Skip to content

Commit f73fe76

Browse files
thinkyheadthinkyhead
committed
🌐 Language export to CSV
1 parent d20ce5f commit f73fe76

File tree

4 files changed

+199
-4
lines changed

4 files changed

+199
-4
lines changed

‎.gitignore

+2
Original file line numberDiff line numberDiff line change
@@ -25,6 +25,8 @@ bdf2u8g.exe
2525
genpages.exe
2626
marlin_config.json
2727
mczip.h
28+
language*.csv
29+
csv-out/
2830
*.gen
2931
*.sublime-workspace
3032

‎Marlin/src/lcd/language/language_el_gr.h

+1-1
Original file line numberDiff line numberDiff line change
@@ -147,7 +147,7 @@ namespace Language_el_gr {
147147
LSTR MSG_STORE_EEPROM = _UxGT("Αποθήκευση");
148148
LSTR MSG_LOAD_EEPROM = _UxGT("Φόρτωση");
149149
LSTR MSG_RESTORE_DEFAULTS = _UxGT("Επαναφορά ασφαλούς αντιγράφου");
150-
LSTR MSG_REFRESH = LCD_STR_REFRESH _UxGT("Ανανέωση");
150+
LSTR MSG_REFRESH = LCD_STR_REFRESH _UxGT("Ανανέωση");
151151
LSTR MSG_INFO_SCREEN = _UxGT("Οθόνη πληροφόρησης");
152152
LSTR MSG_PREPARE = _UxGT("Προετοιμασία");
153153
LSTR MSG_TUNE = _UxGT("Συντονισμός");

‎buildroot/share/scripts/exportTranslations.py

+193
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,193 @@
1+
#!/usr/bin/env python3
2+
#
3+
# exportTranslations.py
4+
#
5+
# Export LCD language strings to CSV files for easier translation.
6+
# Use importTranslations.py to import CSV into the language files.
7+
#
8+
9+
import re
10+
from pathlib import Path
11+
12+
# Write multiple sheets if true, otherwise write one giant sheet
13+
MULTISHEET = True
14+
15+
# Where to look for the language files
16+
LANGHOME = "Marlin/src/lcd/language"
17+
18+
# Check for the path to the language files
19+
if not Path(LANGHOME).is_dir():
20+
print("Error: Couldn't find the '%s' directory." % LANGHOME)
21+
print("Edit LANGHOME or cd to the root of the repo before running.")
22+
exit(1)
23+
24+
# A dictionary to contain language names
25+
LANGNAME = {
26+
'an': "Aragonese",
27+
'bg': "Bulgarian",
28+
'ca': "Catalan",
29+
'cz': "Czech",
30+
'da': "Danish",
31+
'de': "German",
32+
'el': "Greek", 'el_CY': "Greek (Cyprus)", 'el_gr': "Greek (Greece)",
33+
'en': "English",
34+
'es': "Spanish",
35+
'eu': "Basque-Euskera",
36+
'fi': "Finnish",
37+
'fr': "French", 'fr_na': "French (no accent)",
38+
'gl': "Galician",
39+
'hr': "Croatian (Hrvatski)",
40+
'hu': "Hungarian / Magyar",
41+
'it': "Italian",
42+
'jp_kana': "Japanese (Kana)",
43+
'ko_KR': "Korean",
44+
'nl': "Dutch",
45+
'pl': "Polish",
46+
'pt': "Portuguese", 'pt_br': "Portuguese (Brazil)",
47+
'ro': "Romanian",
48+
'ru': "Russian",
49+
'sk': "Slovak",
50+
'sv': "Swedish",
51+
'tr': "Turkish",
52+
'uk': "Ukrainian",
53+
'vi': "Vietnamese",
54+
'zh_CN': "Simplified Chinese", 'zh_TW': "Traditional Chinese"
55+
}
56+
57+
# A limit just for testing
58+
LIMIT = 0
59+
60+
# A dictionary to contain strings for each language.
61+
# Init with 'en' so English will always be first.
62+
language_strings = { 'en': 0 }
63+
64+
# A dictionary to contain all distinct LCD string names
65+
names = {}
66+
67+
# Get all "language_*.h" files
68+
langfiles = sorted(list(Path(LANGHOME).glob('language_*.h')))
69+
70+
# Read each language file
71+
for langfile in langfiles:
72+
# Get the language code from the filename
73+
langcode = langfile.name.replace('language_', '').replace('.h', '')
74+
75+
# Skip 'test' and any others that we don't want
76+
if langcode in ['test']: continue
77+
78+
# Open the file
79+
f = open(langfile, 'r', encoding='utf-8')
80+
if not f: continue
81+
82+
# Flags to indicate a wide or tall section
83+
wideflag = False
84+
tallflag = False
85+
# A counter for the number of strings in the file
86+
stringcount = 0
87+
# A dictionary to hold all the strings
88+
strings = { 'narrow': {}, 'wide': {}, 'tall': {} }
89+
# Read each line in the file
90+
for line in f:
91+
# Clean up the line for easier parsing
92+
line = line.split("//")[0].strip()
93+
if line.endswith(';'): line = line[:-1].strip()
94+
95+
# Check for wide or tall sections, assume no complicated nesting
96+
if line.startswith("#endif") or line.startswith("#else"):
97+
wideflag = False
98+
tallflag = False
99+
elif re.match(r'#if.*WIDTH\s*>=?\s*2[01].*', line): wideflag = True
100+
elif re.match(r'#if.*LCD_HEIGHT\s*>=?\s*4.*', line): tallflag = True
101+
102+
# For string-defining lines capture the string data
103+
match = re.match(r'LSTR\s+([A-Z0-9_]+)\s*=\s*(.+)\s*', line)
104+
if match:
105+
# The name is the first captured group
106+
name = match.group(1)
107+
# The value is the second captured group
108+
value = match.group(2)
109+
# Replace escaped quotes temporarily
110+
value = value.replace('\\"', '__Q__')
111+
112+
# Remove all _UxGT wrappers from the value in a non-greedy way
113+
value = re.sub(r'_UxGT\((".*?")\)', r'\1', value)
114+
115+
# Multi-line strings will get one or more bars | for identification
116+
multiline = 0
117+
multimatch = re.match(r'.*MSG_(\d)_LINE\s*\(\s*(.+?)\s*\).*', value)
118+
if multimatch:
119+
multiline = int(multimatch.group(1))
120+
value = '|' + re.sub(r'"\s*,\s*"', '|', multimatch.group(2))
121+
122+
# Wrap inline defines in parentheses
123+
value = re.sub(r' *([A-Z0-9]+_[A-Z0-9_]+) *', r'(\1)', value)
124+
# Remove quotes around strings
125+
value = re.sub(r'"(.*?)"', r'\1', value).replace('__Q__', '"')
126+
# Store all unique names as dictionary keys
127+
names[name] = 1
128+
# Store the string as narrow or wide
129+
strings['tall' if tallflag else 'wide' if wideflag else 'narrow'][name] = value
130+
131+
# Increment the string counter
132+
stringcount += 1
133+
# Break for testing
134+
if LIMIT and stringcount >= LIMIT: break
135+
136+
# Close the file
137+
f.close()
138+
# Store the array in the dict
139+
language_strings[langcode] = strings
140+
141+
# Get the language codes from the dictionary
142+
langcodes = list(language_strings.keys())
143+
144+
# Print the array
145+
#print(language_strings)
146+
147+
# Write a single language entry to the CSV file with narrow, wide, and tall strings
148+
def write_csv_lang(f, strings, name):
149+
f.write(',')
150+
if name in strings['narrow']: f.write('"%s"' % strings['narrow'][name])
151+
f.write(',')
152+
if name in strings['wide']: f.write('"%s"' % strings['wide'][name])
153+
f.write(',')
154+
if name in strings['tall']: f.write('"%s"' % strings['tall'][name])
155+
156+
if MULTISHEET:
157+
#
158+
# Export a separate sheet for each language
159+
#
160+
OUTDIR = 'csv-out'
161+
Path.mkdir(Path(OUTDIR), exist_ok=True)
162+
163+
for lang in langcodes:
164+
f = open("%s/language_%s.csv" % (OUTDIR, lang), 'w', encoding='utf-8')
165+
if not f: continue
166+
167+
lname = lang + ' ' + LANGNAME[lang]
168+
header = ['name', lname, lname + ' (wide)', lname + ' (tall)']
169+
f.write('"' + '","'.join(header) + '"\n')
170+
171+
for name in names.keys():
172+
f.write('"' + name + '"')
173+
write_csv_lang(f, language_strings[lang], name)
174+
f.write('\n')
175+
f.close()
176+
177+
else:
178+
#
179+
# Export one large sheet containing all languages
180+
#
181+
f = open("languages.csv", 'w', encoding='utf-8')
182+
if f:
183+
header = ['name']
184+
for lang in langcodes:
185+
lname = lang + ' ' + LANGNAME[lang]
186+
header += [lname, lname + ' (wide)', lname + ' (tall)']
187+
f.write('"' + '","'.join(header) + '"\n')
188+
189+
for name in names.keys():
190+
f.write('"' + name + '"')
191+
for lang in langcodes: write_csv_lang(f, language_strings[lang], name)
192+
f.write('\n')
193+
f.close()

‎buildroot/share/scripts/findMissingTranslations.sh

+3-3
Original file line numberDiff line numberDiff line change
@@ -23,9 +23,9 @@ langname() {
2323
it ) echo "Italian" ;; jp_kana) echo "Japanese (Kana)" ;;
2424
ko_KR) echo "Korean" ;; nl ) echo "Dutch" ;;
2525
pl ) echo "Polish" ;; pt ) echo "Portuguese" ;;
26-
pt_br) echo "Portuguese (Brazil)" ;; ru ) echo "Russian" ;;
27-
sk ) echo "Slovak" ;; sv ) echo "Swedish" ;;
28-
test ) echo "TEST" ;; tr ) echo "Turkish" ;;
26+
pt_br) echo "Portuguese (Brazil)" ;; ro ) echo "Romanian" ;;
27+
ru ) echo "Russian" ;; sk ) echo "Slovak" ;;
28+
sv ) echo "Swedish" ;; tr ) echo "Turkish" ;;
2929
uk ) echo "Ukrainian" ;; vi ) echo "Vietnamese" ;;
3030
zh_CN) echo "Simplified Chinese" ;; zh_TW ) echo "Traditional Chinese" ;;
3131
* ) echo "<unknown>" ;;

0 commit comments

Comments
 (0)