app.py

import os

# Redirect cache to a writable path inside container
os.environ["XDG_CACHE_HOME"] = "/tmp/.cache"

import gradio as gr
from impresso_pipelines.solrnormalization import SolrNormalizationPipeline

pipeline = SolrNormalizationPipeline()

LANGUAGES = ["de", "fr", "es", "it", "pt", "nl", "en", "general"]

def normalize(text, lang_choice):
    try:
        lang = None if lang_choice == "Auto-detect" else lang_choice
        result = pipeline(text, lang=lang, diagnostics=True)
        
        # Format analyzer pipeline for better readability
        analyzer_steps = []
        if 'analyzer_pipeline' in result and result['analyzer_pipeline']:
            for i, step in enumerate(result['analyzer_pipeline'], 1):
                step_type = step.get('type', 'unknown')
                step_name = step.get('name', 'unnamed')
                analyzer_steps.append(f"  {i}. {step_type}: {step_name}")
        
        analyzer_display = "\n".join(analyzer_steps) if analyzer_steps else "  No analyzer steps found"
        
        return f"🌍 Language: {result['language']}\n\n🔤 Tokens:\n{result['tokens']}\n\n🚫 Detected stopwords:\n{result['stopwords_detected']}\n\n⚙️ Analyzer pipeline:\n{analyzer_display}"
    except Exception as e:
        print("❌ Pipeline error:", e)
        return f"Error: {e}"

demo = gr.Interface(
    fn=normalize,
    inputs=[
        gr.Textbox(label="Enter Text"),
        gr.Dropdown(choices=LANGUAGES, value="Auto-detect", label="Language")
    ],
    outputs=gr.Textbox(label="Normalized Output"),
    title="Solr Normalization Pipeline",
    description="Text normalization replicating Solr functionality.",
    allow_flagging="never"
)

demo.launch(server_name="0.0.0.0", server_port=7860)