Extract formatter input parsing policy

caption_naturalizer.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_prose_text
 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_prose_text
 
@@ -71,11 +72,7 @@ POSITION_FAMILY_CAPTION_LABELS = {
 
 
 def _clean_text(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 _is_false(value: Any) -> bool:
@@ -189,18 +186,11 @@ def _strip_style_tail(text: str) -> str:
 
 
 def _remove_trigger(text: str, trigger: str) -> str:
-    text = _clean_text(text).strip(" ,")
-    for candidate in (trigger, OLD_TRIGGER, DEFAULT_TRIGGER):
-        candidate = candidate.strip()
-        if not candidate:
-            continue
-        if text.lower().startswith(candidate.lower() + ","):
-            return text[len(candidate) + 1 :].strip(" ,")
-        if text.lower().startswith(candidate.lower() + "."):
-            return text[len(candidate) + 1 :].strip(" ,")
-        if text.lower() == candidate.lower():
-            return ""
-    return text
+    return input_policy.strip_trigger_prefix(
+        text,
+        (trigger, OLD_TRIGGER, DEFAULT_TRIGGER),
+        remove_exact=True,
+    )
 
 
 def _with_trigger(text: str, trigger: str, include_trigger: bool) -> str:
@@ -214,55 +204,24 @@ def _with_trigger(text: str, trigger: str, include_trigger: bool) -> str:
 
 
 def _maybe_json(text: str) -> dict[str, Any] | None:
-    text = _clean_text(text)
-    if not text or 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]:
-    candidates: list[tuple[str, str]] = []
-    if input_hint in ("auto", "metadata_json"):
-        candidates.append((metadata_json, "metadata_json"))
-        candidates.append((source_text, "source_json"))
-    for text, method in candidates:
-        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 _prompt_field(text: str, label: str) -> str:
-    text = _clean_text(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_text(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_text(row.get(key, ""))
-    if value:
-        return value
-    prompt = _clean_text(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 _field_from_any_prompt(text: str, labels: tuple[str, ...]) -> str:
     for label in labels:
-        value = _prompt_field(text, label)
+        value = input_policy.prompt_field(text, label, field_labels=PROMPT_FIELD_LABELS)
         if value:
             return value
     return ""