From 8c88fc594d7127cc78a68fba8108c812fb9ab8f2 Mon Sep 17 00:00:00 2001
From: Matthias Bisping <matthias.bisping@iqser.com>
Date: Sat, 5 Feb 2022 14:42:00 +0100
Subject: [PATCH] renaming; readme

---
 README.md           | 26 ++++++++++++++++++++++++++
 scripts/annotate.py |  8 ++++----
 2 files changed, 30 insertions(+), 4 deletions(-)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..38c9bca
--- /dev/null
+++ b/README.md
@@ -0,0 +1,26 @@
+# Table Parsing
+
+This repository implements computer vision based approaches for detecting and parsing visual features such as tables or previous redactions.
+
+## Installation
+
+```bash
+git clone ssh://git@git.iqser.com:2222/rr/table_parsing.git
+cd table_parsing
+
+python3 -m venv env
+source env/bin/activate
+
+pip install -e .
+pip install -r requirements.txt
+```
+
+## Usage
+
+```bash
+# Parse tables on second page of a PDF
+python scripts/annotate.py <path to pdf> 1 --type table
+
+# Detect redactions (black filled rectangles) on first page of a PDF
+python scripts/annotate.py <path to pdf> 0 --type redaction
+```
diff --git a/scripts/annotate.py b/scripts/annotate.py
index 68e4dd2..1f14019 100644
--- a/scripts/annotate.py
+++ b/scripts/annotate.py
@@ -9,7 +9,7 @@ def parse_args():
     parser = argparse.ArgumentParser()
     parser.add_argument("pdf_path")
     parser.add_argument("page_index", type=int)
-    parser.add_argument("--object", choices=["table", "box", "layout"], default="table")
+    parser.add_argument("--type", choices=["table", "redaction", "layout"], default="table")
 
     args = parser.parse_args()
 
@@ -18,10 +18,10 @@ def parse_args():
 
 if __name__ == "__main__":
     args = parse_args()
-    if args.object == "table":
+    if args.type == "table":
         annotate_tables_in_pdf(args.pdf_path, page_index=args.page_index)
-    elif args.object == "box":
+    elif args.type == "redaction":
         annotate_boxes_in_pdf(args.pdf_path, page_index=args.page_index)
-    elif args.object == "layout":
+    elif args.type == "layout":
         annotate_layout_in_pdf(args.pdf_path, page_index=args.page_index)