Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,14 +1,14 @@
----
-title: EmDashCounter
-emoji: 🧛‍♂️
-colorFrom: purple
-colorTo: green
-sdk: gradio
-sdk_version: 6.14.0
-python_version: '3.13'
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: EmDashCounter
+emoji: 🧛‍♂️
+colorFrom: purple
+colorTo: green
+sdk: gradio
+sdk_version: 6.14.0
+python_version: '3.13'
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,198 +1,198 @@
-import gradio as gr
-import requests
-import zipfile
-import io
-import os
-from pypdf import PdfReader
-
-# Video URL of The Count
-VIDEO_URL = "https://images-ext-1.discordapp.net/external/PD3SdBHrOGxZtFU8zypW2PjGXabBG-OwY3rXB8XWG7Y/https/media.tenor.com/1nFPylOyXZIAAAPo/sesame-street-the-count.mp4"
-
-def get_count_response(count):
-    if count == 0:
-        return "Zero! Zero em dashes! Ah ah ah!"
-    elif count == 1:
-        return "One! One em dash! Ah ah ah!"
-    elif count <= 20:
-        counting = " ".join([f"{i}!" for i in range(1, count + 1)])
-        return f"{counting} {count} em dashes! Ah ah ah!"
-    else:
-        return f"One! Two! Three! ... {count}! {count} em dashes! Ah ah ah!"
-
-def count_em_dashes_in_bytes(content_bytes, filename):
-    count = 0
-    ext = os.path.splitext(filename.lower())[1]
-    
-    if ext == '.pdf':
-        try:
-            reader = PdfReader(io.BytesIO(content_bytes))
-            for page in reader.pages:
-                text = page.extract_text()
-                if text:
-                    count += text.count('—')
-        except Exception:
-            pass
-    else:
-        # Assume text-based for other common extensions
-        try:
-            content = content_bytes.decode('utf-8', errors='ignore')
-            count = content.count('—')
-        except Exception:
-            pass
-    return count
-
-def process_input(input_url, uploaded_file):
-    total_count = 0
-    processed = False
-
-    # Handle Uploaded File
-    if uploaded_file is not None:
-        with open(uploaded_file.name, "rb") as f:
-            file_bytes = f.read()
-            total_count += count_em_dashes_in_bytes(file_bytes, uploaded_file.name)
-        processed = True
-
-    # Handle URL
-    if input_url and input_url.strip():
-        url = input_url.strip()
-        
-        # Check if it's likely a GitHub Repo
-        if "github.com" in url and "/archive/" not in url and not any(url.lower().endswith(ext) for ext in ['.pdf', '.txt', '.md', '.py', '.js']):
-            # Normalize GitHub URL
-            base_url = url.rstrip('/')
-            if base_url.endswith('.git'):
-                base_url = base_url[:-4]
-            
-            branches = ['main', 'master']
-            r = None
-            for branch in branches:
-                test_url = f"{base_url}/archive/refs/heads/{branch}.zip"
-                try:
-                    response = requests.get(test_url, timeout=20)
-                    if response.status_code == 200:
-                        r = response
-                        break
-                except Exception:
-                    continue
-            
-            if r:
-                try:
-                    with zipfile.ZipFile(io.BytesIO(r.content)) as z:
-                        for filename in z.namelist():
-                            if filename.endswith('/'): continue
-                            text_extensions = {'.py', '.md', '.txt', '.js', '.ts', '.html', '.css', '.c', '.cpp', '.h', '.java', '.rs', '.go', '.json', '.yml', '.yaml'}
-                            if any(filename.lower().endswith(ext) for ext in text_extensions):
-                                with z.open(filename) as f:
-                                    total_count += count_em_dashes_in_bytes(f.read(), filename)
-                    processed = True
-                except Exception:
-                    pass
-        else:
-            # Handle as single file URL
-            try:
-                response = requests.get(url, timeout=20)
-                if response.status_code == 200:
-                    filename = url.split('/')[-1] or "file.txt"
-                    total_count += count_em_dashes_in_bytes(response.content, filename)
-                    processed = True
-            except Exception:
-                pass
-
-    if not processed:
-        return "I could not find anything to count! Provide a valid URL or upload a file! Ah ah ah!", gr.update(visible=False)
-
-    return get_count_response(total_count), gr.update(visible=True)
-
-# Define custom CSS for a Sesame Street / The Count theme
-custom_css = """
-body, .gradio-container { background-color: #000000 !important; color: #e0e0e0 !important; font-family: 'Georgia', serif !important; }
-.gr-box { background-color: #1a0633 !important; border: 2px solid #4b0082 !important; }
-#large-input textarea, #large-input input { 
-    background-color: #2b0b4d !important; 
-    color: #ffffff !important; 
-    font-size: 1.5rem !important; 
-    border: 2px solid #9932cc !important;
-}
-#large-output textarea, #large-output input { 
-    background-color: #000000 !important; 
-    color: #32cd32 !important; 
-    font-size: 1.8rem !important; 
-    font-weight: bold !important; 
-    border: 3px solid #32cd32 !important;
-    text-shadow: 2px 2px #1a0633;
-}
-#large-button { 
-    background-color: #4b0082 !important; 
-    color: #32cd32 !important; 
-    font-size: 1.6rem !important; 
-    font-weight: bold !important; 
-    border: 4px solid #32cd32 !important; 
-    height: 80px !important;
-    box-shadow: 0 0 10px #4b0082;
-    transition: all 0.3s ease;
-    cursor: pointer;
-}
-#large-button:hover {
-    background-color: #9932cc !important;
-    color: #ffffff !important;
-    box-shadow: 0 0 20px #32cd32;
-    transform: scale(1.02);
-}
-.gr-form label span { 
-    font-size: 1.4rem !important; 
-    color: #9932cc !important; 
-    font-weight: bold !important;
-    text-transform: uppercase;
-    letter-spacing: 2px;
-}
-h1 { color: #9932cc !important; text-shadow: 2px 2px #000000 !important; font-size: 3rem !important; text-align: center !important; }
-h3 { color: #e0e0e0 !important; text-align: center !important; margin-bottom: 2rem !important; }
-.file-upload { background-color: #2b0b4d !important; border: 2px dashed #9932cc !important; }
-"""
-
-with gr.Blocks(title="The Count's Em Dash Counter", css=custom_css) as demo:
-    gr.Markdown("# 🧛‍♂️ The Count's Em Dash Counter")
-    gr.Markdown("### Provide a GitHub repo, a file URL, or upload documents to count em dashes (—)! Ah ah ah!")
-    
-    with gr.Row():
-        with gr.Column(scale=4):
-            repo_url = gr.Textbox(
-                label="GitHub or File URL", 
-                placeholder="https://github.com/... OR https://example.com/file.pdf",
-                lines=1,
-                elem_id="large-input"
-            )
-            
-            file_upload = gr.File(
-                label="Upload Documents (PDF, TXT, MD...)",
-                file_types=[".pdf", ".txt", ".md", ".py", ".js", ".ts", ".html", ".css", ".json"],
-                elem_classes="file-upload"
-            )
-            
-            count_btn = gr.Button("Count them! Ah ah ah!", variant="primary", elem_id="large-button")
-            result_text = gr.Textbox(
-                label="The Count Says:", 
-                interactive=False, 
-                elem_id="large-output",
-                lines=3
-            )
-            
-        with gr.Column(scale=5):
-            video = gr.Video(
-                value=VIDEO_URL,
-                label="The Count",
-                autoplay=True,
-                loop=True,
-                show_label=False,
-                interactive=False,
-                visible=False
-            )
-
-    count_btn.click(
-        fn=process_input,
-        inputs=[repo_url, file_upload],
-        outputs=[result_text, video]
-    )
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+import requests
+import zipfile
+import io
+import os
+from pypdf import PdfReader
+
+# Video URL of The Count
+VIDEO_URL = "https://images-ext-1.discordapp.net/external/PD3SdBHrOGxZtFU8zypW2PjGXabBG-OwY3rXB8XWG7Y/https/media.tenor.com/1nFPylOyXZIAAAPo/sesame-street-the-count.mp4"
+
+def get_count_response(count):
+    if count == 0:
+        return "Zero! Zero em dashes! Ah ah ah!"
+    elif count == 1:
+        return "One! One em dash! Ah ah ah!"
+    elif count <= 20:
+        counting = " ".join([f"{i}!" for i in range(1, count + 1)])
+        return f"{counting} {count} em dashes! Ah ah ah!"
+    else:
+        return f"One! Two! Three! ... {count}! {count} em dashes! Ah ah ah!"
+
+def count_em_dashes_in_bytes(content_bytes, filename):
+    count = 0
+    ext = os.path.splitext(filename.lower())[1]
+    
+    if ext == '.pdf':
+        try:
+            reader = PdfReader(io.BytesIO(content_bytes))
+            for page in reader.pages:
+                text = page.extract_text()
+                if text:
+                    count += text.count('—')
+        except Exception:
+            pass
+    else:
+        # Assume text-based for other common extensions
+        try:
+            content = content_bytes.decode('utf-8', errors='ignore')
+            count = content.count('—')
+        except Exception:
+            pass
+    return count
+
+def process_input(input_url, uploaded_file):
+    total_count = 0
+    processed = False
+
+    # Handle Uploaded File
+    if uploaded_file is not None:
+        with open(uploaded_file.name, "rb") as f:
+            file_bytes = f.read()
+            total_count += count_em_dashes_in_bytes(file_bytes, uploaded_file.name)
+        processed = True
+
+    # Handle URL
+    if input_url and input_url.strip():
+        url = input_url.strip()
+        
+        # Check if it's likely a GitHub Repo
+        if "github.com" in url and "/archive/" not in url and not any(url.lower().endswith(ext) for ext in ['.pdf', '.txt', '.md', '.py', '.js']):
+            # Normalize GitHub URL
+            base_url = url.rstrip('/')
+            if base_url.endswith('.git'):
+                base_url = base_url[:-4]
+            
+            branches = ['main', 'master']
+            r = None
+            for branch in branches:
+                test_url = f"{base_url}/archive/refs/heads/{branch}.zip"
+                try:
+                    response = requests.get(test_url, timeout=20)
+                    if response.status_code == 200:
+                        r = response
+                        break
+                except Exception:
+                    continue
+            
+            if r:
+                try:
+                    with zipfile.ZipFile(io.BytesIO(r.content)) as z:
+                        for filename in z.namelist():
+                            if filename.endswith('/'): continue
+                            text_extensions = {'.py', '.md', '.txt', '.js', '.ts', '.html', '.css', '.c', '.cpp', '.h', '.java', '.rs', '.go', '.json', '.yml', '.yaml'}
+                            if any(filename.lower().endswith(ext) for ext in text_extensions):
+                                with z.open(filename) as f:
+                                    total_count += count_em_dashes_in_bytes(f.read(), filename)
+                    processed = True
+                except Exception:
+                    pass
+        else:
+            # Handle as single file URL
+            try:
+                response = requests.get(url, timeout=20)
+                if response.status_code == 200:
+                    filename = url.split('/')[-1] or "file.txt"
+                    total_count += count_em_dashes_in_bytes(response.content, filename)
+                    processed = True
+            except Exception:
+                pass
+
+    if not processed:
+        return "I could not find anything to count! Provide a valid URL or upload a file! Ah ah ah!", gr.update(visible=False)
+
+    return get_count_response(total_count), gr.update(visible=True)
+
+# Define custom CSS for a Sesame Street / The Count theme
+custom_css = """
+body, .gradio-container { background-color: #000000 !important; color: #e0e0e0 !important; font-family: 'Georgia', serif !important; }
+.gr-box { background-color: #1a0633 !important; border: 2px solid #4b0082 !important; }
+#large-input textarea, #large-input input { 
+    background-color: #2b0b4d !important; 
+    color: #ffffff !important; 
+    font-size: 1.5rem !important; 
+    border: 2px solid #9932cc !important;
+}
+#large-output textarea, #large-output input { 
+    background-color: #000000 !important; 
+    color: #32cd32 !important; 
+    font-size: 1.8rem !important; 
+    font-weight: bold !important; 
+    border: 3px solid #32cd32 !important;
+    text-shadow: 2px 2px #1a0633;
+}
+#large-button { 
+    background-color: #4b0082 !important; 
+    color: #32cd32 !important; 
+    font-size: 1.6rem !important; 
+    font-weight: bold !important; 
+    border: 4px solid #32cd32 !important; 
+    height: 80px !important;
+    box-shadow: 0 0 10px #4b0082;
+    transition: all 0.3s ease;
+    cursor: pointer;
+}
+#large-button:hover {
+    background-color: #9932cc !important;
+    color: #ffffff !important;
+    box-shadow: 0 0 20px #32cd32;
+    transform: scale(1.02);
+}
+.gr-form label span { 
+    font-size: 1.4rem !important; 
+    color: #9932cc !important; 
+    font-weight: bold !important;
+    text-transform: uppercase;
+    letter-spacing: 2px;
+}
+h1 { color: #9932cc !important; text-shadow: 2px 2px #000000 !important; font-size: 3rem !important; text-align: center !important; }
+h3 { color: #e0e0e0 !important; text-align: center !important; margin-bottom: 2rem !important; }
+.file-upload { background-color: #2b0b4d !important; border: 2px dashed #9932cc !important; }
+"""
+
+with gr.Blocks(title="The Count's Em Dash Counter") as demo:
+    gr.Markdown("# 🧛‍♂️ The Count's Em Dash Counter")
+    gr.Markdown("### Provide a GitHub repo, a file URL, or upload documents to count em dashes (—)! Ah ah ah!")
+    
+    with gr.Row():
+        with gr.Column(scale=4):
+            repo_url = gr.Textbox(
+                label="GitHub or File URL", 
+                placeholder="https://github.com/... OR https://example.com/file.pdf",
+                lines=1,
+                elem_id="large-input"
+            )
+            
+            file_upload = gr.File(
+                label="Upload Documents (PDF, TXT, MD...)",
+                file_types=[".pdf", ".txt", ".md", ".py", ".js", ".ts", ".html", ".css", ".json"],
+                elem_classes="file-upload"
+            )
+            
+            count_btn = gr.Button("Count them! Ah ah ah!", variant="primary", elem_id="large-button")
+            result_text = gr.Textbox(
+                label="The Count Says:", 
+                interactive=False, 
+                elem_id="large-output",
+                lines=3
+            )
+            
+        with gr.Column(scale=5):
+            video = gr.Video(
+                value=VIDEO_URL,
+                label="The Count",
+                autoplay=True,
+                loop=True,
+                show_label=False,
+                interactive=False,
+                visible=False
+            )
+
+    count_btn.click(
+        fn=process_input,
+        inputs=[repo_url, file_upload],
+        outputs=[result_text, video]
+    )
+
+if __name__ == "__main__":
+    demo.launch(css=custom_css, ssr_mode=False)

requirements.txt

@@ -1,3 +1,3 @@
-gradio==6.14.0
-requests
-pypdf
+gradio==6.14.0
+requests
+pypdf