@preapexis/piexis 0.1.2

package/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd

@@ -0,0 +1,20 @@
+ <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:s="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" xmlns:w16="http://schemas.microsoft.com/office/word/2018/wordml" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2018/wordml/cex" targetNamespace="http://schemas.microsoft.com/office/word/2018/wordml/cex">
+   <xsd:import id="w16" namespace="http://schemas.microsoft.com/office/word/2018/wordml" schemaLocation="wml-2018.xsd"/>
+   <xsd:import id="w" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
+   <xsd:import id="s" namespace="http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes" schemaLocation="../ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd"/>
+   <xsd:complexType name="CT_CommentsExtensible">
+     <xsd:sequence>
+       <xsd:element name="commentExtensible" type="CT_CommentExtensible" minOccurs="0" maxOccurs="unbounded"/>
+       <xsd:element name="extLst" type="w16:CT_ExtensionList" minOccurs="0" maxOccurs="1"/>
+     </xsd:sequence>
+   </xsd:complexType>
+   <xsd:complexType name="CT_CommentExtensible">
+     <xsd:sequence>
+       <xsd:element name="extLst" type="w16:CT_ExtensionList" minOccurs="0" maxOccurs="1"/>
+     </xsd:sequence>
+     <xsd:attribute name="durableId" type="w:ST_LongHexNumber" use="required"/>
+     <xsd:attribute name="dateUtc" type="w:ST_DateTime" use="optional"/>
+     <xsd:attribute name="intelligentPlaceholder" type="s:ST_OnOff" use="optional"/>
+   </xsd:complexType>
+   <xsd:element name="commentsExtensible" type="CT_CommentsExtensible"/>
+ </xsd:schema>

package/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd

@@ -0,0 +1,13 @@
+ <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2016/wordml/cid" targetNamespace="http://schemas.microsoft.com/office/word/2016/wordml/cid">
+   <xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
+   <xsd:complexType name="CT_CommentsIds">
+     <xsd:sequence>
+       <xsd:element name="commentId" type="CT_CommentId" minOccurs="0" maxOccurs="unbounded"/>
+     </xsd:sequence>
+   </xsd:complexType>
+   <xsd:complexType name="CT_CommentId">
+     <xsd:attribute name="paraId" type="w12:ST_LongHexNumber" use="required"/>
+     <xsd:attribute name="durableId" type="w12:ST_LongHexNumber" use="required"/>
+   </xsd:complexType>
+   <xsd:element name="commentsIds" type="CT_CommentsIds"/>
+ </xsd:schema>

package/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd

@@ -0,0 +1,4 @@
+ <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash" targetNamespace="http://schemas.microsoft.com/office/word/2020/wordml/sdtdatahash">
+   <xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
+   <xsd:attribute name="storeItemChecksum" type="w12:ST_String"/>
+ </xsd:schema>

package/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd

@@ -0,0 +1,8 @@
+ <xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:w12="http://schemas.openxmlformats.org/wordprocessingml/2006/main" elementFormDefault="qualified" attributeFormDefault="qualified" blockDefault="#all" xmlns="http://schemas.microsoft.com/office/word/2015/wordml/symex" targetNamespace="http://schemas.microsoft.com/office/word/2015/wordml/symex">
+   <xsd:import id="w12" namespace="http://schemas.openxmlformats.org/wordprocessingml/2006/main" schemaLocation="../ISO-IEC29500-4_2016/wml.xsd"/>
+   <xsd:complexType name="CT_SymEx">
+     <xsd:attribute name="font" type="w12:ST_String"/>
+     <xsd:attribute name="char" type="w12:ST_LongHexNumber"/>
+   </xsd:complexType>
+   <xsd:element name="symEx" type="CT_SymEx"/>
+ </xsd:schema>

package/skills/docx/scripts/office/soffice.py

@@ -0,0 +1,192 @@
+"""
+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
+
+    result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"])
+
+Call soffice through run_soffice, not through subprocess with get_soffice_env():
+the env dict carries the shim but names no user profile, and a non-root sandbox
+cannot bootstrap the default one -- soffice aborts with "User installation could
+not be completed" and converts nothing. get_soffice_env() stays public for the
+callers that build their own argv (they must pass -env:UserInstallation too).
+"""
+
+import contextlib
+import os
+import socket
+import subprocess
+import tempfile
+from collections.abc import Iterable
+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: Iterable[str], **kwargs) -> subprocess.CompletedProcess:
+    args = list(args)
+    with contextlib.ExitStack() as stack:
+        if not any(str(a).startswith("-env:UserInstallation") for a in args):
+            profile = stack.enter_context(
+                tempfile.TemporaryDirectory(prefix="lo_profile_", ignore_cleanup_errors=True)
+            )
+            args = [f"-env:UserInstallation={Path(profile).as_uri()}"] + args
+        return subprocess.run(["soffice"] + args, env=get_soffice_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/skills/docx/scripts/office/validate.py

@@ -0,0 +1,173 @@
+"""
+Command line tool to validate Office document XML files against XSD schemas and tracked changes.
+
+Usage:
+    python validate.py <path> [--original <original_file>] [--auto-repair] [--author NAME]
+
+The first argument can be either:
+- An unpacked directory containing the Office document XML files
+- A packed Office file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx template) which will be unpacked to a temp directory
+
+Auto-repair fixes:
+- paraId/durableId values that exceed OOXML limits
+- Missing xml:space="preserve" on w:t elements with whitespace
+"""
+
+import argparse
+import sys
+import tempfile
+import zipfile
+from pathlib import Path
+
+import defusedxml.ElementTree as ET
+from defusedxml.common import DefusedXmlException
+
+from helpers import OOXML_FAMILY, rezip, safe_extract
+from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
+
+WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def _fail(message: str):
+    print(f"Error: {message}", file=sys.stderr)
+    sys.exit(2)
+
+
+def _has_tracked_changes(unpacked_dir: Path) -> bool:
+    document = unpacked_dir / "word" / "document.xml"
+    if not document.is_file():
+        return False
+    try:
+        root = ET.parse(document).getroot()
+    except (ET.ParseError, DefusedXmlException):
+        return False  
+    tracked = {f"{{{WORD_NS}}}ins", f"{{{WORD_NS}}}del"}
+    return any(elem.tag in tracked for elem in root.iter())
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Validate Office document XML files")
+    parser.add_argument(
+        "path",
+        help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx)",
+    )
+    parser.add_argument(
+        "--original",
+        required=False,
+        default=None,
+        help="Path to original file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx). If omitted, all XSD errors are reported and redlining validation is skipped.",
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        help="Enable verbose output",
+    )
+    parser.add_argument(
+        "--auto-repair",
+        action="store_true",
+        help="Automatically repair common issues (hex IDs, whitespace preservation). "
+        "Modifies the input in place: repairs to a packed file are written back to it.",
+    )
+    parser.add_argument(
+        "--author",
+        default=None,
+        help="The name you are redlining under. Passing it turns on the "
+        "tracked-change check: any text differing from --original without a "
+        "<w:ins>/<w:del> recording it is reported. Untracked edits carry no "
+        "author, so the check covers them whoever made them — the name marks "
+        "the run as redlining work and is not used to filter. Requires "
+        "--original; docx only.",
+    )
+    args = parser.parse_args()
+
+    if args.author is not None and not args.original:
+        _fail("--author requires --original")
+
+    path = Path(args.path)
+    if not path.exists():
+        _fail(f"{path} does not exist")
+
+    original_file = None
+    if args.original:
+        original_file = Path(args.original)
+        if not original_file.is_file():
+            _fail(f"{original_file} is not a file")
+        if original_file.suffix.lower() not in OOXML_FAMILY:
+            _fail(f"{original_file} must be one of: {', '.join(sorted(OOXML_FAMILY))}")
+
+    family = OOXML_FAMILY.get((original_file or path).suffix.lower())
+    if family is None:
+        _fail(
+            f"Cannot determine file type from {path}. Use --original or provide one of: {', '.join(sorted(OOXML_FAMILY))}."
+        )
+
+    if args.author is not None and family != "docx":
+        _fail(f"--author only applies to docx files, not {family}")
+
+    packed_file = None
+    temp_dir_ctx = None
+    if path.is_file() and path.suffix.lower() in OOXML_FAMILY:
+        packed_file = path
+        temp_dir_ctx = tempfile.TemporaryDirectory()
+        unpacked_dir = Path(temp_dir_ctx.name)
+        try:
+            with zipfile.ZipFile(path, "r") as zf:
+                safe_extract(zf, unpacked_dir)
+        except (zipfile.BadZipFile, ValueError, OSError) as e:
+            _fail(f"cannot unpack {path}: {e}")
+    else:
+        if not path.is_dir():
+            _fail(f"{path} is not a directory or Office file")
+        unpacked_dir = path
+
+    match family:
+        case "docx":
+            validators = [
+                DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
+            ]
+            if args.author is not None:
+                validators.append(
+                    RedliningValidator(unpacked_dir, original_file, verbose=args.verbose)  
+                )
+            elif original_file and _has_tracked_changes(unpacked_dir):
+                print(
+                    "Note: this document has tracked changes; they were not "
+                    "checked against the original (pass --author to check)."
+                )
+        case "pptx":
+            validators = [
+                PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
+            ]
+        case "xlsx":
+            exts = ", ".join(k for k, v in sorted(OOXML_FAMILY.items()) if v == "xlsx")
+            print(
+                f"No XSD schema validation is performed for xlsx-family files ({exts}). "
+                "For formula-error checking, use scripts/recalc.py instead."
+            )
+            sys.exit(0)
+        case _:
+            print(f"Error: Validation not supported for file type {family}")
+            sys.exit(1)
+
+    if args.auto_repair:
+        total_repairs = sum(v.repair() for v in validators)
+        if total_repairs:
+            print(f"Auto-repaired {total_repairs} issue(s)")
+            if packed_file is not None:
+                rezip(unpacked_dir, packed_file)
+                print(f"Wrote repaired file to {packed_file}")
+
+    success = all([v.validate() for v in validators])
+
+    if temp_dir_ctx is not None:
+        temp_dir_ctx.cleanup()
+
+    if success:
+        print("All validations PASSED!")
+
+    sys.exit(0 if success else 1)
+
+
+if __name__ == "__main__":
+    main()

package/skills/docx/scripts/office/validators/__init__.py

@@ -0,0 +1,15 @@
+"""
+Validation modules for Word document processing.
+"""
+
+from .base import BaseSchemaValidator
+from .docx import DOCXSchemaValidator
+from .pptx import PPTXSchemaValidator
+from .redlining import RedliningValidator
+
+__all__ = [
+    "BaseSchemaValidator",
+    "DOCXSchemaValidator",
+    "PPTXSchemaValidator",
+    "RedliningValidator",
+]