update translation template

This commit is contained in:
FaceDeer 2020-02-20 23:31:10 -07:00
parent 1302803bf5
commit 4416d3f828
2 changed files with 328 additions and 53 deletions

359
i18n.py
View File

@ -1,31 +1,125 @@
#!/usr/bin/env python
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# Script to generate the template file and update the translation files.
# Copy the script into the mod or modpack root folder and run it there.
#
# Copyright (C) 2019 Joachim Stolberg
# Copyright (C) 2019 Joachim Stolberg, 2020 FaceDeer, 2020 Louis Royer
# LGPLv2.1+
from __future__ import print_function
import os, fnmatch, re, shutil, errno
from sys import argv as _argv
# Running params
params = {"recursive": False,
"help": False,
"mods": False,
"verbose": False,
"folders": []
}
# Available CLI options
options = {"recursive": ['--recursive', '-r'],
"help": ['--help', '-h'],
"mods": ['--installed-mods'],
"verbose": ['--verbose', '-v']
}
# Strings longer than this will have extra space added between
# them in the translation files to make it easier to distinguish their
# beginnings and endings at a glance
doublespace_threshold = 60
def set_params_folders(tab: list):
'''Initialize params["folders"] from CLI arguments.'''
# Discarding argument 0 (tool name)
for param in tab[1:]:
stop_param = False
for option in options:
if param in options[option]:
stop_param = True
break
if not stop_param:
params["folders"].append(os.path.abspath(param))
def set_params(tab: list):
'''Initialize params from CLI arguments.'''
for option in options:
for option_name in options[option]:
if option_name in tab:
params[option] = True
break
def print_help(name):
'''Prints some help message.'''
print(f'''SYNOPSIS
{name} [OPTIONS] [PATHS...]
DESCRIPTION
{', '.join(options["help"])}
prints this help message
{', '.join(options["recursive"])}
run on all subfolders of paths given
{', '.join(options["mods"])}
run on locally installed modules
{', '.join(options["verbose"])}
add output information
''')
def main():
'''Main function'''
set_params(_argv)
set_params_folders(_argv)
if params["help"]:
print_help(_argv[0])
elif params["recursive"] and params["mods"]:
print("Option --installed-mods is incompatible with --recursive")
else:
# Add recursivity message
print("Running ", end='')
if params["recursive"]:
print("recursively ", end='')
# Running
if params["mods"]:
print(f"on all locally installed modules in {os.path.abspath('~/.minetest/mods/')}")
run_all_subfolders("~/.minetest/mods")
elif len(params["folders"]) >= 2:
print("on folder list:", params["folders"])
for f in params["folders"]:
if params["recursive"]:
run_all_subfolders(f)
else:
update_folder(f)
elif len(params["folders"]) == 1:
print("on folder", params["folders"][0])
if params["recursive"]:
run_all_subfolders(params["folders"][0])
else:
update_folder(params["folders"][0])
else:
print("on folder", os.path.abspath("./"))
if params["recursive"]:
run_all_subfolders(os.path.abspath("./"))
else:
update_folder(os.path.abspath("./"))
#group 2 will be the string, groups 1 and 3 will be the delimiters (" or ')
#See https://stackoverflow.com/questions/46967465/regex-match-text-in-either-single-or-double-quote
#TODO: support [[]] delimiters
pattern_lua = re.compile(r'[\.=^\t,{\(\s]N?S\(\s*(["\'])((?:\\\1|(?:(?!\1)).)*)(\1)[\s,\)]', re.DOTALL)
pattern_lua_bracketed = re.compile(r'[\.=^\t,{\(\s]N?S\(\s*\[\[(.*?)\]\][\s,\)]', re.DOTALL)
# Handles "concatenation" .. " of strings"
pattern_concat = re.compile(r'["\'][\s]*\.\.[\s]*["\']', re.DOTALL)
pattern_tr = re.compile(r'(.+?[^@])=(.+)')
pattern_name = re.compile(r'^name[ ]*=[ ]*([^ ]*)')
pattern_tr = re.compile(r'(.+?[^@])=(.*)')
pattern_name = re.compile(r'^name[ ]*=[ ]*([^ \n]*)')
pattern_tr_filename = re.compile(r'\.tr$')
pattern_po_language_code = re.compile(r'(.*)\.po$')
#attempt to read the mod's name from the mod.conf file. Returns None on failure
def get_modname(folder):
try:
with open(folder + "mod.conf", "r", encoding='utf-8') as mod_conf:
with open(os.path.join(folder, "mod.conf"), "r", encoding='utf-8') as mod_conf:
for line in mod_conf:
match = pattern_name.match(line)
if match:
@ -37,12 +131,62 @@ def get_modname(folder):
#If there are already .tr files in /locale, returns a list of their names
def get_existing_tr_files(folder):
out = []
for root, dirs, files in os.walk(folder + 'locale/'):
for root, dirs, files in os.walk(os.path.join(folder, 'locale/')):
for name in files:
if pattern_tr_filename.search(name):
out.append(name)
return out
# A series of search and replaces that massage a .po file's contents into
# a .tr file's equivalent
def process_po_file(text):
# The first three items are for unused matches
text = re.sub(r'#~ msgid "', "", text)
text = re.sub(r'"\n#~ msgstr ""\n"', "=", text)
text = re.sub(r'"\n#~ msgstr "', "=", text)
# comment lines
text = re.sub(r'#.*\n', "", text)
# converting msg pairs into "=" pairs
text = re.sub(r'msgid "', "", text)
text = re.sub(r'"\nmsgstr ""\n"', "=", text)
text = re.sub(r'"\nmsgstr "', "=", text)
# various line breaks and escape codes
text = re.sub(r'"\n"', "", text)
text = re.sub(r'"\n', "\n", text)
text = re.sub(r'\\"', '"', text)
text = re.sub(r'\\n', '@n', text)
# remove header text
text = re.sub(r'=Project-Id-Version:.*\n', "", text)
# remove double-spaced lines
text = re.sub(r'\n\n', '\n', text)
return text
# Go through existing .po files and, if a .tr file for that language
# *doesn't* exist, convert it and create it.
# The .tr file that results will subsequently be reprocessed so
# any "no longer used" strings will be preserved.
# Note that "fuzzy" tags will be lost in this process.
def process_po_files(folder, modname):
for root, dirs, files in os.walk(os.path.join(folder, 'locale/')):
for name in files:
code_match = pattern_po_language_code.match(name)
if code_match == None:
continue
language_code = code_match.group(1)
tr_name = modname + "." + language_code + ".tr"
tr_file = os.path.join(root, tr_name)
if os.path.exists(tr_file):
if params["verbose"]:
print(f"{tr_name} already exists, ignoring {name}")
continue
fname = os.path.join(root, name)
with open(fname, "r", encoding='utf-8') as po_file:
if params["verbose"]:
print(f"Importing translations from {name}")
text = process_po_file(po_file.read())
with open(tr_file, "wt", encoding='utf-8') as tr_out:
tr_out.write(text)
# from https://stackoverflow.com/questions/600268/mkdir-p-functionality-in-python/600612#600612
# Creates a directory if it doesn't exist, silently does
# nothing if it already exists
@ -54,24 +198,93 @@ def mkdir_p(path):
pass
else: raise
# Converts the template dictionary to a text to be written as a file
# dKeyStrings is a dictionary of localized string to source file sets
# dOld is a dictionary of existing translations and comments from
# the previous version of this text
def strings_to_text(dkeyStrings, dOld, mod_name):
lOut = [f"# textdomain: {mod_name}\n"]
dGroupedBySource = {}
for key in dkeyStrings:
sourceList = list(dkeyStrings[key])
sourceList.sort()
sourceString = "\n".join(sourceList)
listForSource = dGroupedBySource.get(sourceString, [])
listForSource.append(key)
dGroupedBySource[sourceString] = listForSource
lSourceKeys = list(dGroupedBySource.keys())
lSourceKeys.sort()
for source in lSourceKeys:
localizedStrings = dGroupedBySource[source]
localizedStrings.sort()
lOut.append("")
lOut.append(source)
lOut.append("")
for localizedString in localizedStrings:
val = dOld.get(localizedString, {})
translation = val.get("translation", "")
comment = val.get("comment")
if len(localizedString) > doublespace_threshold and not lOut[-1] == "":
lOut.append("")
if comment != None:
lOut.append(comment)
lOut.append(f"{localizedString}={translation}")
if len(localizedString) > doublespace_threshold:
lOut.append("")
unusedExist = False
for key in dOld:
if key not in dkeyStrings:
val = dOld[key]
translation = val.get("translation")
comment = val.get("comment")
# only keep an unused translation if there was translated
# text or a comment associated with it
if translation != None and (translation != "" or comment):
if not unusedExist:
unusedExist = True
lOut.append("\n\n##### not used anymore #####\n")
if len(key) > doublespace_threshold and not lOut[-1] == "":
lOut.append("")
if comment != None:
lOut.append(comment)
lOut.append(f"{key}={translation}")
if len(key) > doublespace_threshold:
lOut.append("")
return "\n".join(lOut) + '\n'
# Writes a template.txt file
def write_template(templ_file, lkeyStrings):
lOut = []
lkeyStrings.sort()
for s in lkeyStrings:
lOut.append("%s=" % s)
# dkeyStrings is the dictionary returned by generate_template
def write_template(templ_file, dkeyStrings, mod_name):
# read existing template file to preserve comments
existing_template = import_tr_file(templ_file)
text = strings_to_text(dkeyStrings, existing_template[0], mod_name)
mkdir_p(os.path.dirname(templ_file))
with open(templ_file, "wt", encoding='utf-8') as template_file:
template_file.write("\n".join(lOut))
template_file.write(text)
# Gets all translatable strings from a lua file
def read_lua_file_strings(lua_file):
lOut = []
with open(lua_file, encoding='utf-8') as text_file:
text = text_file.read()
text = re.sub(pattern_concat, "", text)
#TODO remove comments here
text = re.sub(pattern_concat, "", text)
strings = []
for s in pattern_lua.findall(text):
s = s[1]
strings.append(s[1])
for s in pattern_lua_bracketed.findall(text):
strings.append(s)
for s in strings:
s = re.sub(r'"\.\.\s+"', "", s)
s = re.sub("@[^@=0-9]", "@@", s)
s = s.replace('\\"', '"')
@ -83,74 +296,112 @@ def read_lua_file_strings(lua_file):
return lOut
# Gets strings from an existing translation file
# returns both a dictionary of translations
# and the full original source text so that the new text
# can be compared to it for changes.
def import_tr_file(tr_file):
dOut = {}
text = None
if os.path.exists(tr_file):
with open(tr_file, "r", encoding='utf-8') as existing_file :
# save the full text to allow for comparison
# of the old version with the new output
text = existing_file.read()
existing_file.seek(0)
# a running record of the current comment block
# we're inside, to allow preceeding multi-line comments
# to be retained for a translation line
latest_comment_block = None
for line in existing_file.readlines():
s = line.strip()
if s == "" or s[0] == "#":
continue
match = pattern_tr.match(s)
line = line.rstrip('\n')
if line[:3] == "###":
# Reset comment block if we hit a header
latest_comment_block = None
continue
if line[:1] == "#":
# Save the comment we're inside
if not latest_comment_block:
latest_comment_block = line
else:
latest_comment_block = latest_comment_block + "\n" + line
continue
match = pattern_tr.match(line)
if match:
dOut[match.group(1)] = match.group(2)
return dOut
# this line is a translated line
outval = {}
outval["translation"] = match.group(2)
if latest_comment_block:
# if there was a comment, record that.
outval["comment"] = latest_comment_block
latest_comment_block = None
dOut[match.group(1)] = outval
return (dOut, text)
# Walks all lua files in the mod folder, collects translatable strings,
# and writes it to a template.txt file
def generate_template(folder):
lOut = []
# Returns a dictionary of localized strings to source file sets
# that can be used with the strings_to_text function.
def generate_template(folder, mod_name):
dOut = {}
for root, dirs, files in os.walk(folder):
for name in files:
if fnmatch.fnmatch(name, "*.lua"):
fname = os.path.join(root, name)
found = read_lua_file_strings(fname)
print(fname + ": " + str(len(found)) + " translatable strings")
lOut.extend(found)
lOut = list(set(lOut))
lOut.sort()
if len(lOut) == 0:
if params["verbose"]:
print(f"{fname}: {str(len(found))} translatable strings")
for s in found:
sources = dOut.get(s, set())
sources.add(f"### {os.path.basename(fname)} ###")
dOut[s] = sources
if len(dOut) == 0:
return None
templ_file = folder + "locale/template.txt"
write_template(templ_file, lOut)
return lOut
templ_file = os.path.join(folder, "locale/template.txt")
write_template(templ_file, dOut, mod_name)
return dOut
# Updates an existing .tr file, copying the old one to a ".old" file
def update_tr_file(lNew, mod_name, tr_file):
print("updating " + tr_file)
lOut = ["# textdomain: %s\n" % mod_name]
# if any changes have happened
# dNew is the data used to generate the template, it has all the
# currently-existing localized strings
def update_tr_file(dNew, mod_name, tr_file):
if params["verbose"]:
print(f"updating {tr_file}")
#TODO only make a .old if there are actual changes from the old file
if os.path.exists(tr_file):
shutil.copyfile(tr_file, tr_file+".old")
tr_import = import_tr_file(tr_file)
dOld = tr_import[0]
textOld = tr_import[1]
textNew = strings_to_text(dNew, dOld, mod_name)
if textOld and textOld != textNew:
print(f"{tr_file} has changed.")
shutil.copyfile(tr_file, f"{tr_file}.old")
dOld = import_tr_file(tr_file)
for key in lNew:
val = dOld.get(key, "")
lOut.append("%s=%s" % (key, val))
lOut.append("##### not used anymore #####")
for key in dOld:
if key not in lNew:
lOut.append("%s=%s" % (key, dOld[key]))
with open(tr_file, "w", encoding='utf-8') as new_tr_file:
new_tr_file.write("\n".join(lOut))
new_tr_file.write(textNew)
# Updates translation files for the mod in the given folder
def update_mod(folder):
modname = get_modname(folder)
if modname is not None:
print("Updating translations for " + modname)
data = generate_template(folder)
process_po_files(folder, modname)
print(f"Updating translations for {modname}")
data = generate_template(folder, modname)
if data == None:
print("No translatable strings found in " + modname)
print(f"No translatable strings found in {modname}")
else:
for tr_file in get_existing_tr_files(folder):
update_tr_file(data, modname, folder + "locale/" + tr_file)
update_tr_file(data, modname, os.path.join(folder, "locale/", tr_file))
else:
print("Unable to find modname in folder " + folder)
# Determines if the folder being pointed to is a mod or a mod pack
# and then runs update_mod accordingly
def update_folder(folder):
is_modpack = os.path.exists(folder+"modpack.txt") or os.path.exists(folder+"modpack.conf")
is_modpack = os.path.exists(os.path.join(folder, "modpack.txt")) or os.path.exists(os.path.join(folder, "modpack.conf"))
if is_modpack:
subfolders = [f.path for f in os.scandir(folder) if f.is_dir()]
for subfolder in subfolders:
@ -159,5 +410,9 @@ def update_folder(folder):
update_mod(folder)
print("Done.")
def run_all_subfolders(folder):
for modfolder in [f.path for f in os.scandir(folder) if f.is_dir()]:
update_folder(modfolder + "/")
update_folder("./")
main()

View File

@ -1,22 +1,42 @@
# textdomain: commoditymarket_fantasy
### init.lua ###
A gold ingot is far too valuable to use as a basic unit of value, so it has become common practice to divide the standard gold bar into @1 small disks to make trade easier.=
At this time of day the King's Market is closed.=
At this time of day the Night Market is closed.=
Caravan summoned@nETA: @1 seconds.=
Deep in the bowels of the world, below even the goblin-infested warrens and ancient delvings of the dwarves, dark and mysterious beings once dwelt. A few still linger to this day, and facilitate barter for those brave souls willing to travel in their lost realms. The Undermarket uses Mese chips ('₥') as a currency - twenty chips to the Mese fragment. Though traders are loathe to physically break Mese crystals up into units that small, as it renders it useless for other purposes.=
Goblin Exchange=
Gold Coins=
Gold coins can be deposited and withdrawn from markets that accept them as currency. These markets can make change if you have @1 coins and would like them back in ingot form again.=
Indicated parking area isn't suitable.@nA 5x3 open space with solid ground@nis required for a caravan.=
King's Market=
Night Market=
One does not usually associate Goblins with the sort of sophistication that running a market requires. Usually one just associates Goblins with savagery and violence. But they understand the principle of tit-for-tat exchange, and if approached correctly they actually respect the concepts of ownership and debt. However, for some peculiar reason they understand this concept in the context of coal lumps. Goblins deal in the standard coal lump as their form of currency, conceptually divided into 100 coal centilumps (though Goblin brokers prefer to "keep the change" when giving back actual coal lumps).=
Right-click on this to open the market interface.=
Right-click to summon a trader's caravan=
The largest and most accessible market for the common man, the King's Market uses gold coins as its medium of exchange (or the equivalent in gold ingots - @1 coins to the ingot). However, as a respectable institution of the surface world, the King's Market operates only during the hours of daylight. The purchase and sale of swords and explosives is prohibited in the King's Market. Gold coins are represented by a '☼' symbol.=
The trader's caravan requires a suitable open space next to the trading post for it to arrive, and takes some time to arrive after being summoned. The post gives a countdown to the caravan's arrival when moused over.=
This post signals passing caravan traders that customers can be found here, and signals to customers that caravan traders can be found here. If no caravan is present, right-click to summon one.=
Trader's Caravan=
Trading Post=
Undermarket=
Unlike most markets that have well-known fixed locations that travelers congregate to, the network of Trader's Caravans is fluid and dynamic in their locations. A Trader's Caravan can show up anywhere, make modest trades, and then be gone the next time you visit them. These caravans accept gold and gold coins as a currency (one gold ingot to @1 gold coins exchange rate). Any reasonably-wealthy person can create a signpost marking a location where Trader's Caravans will make a stop.=
When the sun sets and the stalls of the King's Market close, other vendors are just waking up to share their wares. The Night Market is not as voluminous as the King's Market but accepts a wider range of wares. It accepts the same gold coinage of the realm, @1 coins to the gold ingot.=
When the sun sets and the stalls of the King's Market close, other vendors are just waking up to share their wares. The Night Market is not as voluminous as the King's Market but accepts a wider range of wares. It accepts the same gold coinage of the realm, @1 coins to the gold ingot.=