elements — <w:t>, and <w:delText> for text inside a tracked deletion.
+
+Rendering is unchanged. The text you search is what Word draws, which is not
+always the bytes in the file: an element without xml:space="preserve" has its
+edge whitespace trimmed before it reaches the page, so `<w:t>Hello </w:t>`
+followed by `<w:t>world</w:t>` reads "Helloworld" and merges to exactly that.
+
+Runs in two different <w:ins>/<w:del> wrappers are never merged: that would
+rewrite tracked-change structure, collapsing separate revisions into one.
+
+Only word/document.xml is processed (not headers, footers, or footnotes).
+
+Usage:
+    python merge_runs.py unpacked/                  # after unzip, before editing
+    python merge_runs.py document.docx              # rewrite in place
+    python merge_runs.py document.docx -o out.docx
+"""
+
+
+import argparse
+import sys
+import tempfile
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+from office.helpers import XML_SPACE, rendered_text, rezip, safe_extract
+
+WORDML_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+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
+        run_names = _run_tag_names(root)
+
+        _remove_elements(root, "proofErr")
+
+        runs = _find_runs(root, run_names)
+        _strip_rsid_attrs(runs)
+
+        merge_count = 0
+        for container in {run.parentNode for run in runs}:
+            merge_count += _merge_runs_in(container, run_names)
+
+        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 _is_element(node, tag: str) -> bool:
+    name = node.localName or node.tagName
+    return name == tag or name.endswith(f":{tag}")
+
+
+def _run_tag_names(root) -> set[str]:
+    names = set()
+    for attr in root.attributes.values():
+        if attr.value == WORDML_NS:
+            if attr.name == "xmlns":
+                names.add("r")
+            elif attr.name.startswith("xmlns:"):
+                names.add(attr.name.split(":", 1)[1] + ":r")
+    return names or {"w:r", "r"}
+
+
+def _find_elements(root, tag: str) -> list:
+    results = []
+
+    def traverse(node):
+        if node.nodeType == node.ELEMENT_NODE:
+            if _is_element(node, tag):
+                results.append(node)
+            for child in node.childNodes:
+                traverse(child)
+
+    traverse(root)
+    return results
+
+
+def _find_runs(root, run_names: set[str]) -> list:
+    return [e for e in _find_elements(root, "r") if _is_run(e, run_names)]
+
+
+def _get_child(parent, tag: str):
+    return next(iter(_get_children(parent, tag)), None)
+
+
+def _get_children(parent, tag: str) -> list:
+    return [
+        child
+        for child in parent.childNodes
+        if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag)
+    ]
+
+
+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(XML_SPACE):
+            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_rsid_attrs(runs: list):
+    for run in runs:
+        for attr in list(run.attributes.values()):
+            if "rsid" in attr.name.lower():
+                run.removeAttribute(attr.name)
+
+
+
+
+def _merge_runs_in(container, run_names: set[str]) -> int:
+    merge_count = 0
+    run = _first_child_run(container, run_names)
+
+    while run:
+        while True:
+            next_elem = _next_element_sibling(run)
+            if next_elem and _is_run(next_elem, run_names) 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, run_names)
+
+    return merge_count
+
+
+def _first_child_run(container, run_names: set[str]):
+    for child in container.childNodes:
+        if child.nodeType == child.ELEMENT_NODE and _is_run(child, run_names):
+            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, run_names: set[str]):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            if _is_run(sibling, run_names):
+                return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _is_run(node, run_names: set[str]) -> bool:
+    return node.tagName in run_names
+
+
+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 _element_text(elem) -> str:
+    return "".join(
+        child.data
+        for child in elem.childNodes
+        if child.nodeType in (child.TEXT_NODE, child.CDATA_SECTION_NODE)
+    )
+
+
+def _has_preserve(elem) -> bool:
+    return elem.getAttribute("xml:space") == "preserve"
+
+
+def _rendered_text(elem) -> str:
+    return rendered_text(_element_text(elem), _has_preserve(elem))
+
+
+def _consolidate_text(run):
+    for tag in ("t", "delText"):
+        _consolidate_text_elements(run, tag)
+
+
+def _consolidate_text_elements(run, tag: str):
+    t_elements = _get_children(run, tag)
+
+    for i in range(len(t_elements) - 1, 0, -1):
+        curr, prev = t_elements[i], t_elements[i - 1]
+
+        if _is_adjacent(prev, curr):
+            merged = _rendered_text(prev) + _rendered_text(curr)
+            had_preserve = _has_preserve(prev) or _has_preserve(curr)
+
+            new_text = run.ownerDocument.createTextNode(merged)
+            for node in list(prev.childNodes):
+                if node.nodeType in (node.TEXT_NODE, node.CDATA_SECTION_NODE):
+                    prev.removeChild(node)
+                else:
+                    run.insertBefore(node, curr)
+            prev.appendChild(new_text)
+            for node in list(curr.childNodes):
+                if node.nodeType not in (node.TEXT_NODE, node.CDATA_SECTION_NODE):
+                    run.insertBefore(node, curr)
+
+            if merged != merged.strip(XML_SPACE) or had_preserve:
+                prev.setAttribute("xml:space", "preserve")
+            elif prev.hasAttribute("xml:space"):
+                prev.removeAttribute("xml:space")
+
+            run.removeChild(curr)
+
+
+
+
+def _merge_or_die(path: Path) -> str:
+    _, msg = merge_runs(str(path))
+    if msg.startswith("Error"):
+        print(msg, file=sys.stderr)
+        sys.exit(1)
+    return msg
+
+
+def main() -> None:
+    p = argparse.ArgumentParser(
+        description="Merge adjacent identically-formatted runs in a DOCX (directory or .docx file)."
+    )
+    p.add_argument("input", help="Unpacked DOCX directory OR a .docx/.dotx file")
+    p.add_argument(
+        "-o", "--output",
+        help="Output .docx path (only valid when input is a .docx; default: overwrite input)",
+    )
+    args = p.parse_args()
+
+    src = Path(args.input)
+
+    try:
+        if src.is_dir():
+            if args.output:
+                p.error("--output is only valid for .docx input; directory input is modified in place")
+            print(_merge_or_die(src))
+        elif src.is_file() and src.suffix.lower() in (".docx", ".dotx"):
+            out = Path(args.output) if args.output else src
+            with tempfile.TemporaryDirectory() as tmp:
+                tmp_path = Path(tmp)
+                with zipfile.ZipFile(src) as zf:
+                    safe_extract(zf, tmp_path)
+                msg = _merge_or_die(tmp_path)
+                rezip(tmp_path, out)
+            print(f"{msg}; wrote {out}")
+        else:
+            print(f"Error: {src} is neither a directory nor a .docx/.dotx file", file=sys.stderr)
+            sys.exit(1)
+    except (OSError, ValueError, zipfile.BadZipFile) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()