# -*- coding: utf-8 -*-
"""
Created on Sun Jun  9 21:27:20 2024

@author: Arnd Helmut Hafner
"""

import sys # for sys.exit after error
import re


def sliptextinput(filename):
    '''
    reads the original slip text and returns it as a dictionary accessible by slip number

    Parameters
    ----------
    filename : str
        Structure of file (One slip, two or more lines):
            docstyle,tab,posinstyle,tab,posindoc,tab,slip number
            sliptext
            sliptext
            ...
        docstyle:document style
        posinstyle: position of document within a group of same docstyle
        posindoc: position of slip within the same document

    Returns
    -------
    sliptext : dict
        {slipnumber:[sliptext,docstyle,posinstyle,posindoc]}
    slipnolist : list
        Remembers slip numbers in order of appearance
        in order to check with original file

    '''
    datafile = open(filename, 'r', encoding='utf-8-sig')
    sliptext = []#[[簡番号,釈文]] = 一簡面の釈文を簡番号と共に収録するリストのリスト
    sliptextID = -1
    monjo = []#[[SlipID+SlipID,youshikiID]] = 一つの文書を構成する簡面のIDと様式分類のIDを収めるリストのリスト
    monjoID = -1
    yousiki = []#[[様式記号,様式名称]]様式記号と様式名称のリストのリスト。 
    #様式の名称はshakumon.txtに含まれないから、 それを空の文字列で代替する
    yousikiID = -1
    filetext = []#[[monjoID]] = 釈文ファイルにおける文書出現を記録するリスト
    #釈文ファイルの順番に作成されるから、　このリストのIDは文書のIDと一致するが、理論的に将来の編集によって変わり得る。
    
    for line in datafile:
        line = re.sub('\n','',line)
        m =re.search('^([\d\-]+)\t(\d+)\t(\d+)\t([\d\-+abcdJ⑦⑨⑩⑫⑬⑭⑯]+)$',line)
        if m:#Hits a line with metadata concerning docstyle etc.
            sliptextID += 1    
            sliptext.append([m.group(4),''])
            if m.group(2) == '0' and m.group(3) == '0':
                yousikiID +=1
                yousiki.append([m.group(1),''])
            if m.group(3) == '0':
                monjoID +=1
                monjo.append([str(sliptextID),yousikiID])
                filetext.append([monjoID])
            else:
                monjo[monjoID][0] += '+' + str(sliptextID)
        else:#Hits lines with slip text. In case of multiline texts, linebreak '#' is inserted at end of each line.
            if sliptext[sliptextID][1] == '':
                sliptext[sliptextID][1] = line
            else:
                sliptext[sliptextID][1] += '#' + line
    datafile.close()
    return(sliptext,monjo,yousiki,filetext)

def outputtable(recordlist,filename,head):
    '''
    Outputs a list of records as a CSV file

    Parameters
    ----------
    recordlist : List
        List of records. Every record is a list with as many elements
        as there are fields
        
    filename : str
        output file
    
    head : str
        head line of csv file

    Returns
    -------
    None.

    '''
    outputfile = open(filename, 'w', encoding='utf-8-sig')
    outputfile.write(head + '\n')
    for n in range(len(recordlist)):#accessing records (1 record == 1 list
        line = str(n)
        for x in range(len(recordlist[n])):#accessing elements of list
            line += ',' + str(recordlist[n][x])#creating comma separated line
        outputfile.write(line + '\n')
    outputfile.close()
            


if __name__ == "__main__":
    filename = 'shakumon(linknuki).txt'
    sliptext,monjo,yousiki,filetext = sliptextinput(filename)
    outputtable(sliptext,'sliptext.csv','ID,簡番号,釈文')
    outputtable(monjo,'monjo.csv','ID,構成簡,様式分類')
    outputtable(yousiki,'yousiki.csv','ID,記号,名称')
    outputtable(filetext,'filetext.csv','ID,文書')