laygen 0.1.0__py3-none-any.whl

laygen/cli.py

@@ -0,0 +1,121 @@
+"""Command line interface."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+import zipfile
+from pathlib import Path
+
+from . import registry
+from .workspace import Workspace, WorkspaceError
+
+# DOCX, PPTX, XLSX and HWPX are zip containers. An OLE header instead means a legacy
+# binary format (.doc, .hwp) or a password-protected file wearing the wrong extension.
+_OLE_HEADER = b"\xd0\xcf\x11\xe0"
+
+
+def _reject_unreadable(source: Path) -> None:
+    if source.suffix.lower() in {".csv", ".txt"}:
+        return
+    if source.open("rb").read(4) == _OLE_HEADER:
+        raise SystemExit(
+            f"{source.name} is a legacy binary or password-protected file, not a "
+            f"{source.suffix} package. Unlock it or re-save it in {source.suffix} format."
+        )
+
+
+def cmd_extract(args: argparse.Namespace) -> int:
+    source = Path(args.file)
+    if not source.is_file():
+        raise SystemExit(f"No such file: {source}")
+
+    fmt = registry.resolve(source.suffix)
+    _reject_unreadable(source)
+    segments, structure = registry.extractor(fmt)(source)
+
+    workspace = Workspace(Path(args.workdir))
+    workspace.save(source, fmt, segments, structure)
+
+    print(f"{len(segments)} segments -> {workspace.path / Workspace.SEGMENTS}")
+    return 0
+
+
+def cmd_reconstruct(args: argparse.Namespace) -> int:
+    workspace = Workspace(Path(args.workdir))
+    plan = workspace.plan()
+    segments = workspace.segments()
+
+    translations = dict(segments)
+    if args.translations:
+        supplied = json.loads(Path(args.translations).read_text(encoding="utf-8"))
+        unknown = set(supplied) - set(segments)
+        if unknown:
+            raise SystemExit(
+                f"{len(unknown)} unknown segment id(s), e.g. {sorted(unknown)[:3]}"
+            )
+        # Any id the agent left out keeps its source text rather than going missing.
+        translations.update({k: v for k, v in supplied.items() if v is not None})
+        missing = len(segments) - len(supplied)
+    else:
+        missing = 0
+
+    fmt = plan["format"]
+    output = Path(args.output or f"{Path(plan['source_name']).stem}.out{registry.suffix_for(fmt)}")
+    result = registry.reconstructor(fmt)(
+        workspace.original_bytes(), plan["structure"], translations
+    )
+    output.write_bytes(result)
+
+    note = f" ({missing} untranslated kept as source)" if missing > 0 else ""
+    print(f"wrote {output}{note}")
+    return 0
+
+
+def cmd_formats(args: argparse.Namespace) -> int:
+    for suffix, fmt in sorted(registry.FORMATS.items()):
+        print(f"{suffix:<7} {fmt}")
+    return 0
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="laygen",
+        description="Extract translatable text from documents and rebuild them.",
+    )
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    extract = sub.add_parser("extract", help="extract text into a workspace")
+    extract.add_argument("file")
+    extract.add_argument("-w", "--workdir", required=True, help="workspace directory")
+    extract.set_defaults(func=cmd_extract)
+
+    reconstruct = sub.add_parser("reconstruct", help="rebuild the document")
+    reconstruct.add_argument("-w", "--workdir", required=True)
+    reconstruct.add_argument(
+        "-t", "--translations", help="JSON mapping segment ids to translated text"
+    )
+    reconstruct.add_argument("-o", "--output")
+    reconstruct.set_defaults(func=cmd_reconstruct)
+
+    formats = sub.add_parser("formats", help="list supported file types")
+    formats.set_defaults(func=cmd_formats)
+
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = build_parser().parse_args(argv)
+    try:
+        return args.func(args)
+    except (WorkspaceError, registry.UnsupportedFormat) as error:
+        print(f"error: {error}", file=sys.stderr)
+        return 1
+    except zipfile.BadZipFile:
+        print("error: file is corrupt or not a valid document package", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

laygen/extractors/csv.py

@@ -0,0 +1,41 @@
+"""CSV: one segment per non-empty cell, in reading order."""
+
+from __future__ import annotations
+
+import csv as _csv
+import io
+from pathlib import Path
+from typing import Any
+
+import chardet
+
+# Sniffing a huge file is pointless; the delimiter shows up in the first rows.
+_SNIFF_BYTES = 8192
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    raw = Path(path).read_bytes()
+    encoding = chardet.detect(raw)["encoding"] or "utf-8"
+    text = raw.decode(encoding, errors="replace")
+
+    try:
+        delimiter = _csv.Sniffer().sniff(text[:_SNIFF_BYTES], delimiters=",;\t|").delimiter
+    except _csv.Error:
+        delimiter = ","
+
+    segments: dict[str, str] = {}
+    rows: list[list[str | None]] = []
+
+    for row in _csv.reader(io.StringIO(text, newline=""), delimiter=delimiter):
+        row_cids: list[str | None] = []
+        for cell in row:
+            if cell.strip():
+                cid = f"cid{len(segments)}"
+                segments[cid] = cell
+                row_cids.append(cid)
+            else:
+                row_cids.append(None)
+        rows.append(row_cids)
+
+    structure = {"encoding": encoding, "delimiter": delimiter, "rows": rows}
+    return segments, structure

laygen/extractors/docx.py

@@ -0,0 +1,33 @@
+"""DOCX: one segment per paragraph.
+
+Word splits a paragraph into arbitrarily many runs by formatting and spell-check
+state, so runs are concatenated verbatim - any real spacing is already inside the run
+text, carried by xml:space="preserve".
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..ooxml_ns import A, DOCX_NAMESPACES, W
+
+PARTS = (
+    "word/document.xml",
+    "word/header*.xml",
+    "word/footer*.xml",
+    "word/footnotes.xml",
+    "word/endnotes.xml",
+    "word/comments.xml",
+    "word/charts/chart*.xml",
+    "word/diagrams/data*.xml",
+)
+
+# Word paragraphs, plus DrawingML paragraphs used by shapes and charts.
+KINDS = {"w": (f"{{{W}}}p", f"{{{W}}}t"), "a": (f"{{{A}}}p", f"{{{A}}}t")}
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    zipxml.register(DOCX_NAMESPACES)
+    return paragraphs.extract(Path(path).read_bytes(), PARTS, KINDS)

laygen/extractors/excel.py

@@ -0,0 +1,37 @@
+"""XLSX: one segment per shared string.
+
+Text lives in xl/sharedStrings.xml as <si> entries, which cells reference by index.
+Numbers, dates and formulas are stored elsewhere in the sheet XML and so are skipped by
+construction - there is no way to accidentally overwrite a formula with its result.
+
+Shared strings are deduplicated by Excel, so a label repeated across fifty cells is one
+segment, translated once and consistently.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..ooxml_ns import A, S, XLSX_NAMESPACES
+
+PARTS = (
+    "xl/sharedStrings.xml",
+    "xl/worksheets/sheet*.xml",
+    "xl/charts/chart*.xml",
+)
+
+KINDS = {
+    "si": (f"{{{S}}}si", f"{{{S}}}t"),  # shared strings
+    "is": (f"{{{S}}}is", f"{{{S}}}t"),  # inline strings
+    "a": (f"{{{A}}}p", f"{{{A}}}t"),  # chart titles and labels
+}
+
+# <rPh> holds phonetic guides (furigana), not content.
+SKIP = (f"{{{S}}}rPh",)
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    zipxml.register(XLSX_NAMESPACES)
+    return paragraphs.extract(Path(path).read_bytes(), PARTS, KINDS, SKIP)

laygen/extractors/hwpx.py

@@ -0,0 +1,19 @@
+"""HWPX: one segment per paragraph."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..ooxml_ns import HWPX_NAMESPACES
+
+PARTS = ("Contents/section*.xml",)
+
+HP = HWPX_NAMESPACES["hp"]
+KINDS = {"hp": (f"{{{HP}}}p", f"{{{HP}}}t")}
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    zipxml.register(HWPX_NAMESPACES)
+    return paragraphs.extract(Path(path).read_bytes(), PARTS, KINDS)

laygen/extractors/pptx.py

@@ -0,0 +1,28 @@
+"""PPTX: one segment per paragraph.
+
+Slide layouts and masters are skipped - their text is template boilerplate
+("Click to edit Master title style"), not document content.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..ooxml_ns import A, PPTX_NAMESPACES
+
+PARTS = (
+    "ppt/slides/slide*.xml",
+    "ppt/notesSlides/notesSlide*.xml",
+    "ppt/charts/chart*.xml",
+    "ppt/diagrams/data*.xml",
+)
+
+# PowerPoint text is DrawingML throughout, including tables and charts.
+KINDS = {"a": (f"{{{A}}}p", f"{{{A}}}t")}
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    zipxml.register(PPTX_NAMESPACES)
+    return paragraphs.extract(Path(path).read_bytes(), PARTS, KINDS)

laygen/extractors/txt.py

@@ -0,0 +1,35 @@
+"""Plain text: one segment per non-empty line."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+
+def extract(path: Path) -> tuple[dict[str, str], dict[str, Any]]:
+    raw = Path(path).read_bytes()
+    try:
+        content = raw.decode("utf-8")
+        encoding = "utf-8"
+    except UnicodeDecodeError:
+        content = raw.decode("latin-1")
+        encoding = "latin-1"
+
+    segments: dict[str, str] = {}
+    # One slot per line: a cid for lines with content, None for empty ones.
+    line_cids: list[str | None] = []
+
+    for line in content.splitlines():
+        if line:
+            cid = f"cid{len(segments)}"
+            segments[cid] = line
+            line_cids.append(cid)
+        else:
+            line_cids.append(None)
+
+    structure = {
+        "encoding": encoding,
+        "line_cids": line_cids,
+        "trailing_newline": content.endswith(("\n", "\r")),
+    }
+    return segments, structure

laygen/ooxml_ns.py

@@ -0,0 +1,48 @@
+"""XML namespaces, registered before serialisation so prefixes survive a round trip."""
+
+W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+A = "http://schemas.openxmlformats.org/drawingml/2006/main"
+P = "http://schemas.openxmlformats.org/presentationml/2006/main"
+S = "http://schemas.openxmlformats.org/spreadsheetml/2006/main"
+XML = "http://www.w3.org/XML/1998/namespace"
+
+_SHARED = {
+    "a": A,
+    "r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
+    "pic": "http://schemas.openxmlformats.org/drawingml/2006/picture",
+    "mc": "http://schemas.openxmlformats.org/markup-compatibility/2006",
+    "dgm": "http://schemas.openxmlformats.org/drawingml/2006/diagram",
+    "c": "http://schemas.openxmlformats.org/drawingml/2006/chart",
+}
+
+DOCX_NAMESPACES = {
+    **_SHARED,
+    "w": W,
+    "wp": "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing",
+    "m": "http://schemas.openxmlformats.org/officeDocument/2006/math",
+    "v": "urn:schemas-microsoft-com:vml",
+    "w10": "urn:schemas-microsoft-com:office:word",
+    "w14": "http://schemas.microsoft.com/office/word/2010/wordml",
+    "w15": "http://schemas.microsoft.com/office/word/2012/wordml",
+    "wps": "http://schemas.microsoft.com/office/word/2010/wordprocessingShape",
+    "wpg": "http://schemas.microsoft.com/office/word/2010/wordprocessingGroup",
+}
+
+PPTX_NAMESPACES = {
+    **_SHARED,
+    "p": P,
+    "p14": "http://schemas.microsoft.com/office/powerpoint/2010/main",
+}
+
+# Spreadsheet XML carries the main namespace as the default one, so it is registered
+# without a prefix to keep <si> from being rewritten as <s:si>.
+XLSX_NAMESPACES = {**_SHARED, "": S}
+
+HWPX_NAMESPACES = {
+    "hp": "http://www.hancom.co.kr/hwpml/2011/paragraph",
+    "hs": "http://www.hancom.co.kr/hwpml/2011/section",
+    "hh": "http://www.hancom.co.kr/hwpml/2011/head",
+    "hc": "http://www.hancom.co.kr/hwpml/2011/core",
+    "ha": "http://www.hancom.co.kr/hwpml/2011/app",
+    "hn": "http://www.hancom.co.kr/hwpml/2011/master-page",
+}

laygen/paragraphs.py

@@ -0,0 +1,138 @@
+"""Paragraph extraction and reconstruction for the zip-of-XML formats.
+
+DOCX, PPTX and HWPX all store text as paragraphs of runs across a zip of XML parts. A
+"kind" is a (paragraph tag, run tag) pair; a part is scanned for every kind.
+
+Paragraphs nest - a table cell holds its own paragraphs inside an outer one, and a Word
+text box does the same - so a paragraph owns only the run elements that no nested
+paragraph owns first. Without that rule the outer paragraph swallows the inner text and
+the two writes fight over the same runs.
+"""
+
+from __future__ import annotations
+
+from collections import defaultdict
+from typing import Any, Iterator
+
+from . import zipxml
+from .ooxml_ns import XML
+
+Kinds = dict[str, tuple[str, str]]
+
+
+def own_runs(
+    paragraph, para_tag: str, text_tag: str, skip: tuple[str, ...] = ()
+) -> list:
+    """Run elements belonging to this paragraph, not to a paragraph nested inside it.
+
+    `skip` names subtrees to ignore entirely - XLSX phonetic guides, for instance,
+    hold furigana rather than content.
+    """
+    found: list = []
+
+    def walk(node) -> None:
+        for child in node:
+            if child.tag == para_tag or child.tag in skip:
+                continue
+            if child.tag == text_tag:
+                found.append(child)
+            else:
+                walk(child)
+
+    walk(paragraph)
+    return found
+
+
+def text_of(runs: list) -> str:
+    """Run text plus the tails of any inline children (HWPX highlight marks and such)."""
+    parts: list[str] = []
+    for run in runs:
+        if run.text:
+            parts.append(run.text)
+        for child in run.iter():
+            if child is not run and child.tail:
+                parts.append(child.tail)
+    return "".join(parts)
+
+
+def write(runs: list, text: str) -> None:
+    """Put the paragraph into its first run and empty the rest.
+
+    Translation reorders words, so there is no honest way to redistribute the result
+    across runs that were split mid-sentence. Inline children are removed with them,
+    otherwise their tail text would survive alongside the replacement.
+    """
+    for run in runs:
+        run.text = None
+        for child in list(run):
+            run.remove(child)
+
+    runs[0].text = text
+    if text != text.strip():
+        runs[0].set(f"{{{XML}}}space", "preserve")
+
+
+def _walk(
+    root, kinds: Kinds, skip: tuple[str, ...]
+) -> Iterator[tuple[str, int, list]]:
+    for kind, (para_tag, text_tag) in kinds.items():
+        for index, paragraph in enumerate(root.iter(para_tag)):
+            yield kind, index, own_runs(paragraph, para_tag, text_tag, skip)
+
+
+def extract(
+    source: bytes,
+    parts: tuple[str, ...],
+    kinds: Kinds,
+    skip: tuple[str, ...] = (),
+) -> tuple[dict[str, str], dict[str, Any]]:
+    segments: dict[str, str] = {}
+    found: list[dict[str, Any]] = []
+
+    for name, root in zipxml.read_parts(source, zipxml.matching_parts(source, parts)):
+        for kind, index, runs in _walk(root, kinds, skip):
+            text = text_of(runs)
+            if not text.strip():
+                continue
+            cid = f"cid{len(segments)}"
+            segments[cid] = text
+            found.append({"cid": cid, "part": name, "kind": kind, "index": index})
+
+    return segments, {"paragraphs": found}
+
+
+def apply(
+    original: bytes,
+    structure: dict[str, Any],
+    translations: dict[str, str],
+    kinds: Kinds,
+    skip: tuple[str, ...] = (),
+) -> bytes:
+    by_part: dict[str, list[dict[str, Any]]] = defaultdict(list)
+    for entry in structure["paragraphs"]:
+        by_part[entry["part"]].append(entry)
+
+    replacements: dict[str, bytes] = {}
+    for name, root in zipxml.read_parts(original, list(by_part)):
+        # Iteration order is document order, matching extraction.
+        indexed = {
+            (kind, index): runs for kind, index, runs in _walk(root, kinds, skip)
+        }
+
+        changed = False
+        for entry in by_part[name]:
+            runs = indexed.get((entry["kind"], entry["index"]))
+            if not runs:
+                continue
+
+            translated = translations[entry["cid"]]
+            if translated == text_of(runs):
+                continue
+
+            write(runs, translated)
+            changed = True
+
+        if changed:
+            replacements[name] = zipxml.serialise(root)
+
+    return zipxml.replace_parts(original, replacements)

laygen/reconstructors/csv.py

@@ -0,0 +1,23 @@
+"""CSV reconstruction."""
+
+from __future__ import annotations
+
+import csv as _csv
+import io
+from typing import Any
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    buffer = io.StringIO(newline="")
+    writer = _csv.writer(buffer, delimiter=structure.get("delimiter", ","))
+    for row in structure["rows"]:
+        writer.writerow([translations[cid] if cid else "" for cid in row])
+
+    text = buffer.getvalue()
+    encoding = structure.get("encoding", "utf-8")
+    try:
+        return text.encode(encoding)
+    except UnicodeEncodeError:
+        return text.encode("utf-8")

laygen/reconstructors/docx.py

@@ -0,0 +1,16 @@
+"""DOCX reconstruction."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..extractors.docx import KINDS
+from ..ooxml_ns import DOCX_NAMESPACES
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    zipxml.register(DOCX_NAMESPACES)
+    return paragraphs.apply(original, structure, translations, KINDS)

laygen/reconstructors/excel.py

@@ -0,0 +1,16 @@
+"""XLSX reconstruction."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..extractors.excel import KINDS, SKIP
+from ..ooxml_ns import XLSX_NAMESPACES
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    zipxml.register(XLSX_NAMESPACES)
+    return paragraphs.apply(original, structure, translations, KINDS, SKIP)

laygen/reconstructors/hwpx.py

@@ -0,0 +1,16 @@
+"""HWPX reconstruction."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..extractors.hwpx import KINDS
+from ..ooxml_ns import HWPX_NAMESPACES
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    zipxml.register(HWPX_NAMESPACES)
+    return paragraphs.apply(original, structure, translations, KINDS)

laygen/reconstructors/pptx.py

@@ -0,0 +1,16 @@
+"""PPTX reconstruction."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from .. import paragraphs, zipxml
+from ..extractors.pptx import KINDS
+from ..ooxml_ns import PPTX_NAMESPACES
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    zipxml.register(PPTX_NAMESPACES)
+    return paragraphs.apply(original, structure, translations, KINDS)

laygen/reconstructors/txt.py

@@ -0,0 +1,23 @@
+"""Plain text reconstruction."""
+
+from __future__ import annotations
+
+from typing import Any
+
+
+def reconstruct(
+    original: bytes, structure: dict[str, Any], translations: dict[str, str]
+) -> bytes:
+    lines = [
+        translations[cid] if cid else "" for cid in structure["line_cids"]
+    ]
+    text = "\n".join(lines)
+    if structure.get("trailing_newline"):
+        text += "\n"
+
+    encoding = structure.get("encoding", "utf-8")
+    try:
+        return text.encode(encoding)
+    except UnicodeEncodeError:
+        # Translated text may not fit the source encoding (e.g. latin-1 -> Korean).
+        return text.encode("utf-8")

laygen/registry.py

@@ -0,0 +1,44 @@
+"""Format dispatch."""
+
+from __future__ import annotations
+
+import importlib
+from typing import Any, Callable
+
+# Extension -> module name shared by extractors/ and reconstructors/.
+FORMATS = {
+    ".docx": "docx",
+    ".pptx": "pptx",
+    ".xlsx": "excel",
+    ".hwpx": "hwpx",
+    ".csv": "csv",
+    ".txt": "txt",
+}
+
+
+class UnsupportedFormat(Exception):
+    pass
+
+
+def resolve(suffix: str) -> str:
+    fmt = FORMATS.get(suffix.lower())
+    if fmt is None:
+        raise UnsupportedFormat(
+            f"Unsupported file type '{suffix}'. Supported: {', '.join(sorted(FORMATS))}"
+        )
+    return fmt
+
+
+def extractor(fmt: str) -> Callable[..., tuple[dict[str, str], dict[str, Any]]]:
+    return importlib.import_module(f"laygen.extractors.{fmt}").extract
+
+
+def reconstructor(fmt: str) -> Callable[..., bytes]:
+    return importlib.import_module(f"laygen.reconstructors.{fmt}").reconstruct
+
+
+def suffix_for(fmt: str) -> str:
+    for suffix, name in FORMATS.items():
+        if name == fmt:
+            return suffix
+    raise UnsupportedFormat(fmt)

laygen/workspace.py

@@ -0,0 +1,85 @@
+"""Workspace layout and the only disk I/O in the package."""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import shutil
+from pathlib import Path
+from typing import Any
+
+
+class WorkspaceError(Exception):
+    pass
+
+
+class Workspace:
+    """A directory holding an extraction: the original file, its plan and its segments.
+
+    Self-contained by design - copy the directory to another machine and
+    reconstruction still works.
+    """
+
+    PLAN = "plan.json"
+    SEGMENTS = "segments.json"
+
+    def __init__(self, path: Path) -> None:
+        self.path = Path(path)
+
+    # -- writing ----------------------------------------------------------
+
+    def save(
+        self, source: Path, fmt: str, segments: dict[str, str], structure: dict[str, Any]
+    ) -> None:
+        self.path.mkdir(parents=True, exist_ok=True)
+        original = self.path / f"original{source.suffix.lower()}"
+        shutil.copyfile(source, original)
+
+        self._write_json(
+            self.PLAN,
+            {
+                "format": fmt,
+                "source_name": source.name,
+                "original": original.name,
+                "sha256": sha256(source),
+                "segment_count": len(segments),
+                "structure": structure,
+            },
+        )
+        self._write_json(self.SEGMENTS, segments)
+
+    # -- reading ----------------------------------------------------------
+
+    def plan(self) -> dict[str, Any]:
+        return self._read_json(self.PLAN)
+
+    def segments(self) -> dict[str, str]:
+        return self._read_json(self.SEGMENTS)
+
+    def original_bytes(self) -> bytes:
+        plan = self.plan()
+        original = self.path / plan["original"]
+        if not original.is_file():
+            raise WorkspaceError(f"Original file missing from workspace: {original}")
+        return original.read_bytes()
+
+    # -- helpers ----------------------------------------------------------
+
+    def _write_json(self, name: str, payload: Any) -> None:
+        (self.path / name).write_text(
+            json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8"
+        )
+
+    def _read_json(self, name: str) -> Any:
+        target = self.path / name
+        if not target.is_file():
+            raise WorkspaceError(f"Not a laygen workspace (no {name}): {self.path}")
+        return json.loads(target.read_text(encoding="utf-8"))
+
+
+def sha256(path: Path) -> str:
+    digest = hashlib.sha256()
+    with open(path, "rb") as handle:
+        for block in iter(lambda: handle.read(65536), b""):
+            digest.update(block)
+    return digest.hexdigest()

laygen/zipxml.py

@@ -0,0 +1,55 @@
+"""Shared helpers for the zip-of-XML formats (DOCX, PPTX, HWPX)."""
+
+from __future__ import annotations
+
+import fnmatch
+import io
+import xml.etree.ElementTree as ET
+import zipfile
+from typing import Iterator
+
+_DECLARATION = b'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\r\n'
+
+
+def register(namespaces: dict[str, str]) -> None:
+    """Register prefixes so serialisation keeps them instead of emitting ns0, ns1..."""
+    for prefix, uri in namespaces.items():
+        ET.register_namespace(prefix, uri)
+
+
+def matching_parts(source: bytes, patterns: tuple[str, ...]) -> list[str]:
+    """Names of archive members matching any glob, in a stable order."""
+    with zipfile.ZipFile(io.BytesIO(source)) as archive:
+        names = archive.namelist()
+    return sorted(
+        name
+        for name in names
+        if any(fnmatch.fnmatch(name, pattern) for pattern in patterns)
+    )
+
+
+def read_parts(source: bytes, names: list[str]) -> Iterator[tuple[str, ET.Element]]:
+    """Yield (name, parsed root) for each named member that parses as XML."""
+    with zipfile.ZipFile(io.BytesIO(source)) as archive:
+        for name in names:
+            try:
+                yield name, ET.fromstring(archive.read(name))
+            except (KeyError, ET.ParseError):
+                continue
+
+
+def serialise(root: ET.Element) -> bytes:
+    return _DECLARATION + ET.tostring(root, encoding="utf-8")
+
+
+def replace_parts(source: bytes, replacements: dict[str, bytes]) -> bytes:
+    """Copy the archive, substituting the named members. Everything else is untouched."""
+    output = io.BytesIO()
+    with zipfile.ZipFile(io.BytesIO(source)) as original:
+        with zipfile.ZipFile(output, "w", zipfile.ZIP_DEFLATED) as result:
+            for item in original.infolist():
+                data = replacements.get(item.filename)
+                if data is None:
+                    data = original.read(item.filename)
+                result.writestr(item, data)
+    return output.getvalue()

laygen-0.1.0.dist-info/METADATA

@@ -0,0 +1,108 @@
+Metadata-Version: 2.5
+Name: laygen
+Version: 0.1.0
+Summary: Layout-preserving text extraction and reconstruction for office documents
+Project-URL: Homepage, https://ondevice.neoali.com/laygen
+Author-email: "NEOALI CO., LTD." <neoali.official@gmail.com>
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: docx,hwpx,layout,localization,ooxml,pptx,translation,xlsx
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Localization
+Classifier: Topic :: Text Processing :: Markup
+Requires-Python: >=3.10
+Requires-Dist: chardet>=5.0
+Description-Content-Type: text/markdown
+
+# laygen
+
+Extract translatable text from office documents and rebuild them with the layout intact.
+
+`laygen` does not translate anything. It splits a document into its text segments, hands
+them over as JSON, and puts translated text back where it came from. Whatever does the
+translating — an agent, a script, a person — sits in between. That keeps the tool free of
+model dependencies, API keys and network access.
+
+## Formats
+
+| Extension | Segment |
+|---|---|
+| `.docx` | paragraph (body, headers, footers, notes, charts, SmartArt) |
+| `.pptx` | paragraph (slides, speaker notes, charts, SmartArt) |
+| `.xlsx` | shared string (deduplicated), inline strings, chart labels |
+| `.hwpx` | paragraph |
+| `.csv` | non-empty cell |
+| `.txt` | non-empty line |
+
+## Install
+
+```bash
+uv tool install laygen
+```
+
+The only dependency is `chardet`, for detecting text encodings. Everything else is
+standard library.
+
+## Use
+
+```bash
+# 1. Pull the text out
+laygen extract report.docx -w work/
+# 42 segments -> work/segments.json
+
+# 2. Translate work/segments.json into translated.json, keeping the keys
+
+# 3. Put it back
+laygen reconstruct -w work/ -t translated.json -o report.ko.docx
+```
+
+`work/segments.json` is a flat `{"cid0": "text", ...}` map. Your translation file uses the
+same keys. Any key you leave out keeps its source text, so a partial translation degrades
+into a partly-translated document rather than a broken one.
+
+## The workspace
+
+```
+work/
+├── original.docx    copy of the source
+├── plan.json        format, checksum and the map back to the original elements
+└── segments.json    {"cid0": "…"}  — the only file a translator needs
+```
+
+Self-contained: move the directory to another machine and reconstruction still works.
+
+## Notes and limits
+
+- **Segment ids are positional.** They are assigned in document order at extraction time.
+  Reconstruction re-reads `original.*` from the workspace, so never edit the source
+  document between the two steps — `plan.json` records a SHA-256 to help you notice.
+- **Formatting that varies inside a paragraph is lost.** A translated paragraph goes into
+  its first run and the remaining runs are emptied. Translation reorders words, so there
+  is no honest way to keep a bold span attached to the word it started on. Paragraph and
+  character styling itself is preserved.
+- **XLSX is edited through its shared string table**, not rebuilt by a spreadsheet
+  library, so charts, pivot tables, macros and formulas survive untouched. Numbers, dates
+  and formulas are skipped by construction — they are not stored as shared strings.
+  Because Excel deduplicates that table, a label repeated across fifty cells is one
+  segment, translated once and consistently.
+- **PPTX skips slide layouts and masters**, whose text is template boilerplate.
+- **HWPX drops inline markup inside a rewritten paragraph** (highlight marks, line
+  breaks). The paragraph's own text and styling survive.
+- **No PDF.** It needs layout detection and OCR, which would pull in a GPU-scale
+  dependency stack. Out of scope for this version.
+
+## Development
+
+```bash
+uv sync
+uv run pytest
+```

laygen-0.1.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+laygen/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+laygen/cli.py,sha256=HUA3mBmelebLUjWXV0oaDljbj7bILwa-TsRFGjz8g_Y,4054
+laygen/ooxml_ns.py,sha256=RDHn66aDqOqQrnDWWhctgZAvPxT9v99EAK09NnZ5N-8,2035
+laygen/paragraphs.py,sha256=PSgGMACKab12AZ9PkzB1ZPKtQeBEyFrH63e5VBjCkAg,4358
+laygen/registry.py,sha256=KAp5GfFHHZs8wLK-LBljK2s_AkC-9Jc4gzZBYosrs-M,1052
+laygen/workspace.py,sha256=wNqIwQz_OWWMiwSRBG2ekSMxks6mPEkR2O3IxNhtiwI,2597
+laygen/zipxml.py,sha256=bClhvBmqaJy-eWe_N7DY-ulzNZ3eKwyrhCqTEuFdIJ0,1983
+laygen/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+laygen/extractors/csv.py,sha256=skgr1qX-ZnIL1cym_oDtPwGufoma-_cmbdW78KSX6FA,1211
+laygen/extractors/docx.py,sha256=wOSrRKcUtNrXJSqjhfusKOaZsJ3yGwOuv8jTK1Mfbq4,957
+laygen/extractors/excel.py,sha256=iUHMMl2fzN3F0vPzvUGQQJY_058kkunF_i-UsKopah8,1150
+laygen/extractors/hwpx.py,sha256=owqd3vWLOKjLIS4uO5W5slAArtTU-Uxm78LtZAEJwiE,481
+laygen/extractors/pptx.py,sha256=Zpe_NO7ieW_MKF1SY96Vm5fk96PCxlaNnRbf8bJ2OiY,767
+laygen/extractors/txt.py,sha256=ILVbUS30pkyycxcEjW3Ssh-YsS8Tp8i1-Ogi70xpmV0,949
+laygen/reconstructors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+laygen/reconstructors/csv.py,sha256=GWnVj8uj5R_8QwXEBfPFZUOjRVDw8pbPccqPhDuxKaM,638
+laygen/reconstructors/docx.py,sha256=r0-kVy4HlMAN9ZFVZkHWSVTtsZiUS-cL6EfT-rMJeyU,412
+laygen/reconstructors/excel.py,sha256=geV_bzo53DHWDZPVY64srM89_GAfa6UmxnUSSQyvXQQ,425
+laygen/reconstructors/hwpx.py,sha256=EbnS6JqzzOCXEZLHLqvIWarhBk-9Rj1EGieIimi6A2s,412
+laygen/reconstructors/pptx.py,sha256=b8qXeIEUCxqXhHco1pLFj6cICM5tXpeX-mYCgVYp3to,412
+laygen/reconstructors/txt.py,sha256=FtAQmZLLqXWpio4snS-nrGNwrbr0GNbUVEnCsl5K9ig,635
+laygen-0.1.0.dist-info/METADATA,sha256=27llyr5WZGgpTg_2TrIujunkc8mHZtGOdC4FW2n7nXs,4154
+laygen-0.1.0.dist-info/WHEEL,sha256=zOwg4jB6zX2kU910N-cMawjivD6tO8NEWvE12je1bVk,87
+laygen-0.1.0.dist-info/entry_points.txt,sha256=dZjw4oyvVjOBQIUfxcaQbzz1sdfG_TP8r9mEdnlJWTg,43
+laygen-0.1.0.dist-info/licenses/LICENSE,sha256=rEKmMMjP1BnOEJJvKQvNqq3QKOJ4PBU8Q5NW8T9Cdeg,11347
+laygen-0.1.0.dist-info/licenses/NOTICE,sha256=Y8-W3r2gLXrvD5I7sht-brNhiBftX_cPkbgrpqLAa4M,233
+laygen-0.1.0.dist-info/RECORD,,

laygen-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.0
+Root-Is-Purelib: true
+Tag: py3-none-any

laygen-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+laygen = laygen.cli:main

laygen-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 NEOALI CO., LTD.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

laygen-0.1.0.dist-info/licenses/NOTICE

@@ -0,0 +1,7 @@
+laygen
+Copyright 2026 NEOALI CO., LTD.
+
+This product includes software developed at NEOALI CO., LTD.
+
+Licensed under the Apache License, Version 2.0. You may obtain a copy of
+the License at http://www.apache.org/licenses/LICENSE-2.0