local GRULayerT = nerv.class('nerv.GRULayerT', 'nerv.LayerT')

function GRULayerT:__init(id, global_conf, layer_conf)
    --input1:x input2:h input3:c(h^~)
    self.id = id
    self.dim_in = layer_conf.dim_in
    self.dim_out = layer_conf.dim_out
    self.gconf = global_conf

    if self.dim_in[2] ~= self.dim_out[1] then
        nerv.error("dim_in[2](%d) mismatch with dim_out[1](%d)", self.dim_in[2], self.dim_out[1])
    end

    --prepare a DAGLayerT to hold the lstm structure
    local pr = layer_conf.pr
    if pr == nil then
        pr = nerv.ParamRepo()
    end
    
    local function ap(str)
        return self.id .. '.' .. str
    end

    local layers = {
        ["nerv.CombinerLayer"] = {
            [ap("inputXDup")] = {{}, {["dim_in"] = {self.dim_in[1]}, 
                ["dim_out"] = {self.dim_in[1], self.dim_in[1], self.dim_in[1]}, ["lambda"] = {1}}},
            [ap("inputHDup")] = {{}, {["dim_in"] = {self.dim_in[2]}, 
                ["dim_out"] = {self.dim_in[2], self.dim_in[2], self.dim_in[2], self.dim_in[2], self.dim_in[2]}, ["lambda"] = {1}}},
            [ap("updateGDup")] = {{}, {["dim_in"] = {self.dim_in[2]},
                ["dim_out"] = {self.dim_in[2], self.dim_in[2]}, ["lambda"] = {1}}},
            [ap("updateMergeL")] = {{}, {["dim_in"] = {self.dim_in[2], self.dim_in[2], self.dim_in[2]}, ["dim_out"] = {self.dim_out[1]},
                ["lambda"] = {1, -1, 1}}},
        },
        ["nerv.AffineLayer"] = {
            [ap("mainAffineL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2]}, ["dim_out"] = {self.dim_out[1]}, ["pr"] = pr}},
        },
        ["nerv.TanhLayer"] = {
            [ap("mainTanhL")] = {{}, {["dim_in"] = {self.dim_out[1]}, ["dim_out"] = {self.dim_out[1]}}},
        },
        ["nerv.GateFLayer"] = {
            [ap("resetGateL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2]}, 
                ["dim_out"] = {self.dim_in[2]}, ["pr"] = pr}},
            [ap("updateGateL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2]}, 
                ["dim_out"] = {self.dim_in[2]}, ["pr"] = pr}},
        },
        ["nerv.ElemMulLayer"] = {
            [ap("resetGMulL")] = {{}, {["dim_in"] = {self.dim_in[2], self.dim_in[2]}, ["dim_out"] = {self.dim_in[2]}}},
            [ap("updateGMulCL")] = {{}, {["dim_in"] = {self.dim_in[2], self.dim_in[2]}, ["dim_out"] = {self.dim_in[2]}}},
            [ap("updateGMulHL")] = {{}, {["dim_in"] = {self.dim_in[2], self.dim_in[2]}, ["dim_out"] = {self.dim_in[2]}}},
        },
    }
    
    local layerRepo = nerv.LayerRepo(layers, pr, global_conf)

    local connections_t = {
        ["<input>[1]"] = ap("inputXDup[1]"), 
        ["<input>[2]"] = ap("inputHDup[1]"),

        [ap("inputXDup[1]")] = ap("resetGateL[1]"),
        [ap("inputHDup[1]")] = ap("resetGateL[2]"),
        [ap("inputXDup[2]")] = ap("updateGateL[1]"),
        [ap("inputHDup[2]")] = ap("updateGateL[2]"),
        [ap("updateGateL[1]")] = ap("updateGDup[1]"),

        [ap("resetGateL[1]")] = ap("resetGMulL[1]"),
        [ap("inputHDup[3]")] = ap("resetGMulL[2]"),

        [ap("inputXDup[3]")] = ap("mainAffineL[1]"),
        [ap("resetGMulL[1]")] = ap("mainAffineL[2]"),
        [ap("mainAffineL[1]")] = ap("mainTanhL[1]"),

        [ap("updateGDup[1]")] = ap("updateGMulHL[1]"),
        [ap("inputHDup[4]")] = ap("updateGMulHL[2]"),
        [ap("updateGDup[2]")] = ap("updateGMulCL[1]"),
        [ap("mainTanhL[1]")] = ap("updateGMulCL[2]"),
 
        [ap("inputHDup[5]")] = ap("updateMergeL[1]"),
        [ap("updateGMulHL[1]")] = ap("updateMergeL[2]"),
        [ap("updateGMulCL[1]")] = ap("updateMergeL[3]"),

        [ap("updateMergeL[1]")] = "<output>[1]",
    }

    self.dagL = nerv.DAGLayerT(self.id, global_conf, 
            {["dim_in"] = self.dim_in, ["dim_out"] = self.dim_out, ["sub_layers"] = layerRepo, 
            ["connections"] = connections_t})
    
    self:check_dim_len(2, 1) -- x, h and h
end

function GRULayerT:init(batch_size, chunk_size)
    self.dagL:init(batch_size, chunk_size)
end

function GRULayerT:batch_resize(batch_size, chunk_size)
    self.dagL:batch_resize(batch_size, chunk_size)
end

function GRULayerT:update(bp_err, input, output, t)
    self.dagL:update(bp_err, input, output, t)
end

function GRULayerT:propagate(input, output, t)
    self.dagL:propagate(input, output, t)
end

function GRULayerT:back_propagate(bp_err, next_bp_err, input, output, t)
    self.dagL:back_propagate(bp_err, next_bp_err, input, output, t)
end

function GRULayerT:get_params()
    return self.dagL:get_params()
end