Upload folder using huggingface_hub

.idea/git_toolbox_prj.xml

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="GitToolBoxProjectSettings">
+    <option name="commitMessageIssueKeyValidationOverride">
+      <BoolValueOverride>
+        <option name="enabled" value="true" />
+      </BoolValueOverride>
+    </option>
+    <option name="commitMessageValidationEnabledOverride">
+      <BoolValueOverride>
+        <option name="enabled" value="true" />
+      </BoolValueOverride>
+    </option>
+  </component>
+</project>

.idea/workspace.xml

@@ -4,11 +4,7 @@
     <option name="autoReloadType" value="SELECTIVE" />
   </component>
   <component name="ChangeListManager">
-    <list default="true" id="02cef8cb-a1a8-48aa-8d50-1e20129f7d23" name="Changes" comment="">
-      <change afterPath="$PROJECT_DIR$/requirements.txt" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/.idea/unimoConvertPdfToExcel.iml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/unimoConvertPdfToExcel.iml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/main.py" beforeDir="false" afterPath="$PROJECT_DIR$/main.py" afterDir="false" />
-    </list>
+    <list default="true" id="02cef8cb-a1a8-48aa-8d50-1e20129f7d23" name="Changes" comment="Update project configuration and dependencies&#10;&#10;Updated the Python SDK configuration in the `.iml` file to use Python 3.12. Enabled app sharing in `main.py` by setting `share=True` in the Gradio app launch. Added a `requirements.txt` file to document and manage project dependencies." />
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
     <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
@@ -53,13 +49,27 @@
       <option name="number" value="Default" />
       <option name="presentableId" value="Default" />
       <updated>1741724175531</updated>
-      <workItem from="1741724176678" duration="741000" />
+      <workItem from="1741724176678" duration="1970000" />
     </task>
+    <task id="LOCAL-00001" summary="Update project configuration and dependencies&#10;&#10;Updated the Python SDK configuration in the `.iml` file to use Python 3.12. Enabled app sharing in `main.py` by setting `share=True` in the Gradio app launch. Added a `requirements.txt` file to document and manage project dependencies.">
+      <option name="closed" value="true" />
+      <created>1741726163321</created>
+      <option name="number" value="00001" />
+      <option name="presentableId" value="LOCAL-00001" />
+      <option name="project" value="LOCAL" />
+      <updated>1741726163321</updated>
+    </task>
+    <option name="localTasksCounter" value="2" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">
     <option name="version" value="3" />
   </component>
+  <component name="VcsManagerConfiguration">
+    <MESSAGE value="Update project settings, enable app sharing, and add dependencies&#10;&#10;Updated the Python SDK configuration in the project settings and enabled sharing in the application launch. Added a `requirements.txt` file with all necessary dependencies for the project. These changes improve environment consistency and facilitation of collaboration." />
+    <MESSAGE value="Update project configuration and dependencies&#10;&#10;Updated the Python SDK configuration in the `.iml` file to use Python 3.12. Enabled app sharing in `main.py` by setting `share=True` in the Gradio app launch. Added a `requirements.txt` file to document and manage project dependencies." />
+    <option name="LAST_COMMIT_MESSAGE" value="Update project configuration and dependencies&#10;&#10;Updated the Python SDK configuration in the `.iml` file to use Python 3.12. Enabled app sharing in `main.py` by setting `share=True` in the Gradio app launch. Added a `requirements.txt` file to document and manage project dependencies." />
+  </component>
   <component name="com.intellij.coverage.CoverageDataManagerImpl">
     <SUITE FILE_PATH="coverage/unimoConvertPdfToExcel$main.coverage" NAME="main Coverage Results" MODIFIED="1741724531337" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
   </component>

main.py

@@ -67,11 +67,16 @@ def process_pdf(pdf_file):
     # Ensure correct Brazilian formatting
     df_final["VLR.COMISSAO"] = df_final["VLR.COMISSAO"].str.replace(",", "X", regex=False).str.replace(".", ",", regex=False).str.replace("X", ".", regex=False)
 
+    # Update the NOME DO CLIENTE column with the required pattern
+    df_final["NOME DO CLIENTE"] = df_final.apply(
+        lambda row: f'CLIENTE: {row["NOME DO CLIENTE"]} COTA: {row["COTA"][:4]} GRUPO: {row["COTA"][5:]}', axis=1
+    )
+
     # Save the correctly formatted file
     output_excel_path = "final_filtered_output_brazilian.xlsx"
     df_final.to_excel(output_excel_path, index=False)
 
-    return output_excel_path
+    return df_final, output_excel_path
 
 # Gradio UI
 with gr.Blocks() as app:
@@ -82,9 +87,10 @@ with gr.Blocks() as app:
         pdf_input = gr.File(label="Upload your PDF file")
         process_button = gr.Button("Process PDF")
 
+    output_df = gr.Dataframe(label="Extracted Data Preview")
     output_file = gr.File(label="Download Excel File")
 
-    process_button.click(fn=process_pdf, inputs=[pdf_input], outputs=[output_file])
+    process_button.click(fn=process_pdf, inputs=[pdf_input], outputs=[output_df, output_file])
 
 # Launch the Gradio app
 app.launch(share=True)