From a8e97924120e5b2f6503d1cc6c0a6cc03d2f29d6 Mon Sep 17 00:00:00 2001
From: Folzo <folzo@hotmail.com>
Date: Sat, 11 Apr 2026 01:31:06 +0200
Subject: [PATCH] fix(effi-ocr): improve file search and normalize language
 codes

- Better file finding (startswith + contains)
- Normalize language codes (French->fra, English->eng, etc.)
- List all files in directory when searching
---
 effi-ocr-legacy/TOOL-OPENWEBUI.md | 43 +++++++++++++++++--------------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/effi-ocr-legacy/TOOL-OPENWEBUI.md b/effi-ocr-legacy/TOOL-OPENWEBUI.md
index bf95edc..4b68e93 100644
--- a/effi-ocr-legacy/TOOL-OPENWEBUI.md
+++ b/effi-ocr-legacy/TOOL-OPENWEBUI.md
@@ -24,6 +24,16 @@ class Tools:
         self.uploads_dir = "/app/backend/data/uploads"
         self.host_uploads_dir = "/home/effi/effi/data/uploads"
 
+    def _normalize_language(self, lang):
+        lang_map = {
+            "french": "fra", "francais": "fra", "fr": "fra",
+            "english": "eng", "eng": "eng",
+            "german": "deu", "de": "deu",
+            "spanish": "spa", "es": "spa",
+            "italian": "ita", "it": "ita"
+        }
+        return lang_map.get(lang.lower(), lang)
+
     def extract_text_from_image(self, image_path, language="fra"):
         try:
             file_path = self._find_file(image_path)
@@ -32,8 +42,8 @@ class Tools:
                 return "[ERROR] File not found: " + image_path + ". Use list_recent_files() to see available files."
             
             with open(file_path, 'rb') as f:
-                files = {'file': f}
-                data = {'lang': language, 'preprocess': 'true'}
+                files = {'file': (os.path.basename(file_path), f)}
+                data = {'lang': self._normalize_language(language), 'preprocess': 'true'}
                 
                 response = requests.post(
                     self.ocr_url + "/ocr",
@@ -66,7 +76,10 @@ class Tools:
 
     def list_recent_files(self, count=10):
         try:
-            files = glob.glob(os.path.join(self.uploads_dir, "*"))
+            files = []
+            
+            if os.path.exists(self.uploads_dir):
+                files = glob.glob(os.path.join(self.uploads_dir, "*"))
             
             if not files and os.path.exists(self.host_uploads_dir):
                 files = glob.glob(os.path.join(self.host_uploads_dir, "*"))
@@ -104,22 +117,14 @@ class Tools:
         if os.path.exists(path):
             return path
         
-        for directory in [self.uploads_dir, self.host_uploads_dir]:
-            if not os.path.exists(directory):
-                continue
-            
-            pattern = os.path.join(directory, filename + "*")
-            matches = glob.glob(pattern)
-            if matches:
-                return matches[0]
-            
-            pattern = os.path.join(directory, "*" + filename + "*")
-            matches = glob.glob(pattern)
-            if matches:
-                for m in matches:
-                    if filename in os.path.basename(m):
-                        return m
-                return matches[0]
+        search_dirs = [d for d in [self.uploads_dir, self.host_uploads_dir] if os.path.exists(d)]
+        
+        for directory in search_dirs:
+            all_files = glob.glob(os.path.join(directory, "*"))
+            for f in all_files:
+                basename = os.path.basename(f)
+                if basename.startswith(filename) or filename in basename:
+                    return f
         
         return None