Add test cache

This commit is contained in:
James R. Barlow
2018-03-24 23:50:41 -07:00
parent 8975b72a01
commit ca51514046
175 changed files with 3372 additions and 0 deletions
@@ -0,0 +1,3 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0
@@ -0,0 +1,4 @@
This should be a perfect circle:
@@ -0,0 +1,3 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0
@@ -0,0 +1,4 @@
This should be a perfect circle:
@@ -0,0 +1,27 @@
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title></title>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
<meta name='ocr-system' content='tesseract 4.0.0-beta.1' />
<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
</head>
<body>
<div class='ocr_page' id='page_1' title='image "/var/folders/37/78_114p552q16vv6vmgm5kr00000gn/T/com.github.ocrmypdf.bp6c363s/000001.ocr.png"; bbox 0 0 1000 800; ppageno 0'>
<div class='ocr_carea' id='block_1_1' title="bbox 296 96 704 504">
<p class='ocr_par' id='par_1_1' lang='eng' title="bbox 296 96 704 504">
<span class='ocr_line' id='line_1_1' title="bbox 296 96 704 504; baseline 0 296; x_size 169.33333; x_descenders 42.333332; x_ascenders 42.333336"><span class='ocrx_word' id='word_1_1' title='bbox 296 96 704 504; x_wconf 95'><strong> </strong></span>
</span>
</p>
</div>
<div class='ocr_carea' id='block_1_2' title="bbox 150 592 841 622">
<p class='ocr_par' id='par_1_2' lang='eng' title="bbox 150 592 841 622">
<span class='ocr_line' id='line_1_2' title="bbox 150 592 841 622; baseline 0 -6; x_size 30; x_descenders 6; x_ascenders 8"><span class='ocrx_word' id='word_1_2' title='bbox 150 592 230 616; x_wconf 96'><strong>This</strong></span> <span class='ocrx_word' id='word_1_3' title='bbox 260 592 384 616; x_wconf 95'><strong>should</strong></span> <span class='ocrx_word' id='word_1_4' title='bbox 413 592 449 616; x_wconf 95'><strong>be</strong></span> <span class='ocrx_word' id='word_1_5' title='bbox 479 600 493 616; x_wconf 95'><strong>a</strong></span> <span class='ocrx_word' id='word_1_6' title='bbox 523 592 668 622; x_wconf 95'><strong>perfect</strong></span> <span class='ocrx_word' id='word_1_7' title='bbox 698 592 841 616; x_wconf 55'><strong>circle:</strong></span>
</span>
</p>
</div>
</div>
</body>
</html>
@@ -0,0 +1,3 @@
Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
Too few characters. Skipping this page
OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0
@@ -0,0 +1,4 @@
This should be a perfect circle: