aso2101

import cv2
import glob
import os
import math
import numpy as np

# Parameters:
# xgive is the number of pixels of "give" when determining whether a line of text
# belongs to the main text or commentary, when they are discriminated based on
# width.

aso2101

import argparse
import sanscript
from os.path import abspath
from os.path import splitext
from os.path import basename
import sys

parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter,description="Convert a file from one script to another using Sanscript and print the output to stdout.\n\nAvailable scripts are: bengali, devanagari, gujarati, gurmukhi, kannada, malayalam, oriya, tamil, telugu, hk, iast, iso, itrans, kolkata, slp1, velthuis, wx.")
parser.add_argument("filename",nargs="+",type=str,help="The input file")
parser.add_argument("fr",nargs="+",type=str,help="The input script")

aso2101

# Usage:
# 
# python3 check.py INPUT_FILE 
#
#   where INPUT_FILE is just the name of the file to check.
#
#   This scripts expects that INPUT_FILE will contain one of
#   the following three strings:
#      kittel = Kittel's Kannada-English dictionary
#      ghatage = Ghatage's Prakrit-English dictionary

aso2101

# Uses Tesseract (tesserocr) to recognize files
#   in a directory. I use this as follows:
#
#   1. split the PDF into JPG images in a directory
#        called "IMAGES" (e.g., pdftoppm -jpeg input.pdf IMAGES/output)
#   2. run this script (python OSD.py), which will
#        produce a text file for each image in "IMAGES".
#   3. concatenate the text files with tail
#   4. if desired, 

aso2101

"""OCR with PDF/TIFF as source files on GCS"""
# USAGE: python text_detect.py SOURCE_FILE OUTPUT_FILE
#   Note that both SOURCE_FILE and OUTPUT_FILE must be
#   in the Google Cloud bucket. For example: 
#
#   python text_detect.py gs://project-name/file.pdf gs://project-name/read
#
# The API will gather the responses for each page into
#   a JSON file on the Google Cloud bucket, e.g.
#   OUTPUT_FILE-output-1-to-1.json.

aso2101

aso2101

# -*- coding: utf-8 -*-

""" Usage: python3 versify.py FILENAME """
""" Results in FILENAME.log (errors and statistics)
            and FILENAME.json (a json file of metrically parsed text) """

""" This program expects the text to be in the format
    represented by the GRETIL Kuṟuntokai 
      (http://gretil.sub.uni-goettingen.de/gretil/4_drav/tamil/pm/pm110__u.htm)
    namely: the

aso2101

# -*- coding: utf-8 -*-

""" Usage: python3 verify_gatha.py FILENAME """
""" Results in FILENAME.err (a list of errors)
            and FILENAME.log (metrical data) """

""" Take a file in UTF-8 encoding, in the ISO-15919 transliteration
    scheme, and try to scan its verses and match them against the
    canonical pattern of the Prakrit gāthā. If there are any errors,
    output them to an error file. """

aso2101

{
    "data": {
	"General": {
	    "intro": "<p>These are general terms which apply to various aspects of Sanskrit grammar.</p>",
	    "glossary": [
		{
		    "id" : "prakrtih",
		    "skt" : "prakr̥tiḥ",
		    "eng" : "base",
		    "comm" : "That to which an <a href='#pratyayah'>affix</a> is added. A base can be nominal (see <a href='#pratipadikam'>nominal stem</a>) or verbal. This is a synonym of <a href='#angam'>aṅgam</a>."

aso2101

[X] Ind.Sp. 101 = PaTa.3.96 :simple:nominal:kr̥tya:

anityāni śarīrāni vibhavo naiva śāśvataḥ | nityaṁ saṁnihitō mr̥tyuḥ kartavyō dharmasaṁgrahaḥ ||

[X] Sūktimuktāvalī 4.75 :singular:dual:plural:satisaptamī:

jāte jagati vālmīkau śabdaḥ kavir iti sthitaḥ | vyāse jāte kavī ceti kavayaś ceti daṇḍini || http://prakrit.info/sanskrit/readings/sumu-4-75.html

[ ] Unknown 1