comparison iscc_sum.xml @ 1:2812afc5f30a draft default tip

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

0:01155dd89628

<tool id="iscc_sum" name="Generate ISCC hash" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.1">
    <description>with ISCC-SUM</description>

    <macros>
        <import>macros.xml</import>
        <import>creators.xml</import>

        <expand macro="creators/maartenpaul" />
        <expand macro="creators/etzm" />
    </creator>
        
    <command detect_errors="exit_code"><![CDATA[
        iscc-sum '$input_file' | cut -d':' -f2 | cut -d' ' -f1 > '${output_file}'
    ]]></command>
    
    <inputs>
        <param name="input_file" type="data" format="data" label="Input File" 
               help="Any file type - ISCC-SUM will generate a checksum and similarity hash"/>
    </inputs>
    
    <outputs>
        <data name="output_file" format="txt" label="${tool.name} on ${on_string}"/>
    </outputs>
    
    <tests>
        <test expect_num_outputs="1">
            <param name="input_file" value="test1.png"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="test2.tiff"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AGSPOSB5SS2X427WZ27QASTSBVTS55DXLMFDF7WOJKEOSTDEI3OXQ" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="1">
            <param name="input_file" value="test3.fasta"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AKF7PTZ7JTAAYZ7YZHZPR5RETKYXXE7RTBTJA4JX5GQQMSLZRC6QQ" />
                </assert_contents>
            </output>
        </test>
    </tests>
    
    <help><![CDATA[
**What it does**

Generates an International Standard Content Code (ISCC) based checksum and similarity hash from any input file.

The ISCC-SUM is a content-derived identifier that:    
- Creates a unique checksum based on file content    
- Generates a similarity hash for content comparison    
- Works with any file format    

**Input**

Any file format is accepted as input.

**Output**

A text file containing the ISCC-SUM code for the input file.

**More Information**

For more details about ISCC, visit: https://iscc.codes/
    ]]></help>

    <expand macro="citations" />
    
</tool>

1:2812afc5f30a

<tool id="iscc_sum" name="Generate 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>

        <expand macro="creators/maartenpaul" />
        <expand macro="creators/etzm" />
    </creator>
        
    <command detect_errors="exit_code"><![CDATA[
        ## Generate ISCC-CODE for input dataset
        iscc-sum '${input_file}' | cut -d':' -f2 | cut -d' ' -f1 >> '${output_file}'
    ]]></command>

    <inputs>
        <param name="input_file" type="data" format="data" label="Input file"
               help="Any file type - ISCC-SUM will generate an ISCC-CODE for content identification and verification. When a collection is provided, generates one ISCC-CODE per dataset."/>
    </inputs>
    
    <outputs>
        <data name="output_file" format="txt" label="${tool.name} on ${on_string}"/>
    </outputs>
    
    <tests>
        <!-- Test 1: Single dataset PNG -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test1.png"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test>
        
        <!-- Test 2: Single dataset FASTA -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test3.fasta"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AKF7PTZ7JTAAYZ7YZHZPR5RETKYXXE7RTBTJA4JX5GQQMSLZRC6QQ" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test>
        
        <!-- Test 3: Single dataset TIFF -->
        <test expect_num_outputs="1">
            <param name="input_file" value="test2.tiff"/>
            <output name="output_file">
                <assert_contents>
                    <has_line line="K4AGSPOSB5SS2X427WZ27QASTSBVTS55DXLMFDF7WOJKEOSTDEI3OXQ" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test>
    </tests>
    
    <help><![CDATA[
What it does
============

Generates an ISCC-CODE (International Standard Content Code) for datasets using the ISCC-SUM algorithm.

The ISCC-SUM creates a content-derived identifier that:

- Creates a unique 55-character ISCC-CODE based on dataset content
- Enables both exact matching (checksum) and similarity detection
- Works with any file format

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

When you provide a collection, Galaxy automatically runs this tool once per dataset, generating individual ISCC-CODEs for each dataset in the collection.

Output
======

A text file containing the ISCC-CODE (55 characters)

Example output::

    K4AOMGOGQJA4Y46PAC4YPPA63GKD5RVFPR7FU3I4OOEW44TYXNYOTMY

Use Cases
=========

- Generate ISCC-CODEs for file integrity verification
- Create content identifiers for duplicate detection
- Track file provenance and changes over time
- Enable similarity-based file comparison

ISCC-CODE Structure
===================

The 55-character ISCC-CODE is composed of multiple ISCC-UNITs:

- **Data-Code**: Content similarity hash (enables fuzzy matching for similar files)
- **Instance-Code**: Exact file checksum (for bit-perfect verification)

This combination creates an ISCC-CODE with SubType SUM, hence the name ISCC-SUM.

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

Generate ISCC-CODEs for a collection
-------------------------------------

::

    Input: Collection of 100 datasets
    ↓
    [Generate ISCC-CODE] ← runs 100 times
    ↓
    Output: Collection of 100 ISCC-CODE files
    ↓
    [Collapse Collection] ← Galaxy tool
    ↓
    Result: Single file with all ISCC-CODEs

Create reference ISCC-CODEs
----------------------------

::

    Input: Original datasets
    ↓
    [Generate ISCC-CODE]
    ↓
    Store ISCC-CODEs for future verification

Compare datasets
----------------

::

    Dataset A → [Generate ISCC-CODE] → ISCC-CODE A
    Dataset B → [Generate ISCC-CODE] → ISCC-CODE B
    ↓
    Compare ISCC-CODEs
    ↓
    Result: Exact match or similarity score

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>