skills/xlsx/scripts/office/validators/base.py

"""
Base validator with common validation logic for document files.
"""

import re
from pathlib import Path

import defusedxml.minidom
import lxml.etree


class BaseSchemaValidator:
    IGNORED_VALIDATION_ERRORS = [
        "hyphenationZone",
        "purl.org/dc/terms",
    ]

    UNIQUE_ID_REQUIREMENTS = {
        "comment": ("id", "file"),
        "commentrangestart": ("id", "file"),
        "commentrangeend": ("id", "file"),
        "bookmarkstart": ("id", "file"),
        "bookmarkend": ("id", "file"),
        "sldid": ("id", "file"),
        "sldmasterid": ("id", "global"),
        "sldlayoutid": ("id", "global"),
        "cm": ("authorid", "file"),
        "sheet": ("sheetid", "file"),
        "definedname": ("id", "file"),
        "cxnsp": ("id", "file"),
        "sp": ("id", "file"),
        "pic": ("id", "file"),
        "grpsp": ("id", "file"),
    }

    EXCLUDED_ID_CONTAINERS = {
        "sectionlst",
    }

    ELEMENT_RELATIONSHIP_TYPES = {}

    SCHEMA_MAPPINGS = {
        "word": "ISO-IEC29500-4_2016/wml.xsd",
        "ppt": "ISO-IEC29500-4_2016/pml.xsd",
        "xl": "ISO-IEC29500-4_2016/sml.xsd",
        "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd",
        "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd",
        "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd",
        "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd",
        ".rels": "ecma/fouth-edition/opc-relationships.xsd",
        "people.xml": "microsoft/wml-2012.xsd",
        "commentsIds.xml": "microsoft/wml-cid-2016.xsd",
        "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd",
        "commentsExtended.xml": "microsoft/wml-2012.xsd",
        "chart": "ISO-IEC29500-4_2016/dml-chart.xsd",
        "theme": "ISO-IEC29500-4_2016/dml-main.xsd",
        "drawing": "ISO-IEC29500-4_2016/dml-main.xsd",
    }

    MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006"
    XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace"

    PACKAGE_RELATIONSHIPS_NAMESPACE = "http://schemas.openxmlformats.org/package/2006/relationships"
    OFFICE_RELATIONSHIPS_NAMESPACE = (
        "http://schemas.openxmlformats.org/officeDocument/2006/relationships"
    )
    CONTENT_TYPES_NAMESPACE = "http://schemas.openxmlformats.org/package/2006/content-types"

    MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"}

    OOXML_NAMESPACES = {
        "http://schemas.openxmlformats.org/officeDocument/2006/math",
        "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
        "http://schemas.openxmlformats.org/schemaLibrary/2006/main",
        "http://schemas.openxmlformats.org/drawingml/2006/main",
        "http://schemas.openxmlformats.org/drawingml/2006/chart",
        "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing",
        "http://schemas.openxmlformats.org/drawingml/2006/diagram",
        "http://schemas.openxmlformats.org/drawingml/2006/picture",
        "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing",
        "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing",
        "http://schemas.openxmlformats.org/wordprocessingml/2006/main",
        "http://schemas.openxmlformats.org/presentationml/2006/main",
        "http://schemas.openxmlformats.org/spreadsheetml/2006/main",
        "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes",
        "http://www.w3.org/XML/1998/namespace",
    }

    def __init__(self, unpacked_dir, original_file=None, verbose=False):
        self.unpacked_dir = Path(unpacked_dir).resolve()
        self.original_file = Path(original_file) if original_file else None
        self.verbose = verbose

        self.schemas_dir = Path(__file__).parent.parent / "schemas"

        patterns = ["*.xml", "*.rels"]
        self.xml_files = [f for pattern in patterns for f in self.unpacked_dir.rglob(pattern)]

        if not self.xml_files:
            print(f"Warning: No XML files found in {self.unpacked_dir}")

    def validate(self):
        raise NotImplementedError("Subclasses must implement the validate method")

    def repair(self) -> int:
        return self.repair_whitespace_preservation()

    def repair_whitespace_preservation(self) -> int:
        repairs = 0

        for xml_file in self.xml_files:
            try:
                content = xml_file.read_text(encoding="utf-8")
                dom = defusedxml.minidom.parseString(content)
                modified = False

                for elem in dom.getElementsByTagName("*"):
                    if elem.tagName.endswith(":t") and elem.firstChild:
                        text = elem.firstChild.nodeValue
                        if text and (text.startswith((" ", "\t")) or text.endswith((" ", "\t"))):
                            if elem.getAttribute("xml:space") != "preserve":
                                elem.setAttribute("xml:space", "preserve")
                                text_preview = (
                                    repr(text[:30]) + "..." if len(text) > 30 else repr(text)
                                )
                                print(
                                    f"  Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}"
                                )
                                repairs += 1
                                modified = True

                if modified:
                    xml_file.write_bytes(dom.toxml(encoding="UTF-8"))

            except Exception:
                pass

        return repairs

    def validate_xml(self):
        errors = []

        for xml_file in self.xml_files:
            try:
                lxml.etree.parse(str(xml_file))
            except lxml.etree.XMLSyntaxError as e:
                errors.append(
                    f"  {xml_file.relative_to(self.unpacked_dir)}: Line {e.lineno}: {e.msg}"
                )
            except Exception as e:
                errors.append(
                    f"  {xml_file.relative_to(self.unpacked_dir)}: Unexpected error: {str(e)}"
                )

        if errors:
            print(f"FAILED - Found {len(errors)} XML violations:")
            for error in errors:
                print(error)
            return False
        else:
            if self.verbose:
                print("PASSED - All XML files are well-formed")
            return True

    def validate_namespaces(self):
        errors = []

        for xml_file in self.xml_files:
            try:
                root = lxml.etree.parse(str(xml_file)).getroot()
                declared = set(root.nsmap.keys()) - {None}

                for attr_val in [v for k, v in root.attrib.items() if k.endswith("Ignorable")]:
                    undeclared = set(attr_val.split()) - declared
                    errors.extend(
                        f"  {xml_file.relative_to(self.unpacked_dir)}: "
                        f"Namespace '{ns}' in Ignorable but not declared"
                        for ns in undeclared
                    )
            except lxml.etree.XMLSyntaxError:
                continue

        if errors:
            print(f"FAILED - {len(errors)} namespace issues:")
            for error in errors:
                print(error)
            return False
        if self.verbose:
            print("PASSED - All namespace prefixes properly declared")
        return True

    def validate_unique_ids(self):
        errors = []
        global_ids = {}

        for xml_file in self.xml_files:
            try:
                root = lxml.etree.parse(str(xml_file)).getroot()
                file_ids = {}

                mc_elements = root.xpath(
                    ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE}
                )
                for elem in mc_elements:
                    elem.getparent().remove(elem)

                for elem in root.iter():
                    tag = elem.tag.split("}")[-1].lower() if "}" in elem.tag else elem.tag.lower()

                    if tag in self.UNIQUE_ID_REQUIREMENTS:
                        in_excluded_container = any(
                            ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS
                            for ancestor in elem.iterancestors()
                        )
                        if in_excluded_container:
                            continue

                        attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag]

                        id_value = None
                        for attr, value in elem.attrib.items():
                            attr_local = (
                                attr.split("}")[-1].lower() if "}" in attr else attr.lower()
                            )
                            if attr_local == attr_name:
                                id_value = value
                                break

                        if id_value is not None:
                            if scope == "global":
                                if id_value in global_ids:
                                    prev_file, prev_line, prev_tag = global_ids[id_value]
                                    errors.app
…