Allow signaling issues in label verification

copienator/copy_errors.py

@@ -1,4 +1,4 @@
-"""Persistent copy flags shared by page splitting, margin review and the GUI."""
+"""Persistent per-step copy flags shared by repair commands and the GUI."""
 from pathlib import Path
 
 from copienator import CliError, EvaluationWorkspace, atomic_update_json, read_json
@@ -8,31 +8,57 @@ def _path(workspace: EvaluationWorkspace) -> Path:
     return workspace.metadata_dir / "copy_errors.json"
 
 
-def _validate(value) -> dict[str, str]:
-    if not isinstance(value, dict) or any(
-        not isinstance(name, str) or not isinstance(reason, str)
-        or "/" in name or "\\" in name or Path(name).suffix.casefold() != ".pdf"
-        for name, reason in value.items()
-    ):
-        raise CliError("Invalid copy_errors.json: expected PDF filenames and error descriptions")
-    return value
+def _validate(value) -> dict[str, dict[str, str]]:
+    if not isinstance(value, dict):
+        raise CliError("Invalid copy_errors.json: expected PDF filenames and step flags")
+    normalized = {}
+    for name, flags in value.items():
+        if (not isinstance(name, str) or "/" in name or "\\" in name
+                or Path(name).suffix.casefold() != ".pdf"):
+            raise CliError("Invalid copy_errors.json: invalid PDF filename")
+        # Older versions only reported errors from margin cropping.
+        if isinstance(flags, str):
+            flags = {"cutleft": flags}
+        if (not isinstance(flags, dict) or not flags
+                or any(step not in {"cutleft", "plotting"} or not isinstance(reason, str)
+                       for step, reason in flags.items())):
+            raise CliError("Invalid copy_errors.json: invalid step flags")
+        normalized[name] = dict(flags)
+    return normalized
 
 
 def copy_errors(workspace: EvaluationWorkspace) -> dict[str, str]:
-    return _validate(read_json(_path(workspace), default={}))
+    """Return a summary per copy, preserving the existing GUI-facing API."""
+    flags = _validate(read_json(_path(workspace), default={}))
+    return {name: "; ".join(reasons.values()) for name, reasons in flags.items()}
 
 
-def mark_copy_error(workspace: EvaluationWorkspace, pdf: Path, reason: str) -> None:
+def mark_copy_error(workspace: EvaluationWorkspace, pdf: Path, reason: str,
+                    *, source: str = "cutleft") -> None:
+    if source not in {"cutleft", "plotting"}:
+        raise ValueError(f"Unknown copy flag source: {source}")
     def update(errors):
-        _validate(errors)[pdf.name] = reason
+        normalized = _validate(errors)
+        normalized.setdefault(pdf.name, {})[source] = reason
+        errors.clear()
+        errors.update(normalized)
     atomic_update_json(_path(workspace), update, default_factory=dict)
 
 
-def clear_copy_error(workspace: EvaluationWorkspace, pdf: Path) -> None:
+def clear_copy_error(workspace: EvaluationWorkspace, pdf: Path,
+                     *, source: str = "cutleft") -> None:
+    if source not in {"cutleft", "plotting"}:
+        raise ValueError(f"Unknown copy flag source: {source}")
     if not _path(workspace).exists():
         return
     def update(errors):
-        _validate(errors).pop(pdf.name, None)
+        normalized = _validate(errors)
+        flags = normalized.get(pdf.name, {})
+        flags.pop(source, None)
+        if not flags:
+            normalized.pop(pdf.name, None)
+        errors.clear()
+        errors.update(normalized)
     atomic_update_json(_path(workspace), update, default_factory=dict)