clean up

Signed-off-by: peter szemraj <peterszemraj@gmail.com>

pdf2text.py

@@ -32,56 +32,24 @@ from spellchecker import SpellChecker
 from tqdm.auto import tqdm
 
 
-def fast_scandir(dirname):
-    # return all subfolders in a given filepath
-
-    subfolders = [f.path for f in os.scandir(dirname) if f.is_dir()]
-    for dirname in list(subfolders):
-        subfolders.extend(fast_scandir(dirname))
-    return subfolders  # list
-
-
-def create_folder(directory):
-    os.makedirs(directory, exist_ok=True)
-
 
 def simple_rename(filepath, target_ext=".txt"):
     _fp = Path(filepath)
     basename = _fp.stem
     return f"OCR_{basename}_{target_ext}"
 
+def rm_local_text_files(name_contains="RESULT_"):
+    """
+    rm_local_text_files - remove local text files
 
-def load_dir_files(directory, req_extension=".txt", return_type="list", verbose=False):
-    appr_files = []
-    # r=root, d=directories, f = files
-    for r, d, f in os.walk(directory):
-        for prefile in f:
-            if prefile.endswith(req_extension):
-                fullpath = os.path.join(r, prefile)
-                appr_files.append(fullpath)
-
-    appr_files = natsorted(appr_files)
-
-    if verbose:
-        print("A list of files in the {} directory are: \n".format(directory))
-        if len(appr_files) < 10:
-            pp.pprint(appr_files)
-        else:
-            pp.pprint(appr_files[:10])
-            print("\n and more. There are a total of {} files".format(len(appr_files)))
-
-    if return_type.lower() == "list":
-        return appr_files
-    else:
-        if verbose:
-            print("returning dictionary")
-
-        appr_file_dict = {}
-        for this_file in appr_files:
-            appr_file_dict[basename(this_file)] = this_file
-
-        return appr_file_dict
-
+    Args:
+        name_contains (str, optional): [description]. Defaults to "OCR_".
+    """
+    files = [f for f in Path.cwd().iterdir() if f.is_file() and f.suffix == '.txt' and name_contains in f.name]
+    logging.info(f"removing {len(files)} text files")
+    for f in files:
+        os.remove(f)
+    logging.info("done")
 
 def corr(
     s: str,