@kortix/sandbox 0.4.1

package/opencode/skills/KORTIX-docx/scripts/office/helpers/simplify_redlines.py

@@ -0,0 +1,197 @@
+"""Simplify tracked changes by merging adjacent w:ins or w:del elements.
+
+Merges adjacent <w:ins> elements from the same author into a single element.
+Same for <w:del> elements. This makes heavily-redlined documents easier to
+work with by reducing the number of tracked change wrappers.
+
+Rules:
+- Only merges w:ins with w:ins, w:del with w:del (same element type)
+- Only merges if same author (ignores timestamp differences)
+- Only merges if truly adjacent (only whitespace between them)
+"""
+
+import xml.etree.ElementTree as ET
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def simplify_redlines(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
+
+        merge_count = 0
+
+        containers = _find_elements(root, "p") + _find_elements(root, "tc")
+
+        for container in containers:
+            merge_count += _merge_tracked_changes_in(container, "ins")
+            merge_count += _merge_tracked_changes_in(container, "del")
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Simplified {merge_count} tracked changes"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+def _merge_tracked_changes_in(container, tag: str) -> int:
+    merge_count = 0
+
+    tracked = [
+        child
+        for child in container.childNodes
+        if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag)
+    ]
+
+    if len(tracked) < 2:
+        return 0
+
+    i = 0
+    while i < len(tracked) - 1:
+        curr = tracked[i]
+        next_elem = tracked[i + 1]
+
+        if _can_merge_tracked(curr, next_elem):
+            _merge_tracked_content(curr, next_elem)
+            container.removeChild(next_elem)
+            tracked.pop(i + 1)
+            merge_count += 1
+        else:
+            i += 1
+
+    return merge_count
+
+
+def _is_element(node, tag: str) -> bool:
+    name = node.localName or node.tagName
+    return name == tag or name.endswith(f":{tag}")
+
+
+def _get_author(elem) -> str:
+    author = elem.getAttribute("w:author")
+    if not author:
+        for attr in elem.attributes.values():
+            if attr.localName == "author" or attr.name.endswith(":author"):
+                return attr.value
+    return author
+
+
+def _can_merge_tracked(elem1, elem2) -> bool:
+    if _get_author(elem1) != _get_author(elem2):
+        return False
+
+    node = elem1.nextSibling
+    while node and node != elem2:
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+
+    return True
+
+
+def _merge_tracked_content(target, source):
+    while source.firstChild:
+        child = source.firstChild
+        source.removeChild(child)
+        target.appendChild(child)
+
+
+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_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]:
+    if not doc_xml_path.exists():
+        return {}
+
+    try:
+        tree = ET.parse(doc_xml_path)
+        root = tree.getroot()
+    except ET.ParseError:
+        return {}
+
+    namespaces = {"w": WORD_NS}
+    author_attr = f"{{{WORD_NS}}}author"
+
+    authors: dict[str, int] = {}
+    for tag in ["ins", "del"]:
+        for elem in root.findall(f".//w:{tag}", namespaces):
+            author = elem.get(author_attr)
+            if author:
+                authors[author] = authors.get(author, 0) + 1
+
+    return authors
+
+
+def _get_authors_from_docx(docx_path: Path) -> dict[str, int]:
+    try:
+        with zipfile.ZipFile(docx_path, "r") as zf:
+            if "word/document.xml" not in zf.namelist():
+                return {}
+            with zf.open("word/document.xml") as f:
+                tree = ET.parse(f)
+                root = tree.getroot()
+
+                namespaces = {"w": WORD_NS}
+                author_attr = f"{{{WORD_NS}}}author"
+
+                authors: dict[str, int] = {}
+                for tag in ["ins", "del"]:
+                    for elem in root.findall(f".//w:{tag}", namespaces):
+                        author = elem.get(author_attr)
+                        if author:
+                            authors[author] = authors.get(author, 0) + 1
+                return authors
+    except (zipfile.BadZipFile, ET.ParseError):
+        return {}
+
+
+def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str:
+    modified_xml = modified_dir / "word" / "document.xml"
+    modified_authors = get_tracked_change_authors(modified_xml)
+
+    if not modified_authors:
+        return default
+
+    original_authors = _get_authors_from_docx(original_docx)
+
+    new_changes: dict[str, int] = {}
+    for author, count in modified_authors.items():
+        original_count = original_authors.get(author, 0)
+        diff = count - original_count
+        if diff > 0:
+            new_changes[author] = diff
+
+    if not new_changes:
+        return default
+
+    if len(new_changes) == 1:
+        return next(iter(new_changes))
+
+    raise ValueError(
+        f"Multiple authors added new changes: {new_changes}. "
+        "Cannot infer which author to validate."
+    )

package/opencode/skills/KORTIX-docx/scripts/office/pack.py

@@ -0,0 +1,159 @@
+"""Pack a directory into a DOCX, PPTX, or XLSX file.
+
+Validates with auto-repair, condenses XML formatting, and creates the Office file.
+
+Usage:
+    python pack.py <input_directory> <output_file> [--original <file>] [--validate true|false]
+
+Examples:
+    python pack.py unpacked/ output.docx --original input.docx
+    python pack.py unpacked/ output.pptx --validate false
+"""
+
+import argparse
+import sys
+import shutil
+import tempfile
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
+
+def pack(
+    input_directory: str,
+    output_file: str,
+    original_file: str | None = None,
+    validate: bool = True,
+    infer_author_func=None,
+) -> tuple[None, str]:
+    input_dir = Path(input_directory)
+    output_path = Path(output_file)
+    suffix = output_path.suffix.lower()
+
+    if not input_dir.is_dir():
+        return None, f"Error: {input_dir} is not a directory"
+
+    if suffix not in {".docx", ".pptx", ".xlsx"}:
+        return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file"
+
+    if validate and original_file:
+        original_path = Path(original_file)
+        if original_path.exists():
+            success, output = _run_validation(
+                input_dir, original_path, suffix, infer_author_func
+            )
+            if output:
+                print(output)
+            if not success:
+                return None, f"Error: Validation failed for {input_dir}"
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_content_dir = Path(temp_dir) / "content"
+        shutil.copytree(input_dir, temp_content_dir)
+
+        for pattern in ["*.xml", "*.rels"]:
+            for xml_file in temp_content_dir.rglob(pattern):
+                _condense_xml(xml_file)
+
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf:
+            for f in temp_content_dir.rglob("*"):
+                if f.is_file():
+                    zf.write(f, f.relative_to(temp_content_dir))
+
+    return None, f"Successfully packed {input_dir} to {output_file}"
+
+
+def _run_validation(
+    unpacked_dir: Path,
+    original_file: Path,
+    suffix: str,
+    infer_author_func=None,
+) -> tuple[bool, str | None]:
+    output_lines = []
+    validators = []
+
+    if suffix == ".docx":
+        author = "Claude"
+        if infer_author_func:
+            try:
+                author = infer_author_func(unpacked_dir, original_file)
+            except ValueError as e:
+                print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr)
+
+        validators = [
+            DOCXSchemaValidator(unpacked_dir, original_file),
+            RedliningValidator(unpacked_dir, original_file, author=author),
+        ]
+    elif suffix == ".pptx":
+        validators = [PPTXSchemaValidator(unpacked_dir, original_file)]
+
+    if not validators:
+        return True, None
+
+    total_repairs = sum(v.repair() for v in validators)
+    if total_repairs:
+        output_lines.append(f"Auto-repaired {total_repairs} issue(s)")
+
+    success = all(v.validate() for v in validators)
+
+    if success:
+        output_lines.append("All validations PASSED!")
+
+    return success, "\n".join(output_lines) if output_lines else None
+
+
+def _condense_xml(xml_file: Path) -> None:
+    try:
+        with open(xml_file, encoding="utf-8") as f:
+            dom = defusedxml.minidom.parse(f)
+
+        for element in dom.getElementsByTagName("*"):
+            if element.tagName.endswith(":t"):
+                continue
+
+            for child in list(element.childNodes):
+                if (
+                    child.nodeType == child.TEXT_NODE
+                    and child.nodeValue
+                    and child.nodeValue.strip() == ""
+                ) or child.nodeType == child.COMMENT_NODE:
+                    element.removeChild(child)
+
+        xml_file.write_bytes(dom.toxml(encoding="UTF-8"))
+    except Exception as e:
+        print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr)
+        raise
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Pack a directory into a DOCX, PPTX, or XLSX file"
+    )
+    parser.add_argument("input_directory", help="Unpacked Office document directory")
+    parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)")
+    parser.add_argument(
+        "--original",
+        help="Original file for validation comparison",
+    )
+    parser.add_argument(
+        "--validate",
+        type=lambda x: x.lower() == "true",
+        default=True,
+        metavar="true|false",
+        help="Run validation with auto-repair (default: true)",
+    )
+    args = parser.parse_args()
+
+    _, message = pack(
+        args.input_directory,
+        args.output_file,
+        original_file=args.original,
+        validate=args.validate,
+    )
+    print(message)
+
+    if "Error" in message:
+        sys.exit(1)

package/opencode/skills/KORTIX-docx/scripts/office/soffice.py

@@ -0,0 +1,183 @@
+"""
+Helper for running LibreOffice (soffice) in environments where AF_UNIX
+sockets may be blocked (e.g., sandboxed VMs).  Detects the restriction
+at runtime and applies an LD_PRELOAD shim if needed.
+
+Usage:
+    from office.soffice import run_soffice, get_soffice_env
+
+    # Option 1 – run soffice directly
+    result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"])
+
+    # Option 2 – get env dict for your own subprocess calls
+    env = get_soffice_env()
+    subprocess.run(["soffice", ...], env=env)
+"""
+
+import os
+import socket
+import subprocess
+import tempfile
+from pathlib import Path
+
+
+def get_soffice_env() -> dict:
+    env = os.environ.copy()
+    env["SAL_USE_VCLPLUGIN"] = "svp"
+
+    if _needs_shim():
+        shim = _ensure_shim()
+        env["LD_PRELOAD"] = str(shim)
+
+    return env
+
+
+def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess:
+    env = get_soffice_env()
+    return subprocess.run(["soffice"] + args, env=env, **kwargs)
+
+
+
+_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so"
+
+
+def _needs_shim() -> bool:
+    try:
+        s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+        s.close()
+        return False
+    except OSError:
+        return True
+
+
+def _ensure_shim() -> Path:
+    if _SHIM_SO.exists():
+        return _SHIM_SO
+
+    src = Path(tempfile.gettempdir()) / "lo_socket_shim.c"
+    src.write_text(_SHIM_SOURCE)
+    subprocess.run(
+        ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"],
+        check=True,
+        capture_output=True,
+    )
+    src.unlink()
+    return _SHIM_SO
+
+
+
+_SHIM_SOURCE = r"""
+#define _GNU_SOURCE
+#include <dlfcn.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static int (*real_socket)(int, int, int);
+static int (*real_socketpair)(int, int, int, int[2]);
+static int (*real_listen)(int, int);
+static int (*real_accept)(int, struct sockaddr *, socklen_t *);
+static int (*real_close)(int);
+static int (*real_read)(int, void *, size_t);
+
+/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */
+static int is_shimmed[1024];
+static int peer_of[1024];
+static int wake_r[1024];            /* accept() blocks reading this */
+static int wake_w[1024];            /* close()  writes to this      */
+static int listener_fd = -1;        /* FD that received listen()    */
+
+__attribute__((constructor))
+static void init(void) {
+    real_socket     = dlsym(RTLD_NEXT, "socket");
+    real_socketpair = dlsym(RTLD_NEXT, "socketpair");
+    real_listen     = dlsym(RTLD_NEXT, "listen");
+    real_accept     = dlsym(RTLD_NEXT, "accept");
+    real_close      = dlsym(RTLD_NEXT, "close");
+    real_read       = dlsym(RTLD_NEXT, "read");
+    for (int i = 0; i < 1024; i++) {
+        peer_of[i] = -1;
+        wake_r[i]  = -1;
+        wake_w[i]  = -1;
+    }
+}
+
+/* ---- socket ---------------------------------------------------------- */
+int socket(int domain, int type, int protocol) {
+    if (domain == AF_UNIX) {
+        int fd = real_socket(domain, type, protocol);
+        if (fd >= 0) return fd;
+        /* socket(AF_UNIX) blocked – fall back to socketpair(). */
+        int sv[2];
+        if (real_socketpair(domain, type, protocol, sv) == 0) {
+            if (sv[0] >= 0 && sv[0] < 1024) {
+                is_shimmed[sv[0]] = 1;
+                peer_of[sv[0]]    = sv[1];
+                int wp[2];
+                if (pipe(wp) == 0) {
+                    wake_r[sv[0]] = wp[0];
+                    wake_w[sv[0]] = wp[1];
+                }
+            }
+            return sv[0];
+        }
+        errno = EPERM;
+        return -1;
+    }
+    return real_socket(domain, type, protocol);
+}
+
+/* ---- listen ---------------------------------------------------------- */
+int listen(int sockfd, int backlog) {
+    if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) {
+        listener_fd = sockfd;
+        return 0;
+    }
+    return real_listen(sockfd, backlog);
+}
+
+/* ---- accept ---------------------------------------------------------- */
+int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) {
+    if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) {
+        /* Block until close() writes to the wake pipe. */
+        if (wake_r[sockfd] >= 0) {
+            char buf;
+            real_read(wake_r[sockfd], &buf, 1);
+        }
+        errno = ECONNABORTED;
+        return -1;
+    }
+    return real_accept(sockfd, addr, addrlen);
+}
+
+/* ---- close ----------------------------------------------------------- */
+int close(int fd) {
+    if (fd >= 0 && fd < 1024 && is_shimmed[fd]) {
+        int was_listener = (fd == listener_fd);
+        is_shimmed[fd] = 0;
+
+        if (wake_w[fd] >= 0) {              /* unblock accept() */
+            char c = 0;
+            write(wake_w[fd], &c, 1);
+            real_close(wake_w[fd]);
+            wake_w[fd] = -1;
+        }
+        if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd]  = -1; }
+        if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; }
+
+        if (was_listener)
+            _exit(0);                        /* conversion done – exit */
+    }
+    return real_close(fd);
+}
+"""
+
+
+
+if __name__ == "__main__":
+    import sys
+    result = run_soffice(sys.argv[1:])
+    sys.exit(result.returncode)

package/opencode/skills/KORTIX-docx/scripts/office/unpack.py

@@ -0,0 +1,132 @@
+"""Unpack Office files (DOCX, PPTX, XLSX) for editing.
+
+Extracts the ZIP archive, pretty-prints XML files, and optionally:
+- Merges adjacent runs with identical formatting (DOCX only)
+- Simplifies adjacent tracked changes from same author (DOCX only)
+
+Usage:
+    python unpack.py <office_file> <output_dir> [options]
+
+Examples:
+    python unpack.py document.docx unpacked/
+    python unpack.py presentation.pptx unpacked/
+    python unpack.py document.docx unpacked/ --merge-runs false
+"""
+
+import argparse
+import sys
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+from helpers.merge_runs import merge_runs as do_merge_runs
+from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines
+
+SMART_QUOTE_REPLACEMENTS = {
+    "\u201c": "&#x201C;",  
+    "\u201d": "&#x201D;",  
+    "\u2018": "&#x2018;",  
+    "\u2019": "&#x2019;",  
+}
+
+
+def unpack(
+    input_file: str,
+    output_directory: str,
+    merge_runs: bool = True,
+    simplify_redlines: bool = True,
+) -> tuple[None, str]:
+    input_path = Path(input_file)
+    output_path = Path(output_directory)
+    suffix = input_path.suffix.lower()
+
+    if not input_path.exists():
+        return None, f"Error: {input_file} does not exist"
+
+    if suffix not in {".docx", ".pptx", ".xlsx"}:
+        return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file"
+
+    try:
+        output_path.mkdir(parents=True, exist_ok=True)
+
+        with zipfile.ZipFile(input_path, "r") as zf:
+            zf.extractall(output_path)
+
+        xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels"))
+        for xml_file in xml_files:
+            _pretty_print_xml(xml_file)
+
+        message = f"Unpacked {input_file} ({len(xml_files)} XML files)"
+
+        if suffix == ".docx":
+            if simplify_redlines:
+                simplify_count, _ = do_simplify_redlines(str(output_path))
+                message += f", simplified {simplify_count} tracked changes"
+
+            if merge_runs:
+                merge_count, _ = do_merge_runs(str(output_path))
+                message += f", merged {merge_count} runs"
+
+        for xml_file in xml_files:
+            _escape_smart_quotes(xml_file)
+
+        return None, message
+
+    except zipfile.BadZipFile:
+        return None, f"Error: {input_file} is not a valid Office file"
+    except Exception as e:
+        return None, f"Error unpacking: {e}"
+
+
+def _pretty_print_xml(xml_file: Path) -> None:
+    try:
+        content = xml_file.read_text(encoding="utf-8")
+        dom = defusedxml.minidom.parseString(content)
+        xml_file.write_bytes(dom.toprettyxml(indent="  ", encoding="utf-8"))
+    except Exception:
+        pass  
+
+
+def _escape_smart_quotes(xml_file: Path) -> None:
+    try:
+        content = xml_file.read_text(encoding="utf-8")
+        for char, entity in SMART_QUOTE_REPLACEMENTS.items():
+            content = content.replace(char, entity)
+        xml_file.write_text(content, encoding="utf-8")
+    except Exception:
+        pass
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Unpack an Office file (DOCX, PPTX, XLSX) for editing"
+    )
+    parser.add_argument("input_file", help="Office file to unpack")
+    parser.add_argument("output_directory", help="Output directory")
+    parser.add_argument(
+        "--merge-runs",
+        type=lambda x: x.lower() == "true",
+        default=True,
+        metavar="true|false",
+        help="Merge adjacent runs with identical formatting (DOCX only, default: true)",
+    )
+    parser.add_argument(
+        "--simplify-redlines",
+        type=lambda x: x.lower() == "true",
+        default=True,
+        metavar="true|false",
+        help="Merge adjacent tracked changes from same author (DOCX only, default: true)",
+    )
+    args = parser.parse_args()
+
+    _, message = unpack(
+        args.input_file,
+        args.output_directory,
+        merge_runs=args.merge_runs,
+        simplify_redlines=args.simplify_redlines,
+    )
+    print(message)
+
+    if "Error" in message:
+        sys.exit(1)