http://www.quickpdf.org/forum/ Copyright (c) 2006-2013 Web Wiz Forums - All Rights Reserved. Mon, 11 May 2026 22:15:36 +0000 Sat, 27 Nov 2010 11:41:06 +0000 http://blogs.law.harvard.edu/tech/rss Web Wiz Forums 11.01 360 www.quickpdf.org/forum/RSS_post_feed.asp?TID=1656 http://www.quickpdf.org/forum/forum_images/QPDF_Forum_Title.png http://www.quickpdf.org/forum/ http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7268.html#7268 Author: alinux
Subject: 1656
Posted: 27 Nov 10 at 11:41AM

Thanks guys.

Cheers,
]]> Sat, 27 Nov 2010 11:41:06 +0000 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7268.html#7268 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7267.html#7267 Author: Rowan
Subject: 1656
Posted: 27 Nov 10 at 9:20AM

Great job.]]> Sat, 27 Nov 2010 09:20:36 +0000 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7267.html#7267 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7266.html#7266 Author: Ingo
Subject: 1656
Posted: 26 Nov 10 at 8:13PM

Hi Alinux!

Thanks for this.
I think here are many users looking for this option in QuickPDF.
Your sample could be a starting point for options like "keep
the original layout in txt, too"...
Thanks for sharing with us!

Cheers, Ingo
]]> Fri, 26 Nov 2010 20:13:42 +0000 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7266.html#7266 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7264.html#7264 Author: alinux
Subject: 1656
Posted: 26 Nov 10 at 7:40PM

It's a basic sample of text lines assembling  from GetPageText(4) function result; the results depend on quality of scan & OCR process.
In the case of tables, the OCR engine may detect, "read" & process the tables by line or by column independent of you so you'll need a sort array function for sorting the page lines array by y coordinate of each line.


Private Function full_lines(get_page_text As String) As String

'page text lines array (0,N) - y1 or y2 word coordinate, (1,N) - line words
Dim dmp_pge() As String

ReDim dmp_pge(1, 0)

'page words array
dmp_lns = Split(get_page_text, vbCrLf)

For i = 0 To UBound(dmp_lns)
    If dmp_lns(i) <> "" Then

    'word line array
        dmp_wrd = Split(dmp_lns(i), ",")

        flag_exist = False
        For j = UBound(dmp_pge, 2) To 0 Step -1
            If dmp_wrd(4) = dmp_pge(0, j) Then

               'add next word in the same line
                If dmp_pge(1, j) <> "" Then dmp_pge(1, j) = dmp_pge(1, j) & " " & dmp_wrd(UBound(dmp_wrd)) Else dmp_pge(1, j) = dmp_wrd(UBound(dmp_wrd))
                flag_exist = True
                Exit For
            End If
            DoEvents
        Next
        If Not flag_exist Then
            If dmp_pge(1, UBound(dmp_pge, 2)) <> "" Then
                ReDim Preserve dmp_pge(1, UBound(dmp_pge, 2) + 1)
            End If

           'add y1 word(line) coordinate & first word of the new line
            dmp_pge(0, UBound(dmp_pge, 2)) = dmp_wrd(4)
            dmp_pge(1, UBound(dmp_pge, 2)) = dmp_wrd(UBound(dmp_wrd))
        End If
    End If
    DoEvents
Next

'need sort array function in the case of tables (the OCR engine may identify & "read" the table by column so you must sort the lines array by the y coordinate - see dmp_pge definition)
'sort_array dmp_pge

For i = 0 To UBound(dmp_pge, 2)
    If full_lines = "" Then full_lines = dmp_pge(1, i) Else full_lines = full_lines & vbCrLf & dmp_pge(1, i)
    DoEvents
Next
full_lines = Replace(full_lines, """", "")

End Function
]]> Fri, 26 Nov 2010 19:40:47 +0000 http://www.quickpdf.org/forum/text-lines-assembling-in-vb6_topic1656_post7264.html#7264