updated our verify logic

fccs_config.py

@@ -157,3 +157,135 @@ def check_for_clashes(drawer_ids):
         if matches:
             clashes.append((short, matches))
     return clashes
+
+
+# ---------------------------------------------------------------------------
+# MANIFEST / EXPORT-COMPLETENESS HELPERS
+# ---------------------------------------------------------------------------
+# Shared by fccs_verify.py (batch) and fccs_check.py (interactive) so both
+# judge completeness identically.
+
+# Trailing " Page N" (optionally "Page N of M") appended to multi-page exports.
+_PAGE_RE = re.compile(r"\s*Page\s+\d+(?:\s+of\s+\d+)?\s*$", re.IGNORECASE)
+# Creation-date field ("_MM-DD-YYYY_") that precedes the document name.
+_DATE_ANCHOR = re.compile(r"_\d{2}-\d{2}-\d{4}_")
+
+
+def load_manifest(path):
+    """Load a manifest file and return one row (list of cells) per document.
+
+    Handles both formats:
+      - New: one document per line (tab-separated columns).
+      - Old: a raw ListView dump led by 'List1', then row-major cells with
+        3 columns per document (Drawer ID, Page Title, Application), reshaped
+        so the document count is correct.
+    """
+    with open(path, "r", encoding="utf-8") as f:
+        lines = [line.rstrip("\n") for line in f if line.strip()]
+
+    if lines and lines[0].strip() == "List1":
+        cells = lines[1:]
+        rows = [cells[i:i + 3] for i in range(0, len(cells), 3)]
+        return [r for r in rows if len(r) == 3]
+
+    return [line.split("\t") for line in lines]
+
+
+def manifest_doc_names(path, drawer_id):
+    """Return the expected document (Page Title) names from a manifest file."""
+    rows = load_manifest(path)
+    names = []
+    for row in rows:
+        if len(row) >= 3 and row[0].strip() == drawer_id:
+            names.append(row[1])   # old format: DrawerID, PageTitle, Application
+        elif row:
+            names.append(row[0])   # new format: PageTitle, Application
+    return names
+
+
+def match_key(name):
+    """Normalize a document name for tolerant comparison.
+
+    Strips a trailing 'Page N' page-split suffix, then reduces to lowercase
+    alphanumerics so punctuation and filename-sanitization differences (FCCS
+    strips characters illegal in Windows filenames) don't cause false
+    mismatches.
+    """
+    base = _PAGE_RE.sub("", name)
+    return re.sub(r"[^a-z0-9]+", "", base.lower())
+
+
+def exported_doc_name(filename):
+    """Extract the document-name portion from an exported filename, or None.
+
+    Format: {drawer}_{client}_{folder}_{MM-DD-YYYY}_{docname}.ext
+    The creation-date field is a reliable anchor; the doc name follows the last
+    one (client/folder fields don't carry an "_MM-DD-YYYY_" pattern).
+    """
+    stem = os.path.splitext(filename)[0]
+    anchors = list(_DATE_ANCHOR.finditer(stem))
+    if not anchors:
+        return None
+    return stem[anchors[-1].end():]
+
+
+def index_files_by_drawer(export_dir):
+    """Map each export file to its leading drawer-ID token (before first '_').
+
+    The underscore boundary keeps clashing IDs separate (04289 vs 04289TS).
+    Returns {drawer_id: [filenames]}.
+    """
+    index = {}
+    for f in os.listdir(export_dir):
+        if not os.path.isfile(os.path.join(export_dir, f)):
+            continue
+        token = f.split("_", 1)[0]
+        index.setdefault(token, []).append(f)
+    return index
+
+
+def evaluate_drawer(drawer_id, files, manifest_dir):
+    """Compare a drawer's manifest against its exported files.
+
+    `files` is the list of export filenames belonging to this drawer. Accounts
+    for page-splitting (a document exported as 'Name Page 1/2/...' counts as
+    present) and filename sanitization (via match_key).
+
+    Returns a dict:
+      has_manifest, manifest_path, expected (list), missing (list),
+      extras (list), unparsed (int), file_count (int)
+    """
+    manifest_path = os.path.join(manifest_dir, drawer_id + ".txt")
+    result = {
+        "has_manifest": os.path.exists(manifest_path),
+        "manifest_path": manifest_path,
+        "expected": [],
+        "missing": [],
+        "extras": [],
+        "unparsed": 0,
+        "file_count": len(files),
+    }
+    if not result["has_manifest"]:
+        return result
+
+    expected = manifest_doc_names(manifest_path, drawer_id)
+    result["expected"] = expected
+
+    # Group exported files by normalized doc name; page-splits collapse together.
+    exported = {}      # key -> list of full doc names (one entry per file/page)
+    unparsed = 0
+    for f in files:
+        doc = exported_doc_name(f)
+        if doc is None:
+            unparsed += 1
+            continue
+        exported.setdefault(match_key(doc), []).append(doc)
+
+    result["missing"] = [name for name in expected
+                         if match_key(name) not in exported]
+
+    expected_keys = {match_key(n) for n in expected}
+    result["extras"] = [names[0] for k, names in exported.items()
+                        if k not in expected_keys]
+    result["unparsed"] = unparsed
+    return result