add: using opencc project to transform chinese

This commit is contained in:
afunTW 2020-10-06 00:57:18 +08:00
parent 96a6ef3ced
commit 334425a783
3 changed files with 70 additions and 0 deletions

13
Pipfile Normal file
View File

@ -0,0 +1,13 @@
[[source]]
url = "https://pypi.org/simple"
verify_ssl = true
name = "pypi"
[packages]
opencc = "*"
click = "*"
[dev-packages]
[requires]
python_version = "3.6"

36
Pipfile.lock generated Normal file
View File

@ -0,0 +1,36 @@
{
"_meta": {
"hash": {
"sha256": "e11e067f853c70dd2660c4e3d606219472ef597161bcf00ffcd63872df1183bf"
},
"pipfile-spec": 6,
"requires": {
"python_version": "3.6"
},
"sources": [
{
"name": "pypi",
"url": "https://pypi.org/simple",
"verify_ssl": true
}
]
},
"default": {
"click": {
"hashes": [
"sha256:d2b5255c7c6349bc1bd1e59e08cd12acbbd63ce649f2588755783aa94dfb6b1a",
"sha256:dacca89f4bfadd5de3d7489b7c8a566eee0d3676333fbb50030263894c38c0dc"
],
"index": "pypi",
"version": "==7.1.2"
},
"opencc": {
"hashes": [
"sha256:1e0d40581dd5130ac3160f97e752caff202aa22aa004d468496fa8cba81035e7"
],
"index": "pypi",
"version": "==1.1.1.post1"
}
},
"develop": {}
}

21
transform.py Normal file
View File

@ -0,0 +1,21 @@
"""Convert zh-cn to zh-tw
Refer to https://github.com/BYVoid/OpenCC
"""
import click
import opencc
@click.command()
@click.option("-i", "--input", "infile", required=True)
@click.option("-o", "--output", "outfile", required=True)
@click.option("-c", "--config", "cfg", required=True, default="s2twp.json")
def main(infile, outfile, cfg):
converter = opencc.OpenCC(cfg)
with open(infile, "r") as inf, open(outfile, "w+") as outf:
data = inf.readlines()
data = list(map(converter.convert, data))
outf.writelines(data)
if __name__ == "__main__":
main()