annotate tesseract.xml @ 1:cd9d2e8e3954 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit eb49a0136957dde211907f7b8689bdecbe8245d8
author iuc
date Tue, 04 Nov 2025 13:42:35 +0000
parents 9014c412d96c
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
1 <tool id="tesseract" name="Tesseract" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.2">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
2 <description>Optical Character Recognition</description>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
3 <macros>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
4 <import>macros.xml</import>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
5 </macros>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
6 <expand macro="requirements" />
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
7 <expand macro="creators" />
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
8 <command detect_errors="exit_code"><![CDATA[
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
9 #if str($input_file.ext) == "pdf"
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
10 mkdir extracted_images &&
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
11 pdfimages -png '$input_file' extracted_images/page &&
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
12 ls extracted_images/page*.png > img_paths &&
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
13 #else
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
14 echo '$input_file' > img_paths &&
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
15 #end if
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
16 tesseract img_paths output
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
17 --tessdata-dir '${tessdata.fields.path}'
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
18 #if $language:
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
19 -l ${ str($language).replace(",","+") }
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
20 #end if
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
21 --psm $psm
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
22 #if $dpi:
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
23 --dpi $dpi
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
24 #end if
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
25 #if $user_words
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
26 --user-words '$user_words'
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
27 #end if
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
28 #if $user_patterns
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
29 --user-patterns '$user_patterns'
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
30 #end if
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
31 #for $format in $output_formats
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
32 -c $format=1
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
33 #end for
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
34 ]]></command>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
35 <inputs>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
36 <param name="input_file" type="data" format="jpg,png,tif,tiff,bmp,pdf" label="Image file(s)" multiple="false"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
37 <param name="tessdata" type="select" label="Tessdata" help="Language data models">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
38 <options from_data_table="tessdata">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
39 <column name="value" index="0"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
40 <column name="name" index="1"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
41 <column name="version" index="2"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
42 <column name="path" index="3"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
43 <filter type="sort_by" column="1"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
44 </options>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
45 <validator type="no_options" message="A built-in tesseract model is not available. Please ask the Galaxy admins to install one on the server."/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
46 </param>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
47 <param name="user_words" type="data" format="txt" label="User words file" optional="true" help="The user words file allows you to specify a list of words that Tesseract should treat as known words. One word per line"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
48 <param name="user_patterns" type="data" format="txt" label="User patterns file" optional="true" help="One pattern per line in UTF-8 format. For more information please visit the tesseract docs about patterns linked in the help section"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
49 <param name="language" type="select" label="OCR Language(s)" multiple="true" help="In the case of a multilingual image(s), more the one language can be selected" optional="false">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
50 <option value="afr">Afrikaans</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
51 <option value="amh">Amharic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
52 <option value="ara">Arabic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
53 <option value="asm">Assamese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
54 <option value="aze">Azerbaijani</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
55 <option value="aze_cyrl">Azerbaijani - Cyrilic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
56 <option value="bel">Belarusian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
57 <option value="ben">Bengali</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
58 <option value="bod">Tibetan</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
59 <option value="bos">Bosnian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
60 <option value="bre">Breton</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
61 <option value="bul">Bulgarian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
62 <option value="cat">Catalan; Valencian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
63 <option value="ceb">Cebuano</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
64 <option value="ces">Czech</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
65 <option value="chi_sim">Chinese simplified</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
66 <option value="chi_tra">Chinese traditional</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
67 <option value="chr">Cherokee</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
68 <option value="cos">Corsican</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
69 <option value="cym">Welsh</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
70 <option value="dan">Danish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
71 <option value="deu">German</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
72 <option value="deu_latf">German Fraktur Latin</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
73 <option value="div">Dhivehi</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
74 <option value="dzo">Dzongkha</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
75 <option value="ell">Greek, Modern, 1453-</option>
1
cd9d2e8e3954 planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit eb49a0136957dde211907f7b8689bdecbe8245d8
iuc
parents: 0
diff changeset
76 <option value="eng" selected="true">English</option>
0
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
77 <option value="enm">English, Middle, 1100-1500</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
78 <option value="epo">Esperanto</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
79 <option value="equ">Math / equation detection module</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
80 <option value="est">Estonian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
81 <option value="eus">Basque</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
82 <option value="fas">Persian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
83 <option value="fao">Faroese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
84 <option value="fil">Filipino</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
85 <option value="fin">Finnish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
86 <option value="fra">French</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
87 <option value="frm">French, Middle, ca.1400-1600</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
88 <option value="fry">West Frisian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
89 <option value="gla">Scottish Gaelic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
90 <option value="gle">Irish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
91 <option value="glg">Galician</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
92 <option value="grc">Greek, Ancient, to 1453</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
93 <option value="guj">Gujarati</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
94 <option value="hat">Haitian; Haitian Creole</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
95 <option value="heb">Hebrew</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
96 <option value="hin">Hindi</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
97 <option value="hrv">Croatian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
98 <option value="hun">Hungarian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
99 <option value="hye">Armenian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
100 <option value="iku">Inuktitut</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
101 <option value="ind">Indonesian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
102 <option value="isl">Icelandic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
103 <option value="ita">Italian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
104 <option value="ita_old">Italian - Old</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
105 <option value="jav">Javanese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
106 <option value="jpn">Japanese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
107 <option value="kan">Kannada</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
108 <option value="kat">Georgian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
109 <option value="kat_old">Georgian - Old</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
110 <option value="kaz">Kazakh</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
111 <option value="khm">Central Khmer</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
112 <option value="kir">Kirghiz; Kyrgyz</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
113 <option value="kmr">Kurdish Kurmanji</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
114 <option value="kor">Korean</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
115 <option value="kor_vert">Korean vertical</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
116 <option value="lao">Lao</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
117 <option value="lat">Latin</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
118 <option value="lav">Latvian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
119 <option value="lit">Lithuanian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
120 <option value="ltz">Luxembourgish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
121 <option value="mal">Malayalam</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
122 <option value="mar">Marathi</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
123 <option value="mkd">Macedonian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
124 <option value="mlt">Maltese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
125 <option value="mon">Mongolian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
126 <option value="mri">Maori</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
127 <option value="msa">Malay</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
128 <option value="mya">Burmese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
129 <option value="nep">Nepali</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
130 <option value="nld">Dutch; Flemish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
131 <option value="nor">Norwegian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
132 <option value="oci">Occitan post 1500</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
133 <option value="ori">Oriya</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
134 <option value="osd">Orientation and script detection module</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
135 <option value="pan">Panjabi; Punjabi</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
136 <option value="pol">Polish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
137 <option value="por">Portuguese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
138 <option value="pus">Pushto; Pashto</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
139 <option value="que">Quechua</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
140 <option value="ron">Romanian; Moldavian; Moldovan</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
141 <option value="rus">Russian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
142 <option value="san">Sanskrit</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
143 <option value="sin">Sinhala; Sinhalese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
144 <option value="slk">Slovak</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
145 <option value="slv">Slovenian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
146 <option value="snd">Sindhi</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
147 <option value="spa">Spanish; Castilian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
148 <option value="spa_old">Spanish; Castilian - Old</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
149 <option value="sqi">Albanian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
150 <option value="srp">Serbian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
151 <option value="srp_latn">Serbian - Latin</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
152 <option value="sun">Sundanese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
153 <option value="swa">Swahili</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
154 <option value="swe">Swedish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
155 <option value="syr">Syriac</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
156 <option value="tam">Tamil</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
157 <option value="tat">Tatar</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
158 <option value="tel">Telugu</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
159 <option value="tgk">Tajik</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
160 <option value="tha">Thai</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
161 <option value="tir">Tigrinya</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
162 <option value="ton">Tonga</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
163 <option value="tur">Turkish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
164 <option value="uig">Uighur; Uyghur</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
165 <option value="ukr">Ukrainian</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
166 <option value="urd">Urdu</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
167 <option value="uzb">Uzbek</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
168 <option value="uzb_cyrl">Uzbek - Cyrilic</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
169 <option value="vie">Vietnamese</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
170 <option value="yid">Yiddish</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
171 <option value="yor">Yoruba</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
172 </param>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
173 <param name="output_formats" type="select" label="Output format(s)" multiple="true" optional="false">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
174 <option value="tessedit_create_txt" selected="true">Text</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
175 <option value="tessedit_create_pdf">PDF</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
176 <option value="tessedit_create_hocr">HOCR</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
177 <option value="tessedit_create_tsv">TSV</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
178 </param>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
179 <param argument="--psm" type="select" label="Page Segmentation Mode (PSM)" help="How the page layout is interpreted." optional="true">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
180 <option value="0">Orientation and script detection only</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
181 <option value="1">Automatic page segmentation with OSD</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
182 <option value="2">Automatic page segmentation, but no OSD, or OCR</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
183 <option value="3" selected="true">Fully automatic page segmentation, but no OSD</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
184 <option value="4">Assume a single column of text of variable sizes</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
185 <option value="5">Assume a single uniform block of vertically aligned text</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
186 <option value="6">Assume a single uniform block of text</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
187 <option value="7">Treat the image as a single text line</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
188 <option value="8">Treat the image as a single word</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
189 <option value="9">Treat the image as a single word in a circle</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
190 <option value="10">Treat the image as a single character</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
191 <option value="11">Sparse text. Find as much text as possible in no particular order</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
192 <option value="12">Sparse text with OSD</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
193 <option value="13">Raw line. Treat the image as a single text line, bypassing hacks that are Tesseract-specific</option>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
194 </param>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
195 <param argument="--dpi" type="integer" label="Image DPI (dots per inch)" min="100" help="When left empty, the resolution in retrieved from the image metadata. If this information in not icluded, Tesseract will make a guess. Tesseract performes best on images with at least 300 dpi" optional="true" />
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
196 </inputs>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
197 <outputs>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
198 <data name="output_text" format="txt" from_work_dir="output.txt" label="${tool.name} on ${on_string}: Text">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
199 <filter>'tessedit_create_txt' in output_formats</filter>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
200 </data>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
201 <data name="output_pdf" format="pdf" from_work_dir="output.pdf" label="${tool.name} on ${on_string}: PDF">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
202 <filter>'tessedit_create_pdf' in output_formats</filter>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
203 </data>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
204 <data name="output_hocr" format="html" from_work_dir="output.hocr" label="${tool.name} on ${on_string}: HOCR">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
205 <filter>'tessedit_create_hocr' in output_formats</filter>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
206 </data>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
207 <data name="output_tsv" format="tsv" from_work_dir="output.tsv" label="${tool.name} on ${on_string}: TSV">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
208 <filter>'tessedit_create_tsv' in output_formats</filter>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
209 </data>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
210 </outputs>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
211 <tests>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
212 <test expect_num_outputs="2">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
213 <param name="input_file" value="eurotext.png"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
214 <param name="tessdata" value="test_tessdata"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
215 <param name="user_words" value="eng.user-words"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
216 <param name="user_patterns" value="eng.user-patterns"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
217 <param name="language" value="chr"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
218 <param name="output_formats" value="tessedit_create_txt,tessedit_create_pdf"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
219 <param name="psm" value="3"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
220 <output name="output_text" file="image_output.txt"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
221 <output name="output_pdf" file="image_output.pdf"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
222 </test>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
223 <test expect_num_outputs="2">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
224 <param name="input_file" value="test_image_cherokee.png"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
225 <param name="tessdata" value="test_tessdata"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
226 <param name="language" value="chr"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
227 <param name="output_formats" value="tessedit_create_hocr,tessedit_create_tsv"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
228 <param name="psm" value="11"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
229 <output name="output_hocr">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
230 <assert_contents>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
231 <has_text text="Ꮳ"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
232 <has_text text="ᏌᎠᏯᏙᏣᎠ"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
233 <has_size value="1805" delta="10"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
234 </assert_contents>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
235 </output>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
236 <output name="output_tsv" file="image_output.tsv"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
237 </test>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
238 <test expect_num_outputs="4">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
239 <param name="input_file" value="test_input.pdf"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
240 <param name="tessdata" value="test_tessdata"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
241 <param name="language" value="chr"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
242 <param name="output_formats" value="tessedit_create_txt,tessedit_create_pdf,tessedit_create_hocr,tessedit_create_tsv"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
243 <param name="psm" value="11"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
244 <output name="output_hocr">
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
245 <assert_contents>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
246 <has_text text="Ꮳ"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
247 <has_text text="ᏌᎠᏯᏙᏣᎠ"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
248 <has_size value="13185" delta="10"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
249 </assert_contents>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
250 </output>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
251 <output name="output_tsv" file="pdf_output.tsv"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
252 <output name="output_text" file="pdf_output.txt"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
253 <output name="output_pdf" file="pdf_output.pdf"/>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
254 </test>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
255 </tests>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
256 <help><![CDATA[
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
257 Tesseract OCR Tool
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
258 ------------------
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
259 Tesseract is an OCR engine with support for unicode and the ability to recognize more than 100 languages out of the box.
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
260
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
261 * `Tesseract User Manual <https://tesseract-ocr.github.io/tessdoc/>`_
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
262
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
263 * `API example for user patterns <https://tesseract-ocr.github.io/tessdoc/APIExample-user_patterns.html>`_
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
264
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
265 **Tesseract license**
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
266
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
267 * `Apache-2.0 <https://raw.githubusercontent.com/tesseract-ocr/tesseract/refs/heads/main/LICENSE>`_
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
268
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
269 **Poppler license**
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
270
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
271 * `GPL-2.0-only <https://gitlab.freedesktop.org/poppler/poppler/-/raw/master/COPYING>`_
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
272 ]]></help>
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
273 <expand macro="citations" />
9014c412d96c planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit a5652d3d3d6a07d96d3898659f0254d8265b8215
iuc
parents:
diff changeset
274 </tool>