python-hwpx 2.17.0__py3-none-any.whl → 2.18.0__py3-none-any.whl

hwpx/tools/exporter.py

@@ -14,6 +14,7 @@ from xml.etree import ElementTree as ET
 from zipfile import ZipFile
 
 from ..opc.security import guard_zip_file, parse_xml_stdlib
+from .pii import PIIPolicy, mask_pii
 
 if TYPE_CHECKING:
     from ..document import HwpxDocument
@@ -64,7 +65,18 @@ def _paragraph_text(p: ET.Element, *, tab_token: str = "\t") -> str:
     return "".join(parts)
 
 
-def _table_cells_text(tbl: ET.Element, *, tab_token: str = "\t") -> list[list[str]]:
+def _mask_text(text: str, masking_policy: "PIIPolicy | None") -> str:
+    if masking_policy is None:
+        return text
+    return mask_pii(text, masking_policy)
+
+
+def _table_cells_text(
+    tbl: ET.Element,
+    *,
+    tab_token: str = "\t",
+    masking_policy: "PIIPolicy | None" = None,
+) -> list[list[str]]:
     """Return a row-major 2D list of cell texts from a table element."""
     rows: list[list[str]] = []
     for tr in tbl.findall(f"{_HP}tr"):
@@ -75,7 +87,7 @@ def _table_cells_text(tbl: ET.Element, *, tab_token: str = "\t") -> list[list[st
                 text = _paragraph_text(paragraph, tab_token=tab_token)
                 if text:
                     cell_parts.append(text)
-            row.append("\n".join(cell_parts).strip())
+            row.append(_mask_text("\n".join(cell_parts).strip(), masking_policy))
         rows.append(row)
     return rows
 
@@ -84,19 +96,27 @@ def _find_tables(p: ET.Element) -> list[ET.Element]:
     return p.findall(f".//{_HP}tbl")
 
 
-def export_text(source: HwpxDocument | bytes, *, paragraph_separator: str = "\n", section_separator: str = "\n\n", include_tables: bool = True, tab_token: str = "\t") -> str:
+def export_text(
+    source: HwpxDocument | bytes,
+    *,
+    paragraph_separator: str = "\n",
+    section_separator: str = "\n\n",
+    include_tables: bool = True,
+    tab_token: str = "\t",
+    masking_policy: "PIIPolicy | None" = None,
+) -> str:
     """Export document content as plain text."""
     sections = _section_xmls(source)
     section_texts: list[str] = []
     for section_root in sections:
         para_texts: list[str] = []
         for p in _iter_paragraphs(section_root):
-            text = _paragraph_text(p, tab_token=tab_token)
+            text = _mask_text(_paragraph_text(p, tab_token=tab_token), masking_policy)
             if text:
                 para_texts.append(text)
             if include_tables:
                 for tbl in _find_tables(p):
-                    rows = _table_cells_text(tbl, tab_token=tab_token)
+                    rows = _table_cells_text(tbl, tab_token=tab_token, masking_policy=masking_policy)
                     for row in rows:
                         para_texts.append(tab_token.join(row))
         section_texts.append(paragraph_separator.join(para_texts))
@@ -107,7 +127,15 @@ def _escape_html(text: str) -> str:
     return text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;").replace('"', "&quot;")
 
 
-def export_html(source: HwpxDocument | bytes, *, include_tables: bool = True, full_document: bool = True, title: str = "HWPX Document", tab_token: str = "\t") -> str:
+def export_html(
+    source: HwpxDocument | bytes,
+    *,
+    include_tables: bool = True,
+    full_document: bool = True,
+    title: str = "HWPX Document",
+    tab_token: str = "\t",
+    masking_policy: "PIIPolicy | None" = None,
+) -> str:
     """Export document content as HTML."""
     sections = _section_xmls(source)
     body_parts: list[str] = []
@@ -115,12 +143,12 @@ def export_html(source: HwpxDocument | bytes, *, include_tables: bool = True, fu
         if sec_idx > 0:
             body_parts.append("<hr />")
         for p in _iter_paragraphs(section_root):
-            text = _paragraph_text(p, tab_token=tab_token)
+            text = _mask_text(_paragraph_text(p, tab_token=tab_token), masking_policy)
             if text:
                 body_parts.append(f"<p>{_escape_html(text)}</p>")
             if include_tables:
                 for tbl in _find_tables(p):
-                    rows = _table_cells_text(tbl, tab_token=tab_token)
+                    rows = _table_cells_text(tbl, tab_token=tab_token, masking_policy=masking_policy)
                     if rows:
                         body_parts.append('<table border="1">')
                         for row in rows:
@@ -146,20 +174,27 @@ def export_html(source: HwpxDocument | bytes, *, include_tables: bool = True, fu
     return body
 
 
-def export_markdown(source: HwpxDocument | bytes, *, include_tables: bool = True, section_separator: str = "\n---\n\n", tab_token: str = "\t") -> str:
+def export_markdown(
+    source: HwpxDocument | bytes,
+    *,
+    include_tables: bool = True,
+    section_separator: str = "\n---\n\n",
+    tab_token: str = "\t",
+    masking_policy: "PIIPolicy | None" = None,
+) -> str:
     """Export document content as Markdown."""
     sections = _section_xmls(source)
     section_parts: list[str] = []
     for section_root in sections:
         lines: list[str] = []
         for p in _iter_paragraphs(section_root):
-            text = _paragraph_text(p, tab_token=tab_token)
+            text = _mask_text(_paragraph_text(p, tab_token=tab_token), masking_policy)
             if text:
                 lines.append(text)
                 lines.append("")
             if include_tables:
                 for tbl in _find_tables(p):
-                    rows = _table_cells_text(tbl, tab_token=tab_token)
+                    rows = _table_cells_text(tbl, tab_token=tab_token, masking_policy=masking_policy)
                     if rows:
                         header = rows[0]
                         lines.append("| " + " | ".join(header) + " |")

hwpx/tools/mail_merge.py

@@ -14,6 +14,7 @@ from zipfile import ZIP_DEFLATED, ZipFile
 from ..document import HwpxDocument
 from .exporter import export_text
 from .package_validator import validate_editor_open_safety
+from .pii import DEFAULT_POLICY, PIIPolicy, mask_pii
 
 MAIL_MERGE_REPORT_VERSION = "mail-merge-v1"
 
@@ -180,6 +181,7 @@ def mail_merge(
     split_newlines: bool = True,
     fit_policy: "Any | None" = None,
     max_lines: int = 1,
+    masking_policy: "PIIPolicy | None" = DEFAULT_POLICY,
 ) -> dict[str, Any]:
     """Generate one HWPX per row from a placeholder template.
 
@@ -237,6 +239,7 @@ def mail_merge(
                     "unresolvedPlaceholders": [item["token"] for item in placeholders if item["key"] in missing_keys],
                     "openSafety": None,
                     "fitFields": [],
+                    "maskedFields": [],
                     "reasons": ["missing_required"],
                     "ok": False,
                 }
@@ -247,11 +250,17 @@ def mail_merge(
         row_cells = _iter_cells(document)
         replaced_count = 0
         fit_fields: list[dict[str, Any]] = []
+        masked_fields: list[str] = []
         try:
             for placeholder in placeholders:
                 key = str(placeholder["key"])
                 token = str(placeholder["token"])
                 value = "" if _is_missing(row.get(key)) else str(row.get(key))
+                if masking_policy is not None:
+                    masked_value = mask_pii(value, masking_policy)
+                    if masked_value != value and key not in masked_fields:
+                        masked_fields.append(key)
+                    value = masked_value
                 if not split_newlines:
                     value = value.replace("\r\n", " ").replace("\n", " ")
                 apply_value = value
@@ -287,6 +296,7 @@ def mail_merge(
                 "unresolvedPlaceholders": unresolved,
                 "openSafety": open_safety,
                 "fitFields": fit_fields,
+                "maskedFields": masked_fields,
                 "reasons": reasons,
                 "ok": row_ok,
             }

hwpx/tools/pii.py

@@ -0,0 +1,389 @@
+# SPDX-License-Identifier: Apache-2.0
+"""PII detection, masking, and structural privacy helpers.
+
+The machine-checkable set is intentionally always enabled by default. Contextual
+patterns are label-gated and reported as low-confidence to avoid broad free-text
+over-masking.
+"""
+from __future__ import annotations
+
+import hashlib
+import logging
+import re
+from collections.abc import Iterable, Mapping, Sized
+from dataclasses import dataclass
+from typing import Any, Literal, TypedDict
+
+
+Confidence = Literal["high", "low"]
+
+
+class PIISpan(TypedDict):
+    type: str
+    start: int
+    end: int
+    value: str
+    confidence: Confidence
+
+
+@dataclass(frozen=True)
+class PIIPolicy:
+    """Controls PII detection and masking behavior."""
+
+    mask_char: str = "*"
+    machine_enabled: bool = True
+    contextual_enabled: bool = True
+    prefix_len: int = 1
+    suffix_len: int = 0
+
+    def __post_init__(self) -> None:
+        if len(self.mask_char) != 1:
+            raise ValueError("mask_char must be exactly one character")
+        if self.prefix_len < 0 or self.suffix_len < 0:
+            raise ValueError("prefix_len and suffix_len must be non-negative")
+
+
+DEFAULT_POLICY = PIIPolicy()
+
+__all__ = [
+    "Confidence",
+    "DEFAULT_POLICY",
+    "PIIPolicy",
+    "PIISpan",
+    "PiiLogFilter",
+    "Pseudonymizer",
+    "deidentify",
+    "detect_pii",
+    "mask_pii",
+    "mask_value",
+    "minimize_fields",
+    "scrub_exception_message",
+]
+
+_RRN_RE = re.compile(r"(?<!\d)(?P<front>\d{6})-?(?P<gender>[1-4])(?P<rear>\d{6})(?!\d)")
+_PHONE_RE = re.compile(
+    r"(?<!\d)(?P<prefix>010|011|016|017|018|019)-?(?P<middle>\d{3,4})-?(?P<last>\d{4})(?!\d)"
+)
+_EMAIL_RE = re.compile(
+    r"(?<![A-Za-z0-9.!#$%&'*+/=?^_`{|}~-])"
+    r"(?P<local>[A-Za-z0-9.!#$%&'*+/=?^_`{|}~-]+)"
+    r"@"
+    r"(?P<domain>[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?"
+    r"(?:\.[A-Za-z0-9](?:[A-Za-z0-9-]{0,61}[A-Za-z0-9])?)+)"
+    r"(?![A-Za-z0-9-])"
+)
+_CARD_RE = re.compile(r"(?<!\d)(?:\d{4}[- ]?){3}\d{4}(?!\d)")
+
+_ACCOUNT_RE = re.compile(
+    r"(?:계좌(?:번호)?|통장(?:번호)?)[^\d\n]{0,12}(?P<value>\d[\d-]{8,20}\d)"
+)
+_REGIONS = (
+    "서울특별시",
+    "부산광역시",
+    "대구광역시",
+    "인천광역시",
+    "광주광역시",
+    "대전광역시",
+    "울산광역시",
+    "세종특별자치시",
+    "경기도",
+    "강원도",
+    "충청북도",
+    "충청남도",
+    "전라북도",
+    "전라남도",
+    "경상북도",
+    "경상남도",
+    "제주특별자치도",
+    "서울",
+    "부산",
+    "대구",
+    "인천",
+    "광주",
+    "대전",
+    "울산",
+    "세종",
+    "경기",
+    "강원",
+    "충북",
+    "충남",
+    "전북",
+    "전남",
+    "경북",
+    "경남",
+    "제주",
+)
+_REGION_RE = "|".join(re.escape(region) for region in _REGIONS)
+_ADDRESS_RE = re.compile(
+    rf"(?:주소|도로명주소|소재지|거주지)\s*[:：]?\s*(?P<value>(?:{_REGION_RE})[^\n,;]{{2,80}})"
+)
+_NAME_RE = re.compile(r"(?:성명|수신자|이름)\s*[:：]\s*(?P<value>[가-힣]{2,4})")
+
+_TYPE_ALIASES = {
+    "resident_registration_number": "rrn",
+    "registration_number": "rrn",
+    "jumin": "rrn",
+    "주민등록번호": "rrn",
+    "휴대폰": "phone",
+    "전화번호": "phone",
+    "mobile": "phone",
+    "email_address": "email",
+    "이메일": "email",
+    "card_number": "card",
+    "credit_card": "card",
+    "카드": "card",
+    "account_number": "account",
+    "계좌번호": "account",
+    "계좌": "account",
+    "주소": "address",
+    "이름": "name",
+    "성명": "name",
+    "수신자": "name",
+}
+
+
+def detect_pii(text: str, policy: PIIPolicy = DEFAULT_POLICY) -> list[PIISpan]:
+    """Detect PII spans in ``text`` according to ``policy``."""
+
+    spans: list[PIISpan] = []
+    if not text:
+        return spans
+
+    if policy.machine_enabled:
+        for match in _RRN_RE.finditer(text):
+            spans.append(_span("rrn", match.start(), match.end(), match.group(0), "high"))
+        for match in _PHONE_RE.finditer(text):
+            spans.append(_span("phone", match.start(), match.end(), match.group(0), "high"))
+        for match in _EMAIL_RE.finditer(text):
+            spans.append(_span("email", match.start(), match.end(), match.group(0), "high"))
+        for match in _CARD_RE.finditer(text):
+            value = match.group(0)
+            if _luhn_valid(_digits(value)):
+                spans.append(_span("card", match.start(), match.end(), value, "high"))
+
+    if policy.contextual_enabled:
+        for match in _ACCOUNT_RE.finditer(text):
+            value = match.group("value")
+            digits = _digits(value)
+            if 10 <= len(digits) <= 14:
+                spans.append(_span("account", match.start("value"), match.end("value"), value, "low"))
+        for match in _ADDRESS_RE.finditer(text):
+            value = match.group("value").rstrip()
+            start = match.start("value")
+            spans.append(_span("address", start, start + len(value), value, "low"))
+        for match in _NAME_RE.finditer(text):
+            value = match.group("value")
+            spans.append(_span("name", match.start("value"), match.end("value"), value, "low"))
+
+    return _without_overlaps(spans)
+
+
+def mask_pii(text: str, policy: PIIPolicy = DEFAULT_POLICY) -> str:
+    """Return ``text`` with detected PII spans masked."""
+
+    masked = text
+    for span in sorted(detect_pii(text, policy), key=lambda item: item["start"], reverse=True):
+        start = span["start"]
+        end = span["end"]
+        masked = masked[:start] + mask_value(span["value"], span["type"], policy) + masked[end:]
+    return masked
+
+
+def mask_value(value: str, pii_type: str, policy: PIIPolicy = DEFAULT_POLICY) -> str:
+    """Mask a single known PII value."""
+
+    normalized_type = _normalize_type(pii_type)
+    if normalized_type == "rrn":
+        match = _RRN_RE.fullmatch(value)
+        if match:
+            return f"{match.group('front')}-{match.group('gender')}{policy.mask_char * 6}"
+        digits = _digits(value)
+        if len(digits) == 13 and digits[6] in "1234":
+            return f"{digits[:6]}-{digits[6]}{policy.mask_char * 6}"
+    if normalized_type == "phone":
+        match = _PHONE_RE.fullmatch(value)
+        if match:
+            return f"{match.group('prefix')}-{policy.mask_char * 4}-{policy.mask_char * 4}"
+    if normalized_type == "email":
+        match = _EMAIL_RE.fullmatch(value)
+        if match:
+            return f"{match.group('local')[:1]}{policy.mask_char * 4}@{match.group('domain')}"
+    if normalized_type == "card":
+        digits = _digits(value)
+        if len(digits) == 16:
+            return f"{digits[:4]}-{policy.mask_char * 4}-{policy.mask_char * 4}-{digits[-4:]}"
+    if normalized_type == "account":
+        digits = _digits(value)
+        suffix_len = policy.suffix_len if policy.suffix_len > 0 else 4
+        if len(digits) > suffix_len:
+            return f"{policy.mask_char * 3}-{policy.mask_char * 4}-{digits[-suffix_len:]}"
+    if normalized_type == "name":
+        return _mask_generic(value, policy, suffix_len=0)
+    if normalized_type == "address":
+        return _mask_generic(value, policy, prefix_len=max(policy.prefix_len, 2), suffix_len=0)
+    return _mask_generic(value, policy)
+
+
+def minimize_fields(
+    record: Mapping[str, Any],
+    allowed: Iterable[str],
+    *,
+    drop_empty: bool = False,
+) -> dict[str, Any]:
+    """Return a minimized copy containing only allowed fields.
+
+    Output order follows the order of ``allowed``. Missing fields are skipped.
+    When ``drop_empty`` is true, ``None`` and empty sized values are omitted
+    while falsey scalars such as ``0`` and ``False`` are retained.
+    """
+
+    minimized: dict[str, Any] = {}
+    for key in allowed:
+        if key not in record:
+            continue
+        value = record[key]
+        if drop_empty and _is_empty_value(value):
+            continue
+        minimized[key] = value
+    return minimized
+
+
+class Pseudonymizer:
+    """Deterministic in-memory reversible pseudonym token map.
+
+    ``mapping()`` exposes the value-to-token map. Persisting that map outside
+    this instance makes the pseudonymization reversible; v1 keeps it in memory
+    only.
+    """
+
+    def __init__(self) -> None:
+        self._tokens: dict[str, str] = {}
+        self._counts: dict[str, int] = {}
+
+    def token(self, value: str, *, kind: str = "이름") -> str:
+        """Return a stable token for ``value`` within this instance."""
+
+        if value in self._tokens:
+            return self._tokens[value]
+        count = self._counts.get(kind, 0) + 1
+        self._counts[kind] = count
+        token = f"{kind}_{count:03d}"
+        self._tokens[value] = token
+        return token
+
+    def mapping(self) -> dict[str, str]:
+        """Return a copy of the in-memory value-to-token map."""
+
+        return dict(self._tokens)
+
+
+def deidentify(value: str, *, salt: str, length: int = 12) -> str:
+    """Return an irreversible deterministic salted hash token."""
+
+    digest = hashlib.sha256((salt + "\x00" + value).encode()).hexdigest()
+    return "di_" + digest[:length]
+
+
+class PiiLogFilter(logging.Filter):
+    """Logging filter that masks PII in formatted log messages."""
+
+    def __init__(self, name: str = "", policy: PIIPolicy = DEFAULT_POLICY) -> None:
+        super().__init__(name)
+        self.policy = policy
+
+    def filter(self, record: logging.LogRecord) -> bool:
+        record.msg = _scrub_log_value(record.msg, self.policy)
+        record.args = _scrub_log_value(record.args, self.policy)
+        try:
+            message = record.getMessage()
+        except Exception:
+            message = str(record.msg)
+        masked_message = mask_pii(message, self.policy)
+        record.msg = masked_message
+        record.args = ()
+        return True
+
+
+def scrub_exception_message(msg: str, policy: PIIPolicy = DEFAULT_POLICY) -> str:
+    """Mask PII in an exception message before exposing or logging it."""
+
+    return mask_pii(msg, policy)
+
+
+def _span(kind: str, start: int, end: int, value: str, confidence: Confidence) -> PIISpan:
+    return {"type": kind, "start": start, "end": end, "value": value, "confidence": confidence}
+
+
+def _is_empty_value(value: Any) -> bool:
+    if value is None:
+        return True
+    return isinstance(value, Sized) and len(value) == 0
+
+
+def _scrub_log_value(value: Any, policy: PIIPolicy) -> Any:
+    if isinstance(value, str):
+        return mask_pii(value, policy)
+    if isinstance(value, tuple):
+        return tuple(_scrub_log_value(item, policy) for item in value)
+    if isinstance(value, Mapping):
+        return {key: _scrub_log_value(item, policy) for key, item in value.items()}
+    return value
+
+
+def _normalize_type(pii_type: str) -> str:
+    lowered = pii_type.strip().lower()
+    return _TYPE_ALIASES.get(lowered, lowered)
+
+
+def _digits(value: str) -> str:
+    return "".join(ch for ch in value if ch.isdigit())
+
+
+def _luhn_valid(digits: str) -> bool:
+    if len(digits) != 16 or not digits.isdigit():
+        return False
+    total = 0
+    double = False
+    for char in reversed(digits):
+        value = int(char)
+        if double:
+            value *= 2
+            if value > 9:
+                value -= 9
+        total += value
+        double = not double
+    return total % 10 == 0
+
+
+def _without_overlaps(spans: list[PIISpan]) -> list[PIISpan]:
+    selected: list[PIISpan] = []
+    for span in sorted(spans, key=lambda item: (item["start"], -(item["end"] - item["start"]))):
+        if any(_overlaps(span, existing) for existing in selected):
+            continue
+        selected.append(span)
+    return sorted(selected, key=lambda item: (item["start"], item["end"]))
+
+
+def _overlaps(left: PIISpan, right: PIISpan) -> bool:
+    return left["start"] < right["end"] and right["start"] < left["end"]
+
+
+def _mask_generic(
+    value: str,
+    policy: PIIPolicy,
+    *,
+    prefix_len: int | None = None,
+    suffix_len: int | None = None,
+) -> str:
+    if not value:
+        return value
+    requested_prefix = policy.prefix_len if prefix_len is None else prefix_len
+    requested_suffix = policy.suffix_len if suffix_len is None else suffix_len
+    if len(value) <= requested_prefix + requested_suffix:
+        visible_prefix = min(requested_prefix, max(len(value) - 1, 0))
+        return f"{value[:visible_prefix]}{policy.mask_char * (len(value) - visible_prefix)}"
+    prefix = min(len(value), requested_prefix)
+    suffix = min(len(value) - prefix, requested_suffix)
+    mask_count = len(value) - prefix - suffix
+    suffix_text = value[-suffix:] if suffix else ""
+    return f"{value[:prefix]}{policy.mask_char * mask_count}{suffix_text}"

{python_hwpx-2.17.0.dist-info → python_hwpx-2.18.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-hwpx
-Version: 2.17.0
+Version: 2.18.0
 Summary: 한글 없이 HWPX 문서를 열고, 편집하고, 생성하고, 검증하는 Python 자동화 라이브러리
 Author: python-hwpx Maintainers
 License-Expression: Apache-2.0

{python_hwpx-2.17.0.dist-info → python_hwpx-2.18.0.dist-info}/RECORD

@@ -103,19 +103,20 @@ hwpx/tools/__init__.py,sha256=SntwT_dutXSMyqyXbUK-vmyns91EBoEhqXDfS600C0Y,4120
 hwpx/tools/advanced_generators.py,sha256=ucUNnT2Pkto2jiyCU5_c1abbiskO65WOimgH0l-3Tv0,5164
 hwpx/tools/archive_cli.py,sha256=gkQHuCPUqNGy2S2rKis9NOI1-xZCfwDakF9o8kikPuQ,12775
 hwpx/tools/doc_diff.py,sha256=Yr_MxP9Z1UDmrB7KdL2Bts_nouQ23_WLTSD0yn6Oyu0,12079
-hwpx/tools/exporter.py,sha256=yVBWIEhlsp_Z27X4Y7NKU7_9d6p4Vm0NfFT5tx-_Evg,6686
+hwpx/tools/exporter.py,sha256=QhGgZXfJ5ccTQpfvnKov38io8aQSEUByQ4tPjhRvNso,7373
 hwpx/tools/generic_inventory.py,sha256=pHVP8-htX_vO02ARdQR37XFxm7fUPK68VtMeeOJ1NZY,4835
 hwpx/tools/id_integrity.py,sha256=TBI2WOwbaMbwTGyMv0hEO-uZqyewZtdvawqqA42Tums,14245
 hwpx/tools/idempotence.py,sha256=kRZBWsPJFVprYRJkkxn3DHjrT6qX2nK7KvhmdgJ4JpA,5017
 hwpx/tools/ir_equality.py,sha256=NIjq33-4q7iTo_asv7WUvh_-EfB1JZMTwbLfYIw2c5w,4765
 hwpx/tools/layout_preview.py,sha256=XdKxNL34zVBvFDQv5LFErz1ESuVhkW8jHdyQ1EGbSBU,19857
-hwpx/tools/mail_merge.py,sha256=EXdx7gcG4YrrIb-yFDghWIHpaiFKlZ3h_s2XY7ZMRN4,17932
+hwpx/tools/mail_merge.py,sha256=l3ukaW9noQga0jq_3xWZAdtniBlHHLrSGIGYer0xFW8,18447
 hwpx/tools/markdown_export.py,sha256=FejutCpQHbycO185uljcSwfZuwXMTbGEgXtf5e-a4_k,19139
 hwpx/tools/object_finder.py,sha256=7i6XI1-r7-ar_IzSZQ82hfOcxVzJFK2XjMDB8oxcmMA,13478
 hwpx/tools/official_lint.py,sha256=9iszI4CAAEMGdPCOhmQ6XonO1jc1XE2BJXMHgv9hIvY,18600
 hwpx/tools/package_reconcile.py,sha256=y1Hl7hbPh4YaV59LTdDLzQwgn4g1qEnFmSjmajnrEbA,2416
 hwpx/tools/package_validator.py,sha256=AA5wy6YgwlU6BTq1p2qCbCVCM8lmIBLhPANKCfaPb-s,29369
 hwpx/tools/page_guard.py,sha256=nDAVPcvrnuyDxVTA_j22wiYD7CXAD6XlzsMzaz3h_q8,9701
+hwpx/tools/pii.py,sha256=N3c36eqblaVQ7o6jiT1BV0WrJK_G3gKhQh6MQGAbvCs,12617
 hwpx/tools/recover.py,sha256=EOVAzMFAqR9YAT3sinZKCdjSkKygo4dKrs6T6SbGA7o,4963
 hwpx/tools/redline.py,sha256=p6aMVDBOrkqywlrlxqhB-5ZjCEtgrCNa8cYeRMJlprk,6478
 hwpx/tools/repair.py,sha256=wYO4Zd8ZMwkbYy2_EPz0eyqvTCrzcAyvbEsVE1P87Zk,11197
@@ -146,10 +147,10 @@ hwpx/visual/diff.py,sha256=0X5T9IgwRZU3td-7vnPrlowovtGud7P_ymq0KVehlKk,5677
 hwpx/visual/masks.py,sha256=oXhgynAb4uKjJtZ2BGHHdAjyvWGqSFlZFQ-iJxzHiuo,1832
 hwpx/visual/oracle.py,sha256=QXAyc0xVIjLPWUHM2rBjsustQTmwfoW2Xkb9iX9ai2E,21786
 hwpx/visual/report.py,sha256=2RhXN1KBYOZTim9FNpeUhaaDHR7oFxI6Z2DLUkDIiwE,1717
-python_hwpx-2.17.0.dist-info/licenses/LICENSE,sha256=_ubz4wv-BkkT3l3gu-QuH7JGeVjuRYGZoZK95eNsCHU,9688
-python_hwpx-2.17.0.dist-info/licenses/NOTICE,sha256=k48h6EaGQE8Y1c0dS9sIOOcz4YqkbcImWClF7pBOgsg,2473
-python_hwpx-2.17.0.dist-info/METADATA,sha256=PnLwDDOUcJkC-b4pK-qryUc1p5ru2zbssEpBfhmjaV0,19982
-python_hwpx-2.17.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-python_hwpx-2.17.0.dist-info/entry_points.txt,sha256=4U6WXYWHxEiWp2VRHo97fvOYNh7ebu6roonk7chxKcY,453
-python_hwpx-2.17.0.dist-info/top_level.txt,sha256=R1iToqDh80Nf2oQhRjTN0rbN2X6kyDUizIocZjkhuxc,5
-python_hwpx-2.17.0.dist-info/RECORD,,
+python_hwpx-2.18.0.dist-info/licenses/LICENSE,sha256=_ubz4wv-BkkT3l3gu-QuH7JGeVjuRYGZoZK95eNsCHU,9688
+python_hwpx-2.18.0.dist-info/licenses/NOTICE,sha256=k48h6EaGQE8Y1c0dS9sIOOcz4YqkbcImWClF7pBOgsg,2473
+python_hwpx-2.18.0.dist-info/METADATA,sha256=uHs8_pBm80hLCUNrfs20a6szLITYaWgK-s8UloSmA68,19982
+python_hwpx-2.18.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+python_hwpx-2.18.0.dist-info/entry_points.txt,sha256=4U6WXYWHxEiWp2VRHo97fvOYNh7ebu6roonk7chxKcY,453
+python_hwpx-2.18.0.dist-info/top_level.txt,sha256=R1iToqDh80Nf2oQhRjTN0rbN2X6kyDUizIocZjkhuxc,5
+python_hwpx-2.18.0.dist-info/RECORD,,