"""Confidence-based [unleserlich] marker insertion for OCR output."""

import os

CONFIDENCE_THRESHOLD = float(os.environ.get("OCR_CONFIDENCE_THRESHOLD", "0.3"))

ILLEGIBLE_MARKER = "[unleserlich]"


def apply_confidence_markers(words: list[dict]) -> str:
    """Replace low-confidence words with [unleserlich], collapsing adjacent markers.

    Args:
        words: list of {"text": str, "confidence": float} dicts

    Returns:
        Reconstructed text string with [unleserlich] substitutions.
    """
    if not words:
        return ""

    result: list[str] = []
    prev_was_marker = False

    for word in words:
        if word["confidence"] < CONFIDENCE_THRESHOLD:
            if not prev_was_marker:
                result.append(ILLEGIBLE_MARKER)
            prev_was_marker = True
        else:
            result.append(word["text"])
            prev_was_marker = False

    return " ".join(result)


def words_from_characters(prediction: str, confidences: list[float]) -> list[dict]:
    """Reconstruct word-level confidence from character-level data.

    Splits prediction on whitespace, maps characters to their confidences,
    computes mean confidence per word.

    Args:
        prediction: full line text from Kraken
        confidences: per-character confidence list (same length as prediction)

    Returns:
        list of {"text": str, "confidence": float} dicts
    """
    if not prediction or not prediction.strip():
        return []

    if len(confidences) != len(prediction):
        return [{"text": prediction, "confidence": 1.0}]

    result: list[dict] = []
    current_word: list[str] = []
    current_confs: list[float] = []

    for char, conf in zip(prediction, confidences):
        if char == " ":
            if current_word:
                result.append({
                    "text": "".join(current_word),
                    "confidence": sum(current_confs) / len(current_confs),
                })
                current_word = []
                current_confs = []
        else:
            current_word.append(char)
            current_confs.append(conf)

    if current_word:
        result.append({
            "text": "".join(current_word),
            "confidence": sum(current_confs) / len(current_confs),
        })

    return result