def semiticListTransliterate(charlist, script2, fix=''):
results = {}
results['Latn'] = charlist.replace('،', ',').split(',')
results['script2'] = transliterate.process('Latn',
script2,
charlist,
nativize=False).replace(
'،', ',').split(',')
results['script2R'] = transliterate.process(script2, 'Latn', transliterate.process('Latn', script2, charlist, nativize=False))\
.replace('،',',').split(',')
results['script2G'] = transliterate.process('Brahmi', script2, transliterate.process('Latn', 'Brah', charlist))\
.replace('،',',').split(',')
results['script2GR'] = transliterate.process('Brah', 'Latn', transliterate.process('Latn', 'Brah', charlist))\
.replace('،',',').split(',')
for script in GM.SemiticScripts:
if script != 'Latn' and script != 'Arab-Ph' and script != 'Arab-Ga':
#print(script)
results[script] = transliterate.process('Latn', script, charlist, nativize=False)\
.replace('،',',').split(',')
results[script + 'R'] = transliterate.process(script, 'Latn', \
transliterate.process('Latn', script, charlist, nativize=False), nativize=False)\
.replace('،',',').split(',')
if fix == 'alephA':
results['script2R'][0] = 'ʾ'
elif fix == 'inherentA':
results['script2R'][0] += 'a'
return results
def convertNumerals(bnLine, enLine):
newBnLine, newEnLine = bnLine, enLine
for enNumeral in re.findall(r'[0-9]+', newBnLine, flags=re.UNICODE):
newBnLine = newBnLine.replace(
enNumeral,
transliterate.process('RomanReadable', 'Bengali', enNumeral), 1)
for bnNumeral in re.findall(r'[০-৯]+', newEnLine, flags=re.UNICODE):
newEnLine = newEnLine.replace(
bnNumeral,
transliterate.process('Bengali', 'RomanReadable', bnNumeral), 1)
return newBnLine, newEnLine
def get(self, uid, target):
db = get_db()
results = db.aql.execute(SUTTA_SINGLE_PALI_TEXT,
bind_vars={'uid': uid})
result = next(results)
if not result:
return {'error': 'Not Found'}, 404
sutta_texts = {k: json_load(v) for k, v in result.items()}
for key, value in sutta_texts[uid].items():
sutta_texts[uid][key] = transliterate.process('ISO', target, value)
return sutta_texts[uid]
def romanize_file(fname):
with codecs.open(fname + ".txt", encoding='utf-8') as f:
parsed = f.readlines()
parsed = [x.strip() for x in parsed]
trans_list = []
print(parsed)
for word in parsed:
text = word
translated_txt = transliterate.process('Telugu', 'ISO', word)
print(word)
print(translated_txt)
trans_list.append(translated_txt)
with io.open(fname + "_transliterated.txt", "w", encoding="utf-8") as f:
for padam in trans_list:
f.write(padam + '\n')
return trans_list
def get(self, target, text):
return transliterate.process('IAST', target, text)
def main(argv):
global GOOGLE_SHEETS_FILE_ID
global prevSection
global section
global title
global bookName
try:
opts, args = getopt.getopt(argv, "i:b:", ["InputFile=", "BookName="])
except getopt.GetoptError:
print('pg.py [-i] <GoogleSheetId> [-b <BookName>]')
sys.exit(2)
for opt, arg in opts:
if opt in ("-i", "--ifile"):
GOOGLE_SHEETS_FILE_ID = arg
elif opt in ("-b", "--BookName"):
bookName = arg
if GOOGLE_SHEETS_FILE_ID == '' or bookName == '':
print('pg.py [-i] <GoogleSheetId> [-b <BookName>]')
sys.exit()
google_client = pygsheets.authorize()
spreadsheet = google_client.open_by_key(GOOGLE_SHEETS_FILE_ID)
wks_list = spreadsheet.worksheets()
dirname = path.dirname(__file__)
wks = wks_list[0]
count = 0
firstPageList = ''
target = []
targetTransliterated = []
firstTime = True
#wks = [*wks]
makeLists(
wks
) # prepare the index tables for chapter pages and chapters, if any.
prevSection = ''
section = ''
for row in [*wks][1:]:
verseNumber = row[verseNumberCol]
if firstTime:
prevSection = section
target.append("{{-start-}}\n")
if sectionTableList: # only if sectionTableList was prepared, append it.
target.append(
sectionTableList[0]) # index table of the sections
firstPageList += "<div style='text-align: center;float:left;width:100%;'>'''" + 'XXXXXXXXXX' + "'''</div>\n" # title div
firstPageList += "\n"
firstPageList += '{{#widget:LanguageSelectorWidgetNew|textDiv=sloka|displayDiv=transliteration}}\n' # insert the language selection dropdown
firstPageList += '<div class="siva_container">\n' # div for sloka text for transliteration
firstPageList += '<div id="sloka";name="sloka" class="siva_sutra">\n' # div for sloka text for transliteration
firstPageList += '{{ScriptureTranscludeSource500|\n' # ttemplate
#firstPageList += 'YYYYYYYYYY' + '|\n' # Sloka heading
targetTransliterated.append('{{ScriptureTransliterateSource500|\n'
) # start code for transliteration
getChapterSectionVerse(verseNumber)
if firstTime:
firstTime = False
firstPageList = firstPageList.replace(
'XXXXXXXXXX',
getTitle(row)) # update title now that we know it.
#firstPageList = firstPageList.replace ( 'YYYYYYYYYY', (row[sectionNameCol] or getTitle(row))) # update Section now that we know it.
target.append(firstPageList)
prevSection = section
if (section != prevSection):
target.append("}}\n</div>\n"
) # complete template ScriptureTranscludeSource500
targetTransliterated.append(
"}}\n</div>\n"
) # complete template ScriptureTransliteratedSource500
target.append(targetTransliterated) # add the transliterated table
if (chapter == ''):
target.append(
sectionTableList[0]) # index table of the sections
else:
target.append(
sectionTableList[int(chapter) -
1]) # index table of the sections
if (len(chapterList) > 2):
target.append(chapterTable) # index table of the chapters
target.append("{{-stop-}}\n")
#targetTransliterated.append("}}\n")
printFile("verses/" + bookName + chapter + prevSection, target)
prevSection = section
target.clear()
targetTransliterated.clear()
target.append("{{-start-}}\n")
if (chapter == ''):
target.append(
sectionTableList[0]) # index table of the sections
else:
target.append(
sectionTableList[int(chapter) -
1]) # index table of the sections
target.append(
"<div style='text-align: center;float:left;width:100%;'>'''" +
getTitle(row) + "'''</div>\n") # title div
target.append("\n")
target.append(
'{{#widget:LanguageSelectorWidgetNew|textDiv=sloka|displayDiv=transliteration}}\n'
) # insert the language selection dropdown
target.append('<div class="siva_container">\n')
target.append('<div id="sloka";name="sloka" class="siva_sutra">\n')
target.append('{{ScriptureTranscludeSource500|\n')
#target.append((row[sectionNameCol] or getTitle(row)) + "|\n" )
targetTransliterated.append('{{ScriptureTransliterateSource500|\n'
) # start code for transliteration
lines = str(row[slokaCol]).splitlines()
linesRead = 0 # no of lines of text witin the given cell
linesToRead = len(lines) # no of lines of text witin the given cell
for e in lines:
e = '{{ns}}' + e.lstrip().rstrip(
) #strip all leand and traing white space
if e.rstrip(
'|') == '': # ignore empty lines or lines with only '|'
continue
parts = e.rsplit('||', 2)
if len(parts) > 1:
appendSlokaNo = True
else:
appendSlokaNo = False
e = e.replace("|", "{{!}}")
if appendSlokaNo and verseNumber:
e = e + verseNumber + "{{!}}{{!}}|\n"
else:
e = e + "|\n"
if debug():
print("line: ", e)
if linesRead < linesToRead:
transliteratedText = transliterate.process('autodetect',
'IAST',
e,
nativize=False)
target.append(e)
targetTransliterated.append(transliteratedText)
if appendSlokaNo:
target.append("----\n")
targetTransliterated.append("----\n")
linesRead += 1
target.append(
"}}\n</div>\n") # complete template ScriptureTranscludeSource500
targetTransliterated.append(
"}}\n</div>\n") # complete template ScriptureTransliteratedSource500
target.append(targetTransliterated)
if (chapter == ''):
if sectionTableList: # only if at least one sectionTableList was prepared, append it.
target.append(sectionTableList[0]) # index table of the sections
else:
target.append(sectionTableList[int(chapter) -
1]) # index table of the sections
if (len(chapterList) > 2):
target.append(chapterTable) # index table of the chapters
target.append("{{-stop-}}\n")
printFile("verses/" + bookName + chapter + prevSection, target)
target.clear()
targetTransliterated.clear()
debug()
from aksharamukha import transliterate
print(transliterate.process('HK', 'Siddham', 'buddhaH'))
print(transliterate.process('autodetect', 'IAST', 'ꯃꯤꯇꯩ_ꯃꯌꯦꯛ'))
print(transliterate.process('HK', 'Tamil', 'maMgaLa', False))
print(
transliterate.process(
'HK',
'Tamil',
'bRhaspati gaMgA',
False,
post_options=['TamilSubScript', 'TamilRemoveApostrophe']))
print(
transliterate.process('Thai',
'Devanagari',
'พุทธัง สะระณัง คัจฉามิ',
pre_options=['ThaiOrthography']))
print(transliterate.process('autodetect', 'IAST', 'พุทธัง สะระณัง คัจฉามิ'))
print(transliterate.auto_detect('ꯃꯤꯇꯩ_ꯃꯌꯦꯛ'))
print(
transliterate.process(
'Devanagari',
'IAST',
'धर्म भारत की श्रमण परम्परा से निकला धर्म और दर्शन है',
def describe_list_semitic():
from main import get_semitic_json
from aksharamukha import GeneralMap
semitic_json = get_semitic_json()
script_json = [script for script in GM.SemiticScripts if script != 'Latn']
for script1 in script_json:
for script2 in ['Latn', 'Type']:
charsScript1 = []
charsScript1R = []
charsScript2 = []
charsScript2R = []
charsLatn = []
results = {}
vowels = GeneralMap.semiticVowelsAll
vowelsInitial = GeneralMap.vowelsInitialAll
m = transliterate.process('Latn', script1, 'm')
for lat, char in semitic_json['ssub']['Latn'][script1].items():
latOrig = lat
if lat in vowels:
lat = 'm' + lat
char = m + char
charsScript1.append(char)
charguide = transliterate.process('Latn',
script2,
lat,
nativize=False)
charsScript2.append(charguide)
if latOrig in vowels or latOrig in vowelsInitial:
charguideReverse = transliterate.process(script2,
script1,
charguide,
nativize=False)
else:
if latOrig != 'ˀâ':
charguideReverse = transliterate.process(script2, script1, charguide, nativize=False, \
post_options = ['removeVowelsSyriac', 'removeDiacriticsArabic', 'ArabAtoAleph', ''])\
.replace('\u05B7', '').replace('\u07A6', '')
else:
charguideReverse = transliterate.process(
script2, script1, charguide, nativize=False)
charsScript2R.append(charguideReverse)
charReverse = transliterate.process(script1,
script2,
char,
nativize=False)
charsScript1R.append(charReverse)
charsLatn.append(lat)
#print(charsScript2R)
results['script1'] = charsScript1
results['script1R'] = charsScript1R
results['script2'] = charsScript2
results['script2R'] = charsScript2R
results['scriptLatn'] = charsLatn
print(script1, script2)
f = io.open("resources/semitic_syllabary/semitic_syllabary_" +
script1 + "_" + script2 + ".json",
mode="w",
encoding="utf-8")
f.write(
json.dumps(results,
ensure_ascii=False,
sort_keys=True,
indent=4))
f.close()
def describe_list_semitic():
semitic_json = get_semitic_json()
script1 = request.json['script1']
script2 = request.json['script2']
if script2 in ['Type', 'Latn']:
f = open("resources/semitic_syllabary/semitic_syllabary_" + script1 +
"_" + script2 + ".json",
'r',
encoding='utf-8')
results_final = json.loads(f.read())
f.close()
return jsonify(results_final)
charsScript1 = []
charsScript1R = []
charsScript2 = []
charsScript2R = []
charsLatn = []
results = {}
vowels = GeneralMap.semiticVowelsAll
vowelsInitial = GeneralMap.vowelsInitialAll
m = transliterate.process('Latn', script1, 'm')
for lat, char in semitic_json['ssub']['Latn'][script1].items():
latOrig = lat
if lat in vowels:
lat = 'm' + lat
char = m + char
charsScript1.append(char)
charguide = transliterate.process('Latn', script2, lat, nativize=False)
charsScript2.append(charguide)
if latOrig in vowels or latOrig in vowelsInitial:
charguideReverse = transliterate.process(script2,
script1,
charguide,
nativize=False)
else:
if latOrig != 'ˀâ':
charguideReverse = transliterate.process(script2, script1, charguide, nativize=False, \
post_options = ['removeVowelsSyriac', 'removeDiacriticsArabic', 'ArabAtoAleph', ''])\
.replace('\u05B7', '').replace('\u07A6', '')
else:
charguideReverse = transliterate.process(script2,
script1,
charguide,
nativize=False)
charsScript2R.append(charguideReverse)
charReverse = transliterate.process(script1,
script2,
char,
nativize=False)
charsScript1R.append(charReverse)
charsLatn.append(lat)
#print(charsScript2R)
results['script1'] = charsScript1
results['script1R'] = charsScript1R
results['script2'] = charsScript2
results['script2R'] = charsScript2R
results['scriptLatn'] = charsLatn
return jsonify(results)
def main(argv):
global GOOGLE_SHEETS_FILE_ID
global prevChapter
global prevSection
global chapter
global section
global title
global bookName
global xcelFile
global csvFile
global skipCount
global target
global targetTransliterated
global newCsvPage
bookName = ''
xcelFile = ''
csvFile = ''
skipCount = 1
try:
opts, args = getopt.getopt(
argv, ":g:c:x:b:s:",
["GoogleSheetId=", "CsvFile=", "Skip=", "BookName=", "Excel="])
except getopt.GetoptError:
print(
'pg.py [ -g <GoogleSheetId> | -x <ExcelFile> | -c <CsvFile> ] [-s <SkipLines>] [-b <BookName>]'
)
sys.exit(2)
for opt, arg in opts:
if opt in ("-s", "--Skip"):
skipCount = int(arg)
if opt in ("-b", "--BookName"):
bookName = arg
if opt in ("-g", "--GoogleSheetId"):
GOOGLE_SHEETS_FILE_ID = arg
if bookName == '':
bookName = (str(arg).split('.', 2)[0]).replace(
' ',
'_') # first part ofthe filename is taken as the bookname
elif opt in ("-x", "--Excel"):
GOOGLE_SHEETS_FILE_ID = ""
xcelFile = arg
if bookName == '':
bookName = (str(arg).split('.', 2)[0]).replace(
' ',
'_') # first part ofthe filename is taken as the bookname
#bookName = arg
elif opt in ("-c", "--CsvFile"):
GOOGLE_SHEETS_FILE_ID = ""
csvFile = arg
if bookName == '':
bookName = (str(arg).split('.', 2)[0]).replace(
' ',
'_') # first part ofthe filename is taken as the bookname
if (GOOGLE_SHEETS_FILE_ID == '' and xcelFile == ''
and csvFile == '') or bookName == '':
print(
'pg.py [ -g <GoogleSheetId> | -x <ExcelFile> | -c <CsvFile> ] [-s <SkipLines>] [-b <BookName>]'
)
sys.exit()
if GOOGLE_SHEETS_FILE_ID:
google_client = pygsheets.authorize()
spreadsheet = google_client.open_by_key(GOOGLE_SHEETS_FILE_ID)
wks_list = spreadsheet.worksheets()
wks = wks_list[0].get_all_values()
elif csvFile:
# pip3 install requests
import requests
df = pd.read_csv(csvFile, header=None, skiprows=None)
df.insert(0, 'RowNumber', '')
df.insert(0, 'Section', '')
df.insert(0, 'Chapter', '')
wks = df.values
elif xcelFile:
# pip3 install openpyxl
from openpyxl import load_workbook
wks = pd.read_excel(xcelFile, sheet_name=0, header=None,
skiprows=None).values
#wks= df
count = 0
firstTime = True
#wks = [*wks]
makeLists(
wks
) # prepare the index tables for chapter pages and chapters, if any.
prevSection = ''
prevChapter = ''
section = ''
firstPageList = ''
target = []
targetTransliterated = []
newCsvPage = 1
senp = 1
for row in [*wks][skipCount - 2:]:
verseNumber = row[verseNumberCol]
if firstTime:
prevSection = section
prevChapter = chapter
target.append("{{-start-}}\n")
appendPageLists()
firstPageList = startPageHeader('XXXXXXXXXX')
targetTransliterated.append('{{ScriptureTransliterateSource500|\n'
) # start code for transliteration
getChapterSectionVerse(verseNumber)
if firstTime:
firstTime = False
firstPageList = firstPageList.replace(
'XXXXXXXXXX',
getTitle(row)) # update title now that we know it.
target.append(firstPageList)
prevSection = section
if (section != prevSection):
startNewPage(row)
lines = str(row[slokaCol]).splitlines()
linesRead = 0 # no of lines of text witin the given cell
linesToRead = len(lines) # no of lines of text witin the given cell
for e in lines:
e = '{{ns}}' + e.lstrip().rstrip(
) #strip all leand and traing white space
if e.rstrip('|') == '{{ns}}StartNewPage':
if csvFile:
prevChapter = newCsvPage
newCsvPage += 1
startNewPage(
row) # empty line in csv file starts a new page
#else:
continue # ignore empty lines or lines with only '|' for excel or google sheets
parts = e.rsplit('||', 2)
if len(parts) > 1:
appendSlokaNo = True
else:
appendSlokaNo = False
e = e.replace("|", "{{!}}")
if appendSlokaNo and verseNumber:
e = e + verseNumber + "{{!}}{{!}}|\n"
else:
e = e + "|\n"
if debug():
print("line: ", e)
if linesRead < linesToRead:
transliteratedText = transliterate.process('autodetect',
'IAST',
e,
nativize=False)
target.append(e)
targetTransliterated.append(transliteratedText)
if appendSlokaNo:
target.append("----\n")
targetTransliterated.append("----\n")
linesRead += 1
if csvFile:
prevChapter = newCsvPage
newCsvPage += 1
startNewPage(row)
debug()
