python-hwpx 2.4__py3-none-any.whl → 2.6__py3-none-any.whl

hwpx/document.py

@@ -1280,7 +1280,7 @@ class HwpxDocument:
         """
         from .tools.validator import validate_document
 
-        return validate_document(self._to_bytes_raw())
+        return validate_document(self._to_bytes_raw(reset_dirty=False))
 
     def _run_pre_save_validation(self) -> None:
         """Raise if validate_on_save is enabled and the document is invalid."""
@@ -1318,11 +1318,16 @@ class HwpxDocument:
         self._run_pre_save_validation()
         return self._to_bytes_raw()
 
-    def _to_bytes_raw(self) -> bytes:
-        """Serialize without validation (used by :meth:`validate`)."""
+    def _to_bytes_raw(self, *, reset_dirty: bool = True) -> bytes:
+        """Serialize without validation.
+
+        When ``reset_dirty`` is ``False``, the document remains marked as
+        modified after the archive snapshot is generated.
+        """
         updates = self._root.serialize()
         result = self._package.save(None, updates)
-        self._root.reset_dirty()
+        if reset_dirty:
+            self._root.reset_dirty()
         if isinstance(result, bytes):
             return result
         raise TypeError("package.save(None) must return bytes")

hwpx/oxml/document.py

@@ -2541,7 +2541,12 @@ class HwpxOxmlTable:
                     existing_target.set_size(col_width, row_height)
                     continue
 
-                new_cell_element = ET.Element(f"{_HP}tc", dict(template_attrs))
+                # Use makeelement() so the new cell matches the XML engine
+                # of the existing tree (stdlib ET or lxml).  ET.Element()
+                # always produces stdlib elements which cannot be appended to
+                # an lxml tree (and vice-versa), causing TypeError at runtime
+                # when splitting cells in documents parsed via lxml.
+                new_cell_element = row_element.makeelement(f"{_HP}tc", dict(template_attrs))
                 for child in preserved_children:
                     new_cell_element.append(deepcopy(child))
 

hwpx/tools/__init__.py

@@ -6,6 +6,16 @@ from .exporter import (
     export_text,
 )
 from .object_finder import FoundElement, ObjectFinder
+from .package_validator import (
+    PackageValidationIssue,
+    PackageValidationReport,
+    validate_package,
+)
+from .page_guard import (
+    DocumentMetrics,
+    collect_metrics,
+    compare_metrics,
+)
 from .text_extractor import (
     DEFAULT_NAMESPACES,
     ParagraphInfo,
@@ -33,6 +43,12 @@ __all__ = [
     "strip_namespace",
     "FoundElement",
     "ObjectFinder",
+    "PackageValidationIssue",
+    "PackageValidationReport",
+    "validate_package",
+    "DocumentMetrics",
+    "collect_metrics",
+    "compare_metrics",
     "DocumentSchemas",
     "ValidationIssue",
     "ValidationReport",

hwpx/tools/package_validator.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+import argparse
+import io
+import xml.etree.ElementTree as ET
+from dataclasses import dataclass
+from pathlib import Path
+from typing import BinaryIO, Sequence
+from zipfile import ZIP_STORED, BadZipFile, ZipFile
+
+EXPECTED_MIMETYPE = "application/hwp+zip"
+CONTAINER_PATH = "META-INF/container.xml"
+MANIFEST_PATH = "Contents/content.hpf"
+HEADER_PATH = "Contents/header.xml"
+VERSION_PATH = "version.xml"
+REQUIRED_CORE_FILES = ("mimetype", CONTAINER_PATH, MANIFEST_PATH, HEADER_PATH, VERSION_PATH)
+OPF_NS = {"opf": "http://www.idpf.org/2007/opf/"}
+CONTAINER_NS = {
+    "ct": "urn:oasis:names:tc:opendocument:xmlns:container",
+    "ocf": "urn:oasis:names:tc:opendocument:xmlns:container",
+}
+
+__all__ = [
+    "PackageValidationIssue",
+    "PackageValidationReport",
+    "validate_package",
+    "main",
+]
+
+
+@dataclass(frozen=True)
+class PackageValidationIssue:
+    part_name: str
+    message: str
+
+    def __str__(self) -> str:  # pragma: no cover - human readable helper
+        return f"{self.part_name}: {self.message}"
+
+
+@dataclass(frozen=True)
+class PackageValidationReport:
+    checked_parts: tuple[str, ...]
+    issues: tuple[PackageValidationIssue, ...]
+
+    @property
+    def ok(self) -> bool:
+        return not self.issues
+
+    def __bool__(self) -> bool:  # pragma: no cover - convenience alias
+        return self.ok
+
+
+def _open_zip(source: str | Path | bytes | BinaryIO) -> ZipFile:
+    if isinstance(source, (str, Path)):
+        return ZipFile(source, "r")
+    if isinstance(source, bytes):
+        return ZipFile(io.BytesIO(source), "r")
+    return ZipFile(source, "r")
+
+
+def _parse_xml(payload: bytes) -> ET.Element:
+    try:
+        return ET.fromstring(payload)
+    except ET.ParseError as exc:
+        raise ValueError(f"malformed XML: {exc}") from exc
+
+
+def _container_rootfiles(container_root: ET.Element) -> list[str]:
+    paths: list[str] = []
+    for namespace in CONTAINER_NS.values():
+        paths.extend(
+            elem.get("full-path")
+            or elem.get("fullPath")
+            or elem.get("full_path")
+            for elem in container_root.findall(f".//{{{namespace}}}rootfile")
+        )
+    return [path for path in paths if path]
+
+
+def _manifest_hrefs(manifest_root: ET.Element) -> set[str]:
+    hrefs: set[str] = set()
+    for item in manifest_root.findall(".//opf:item", OPF_NS):
+        href = item.get("href")
+        if href:
+            hrefs.add(href)
+    return hrefs
+
+
+def _spine_hrefs(manifest_root: ET.Element) -> list[str]:
+    hrefs: list[str] = []
+    id_to_href: dict[str, str] = {}
+    for item in manifest_root.findall(".//opf:item", OPF_NS):
+        item_id = item.get("id")
+        href = item.get("href")
+        if item_id and href:
+            id_to_href[item_id] = href
+
+    for itemref in manifest_root.findall(".//opf:itemref", OPF_NS):
+        idref = itemref.get("idref")
+        if idref and idref in id_to_href:
+            hrefs.append(id_to_href[idref])
+    return hrefs
+
+
+def validate_package(source: str | Path | bytes | BinaryIO) -> PackageValidationReport:
+    checked_parts: list[str] = []
+    issues: list[PackageValidationIssue] = []
+
+    try:
+        archive = _open_zip(source)
+    except BadZipFile:
+        return PackageValidationReport(
+            checked_parts=(),
+            issues=(PackageValidationIssue("archive", "not a valid ZIP archive"),),
+        )
+
+    with archive as zf:
+        names = zf.namelist()
+        checked_parts.extend(names)
+
+        for required in REQUIRED_CORE_FILES:
+            if required not in names:
+                issues.append(PackageValidationIssue(required, "missing required file"))
+
+        if not names:
+            issues.append(PackageValidationIssue("archive", "empty archive"))
+            return PackageValidationReport(tuple(checked_parts), tuple(issues))
+
+        if "mimetype" in names:
+            try:
+                mimetype = zf.read("mimetype").decode("utf-8").strip()
+            except UnicodeDecodeError:
+                mimetype = "<binary>"
+            if mimetype != EXPECTED_MIMETYPE:
+                issues.append(
+                    PackageValidationIssue(
+                        "mimetype",
+                        f"expected {EXPECTED_MIMETYPE!r}, got {mimetype!r}",
+                    )
+                )
+            if names[0] != "mimetype":
+                issues.append(PackageValidationIssue("mimetype", "must be the first ZIP entry"))
+            if zf.getinfo("mimetype").compress_type != ZIP_STORED:
+                issues.append(PackageValidationIssue("mimetype", "must use ZIP_STORED"))
+
+        xml_roots: dict[str, ET.Element] = {}
+        for name in names:
+            if not (name.endswith(".xml") or name.endswith(".hpf")):
+                continue
+            try:
+                xml_roots[name] = _parse_xml(zf.read(name))
+            except ValueError as exc:
+                issues.append(PackageValidationIssue(name, str(exc)))
+
+        container_root = xml_roots.get(CONTAINER_PATH)
+        if container_root is not None:
+            rootfiles = _container_rootfiles(container_root)
+            if not rootfiles:
+                issues.append(PackageValidationIssue(CONTAINER_PATH, "declares no rootfile entries"))
+            for rootfile in rootfiles:
+                if rootfile not in names:
+                    issues.append(
+                        PackageValidationIssue(
+                            CONTAINER_PATH,
+                            f"rootfile points to missing part {rootfile!r}",
+                        )
+                    )
+
+        manifest_root = xml_roots.get(MANIFEST_PATH)
+        if manifest_root is not None:
+            hrefs = _manifest_hrefs(manifest_root)
+            for href in sorted(hrefs):
+                if href not in names:
+                    issues.append(
+                        PackageValidationIssue(
+                            MANIFEST_PATH,
+                            f"manifest href missing from archive: {href}",
+                        )
+                    )
+
+            spine_hrefs = _spine_hrefs(manifest_root)
+            if not spine_hrefs:
+                issues.append(PackageValidationIssue(MANIFEST_PATH, "spine declares no section parts"))
+            for href in spine_hrefs:
+                if href not in names:
+                    issues.append(
+                        PackageValidationIssue(
+                            MANIFEST_PATH,
+                            f"spine item missing from archive: {href}",
+                        )
+                    )
+
+            if HEADER_PATH in names and HEADER_PATH not in hrefs:
+                issues.append(
+                    PackageValidationIssue(MANIFEST_PATH, "header.xml is not referenced in manifest")
+                )
+
+    return PackageValidationReport(tuple(checked_parts), tuple(issues))
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Validate HWPX package structure")
+    parser.add_argument("source", help="Path to the HWPX file")
+    args = parser.parse_args(argv)
+
+    report = validate_package(args.source)
+    if report.issues:
+        for issue in report.issues:
+            print(f"ERROR: {issue}")
+        return 1
+
+    print("All package validations passed.")
+    return 0
+
+
+if __name__ == "__main__":  # pragma: no cover - CLI convenience
+    raise SystemExit(main())

hwpx/tools/page_guard.py

@@ -0,0 +1,242 @@
+from __future__ import annotations
+
+import argparse
+import io
+import json
+from dataclasses import asdict, dataclass
+from pathlib import Path
+from typing import BinaryIO, Iterable, Sequence
+from zipfile import ZipFile
+
+from lxml import etree
+
+NS = {
+    "hp": "http://www.hancom.co.kr/hwpml/2011/paragraph",
+    "hs": "http://www.hancom.co.kr/hwpml/2011/section",
+    "opf": "http://www.idpf.org/2007/opf/",
+}
+
+__all__ = [
+    "DocumentMetrics",
+    "collect_metrics",
+    "compare_metrics",
+    "main",
+]
+
+
+@dataclass(frozen=True)
+class DocumentMetrics:
+    section_count: int
+    paragraph_count: int
+    page_break_count: int
+    column_break_count: int
+    table_count: int
+    table_shapes: list[tuple[str, str, str, str, str, str]]
+    text_char_total: int
+    text_char_total_nospace: int
+    paragraph_text_lengths: list[int]
+
+
+def _section_files(zf: ZipFile) -> list[str]:
+    try:
+        root = etree.fromstring(zf.read("Contents/content.hpf"))
+    except KeyError:
+        return [
+            name
+            for name in zf.namelist()
+            if name.startswith("Contents/section") and name.endswith(".xml")
+        ]
+
+    id_to_href: dict[str, str] = {}
+    for item in root.findall(".//opf:item", namespaces=NS):
+        item_id = item.get("id")
+        href = item.get("href")
+        if item_id and href:
+            id_to_href[item_id] = href
+
+    files: list[str] = []
+    for itemref in root.findall(".//opf:itemref", namespaces=NS):
+        idref = itemref.get("idref")
+        if idref and idref in id_to_href:
+            files.append(id_to_href[idref])
+    return files
+
+
+def _text_of_t_node(node: etree._Element) -> str:
+    return "".join(node.itertext())
+
+
+def _iter_section_roots(source: str | Path | bytes | BinaryIO) -> Iterable[etree._Element]:
+    if isinstance(source, bytes):
+        archive = ZipFile(io.BytesIO(source), "r")
+    else:
+        archive = ZipFile(source, "r")
+
+    try:
+        for name in _section_files(archive):
+            yield etree.fromstring(archive.read(name))
+    finally:
+        archive.close()
+
+
+def collect_metrics(source: str | Path | bytes | BinaryIO) -> DocumentMetrics:
+    section_roots = list(_iter_section_roots(source))
+
+    paragraphs: list[etree._Element] = []
+    tables: list[etree._Element] = []
+    table_shapes: list[tuple[str, str, str, str, str, str]] = []
+    paragraph_text_lengths: list[int] = []
+    text_char_total = 0
+    text_char_total_nospace = 0
+    page_break_count = 0
+    column_break_count = 0
+
+    for root in section_roots:
+        section_paragraphs = root.xpath(".//hs:sec/hp:p", namespaces=NS)
+        if not section_paragraphs:
+            section_paragraphs = root.xpath(".//hp:p", namespaces=NS)
+        paragraphs.extend(section_paragraphs)
+
+        section_tables = root.xpath(".//hp:tbl", namespaces=NS)
+        tables.extend(section_tables)
+
+        for table in section_tables:
+            size = table.find("hp:sz", namespaces=NS)
+            table_shapes.append(
+                (
+                    table.get("rowCnt", ""),
+                    table.get("colCnt", ""),
+                    size.get("width", "") if size is not None else "",
+                    size.get("height", "") if size is not None else "",
+                    table.get("repeatHeader", ""),
+                    table.get("pageBreak", ""),
+                )
+            )
+
+        for paragraph in section_paragraphs:
+            if paragraph.get("pageBreak") == "1":
+                page_break_count += 1
+            if paragraph.get("columnBreak") == "1":
+                column_break_count += 1
+            paragraph_length = 0
+            for text_node in paragraph.xpath(".//hp:t", namespaces=NS):
+                text = _text_of_t_node(text_node)
+                paragraph_length += len(text)
+                text_char_total += len(text)
+                text_char_total_nospace += len("".join(text.split()))
+            paragraph_text_lengths.append(paragraph_length)
+
+    return DocumentMetrics(
+        section_count=len(section_roots),
+        paragraph_count=len(paragraphs),
+        page_break_count=page_break_count,
+        column_break_count=column_break_count,
+        table_count=len(tables),
+        table_shapes=table_shapes,
+        text_char_total=text_char_total,
+        text_char_total_nospace=text_char_total_nospace,
+        paragraph_text_lengths=paragraph_text_lengths,
+    )
+
+
+def _ratio_delta(reference_value: int, output_value: int) -> float:
+    base = max(reference_value, 1)
+    return abs(output_value - reference_value) / base
+
+
+def compare_metrics(
+    reference: DocumentMetrics,
+    output: DocumentMetrics,
+    *,
+    max_text_delta_ratio: float = 0.15,
+    max_paragraph_delta_ratio: float = 0.25,
+) -> list[str]:
+    errors: list[str] = []
+
+    if reference.section_count != output.section_count:
+        errors.append(
+            f"section count mismatch: ref={reference.section_count}, out={output.section_count}"
+        )
+    if reference.paragraph_count != output.paragraph_count:
+        errors.append(
+            f"paragraph count mismatch: ref={reference.paragraph_count}, out={output.paragraph_count}"
+        )
+    if reference.page_break_count != output.page_break_count:
+        errors.append(
+            "pageBreak count mismatch: "
+            f"ref={reference.page_break_count}, out={output.page_break_count}"
+        )
+    if reference.column_break_count != output.column_break_count:
+        errors.append(
+            "columnBreak count mismatch: "
+            f"ref={reference.column_break_count}, out={output.column_break_count}"
+        )
+    if reference.table_count != output.table_count:
+        errors.append(f"table count mismatch: ref={reference.table_count}, out={output.table_count}")
+    if reference.table_shapes != output.table_shapes:
+        errors.append("table shape mismatch (rowCnt/colCnt/width/height/repeatHeader/pageBreak)")
+
+    text_delta = _ratio_delta(reference.text_char_total_nospace, output.text_char_total_nospace)
+    if text_delta > max_text_delta_ratio:
+        errors.append(
+            "total text length drift exceeded: "
+            f"ref={reference.text_char_total_nospace}, out={output.text_char_total_nospace}, "
+            f"delta={text_delta:.2%}, limit={max_text_delta_ratio:.2%}"
+        )
+
+    if len(reference.paragraph_text_lengths) == len(output.paragraph_text_lengths):
+        for index, (ref_len, out_len) in enumerate(
+            zip(reference.paragraph_text_lengths, output.paragraph_text_lengths),
+            start=1,
+        ):
+            if ref_len == 0 and out_len == 0:
+                continue
+            delta = _ratio_delta(ref_len, out_len)
+            if delta > max_paragraph_delta_ratio:
+                errors.append(
+                    f"paragraph {index} text drift exceeded: "
+                    f"ref={ref_len}, out={out_len}, delta={delta:.2%}, "
+                    f"limit={max_paragraph_delta_ratio:.2%}"
+                )
+    return errors
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Reference-vs-output HWPX page drift guard")
+    parser.add_argument("--reference", "-r", required=True, help="Reference HWPX path")
+    parser.add_argument("--output", "-o", required=True, help="Output HWPX path")
+    parser.add_argument("--max-text-delta-ratio", type=float, default=0.15)
+    parser.add_argument("--max-paragraph-delta-ratio", type=float, default=0.25)
+    parser.add_argument("--json", action="store_true", help="Print collected metrics as JSON")
+    args = parser.parse_args(argv)
+
+    reference = collect_metrics(args.reference)
+    output = collect_metrics(args.output)
+
+    if args.json:
+        print(
+            json.dumps(
+                {"reference": asdict(reference), "output": asdict(output)},
+                ensure_ascii=False,
+                indent=2,
+            )
+        )
+
+    errors = compare_metrics(
+        reference,
+        output,
+        max_text_delta_ratio=args.max_text_delta_ratio,
+        max_paragraph_delta_ratio=args.max_paragraph_delta_ratio,
+    )
+    if errors:
+        print("FAIL: page guard")
+        for error in errors:
+            print(f" - {error}")
+        return 1
+
+    print("PASS: page guard")
+    return 0
+
+
+if __name__ == "__main__":  # pragma: no cover - CLI convenience
+    raise SystemExit(main())

hwpx/tools/text_extract_cli.py

@@ -0,0 +1,66 @@
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+from typing import Sequence
+
+from .text_extractor import TextExtractor
+
+__all__ = [
+    "extract_plain",
+    "extract_markdown",
+    "main",
+]
+
+
+def extract_plain(hwpx_path: str, *, include_tables: bool = False) -> str:
+    with TextExtractor(hwpx_path) as extractor:
+        return extractor.extract_text(
+            include_nested=include_tables,
+            object_behavior="skip",
+            skip_empty=True,
+        )
+
+
+def extract_markdown(hwpx_path: str) -> str:
+    lines: list[str] = []
+    with TextExtractor(hwpx_path) as extractor:
+        for section in extractor.iter_sections():
+            if lines:
+                lines.extend(["", "---", ""])
+            for paragraph in extractor.iter_paragraphs(section, include_nested=True):
+                text = paragraph.text(object_behavior="skip")
+                if not text.strip():
+                    continue
+                lines.append(f"  {text}" if paragraph.is_nested else text)
+    return "\n".join(lines)
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Extract text from an HWPX document")
+    parser.add_argument("input", help="Path to the .hwpx file")
+    parser.add_argument("--format", "-f", choices=["plain", "markdown"], default="plain")
+    parser.add_argument("--include-tables", action="store_true", help="Include nested table text")
+    parser.add_argument("--output", "-o", help="Write output to a file instead of stdout")
+    args = parser.parse_args(argv)
+
+    input_path = Path(args.input)
+    if not input_path.is_file():
+        print(f"Error: File not found: {args.input}", file=sys.stderr)
+        return 1
+
+    if args.format == "markdown":
+        result = extract_markdown(str(input_path))
+    else:
+        result = extract_plain(str(input_path), include_tables=args.include_tables)
+
+    if args.output:
+        Path(args.output).write_text(result, encoding="utf-8")
+    else:
+        print(result)
+    return 0
+
+
+if __name__ == "__main__":  # pragma: no cover - CLI convenience
+    raise SystemExit(main())

{python_hwpx-2.4.dist-info → python_hwpx-2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-hwpx
-Version: 2.4
+Version: 2.6
 Summary: Hancom HWPX 패키지를 로드하고 편집하기 위한 Python 유틸리티 모음
 Author: python-hwpx Maintainers
 License: Non-Commercial License

{python_hwpx-2.4.dist-info → python_hwpx-2.6.dist-info}/RECORD

@@ -1,5 +1,5 @@
 hwpx/__init__.py,sha256=RZ4O84G3Zp_L8ELArtwO3KVPvhx1vLYyKC2Ka1M5mwc,857
-hwpx/document.py,sha256=baRLoczbbWvQQg7cUByLbo-agMGnT7rlnJcJyWZo7Gk,47944
+hwpx/document.py,sha256=UnM61gSf9Hno5n0YWrVSTod9USmA3WtRQeeQadLbYdQ,48133
 hwpx/package.py,sha256=YK4oYEPk7la2BZKZepoVHzrjGIPMDnDdPa02Hh-RTBw,1103
 hwpx/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hwpx/templates.py,sha256=kZ_gV0bP-DIvr5CJuzs-uGnt8XVncJCI3cGFq083uTg,1149
@@ -9,7 +9,7 @@ hwpx/opc/xml_utils.py,sha256=1Cr9ZGR0z1N0NaFxnaHcC7Ne38UoyERGEd878F3co5s,3445
 hwpx/oxml/__init__.py,sha256=N7APpTysxbxfZ2UehK2pGeiAuP0MeQrUA8hzIkY4mkQ,4962
 hwpx/oxml/body.py,sha256=ALvxB_sLU-EoNpldMlnbv4QZEUXyWJMj6cwWVNRXRx4,13284
 hwpx/oxml/common.py,sha256=-WkPxXsAcCxddzRPBfVHS_nZBuSd5g3_CzZyz2lU7Ss,1006
-hwpx/oxml/document.py,sha256=HrSs0aaCFv9kEUrDzKJLnoNE_Q8go1rmwRXjU3ciaB0,170338
+hwpx/oxml/document.py,sha256=Nreec60dgsU_KWW83_JIv3jp6hlVkiAJvMO3ELi6VnE,170725
 hwpx/oxml/header.py,sha256=L1gcBMgROFX9mH8Fj9Kipb7tKWItTKO4mxBbwaoLpDM,43042
 hwpx/oxml/header_part.py,sha256=HXTDlaUzZ6DVfiZDGge2FuqTstEmUqdobiJ0dqjuYyk,193
 hwpx/oxml/memo.py,sha256=qow_mWIQv0AlnIdFdnaL9n-tR0Xws0kv2lGNzefrCB8,190
@@ -20,16 +20,19 @@ hwpx/oxml/schema.py,sha256=THswXdMNpAiSoLxpvUGbdbI66hW-SKuUqSw4vdkIYmA,1246
 hwpx/oxml/section.py,sha256=WwxZ6PWPeMrj2L9mz4JlqFGXwd7E7qAuSBuM5dgRjZk,199
 hwpx/oxml/table.py,sha256=pdO2TTAcbEC6Z4cnaOnB-bcmuZ1KVado7J3RiY_zOfE,193
 hwpx/oxml/utils.py,sha256=to0yytS7vtLSvWl-dQyegT6MWClMK55b1Sp1uagEkI4,2591
-hwpx/tools/__init__.py,sha256=xdC5-XgLEMOKAvHAafhSk6tCVd9psF3PtcZfuWDTpb8,911
+hwpx/tools/__init__.py,sha256=e1OaIVdbkmjTvLOzQ7qVRfuuQ1611225pNZByB2ln9w,1270
 hwpx/tools/exporter.py,sha256=GcbNtV4rIWOJv5nBcgdX0yfkXQa-xQhfrCzXWgaNbTE,8862
 hwpx/tools/object_finder.py,sha256=vbZ8FuIpGF-2vpbWDeZWi4UgZ2-3PK_ddQCs0oq1dRw,13440
+hwpx/tools/package_validator.py,sha256=ZixhRjv_RYwBshk3NEJXyakRVsN7hM4WI47euvWFETU,7379
+hwpx/tools/page_guard.py,sha256=nholL2cMv249yieVBWGqW3WHqkFR1qVutBVz59V_kYo,8351
+hwpx/tools/text_extract_cli.py,sha256=pIBMIFuFX10IEegw7fQ3gtUbQyjNgbAUYkQWh2S3aQs,2150
 hwpx/tools/text_extractor.py,sha256=r2OJRgDOiR6n14hXRcvkYuSFtEHpAV6jasHv-ZLHx1Y,24238
 hwpx/tools/validator.py,sha256=KThqBQKKQfZkuLMGtzONbPkzy877-2FgT22FHPmt_gI,5979
 hwpx/tools/_schemas/header.xsd,sha256=mJXuFMuHGT1JnFFaluUpYUglwjMCNlfbFCRVM26eHXE,664
 hwpx/tools/_schemas/section.xsd,sha256=MgvavVHG05RDfUnVPxVU10H4FQOja5ON04_m9Uk_m7E,522
-python_hwpx-2.4.dist-info/licenses/LICENSE,sha256=3F1-JUTcmjmxMpHGeB77ZzaSdhms3h8p1DBBa3lvV08,1609
-python_hwpx-2.4.dist-info/METADATA,sha256=a4RK1aM71KePp59WUv1K27ZP4MIh_klPRXfxfVr5fuA,12974
-python_hwpx-2.4.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
-python_hwpx-2.4.dist-info/entry_points.txt,sha256=wBO_QZkkQ0FIyAxBhJ08EAtv2SmBnN1xabRHE5G2CyM,60
-python_hwpx-2.4.dist-info/top_level.txt,sha256=R1iToqDh80Nf2oQhRjTN0rbN2X6kyDUizIocZjkhuxc,5
-python_hwpx-2.4.dist-info/RECORD,,
+python_hwpx-2.6.dist-info/licenses/LICENSE,sha256=3F1-JUTcmjmxMpHGeB77ZzaSdhms3h8p1DBBa3lvV08,1609
+python_hwpx-2.6.dist-info/METADATA,sha256=9LDnFWuCNTEqQpF_WMyH7Mm3Ah7uYYnGazGI3C8pE20,12974
+python_hwpx-2.6.dist-info/WHEEL,sha256=YCfwYGOYMi5Jhw2fU4yNgwErybb2IX5PEwBKV4ZbdBo,91
+python_hwpx-2.6.dist-info/entry_points.txt,sha256=KvwTIdfB-3OL8BEAmoiICdfqqndolqiET-zBEgbIyiM,216
+python_hwpx-2.6.dist-info/top_level.txt,sha256=R1iToqDh80Nf2oQhRjTN0rbN2X6kyDUizIocZjkhuxc,5
+python_hwpx-2.6.dist-info/RECORD,,

python_hwpx-2.6.dist-info/entry_points.txt

@@ -0,0 +1,5 @@
+[console_scripts]
+hwpx-page-guard = hwpx.tools.page_guard:main
+hwpx-text-extract = hwpx.tools.text_extract_cli:main
+hwpx-validate = hwpx.tools.validator:main
+hwpx-validate-package = hwpx.tools.package_validator:main

python_hwpx-2.4.dist-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-hwpx-validate = hwpx.tools.validator:main