From 7e5516eb5da7f19ff625b4266be6f9932fee12cc Mon Sep 17 00:00:00 2001
From: Eric Ihli <ericihli@gmail.com>
Date: Sat, 17 Oct 2020 05:36:40 -0700
Subject: [PATCH] Update README in setup.py

---
 README.md                        | 60 ++++++++++++++++++++++++++++++++
 pdf_table_extraction_and_ocr.org |  8 ++---
 setup.py                         |  8 ++---
 3 files changed, 68 insertions(+), 8 deletions(-)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..043edfe
--- /dev/null
+++ b/README.md
@@ -0,0 +1,60 @@
+
+# Table of Contents
+
+
+
+This python package contains modules to help with finding and extracting tabular
+data from a PDF or image into a CSV format.
+
+Given an image that contains a table&#x2026;
+
+![img](resources/examples/example-page.png)
+
+Extract the the text into a CSV format&#x2026;
+
+    PRIZE,ODDS 1 IN:,# OF WINNERS*
+    $3,9.09,"282,447"
+    $5,16.66,"154,097"
+    $7,40.01,"64,169"
+    $10,26.67,"96,283"
+    $20,100.00,"25,677"
+    $30,290.83,"8,829"
+    $50,239.66,"10,714"
+    $100,919.66,"2,792"
+    $500,"6,652.07",386
+    "$40,000","855,899.99",3
+    1,i223,
+    Toa,,
+    ,,
+    ,,"* Based upon 2,567,700"
+
+The package is split into modules with narrow focuses.
+
+-   `pdf_to_images` uses Poppler and ImageMagick to extract images from a PDF.
+-   `extract_tables` finds and extracts table-looking things from an image.
+-   `extract_cells` extracts and orders cells from a table.
+-   `ocr_image` uses Tesseract to OCR the text from an image of a cell.
+-   `ocr_to_csv` converts into a CSV the directory structure that `ocr_image` outputs.
+
+The outputs of a previous module can be used by a subsequent module so that they
+can be chained together to create the entire workflow, as demonstrated by the
+following shell script.
+
+    #!/bin/sh
+    
+    PDF=$1
+    
+    python -m table_ocr.pdf_to_images $PDF | grep .png > /tmp/pdf-images.txt
+    cat /tmp/pdf-images.txt | xargs -I{} python -m table_ocr.extract_tables {}  | grep table > /tmp/extracted-tables.txt
+    cat /tmp/extracted-tables.txt | xargs -I{} python -m table_ocr.extract_cells {} | grep cells > /tmp/extracted-cells.txt
+    cat /tmp/extracted-cells.txt | xargs -I{} python -m table_ocr.ocr_image {}
+    
+    for image in $(cat /tmp/extracted-tables.txt); do
+        dir=$(dirname $image)
+        python -m table_ocr.ocr_to_csv $(find $dir/cells -name "*.txt")
+    done
+
+The package was written in a [literate programming](https://en.wikipedia.org/wiki/Literate_programming) style. The source code at
+<https://eihli.github.io/image-table-ocr/pdf_table_extraction_and_ocr.html> is
+meant to act as the documentation and reference material.
+
diff --git a/pdf_table_extraction_and_ocr.org b/pdf_table_extraction_and_ocr.org
index a86c5f4..7b5e966 100644
--- a/pdf_table_extraction_and_ocr.org
+++ b/pdf_table_extraction_and_ocr.org
@@ -785,13 +785,13 @@ ocr_image(image, "--psm 7")
 
 ** setup.py
 #+BEGIN_SRC python :tangle setup.py :results none
+import os
 import setuptools
 
-long_description = """
-Utilities for turning images of tables into CSV data. Uses Tesseract and OpenCV.
+this_dir = os.path.abspath(os.path.dirname(__file__))
+with open(os.path.join(this_dir, "README.md"), encoding="utf-8") as f:
+    long_description = f.read()
 
-Requires binaries for tesseract, ImageMagick, and pdfimages (from Poppler).
-"""
 setuptools.setup(
     name="table_ocr",
     version="0.2.1",
diff --git a/setup.py b/setup.py
index 9f65856..78d375c 100644
--- a/setup.py
+++ b/setup.py
@@ -1,10 +1,10 @@
+import os
 import setuptools
 
-long_description = """
-Utilities for turning images of tables into CSV data. Uses Tesseract and OpenCV.
+this_dir = os.path.abspath(os.path.dirname(__file__))
+with open(os.path.join(this_dir, "README.md"), encoding="utf-8") as f:
+    long_description = f.read()
 
-Requires binaries for tesseract, ImageMagick, and pdfimages (from Poppler).
-"""
 setuptools.setup(
     name="table_ocr",
     version="0.2.1",