initial version

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+from impresso_pipelines.solrnormalization import SolrNormalizationPipeline
+
+pipeline = SolrNormalizationPipeline()
+
+LANGUAGES = ["Auto-detect", "de", "fr", "el", "ru"]
+
+def normalize(text, lang_choice):
+    lang = None if lang_choice == "Auto-detect" else lang_choice
+    result = pipeline(text, lang=lang, diagnostics=True)
+    return f"Language: {result['language']}\n\nTokens:\n{result['tokens']}\n\nDetected stopwords:\n{result['stopwords_detected']}"
+
+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 using Lucene analyzers. Language auto-detected if not selected."
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+impresso_pipelines[solrnormalization]
+gradio
+jpype1