Fix some typos (found by codespell)

Signed-off-by: Stefan Weil <[email protected]>

examples/catalogue_30s/catalog_30s.py

@@ -126,7 +126,7 @@ def save_image_w_lines(iproc_obj, imgfilebasename, orig_img_as_background):
 
     # cluster the detected *vertical* lines using find_clusters_1d_break_dist as simple clustering function
     # (break on distance MIN_COL_WIDTH/2)
-    # additionaly, remove all cluster sections that are considered empty
+    # additionally, remove all cluster sections that are considered empty
     # a cluster is considered empty when the number of text boxes in it is below 10% of the median number of text boxes
     # per cluster section
     vertical_clusters = iproc_obj.find_clusters(imgproc.DIRECTION_VERTICAL, find_clusters_1d_break_dist,

examples/catalogue_30s/catalog_30s_notebook.ipynb

@@ -705,7 +705,7 @@
     "\n",
     "# cluster the detected *vertical* lines using find_clusters_1d_break_dist as simple clustering function\n",
     "# (break on distance MIN_COL_WIDTH/2)\n",
-    "# additionaly, remove all cluster sections that are considered empty\n",
+    "# additionally, remove all cluster sections that are considered empty\n",
     "# a cluster is considered empty when the number of text boxes in it is below 10% of the median number of text boxes\n",
     "# per cluster section\n",
     "vertical_clusters = iproc_obj.find_clusters(imgproc.DIRECTION_VERTICAL, find_clusters_1d_break_dist,\n",

examples/schoollist_1/schoollist_1.py

@@ -171,7 +171,7 @@ def save_image_w_lines(iproc_obj, imgfilebasename, orig_img_as_background, file_
 
     # cluster the detected *horizontal* lines using find_clusters_1d_break_dist as simple clustering function
     # (break on distance MIN_ROW_HEIGHT/2)
-    # additionaly, remove all cluster sections that are considered empty
+    # additionally, remove all cluster sections that are considered empty
     # a cluster is considered empty when the number of text boxes in it is below 10% of the median number of text boxes
     # per cluster section
     hori_clusters = iproc_obj.find_clusters(imgproc.DIRECTION_HORIZONTAL, find_clusters_1d_break_dist,
@@ -306,7 +306,7 @@ def save_image_w_lines(iproc_obj, imgfilebasename, orig_img_as_background, file_
 
 # For sake of simplicity, we will just fit the text boxes into the grid, merge the texts in their cells (splitting text
 # boxes to separate lines if necessary) and output the result. Normally, you would do some more parsing here, e.g.
-# extracting the adress components from the second column.
+# extracting the address components from the second column.
 
 full_df = pd.DataFrame()
 print("fitting text boxes into page grids and generating final output...")

examples/schoollist_2/schoollist_2.py

@@ -322,7 +322,7 @@ def save_image_w_lines(iproc_obj, imgfilebasename, orig_img_as_background, file_
 
 # For sake of simplicity, we will just fit the text boxes into the grid, merge the texts in their cells (splitting text
 # boxes to separate lines if necessary) and output the result. Normally, you would do some more parsing here, e.g.
-# extracting the adress components from the second column.
+# extracting the address components from the second column.
 
 full_df = pd.DataFrame()
 print("fitting text boxes into page grids and generating final output...")

pdftabextract/common.py

@@ -246,7 +246,7 @@ def levenshtein(source, target):
 
 def fill_array_a_with_values_from_b(a, b, fill_indices):
     """
-    Fill array <a> with values from <b> taking values from indicies specified by <fill_indices>.
+    Fill array <a> with values from <b> taking values from indices specified by <fill_indices>.
     
     Example:
     fill_array_a_with_values_from_b(np.array(list('136')), np.array(list('abcdef')), [1, 3, 4])