`.bib` 内のアクセント付き文字の unicode <-> LaTeX command 変換用スクリプト

ltx2utf.py

#! /usr/bin/env python3

# Copyright (C) 2019  Mahito TANNO

# This is free and unencumbered software released into the public domain.

# Anyone is free to copy, modify, publish, use, compile, sell, or
# distribute this software, either in source code form or as a compiled
# binary, for any purpose, commercial or non-commercial, and by any
# means.

# In jurisdictions that recognize copyright laws, the author or authors
# of this software dedicate any and all copyright interest in the
# software to the public domain. We make this dedication for the benefit
# of the public at large and to the detriment of our heirs and
# successors. We intend this dedication to be an overt act of
# relinquishment in perpetuity of all present and future rights to this
# software under copyright law.

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.

# For more information, please refer to <http://unlicense.org>

"""
* Overview:
  This is my personal Python script which convert LaTeX command to
  unicode characters.  Typically, I use this for BibTeX database.

* Requirements:

  - Python3
  - pylatexenc

  You can install by `pip install pylatexenc`

* Usage:
  `ltx2utf FILE.bib`.
"""

import os
import sys
import shutil
from pylatexenc.latex2text import LatexNodes2Text

bib_file = sys.argv[1]
backup_file = bib_file + '.bak'

if not os.path.isfile(bib_file):
    print('Error: please input your file.')
    sys.exit(1)

shutil.copy(bib_file, backup_file)

with open(bib_file, 'rt') as file:
    latex = file.read()

text = LatexNodes2Text(keep_inline_math=True, strict_latex_spaces=True, keep_braced_groups=True).latex_to_text(latex)

with open(bib_file, 'wt') as file:
    file.write(text)

utf2ltx.py

#! /usr/bin/env python3

# Copyright (C) 2019  Mahito TANNO

# This is free and unencumbered software released into the public domain.

# Anyone is free to copy, modify, publish, use, compile, sell, or
# distribute this software, either in source code form or as a compiled
# binary, for any purpose, commercial or non-commercial, and by any
# means.

# In jurisdictions that recognize copyright laws, the author or authors
# of this software dedicate any and all copyright interest in the
# software to the public domain. We make this dedication for the benefit
# of the public at large and to the detriment of our heirs and
# successors. We intend this dedication to be an overt act of
# relinquishment in perpetuity of all present and future rights to this
# software under copyright law.

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.

# For more information, please refer to <http://unlicense.org>

"""
* Overview:
  This is my personal Python script which covert unicode accented characters
  to LaTeX commands.  Typically, I use this for BibTeX databases.

* Requirements:
  - Python3
  - pylatexenc

  You can install by `pip install pylatexenc`.

* Usage:
  `utf2ltx FILE.bib`.
"""

import os
import sys
import fileinput
from pylatexenc.latexencode import utf8tolatex

bib_file = sys.argv[1]

if not os.path.isfile(bib_file):
    print('Error: please input your file.')
    sys.exit(1)

with fileinput.FileInput(bib_file, inplace=True, backup='.bak') as file:
    for line in file:
        line = utf8tolatex(line, non_ascii_only=True)
        print(line, end='')