@xopcai/xopc 0.0.102 → 0.0.104

package/skills/documents/pptx/scripts/office/validators/pptx.py

@@ -1,275 +0,0 @@
-"""
-Validator for PowerPoint presentation XML files against XSD schemas.
-"""
-
-import re
-
-from .base import BaseSchemaValidator
-
-
-class PPTXSchemaValidator(BaseSchemaValidator):
-
-    PRESENTATIONML_NAMESPACE = (
-        "http://schemas.openxmlformats.org/presentationml/2006/main"
-    )
-
-    ELEMENT_RELATIONSHIP_TYPES = {
-        "sldid": "slide",
-        "sldmasterid": "slidemaster",
-        "notesmasterid": "notesmaster",
-        "sldlayoutid": "slidelayout",
-        "themeid": "theme",
-        "tablestyleid": "tablestyles",
-    }
-
-    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_uuid_ids():
-            all_valid = False
-
-        if not self.validate_file_references():
-            all_valid = False
-
-        if not self.validate_slide_layout_ids():
-            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_notes_slide_references():
-            all_valid = False
-
-        if not self.validate_all_relationship_ids():
-            all_valid = False
-
-        if not self.validate_no_duplicate_slide_layouts():
-            all_valid = False
-
-        return all_valid
-
-    def validate_uuid_ids(self):
-        import lxml.etree
-
-        errors = []
-        uuid_pattern = re.compile(
-            r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$"
-        )
-
-        for xml_file in self.xml_files:
-            try:
-                root = lxml.etree.parse(str(xml_file)).getroot()
-
-                for elem in root.iter():
-                    for attr, value in elem.attrib.items():
-                        attr_name = attr.split("}")[-1].lower()
-                        if attr_name == "id" or attr_name.endswith("id"):
-                            if self._looks_like_uuid(value):
-                                if not uuid_pattern.match(value):
-                                    errors.append(
-                                        f"  {xml_file.relative_to(self.unpacked_dir)}: "
-                                        f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters"
-                                    )
-
-            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)} UUID ID validation errors:")
-            for error in errors:
-                print(error)
-            return False
-        else:
-            if self.verbose:
-                print("PASSED - All UUID-like IDs contain valid hex values")
-            return True
-
-    def _looks_like_uuid(self, value):
-        clean_value = value.strip("{}()").replace("-", "")
-        return len(clean_value) == 32 and all(c.isalnum() for c in clean_value)
-
-    def validate_slide_layout_ids(self):
-        import lxml.etree
-
-        errors = []
-
-        slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml"))
-
-        if not slide_masters:
-            if self.verbose:
-                print("PASSED - No slide masters found")
-            return True
-
-        for slide_master in slide_masters:
-            try:
-                root = lxml.etree.parse(str(slide_master)).getroot()
-
-                rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels"
-
-                if not rels_file.exists():
-                    errors.append(
-                        f"  {slide_master.relative_to(self.unpacked_dir)}: "
-                        f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}"
-                    )
-                    continue
-
-                rels_root = lxml.etree.parse(str(rels_file)).getroot()
-
-                valid_layout_rids = set()
-                for rel in rels_root.findall(
-                    f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
-                ):
-                    rel_type = rel.get("Type", "")
-                    if "slideLayout" in rel_type:
-                        valid_layout_rids.add(rel.get("Id"))
-
-                for sld_layout_id in root.findall(
-                    f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId"
-                ):
-                    r_id = sld_layout_id.get(
-                        f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id"
-                    )
-                    layout_id = sld_layout_id.get("id")
-
-                    if r_id and r_id not in valid_layout_rids:
-                        errors.append(
-                            f"  {slide_master.relative_to(self.unpacked_dir)}: "
-                            f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' "
-                            f"references r:id='{r_id}' which is not found in slide layout relationships"
-                        )
-
-            except (lxml.etree.XMLSyntaxError, Exception) as e:
-                errors.append(
-                    f"  {slide_master.relative_to(self.unpacked_dir)}: Error: {e}"
-                )
-
-        if errors:
-            print(f"FAILED - Found {len(errors)} slide layout ID validation errors:")
-            for error in errors:
-                print(error)
-            print(
-                "Remove invalid references or add missing slide layouts to the relationships file."
-            )
-            return False
-        else:
-            if self.verbose:
-                print("PASSED - All slide layout IDs reference valid slide layouts")
-            return True
-
-    def validate_no_duplicate_slide_layouts(self):
-        import lxml.etree
-
-        errors = []
-        slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
-
-        for rels_file in slide_rels_files:
-            try:
-                root = lxml.etree.parse(str(rels_file)).getroot()
-
-                layout_rels = [
-                    rel
-                    for rel in root.findall(
-                        f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
-                    )
-                    if "slideLayout" in rel.get("Type", "")
-                ]
-
-                if len(layout_rels) > 1:
-                    errors.append(
-                        f"  {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references"
-                    )
-
-            except Exception as e:
-                errors.append(
-                    f"  {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
-                )
-
-        if errors:
-            print("FAILED - Found slides with duplicate slideLayout references:")
-            for error in errors:
-                print(error)
-            return False
-        else:
-            if self.verbose:
-                print("PASSED - All slides have exactly one slideLayout reference")
-            return True
-
-    def validate_notes_slide_references(self):
-        import lxml.etree
-
-        errors = []
-        notes_slide_references = {}  
-
-        slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels"))
-
-        if not slide_rels_files:
-            if self.verbose:
-                print("PASSED - No slide relationship files found")
-            return True
-
-        for rels_file in slide_rels_files:
-            try:
-                root = lxml.etree.parse(str(rels_file)).getroot()
-
-                for rel in root.findall(
-                    f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship"
-                ):
-                    rel_type = rel.get("Type", "")
-                    if "notesSlide" in rel_type:
-                        target = rel.get("Target", "")
-                        if target:
-                            normalized_target = target.replace("../", "")
-
-                            slide_name = rels_file.stem.replace(
-                                ".xml", ""
-                            )  
-
-                            if normalized_target not in notes_slide_references:
-                                notes_slide_references[normalized_target] = []
-                            notes_slide_references[normalized_target].append(
-                                (slide_name, rels_file)
-                            )
-
-            except (lxml.etree.XMLSyntaxError, Exception) as e:
-                errors.append(
-                    f"  {rels_file.relative_to(self.unpacked_dir)}: Error: {e}"
-                )
-
-        for target, references in notes_slide_references.items():
-            if len(references) > 1:
-                slide_names = [ref[0] for ref in references]
-                errors.append(
-                    f"  Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}"
-                )
-                for slide_name, rels_file in references:
-                    errors.append(f"    - {rels_file.relative_to(self.unpacked_dir)}")
-
-        if errors:
-            print(
-                f"FAILED - Found {len([e for e in errors if not e.startswith('    ')])} notes slide reference validation errors:"
-            )
-            for error in errors:
-                print(error)
-            print("Each slide may optionally have its own slide file.")
-            return False
-        else:
-            if self.verbose:
-                print("PASSED - All notes slide references are unique")
-            return True
-
-
-if __name__ == "__main__":
-    raise RuntimeError("This module should not be run directly.")

package/skills/documents/pptx/scripts/office/validators/redlining.py

@@ -1,247 +0,0 @@
-"""
-Validator for tracked changes in Word documents.
-"""
-
-import subprocess
-import tempfile
-import zipfile
-from pathlib import Path
-
-
-class RedliningValidator:
-
-    def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"):
-        self.unpacked_dir = Path(unpacked_dir)
-        self.original_docx = Path(original_docx)
-        self.verbose = verbose
-        self.author = author
-        self.namespaces = {
-            "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
-        }
-
-    def repair(self) -> int:
-        return 0
-
-    def validate(self):
-        modified_file = self.unpacked_dir / "word" / "document.xml"
-        if not modified_file.exists():
-            print(f"FAILED - Modified document.xml not found at {modified_file}")
-            return False
-
-        try:
-            import xml.etree.ElementTree as ET
-
-            tree = ET.parse(modified_file)
-            root = tree.getroot()
-
-            del_elements = root.findall(".//w:del", self.namespaces)
-            ins_elements = root.findall(".//w:ins", self.namespaces)
-
-            author_del_elements = [
-                elem
-                for elem in del_elements
-                if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
-            ]
-            author_ins_elements = [
-                elem
-                for elem in ins_elements
-                if elem.get(f"{{{self.namespaces['w']}}}author") == self.author
-            ]
-
-            if not author_del_elements and not author_ins_elements:
-                if self.verbose:
-                    print(f"PASSED - No tracked changes by {self.author} found.")
-                return True
-
-        except Exception:
-            pass
-
-        with tempfile.TemporaryDirectory() as temp_dir:
-            temp_path = Path(temp_dir)
-
-            try:
-                with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
-                    zip_ref.extractall(temp_path)
-            except Exception as e:
-                print(f"FAILED - Error unpacking original docx: {e}")
-                return False
-
-            original_file = temp_path / "word" / "document.xml"
-            if not original_file.exists():
-                print(
-                    f"FAILED - Original document.xml not found in {self.original_docx}"
-                )
-                return False
-
-            try:
-                import xml.etree.ElementTree as ET
-
-                modified_tree = ET.parse(modified_file)
-                modified_root = modified_tree.getroot()
-                original_tree = ET.parse(original_file)
-                original_root = original_tree.getroot()
-            except ET.ParseError as e:
-                print(f"FAILED - Error parsing XML files: {e}")
-                return False
-
-            self._remove_author_tracked_changes(original_root)
-            self._remove_author_tracked_changes(modified_root)
-
-            modified_text = self._extract_text_content(modified_root)
-            original_text = self._extract_text_content(original_root)
-
-            if modified_text != original_text:
-                error_message = self._generate_detailed_diff(
-                    original_text, modified_text
-                )
-                print(error_message)
-                return False
-
-            if self.verbose:
-                print(f"PASSED - All changes by {self.author} are properly tracked")
-            return True
-
-    def _generate_detailed_diff(self, original_text, modified_text):
-        error_parts = [
-            f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes",
-            "",
-            "Likely causes:",
-            "  1. Modified text inside another author's <w:ins> or <w:del> tags",
-            "  2. Made edits without proper tracked changes",
-            "  3. Didn't nest <w:del> inside <w:ins> when deleting another's insertion",
-            "",
-            "For pre-redlined documents, use correct patterns:",
-            "  - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
-            "  - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
-            "",
-        ]
-
-        git_diff = self._get_git_word_diff(original_text, modified_text)
-        if git_diff:
-            error_parts.extend(["Differences:", "============", git_diff])
-        else:
-            error_parts.append("Unable to generate word diff (git not available)")
-
-        return "\n".join(error_parts)
-
-    def _get_git_word_diff(self, original_text, modified_text):
-        try:
-            with tempfile.TemporaryDirectory() as temp_dir:
-                temp_path = Path(temp_dir)
-
-                original_file = temp_path / "original.txt"
-                modified_file = temp_path / "modified.txt"
-
-                original_file.write_text(original_text, encoding="utf-8")
-                modified_file.write_text(modified_text, encoding="utf-8")
-
-                result = subprocess.run(
-                    [
-                        "git",
-                        "diff",
-                        "--word-diff=plain",
-                        "--word-diff-regex=.",  
-                        "-U0",  
-                        "--no-index",
-                        str(original_file),
-                        str(modified_file),
-                    ],
-                    capture_output=True,
-                    text=True,
-                )
-
-                if result.stdout.strip():
-                    lines = result.stdout.split("\n")
-                    content_lines = []
-                    in_content = False
-                    for line in lines:
-                        if line.startswith("@@"):
-                            in_content = True
-                            continue
-                        if in_content and line.strip():
-                            content_lines.append(line)
-
-                    if content_lines:
-                        return "\n".join(content_lines)
-
-                result = subprocess.run(
-                    [
-                        "git",
-                        "diff",
-                        "--word-diff=plain",
-                        "-U0",  
-                        "--no-index",
-                        str(original_file),
-                        str(modified_file),
-                    ],
-                    capture_output=True,
-                    text=True,
-                )
-
-                if result.stdout.strip():
-                    lines = result.stdout.split("\n")
-                    content_lines = []
-                    in_content = False
-                    for line in lines:
-                        if line.startswith("@@"):
-                            in_content = True
-                            continue
-                        if in_content and line.strip():
-                            content_lines.append(line)
-                    return "\n".join(content_lines)
-
-        except (subprocess.CalledProcessError, FileNotFoundError, Exception):
-            pass
-
-        return None
-
-    def _remove_author_tracked_changes(self, root):
-        ins_tag = f"{{{self.namespaces['w']}}}ins"
-        del_tag = f"{{{self.namespaces['w']}}}del"
-        author_attr = f"{{{self.namespaces['w']}}}author"
-
-        for parent in root.iter():
-            to_remove = []
-            for child in parent:
-                if child.tag == ins_tag and child.get(author_attr) == self.author:
-                    to_remove.append(child)
-            for elem in to_remove:
-                parent.remove(elem)
-
-        deltext_tag = f"{{{self.namespaces['w']}}}delText"
-        t_tag = f"{{{self.namespaces['w']}}}t"
-
-        for parent in root.iter():
-            to_process = []
-            for child in parent:
-                if child.tag == del_tag and child.get(author_attr) == self.author:
-                    to_process.append((child, list(parent).index(child)))
-
-            for del_elem, del_index in reversed(to_process):
-                for elem in del_elem.iter():
-                    if elem.tag == deltext_tag:
-                        elem.tag = t_tag
-
-                for child in reversed(list(del_elem)):
-                    parent.insert(del_index, child)
-                parent.remove(del_elem)
-
-    def _extract_text_content(self, root):
-        p_tag = f"{{{self.namespaces['w']}}}p"
-        t_tag = f"{{{self.namespaces['w']}}}t"
-
-        paragraphs = []
-        for p_elem in root.findall(f".//{p_tag}"):
-            text_parts = []
-            for t_elem in p_elem.findall(f".//{t_tag}"):
-                if t_elem.text:
-                    text_parts.append(t_elem.text)
-            paragraph_text = "".join(text_parts)
-            if paragraph_text:
-                paragraphs.append(paragraph_text)
-
-        return "\n".join(paragraphs)
-
-
-if __name__ == "__main__":
-    raise RuntimeError("This module should not be run directly.")