skills/pptx/scripts/office/validators/docx.py

"""
Validator for Word document XML files against XSD schemas.
"""

import random
import re
import tempfile
import zipfile

import defusedxml.minidom
import lxml.etree

from .base import BaseSchemaValidator


class DOCXSchemaValidator(BaseSchemaValidator):
    WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
    W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml"
    W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid"

    ELEMENT_RELATIONSHIP_TYPES = {}

    def validate(self):
        if not self.validate_xml():
            return False

        all_valid = True
        if not self.validate_namespaces():
            all_valid = False

        if not self.validate_unique_ids():
            all_valid = False

        if not self.validate_file_references():
            all_valid = False

        if not self.validate_content_types():
            all_valid = False

        if not self.validate_against_xsd():
            all_valid = False

        if not self.validate_whitespace_preservation():
            all_valid = False

        if not self.validate_deletions():
            all_valid = False

        if not self.validate_insertions():
            all_valid = False

        if not self.validate_all_relationship_ids():
            all_valid = False

        if not self.validate_id_constraints():
            all_valid = False

        if not self.validate_comment_markers():
            all_valid = False

        self.compare_paragraph_counts()

        return all_valid

    def validate_whitespace_preservation(self):
        errors = []

        for xml_file in self.xml_files:
            if xml_file.name != "document.xml":
                continue

            try:
                root = lxml.etree.parse(str(xml_file)).getroot()

                for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"):
                    if elem.text:
                        text = elem.text
                        if re.search(r"^[ \t\n\r]", text) or re.search(r"[ \t\n\r]$", text):
                            xml_space_attr = f"{{{self.XML_NAMESPACE}}}space"
                            if (
                                xml_space_attr not in elem.attrib
                                or elem.attrib[xml_space_attr] != "preserve"
                            ):
                                text_preview = (
                                    repr(text)[:50] + "..." if len(repr(text)) > 50 else repr(text)
                                )
                                errors.append(
                                    f"  {xml_file.relative_to(self.unpacked_dir)}: "
                                    f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}"
                                )

            except (lxml.etree.XMLSyntaxError, Exception) as e:
                errors.append(f"  {xml_file.relative_to(self.unpacked_dir)}: Error: {e}")

        if errors:
            print(f"FAILED - Found {len(errors)} whitespace preservation violations:")
            for error in errors:
                print(error)
            return False
        else:
            if self.verbose:
                print("PASSED - All whitespace is properly preserved")
            return True

    def validate_deletions(self):
        errors = []

        for xml_file in self.xml_files:
            if xml_file.name != "document.xml":
                continue

            try:
                root = lxml.etree.parse(str(xml_file)).getroot()
                namespaces = {"w": self.WORD_2006_NAMESPACE}

                for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces):
                    if t_elem.text:
                        text_preview = (
                            repr(t_elem.text)[:50] + "..."
                            if len(repr(t_elem.text)) > 50
                            else repr(t_elem.text)
                        )
                        errors.append(
                            f"  {xml_file.relative_to(self.unpacked_dir)}: "
                            f"Line {t_elem.sourceline}: <w:t> found within <w:del>: {text_preview}"
                        )

                for instr_elem in root.xpath(".//w:del//w:instrText", namespaces=namespaces):
                    text_preview = (
                        repr(instr_elem.text or "")[:50] + "..."
                        if len(repr(instr_elem.text or "")) > 50
                        else repr(instr_elem.text or "")
                    )
                    errors.append(
                        f"  {xml_file.relative_to(self.unpacked_dir)}: "
                        f"Line {instr_elem.sourceline}: <w:instrText> found within <w:del> (use <w:delInstrText>): {text_preview}"
                    )

            except (lxml.etree.XMLSyntaxError, Exception) as e:
                errors.append(f"  {xml_file.relative_to(self.unpacked_dir)}: Error: {e}")

        if errors:
            print(f"FAILED - Found {len(errors)} deletion validation violations:")
            for error in errors:
                print(error)
            return False
        else:
            if self.verbose:
                print("PASSED - No w:t elements found within w:del elements")
            return True

    def count_paragraphs_in_unpacked(self):
        count = 0

        for xml_file in self.xml_files:
            if xml_file.name != "document.xml":
                continue

            try:
                root = lxml.etree.parse(str(xml_file)).getroot()
                paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p")
                count = len(paragraphs)
            except Exception as e:
                print(f"Error counting paragraphs in unpacked documen
…