def transliterate(data, _from=None, _to=None, scheme_map=None, **kw):
"""Transliterate `data` with the given parameters::
output = transliterate('idam adbhutam', HK, DEVANAGARI)
Each time the function is called, a new :class:`SchemeMap` is created
to map the input scheme to the output scheme. This operation is fast
enough for most use cases. But for higher performance, you can pass a
pre-computed :class:`SchemeMap` instead::
scheme_map = SchemeMap(SCHEMES[HK], SCHEMES[DEVANAGARI])
output = transliterate('idam adbhutam', scheme_map=scheme_map)
:param data: the data to transliterate
:param _from: the name of a source scheme
:param _to: the name of a destination scheme
:param scheme_map: the :class:`SchemeMap` to use. If specified, ignore
`_from` and `_to`. If unspecified, create a
:class:`SchemeMap` from `_from` to `_to`.
"""
if scheme_map is None:
from_scheme = SCHEMES[_from]
to_scheme = SCHEMES[_to]
scheme_map = sanscript.SchemeMap(from_scheme, to_scheme)
return sanscript.transliterate(data=data, scheme_map=scheme_map)
def s_to_d(input_string):
scheme = detect.detect(input_string)
print("input: " + input_string + " --- encoding = " + str(scheme))
v_scheme_map = sanscript.SchemeMap(sanscript.SCHEMES[sanscript.SLP1],
sanscript.SCHEMES[sanscript.DEVANAGARI])
output_string = sanscript.transliterate(input_string,
scheme_map=v_scheme_map)
scheme = detect.detect(output_string)
print("output: " + output_string + " --- encoding = " + str(scheme))
return output_string
def v_to_d(input_string):
scheme = detect.detect(input_string)
if (str(scheme) == "Velthuis"):
v_scheme_map = sanscript.SchemeMap(
sanscript.SCHEMES[sanscript.VELTHUIS],
sanscript.SCHEMES[sanscript.DEVANAGARI])
output_string = sanscript.transliterate(input_string,
scheme_map=v_scheme_map)
scheme = detect.detect(output_string)
else:
output_string = input_string
return output_string
def i_to_d(input_string):
scheme = detect.detect(input_string)
if (str(scheme) == "ITRANS"):
inputSchemeIndex = sanscript.ITRANS
elif (str(scheme) == "HK"):
inputSchemeIndex = sanscript.HK
if ((str(scheme) == "ITRANS") or (str(scheme) == "HK")):
v_scheme_map = sanscript.SchemeMap(
sanscript.SCHEMES[inputSchemeIndex],
sanscript.SCHEMES[sanscript.DEVANAGARI])
output_string = sanscript.transliterate(input_string,
scheme_map=v_scheme_map)
else:
output_string = input_string
return output_string
def d_to_i(input_string):
scheme = detect.detect(input_string)
#print("input: " + input_string + " --- encoding = " + str(scheme))
if (str(scheme) == "Devanagari"):
v_scheme_map = sanscript.SchemeMap(
sanscript.SCHEMES[sanscript.DEVANAGARI],
sanscript.SCHEMES[sanscript.ITRANS])
output_string = sanscript.transliterate(input_string,
scheme_map=v_scheme_map)
#print("Ascii translation for tokenization:")
scheme = detect.detect(output_string)
#print("output: " + output_string + " --- encoding = " + str(scheme))
else:
output_string = input_string
#print("please enter the input in devanagari")
return output_string
def main():
is_pragrahya = False
print("input:" + sys.argv[1])
scheme = detect.detect(sys.argv[1])
input_string = ""
print("input: " + sys.argv[1] + " --- encoding = " + str(scheme))
if (str(scheme) == "Devanagari"):
v_scheme_map = sanscript.SchemeMap(
sanscript.SCHEMES[sanscript.DEVANAGARI],
sanscript.SCHEMES[sanscript.VELTHUIS])
input_string = sanscript.transliterate(sys.argv[1],
scheme_map=v_scheme_map)
else:
print("please enter the input in devanagari")
is_pragrahya = pragrahya_check(input_string)
print("**Pragrahya " + str(is_pragrahya))
import time
from collections import OrderedDict
from concurrent.futures import ThreadPoolExecutor
from functools import reduce
import requests
from lxml import etree
from indic_transliteration import sanscript
from requests import Session
LISTINGS_BASE_URI = 'http://eoh.rkmathbangalore.org/listing/alphabet'
WORD_PAGE_BASE_URI = 'http://eoh.rkmathbangalore.org/describe/word'
concurrency = 10
HWS_XLITERATE_SCHEME_MAPS = [
sanscript.SchemeMap(sanscript.SCHEMES[sanscript.IAST],
sanscript.SCHEMES[script]) for script in [
sanscript.DEVANAGARI, sanscript.ITRANS,
sanscript.TAMIL, sanscript.TELUGU
]
]
def get_listing_pages():
# we are getting all once for proper hyperlinking
for alphabet in string.ascii_uppercase:
yield requests.get('{}/{}'.format(LISTINGS_BASE_URI, alphabet)).text
def _get_class_matching_xpath(tag: str, clsname: str):
return "//{tag}[contains(concat(' ', normalize-space(@class), ' '), ' {cls} ')]".format(
tag=tag, cls=clsname)
