Add --txt-page-separator argument (closes #10)

tahweel/cli.py

@@ -56,5 +56,9 @@ def process_file(args: TahweelArgumentParser, processor: GoogleDriveOcrProcessor
   content = list(map(lambda text: text.replace('\ufeff', ''), content))
   content = list(map(str.strip, content))
 
-  TxtWriter(file_manager.txt_file_path(args.tahweel_type, args.dir_output_type, args.file_or_dir_path)).write(content)
+  TxtWriter(file_manager.txt_file_path(args.tahweel_type, args.dir_output_type, args.file_or_dir_path)).write(
+    content,
+    args.txt_page_separator,
+  )
+
   DocxWriter(file_manager.docx_file_path(args.tahweel_type, args.dir_output_type, args.file_or_dir_path)).write(content)

tahweel/tahweel_argument_parser.py

@@ -9,7 +9,6 @@
 
 class TahweelArgumentParser(Tap):
   file_or_dir_path: Path
-  """Path to the file or directory to be processed."""
 
   service_account_credentials: Path
   """Path to the service account credentials JSON file."""
@@ -22,6 +21,9 @@ class TahweelArgumentParser(Tap):
 
   dir_output_type: DirOutputType = DirOutputType.TREE_TO_TREE
 
+  txt_page_separator: str = 'PAGE_SEPARATOR'
+  """Separator to use between pages in the output TXT file."""
+
   skip_output_check: bool = False
   """Use this flag in development only to skip the output check."""
 

tahweel/writers/txt_writer.py

@@ -1,14 +1,11 @@
 from pathlib import Path
 
 
-PAGE_SEPARATOR = 'PAGE_SEPARATOR'
-
-
 class TxtWriter:
   def __init__(self, file_path: Path):
     self.file_path = file_path
 
     self.file_path.parent.mkdir(parents=True, exist_ok=True)
 
-  def write(self, texts: list[str]):
-    self.file_path.write_text(f'\n{PAGE_SEPARATOR}\n'.join(texts))
+  def write(self, texts: list[str], page_separator: str):
+    self.file_path.write_text(f'\n{page_separator}\n'.join(texts))