SQL Server Requires Chilkat v11.7.0+
SQL Server
PDF Text Layouts: flow, lines and grid
See more PDF Text Extraction Examples
Demonstrates the "layout" option of the "text" operation. "flow" (the default) joins the lines of each paragraph and returns tables as tab-separated rows; "lines" keeps each visual line of the page on its own line; "grid" pads with spaces so that the horizontal positions are preserved, like a fixed-pitch rendering of the page.Chilkat SQL Server Downloads
--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
DECLARE @hr int
DECLARE @sTmp0 nvarchar(4000)
DECLARE @success int
SELECT @success = 0
-- This example requires the Chilkat API to have been previously unlocked.
-- See Global Unlock Sample for sample code.
-- The PDF used in this example (a title, a paragraph, and a table with ruled cells) is available at warehouse_inventory.pdf
DECLARE @pdf int
EXEC @hr = sp_OACreate 'Chilkat.Pdf', @pdf OUT
IF @hr <> 0
BEGIN
PRINT 'Failed to create ActiveX component'
RETURN
END
EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/warehouse_inventory.pdf'
IF @success = 0
BEGIN
EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
PRINT @sTmp0
EXEC @hr = sp_OADestroy @pdf
RETURN
END
DECLARE @json int
EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @json OUT
DECLARE @sb int
EXEC @hr = sp_OACreate 'Chilkat.StringBuilder', @sb OUT
DECLARE @jsonOut int
EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @jsonOut OUT
-- ---- flow (the default) ----
-- The lines of a paragraph are joined into one line. A table becomes one line per row
-- with the cells separated by tabs, followed by a blank line.
EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'layout', 'flow'
EXEC sp_OAMethod @pdf, 'ExtractTextSb', @success OUT, 'text', @json, @sb, @jsonOut
IF @success = 0
BEGIN
EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
PRINT @sTmp0
EXEC @hr = sp_OADestroy @pdf
EXEC @hr = sp_OADestroy @json
EXEC @hr = sp_OADestroy @sb
EXEC @hr = sp_OADestroy @jsonOut
RETURN
END
PRINT '---- flow ----'
EXEC sp_OAMethod @sb, 'GetAsString', @sTmp0 OUT
PRINT @sTmp0
-- ---- lines ----
-- Each visual line of the page is one output line. A table row is its cells joined by single spaces.
EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'layout', 'lines'
EXEC sp_OAMethod @sb, 'Clear', NULL
EXEC sp_OAMethod @pdf, 'ExtractTextSb', @success OUT, 'text', @json, @sb, @jsonOut
IF @success = 0
BEGIN
EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
PRINT @sTmp0
EXEC @hr = sp_OADestroy @pdf
EXEC @hr = sp_OADestroy @json
EXEC @hr = sp_OADestroy @sb
EXEC @hr = sp_OADestroy @jsonOut
RETURN
END
PRINT '---- lines ----'
EXEC sp_OAMethod @sb, 'GetAsString', @sTmp0 OUT
PRINT @sTmp0
-- ---- grid ----
-- Each line is padded with spaces so that the text sits at its horizontal position on the page.
-- Table columns line up as they do on the page, which suits fixed-width parsing.
EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'layout', 'grid'
EXEC sp_OAMethod @sb, 'Clear', NULL
EXEC sp_OAMethod @pdf, 'ExtractTextSb', @success OUT, 'text', @json, @sb, @jsonOut
IF @success = 0
BEGIN
EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
PRINT @sTmp0
EXEC @hr = sp_OADestroy @pdf
EXEC @hr = sp_OADestroy @json
EXEC @hr = sp_OADestroy @sb
EXEC @hr = sp_OADestroy @jsonOut
RETURN
END
PRINT '---- grid ----'
EXEC sp_OAMethod @sb, 'GetAsString', @sTmp0 OUT
PRINT @sTmp0
-- Sample output (abbreviated; the tabs in the flow output are shown as -> here):
-- ---- flow ----
-- Warehouse Inventory Report
--
-- Stock on hand at the Wheaton distribution center as of September 30, 2026. Quantities are counted units; the unit cost is the average landed cost in US dollars. Items at or below their reorder point are flagged in the status column.
--
-- SKU->Description->Category->Qty on Hand->Unit Cost->Status
-- WH-1001->Steel shelving unit, 5 tier->Storage->42->189.50->OK
-- WH-1002->Pallet jack, 5500 lb->Equipment->7->412.00->Reorder
-- WH-1003->Stretch wrap, 18 in roll->Packaging->640->9.75->OK
-- ...
-- WH-1012->Wire shelf liner, 48 in->Storage->24->6.15->Reorder
--
-- Four items are at or below their reorder point and one item is out of stock. Purchase orders for the flagged items should be raised before the October cycle count.
--
-- ---- lines ----
-- Warehouse Inventory Report
-- Stock on hand at the Wheaton distribution center as of September 30, 2026. Quantities are counted units; the
-- unit cost is the average landed cost in US dollars. Items at or below their reorder point are flagged in the status
-- column.
-- SKU Description Category Qty on Hand Unit Cost Status
-- WH-1001 Steel shelving unit, 5 tier Storage 42 189.50 OK
-- WH-1002 Pallet jack, 5500 lb Equipment 7 412.00 Reorder
-- WH-1003 Stretch wrap, 18 in roll Packaging 640 9.75 OK
-- ...
-- WH-1012 Wire shelf liner, 48 in Storage 24 6.15 Reorder
-- Four items are at or below their reorder point and one item is out of stock. Purchase orders for the flagged items
-- should be raised before the October cycle count.
--
-- ---- grid ----
-- Warehouse Inventory Report
-- Stock on hand at the Wheaton distribution center as of September 30, 2026. Quantities are counted units; the
-- unit cost is the average landed cost in US dollars. Items at or below their reorder point are flagged in the status
-- column.
--
-- SKU Description Category Qty on Hand Unit Cost Status
-- WH-1001 Steel shelving unit, 5 tier Storage 42 189.50 OK
-- WH-1002 Pallet jack, 5500 lb Equipment 7 412.00 Reorder
-- WH-1003 Stretch wrap, 18 in roll Packaging 640 9.75 OK
-- ...
-- WH-1012 Wire shelf liner, 48 in Storage 24 6.15 Reorder
--
-- Four items are at or below their reorder point and one item is out of stock. Purchase orders for the flagged items
-- should be raised before the October cycle count.
EXEC @hr = sp_OADestroy @pdf
EXEC @hr = sp_OADestroy @json
EXEC @hr = sp_OADestroy @sb
EXEC @hr = sp_OADestroy @jsonOut
END
GO