view iscc_verify.xml @ 0:9fee6d81910d draft default tip

planemo upload for repository https://github.com/BMCV/galaxy-image-analysis/tree/master/tools/iscc-sum commit 6db86b8b65a0e05b7f3541d505fbe900633fc72a

<tool id="iscc_sum_verify" name="Verify ISCC-CODE" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.1">
    <description>with ISCC-SUM</description>
    <macros>
        <import>macros.xml</import>
        <import>creators.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <creator>
        <expand macro="creators/iscc" />
        <expand macro="creators/lco" />
        <expand macro="creators/maartenpaul" />
        <expand macro="creators/etzm" />
    </creator>

    <command detect_errors="exit_code"><![CDATA[
        ## Generate ISCC-CODE for input dataset
        GENERATED=\$(iscc-sum '${input_file}' | cut -d':' -f2 | cut -d' ' -f1) &&
        
        ## Get expected ISCC-CODE
        EXPECTED='${expected_code}' &&
        
        ## Validate expected ISCC-CODE length
        if [ \${#EXPECTED} -ne 55 ]; then
            echo "ERROR: Expected ISCC-CODE must be exactly 55 characters" >&2;
            echo "Found: \${#EXPECTED} characters" >&2;
            exit 1;
        fi &&
        
        ## Output verification report
        if [ "\$GENERATED" = "\$EXPECTED" ]; then
            echo "OK - ISCC-CODEs match" > '${output_file}'; 
        else
            echo "FAILED - ISCC-CODEs do not match" > '${output_file}'; 
        fi &&
        echo "Expected:  \$EXPECTED" >> '${output_file}' &&
        echo "Generated: \$GENERATED" >> '${output_file}' &&
        echo "" >> '${output_file}' 

    ]]></command>
        
    <inputs>
        <param name="input_file" type="data" format="data" label="Dataset to verify"
            help="Verify this dataset's ISCC-CODE. When a collection is provided, each dataset is verified separately against the same expected ISCC-CODE."/>
        <param name="expected_code" type="text" label="Expected ISCC-CODE"
            help="The 55-character ISCC-CODE to verify against">
            <validator type="length" min="55" max="55" message="ISCC-CODE must be exactly 55 characters"/>
        </param>
    </inputs>
    
    <outputs>
        <data name="output_file" format="txt" label="${tool.name} on ${on_string}"/>
    </outputs>
    
    <tests>
        <!-- Test 1: Successful verification -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test1.png"/>
            <param name="expected_code" value="K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY"/>
            <output name="output_file">
                <assert_contents>
                    <has_text text="OK - ISCC-CODEs match"/>
                    <has_text text="Expected:  K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY"/>
                    <has_text text="Generated: K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY"/>
                    <has_n_lines n="4"/>
                </assert_contents>
            </output>
        </test>
        
        <!-- Test 2: Failed verification -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test1.png"/>
            <param name="expected_code" value="K4AGSPOSB5SS2X427WZ27QASTSBVTS55DXLMFDF7WOJKEOSTDEI3OXQ"/>
            <output name="output_file">
                <assert_contents>
                    <has_text text="FAILED - ISCC-CODEs do not match"/>
                    <has_text text="Expected:  K4AGSPOSB5SS2X427WZ27QASTSBVTS55DXLMFDF7WOJKEOSTDEI3OXQ"/>
                    <has_text text="Generated: K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY"/>
                    <has_n_lines n="4"/>
                </assert_contents>
            </output>
        </test>
        
        <!-- Test 3: FASTA file verification -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test3.fasta"/>
            <param name="expected_code" value="K4AKF7PTZ7JTAAYZ7YZHZPR5RETKYXXE7RTBTJA4JX5GQQMSLZRC6QQ"/>
            <output name="output_file">
                <assert_contents>
                    <has_text text="OK - ISCC-CODEs match"/>
                    <has_text text="Expected:  K4AKF7PTZ7JTAAYZ7YZHZPR5RETKYXXE7RTBTJA4JX5GQQMSLZRC6QQ"/>
                    <has_text text="Generated: K4AKF7PTZ7JTAAYZ7YZHZPR5RETKYXXE7RTBTJA4JX5GQQMSLZRC6QQ"/>
                    <has_n_lines n="4"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    
    <help><![CDATA[
What it does
============

Verifies that a file (dataset) matches an expected ISCC-CODE (International Standard Content Code) for exact content verification. This tool uses ISCC-SUM, which generates an ISCC-CODE containing Data-Code and Instance-Code units for bit-level file comparison.

Exit Codes
==========

The tool uses exit codes for workflow logic:

- **0**: Verification successful (OK - ISCC-CODEs match)
- **1**: Verification failed (FAILED - ISCC-CODEs do not match)

Dataset Mapping
===============

When you provide a collection, Galaxy automatically runs verification once per dataset. All datasets are verified against the same expected ISCC-CODE.

Output
======

A verification report containing:

- Filename (or element identifier)
- Expected ISCC-CODE
- Generated ISCC-CODE
- Status: OK or FAILED

Example output::
    Status: OK - ISCC-CODEs match

    Expected:  K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY
    Generated: K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY
    
Use Cases
=========

- Verify file integrity after transfer or storage
- Confirm downloaded datasets match reference ISCC-CODEs
- Validate that backups are identical to originals
- Quality control for data archiving

Workflow Examples
=================

Verify a single dataset
-----------------------

::

    Input: document.pdf
    Expected ISCC-CODE: K4AOMG...
    ↓
    [Verify ISCC-CODE]
    ↓
    Output: "OK" or "FAILED"

Verify against reference table
-------------------------------

Generate reference ISCC-CODEs first::

    Original files → [Generate ISCC-CODE] → Reference ISCC-CODEs
    
Later verify::

    New datasets → [Generate ISCC-CODE] → New ISCC-CODEs
    ↓
    [Join two Datasets] on filename
    ↓
    Compare ISCC-CODE columns
    ↓
    Result: Which files match/differ

Working with ISCC-CODE Files in Workflows
==========================================

If you have the expected ISCC-CODE in a dataset (e.g., from Generate ISCC tool):

1. In the workflow editor, connect the ISCC-CODE file to this tool
2. The ISCC-CODE file content will be used automatically
3. Or manually copy the ISCC-CODE from the file into the text field

Important Notes
===============

- **Exact match only**: Any change to the file will cause verification to fail
- **Bit-level comparison**: Even metadata changes are detected
- **For similarity detection**: Use "Find similar ISCC-CODEs" tool instead

More Information
================

For details about ISCC: https://sum.iscc.codes/ and https://iscc.codes/
For ISCC structure and subtypes: https://ieps.iscc.codes/iep-0001/
    ]]></help>
    <expand macro="citations" />
</tool>