Allows to add the headers separating in fields the data of the text obtained of the HOCR document.

1 ocr.array.header

<ocr.array.header
    date-pattern='date-pattern'
    date-format='date-format'
    number-pattern='number-pattern'
    decimal-separator='decimal-separator'
    grouping-separator='grouping-separator'
>
    <ocr.array.header.item
        type='type'
        column='column'
        pattern='pattern'
    /> +
</ocr.array.header>
Example

Gets the text through a HOCR document and it adds headers to the data of the obtained text.

Copy
<xsql-script name='ocr'>
    <body>
        <set name='m_ocr'>
            <ocr>
                <m_ocr_text />
            </ocr>
        </set>
        <ocr.array.header 
            date-pattern='(0[1-9]|1[012])[- /.](0[1-9]|[12][0-9]|3[01])[-/.](19|20)\\d\\d(?:,)' 
            date-format='MM/DD/YYYY' 
            number-pattern='(((\d{1,3})(.\d{3})*)|(\d+))(,\d+)?' 
            decimal-separator=',' 
            grouping-separator='.'>
            <ocr.array.header.item column='Codigo'><m_ocr/<</ocr.array.header.item>
            <ocr.array.header.item type='char' column='Especialidad'><m_ocr/></ocr.array.header.item>
            <ocr.array.header.item type='number' column='IVA'><m_ocr/></ocr.array.header.item>
            <ocr.array.header.item type='number' column='Cantidad'><m_ocr/></ocr.array.header.item>
            <ocr.array.header.item type='number' column='Precio'><m_ocr/></ocr.array.header.item>
            <ocr.array.header.item type='number' column='Dto.'><m_ocr/></ocr.array.header.item>
            <ocr.array.header.item type='number' column='Importe' pattern="(((\d{1,3})(.\d{3})*)|(\d+))(,\d+)?"><m_ocr/></ocr.array.header.item>
        </ocr.array.header>
    </body>
</xsql-script>