KLCtoAnki.py

import re
from enum import Enum
import csv

txtFolder = "C:\\FOLDERPATH\\"
filename = "Kanji_Learner_s_Course_Graded_Reading_Sets_vol_1.txt"

class ParseMode(Enum):
    ChapterOrEntryLine = 0
    ExpandedJapanese = 1
    Translation = 2

class Entry(object):
    def __init__(self):
        self.chapterKanji = ""
        self.chapterNumber = -1
        self.entryNumber = -1
        self.japaneseSentence = ""
        self.expandedJapanese = []
        self.translation = []
        self.expandedTranslation = []

file = open(txtFolder+filename, "r", encoding="utf-8")

entries = []
currentChapter = 0
currentEntryNumber = 0
entry = None
chapterKanji = ""

parseMode = ParseMode.ChapterOrEntryLine

def ps(str):
    str = " ".join(str.split())
    return str

for rawIndex, rawline in enumerate(file.readlines()):
    line = rawline.replace("\f", "")
    index = rawIndex+1

    if parseMode == ParseMode.ChapterOrEntryLine:
        match = re.match(r'(\d+)\s*：(.+)', line)
        if match:
            chapter = int(match.group(1))
            chapterKanji = match.group(2)

            assert(currentChapter==chapter or currentChapter+1 == chapter)
            currentChapter = chapter

            print("Match: " + line)
            currentEntryNumber = 0

        else:
            match = re.match(r'(\d+)-(\d+)\.(.+)', line)
            if match:
                chapterNumber = int(match.group(1))
                entryNumber = int(match.group(2))
                japaneseSentence = match.group(3).strip()

                assert(currentChapter == chapterNumber), str(currentChapter) + " " + chapterNumber
                currentEntryNumber = currentEntryNumber+1
                assert entryNumber == currentEntryNumber, f"Entry Number {entryNumber} Current Entry Number {currentEntryNumber} Line {index}"
                parseMode = ParseMode.ExpandedJapanese

                if entry:
                    print(f"Entry: {entry.chapterNumber}-{entry.entryNumber} {entry.japaneseSentence} {entry.expandedJapanese} {entry.translation}")
                    entries.append(entry)
                entry = Entry()
                entry.chapterKanji = chapterKanji
                entry.chapterNumber = chapterNumber
                entry.entryNumber = entryNumber
                entry.japaneseSentence = japaneseSentence
            else:
                if entry:
                    entry.expandedTranslation.append(line)
    elif parseMode == ParseMode.ExpandedJapanese:
        if len(entry.expandedJapanese)>0:
            alphaCount = sum( (c>='a' and c<='z') or (c>='A' and c<='Z') for c in line)
            if alphaCount / len(line) > 0.3:
                parseMode = ParseMode.Translation
            else:
                entry.expandedJapanese.append(line)
        else:
            entry.expandedJapanese.append(line)

    if parseMode == ParseMode.Translation:
        entry.translation.append(line)

        stripped = line.strip()
        if len(stripped) > 0:
            if stripped[-1] in ".)?!…":
                parseMode = ParseMode.ChapterOrEntryLine

entries.append(entry)

with open('klc1.csv', 'w', newline='', encoding="utf-8") as csvfile:
    csvWriter = csv.writer(csvfile, delimiter=",", quotechar='"', quoting=csv.QUOTE_ALL)
    for entry in entries:
        csvWriter.writerow([("%04d" % (entry.chapterNumber,))+("%04d" % (entry.entryNumber,)), entry.chapterKanji, entry.chapterNumber, entry.entryNumber, ps(entry.japaneseSentence), ps(''.join(entry.expandedJapanese)), ps(''.join(entry.translation)), ps(''.join(entry.expandedTranslation))])