@preapexis/piexis 0.1.2

package/skills/pptx/scripts/clean.py

@@ -0,0 +1,309 @@
+"""Remove unreferenced files from an unpacked PPTX directory.
+
+Usage: python clean.py <unpacked_dir>
+
+Example:
+    python clean.py unpacked/
+
+This script removes:
+- Orphaned slides (not in sldIdLst) and their relationships
+- [trash] directory (unreferenced files)
+- Orphaned .rels files for deleted resources
+- Unreferenced media, embeddings, charts, diagrams, drawings, ink files
+- Unreferenced theme files
+- Unreferenced notes slides
+- Content-Type overrides for deleted files
+"""
+
+import posixpath
+import re
+import sys
+from pathlib import Path
+
+import defusedxml.minidom
+
+from office.helpers import SLIDE_REL_TYPE, opc_target, rels_source_part
+
+
+def _slide_rids(pres_rels_path: Path, unpacked_dir: Path) -> dict[str, str]:
+    source_part = rels_source_part(pres_rels_path, unpacked_dir)
+    rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+
+    rids: dict[str, str] = {}
+    for rel in rels_dom.getElementsByTagName("Relationship"):
+        if rel.getAttribute("Type") != SLIDE_REL_TYPE:
+            continue
+        part = opc_target(
+            rel.getAttribute("Target"), source_part, rel.getAttribute("TargetMode")
+        )
+        if part is not None:
+            rids[rel.getAttribute("Id")] = part
+    return rids
+
+
+def get_slides_in_sldidlst(unpacked_dir: Path) -> set[str]:
+    pres_path = unpacked_dir / "ppt" / "presentation.xml"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not pres_path.exists() or not pres_rels_path.exists():
+        return set()
+
+    rid_to_slide = _slide_rids(pres_rels_path, unpacked_dir)
+
+    pres_content = pres_path.read_text(encoding="utf-8")
+    referenced_rids = set(re.findall(r'<p:sldId[^>]*r:id="([^"]+)"', pres_content))
+
+    return {
+        posixpath.basename(rid_to_slide[rid])
+        for rid in referenced_rids
+        if rid in rid_to_slide
+    }
+
+
+class RefusedToClean(Exception):
+    """The package does not look the way a readable package should."""
+
+
+def remove_orphaned_slides(unpacked_dir: Path) -> list[str]:
+    slides_dir = unpacked_dir / "ppt" / "slides"
+    slides_rels_dir = slides_dir / "_rels"
+    pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels"
+
+    if not slides_dir.exists():
+        return []
+
+    referenced_slides = get_slides_in_sldidlst(unpacked_dir)
+    on_disk = sorted(slides_dir.glob("slide*.xml"))
+
+    if on_disk and not any(s.name in referenced_slides for s in on_disk):
+        listed = re.findall(
+            r'<p:sldId[^>]*r:id="([^"]+)"',
+            (unpacked_dir / "ppt" / "presentation.xml").read_text(encoding="utf-8")
+            if (unpacked_dir / "ppt" / "presentation.xml").exists()
+            else "",
+        )
+        if listed:
+            raise RefusedToClean(
+                f"<p:sldIdLst> lists {len(listed)} slide(s) and none of the "
+                f"{len(on_disk)} slide(s) on disk match any of them. Refusing to "
+                f"delete them all — this is a parse failure, not an empty deck."
+            )
+
+    removed = []
+
+    for slide_file in on_disk:
+        if slide_file.name not in referenced_slides:
+            rel_path = slide_file.relative_to(unpacked_dir)
+            slide_file.unlink()
+            removed.append(str(rel_path))
+
+            rels_file = slides_rels_dir / f"{slide_file.name}.rels"
+            if rels_file.exists():
+                rels_file.unlink()
+                removed.append(str(rels_file.relative_to(unpacked_dir)))
+
+    if removed and pres_rels_path.exists():
+        rels_dom = defusedxml.minidom.parse(str(pres_rels_path))
+        source_part = rels_source_part(pres_rels_path, unpacked_dir)
+        changed = False
+
+        for rel in list(rels_dom.getElementsByTagName("Relationship")):
+            if rel.getAttribute("Type") != SLIDE_REL_TYPE:
+                continue
+            part = opc_target(
+                rel.getAttribute("Target"), source_part, rel.getAttribute("TargetMode")
+            )
+            if part is None:
+                continue
+            if posixpath.basename(part) not in referenced_slides:
+                if rel.parentNode:
+                    rel.parentNode.removeChild(rel)
+                    changed = True
+
+        if changed:
+            with open(pres_rels_path, "wb") as f:
+                f.write(rels_dom.toxml(encoding="utf-8"))
+
+    return removed
+
+
+def remove_trash_directory(unpacked_dir: Path) -> list[str]:
+    trash_dir = unpacked_dir / "[trash]"
+    removed = []
+
+    if trash_dir.exists() and trash_dir.is_dir():
+        for file_path in trash_dir.iterdir():
+            if file_path.is_file():
+                rel_path = file_path.relative_to(unpacked_dir)
+                removed.append(str(rel_path))
+                file_path.unlink()
+        trash_dir.rmdir()
+
+    return removed
+
+
+def _referenced_by(rels_files, unpacked_dir: Path) -> set:
+    referenced = set()
+
+    for rels_file in rels_files:
+        source_part = rels_source_part(rels_file, unpacked_dir)
+        dom = defusedxml.minidom.parse(str(rels_file))
+        for rel in dom.getElementsByTagName("Relationship"):
+            part = opc_target(
+                rel.getAttribute("Target"), source_part, rel.getAttribute("TargetMode")
+            )
+            if part is not None:
+                referenced.add(Path(part))
+
+    return referenced
+
+
+def remove_orphaned_rels_files(unpacked_dir: Path) -> list[str]:
+    resource_dirs = ["charts", "diagrams", "drawings"]
+    removed = []
+
+    for dir_name in resource_dirs:
+        rels_dir = unpacked_dir / "ppt" / dir_name / "_rels"
+        if not rels_dir.exists():
+            continue
+
+        for rels_file in rels_dir.glob("*.rels"):
+            resource_file = rels_dir.parent / rels_file.name.replace(".rels", "")
+            if not resource_file.exists():
+                rels_file.unlink()
+                removed.append(str(rels_file.relative_to(unpacked_dir)))
+
+    return removed
+
+
+def get_referenced_files(unpacked_dir: Path) -> set:
+    return _referenced_by(sorted(unpacked_dir.rglob("*.rels")), unpacked_dir)
+
+
+def remove_orphaned_files(unpacked_dir: Path, referenced: set) -> list[str]:
+    resource_dirs = ["media", "embeddings", "charts", "diagrams", "tags", "drawings", "ink"]
+    removed = []
+
+    for dir_name in resource_dirs:
+        dir_path = unpacked_dir / "ppt" / dir_name
+        if not dir_path.exists():
+            continue
+
+        for file_path in dir_path.glob("*"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+    theme_dir = unpacked_dir / "ppt" / "theme"
+    if theme_dir.exists():
+        for file_path in theme_dir.glob("theme*.xml"):
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+                theme_rels = theme_dir / "_rels" / f"{file_path.name}.rels"
+                if theme_rels.exists():
+                    theme_rels.unlink()
+                    removed.append(str(theme_rels.relative_to(unpacked_dir)))
+
+    notes_dir = unpacked_dir / "ppt" / "notesSlides"
+    if notes_dir.exists():
+        for file_path in notes_dir.glob("*.xml"):
+            if not file_path.is_file():
+                continue
+            rel_path = file_path.relative_to(unpacked_dir)
+            if rel_path not in referenced:
+                file_path.unlink()
+                removed.append(str(rel_path))
+
+        notes_rels_dir = notes_dir / "_rels"
+        if notes_rels_dir.exists():
+            for file_path in notes_rels_dir.glob("*.rels"):
+                notes_file = notes_dir / file_path.name.replace(".rels", "")
+                if not notes_file.exists():
+                    file_path.unlink()
+                    removed.append(str(file_path.relative_to(unpacked_dir)))
+
+    return removed
+
+
+def update_content_types(unpacked_dir: Path, removed_files: list[str]) -> None:
+    ct_path = unpacked_dir / "[Content_Types].xml"
+    if not ct_path.exists():
+        return
+
+    dom = defusedxml.minidom.parse(str(ct_path))
+    changed = False
+
+    for override in list(dom.getElementsByTagName("Override")):
+        part_name = override.getAttribute("PartName").lstrip("/")
+        if part_name in removed_files:
+            if override.parentNode:
+                override.parentNode.removeChild(override)
+                changed = True
+
+    if changed:
+        with open(ct_path, "wb") as f:
+            f.write(dom.toxml(encoding="utf-8"))
+
+
+def clean_unused_files(unpacked_dir: Path) -> list[str]:
+    all_removed = []
+
+    if list(unpacked_dir.rglob("*.rels")) and not get_referenced_files(unpacked_dir):
+        raise RefusedToClean(
+            "no relationship in this package names a part we can resolve. "
+            "Refusing to treat every file as unreferenced."
+        )
+
+    slides_removed = remove_orphaned_slides(unpacked_dir)
+    all_removed.extend(slides_removed)
+
+    trash_removed = remove_trash_directory(unpacked_dir)
+    all_removed.extend(trash_removed)
+
+    while True:
+        removed_rels = remove_orphaned_rels_files(unpacked_dir)
+        referenced = get_referenced_files(unpacked_dir)
+        removed_files = remove_orphaned_files(unpacked_dir, referenced)
+
+        total_removed = removed_rels + removed_files
+        if not total_removed:
+            break
+
+        all_removed.extend(total_removed)
+
+    if all_removed:
+        update_content_types(unpacked_dir, all_removed)
+
+    return all_removed
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python clean.py <unpacked_dir>", file=sys.stderr)
+        print("Example: python clean.py unpacked/", file=sys.stderr)
+        sys.exit(1)
+
+    unpacked_dir = Path(sys.argv[1])
+
+    if not unpacked_dir.exists():
+        print(f"Error: {unpacked_dir} not found", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        removed = clean_unused_files(unpacked_dir)
+    except (RefusedToClean, ValueError) as e:
+        print(f"Error: {e}", file=sys.stderr)
+        print("Nothing was deleted.", file=sys.stderr)
+        sys.exit(1)
+
+    if removed:
+        print(f"Removed {len(removed)} unreferenced files:")
+        for f in removed:
+            print(f"  {f}")
+    else:
+        print("No unreferenced files found")

package/skills/pptx/scripts/office/helpers/__init__.py

@@ -0,0 +1,111 @@
+import os
+import posixpath
+import re
+import stat
+import tempfile
+import urllib.parse
+import zipfile
+from pathlib import Path
+
+OOXML_FAMILY = {
+    ".docx": "docx",
+    ".dotx": "docx",
+    ".pptx": "pptx",
+    ".potx": "pptx",
+    ".xlsx": "xlsx",
+    ".xltx": "xlsx",
+}
+
+_SCHEME_RE = re.compile(r"^[A-Za-z][A-Za-z0-9+.\-]*:")
+
+SLIDE_REL_TYPE = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/slide"
+
+
+def opc_target(target: str, source_part: str, target_mode: str = "") -> str | None:
+    if not target:
+        return None
+    if target_mode.lower() == "external":
+        return None
+    if _SCHEME_RE.match(target):
+        return None
+
+    target = urllib.parse.unquote(target)
+
+    if "\\" in target:
+        raise ValueError(f"relationship target is not a POSIX part name: {target!r}")
+
+    if target.startswith("/"):
+        joined = target.lstrip("/")
+    else:
+        joined = posixpath.join(posixpath.dirname(source_part), target)
+
+    parts: list[str] = []
+    for segment in posixpath.normpath(joined).split("/"):
+        if segment in ("", "."):
+            continue
+        if segment == "..":
+            if not parts:
+                raise ValueError(f"relationship target escapes the package: {target!r}")
+            parts.pop()
+        else:
+            parts.append(segment)
+
+    if not parts:
+        raise ValueError(f"relationship target resolves to nothing: {target!r}")
+    return "/".join(parts)
+
+
+def rels_source_part(rels_file: Path, unpacked_dir: Path) -> str:
+    owner_dir = rels_file.parent.parent.relative_to(unpacked_dir)
+    return posixpath.join(owner_dir.as_posix(), rels_file.name[: -len(".rels")]).lstrip("./")
+
+
+def part_text(data: bytes) -> str:
+    return data.decode("utf-8", "surrogateescape")
+
+
+XML_SPACE = " \t\r\n"
+
+
+def rendered_text(text: str, preserve: bool) -> str:
+    return text if preserve else text.strip(XML_SPACE)
+
+
+def safe_extract(zf: zipfile.ZipFile, dest: Path) -> None:
+    dest = dest.resolve()
+    for m in zf.infolist():
+        if stat.S_ISLNK(m.external_attr >> 16):
+            raise ValueError(f"symlink archive entry not allowed: {m.filename!r}")
+        target = (dest / m.filename).resolve()
+        if not target.is_relative_to(dest):
+            raise ValueError(f"unsafe archive entry: {m.filename!r}")
+        zf.extract(m, dest)
+
+
+def rezip(src_dir: Path, out_path: Path) -> None:
+    files = sorted(p for p in src_dir.rglob("*") if p.is_file())
+    ct = src_dir / "[Content_Types].xml"
+    fd, tmp_name = tempfile.mkstemp(
+        prefix=out_path.name + ".", suffix=".tmp", dir=out_path.parent
+    )
+    tmp_out = Path(tmp_name)
+    try:
+        with os.fdopen(fd, "wb") as fh:
+            with zipfile.ZipFile(fh, "w", zipfile.ZIP_DEFLATED) as zf:
+                if ct.exists():
+                    zf.write(ct, ct.relative_to(src_dir), compress_type=zipfile.ZIP_STORED)
+                for f in files:
+                    if f == ct:
+                        continue
+                    zf.write(f, f.relative_to(src_dir))
+        if out_path.exists():
+            mode = out_path.stat().st_mode & 0o777
+        else:
+            umask = os.umask(0)
+            os.umask(umask)
+            mode = 0o666 & ~umask
+        os.chmod(tmp_out, mode)
+        os.replace(tmp_out, out_path)
+    finally:
+        if tmp_out.exists():
+            tmp_out.unlink()

package/skills/pptx/scripts/office/helpers/pptx_chart.py

@@ -0,0 +1,170 @@
+"""Find chart XML that PowerPoint refuses but the schema accepts.
+
+Detection only: for either fault more than one repair is valid, and only the
+author knows which was meant.
+"""
+
+
+from __future__ import annotations
+
+import re
+from typing import Mapping
+
+from . import part_text
+
+
+_CHART_PART_RE = re.compile(r"ppt/charts/chart\d+\.xml")
+
+_GROUPING_RE = re.compile(r"""<c:grouping\b[^>]*?\bval=["'](\w+)["']""")
+_DLBL_POS_RE = re.compile(r"""<c:dLblPos\b[^>]*?\bval=["'](\w+)["']""")
+
+def _strip_ext_lst(text: str) -> str:
+    out, cursor = [], 0
+    for lo, hi in _ext_lst_spans(text):
+        out.append(text[cursor:lo])
+        cursor = hi
+    out.append(text[cursor:])
+    return "".join(out)
+
+_BAR_GROUP_RE = re.compile(r"<c:(bar3DChart|barChart)\b[^>]*(?<!/)>.*?</c:\1\s*>", re.DOTALL)
+
+STACKED_GROUPINGS = frozenset({"stacked", "percentStacked"})
+ILLEGAL_ON_STACKED = frozenset({"outEnd"})
+LEGAL_ON_STACKED = ("ctr", "inEnd", "inBase")
+
+
+def _check_stacked_label_positions(part: str, xml: str) -> list[str]:
+    problems: list[str] = []
+    for match in _BAR_GROUP_RE.finditer(xml):
+        block = _strip_ext_lst(match.group(0))
+        group = match.group(1)
+
+        grouping = _GROUPING_RE.search(block)
+        if grouping is None or grouping.group(1) not in STACKED_GROUPINGS:
+            continue
+
+        bad = [p for p in _DLBL_POS_RE.findall(block) if p in ILLEGAL_ON_STACKED]
+        for pos in sorted(set(bad)):
+            problems.append(
+                f'{part}: {bad.count(pos)} data label(s) use dLblPos="{pos}" on a '
+                f"{grouping.group(1)} {group}; PowerPoint allows only "
+                f"{', '.join(LEGAL_ON_STACKED)} there"
+            )
+    return problems
+
+
+
+_ANY_CHART_GROUP_RE = re.compile(r"<c:(\w+Chart)\b[^>]*(?<!/)>.*?</c:\1\s*>", re.DOTALL)
+
+_AXID_RE = re.compile(
+    r"""\s*<c:axId\b[^>]*?\bval=["'](-?\d+)["']\s*(?:/>|>\s*</c:axId\s*>)"""
+)
+
+_AXIS_DECL_RE = re.compile(
+    r"""<c:(catAx|valAx|serAx|dateAx)\b[^>]*(?<!/)>\s*<c:axId\b[^>]*?\bval=["'](-?\d+)["']"""
+)
+
+AXID_LIMIT = {
+    "barChart": 2, "lineChart": 2, "areaChart": 2, "scatterChart": 2,
+    "bubbleChart": 2, "radarChart": 2, "stockChart": 2,
+    "bar3DChart": 3, "line3DChart": 3, "area3DChart": 3,
+    "surfaceChart": 3, "surface3DChart": 3,
+}
+
+AXID_MINIMUM = {
+    "barChart": 2, "lineChart": 2, "areaChart": 2, "scatterChart": 2,
+    "bubbleChart": 2, "radarChart": 2, "stockChart": 2,
+    "bar3DChart": 2, "area3DChart": 2, "surfaceChart": 2,
+    "line3DChart": 3, "surface3DChart": 3,
+}
+
+
+def _declared_axes(xml: str) -> dict[str, list[str]]:
+    axes: dict[str, list[str]] = {}
+    for kind, axid in _AXIS_DECL_RE.findall(xml):
+        axes.setdefault(kind, []).append(axid)
+    return axes
+
+
+def _canonical_ids(axes: dict[str, list[str]], limit: int) -> list[str] | None:
+    category = axes.get("catAx", []) + axes.get("dateAx", [])
+    value = axes.get("valAx", [])
+    series = axes.get("serAx", [])
+    if len(category) != 1 or len(value) != 1 or len(series) > 1:
+        return None
+    ids = [category[0], value[0]]
+    if limit >= 3 and series:
+        ids.append(series[0])
+    return ids
+
+
+def _undeclared_axes(kind: str, block: str, axes: dict[str, list[str]]) -> list[str] | None:
+    if kind not in AXID_LIMIT:
+        return None
+    ids = _AXID_RE.findall(block)
+    declared = {i for group in axes.values() for i in group}
+    if len([i for i in ids if i in declared]) >= 2:
+        return None
+    return ids
+
+
+def _check_chart_axis_references(part: str, xml: str) -> list[str]:
+    axes = _declared_axes(xml)
+    problems: list[str] = []
+    declared = {i for group in axes.values() for i in group}
+    for match in _ANY_CHART_GROUP_RE.finditer(xml):
+        kind, block = match.group(1), match.group(0)
+        ids = _undeclared_axes(kind, block, axes)
+        if ids is None:
+            continue
+        if not ids:
+            problems.append(
+                f"{part}: <c:{kind}> declares no <c:axId> this part can resolve; a chart "
+                f"group needs {AXID_MINIMUM[kind]}, and PowerPoint discards one with fewer"
+            )
+            continue
+        dead = [i for i in ids if i not in declared]
+        canonical = _canonical_ids(axes, AXID_LIMIT[kind])
+        if canonical is not None and len(canonical) >= AXID_MINIMUM[kind]:
+            hint = f"Fix: point them at the axes this part declares ({', '.join(canonical)})"
+        else:
+            hint = ("Fix: the part declares several axes of a kind -- declare the "
+                    "secondary axes the series expects, or drop them")
+        detail = (f"of which {', '.join(dead)} name no declared axis"
+                  if dead else f"only {len(ids)} of which this part declares")
+        problems.append(
+            f"{part}: <c:{kind}> references axId {', '.join(ids)}, {detail}, "
+            f"leaving fewer than two live axes; PowerPoint discards the chart. {hint}"
+        )
+    return problems
+
+
+def _ext_lst_spans(text: str) -> list[tuple[int, int]]:
+    spans: list[tuple[int, int]] = []
+    depth = 0
+    start = 0
+    for match in re.finditer(r"<(/?)c:extLst\b[^>]*?(/?)>", text):
+        closing, self_closing = match.group(1), match.group(2)
+        if self_closing:
+            continue
+        if closing:
+            depth -= 1
+            if depth == 0:
+                spans.append((start, match.end()))
+        else:
+            if depth == 0:
+                start = match.start()
+            depth += 1
+    return spans
+
+
+CHART_CHECKS = (_check_stacked_label_positions, _check_chart_axis_references)
+
+
+def find_chart_problems(files: Mapping[str, bytes]) -> list[str]:
+    problems: list[str] = []
+    for part in sorted(n for n in files if _CHART_PART_RE.fullmatch(n)):
+        xml = part_text(files[part])
+        for check in CHART_CHECKS:
+            problems.extend(check(part, xml))
+    return problems

package/skills/pptx/scripts/office/helpers/pptx_slide.py

@@ -0,0 +1,60 @@
+"""Pick the slide-XML schema errors PowerPoint refuses the file over.
+
+A denylist over lxml's messages, so an unrecognised error class is a miss rather
+than a false alarm.
+"""
+
+
+from __future__ import annotations
+
+import re
+
+SLIDE_PART_RE = re.compile(
+    r"ppt/(slides|slideLayouts|slideMasters|notesSlides|notesMasters|handoutMasters)"
+    r"/[^/]+\.xml"
+)
+
+FATAL_SLIDE_ERRORS: tuple[tuple[re.Pattern[str], str], ...] = (
+    (
+        re.compile(r"\}tableStyleId': This element is not expected"),
+        "two <a:tableStyleId> in one <a:tblPr> (the schema allows one)",
+    ),
+    (
+        re.compile(r"\}srgbClr', attribute 'val'"),
+        "a colour that is not six hex digits",
+    ),
+    (
+        re.compile(r"\}txBody': Missing child element"),
+        "a <p:txBody> with no children",
+    ),
+    (
+        re.compile(r"\}miter', attribute 'lim'"),
+        'a line join with lim="NaN"',
+    ),
+    (
+        re.compile(r"\}uLnTx': This element is not expected"),
+        "<a:uLnTx> in a position the schema forbids",
+    ),
+    (
+        re.compile(r"\}overrideClrMapping': This element is not expected"),
+        "<p:overrideClrMapping> in a position the schema forbids",
+    ),
+    (
+        re.compile(r"\}nvGrpSpPr': Missing child element"),
+        "a <p:nvGrpSpPr> with no children",
+    ),
+)
+
+
+def is_schema_verdict(error: str) -> bool:
+    return error.startswith("Element ")
+
+
+def fatal_slide_errors(errors: set[str]) -> list[str]:
+    out = []
+    for error in sorted(errors):
+        for pattern, meaning in FATAL_SLIDE_ERRORS:
+            if pattern.search(error):
+                out.append(f"{meaning}: {error}")
+                break
+    return out