C.E.L_Slide_test2/src/region_marker_stamper.py

"""IMP-94 (#94) u1 — region/content marker stamper for Phase Z final.html.

Annotates each rendered family-partial root ``<div>`` with stable
``data-region-id="..."`` and ``data-content-unit-id="..."`` attributes so
downstream Layer A telemetry (placement_trace ↔ DOM parity, Step 21 self-
report, fit_classifier read targets §6.4) can resolve a rendered zone
back to its PlacementPlan ``slot_assignments[]`` entry.

DOM contract (single point of truth — mirrored verbatim across the axis) ::

    <div class="..." data-region-id="{region_id}" data-content-unit-id="{cuid}" ...
         data-frame-id="..." data-template-id="...">

The anchor is the uniform root-div emitted by every Phase Z family
partial under ``templates/phase_z2/families/`` (13 partials, evidence
confirmed via ``grep -l data-template-id`` = 13/13). All 13 partials
carry the pattern::

    <div class="<fNb>" data-frame-id="..." data-template-id="<family>">

The stamper finds the FIRST such opening tag with a permissive regex
and injects ``data-region-id`` + ``data-content-unit-id`` as new
attributes. Existing attributes (class, data-frame-id, data-template-id,
etc.) are preserved verbatim. The injection is idempotent — a zone that
already carries ``data-region-id`` on its root div is left alone.

Source of marker values : ``PlacementPlan.slot_assignments[].region_id``
and ``.content_unit_id`` (see ``src/phase_z2_placement_planner.py``
L253-258). u3 wires the live B4 path; u4 ensures non-live append paths
default to ``placement_markers=[]`` so this stamper safely no-ops.

Forward-compat / safety :
- Empty / None ``markers`` → passthrough (returns ``zone_html`` unchanged).
- Non-str / empty ``zone_html`` → passthrough.
- Re-stamping (idempotent) preserves the first stamp.
- Only the FIRST data-template-id root div is stamped (one per zone).
- Markers with empty / missing ``region_id`` AND ``content_unit_id`` →
  passthrough (no attribute injection).

Guardrails (refs : Stage 1 binding contract, Stage 2 unit u1) :
- AI-isolation : pure deterministic Python; no LLM calls.
- Additive only : never edits / removes existing attributes.
- Idempotent : ``data-region-id`` probe short-circuits before re-inject.
- Disjoint from #96 (``data-frame-slot-id`` is a separate axis / attr).
"""
from __future__ import annotations

import re
from typing import Any, Iterable, Mapping

REGION_ID_ATTR: str = "data-region-id"
CONTENT_UNIT_ID_ATTR: str = "data-content-unit-id"

# Matches the FIRST ``<div ... data-template-id="...">`` opening tag.
# Group 1 captures the inner attribute string verbatim (incl. leading
# whitespace) so the rewriter can re-emit it unchanged after injection.
_ROOT_DIV_TAG_RE = re.compile(
    r'<div\b((?=[^>]*\bdata-template-id\s*=\s*"[^"]+")[^>]*?)>',
    flags=re.IGNORECASE | re.DOTALL,
)
# Probe for an existing ``data-region-id`` attribute (any value, any
# quote) so re-stamping is idempotent.
_HAS_REGION_ID_RE = re.compile(r"""\bdata-region-id\s*=""", flags=re.IGNORECASE)


def _coerce_marker_value(value: Any) -> str:
    """Return a safe attribute-value string for ``value``.

    Non-str / None → ''. Strings are returned verbatim (caller responsible
    for not embedding ``"`` since marker ids derive from
    PlacementPlan.slot_assignments which are deterministic identifiers).
    """
    if value is None:
        return ""
    if not isinstance(value, str):
        return ""
    return value


def stamp_zone_html(
    zone_html: str,
    markers: Iterable[Mapping[str, Any]] | None,
) -> str:
    """Stamp the root family-partial ``<div>`` with region / content-unit ids.

    ``markers`` is an iterable of mapping objects shaped as ::

        {
          "region_id": "<region_id>",
          "content_unit_id": "<content_unit_id>",
          # optional, ignored here — reserved for #96 (89-d):
          "frame_slot_id": "<frame_slot_id>",
        }

    Only ``markers[0]`` is consumed (one root div per zone). Excess
    markers are reserved for a future per-slot stamper (#96) and are
    silently ignored by this module.

    Returns ``zone_html`` unchanged when:
      - ``zone_html`` is not a non-empty string,
      - ``markers`` is None / empty,
      - no ``data-template-id`` root div is found,
      - the root div already carries ``data-region-id`` (idempotent),
      - the first marker carries neither ``region_id`` nor ``content_unit_id``.
    """
    if not isinstance(zone_html, str) or not zone_html:
        return zone_html
    if markers is None:
        return zone_html
    marker_list = list(markers)
    if not marker_list:
        return zone_html
    first = marker_list[0]
    if not isinstance(first, Mapping):
        return zone_html
    region_id = _coerce_marker_value(first.get("region_id"))
    content_unit_id = _coerce_marker_value(first.get("content_unit_id"))
    if not region_id and not content_unit_id:
        return zone_html

    stamped = {"done": False}

    def _replace(match: re.Match[str]) -> str:
        if stamped["done"]:
            return match.group(0)
        attrs = match.group(1) or ""
        if _HAS_REGION_ID_RE.search(attrs):
            stamped["done"] = True
            return match.group(0)
        stamped["done"] = True
        injected = (
            f' {REGION_ID_ATTR}="{region_id}"'
            f' {CONTENT_UNIT_ID_ATTR}="{content_unit_id}"'
        )
        return f"<div{injected}{attrs}>"

    return _ROOT_DIV_TAG_RE.sub(_replace, zone_html, count=1)