Wincent Balin wincentbalin

## telegram_markdown_corpus.py
#!/usr/bin/env python3
"""Convert Telegram channel JSON export to a Markdown text corpus"""

import sys
import json
import argparse
parser = argparse.ArgumentParser(description=sys.modules[__name__].__doc__)
parser.add_argument('export_json', help='Exported JSON file', type=argparse.FileType('r', encoding='utf-8'))
parser.add_argument('markdown_corpus', help='Markdown text corpus', type=argparse.FileType('w', encoding='utf-8'))
args = parser.parse_args()

## Makefile
# Train Tesseract OCR for Akkadian language

LANG = akk
CORPUS = corpus-12pt.txt
LANGDATA_ROOT = ../langdata
FREQ_DAWG_SIZE = 100

FONTS := "CuneiformNAOutline Medium" "CuneiformOB" "CuneiformComposite" "Segoe UI Historic"
FONTSJOINED := CuneiformNAOutlineMedium CuneiformOB CuneiformComposite SegoeUIHistoric
EXPOSURES := 0

## oracc-export.py
#!/usr/bin/env python
"""Export cuneiform corpus from ORACC
"""

import sys
import os
import argparse
import logging
import re
import shutil

## aktuellparser.py
import re
from html.parser import HTMLParser

RE_TEILLISTE = re.compile(r'/Teilliste_\w\.html$', re.IGNORECASE)

def get_url(attrs):
    """Find href attribute and join it with base URL"""
    for key, value in attrs:
        if key == 'href':
            return urljoin(START_URL, value)

## giitotext.xsl
<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
    <xsl:output method="text" encoding="utf-8" omit-xml-declaration="yes"/>
    <xsl:strip-space elements="*"/>
    <xsl:variable name="newline"><xsl:text>
</xsl:text></xsl:variable>
    <xsl:variable name="space"><xsl:text> </xsl:text></xsl:variable>
    <xsl:variable name="tab" select="concat($space, $space, $space, $space)"/>

    <xsl:template match="/dokumente">

## Vagrantfile
# -*- mode: ruby -*-
# vi: set ft=ruby :

Vagrant.configure("2") do |config|
  required_plugins = %w( vagrant-vbguest vagrant-disksize )
  _retry = false
  required_plugins.each do |plugin|
      unless Vagrant.has_plugin? plugin
          system "vagrant plugin install #{plugin}"
          _retry=true

## batch_tester.patch
--- export/batch_tester/batch_tester.cc.orig	2016-02-09 12:38:34.000000000 +0000
+++ export/batch_tester/batch_tester.cc	2019-04-27 20:04:32.358891300 +0000
@@ -37,11 +37,11 @@
 using thrax::GrmManager;
 using thrax::InputBuffer;
 using thrax::OpenOrDie;
-using thrax::Split;
+//using thrax::Split;

-typedef StringCompiler<StdArc> Compiler;

## make_me.sh
#!/bin/sh
#
# Function switcher for USB armory

if [ $# -eq 0 -o $# -eq 1 -a \( "$1" != "stick" -a "$1" != "stick-win" -a "$1" != "stick-mac" -a "$1" != "host" \) ]
then
  echo "Usage: $0 stick|stick-win|stick-mac|host"
  exit 1
fi

## abc2svg.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
    <title>abc2svg test</title>
    <style>
        #output {
            position: absolute;
            top: 0;
            right: 0

## audiobuttons.html
<!DOCTYPE html>
<html>
    <head>
        <title>Audio buttons</title>
        <meta charset="UTF-8">
        <meta name="viewport" content="width=device-width, initial-scale=1.0">
        <style type="text/css">
            html,
            body
            {
	#!/usr/bin/env python3
	"""Convert Telegram channel JSON export to a Markdown text corpus"""

	import sys
	import json
	import argparse
	parser = argparse.ArgumentParser(description=sys.modules[__name__].__doc__)
	parser.add_argument('export_json', help='Exported JSON file', type=argparse.FileType('r', encoding='utf-8'))
	parser.add_argument('markdown_corpus', help='Markdown text corpus', type=argparse.FileType('w', encoding='utf-8'))
	args = parser.parse_args()
	# Train Tesseract OCR for Akkadian language

	LANG = akk
	CORPUS = corpus-12pt.txt
	LANGDATA_ROOT = ../langdata
	FREQ_DAWG_SIZE = 100

	FONTS := "CuneiformNAOutline Medium" "CuneiformOB" "CuneiformComposite" "Segoe UI Historic"
	FONTSJOINED := CuneiformNAOutlineMedium CuneiformOB CuneiformComposite SegoeUIHistoric
	EXPOSURES := 0
	#!/usr/bin/env python
	"""Export cuneiform corpus from ORACC
	"""

	import sys
	import os
	import argparse
	import logging
	import re
	import shutil
	import re
	from html.parser import HTMLParser

	RE_TEILLISTE = re.compile(r'/Teilliste_\w\.html$', re.IGNORECASE)

	def get_url(attrs):
	"""Find href attribute and join it with base URL"""
	for key, value in attrs:
	if key == 'href':
	return urljoin(START_URL, value)
	<?xml version="1.0" encoding="UTF-8"?>
	<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
	<xsl:output method="text" encoding="utf-8" omit-xml-declaration="yes"/>
	<xsl:strip-space elements="*"/>
	<xsl:variable name="newline"><xsl:text>
	</xsl:text></xsl:variable>
	<xsl:variable name="space"><xsl:text> </xsl:text></xsl:variable>
	<xsl:variable name="tab" select="concat($space, $space, $space, $space)"/>

	<xsl:template match="/dokumente">
	# -- mode: ruby --
	# vi: set ft=ruby :

	Vagrant.configure("2") do \|config\|
	required_plugins = %w( vagrant-vbguest vagrant-disksize )
	_retry = false
	required_plugins.each do \|plugin\|
	unless Vagrant.has_plugin? plugin
	system "vagrant plugin install #{plugin}"
	_retry=true
	--- export/batch_tester/batch_tester.cc.orig 2016-02-09 12:38:34.000000000 +0000
	+++ export/batch_tester/batch_tester.cc 2019-04-27 20:04:32.358891300 +0000
	@@ -37,11 +37,11 @@
	using thrax::GrmManager;
	using thrax::InputBuffer;
	using thrax::OpenOrDie;
	-using thrax::Split;
	+//using thrax::Split;

	-typedef StringCompiler<StdArc> Compiler;
	#!/bin/sh
	#
	# Function switcher for USB armory

	if [ $# -eq 0 -o $# -eq 1 -a \( "$1" != "stick" -a "$1" != "stick-win" -a "$1" != "stick-mac" -a "$1" != "host" \) ]
	then
	echo "Usage: $0 stick\|stick-win\|stick-mac\|host"
	exit 1
	fi
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
	<title>abc2svg test</title>
	<style>
	#output {
	position: absolute;
	top: 0;
	right: 0
	<!DOCTYPE html>
	<html>
	<head>
	<title>Audio buttons</title>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<style type="text/css">
	html,
	body
	{