Move `main` to __init__ for extract_tables

Since this function is the meat and potatoes, it's nice to be able to
import it as typical, which you can't really do if it only resides in
__main__.py.

Also, __main__.py doesn't need `if __name__ == "__main__"`. The whole
point of __main__.py is that it only gets run when that condition is true.

pdf_table_extraction_and_ocr.org

@@ -849,9 +849,32 @@ if __name__ == "__main__":
 #+NAME: extract_tables/__init__.py
 #+HEADER: :tangle table_ocr/extract_tables/__init__.py
 #+BEGIN_SRC python
+import os
 import cv2
 
 <<detect-tables>>
+
+def main(files):
+    results = []
+    for f in files:
+        directory, filename = os.path.split(f)
+        image = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
+        tables = find_tables(image)
+        files = []
+        filename_sans_extension = os.path.splitext(filename)[0]
+        if tables:
+            os.makedirs(os.path.join(directory, filename_sans_extension), exist_ok=True)
+        for i, table in enumerate(tables):
+            table_filename = "table-{:03d}.png".format(i)
+            table_filepath = os.path.join(
+                directory, filename_sans_extension, table_filename
+            )
+            files.append(table_filepath)
+            cv2.imwrite(table_filepath, table)
+        if tables:
+            results.append((f, files))
+    # Results is [[<input image>, [<images of detected tables>]]]
+    return results
 #+END_SRC
 
 **** table_ocr/extract_tables/__main__.py
@@ -876,43 +899,15 @@ For each image path given as an agument, outputs:
 #+NAME: extract_tables/__main__.py
 #+BEGIN_SRC python :tangle table_ocr/extract_tables/__main__.py :results none
 import argparse
-import os
 
-import cv2
+from table_ocr.extract_tables import main
-
-from table_ocr.extract_tables import find_tables
 
 parser = argparse.ArgumentParser()
 parser.add_argument("files", nargs="+")
-
+args = parser.parse_args()
-
+files = args.files
-def main(files):
+results = main(files)
-    results = []
+for image, tables in results:
-    for f in files:
-        directory, filename = os.path.split(f)
-        image = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
-        tables = find_tables(image)
-        files = []
-        filename_sans_extension = os.path.splitext(filename)[0]
-        if tables:
-            os.makedirs(os.path.join(directory, filename_sans_extension), exist_ok=True)
-        for i, table in enumerate(tables):
-            table_filename = "table-{:03d}.png".format(i)
-            table_filepath = os.path.join(
-                directory, filename_sans_extension, table_filename
-            )
-            files.append(table_filepath)
-            cv2.imwrite(table_filepath, table)
-        if tables:
-            results.append((f, files))
-    # Results is [[<input image>, [<images of detected tables>]]]
-    return results
-
-if __name__ == "__main__":
-    args = parser.parse_args()
-    files = args.files
-    results = main(files)
-    for image, tables in results:
     print("\n".join(tables))
 #+END_SRC
 

table_ocr/extract_tables/__init__.py

@@ -1,3 +1,4 @@
+import os
 import cv2
 
 def find_tables(image):
@@ -47,3 +48,25 @@ def find_tables(image):
     # Leaving that step as a future TODO if it is ever necessary.
     images = [image[y:y+h, x:x+w] for x, y, w, h in bounding_rects]
     return images
+
+def main(files):
+    results = []
+    for f in files:
+        directory, filename = os.path.split(f)
+        image = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
+        tables = find_tables(image)
+        files = []
+        filename_sans_extension = os.path.splitext(filename)[0]
+        if tables:
+            os.makedirs(os.path.join(directory, filename_sans_extension), exist_ok=True)
+        for i, table in enumerate(tables):
+            table_filename = "table-{:03d}.png".format(i)
+            table_filepath = os.path.join(
+                directory, filename_sans_extension, table_filename
+            )
+            files.append(table_filepath)
+            cv2.imwrite(table_filepath, table)
+        if tables:
+            results.append((f, files))
+    # Results is [[<input image>, [<images of detected tables>]]]
+    return results

table_ocr/extract_tables/__main__.py

@@ -1,39 +1,11 @@
 import argparse
-import os
 
-import cv2
+from table_ocr.extract_tables import main
-
-from table_ocr.extract_tables import find_tables
 
 parser = argparse.ArgumentParser()
 parser.add_argument("files", nargs="+")
-
+args = parser.parse_args()
-
+files = args.files
-def main(files):
+results = main(files)
-    results = []
+for image, tables in results:
-    for f in files:
-        directory, filename = os.path.split(f)
-        image = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
-        tables = find_tables(image)
-        files = []
-        filename_sans_extension = os.path.splitext(filename)[0]
-        if tables:
-            os.makedirs(os.path.join(directory, filename_sans_extension), exist_ok=True)
-        for i, table in enumerate(tables):
-            table_filename = "table-{:03d}.png".format(i)
-            table_filepath = os.path.join(
-                directory, filename_sans_extension, table_filename
-            )
-            files.append(table_filepath)
-            cv2.imwrite(table_filepath, table)
-        if tables:
-            results.append((f, files))
-    # Results is [[<input image>, [<images of detected tables>]]]
-    return results
-
-if __name__ == "__main__":
-    args = parser.parse_args()
-    files = args.files
-    results = main(files)
-    for image, tables in results:
     print("\n".join(tables))