From a692fbcb744ec2ba97a58b74c57d8374e5727994 Mon Sep 17 00:00:00 2001
From: Bruce Robertson <brobertson@mta.ca>
Date: Thu, 15 Aug 2013 09:59:12 -0400
Subject: [PATCH] move files

---
 Scripts/Training/generate_ocropus_training.py | 52 -------------------
 Scripts/Training/hocr_to_plain_text.xsl       | 16 ------
 2 files changed, 68 deletions(-)
 delete mode 100644 Scripts/Training/generate_ocropus_training.py
 delete mode 100755 Scripts/Training/hocr_to_plain_text.xsl

diff --git a/Scripts/Training/generate_ocropus_training.py b/Scripts/Training/generate_ocropus_training.py
deleted file mode 100644
index dc548a6..0000000
--- a/Scripts/Training/generate_ocropus_training.py
+++ /dev/null
@@ -1,52 +0,0 @@
-from HTMLParser import HTMLParser
-from gamera.core import *
-
-init_gamera()
-from gamera.plugin import *
-class SpanLister(HTMLParser):
-    def __init__(self, id_string):
-	HTMLParser.__init__(self)
-	self.id_string = id_string
-
-
-
-    def reset(self):
-            HTMLParser.reset(self)
-            self.spans = []
-    def handle_starttag(self, tag, attrs):
-            foo = [v for k, v in attrs if k=='class']
-            bar = [j for i, j in attrs if i=='title']
-            if foo:
-		if foo[0] == self.id_string:
-                	print foo[0]
-			#print self.get_starttag_text()
-                	self.spans.extend(bar)
-def drawParser(parser,color,image):
-	file_number = 0
-	for span in parser.spans: 
-		boxes =  span.split(';')[0].split()
-		#draw the word boxes
-		#image.draw_hollow_rect((int(boxes[1]) -1,int(boxes[2]) -1),(int(boxes[3]) +1 , int(boxes[4]) +1 ), color, 2)
-		subimg = SubImage(image,(int(boxes[1]) -1,int(boxes[2]) -1),(int(boxes[3]) +1 , int(boxes[4]) +1 ))
-		print 'printing subimg'
-		subimg.save_PNG('/tmp/sub_img_out_' + str(file_number) + '.png')
-		file_number = file_number + 1
-lineParser = SpanLister('ocr_line')
-#wordParser  = SpanLister('ocr_word')
-#wordXParser = SpanLister('ocrx_word')
-image_name = sys.argv[1]
-hocr_name = sys.argv[2]
-#dirName = name[:len(name)-5]
-#print dirName
-image = load_image(image_name)
-image = image.to_rgb()
-lineParser.feed(open(hocr_name).read())
-#wordParser.feed(open(hocr_name).read())
-#wordXParser.feed(open(hocr_name).read())
-drawParser(lineParser,RGBPixel(255,0,255),image)
-#drawParser(wordParser,RGBPixel(0,255,255),image)
-#drawParser(wordXParser,RGBPixel(255,0,255),image)
-
-#save the image
-#print "image out: ", sys.argv[3]
-#image.save_PNG(sys.argv[3])	
diff --git a/Scripts/Training/hocr_to_plain_text.xsl b/Scripts/Training/hocr_to_plain_text.xsl
deleted file mode 100755
index 9bd41bd..0000000
--- a/Scripts/Training/hocr_to_plain_text.xsl
+++ /dev/null
@@ -1,16 +0,0 @@
-<?xml version="1.0"?>
-<xsl:stylesheet version="1.0"
-xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:abbyy="http://www.abbyy.com/FineReader_xml/FineReader6-schema-v1.xml">
-<xsl:output method="text" encoding="UTF-8"/>
-<xsl:template match="html">
-  <xsl:apply-templates select="//span[@class='ocr_line']"/>
-</xsl:template>
-<xsl:template match="span[@class='ocr_line']"><xsl:text disable-output-escaping="yes">
-</xsl:text>
-<xsl:apply-templates/>
-</xsl:template>
-<xsl:template match="span[@class='ocr_word']">
-<xsl:value-of select="."/><xsl:text disable-output-escaping="yes"> </xsl:text>
-</xsl:template>
-</xsl:stylesheet>
-