Update app.py

app.py

@@ -1,129 +1,129 @@
-import gradio as gr
-import re
-import cv2
-import pytesseract
-import numpy as np
-from pytesseract import Output
-from PIL import Image
-
-# Define keywords for highlighting
-KEYWORDS = ["fatal", "unreachable", "ssh", "publickey", "psrp", "5985", "python", "sudo", "8081", 
-            "umask", "storage", "ssl/tls", "powershell", "authenticate"]
-
-ERROR_TYPES = {
-    "ssh": "PORT ISSUE",
-    "publickey": "KEYS ISSUE",
-    "psrp": "PORT 5985 ISSUE",
-    "5985": "PORT 5985 ISSUE",
-    "python": "PYTHON ERROR",
-    "sudo": "SUDO ISSUE",
-    "8081": "PORT 8081 ISSUE",
-    "umask": "UMASK77 ISSUE",
-    "storage": "STORAGE ISSUE",
-    "ssl/tls": "SSL/TLS ISSUE",
-    "powershell": "POWERSHELL ISSUE",
-    "authenticate": "AUTHENTICATION ISSUE"
-}
-
-ERROR_DOCS = {
-    "KEYS ISSUE": "https://github.com/suryaT1/Documents/blob/main/keys-issue.md",
-    "PORT ISSUE": "https://github.com/suryaT1/Documents/blob/main/port-issue.md",
-    "PORT 5985 ISSUE": "https://github.com/suryaT1/Documents/blob/main/port5985-doc.md",
-    "PYTHON ERROR": "https://github.com/suryaT1/Documents/blob/main/python-issue.md",
-    "SUDO ISSUE": "https://github.com/suryaT1/Documents/blob/main/sudoers-issue.md",
-    "PORT 8081 ISSUE": "https://github.com/suryaT1/Documents/blob/main/port8081-issue.md",
-    "UMASK77 ISSUE": "https://github.com/suryaT1/Documents/blob/main/umask-issue.md",
-    "STORAGE ISSUE": "https://github.com/suryaT1/Documents/blob/main/storage-issue.md",
-    "SSL/TLS ISSUE": "https://github.com/suryaT1/Documents/blob/main/ssl_tls-issue.md",
-    "POWERSHELL ISSUE": "https://github.com/suryaT1/Documents/blob/main/powershell-issue.md",
-    "AUTHENTICATION ISSUE": "https://github.com/authentication-doc",
-}
-
-DEVICE_NAME_PATTERN = r'\[([A-Za-z0-9@.\-]+)(?:\s*->\s*[A-Za-z0-9@.\-]+)?\]'
-
-# Function to highlight keywords in text
-def highlight_keywords(text):
-    for keyword in KEYWORDS:
-        text = re.sub(rf'\b{keyword}\b', f'<b style="color:red;">{keyword}</b>', text, flags=re.IGNORECASE)
-    return text
-
-# Extract text from an image
-def extract_text_from_image(image_path):
-    image = Image.open(image_path)
-    image_cv = np.array(image)
-    image_cv = cv2.cvtColor(image_cv, cv2.COLOR_RGB2BGR)
-    extracted_text = pytesseract.image_to_string(image_cv)
-    return extracted_text.strip()
-
-# Label and detect error types in text
-def analyze_text(text):
-    labeled_entities = []
-    detected_errors = set()
-    device_name = "Unknown"
-
-    # Check for keywords
-    for keyword in KEYWORDS:
-        if keyword in text.lower():
-            labeled_entities.append((keyword, "KEYWORD"))
-
-    # Detect error types
-    for key, error_type in ERROR_TYPES.items():
-        if key in text.lower():
-            detected_errors.add(error_type)
-
-    # Extract device name
-    device_match = re.search(DEVICE_NAME_PATTERN, text)
-    if device_match:
-        device_name = device_match.group(1)
-        labeled_entities.append((device_name, "DEVICE"))
-
-    return labeled_entities, detected_errors, device_name
-
-# Process the input (image or text)
-def process_input(image, text):
-    extracted_text = ""
-
-    if image is not None:
-        extracted_text = extract_text_from_image(image)
-    elif text.strip():
-        extracted_text = text.strip()
-
-    if not extracted_text:
-        return "No text detected!", "", ""
-
-    labeled_entities, detected_errors, device_name = analyze_text(extracted_text)
-
-    # Highlighted text output
-    highlighted_text = highlight_keywords(extracted_text)
-
-    # Issue detection and documentation links
-    logs_info = [f"Device: {device_name}, Issue: {error}" for error in detected_errors]
-    docs_links = [f'<a href="{ERROR_DOCS[error]}" target="_blank">{error} Documentation</a>' for error in detected_errors if error in ERROR_DOCS]
-
-    logs_html = "<br>".join(logs_info)
-    docs_html = "<br>".join(docs_links)
-
-    return highlighted_text, logs_html, docs_html
-
-# Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Ansible Log Annotator")
-    gr.Markdown("Upload a log image or enter log text below to extract and analyze errors.")
-
-    with gr.Row():
-        image_input = gr.File(type="filepath", label="Upload Log Image (PNG, JPG)")
-        text_input = gr.Textbox(label="Or Paste Log Text", lines=5)
-
-    with gr.Row():
-        analyze_button = gr.Button("Analyze")
-
-    with gr.Row():
-        output_highlighted = gr.HTML(label="Highlighted Log")
-    with gr.Row():
-        output_logs = gr.HTML(label="Detected Issues")
-    with gr.Row():
-        output_docs = gr.HTML(label="Documentation Links")
-
-    analyze_button.click(process_input, inputs=[image_input, text_input], outputs=[output_highlighted, output_logs, output_docs])
-
-demo.launch()
+import gradio as gr
+import re
+import cv2
+import pytesseract
+import numpy as np
+from pytesseract import Output
+from PIL import Image
+
+# Define keywords for highlighting
+KEYWORDS = ["fatal", "unreachable", "ssh", "publickey", "psrp", "5985", "python", "sudo", "8081", 
+            "umask", "storage", "ssl/tls", "powershell", "authenticate"]
+
+ERROR_TYPES = {
+    "ssh": "PORT ISSUE",
+    "publickey": "KEYS ISSUE",
+    "psrp": "PORT 5985 ISSUE",
+    "5985": "PORT 5985 ISSUE",
+    "python": "PYTHON ERROR",
+    "sudo": "SUDO ISSUE",
+    "8081": "PORT 8081 ISSUE",
+    "umask": "UMASK77 ISSUE",
+    "storage": "STORAGE ISSUE",
+    "ssl/tls": "SSL/TLS ISSUE",
+    "powershell": "POWERSHELL ISSUE",
+    "authenticate": "AUTHENTICATION ISSUE"
+}
+
+ERROR_DOCS = {
+    "KEYS ISSUE": "https://github.com/suryaT1/Documents/blob/main/keys-issue.md",
+    "PORT ISSUE": "https://github.com/suryaT1/Documents/blob/main/port-issue.md",
+    "PORT 5985 ISSUE": "https://github.com/suryaT1/Documents/blob/main/port5985-doc.md",
+    "PYTHON ERROR": "https://github.com/suryaT1/Documents/blob/main/python-issue.md",
+    "SUDO ISSUE": "https://github.com/suryaT1/Documents/blob/main/sudoers-issue.md",
+    "PORT 8081 ISSUE": "https://github.com/suryaT1/Documents/blob/main/port8081-issue.md",
+    "UMASK77 ISSUE": "https://github.com/suryaT1/Documents/blob/main/umask-issue.md",
+    "STORAGE ISSUE": "https://github.com/suryaT1/Documents/blob/main/storage-issue.md",
+    "SSL/TLS ISSUE": "https://github.com/suryaT1/Documents/blob/main/ssl_tls-issue.md",
+    "POWERSHELL ISSUE": "https://github.com/suryaT1/Documents/blob/main/powershell-issue.md",
+    "AUTHENTICATION ISSUE": "https://github.com/authentication-doc",
+}
+
+DEVICE_NAME_PATTERN = r'\[([A-Za-z0-9@.\-]+)(?:\s*->\s*[A-Za-z0-9@.\-]+)?\]'
+
+# Function to highlight keywords in text
+def highlight_keywords(text):
+    for keyword in KEYWORDS:
+        text = re.sub(rf'\b{keyword}\b', f'<b style="color:red;">{keyword}</b>', text, flags=re.IGNORECASE)
+    return text
+
+# Extract text from an image
+def extract_text_from_image(image_path):
+    image = Image.open(image_path)
+    image_cv = np.array(image)
+    image_cv = cv2.cvtColor(image_cv, cv2.COLOR_RGB2BGR)
+    extracted_text = pytesseract.image_to_string(image_cv)
+    return extracted_text.strip()
+
+# Label and detect error types in text
+def analyze_text(text):
+    labeled_entities = []
+    detected_errors = set()
+    device_name = "Unknown"
+
+    # Check for keywords
+    for keyword in KEYWORDS:
+        if keyword in text.lower():
+            labeled_entities.append((keyword, "KEYWORD"))
+
+    # Detect error types
+    for key, error_type in ERROR_TYPES.items():
+        if key in text.lower():
+            detected_errors.add(error_type)
+
+    # Extract device name
+    device_match = re.search(DEVICE_NAME_PATTERN, text)
+    if device_match:
+        device_name = device_match.group(1)
+        labeled_entities.append((device_name, "DEVICE"))
+
+    return labeled_entities, detected_errors, device_name
+
+# Process the input (image or text)
+def process_input(image, text):
+    extracted_text = ""
+
+    if image is not None:
+        extracted_text = extract_text_from_image(image)
+    elif text.strip():
+        extracted_text = text.strip()
+
+    if not extracted_text:
+        return "No text detected!", "", ""
+
+    labeled_entities, detected_errors, device_name = analyze_text(extracted_text)
+
+    # Highlighted text output
+    highlighted_text = highlight_keywords(extracted_text)
+
+    # Issue detection and documentation links
+    logs_info = [f"Device: {device_name}, Issue: {error}" for error in detected_errors]
+    docs_links = [f'<a href="{ERROR_DOCS[error]}" target="_blank">{error} Documentation</a>' for error in detected_errors if error in ERROR_DOCS]
+
+    logs_html = "<br>".join(logs_info)
+    docs_html = "<br>".join(docs_links)
+
+    return highlighted_text, logs_html, docs_html
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Ansible Log Annotator")
+    gr.Markdown("Upload a log image or enter log text below to extract and analyze errors.")
+
+    with gr.Row():
+        image_input = gr.File(type="filepath", label="Upload Log Image (PNG, JPG)")
+        text_input = gr.Textbox(label="Or Paste Log Text", lines=5)
+
+    with gr.Row():
+        analyze_button = gr.Button("Analyze")
+
+    with gr.Row():
+        output_highlighted = gr.HTML(label="Highlighted Log")
+    with gr.Row():
+        output_logs = gr.HTML(label="Detected Issues")
+    with gr.Row():
+        output_docs = gr.HTML(label="Documentation Links")
+
+    analyze_button.click(process_input, inputs=[image_input, text_input], outputs=[output_highlighted, output_logs, output_docs])
+
+demo.launch()