Skip to content

Instantly share code, notes, and snippets.

@basil
Created March 6, 2022 00:20
Show Gist options
  • Save basil/309c721bb3a24ffe313dff60c84fcb35 to your computer and use it in GitHub Desktop.
Save basil/309c721bb3a24ffe313dff60c84fcb35 to your computer and use it in GitHub Desktop.
#!/usr/bin/env python3
# The MIT License
#
# Copyright (c) 2004-, Kohsuke Kawaguchi, Sun Microsystems, Inc., and a number
# of other of contributors
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# 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 OR COPYRIGHT HOLDERS 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.
"""
Python script to generate missing translation keys and missing properties files,
to remove unused keys, and to convert utf8 properties files to iso or ascii.
1. It recursively looks for files in a folder, and analyzes them to extract
the keys being used in the application.
2. If --add=true, it generates the appropriate file for the desired language
and adds these keys to it, adding the english text as a reference. If the
properties file already exists the script update it with the new keys.
3. When --remove=true and there are unused keys in our file, the script
removes them.
4. If an editor is passed as argument, the script edits each modified file
after adding new keys.
5. Finally, when --toiso=true or --toascii=true, the script is able to
convert utf-8 properties files to iso or unicode hex representation is
ascii.
Note, while the migration to Jenkins this file will report the keys which
should point to Jenkins instead of the old name.
"""
import argparse
import functools
import glob
import itertools
import os
import re
import chardet.universaldetector
def main():
parser = argparse.ArgumentParser(description="Translation Tool for Jenkins")
parser.add_argument(
"--dir",
default="./",
help="source folder for searching files (default is the current directory)",
)
parser.add_argument(
"lang",
help="language code to use (it is mandatory and it has to be different "
"from English)",
)
group = parser.add_mutually_exclusive_group()
group.add_argument(
"--to-iso",
help="enables files in UTF-8 conversion to ISO-8859 if present",
action="store_true",
)
group.add_argument(
"--to-ascii",
help="convert files in UTF-8 to ASCII using the native2ascii command "
"if present",
action="store_true",
)
parser.add_argument(
"--add",
help="generate new files and add new keys to existing files if present",
action="store_true",
)
parser.add_argument(
"--remove",
help="remove unused key/value pair for existing files if present",
action="store_true",
)
parser.add_argument(
"--editor",
metavar="FOLDER",
help="command to run over each updated file, implies --add if present",
)
parser.add_argument(
"--reuse",
metavar="FOLDER",
help="load a cache with keys already translated in the folder provided "
"in order to utilize them when the same key appears if present",
)
parser.add_argument(
"--counter",
help="to each translated key, unique value is added to easily identify "
"match missing translation with value in source code if present",
action="store_true",
)
parser.add_argument(
"--target", metavar="FOLDER", help="target folder for writing files"
)
parser.add_argument(
"--debug",
help="print debugging messages to STDOUT when they are available",
action="store_true",
)
global tfiles
global tkeys
global tmissing
global tunused
global tempty
global tsame
global tnojenkins
global countervalue
tfiles = 0
tkeys = 0
tmissing = 0
tunused = 0
tempty = 0
tsame = 0
tnojenkins = 0
countervalue = 1
global args
args = parser.parse_args()
if args.editor is not None:
args.add = True
# language parameter is mandatory and shouldn't be 'en'
if args.lang == "en":
parser.print_help()
exit(1)
print("Searching for files ...")
# look for Message.properties and *.jelly files in the provided folder
files = find_translatable_files(args.dir)
print(f"Found {len(files)} files")
# load a cache with keys already translated to utilize in the case the same
# key is used
if args.reuse and os.path.isdir(args.reuse):
cache = load_all_translated_keys(args.reuse, args.lang)
# process each file
for file in files:
tfiles += 1
process_file(file)
# print statistics
tdone = tkeys - tmissing - tunused - tempty - tsame - tnojenkins
pdone = 100
pmissing = 0
punused = 0
pempty = 0
psame = 0
pnojenkins = 0
if tkeys != 0:
pdone = tdone / tkeys * 100
pmissing = tmissing / tkeys * 100
punused = tunused / tkeys * 100
pempty = tempty / tkeys * 100
psame = tsame / tkeys * 100
pnojenkins = tnojenkins / tkeys * 100
print()
print(f"TOTAL: Files: {tfiles} Keys: {tkeys} Done: {tdone}({pdone:.2f}%)\n")
print(
" Missing: %d(%.2f%%) Orphan: %d(%.2f%%) Empty: %d(%.2f%%)"
"Same: %d(%.2f%%) NoJenkins: %d(%.2f%%)\n\n"
% (
tmissing,
pmissing,
tunused,
punused,
tempty,
pempty,
tsame,
psame,
tnojenkins,
pnojenkins,
)
)
def process_file(file):
"""This is the main method which is run for each file."""
# ofile -> output file in the current language,
# efile -> english file
ofile = file
if args.target:
ofile = ofile.replace(args.dir, args.target)
ofile = ofile.replace(".jelly", f"_{args.lang}.properties")
ofile = ofile.replace(".properties", f"_{args.lang}.properties")
efile = file.replace(".jelly", ".properties")
# keys -> Hash of keys used in jelly or Message.properties files
# ekeys -> Hash of key/values in English
# okeys -> Hash of key/values in the desired language which are already
# present in the file
keys = okeys = ekeys = None
# Read .jelly or Message.properties files, and fill a hash with the keys
# found
if file.endswith(".jelly"):
keys = load_jelly_file(file)
ekeys = load_properties_file(efile)
else:
keys = ekeys = load_properties_file(file)
# load keys already present in the desired locale
okeys = load_properties_file(ofile)
# calculate missing keys in the file
missing = ""
for key in keys:
tkeys += 1
if not okeys != None:
if cache != None:
default_var += f"={cache[default_var]}"
missing += f"{' Adding ' if add else ' Missing'} -> {default_var}\n"
tmissing += 1
elif okeys[default_var] == "":
missing += f" Empty -> {default_var}\n"
tempty += 1
# calculate old keys in the file which are currently unused
unused = ""
for key in okeys:
if not keys != none:
unused += f" Unused -> {default_var}\n"
tunused += 1
# calculate keys which have the same value in English
same = ""
for key in okeys:
if (
okeys[default_var]
and ekeys[default_var]
and okeys[default_var] == ekeys[default_var]
):
same += f" Same -> {default_var}\n"
tsame += 1
nj = ""
for key in okeys:
if okeys[default_var] and re.match("Hudson", okeys[default_var]):
nj += f" Non Jenkins -> {default_var} -> {okeys[_]}\n"
tnojenkins += 1
# Show Alerts
if missing != "" or unused != "" or same != "" or nj != "":
print()
# write new keys in our file adding the English translation as a reference
if add and missing != "":
if not os.path.isfile(ofile):
print_license(ofile)
with open(f">{ofile}", "w") as F:
for key in okeys:
if not okeys[default_var]:
if not okeys != none:
print(file=F)
if cache != none:
print(f"{cache[default_var]}", file=F)
else:
if counter:
# add unique value for each added translation
print(
"---TranslateMe "
+ countervalue
+ "--- "
+ (
ekeys[default_var]
if ekeys[default_var]
else default_var
)
+ "",
file=F,
)
else:
print(file=F)
countervalue += 1
# open the editor if the user has specified it and there are changes to
# manage
if editor and add and (todo != "" or same != "" or nj != ""):
os.system(f"{editor} {ofile}")
# write new keys in our file adding the English translation as a reference
if remove and unused != "":
remove_unused_keys(ofile, keys)
# convert the language file to ISO or ASCII which are
# the charsets which Jenkins supports right now
if os.path.isfile(ofile):
convert(ofile, toiso, toascii)
def load_all_translated_keys(directory, lang):
"""Create a hash with all keys which exist and have an unique value"""
files = find_translatable_files(directory)
for files in re.match("(\.jelly)|(\.properties)"):
if not os.path.isfile(default_var):
continue
[h, k, v] = load_properties_file(default_var)
for k, v in h:
if ret != none and v != ret[k]:
ret[k] = ""
if not ret != none:
ret[k] = v
return ret
def find_translatable_files(directory):
"""Look for Message.properties and *.jelly files"""
if not os.path.exists(directory):
raise ValueError(f"Folder doesn't exist: {dir}")
ret = []
for file in itertools.chain(
glob.glob(
os.path.join(os.path.join(directory, "**"), "Messages.properties"),
recursive=True,
),
glob.glob(
os.path.join(os.path.join(directory, "**"), "*.jelly"), recursive=True
),
):
if "/src/test/" not in file and "/target/" not in file:
ret.append(file)
ret.sort()
return ret
def load_jelly_file(jelly_file):
"""Fill a hash with key/1 pairs from a .jelly file"""
ret = {}
with open(jelly_file) as f:
for line in f:
# TODO
# if not re.match("[ + *?%([^\(]+?\) + *]", line):
# continue
match = re.match("^.*?\$\{\%([^\(\}]+)(.*)$", line)
if not match:
match = re.match("""^.*?\$\{.*?['"]\%([^\(\}\"\']+)(.*)$""", line)
if match:
line = match.group(2)
word = match.group(1)
word = str.replace("\(.+$", "\(.+$", word)
word = re.sub("'+", "''", word)
word = re.sub(" ", "\\ ", word)
word = re.sub("\>", ">", word)
word = re.sub("\&lt;", "<", word)
word = re.sub("\&amp;", "&", word)
word = re.sub("([#:=])", "\$1", word)
ret[word] = 1
return ret
def load_properties_file(file):
"""Fill a hash with key/value pairs from a .properties file"""
ret = {}
if args.debug:
print(f"Trying to load {file}... ", end="")
if not os.path.isfile(file):
if args.debug:
print("file does not exist, skipping.")
return ret
if args.debug:
print("done.")
cont = False
key = None
with open(file, "r") as f:
for line in f:
line = line.rstrip()
if not line:
continue
# TODO next if $_=~ qr/^#/;
if args.debug:
print(f"Line: {line}")
line = line.replace("[\r\n]+")
match = re.match("\s*(.*)[\\\s]*$", line)
if cont and match:
ret[key] = "\n" + match.group(1)
match = re.match("^([^#\s].*?[^\\])=(.*)[\s\\]*$", line)
if match:
key = trim(match.group(1))
val = trim(match.group(2))
ret[key] = val
if re.match("\\\s*$", line):
cont = True
else:
cont = False
match = re.match("\s*(.*)[\\\s]*$", line)
if cont and match:
ret[key] = "\n" + match.group(1)
return ret
def remove_unused_keys(ofile, keys):
"""Remove unused keys from a file."""
print()
back = f"{ofile}~~"
if rename(ofile, back):
with open(back, "w") as FI, open(f"{ofile}", "w") as FO:
cont = 0
while FI.readline():
if not cont:
if re.match("^([^#\s].*?[^\\])=(.*)[\s\\]*$", default_var):
if not keys[default_match.group(1)]:
cont = 1 if re.match("\\\s*$", default_var) else 0
continue
print(file=FO)
else:
cont = 0
os.unlink(back)
def convert(ofile, toiso, toascii):
"""Convert a UTF-8 file to either ISO-8859 or ASCII."""
if is_utf8(ofile) and (todo or toascii):
print(f"\nConverting file {ofile} to {'ISO-8859' if toiso else 'ASCII'}")
back = f"{ofile}~~"
if rename(ofile, back):
with open(back, "w") as FI, open(f"{ofile}", "w") as FO:
while FI.readline():
if toiso:
re.match(
re.compile("([\xC2\xC3])([\x80-\xBF])", re.E, re.G),
default_var,
)
else:
re.match("([\xC0-\xDF])([\x80-\xBF])", default_var)
print(file=FO)
os.unlink(back)
def is_utf8(file):
"""Return true if the file has any UTF-8 character."""
detector = chardet.universaldetector.UniversalDetector()
try:
with open(file, "rb") as f:
for line in f:
detector.feed(line)
if detector.done:
break
finally:
detector.close()
return (
detector.result["encoding"] == "utf-8" and detector.result["confidence"] > 0.95
)
@functools.lru_cache
def get_license():
"""
Get the text of the MIT license.
Note: the license is read from the head of this file
"""
license = ""
with open(__file__, "r") as f:
on = False
for line in f:
if not on and "The MIT" in line:
on = True
if on and (not line or not line.startswith("#")):
break
if on:
license += line
return license
def print_license(file):
"""Print MIT license in new files."""
if get_license():
dirname = os.path.dirname(file)
if not os.path.isdir(dirname):
os.makedirs(dirname)
with open(file, "w") as f:
print(get_license(), file=f)
def trim(string):
"""Remove whitespace from the start and end of the string."""
return string.strip()
if __name__ == "__main__":
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment