From 2499fb4e1910d31ff12c24110f161b20641b8835 Mon Sep 17 00:00:00 2001
From: Raphael Stoeckli <github@rabanti.ch>
Date: Wed, 5 Oct 2022 21:57:18 +0200
Subject: Add sanitizer for captions in Textual inversion

---
 modules/textual_inversion/preprocess.py | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'modules/textual_inversion')

diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py
index f545a993..4f3df4bd 100644
--- a/modules/textual_inversion/preprocess.py
+++ b/modules/textual_inversion/preprocess.py
@@ -1,5 +1,8 @@
+from cmath import log
 import os
 from PIL import Image, ImageOps
+import platform
+import sys
 import tqdm
 
 from modules import shared, images
@@ -25,6 +28,7 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     def save_pic_with_caption(image, index):
         if process_caption:
             caption = "-" + shared.interrogator.generate_caption(image)
+            caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
         else:
             caption = filename
             caption = os.path.splitext(caption)[0]
@@ -75,3 +79,27 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
 
     if process_caption:
         shared.interrogator.send_blip_to_ram()
+
+def sanitize_caption(base_path, original_caption, suffix):
+    operating_system = platform.system().lower()
+    if (operating_system == "windows"):
+        invalid_path_characters = "\\/:*?\"<>|"
+        max_path_length = 259
+    else:
+        invalid_path_characters = "/" #linux/macos
+        max_path_length = 1023
+    caption = original_caption
+    for invalid_character in invalid_path_characters:
+        caption = caption.replace(invalid_character, "")
+    fixed_path_length = len(base_path) + len(suffix) 
+    if fixed_path_length + len(caption) <= max_path_length:
+        return caption
+    caption_tokens = caption.split()
+    new_caption = ""
+    for token in caption_tokens:
+        last_caption = new_caption
+        new_caption = new_caption + token + " "
+        if (len(new_caption) + fixed_path_length - 1  > max_path_length):
+            break
+    print(f"\nPath will be too long. Truncated caption: {original_caption}\nto: {last_caption}", file=sys.stderr)
+    return last_caption.strip()
-- 
cgit v1.2.1