from OCRBase.text_recognition import ocr_predict
import cv2
from shapely.geometry import Polygon
import urllib
import numpy as np

def check_percent_overlap_bbox(boxA, boxB):
    """check percent box A in boxB

    Args:
        boxA (_type_): _description_
        boxB (_type_): _description_

    Returns:
        Float: percent overlap bbox
    """
    # determine the (x, y)-coordinates of the intersection rectangle
    box_shape_1 = [
        [boxA[0], boxA[1]],
        [boxA[2], boxA[1]],
        [boxA[2], boxA[3]],
        [boxA[0], boxA[3]],
    ]

    # Give dimensions of shape 2
    box_shape_2 = [
        [boxB[0], boxB[1]],
        [boxB[2], boxB[1]],
        [boxB[2], boxB[3]],
        [boxB[0], boxB[3]],
    ]
    # Draw polygon 1 from shape 1
    # dimensions
    polygon_1 = Polygon(box_shape_1)

    # Draw polygon 2 from shape 2
    # dimensions
    polygon_2 = Polygon(box_shape_2)

    # Calculate the intersection of
    # bounding boxes
    intersect = polygon_1.intersection(polygon_2).area / polygon_1.area

    return intersect


def check_box_in_box(boxA, boxB):
    """check boxA in boxB

    Args:
        boxA (_type_): _description_
        boxB (_type_): _description_

    Returns:
        Boolean: True if boxA in boxB
    """
    if (
        boxA[0] >= boxB[0]
        and boxA[1] >= boxB[1]
        and boxA[2] <= boxB[2]
        and boxA[3] <= boxB[3]
    ):
        return True
    else:
        return False


def word_to_line_image_origin(list_words, bbox):
    """use for predict image with bbox selected

    Args:
        list_words (_type_): _description_
        bbox (_type_): _description_

    Returns:
        _type_: _description_
    """
    texts, boundingboxes = [], []
    for line in list_words:
        if line.text == "":
            continue
        else:
            # convert to bbox image original
            boundingbox = line.boundingbox
            boundingbox = list(boundingbox)
            boundingbox[0] = boundingbox[0] + bbox[0]
            boundingbox[1] = boundingbox[1] + bbox[1]
            boundingbox[2] = boundingbox[2] + bbox[0]
            boundingbox[3] = boundingbox[3] + bbox[1]
            texts.append(line.text)
            boundingboxes.append(boundingbox)
    return texts, boundingboxes


def word_to_line(list_words):
    """use for predict full image

    Args:
        list_words (_type_): _description_
    """
    texts, boundingboxes = [], []
    for line in list_words:
        if line.text == "":
            continue
        else:
            boundingbox = line.boundingbox
            boundingbox = list(boundingbox)
            texts.append(line.text)
            boundingboxes.append(boundingbox)
    return texts, boundingboxes


def predict(page_numb, image_url):
    """predict text from image

    Args:
        image_path (String): path image to predict
        list_id (List): List id of bbox selected
        list_bbox (List): List bbox selected

    Returns:
        Dict: Dict result of prediction
    """
    
    req = urllib.request.urlopen(image_url)
    arr = np.asarray(bytearray(req.read()), dtype=np.uint8)
    image = cv2.imdecode(arr, -1)
    list_lines = ocr_predict(image)
    texts, boundingboxes = word_to_line(list_lines)
    result = {}
    texts_replace = []
    for text in texts:
        if "✪" in text:
            text = text.replace("✪", " ")
            texts_replace.append(text)
        else:
            texts_replace.append(text)
    result["texts"] = texts_replace
    result["boundingboxes"] = boundingboxes
    
    output_dict = {
        "document_type": "ocr-base",
        "fields": []
    }
    field = {
        "label": "Text",
        "value": result["texts"],
        "box": result["boundingboxes"],
        "confidence": 0.98,
        "page": page_numb
    }
    output_dict['fields'].append(field)
    
    return output_dict