[cli] Add ability to customize delimiters for CSV output (#423)

Author: Breakthrough

scenedetect.cfg

@@ -266,6 +266,14 @@
 # Display list of cut points generated from scene boundaries (yes/no).
 #display-cuts = yes
 
+# Separator to use between columns in output file. Must be single (escaped)
+# ASCII character.
+#col-separator = ,
+
+# Separator to use between rows in output file. Must be (escaped) ASCII
+# characters.
+#row-separator = \n
+
 # Format to use for list of cut points (frames, seconds, timecode).
 #cut-format = timecode
 

scenedetect/_cli/__init__.py

@@ -1064,14 +1064,17 @@ def list_scenes_command(
     scene_list_name_format = ctx.config.get_value("list-scenes", "filename", filename)
     list_scenes_args = {
         "cut_format": TimecodeFormat[ctx.config.get_value("list-scenes", "cut-format").upper()],
+        "col_separator": ctx.config.get_value("list-scenes", "col-separator"),
         "display_scenes": ctx.config.get_value("list-scenes", "display-scenes"),
         "display_cuts": ctx.config.get_value("list-scenes", "display-cuts"),
+        "row_separator": ctx.config.get_value("list-scenes", "row-separator"),
         "scene_list_output": not no_output_file,
         "scene_list_name_format": scene_list_name_format,
         "skip_cuts": skip_cuts or ctx.config.get_value("list-scenes", "skip-cuts"),
         "output_dir": scene_list_dir,
         "quiet": quiet or ctx.config.get_value("list-scenes", "quiet") or ctx.quiet_mode,
     }
+    # TODO(#423): Need to validate that col_separator is a 1-character string after decoding.
     ctx.add_command(cli_commands.list_scenes, list_scenes_args)
 
 

scenedetect/_cli/commands.py

@@ -76,6 +76,8 @@ def list_scenes(
     display_scenes: bool,
     display_cuts: bool,
     cut_format: str,
+    col_separator: str,
+    row_separator: str,
 ):
     """Handles the `list-scenes` command."""
     # Write scene list CSV to if required.
@@ -96,6 +98,8 @@ def list_scenes(
                 scene_list=scenes,
                 include_cut_list=not skip_cuts,
                 cut_list=cuts,
+                col_separator=col_separator.encode("utf-8").decode("unicode_escape"),
+                row_separator=row_separator.encode("utf-8").decode("unicode_escape"),
             )
     # Suppress output if requested.
     if quiet:

scenedetect/_cli/config.py

@@ -303,10 +303,12 @@ def format(self, timecode: FrameTimecode) -> str:
     },
     "list-scenes": {
         "cut-format": "timecode",
+        "col-separator": ",",
         "display-cuts": True,
         "display-scenes": True,
         "filename": "$VIDEO_NAME-Scenes.csv",
         "output": None,
+        "row-separator": "\n",
         "no-output-file": False,
         "quiet": False,
         "skip-cuts": False,

scenedetect/scene_manager.py

@@ -216,6 +216,8 @@ def write_scene_list(
     scene_list: SceneList,
     include_cut_list: bool = True,
     cut_list: Optional[CutList] = None,
+    col_separator: str = ",",
+    row_separator: str = "\n",
 ) -> None:
     """Writes the given list of scenes to an output file handle in CSV format.
 
@@ -227,8 +229,13 @@ def write_scene_list(
         cut_list: Optional list of FrameTimecode objects denoting the cut list (i.e. the frames
             in the video that need to be split to generate individual scenes). If not specified,
             the cut list is generated using the start times of each scene following the first one.
+        delimiter: Delimiter to use between values. Must be single character.
+        lineterminator: Line terminator to use between rows.
+
+    Raises:
+        TypeError: "delimiter" must be a 1-character string
     """
-    csv_writer = csv.writer(output_csv_file, lineterminator="\n")
+    csv_writer = csv.writer(output_csv_file, delimiter=col_separator, lineterminator=row_separator)
     # If required, output the cutting list as the first row (i.e. before the header row).
     if include_cut_list:
         csv_writer.writerow(

website/pages/changelog.md

@@ -588,3 +588,5 @@ Development
  - [bugfix] Fix `ContentDetector` crash when using callbacks [#416](https://github.com/Breakthrough/PySceneDetect/issues/416) [#420](https://github.com/Breakthrough/PySceneDetect/issues/420)
  - [general] Timecodes of the form `MM:SS[.nnn]` are now processed correctly [#443](https://github.com/Breakthrough/PySceneDetect/issues/443)
  - [api] The `save_to_csv` function now works correctly with paths from the `pathlib` module
+ - [api] Add `col_separator` and `row_separator` args to `write_scene_list` function in `scenedetect.scene_manager`
+ - [feature] Add ability to configure CSV separators for rows/columns in config file [#423](https://github.com/Breakthrough/PySceneDetect/issues/423)