main.py

import treetaggerwrapper
from read_json_data import read_json_data
from correct_word import delete_unuse_word
from correct_word import correct_word
from convert_strings import pos_to_jpos
from convert_strings import jpos_to_hinshi
from output_wordlist import export_xlsx

# Windows C:/TreeTagger/
# Mac /Users/kazuomiyajima

# コンソール入力でMac・Windows選択 #######
while True:
	choice = input('please select Windows(w) or Mac(m): ')
	if choice in ['w', 'Windows', 'win', 'windows']:
		tagger_path = 'C:/TreeTagger/'
		break
	elif choice in ['m', 'mac', 'Mac']:
		tagger_path = '/Users/kazuomiyajima'
		break
#########################
tagger = treetaggerwrapper.TreeTagger(TAGLANG='en', TAGDIR=tagger_path)  # binやlibのフォルダがあるディレクトリ
tags = tagger.TagText("Hi, Mao.  I'm Felipe. Sorry, I'm not Mao.  I am Mao.  Oh, you are Mao.  Are you from Australia ?  No, I'm not. Where are you from ?  I'm from Brazil.  p30. I have a dog at home. Oh, nice!	 I have five frogs . I don't like frogs….   Do you walk your dog every day ?  No, I don't . When do you walk your dog ?  On weekends.  p38. I can make sushi. That's nice.  But I can't eat fish. Then I can make natto rolls for you. Thanks.  Can you cook Japanese food ?  Yes, I can . What can you make ?  I can make ramen.  p52. This is yokan. Oh, I like yokan. Is that yokan too ?  No, it isn't.  It's coffee jelly.  Let's have some sweet. I like this cookie. Who is this woman ?  She is a famous cook in Japan.  p62. Is this your sister's work? Yes.  She likes home economics. She saws very well. Thanks.  But she doesn't cook.  Does your sister make clothes ?  Yes, she does . What can she make? She can make pajamas.  p72. Do you know that cool girl? No.  I don't know her . Then do you know him ? Oh, he's my brother.   Do you have a girlfriend? Yes, I do.  Her name is Rei. Why do you like her ?  Because she is always kind to me.  p82. Dad, I'm very hungry. Me too. Oh, there is a steak restaurant over there. Let's go soon!   I'm full.  But I want something sweet. I know a new cake shop. Wow!  How can we go there ? By bus.  p82. Can you help me? Sorry, I now. How about you, Kevin? OK.  I'm not doing anything now.  Are you still studying?  No, I'm not . Then  what are you doing?  I'm preparing for the countdown event.  p82. Tell me about your holidays. I stayed home and watched TV. You relaxed well. Yes.  I also cooked nikujaga.  I came back from Finland yesterday. Wow! I saw the aurora there. How lucky!  Did you enjoy your trip to Finland ?  Yes, I did . Do you have jet lag? Yes.  I didn't sleep well last night.  p82. Look.  I was a student thirty years ago.  Oh, my.  You were very cute. You WERE? Sorry.  You are still cute.  How was your day?  Were you busy ?  No, I wasn't so busy today. Great.  Let's have dinner. Awesome!  What were you doing?  I was reading this book. Ah, is it a picture book? Yes.  I enjoyed the story.")

# タグ付きテキストを辞書型に変換
wordandtag = []
for tag in tags:
	wordandtag.append({'original_word': tag.split('\t')[0].lower(), 'pos': tag.split('\t')[1], 'lemma': tag.split('\t')[2]})

# 不要な単語を削除する。句読点や数字など
wordlist = delete_unuse_word(wordandtag)

# ここで単語と品詞を修正TreeTaggerで小文字になってしまったものや、分割された省略形を正す。
wordlist = correct_word(wordlist)

# key'word'でソートをかける #lower()をつけないと大文字小文字を区別してソート（大文字が先頭に来る）。
#wordlist.sort(key=lambda x: x['word'].lower(), reverse=False)

# 配列に納められた辞書型データに一致するデータを取得
# 下の例はphoneという配列辞書型データの中にある'単語'というキーで'a.m.'にマッチするキー'発音記号'のデータを取り出す。
# next((x for x in phone if x['単語'] == 'a.m.'), None)['発音記号']でマッチした値（左の例では発音記号）
# phone['key']=''で辞書型のデータを追加できる。

# 単語の比較は原型[lemma]を使っているので注意
# 発音記号・和訳を入れるエラー処理を確実にするためループは別々にした

# 判定した品詞を判読可能な文字に変換して追加
pos_to_jpos(wordlist)    # いったん日本語の品詞名に変換する
jpos_to_hinshi(wordlist)  # 日本語の品詞名からHinshiフォントで表示できるアルファベットに変換する

# ここから既習後データを読み込んでデータを称号・追加
# 既習語データを読み込み
exData = read_json_data('R4ワードリスト重複削除.json')
phoneData = read_json_data('発音記号品詞H28R4.json')
# 発音記号を追加
for i in wordlist:
	try:
		i['phone'] = next((x for x in phoneData if x['単語'] == i['word'] and x['品詞'] == i['pos_m']), None)['発音記号']
	except KeyError:
		i['phone'] = ''
	except TypeError:
		i['phone'] = ''

# 和訳を入れる
for i in wordlist:
	try:
		i['mean'] = next((x for x in exData if x['単語'] == i['word'] and x['品詞'] == i['pos_m']), None)['和訳']
	except KeyError:
		i['mean'] = ''
'''
# 識別子（参照元）を入れる
for i in wordlist:
	try:
		i['identifier'] = next((x for x in exData if x['単語'] == i['lemma']), None)['識別子']
	except KeyError:
		i['identifier'] = ''

# 識別子に対応するページを入れる（参照元のページ）を入れる
for i in wordlist:
	try:
		i['page'] = next((x for x in exData if x['単語'] == i['lemma']), None)['掲載']
	except KeyError:
		i['page'] = ''
'''
print(wordlist)
# export_xlsx(wordlist)