require 'lmptb.lmvocab'
require 'lmptb.lmfeeder'
require 'lmptb.lmutil'
require 'lmptb.layer.init'
require 'lmptb.lmseqreader'
require 'rnn.tnn'

--[[global function rename]]--
printf = nerv.printf
--[[global function rename ends]]--

--global_conf: table
--first_time: bool
--Returns: a ParamRepo
function prepare_parameters(global_conf, first_time)
    printf("%s preparing parameters...\n", global_conf.sche_log_pre) 
    
    if (first_time) then
        ltp_ih = nerv.LinearTransParam("ltp_ih", global_conf)  
        ltp_ih.trans = global_conf.cumat_type(global_conf.vocab:size() + 1, global_conf.hidden_size) --index 0 is for zero, others correspond to vocab index(starting from 1)
        ltp_ih.trans:generate(global_conf.param_random)
        ltp_ih.trans[0]:fill(0)

        ltp_hh = nerv.LinearTransParam("ltp_hh", global_conf)
        ltp_hh.trans = global_conf.cumat_type(global_conf.hidden_size, global_conf.hidden_size)
        ltp_hh.trans:generate(global_conf.param_random) 

        ltp_ho = nerv.LinearTransParam("ltp_ho", global_conf)
        ltp_ho.trans = global_conf.cumat_type(global_conf.hidden_size, global_conf.vocab:size())
        ltp_ho.trans:generate(global_conf.param_random)

        bp_h = nerv.BiasParam("bp_h", global_conf)
        bp_h.trans = global_conf.cumat_type(1, global_conf.hidden_size)
        bp_h.trans:generate(global_conf.param_random)

        bp_o = nerv.BiasParam("bp_o", global_conf)
        bp_o.trans = global_conf.cumat_type(1, global_conf.vocab:size())
        bp_o.trans:generate(global_conf.param_random)

        local f = nerv.ChunkFile(global_conf.param_fn, 'w')
        f:write_chunk(ltp_ih)
        f:write_chunk(ltp_hh)
        f:write_chunk(ltp_ho)
        f:write_chunk(bp_h)
        f:write_chunk(bp_o)
        f:close()
    end
    
    local paramRepo = nerv.ParamRepo()
    paramRepo:import({global_conf.param_fn}, nil, global_conf)

    printf("%s preparing parameters end.\n", global_conf.sche_log_pre)

    return paramRepo
end

--global_conf: table
--Returns: nerv.LayerRepo
function prepare_layers(global_conf, paramRepo)
    printf("%s preparing layers...\n", global_conf.sche_log_pre)

    local recurrentLconfig = {{["bp"] = "bp_h", ["ltp_hh"] = "ltp_hh"}, {["dim_in"] = {global_conf.hidden_size, global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}, ["break_id"] = global_conf.vocab:get_sen_entry().id, ["independent"] = global_conf.independent, ["clip"] = 10}}

    local layers = {
        ["nerv.IndRecurrentLayer"] = {
            ["recurrentL1"] = recurrentLconfig, 
        },

        ["nerv.SelectLinearLayer"] = {
            ["selectL1"] = {{["ltp"] = "ltp_ih"}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}}},
        },

        ["nerv.SigmoidLayer"] = {
            ["sigmoidL1"] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}}
        },
        
        ["nerv.AffineLayer"] = {
            ["outputL"] = {{["ltp"] = "ltp_ho", ["bp"] = "bp_o"}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.vocab:size()}}},
        },

        ["nerv.SoftmaxCELayer"] = {
            ["softmaxL"] = {{}, {["dim_in"] = {global_conf.vocab:size(), global_conf.vocab:size()}, ["dim_out"] = {1}}},
        },
    }
    
    --[[ --we do not need those in the new rnn framework
    printf("%s adding %d bptt layers...\n", global_conf.sche_log_pre, global_conf.bptt)
    for i = 1, global_conf.bptt do
        layers["nerv.IndRecurrentLayer"]["recurrentL" .. (i + 1)] = recurrentLconfig 
        layers["nerv.SigmoidLayer"]["sigmoidL" .. (i + 1)] = {{}, {["dim_in"] = {global_conf.hidden_size}, ["dim_out"] = {global_conf.hidden_size}}}
        layers["nerv.SelectLinearLayer"]["selectL" .. (i + 1)] = {{["ltp"] = "ltp_ih"}, {["dim_in"] = {1}, ["dim_out"] = {global_conf.hidden_size}}}
    end
    --]]

    local layerRepo = nerv.LayerRepo(layers, paramRepo, global_conf)
    printf("%s preparing layers end.\n", global_conf.sche_log_pre)
    return layerRepo
end

--global_conf: table
--layerRepo: nerv.LayerRepo
--Returns: a nerv.TNN
function prepare_dagLayer(global_conf, layerRepo)
    printf("%s Initing TNN ...\n", global_conf.sche_log_pre)

    --input: input_w, input_w, ... input_w_now, last_activation
    local connections_t = {
        {"<input>[1]", "selectL1[1]", 0},
        {"selectL1[1]", "recurrentL1[1]", 0},  
        {"recurrentL1[1]", "sigmoidL1[1]", 0},
        {"sigmoidL1[1]", "outputL[1]", 0},
        {"sigmoidL1[1]", "recurrentL1[2]", 1},
        {"outputL[1]", "softmaxL[1]", 0},
        {"<input>[2]", "softmaxL[2]", 0},
        {"softmaxL[1]", "<output>[1]", 0}
    }

    --[[
    printf("%s printing DAG connections:\n", global_conf.sche_log_pre)
    for key, value in pairs(connections_t) do
        printf("\t%s->%s\n", key, value)
    end
    ]]--

    local tnn = nerv.TNN("TNN", global_conf, {["dim_in"] = {1, global_conf.vocab:size()}, ["dim_out"] = {1}, ["sub_layers"] = layerRepo,
            ["connections"] = connections_t, 
        })
    printf("%s Initing TNN end.\n", global_conf.sche_log_pre)
    return tnn
end

local train_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text'
local test_fn = '/home/slhome/txh18/workspace/nerv/nerv/nerv/examples/lmptb/m-tests/some-text'

local global_conf = {
    lrate = 1, wcost = 1e-6, momentum = 0,
    cumat_type = nerv.CuMatrixFloat,
    mmat_type = nerv.CuMatrixFloat,
    nn_act_default = 0, 

    hidden_size = 20,
    chunk_size = 5,
    batch_size = 3, 
    max_iter = 18,
    param_random = function() return (math.random() / 5 - 0.1) end,
    independent = true,

    train_fn = train_fn,
    test_fn = test_fn,
    sche_log_pre = "[SCHEDULER]:",
    log_w_num = 10, --give a message when log_w_num words have been processed
    timer = nerv.Timer()
}
global_conf.work_dir = '/home/slhome/txh18/workspace/nerv/play/dagL_test'
global_conf.param_fn = global_conf.work_dir.."/params"

local vocab = nerv.LMVocab()
global_conf["vocab"] = vocab
global_conf.vocab:build_file(global_conf.train_fn, false)
local paramRepo = prepare_parameters(global_conf, true)
local layerRepo = prepare_layers(global_conf, paramRepo)
local tnn = prepare_dagLayer(global_conf, layerRepo)
tnn:init(global_conf.batch_size, global_conf.chunk_size)

local reader = nerv.LMSeqReader(global_conf, global_conf.batch_size, global_conf.chunk_size, global_conf.vocab)
reader:open_file(global_conf.train_fn)

local batch_num = 1
while (1) do
    local r, feeds
    r, feeds = tnn:getFeedFromReader(reader)
    if (r == false) then break end
    for j = 1, global_conf.chunk_size, 1 do
        for i = 1, global_conf.batch_size, 1 do
            printf("%s[L(%s)] ", feeds.inputs_s[j][i], feeds.labels_s[j][i])   --vocab:get_word_str(input[i][j]).id
        end
        printf("\n")
    end
    printf("\n")
end