def main():
py_location = os.path.dirname(os.path.abspath(__file__))
print(py_location) # 打印当前 py 文件所在目录
workbook = xlrd.open_workbook(os.path.join(py_location, r"通用规范汉字表.xls"))
dictionary = {}
for sheet in workbook.sheets():
for row in range(sheet.nrows):
zi_tou = sheet.cell(row, 1).value
xu_hao = str(int(sheet.cell(row, 0).value)).zfill(4)
print(sheet.name, xu_hao, zi_tou)
#f.write(zi_tou + '\t' + xu_hao + '\t' + sheet.name + '\n')
dictionary[
zi_tou] = '<b>' + zi_tou + '</b>' + '\t' + xu_hao + '\t' + sheet.name
writer = MDictWriter(dictionary, title="", description="")
outfile = open(os.path.join(py_location, r"通用规范汉字表.mdx"), "wb")
writer.write(outfile)
outfile.close()
print('done!')
def write_mdict():
"""
Zip/Write button's command: zip/write .txt files into a file that ends with "mdx"/"mdd".
(Adapted from "readmdict", cf. https://jingyan.baidu.com/article/95c9d20d47583bec4e756132.html)
Returns:
If successful, internal files of .mdx/.mdd will appear in a folder (named ""Unzipped_mdx)
in the same folder as .mdx/.mdd, and an messagebox will pop up showing the number of entries in .mdx
or the number of files in .mdd.
If failed, an errorbox will pop up requesting you to specify a valid MDX/MDD file.
"""
import io
import sys
import importlib
importlib.reload(sys)
import collections
from collections import defaultdict
from writemdict import MDictWriter, encrypt_key
from ripemd128 import ripemd128
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
if write_path.split(os.path.sep)[-1].endswith('mdx'):
# Zip files (dictionary_name.txt (and about.txt)) into .mdx
# Delete .DS_Store in Mac:
files_in_write_path = os.listdir(write_path)
if '.DS_Store' in files_in_write_path:
files_in_write_path.remove('.DS_Store')
# The folder can only have at most 2 files:
if len(files_in_write_path) > 2:
tkinter.messagebox.showerror(
'Error', "The number of files in the folder must be <=2.")
elif len(files_in_write_path) == 0:
tkinter.messagebox.showerror(
'Error', "The number of files in the folder must be <=2.")
elif len(files_in_write_path) == 1:
# When the folder only has one .txt including entries
global dictionary_txt
dictionary_txt = files_in_write_path[0]
head = 0
new_mean = []
f = io.open(os.path.join(write_path, dictionary_txt),
'r',
encoding='utf-8')
d = defaultdict(list) # 建立一个空字典，也可使用{}建立。
for line in f: # 每次从f中读入一行
line = line.rstrip('\n') # 去除行尾的换行符
if line == '</>':
if head == 2:
new_mean[0:] = ["".join(new_mean[0:])]
d[word].append(new_mean[0])
head = 1
new_mean = []
elif head == 1:
word = line
head = 2
elif head == 2:
new_mean.append(line)
head = 2
f.close()
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
if not os.path.exists(os.path.join(write_path, 'Zipped_mdx')):
os.makedirs(os.path.join(write_path, 'Zipped_mdx'))
outfile_mdx = open(
os.path.join(write_path, 'Zipped_mdx',
dictionary_txt.split(os.path.extsep)[0] + '.mdx'),
"wb")
writer = MDictWriter(d,
dictionary_txt.split(os.path.extsep)[0],
dictionary_txt.split(os.path.extsep)[0])
writer.write(outfile_mdx)
outfile_mdx.close()
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
print('======== {} ========'.format(write_path))
global write_number_report
write_number_report = '{}.mdx'.format(
dictionary_txt.split(os.path.extsep)[0])
print('Output: {}'.format(write_number_report))
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
# region Messagebox for reporting outcome:
tkinter.messagebox.showinfo(
'Output', 'Write/Zip: \n\t{}\n\nOutput: \n\t{}'.format(
write_path, write_number_report))
# endregion
else:
# When the folder have two .txt files including entries and about_information
for file in files_in_write_path:
if not file.startswith('about'):
dictionary_txt = file
else:
global about_txt
about_txt = file
head = 0
new_mean = []
f = io.open(os.path.join(write_path, dictionary_txt),
'r',
encoding='utf-8')
d = defaultdict(list) # 建立一个空字典，也可使用{}建立。
for line in f: # 每次从f中读入一行
line = line.rstrip('\n') # 去除行尾的换行符
if line == '</>':
if head == 2:
new_mean[0:] = ["".join(new_mean[0:])]
d[word].append(new_mean[0])
head = 1
new_mean = []
elif head == 1:
word = line
head = 2
elif head == 2:
new_mean.append(line)
head = 2
f.close()
ff = io.open(os.path.join(write_path, about_txt),
'r',
encoding='utf-8') # 词典about信息，txt文件请保存为utf-8
about = []
for line in ff: # 每次从f中读入一行
about.append(line)
about[0:] = ["".join(about[0:])]
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
if not os.path.exists(os.path.join(write_path, 'Zipped_mdx')):
os.makedirs(os.path.join(write_path, 'Zipped_mdx'))
outfile_mdx = open(
os.path.join(write_path, 'Zipped_mdx',
dictionary_txt.split(os.path.extsep)[0] + '.mdx'),
"wb")
writer = MDictWriter(d,
dictionary_txt.split(os.path.extsep)[0],
about[0])
writer.write(outfile_mdx)
outfile_mdx.close()
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
print('======== {} ========'.format(write_path))
write_number_report = '{}.mdx'.format(
dictionary_txt.split(os.path.extsep)[0])
print('Output: {}'.format(write_number_report))
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
# region Messagebox for reporting outcome:
tkinter.messagebox.showinfo(
'Output', 'Write/Zip: \n\t{}\n\nOutput: \n\t{}'.format(
write_path, write_number_report))
# endregion
# elif write_path.split(os.path.sep)[-1].endswith('mdd'):
# # Zip files in mdd
# folder_name = re.search(r'^.*{}'.format(os.path.sep), write_path).group() + 'Zipped_mdd'
# if not os.path.exists(folder_name):
# os.makedirs(folder_name)
# outfile_name = os.path.join(folder_name, write_path.split(os.path.sep)[-1])
# for file in os.listdir(write_path):
# if file.lower().endswith('png'or'gif'or'jpg'or'jpeg'or'css'):
# file_object = open(os.path.join(write_path, file), 'rb')
# file_contents = file_object.read()
# outfile_mdd = open(outfile_name, 'wb')
# d = {"\\{}".format(file) : file_contents}
# writer = MDictWriter(d, file.split('.')[0], file, is_mdd=True)
# writer.write(outfile_mdd)
# file_object.close()
# outfile_mdd.close()
# else:
# file_object = open(os.path.join(write_path, file), 'r', encoding='utf-8', errors='ignore')
# file_contents = file_object.read()
# outfile_mdd = open(outfile_name, 'w')
# d = {"\\{}".format(file): file_contents}
# writer = MDictWriter(d, file.split('.')[0], file, is_mdd=True)
# writer.write(outfile_mdd)
# file_object.close()
# outfile_mdd.close()
# write_number_report = outfile_name
# print('Output: {}'.format(write_number_report))
# # region Messagebox for reporting outcome:
# tkinter.messagebox.showinfo('Output', 'Write/Zip: \n\t{}\n\nOutput: \n\t{}'.format(write_path, write_number_report))
# # endregion
else:
# Modified by 掌上百科@maomaowei5655 in 2020-04-23:
print('Please put files in a folder suffixed mdx/mdd.')
# region Messagebox for error:
tkinter.messagebox.showerror('Error',
"Please specify a valid MDX file.")
# directory.
from writemdict import MDictWriter, encrypt_key
from ripemd128 import ripemd128
import io
# This is the dictionary we will use.
d = {
"alpha":"<i>alpha</i>",
"beta":"Letter <b>beta</b>",
"gamma":"Capital version is Γ <"}
### Example 1: Basic writing. All options default.
outfile = open("example_output/basic.mdx", "wb")
writer = MDictWriter(d, "Basic dictionary", "This is a basic test dictionary.")
writer.write(outfile)
outfile.close()
### Example 2: Demonstrates the use of UTF-16 encoding.
outfile = open("example_output/utf16.mdx", "wb")
writer = MDictWriter(d,
"UTF-16 dictionary",
"This is a test for the \"UTF-16\" encoding.",
encoding="utf-16")
writer.write(outfile)
outfile.close()
### Example 3: This is a test to create a UTF-16 dictionary containing characters outside the
# Basic Multilingual Plane
# directory.
from writemdict import MDictWriter, encrypt_key
from ripemd128 import ripemd128
import io
# This is the dictionary we will use.
d = {
"alpha": "<i>alpha</i>",
"beta": "Letter <b>beta</b>",
"gamma": "Capital version is Γ <"
}
### Example 1: Basic writing. All options default.
outfile = open("example_output/basic.mdx", "wb")
writer = MDictWriter(d, "Basic dictionary", "This is a basic test dictionary.")
writer.write(outfile)
outfile.close()
### Example 2: Demonstrates the use of UTF-16 encoding.
outfile = open("example_output/utf16.mdx", "wb")
writer = MDictWriter(d,
"UTF-16 dictionary",
"This is a test for the \"UTF-16\" encoding.",
encoding="utf-16")
writer.write(outfile)
outfile.close()
### Example 3: This is a test to create a UTF-16 dictionary containing characters outside the
# Basic Multilingual Plane
d2 = {"𩷶": "A fish"}
#+'<button type="button" onclick="startmy()">Click Me!</button>'
+'<canvas id="glcanvas" width="640" height="480" >'
+' asdasd'
+'</canvas>'
+'</div>'
+'<div id="the-div">Content</div>'
+'<script>$(document).trigger("startmyfunc");</script>')
# This is the dictionary we will use.
d = {
"alpha":asd,
"beta":"Letter <b>beta</b>",
"gamma":"Capital version is Γ <"}
### Example 4: Uses the Big5 encoding.
outfile = open("example_output/big5.mdx", "wb")
writer = MDictWriter(d,
"Big5 dictionary",
"This is a test for the \"Big5\" encoding.",
encoding="big5")
writer.write(outfile)
outfile.close()
# directory.
from writemdict import MDictWriter, encrypt_key
from ripemd128 import ripemd128
import io
# This is the dictionary we will use.
d = {
"alpha":"<i>alpha</i>",
"beta":"Letter <b>beta</b>",
"gamma":"Capital version is Γ <"}
### Example 1: Basic writing. All options default.
outfile = open("example_output/basic.mdx", "wb")
writer = MDictWriter(d, "Basic dictionary", "This is a basic test dictionary.")
writer.write(outfile)
outfile.close()
### Example 2: Demonstrates the use of UTF-16 encoding.
outfile = open("example_output/utf16.mdx", "wb")
writer = MDictWriter(d,
"UTF-16 dictionary",
"This is a test for the \"UTF-16\" encoding.",
encoding="utf-16")
writer.write(outfile)
outfile.close()
### Example 3: This is a test to create a UTF-16 dictionary containing characters outside the
# Basic Multilingual Plane
from ripemd128 import ripemd128
import io
# This is the dictionary we will use.
d = {
"alpha":"<i>alpha</i>",
"beta":"Letter <b>beta</b>",
"gamma":"Capital version is Γ <"}
### Example 1: Basic writing. All options default.
outfile = open("example_output/basic.mdx", "wb")
writer = MDictWriter(d, "Basic dictionary", "This is a basic test dictionary.")
writer.write(outfile)
outfile.close()
### Example 2: Demonstrates the use of UTF-16 encoding.
outfile = open("example_output/utf16.mdx", "wb")
writer = MDictWriter(d,
"UTF-16 dictionary",
"This is a test for the \"UTF-16\" encoding.",
encoding="utf-16")
writer.write(outfile)
outfile.close()
### Example 3: This is a test to create a UTF-16 dictionary containing characters outside the
# Basic Multilingual Plane
# -*- coding: utf-8 -*-
"""
ejdicをMDict形式に変換します。
"""
from writemdict import MDictWriter, encrypt_key
import sys
args = sys.argv
d = {}
with open(args[1]) as f:
line = f.readline()
while line:
word, meaning = line.split('\t', 1)
meaning = meaning.replace('/', '\n').replace('・', ',')
line = f.readline()
d[word] = meaning
with open("ejdic.mdx", "wb") as outfile:
writer = MDictWriter(d, "EJDIC", "\"UTF-8\" encoding.", encoding="utf-8")
writer.write(outfile)
from __future__ import unicode_literals
from writemdict import MDictWriter
import os
import codecs
import json
filelist = os.listdir()
mdxcontent = []
content = []
dictionary = {}
for filename in filelist:
if (filename.split(".")[-1] not in ["html", "htm"]):
continue
entryname = filename.replace(".html",
'') #".".join(filename.split(".")[0:-1])
with codecs.open(filename, "r+", encoding='utf-8') as ent:
entrycontent = ent.read()
entry = entryname + "\n" + entrycontent
entry = entry + "\n</>"
dictionary[entryname] = entrycontent
mdxcontent.append(entry)
print(filename)
with codecs.open("notes.txt", 'w+', encoding='utf-8') as f:
f.write("\n".join(mdxcontent).replace("\n\n", "\n").replace("\n\n", "\n"))
writer = MDictWriter(dictionary, title="Notes", description="My best notes!")
outfile = open("notes.mdx", "wb")
writer.write(outfile)
outfile.close()
