diff --git a/docs/benchmark/stream/12s0324/12s0324-data-tabula-0.csv.csv b/docs/benchmark/stream/12s0324/12s0324-data-tabula-0.csv similarity index 100% rename from docs/benchmark/stream/12s0324/12s0324-data-tabula-0.csv.csv rename to docs/benchmark/stream/12s0324/12s0324-data-tabula-0.csv diff --git a/docs/benchmark/stream/12s0324/12s0324-data-tabula-1.csv.csv b/docs/benchmark/stream/12s0324/12s0324-data-tabula-1.csv similarity index 100% rename from docs/benchmark/stream/12s0324/12s0324-data-tabula-1.csv.csv rename to docs/benchmark/stream/12s0324/12s0324-data-tabula-1.csv diff --git a/docs/benchmark/stream/superscript/superscript-data-camelot-page-1-table-1.csv b/docs/benchmark/stream/superscript/superscript-data-camelot-page-1-table-1.csv new file mode 100755 index 0000000..1bd4857 --- /dev/null +++ b/docs/benchmark/stream/superscript/superscript-data-camelot-page-1-table-1.csv @@ -0,0 +1,41 @@ +"","TABLE 125: STATE-WISE COMPOSITION OF OUTSTANDING LIABILITIES - 1997 (Contd.)","","","","","","","","","" +"","","","","(As at end-March)","","","","","","" +"","","","","","","","","","","(` Billion)" +"States","Total","Market","NSSF","WMA","Loans","Loans","Loans","Loans","Loans","Loans" +"","Internal","Loans","","from","from","from","from","from","from SBI","from" +"","Debt","","","RBI","Banks","LIC","GIC","NABARD","& Other","NCDC" +"","","","","","& FIs","","","","Banks","" +"1","2=","3","4","5","6=","7","8","9","10","11" +"","(3 to 6)+14","","","","(7 to13)","","","","","" +"Andhra Pradesh","48.11","40.45","-","3.26","4.4","2.62","-","0.91","-","0.25" +"Arunachal Pradesh","1.23","1.1","-","-","0.13","-","-","-","-","-" +"Assam","12.69","10.02","-","2.41","0.26","0.08","-","-0.06","0.01","0.24" +"Bihar","40.75","41.54","-","-","-1.42","0.19","-","-1.01","-0.36","0.2" +"Chhattisgarh","-","-","-","-","-","-","-","-","-","-" +"Goa","1.4","1.02","-","-","0.38","0.31","-","0.07","-","-" +"Gujarat","19.75","17.1","-","-","2.64","1.17","-","1.11","-","0.44" +"Haryana","11.53","9.67","-","0.06","1.8","0.55","-","0.64","-","0.49" +"Himachal Pradesh","8.02","2.94","-","4.55","0.53","0.13","-","0.05","-","0.25" +"Jammu and Kashmir","11.72","4.49","-","-","7.23","0.66","-","0.02","6.08","-" +"Jharkhand","-","-","-","-","-","-","-","-","-","-" +"Karnataka","22.44","19.59","-","-","2.86","1.22","-","0.89","-","0.69" +"Kerala","29.03","24.912","-","-","4.11","1.77","-","0.48","-","1.45" +"Madhya Pradesh","27.13","23.57","-","-","3.56","0.38","-","1.86","-","1.28" +"Maharashtra","30.47","26.07","-","-","4.39","0.21","-","-0.12","0.02","2.89" +"Manipur","2.17","1.61","-","0.26","0.29","0.08","-","-","-","0.09" +"Meghalaya","1.36","1.38","-","-","-0.02","0.04","-","-0.05","-","0.03" +"Mizoram","1.17","0.46","-","0.27","0.43","0.11","-","-","-","0.03" +"Nagaland","2.99","2.6","-","-","0.39","0.24","-","-","-","0.04" +"Odisha","34.04","27.58","-","4.4","2.06","0.56","-","0.66","-","0.2" +"Punjab","19.18","10.93","-","1.03","7.23","0.17","-","0.71","5.9","0.46" +"Rajasthan","36.77","28.63","-","4.99","3.16","0.57","-","1.64","-","0.81" +"Sikkim","0.16","-","-","-","0.16","0.03","-","-","-","0.01" +"Tamil Nadu","34.11","31.41","-","-","2.7","1.3","-","0.6","-","0.68" +"Tripura","2.3","1.89","-","-","0.41","0.41","-","-0.05","-","0.02" +"Uttaranchal","-","-","-","-","-","-","-","-","-","-" +"Uttar Pradesh","80.62","74.89","-","4.34","1.34","0.6","-","-0.21","0.18","0.03" +"West Bengal","34.23","32.19","-","-","2.04","0.77","-","0.06","-","0.51" +"NCT Delhi","-","-","-","-","-","-","-","-","-","-" +"ALL STATES","513.38","436.02","-","25.57","51.06","14.18","-","8.21","11.83","11.08" +"2 Includes `2.45 crore outstanding under “Market Loan Suspense”.","","","","","","","","","","" +"","","","","445","","","","","","" diff --git a/docs/benchmark/stream/superscript/superscript-data-tabula.csv b/docs/benchmark/stream/superscript/superscript-data-tabula.csv new file mode 100755 index 0000000..8650656 --- /dev/null +++ b/docs/benchmark/stream/superscript/superscript-data-tabula.csv @@ -0,0 +1,36 @@ +States,Total,Market,NSSF,WMA,Loans,Loans,Loans,Loans,Loans,Loans +"",Internal,Loans,,from,from,from,from,from,from SBI,from +"",Debt,,,RBI,Banks,LIC,GIC,NABARD,& Other,NCDC +"",,,,,& FIs,,,,Banks, +1,2=,3,4,5,6=,7,8,9,10,11 +"",(3 to 6)+14,,,,(7 to13),,,,, +Andhra Pradesh,48.11,40.45,-,3.26,4.4,2.62,-,0.91,-,0.25 +Arunachal Pradesh,1.23,1.1,-,-,0.13,-,-,-,-,- +Assam,12.69,10.02,-,2.41,0.26,0.08,-,-0.06,0.01,0.24 +Bihar,40.75,41.54,-,-,-1.42,0.19,-,-1.01,-0.36,0.2 +Chhattisgarh,-,-,-,-,-,-,-,-,-,- +Goa,1.4,1.02,-,-,0.38,0.31,-,0.07,-,- +Gujarat,19.75,17.1,-,-,2.64,1.17,-,1.11,-,0.44 +Haryana,11.53,9.67,-,0.06,1.8,0.55,-,0.64,-,0.49 +Himachal Pradesh,8.02,2.94,-,4.55,0.53,0.13,-,0.05,-,0.25 +Jammu and Kashmir,11.72,4.49,-,-,7.23,0.66,-,0.02,6.08,- +Jharkhand,-,-,-,-,-,-,-,-,-,- +Karnataka,22.44,19.59,-,-,2.86,1.22,-,0.89,-,0.69 +Kerala,29.03,24.912,-,-,4.11,1.77,-,0.48,-,1.45 +Madhya Pradesh,27.13,23.57,-,-,3.56,0.38,-,1.86,-,1.28 +Maharashtra,30.47,26.07,-,-,4.39,0.21,-,-0.12,0.02,2.89 +Manipur,2.17,1.61,-,0.26,0.29,0.08,-,-,-,0.09 +Meghalaya,1.36,1.38,-,-,-0.02,0.04,-,-0.05,-,0.03 +Mizoram,1.17,0.46,-,0.27,0.43,0.11,-,-,-,0.03 +Nagaland,2.99,2.6,-,-,0.39,0.24,-,-,-,0.04 +Odisha,34.04,27.58,-,4.4,2.06,0.56,-,0.66,-,0.2 +Punjab,19.18,10.93,-,1.03,7.23,0.17,-,0.71,5.9,0.46 +Rajasthan,36.77,28.63,-,4.99,3.16,0.57,-,1.64,-,0.81 +Sikkim,0.16,-,-,-,0.16,0.03,-,-,-,0.01 +Tamil Nadu,34.11,31.41,-,-,2.7,1.3,-,0.6,-,0.68 +Tripura,2.3,1.89,-,-,0.41,0.41,-,-0.05,-,0.02 +Uttaranchal,-,-,-,-,-,-,-,-,-,- +Uttar Pradesh,80.62,74.89,-,4.34,1.34,0.6,-,-0.21,0.18,0.03 +West Bengal,34.23,32.19,-,-,2.04,0.77,-,0.06,-,0.51 +NCT Delhi,-,-,-,-,-,-,-,-,-,- +ALL STATES,513.38,436.02,-,25.57,51.06,14.18,-,8.21,11.83,11.08 diff --git a/docs/benchmark/stream/superscript/superscript.pdf b/docs/benchmark/stream/superscript/superscript.pdf new file mode 100755 index 0000000..855a3bd Binary files /dev/null and b/docs/benchmark/stream/superscript/superscript.pdf differ diff --git a/docs/user/advanced.rst b/docs/user/advanced.rst index 2c09d5f..607e8d0 100644 --- a/docs/user/advanced.rst +++ b/docs/user/advanced.rst @@ -5,16 +5,11 @@ Advanced Usage This page covers some of the more advanced configurations for :ref:`Stream ` and :ref:`Lattice `. -Plot geometry -------------- - - - -You can call Lattice with debug={'line', 'intersection', 'contour', 'table'}, and call `debug_plot()` which will generate an image like the ones on this page, with the help of which you can modify various parameters. See :doc:`API doc ` for more information. - Process background lines ------------------------ +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/lattice/background_lines_1/background_lines_1.pdf + To find line segments, Lattice needs the lines of the pdf file to be in foreground. So, if you encounter a file like this, just set invert to True. :: @@ -26,26 +21,43 @@ To find line segments, Lattice needs the lines of the pdf file to be in foregrou >>> tables = manager.extract() >>> print tables['page-1']['table-1']['data'] +Plot geometry +------------- + +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/us-007/us-007.pdf + +You can call Lattice with debug={'line', 'intersection', 'contour', 'table'}, and call `debug_plot()` which will generate an image like the ones on this page, with the help of which you can modify various parameters. See :doc:`API doc ` for more information. + Specify table areas ------------------- -Specify columns ---------------- +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/us-007/us-007.pdf -Split text in spanning cells ----------------------------- +Specify column separators +------------------------- + +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/m27/m27.pdf + +Split text along separators +--------------------------- + +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/m27/m27.pdf Flag subscripts and superscripts -------------------------------- -.. note:: This will available in a future release. +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/superscript/superscript.pdf Control how text is grouped into rows ------------------------------------- -Detect small lines +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/mexican_towns/mexican_towns.pdf + +Detect short lines ------------------ +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/lattice/row_span/row_span.pdf + The scale parameter is used to determine the length of the structuring element used for morphological transformations. The length of vertical and horizontal structuring elements are found by dividing the image's height and width respectively, by `scale`. Large `scale` will lead to a smaller structuring element, which means that smaller lines will be detected. The default value for scale is 15. Let's consider this pdf file. @@ -68,12 +80,12 @@ Clearly, it couldn't detected those small lines in the lower left part. Therefor Voila! It detected the smaller lines. -Detect faint lines ------------------- Copy text in spanning cells --------------------------- +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/lattice/row_span/row_span.pdf + In the file used above, you can see that some cells spanned a lot of rows, `fill` just copies the same value to all rows/columns of a spanning cell. You can apply fill horizontally, vertically or both. Let us fill the output for the file we used above, vertically. :: @@ -88,5 +100,4 @@ In the file used above, you can see that some cells spanned a lot of rows, `fill Shift text in spanning cells ---------------------------- -Tweak PDFMiner margins ----------------------- \ No newline at end of file +https://github.com/socialcopsdev/camelot/blob/docs/docs/benchmark/stream/m27/m27.pdf \ No newline at end of file