Extract formatter input parsing policy

sdxl_formatter.py

@@ -1,13 +1,14 @@
 from __future__ import annotations
 
-import json
 import re
 from typing import Any
 
 try:
+    from . import formatter_input as input_policy
     from .hardcore_action_metadata import normalize_hardcore_action_family
     from .prompt_hygiene import sanitize_negative_text, sanitize_tag_prompt
 except ImportError:  # Allows local smoke tests with `python -c`.
+    import formatter_input as input_policy
     from hardcore_action_metadata import normalize_hardcore_action_family
     from prompt_hygiene import sanitize_negative_text, sanitize_tag_prompt
 
@@ -95,74 +96,31 @@ def sdxl_quality_preset_choices() -> list[str]:
 
 
 def _clean(value: Any) -> str:
-    text = "" if value is None else str(value)
-    text = text.replace("\n", " ")
-    text = re.sub(r"\s+", " ", text).strip()
-    text = re.sub(r"\s+([,.;:])", r"\1", text)
-    return text
+    return input_policy.clean_text(value)
 
 
 def _maybe_json(text: str) -> dict[str, Any] | None:
-    text = _clean(text)
-    if not text.startswith("{"):
-        return None
-    try:
-        value = json.loads(text)
-    except json.JSONDecodeError:
-        return None
-    return value if isinstance(value, dict) else None
+    return input_policy.maybe_json(text)
 
 
 def _row_from_inputs(source_text: str, metadata_json: str, input_hint: str) -> tuple[dict[str, Any] | None, str]:
-    if input_hint in ("auto", "metadata_json"):
-        for text, method in ((metadata_json, "metadata_json"), (source_text, "source_json")):
-            row = _maybe_json(text)
-            if row is not None:
-                return row, method
-    return None, "text"
+    return input_policy.row_from_inputs(source_text, metadata_json, input_hint)
 
 
 def _strip_trigger(text: str, preserve_trigger: bool) -> str:
-    text = _clean(text)
-    if preserve_trigger:
-        return text
-    for trigger in TRIGGER_CANDIDATES:
-        if text.lower().startswith(trigger.lower() + ","):
-            return text[len(trigger) + 1 :].strip(" ,")
-        if text.lower().startswith(trigger.lower() + "."):
-            return text[len(trigger) + 1 :].strip(" ,")
-    return text
+    return input_policy.strip_trigger_prefix(text, TRIGGER_CANDIDATES, preserve_trigger=preserve_trigger)
 
 
 def _split_avoid(text: str) -> tuple[str, str]:
-    match = re.search(r"\bAvoid:\s*(.*)$", text)
-    if not match:
-        return text, ""
-    return text[: match.start()].strip(" ."), match.group(1).strip(" .")
+    return input_policy.split_avoid(text)
 
 
 def _prompt_field(text: str, label: str) -> str:
-    text = _clean(text)
-    if not text:
-        return ""
-    labels = "|".join(re.escape(name) for name in PROMPT_FIELD_LABELS)
-    pattern = rf"{re.escape(label)}:\s*(.*?)(?=\. (?:{labels}):|\. Use\b|\. Avoid\b|$)"
-    match = re.search(pattern, text)
-    if not match:
-        return ""
-    return _clean(match.group(1)).rstrip(".")
+    return input_policy.prompt_field(text, label, field_labels=PROMPT_FIELD_LABELS)
 
 
 def _row_value(row: dict[str, Any], key: str, labels: tuple[str, ...] = ()) -> str:
-    value = _clean(row.get(key, ""))
-    if value:
-        return value
-    prompt = _clean(row.get("prompt", ""))
-    for label in labels:
-        value = _prompt_field(prompt, label)
-        if value:
-            return value
-    return ""
+    return input_policy.row_value(row, key, labels, field_labels=PROMPT_FIELD_LABELS)
 
 
 def _split_tag_text(text: Any) -> list[str]: