import scipy
import PIL
import numpy as np
import torch
import torch.nn.functional as F

@torch.no_grad()
def project_face_embs(pipeline, face_embs):

    '''
    face_embs: (N, 512) normalized ArcFace embeddings
    '''

    arcface_token_id = pipeline.tokenizer.encode("id", add_special_tokens=False)[0]

    input_ids = pipeline.tokenizer(
            "photo of a id person",
            truncation=True,
            padding="max_length",
            max_length=pipeline.tokenizer.model_max_length,
            return_tensors="pt",
        ).input_ids.to(pipeline.device)

    face_embs_padded = F.pad(face_embs, (0, pipeline.text_encoder.config.hidden_size-512), "constant", 0)
    token_embs = pipeline.text_encoder(input_ids=input_ids.repeat(len(face_embs), 1), return_token_embs=True)
    token_embs[input_ids==arcface_token_id] = face_embs_padded

    prompt_embeds = pipeline.text_encoder(
        input_ids=input_ids,
        input_token_embs=token_embs
    )[0]

    return prompt_embeds


def project_face_embs_with_grad(encoder, tokenizer, face_embs):
    """
    Same as project_face_embs but allows gradients for training.
    """
    arcface_token_id = tokenizer.encode("id", add_special_tokens=False)[0]

    input_ids = tokenizer(
        "photo of a id person",
        truncation=True,
        padding="max_length",
        max_length=tokenizer.model_max_length,
        return_tensors="pt",
    ).input_ids.to(encoder.device)

    face_embs_padded = F.pad(face_embs, (0, encoder.config.hidden_size - 512), "constant", 0)

    input_ids_batch = input_ids.repeat(len(face_embs), 1)
    token_embs = encoder(input_ids=input_ids_batch, return_token_embs=True)

    face_embs_padded = face_embs_padded.to(token_embs.dtype)
    token_embs[input_ids_batch == arcface_token_id] = face_embs_padded

    prompt_embeds = encoder(
        input_ids=input_ids_batch,
        input_token_embs=token_embs
    )[0]

    return prompt_embeds


def image_align(img,
                face_landmarks,
                output_size=1024,
                transform_size=4096,
                enable_padding=True):
    # Align function from FFHQ dataset pre-processing step
    # https://github.com/NVlabs/ffhq-dataset/blob/master/download_ffhq.py

    lm = face_landmarks
    lm_eye_left = lm[36:42]
    lm_eye_right = lm[42:48]
    lm_mouth_outer = lm[48:60]

    eye_left = np.mean(lm_eye_left, axis=0)
    eye_right = np.mean(lm_eye_right, axis=0)
    eye_avg = (eye_left + eye_right) * 0.5
    eye_to_eye = eye_right - eye_left
    mouth_left = lm_mouth_outer[0]
    mouth_right = lm_mouth_outer[6]
    mouth_avg = (mouth_left + mouth_right) * 0.5
    eye_to_mouth = mouth_avg - eye_avg

    x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
    x /= np.hypot(*x)
    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
    y = np.flipud(x) * [-1, 1]
    c = eye_avg + eye_to_mouth * 0.1
    quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
    qsize = np.hypot(*x) * 2

    img = img.convert('RGB')

    shrink = int(np.floor(qsize / output_size * 0.5))
    if shrink > 1:
        rsize = (int(np.rint(float(img.size[0]) / shrink)),
                 int(np.rint(float(img.size[1]) / shrink)))
        img = img.resize(rsize, PIL.Image.LANCZOS)
        quad /= shrink
        qsize /= shrink

    border = max(int(np.rint(qsize * 0.1)), 3)
    crop = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))),
            int(np.ceil(max(quad[:, 0]))), int(np.ceil(max(quad[:, 1]))))
    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0),
            min(crop[2] + border, img.size[0]), min(crop[3] + border, img.size[1]))
    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
        img = img.crop(crop)
        quad -= crop[0:2]

    pad = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))),
           int(np.ceil(max(quad[:, 0]))), int(np.ceil(max(quad[:, 1]))))
    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0),
           max(pad[2] - img.size[0] + border, 0), max(pad[3] - img.size[1] + border, 0))
    if enable_padding and max(pad) > border - 4:
        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
        img = np.pad(np.float32(img),
                     ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
        h, w, _ = img.shape
        y, x, _ = np.ogrid[:h, :w, :1]
        mask = np.maximum(
            1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w - 1 - x) / pad[2]),
            1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h - 1 - y) / pad[3]))
        blur = qsize * 0.02
        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
        img += (np.median(img, axis=(0, 1)) - img) * np.clip(mask, 0.0, 1.0)
        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        quad += pad[:2]

    img = img.transform((transform_size, transform_size), PIL.Image.QUAD,
                        (quad + 0.5).flatten(), PIL.Image.BILINEAR)
    if output_size < transform_size:
        img = img.resize((output_size, output_size), PIL.Image.LANCZOS)

    return img