Created
May 22, 2022 06:07
-
-
Save etsune/a5d67620dc5bf6f0b96982226b2c9559 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
import re, json, pathlib, sys | |
from time import time | |
dictFile = '西夏(俗).txt' | |
outputDirectory = 'yomi' | |
def writeDictionaryToFile(data, count): | |
filename = outputDirectory + f'/term_bank_{count}.json' | |
pathlib.Path(outputDirectory).mkdir(parents=True, exist_ok=True) | |
with open(filename, 'w') as f: | |
json.dump(data, f) | |
def createIndexFile(name): | |
data = { | |
"title":name, | |
"format":3, | |
"revision":f'{time()}', | |
"sequenced":True, | |
} | |
filename = outputDirectory + '/index.json' | |
pathlib.Path(outputDirectory).mkdir(parents=True, exist_ok=True) | |
with open(filename, 'w') as f: | |
json.dump(data, f) | |
def cleanBBTags(line): | |
line = re.sub(r'\[\/?([\*cebip]|m\d*|ex|c\s[a-z]+)\]', '', line) | |
line = line.replace("\\[", "[").replace("\\]", "]") | |
return line | |
class Entry(object): | |
expression = '' | |
reading = '' | |
definitionTags = '' | |
rules = '' | |
score = 1 | |
glossary = '' | |
sequence = 1791660 | |
termTags = '' | |
def exportToYomichanArray(self): | |
return [self.expression.strip(), self.reading.strip(), self.definitionTags, self.rules, | |
self.score, [self.glossary.strip()], self.sequence, self.termTags] | |
if (len(sys.argv) != 3): | |
print("Incorrect number of arguments, should be 2.") | |
sys.exit() | |
dictFile = sys.argv[1] | |
outputDirectory = sys.argv[2] | |
createIndexFile(dictFile) | |
dictionaryTxt = open(dictFile, mode='r', encoding='utf-8') | |
entriesCountTotal = 0 | |
filesCount = 1 | |
currentEntry = Entry() | |
yomichanDictionary = [] | |
endOfTheEntry = False | |
isBody = False | |
for line in dictionaryTxt: | |
line = line.strip() | |
if not line or line[0] == '#' or line[0] == '{': | |
continue | |
if line[0] == '[': | |
isBody = True | |
elif isBody: | |
endOfTheEntry = True | |
isBody = False | |
if endOfTheEntry: | |
yomichanDictionary.append(currentEntry.exportToYomichanArray()) | |
endOfTheEntry = False | |
currentEntry = Entry() | |
line = cleanBBTags(line) | |
if isBody: | |
currentEntry.glossary += "\n" + line | |
else: | |
currentEntry.expression = line | |
if len(yomichanDictionary) >= 10000: | |
entriesCountTotal += len(yomichanDictionary) | |
writeDictionaryToFile(yomichanDictionary, filesCount) | |
filesCount += 1 | |
yomichanDictionary = [] | |
if currentEntry: | |
yomichanDictionary.append(currentEntry.exportToYomichanArray()) | |
if len(yomichanDictionary) > 0: | |
writeDictionaryToFile(yomichanDictionary, filesCount) | |
entriesCountTotal += len(yomichanDictionary) | |
print("Total entries: %d" % entriesCountTotal) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment