feat: add optional Rich-powered terminal UI for parsed content

any_parser/any_parser.py

@@ -6,6 +6,8 @@
 from collections.abc import Iterable
 from io import StringIO
 from pathlib import Path
+from .terminal_ui import TerminalParserUI
+
 
 from any_parser.async_parser import AsyncParser
 from any_parser.batch_parser import BatchParser
@@ -126,25 +128,32 @@ def parse(
         file_content=None,
         file_type=None,
         extract_args=None,
+        show_ui=False  # New optional parameter
     ):
-        """Extract full content from a file synchronously.
+        """Extract full content from a file synchronously with optional terminal UI.
 
         Args:
             file_path: Path to input file
             file_content: Base64 encoded file content
             file_type: File format extension
             extract_args: Additional extraction parameters
+            show_ui: Whether to display formatted output in terminal (default: False)
 
         Returns:
             tuple: (result, timing_info) or (error_message, "")
         """
-        return self._sync_parse.parse(
+        result, timing = self._sync_parse.parse(
             file_path=file_path,
             file_content=file_content,
             file_type=file_type,
-            extract_args=extract_args,
+            extract_args=extract_args
         )
-
+
+        if show_ui:
+            TerminalParserUI().display(result)
+
+        return result, timing
+
     @handle_file_processing
     def parse_pro(
         self,

any_parser/terminal_ui.py

@@ -0,0 +1,66 @@
+from rich.console import Console
+from rich.panel import Panel
+from rich.markdown import Markdown
+import re
+
+class TerminalParserUI:
+    def __init__(self):
+        self.console = Console()
+
+    def clean_text(self, text):
+        """Clean and normalize the parsed text"""
+        if isinstance(text, list):
+            text = "\n".join(text)
+        text = re.sub(r'\n{3,}', '\n\n', text)
+        return text.strip()
+
+    def detect_sections(self, text):
+        """Identify sections based on headers"""
+        sections = []
+        current_section = []
+        header_level = 0
+
+        for line in text.split('\n'):
+            if line.startswith('## '):
+                if current_section:
+                    sections.append(('\n'.join(current_section), header_level))
+                current_section = [line[3:]]
+                header_level = 2
+            elif line.startswith('# '):
+                if current_section:
+                    sections.append(('\n'.join(current_section), header_level))
+                current_section = [line[2:]]
+                header_level = 1
+            else:
+                current_section.append(line)
+
+        if current_section:
+            sections.append(('\n'.join(current_section), header_level))
+
+        return sections
+
+    def display(self, parsed_data):
+        """Display parsed content with rich formatting"""
+        clean_text = self.clean_text(parsed_data)
+        sections = self.detect_sections(clean_text)
+
+        if not sections:
+            self.console.print(Markdown(clean_text))
+            return
+
+        for content, level in sections:
+            if level == 1:
+                self.console.print(Panel.fit(
+                    Markdown(content),
+                    border_style="bright_blue",
+                    title_align="left"
+                ))
+            elif level == 2:
+                self.console.print(Panel.fit(
+                    Markdown(content),
+                    border_style="bright_green", 
+                    title_align="left"
+                ))
+            else:
+                self.console.print(Markdown(content))
+            self.console.print()

main.py

@@ -0,0 +1,23 @@
+import os
+from dotenv import load_dotenv
+from any_parser import AnyParser
+
+# Load environment variables
+load_dotenv(override=True)
+
+# Get the API key from the environment
+example_apikey = os.getenv("CAMBIO_API_KEY")
+
+# Create an AnyParser instance
+ap = AnyParser(api_key=example_apikey)
+
+# Extract content with beautiful terminal UI display
+markdown, total_time = ap.parse(
+    file_path="./data/qa.pdf",
+    show_ui=True  # This enables the formatted terminal display
+)
+
+# The results will automatically display in a nice format
+
+# Timing
+print("\nProcessing Time (seconds):", total_time)