Mercurial > repos > iuc > tesseract

diff tesseract.xml @ 6:64866a0b32b2 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/tesseract commit 5aa82b893895d90bfe44502f1494d23c7fbc70f9
author iuc
date Fri, 23 Jan 2026 07:37:39 +0000
parents a3c79d2b1041
children e74df764bfd9
line wrap: on
line diff
--- a/tesseract.xml	Thu Jan 15 19:53:12 2026 +0000
+++ b/tesseract.xml	Fri Jan 23 07:37:39 2026 +0000
@@ -199,6 +199,7 @@
             <option value="tessedit_create_hocr">HOCR</option>
             <option value="tessedit_create_tsv">TSV</option>
             <option value="tessedit_create_alto">ALTO</option>
+            <option value="tessedit_create_page_xml">PAGE</option>
         </param>
         <param argument="--psm" type="select" label="Page Segmentation Mode (PSM)" help="How the page layout is interpreted." optional="true">
             <option value="0">Orientation and script detection only</option>
@@ -234,9 +235,12 @@
         <data name="output_alto" format="xml" from_work_dir="output.xml" label="${tool.name} on ${on_string}: ALTO">
             <filter>'tessedit_create_alto' in output_formats</filter>
         </data>
+        <data name="output_page" format="xml" from_work_dir="output.xml" label="${tool.name} on ${on_string}: PAGE">
+            <filter>'tessedit_create_page_xml' in output_formats</filter>
+        </data>
     </outputs>
     <tests>
-        <test expect_num_outputs="3">
+        <test expect_num_outputs="4">
             <conditional name="models">
                 <param name="models_select" value="official"/>
                 <param name="tessdata" value="test_tessdata"/>
@@ -245,7 +249,7 @@
             <param name="input_file" value="eurotext.png"/>
             <param name="user_patterns" value="eng.user-patterns"/>
             <param name="user_words" value="eng.user-words"/>
-            <param name="output_formats" value="tessedit_create_txt,tessedit_create_pdf,tessedit_create_alto"/>
+            <param name="output_formats" value="tessedit_create_txt,tessedit_create_pdf,tessedit_create_alto,tessedit_create_page_xml"/>
             <param name="psm" value="3"/>
             <output name="output_text" file="image_output.txt"/>
             <output name="output_pdf" file="image_output.pdf"/>
@@ -254,6 +258,11 @@
                     <is_valid_xml/>
                 </assert_contents>
             </output>
+            <output name="output_page">
+                <assert_contents>
+                    <is_valid_xml/>
+                </assert_contents>
+            </output>
         </test>
         <test expect_num_outputs="2">
             <conditional name="models">