xdu/divatool
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

translate command now works with global languages

Browse source
This commit is contained in:
argoneus 2020-02-20 23:57:09 +01:00 • committed by Gitea
parent 9b998704e2
commit 15afb39759
2 changed files with 46 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

2
diva/quest.py
View file

@ -18,8 +18,6 @@ def scene_mst(qdb, old_path, dir_in, languages):
locations = load_locations(dir_in) locations = load_locations(dir_in)
print(locations)
for id, scene in scenes.items(): for id, scene in scenes.items():
i = 0 i = 0
while True: while True:

61
utage/translate.py
View file

@ -4,6 +4,7 @@ import io
import json import json
import os import os
import traceback import traceback
from contextlib import suppress
from functools import partial from functools import partial
from glob import glob from glob import glob
@ -49,9 +50,17 @@ def translate_file(file_in, tsv_out_dir, json_out_dir, is_global):
tsv_output_path = os.path.join( tsv_output_path = os.path.join(
tsv_out_dir, event_folder, "Scenario", "{}_t.tsv".format(id_num) tsv_out_dir, event_folder, "Scenario", "{}_t.tsv".format(id_num)
) )
json_output_path = os.path.join( languages = ["jpn"]
json_out_dir, event_folder, "{}_translations_jpn.json".format(id_num), if is_global:
) languages += ["enm", "zh", "ko"]
json_output_paths = {
lang: os.path.join(
json_out_dir,
event_folder,
"{}_translations_{}.json".format(id_num, lang),
)
for lang in languages
}
# need to create output paths and avoid races when threading # need to create output paths and avoid races when threading
if not os.path.exists(os.path.dirname(tsv_output_path)): if not os.path.exists(os.path.dirname(tsv_output_path)):
@ -61,16 +70,21 @@ def translate_file(file_in, tsv_out_dir, json_out_dir, is_global):
if e.errno != errno.EEXIST: if e.errno != errno.EEXIST:
raise raise
if not os.path.exists(os.path.dirname(json_output_path)): if not os.path.exists(os.path.dirname(json_output_paths["jpn"])):
try: try:
os.makedirs(os.path.dirname(json_output_path)) os.makedirs(os.path.dirname(json_output_paths["jpn"]))
except OSError as e: except OSError as e:
if e.errno != errno.EEXIST: if e.errno != errno.EEXIST:
raise raise
with open(file_in, "r") as tsv_file: with open(file_in, "r") as tsv_file:
tsv = csv.DictReader(tsv_file, delimiter="\t", quotechar='"') tsv = csv.DictReader(tsv_file, delimiter="\t", quotechar='"')
tsv_keyed, json_str = process_tsv(tsv, id_num)
t_fieldnames = tsv.fieldnames
if is_global:
t_fieldnames = tsv.fieldnames[: tsv.fieldnames.index("English") + 1]
tsv_keyed, json_str = process_tsv(tsv, id_num, is_global)
# csv handles newlines, don't set it in io.open # csv handles newlines, don't set it in io.open
with io.open(tsv_output_path, "w", newline="") as tsv_out: with io.open(tsv_output_path, "w", newline="") as tsv_out:
@ -79,28 +93,39 @@ def translate_file(file_in, tsv_out_dir, json_out_dir, is_global):
delimiter="\t", delimiter="\t",
quotechar='"', quotechar='"',
lineterminator="\n", lineterminator="\n",
fieldnames=tsv.fieldnames, fieldnames=t_fieldnames,
extrasaction="ignore", extrasaction="ignore",
) )
writer.writeheader() writer.writeheader()
for row in tsv_keyed: for row in tsv_keyed:
writer.writerow(row) writer.writerow(row)
with io.open(json_output_path, "w", newline="\n") as json_out: for lang in languages:
# we don't want to sort these because they're _1, ..., _10, etc if not json_str[lang]:
json.dump( continue
json_str, json_out, ensure_ascii=False, indent="\t", sort_keys=False, with io.open(json_output_paths[lang], "w", newline="\n") as json_out:
) # we don't want to sort these because they're _1, ..., _10, etc
json.dump(
json_str[lang],
json_out,
ensure_ascii=False,
indent="\t",
sort_keys=False,
)
except Exception: except Exception:
traceback.print_exc() traceback.print_exc()
print("Error processing file: " + file_in) print("Error processing file: " + file_in)
def process_tsv(tsv, id_num): def process_tsv(tsv, id_num, is_global):
i = 0 i = 0
tsv_keyed = [] tsv_keyed = []
key_dict = {} key_dict = {"jpn": {}}
if is_global:
key_dict["enm"] = {}
key_dict["zh"] = {}
key_dict["ko"] = {}
for row in tsv: for row in tsv:
try: try:
@ -110,8 +135,14 @@ def process_tsv(tsv, id_num):
if row["Text"] and row["Text"].strip(): if row["Text"] and row["Text"].strip():
key = "{}_{}".format(id_num, i) key = "{}_{}".format(id_num, i)
i += 1 i += 1
key_dict["jpn"][key] = row["Text"]
if is_global:
with suppress(KeyError):
if row["English"]:
key_dict["enm"][key] = row["English"]
key_dict["zh"][key] = row["Chinese"]
key_dict["ko"][key] = row["Korean"]
row["English"] = key row["English"] = key
key_dict[key] = row["Text"]
tsv_keyed.append(row) tsv_keyed.append(row)
except Exception: except Exception:
traceback.print_exc() traceback.print_exc()