feat: tableurs indexables, saisie typée et valeurs calculées #153

Les tableurs étaient invisibles à la recherche, chaque saisie devenait
du texte, et une formule n'affichait que sa formule.

- A5 : extract_indexable_text() indexe les noms de feuilles et les 20
  premières lignes (plafond 5 k caractères) pour le TF-IDF et la
  recherche sémantique. Un mot tapé dans une cellule rend le fichier
  trouvable ; un classeur chiffré s'indexe par son seul nom.
- A10 : la saisie est typée comme dans Excel — booléens
  (TRUE/FAUX/OUI/NON) et dates FR JJ/MM/AAAA en ordre jour-first, donc
  01/02/2026 est le 1er février. Une saisie ressemblant à une formule
  n'est jamais convertie (BUG-088 préservé).
- A12 : la valeur calculée par Excel s'affiche sous la formule, via une
  2e lecture data_only=True faite seulement si l'archive contient un
  <v>. Info-bulle traduite FR/EN, aucun texte d'interface côté backend.
- BUG-089 : un reindex manuel ne reconstruisait pas l'index inversé, et
  backend/search.py lisait l'index via un import par valeur — après un
  rechargement du module, la recherche écrivait dans un dict périmé.

Contre-preuves vérifiées pour A5, A10 et A12 (neutralisation de chaque
fonction → échec des tests concernés). Tests : 1402 pytest, 10 JSDOM,
4 E2E, suite E2E complète verte, ruff/mypy 0.

🤖 Generated with Codebuff
Co-Authored-By: Codebuff <[email protected]>

backend/xlsx_reader.py

@@ -11,6 +11,7 @@ round-trip would drop (#153 A1) so the UI can warn before saving.
 from __future__ import annotations
 
 import html
+import logging
 import re
 import zipfile
 from datetime import date, datetime
@@ -20,6 +21,8 @@ from typing import Any
 from openpyxl import load_workbook
 from openpyxl.utils import get_column_letter
 
+logger = logging.getLogger("obsigate.xlsx_reader")
+
 # ponytail: hard caps bound the rendered grid (500 rows x 40 cols per sheet).
 # Raise them, or paginate per sheet, if a real workbook needs more.
 MAX_ROWS = 500
@@ -48,6 +51,14 @@ _CACHED_FORMULA_RE = re.compile(rb"<f[ >][^<]*</f>\s*<v>[^<]")
 # Sheet XML scanned by the cached-formula probe (CPU guard, like MAX_REPLACE_FILE_BYTES).
 _MAX_PROBE_BYTES = 8_000_000
 
+# #153 A5 — ceiling on the text handed to the TF-IDF / semantic index. A workbook
+# is a data dump, not prose: indexing every cell would flood the inverted index
+# and bury the notes. Sheet names + the first rows are enough to make a
+# spreadsheet findable by its headers.
+MAX_INDEX_CHARS = 5_000
+_INDEX_ROWS_PER_SHEET = 20
+MAX_INDEX_SHEETS = 20
+
 
 def _fmt(value: Any) -> str:
     if value is None:
@@ -74,7 +85,29 @@ def _trim(grid: list[list[str]]) -> list[list[str]]:
     return [row[:width] for row in grid]
 
 
-def _table(grid: list[list[str]]) -> str:
+def _cell_cached(cached: list[list[str]] | None, r: int, c: int) -> str:
+    """Return the cached result for a 0-based cell, or ``""``.
+
+    The shadow grid is read positionally and may be narrower than the formula
+    grid (``_trim`` collapses the trailing empty columns of each grid
+    independently), so every lookup is bounds-checked rather than assumed.
+    """
+    if not cached or r >= len(cached):
+        return ""
+    row = cached[r]
+    return row[c] if c < len(row) else ""
+
+
+def _table(grid: list[list[str]], cached: list[list[str]] | None = None) -> str:
+    """Render a grid as an HTML table.
+
+    ``cached`` is the same grid read with ``data_only=True`` (#153 A12): where a
+    formula cell still carries its last computed result, it is shown as a
+    discreet second line (``<span class="xlsx-cached">``) so the user sees the
+    number Excel last calculated instead of only the formula text. The span
+    carries ``data-cached-value`` and is titled client-side from
+    ``xlsx.cached_value_title`` — the backend never emits UI text.
+    """
     if not grid:
         return "<p><em>Feuille vide</em></p>"
     n_cols = max(len(row) for row in grid)
@@ -90,7 +123,24 @@ def _table(grid: list[list[str]]) -> str:
         out.append(f'<tr><th class="xlsx-rownum">{r}</th>')
         for c, val in enumerate(row, start=1):
             ref = f"{get_column_letter(c)}{r}"
-            out.append(f'<td data-cell="{ref}">{html.escape(val)}</td>')
+            # The cached result only makes sense for a formula cell: on a plain
+            # value cell the two reads are identical and showing both would
+            # duplicate the text.
+            shadow = ""
+            if cached is not None and val.startswith("="):
+                # `c` is 1-based (A1 notation) and `r` too, while the grid is
+                # 0-based: translate both.
+                cval = _cell_cached(cached, r - 1, c - 1)
+                if cval and cval != val:
+                    # The tooltip is translated client-side from
+                    # `xlsx.cached_value_title`; never hardcode UI text here.
+                    shadow = (
+                        f'<span class="xlsx-cached" data-cached-value="1">'
+                        f"{html.escape(cval)}</span>"
+                    )
+            out.append(
+                f'<td data-cell="{ref}">{html.escape(val)}{shadow}</td>'
+            )
         out.append("</tr>")
     out.append("</tbody></table></div>")
     return "".join(out)
@@ -142,18 +192,118 @@ def inspect_workbook(file_path: Path) -> list[str]:
 
 
 def render_sheets(file_path: Path) -> list[dict[str, str]]:
-    """Return ``[{"name": sheet_title, "html": table_html}, ...]``."""
+    """Return ``[{"name": sheet_title, "html": table_html}, ...]``.
+
+    Reads the workbook twice: once with ``data_only=False`` for the formulas
+    (what the user must edit) and, when any formula carries a cached result
+    (#153 A12), once with ``data_only=True`` to show what Excel last computed.
+    The second pass is skipped entirely when the archive holds no cached value,
+    so the common case still costs a single load.
+    """
     wb = load_workbook(str(file_path), read_only=True, data_only=False)
     try:
-        sheets = []
-        for ws in wb.worksheets:
-            grid = [
-                [_fmt(v) for v in row]
-                for row in ws.iter_rows(
-                    min_row=1, max_row=MAX_ROWS, max_col=MAX_COLS, values_only=True
-                )
-            ]
-            sheets.append({"name": ws.title, "html": _table(_trim(grid))})
-        return sheets
+        formulas = [_sheet_grid(ws) for ws in wb.worksheets]
+        titles = [ws.title for ws in wb.worksheets]
     finally:
         wb.close()
+
+    cached: list[list[list[str]]] | None = None
+    if _has_cached_values(file_path):
+        cached = _read_cached_grids(file_path, titles)
+
+    sheets = []
+    for i, title in enumerate(titles):
+        grid = _trim(formulas[i])
+        # The shadow grid is NOT trimmed independently: _trim drops the
+        # trailing empty columns of each grid on its own width, which would
+        # shift every cached value left of its formula. Indexing it
+        # positionally against the untrimmed grid keeps the two aligned.
+        shadow = cached[i] if cached is not None and i < len(cached) else None
+        sheets.append({"name": title, "html": _table(grid, shadow)})
+    return sheets
+
+
+def _sheet_grid(ws: Any) -> list[list[str]]:
+    """Read one worksheet into a grid of formatted strings, bounded by the caps."""
+    return [
+        [_fmt(v) for v in row]
+        for row in ws.iter_rows(
+            min_row=1, max_row=MAX_ROWS, max_col=MAX_COLS, values_only=True
+        )
+    ]
+
+
+def _has_cached_values(file_path: Path) -> bool:
+    """True when the archive holds at least one ``<f>…</f><v>…</v>``."""
+    try:
+        with zipfile.ZipFile(file_path) as zf:
+            return _has_cached_formulas(zf)
+    except (OSError, zipfile.BadZipFile):
+        return False
+
+
+def _read_cached_grids(
+    file_path: Path, titles: list[str]
+) -> list[list[list[str]]] | None:
+    """Read every sheet with ``data_only=True`` (what Excel last computed).
+
+    Best effort: returns ``None`` on any failure so the viewer falls back to the
+    formula-only rendering. A workbook Excel opens but openpyxl cannot re-read
+    must still display.
+    """
+    try:
+        wb = load_workbook(str(file_path), read_only=True, data_only=True)
+    except Exception:
+        return None
+    try:
+        grids = [_sheet_grid(ws) for ws in wb.worksheets]
+        if [ws.title for ws in wb.worksheets] != titles:
+            return None
+        return grids
+    except Exception:
+        logger.debug("xlsx cached values unavailable", exc_info=True)
+        return None
+    finally:
+        wb.close()
+
+
+def extract_indexable_text(file_path: Path) -> str:
+    """Return searchable text for the TF-IDF / semantic index (#153 A5).
+
+    Sheet names plus the first :data:`_INDEX_ROWS_PER_SHEET` rows of each
+    sheet, capped at :data:`MAX_INDEX_CHARS`. Rows are tab-joined so a search
+    for a header matches the sheet it belongs to.
+
+    Never raises: a corrupt, encrypted or unsupported workbook yields ``""`` so
+    the file still gets indexed by name (same contract as :func:`inspect_workbook`).
+    """
+    chunks: list[str] = []
+    budget = MAX_INDEX_CHARS
+    try:
+        wb = load_workbook(str(file_path), read_only=True, data_only=True)
+    except Exception:
+        # Encrypted (BadZipFile) or not a real workbook: name-only indexing.
+        return ""
+    try:
+        for ws in wb.worksheets[:MAX_INDEX_SHEETS]:
+            if budget <= 0:
+                break
+            # The sheet title alone is a strong signal ("Recettes", "Budget").
+            block = [ws.title]
+            for row in ws.iter_rows(
+                min_row=1, max_row=_INDEX_ROWS_PER_SHEET, max_col=MAX_COLS, values_only=True
+            ):
+                cells = [_fmt(v) for v in row]
+                # Skip blank rows instead of emitting runs of tabs.
+                if not any(c.strip() for c in cells):
+                    continue
+                block.append("\t".join(cells).rstrip())
+            text = "\n".join(block)
+            chunks.append(text[:budget])
+            budget -= len(text)
+    except Exception:
+        # Truncated but still useful: keep whatever was collected.
+        pass
+    finally:
+        wb.close()
+    return "\n".join(c for c in chunks if c).strip()