import xml.etree.ElementTree as ET
import os
import numpy as np
import glob

# classes = (
#             '__background__',  # always index 0
#             'balloon')
# class_to_ind = dict(
#             list(zip(classes, list(range(len(classes))))))

def parse_rec(filename):
    """ Parse a PASCAL VOC xml file """
    tree = ET.parse(filename)
    objects = []
    for obj in tree.findall('object'):
        obj_struct = {}
        obj_struct['name'] = obj.find('name').text
        # obj_struct['pose'] = obj.find('pose').text
        # obj_struct['truncated'] = int(obj.find('truncated').text)
        obj_struct['difficult'] = int(obj.find('difficult').text)
        bbox = obj.find('bndbox')
        obj_struct['bbox'] = [
            float(bbox.find('xmin').text),
            float(bbox.find('ymin').text),
            float(bbox.find('xmax').text),
            float(bbox.find('ymax').text)
        ]
        objects.append(obj_struct)

    return objects


def voc_ap(rec, prec, use_07_metric=False):
    """ ap = voc_ap(rec, prec, [use_07_metric])
  Compute VOC AP given precision and recall.
  If use_07_metric is true, uses the
  VOC 07 11 point method (default:False).
  """
    if use_07_metric:
        # 11 point metric
        ap = 0.
        for t in np.arange(0., 1.1, 0.1):
            if np.sum(rec >= t) == 0:
                p = 0
            else:
                p = np.max(prec[rec >= t])
            ap = ap + p / 11.
    else:
        # correct AP calculation
        # first append sentinel values at the end
        mrec = np.concatenate(([0.], rec, [1.]))
        mpre = np.concatenate(([0.], prec, [0.]))

        # compute the precision envelope
        for i in range(mpre.size - 1, 0, -1):
            mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])

        # to calculate area under PR curve, look for points
        # where X axis (recall) changes value
        i = np.where(mrec[1:] != mrec[:-1])[0]

        # and sum (\Delta recall) * prec
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
    return ap


def voc_eval(pred_values,
             annopath,
             classname,
             ovthresh=0.5,
             use_07_metric=False,
             use_diff=False):
    """rec, prec, ap = voc_eval(pred_values,
                              annopath,
                              imagesetfile,
                              classname,
                              [ovthresh],
                              [use_07_metric])

  Top level function that does the PASCAL VOC evaluation.

  pred_values：
    是一个2维矩阵，[[图片地址，一个bbox对于cls的分数，bbox_xmin, bbox_ymin, bbox_xmax, bbox_ymax]]
  annopath: Path to annotations
      annopath.format(imagename) should be the xml annotations file.
  classname: Category name (duh)
  [ovthresh]: Overlap threshold (default = 0.5)
  [use_07_metric]: Whether to use VOC07's 11 point AP computation
      (default False)
  """
    recs = {}
    for xmlP in glob.glob(annopath + "/*.*"):
        recs[xmlP] = parse_rec(xmlP)
    class_recs = {}
    # extract gt objects for this cls class
    npos = 0
    for xmlP in glob.glob(annopath + "/*.*"):
        R = [obj for obj in recs[xmlP] if obj['name'] == classname]
        bbox = np.array([x['bbox'] for x in R])
        if use_diff:
            difficult = np.array([False for x in R]).astype(np.bool)
        else:
            difficult = np.array([x['difficult'] for x in R]).astype(np.bool)
        det = [False] * len(R)
        npos = npos + sum(~difficult)
        class_recs[xmlP] = {
            'bbox': bbox,
            'difficult': difficult,
            'det': det
        }

    image_ids = [x[0] for x in pred_values]  # 图片下标或文件名（不包括.jpg）,与imagename表示同样的意思
    confidence = np.array([float(x[1]) for x in pred_values])  # 置信度
    BB = np.array([[float(z) for z in x[2:]] for x in pred_values])  # bbox

    nd = len(image_ids)
    tp = np.zeros(nd)
    fp = np.zeros(nd)

    if BB.shape[0] > 0:
        # sort by confidence
        sorted_ind = np.argsort(-confidence)
        sorted_scores = np.sort(-confidence)
        BB = BB[sorted_ind, :]
        image_ids = [image_ids[x] for x in sorted_ind]

        # go down dets and mark TPs and FPs
        for d in range(nd):
            R = class_recs[image_ids[d]]
            bb = BB[d, :].astype(float)
            ovmax = -np.inf
            BBGT = R['bbox'].astype(float)

            if BBGT.size > 0:
                # compute overlaps
                # intersection
                ixmin = np.maximum(BBGT[:, 0], bb[0])
                iymin = np.maximum(BBGT[:, 1], bb[1])
                ixmax = np.minimum(BBGT[:, 2], bb[2])
                iymax = np.minimum(BBGT[:, 3], bb[3])
                iw = np.maximum(ixmax - ixmin + 1., 0.)
                ih = np.maximum(iymax - iymin + 1., 0.)
                inters = iw * ih

                # union
                uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +
                       (BBGT[:, 2] - BBGT[:, 0] + 1.) *
                       (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)

                overlaps = inters / uni
                ovmax = np.max(overlaps)
                jmax = np.argmax(overlaps)

            if ovmax > ovthresh:
                if not R['difficult'][jmax]:
                    if not R['det'][jmax]:
                        tp[d] = 1.
                        R['det'][jmax] = 1
                    else:
                        fp[d] = 1.
            else:
                fp[d] = 1.

    # compute precision recall
    fp = np.cumsum(fp)  # 在该方法之前fp中取值只能是0/1， np.cumsum方法是将fp数组中的所有数据加起来，
                        # 所加的总和在fp[-1]最后一位上(表示总共fp【错误肯定】的个数)。具体可以查看np.cumsum方法源码，在源码注释后面还有样例讲解
    tp = np.cumsum(tp)  # 在该方法之前tp中取值只能是0/1， np.cumsum方法是将tp数组中的所有数据加起来，
                        # 所加的总和在tp[-1]最后一位上(表示总共tp【正确肯定】的个数)。具体可以查看np.cumsum方法源码，在源码注释后面还有样例讲解
    rec = tp / float(npos)
    # avoid divide by zero in case the first detection matches a difficult
    # ground truth
    prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
    ap = voc_ap(rec, prec, use_07_metric)

    return rec, prec, ap