Python에서 문서 내용을 검색하는 방법: 2가지 구현 접근법을 포함한 완전 가이드

# ❌ This approach WILL NOT work
import os
import sys

# Load coreclr first
from pythonnet import load
load("coreclr")

import clr

# Add folder with the library and dependencies to the system path
dll_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "dlls"))
sys.path.append(dll_dir)

# Add reference to the library
clr.AddReference("GroupDocs.Search")
# Import the Index class
from GroupDocs.Search import Index
index = Index("search_index")
index.Add("documents_folder")

// C# Wrapper Implementation (SearchWrapper.cs)
using GroupDocs.Search;
using System;
using System.IO;

public static class SearchWrapper
{
    public static void BuildIndex(string indexPath, string documentsPath)
    {
        using (var index = new Index(indexPath))
        {
            index.Add(documentsPath);
        }
    }
    
    public static string[] SearchDocuments(string indexPath, string query)
    {
        using (var index = new Index(indexPath))
        {
            var searchResult = index.Search(query);
            var results = new string[searchResult.Count];
            for (int i = 0; i < searchResult.Count; i++)
            {
                results[i] = searchResult[i].DocumentInfo.FileName;
            }
            return results;
        }
    }
}

# Python Usage (run_search_wrapper.py)
import os
import sys
import clr

# Add the dlls directory to the path
dll_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "dlls"))
sys.path.append(dll_dir)

# Load coreclr
from pythonnet import load
load("coreclr")

# Add reference to the wrapper
clr.AddReference("GroupDocs.Search.Wrapper")

# Import the wrapper class
from GroupDocs.Search.Wrapper import SearchWrapper

# Use the simplified API
SearchWrapper.BuildIndex("index", "files")
results = SearchWrapper.SearchDocuments("index", "invoice")
print(f"Found {len(results)} documents: {results}")

# Manual Type Resolution (run_search_manual.py)
import os
import sys
import clr

# Add the dlls directory to the path
dll_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), "dlls"))
sys.path.append(dll_dir)

# Load coreclr
from pythonnet import load
load("coreclr")

# Add reference to the wrapper (for dependency resolution)
clr.AddReference("GroupDocs.Search.Wrapper")

# Now add reference to the main library
clr.AddReference("GroupDocs.Search")

# Import System for reflection
import System
from System import Type, Activator, Array

# Get the Index type using reflection
index_type = Type.GetType("GroupDocs.Search.Index, GroupDocs.Search")

# Create index instance
index_path = "index"
index_instance = Activator.CreateInstance(index_type, index_path)

# Get the Add method
add_method = index_type.GetMethod("Add", [System.String])
add_method.Invoke(index_instance, ["files"])

# Get the Search method
search_method = index_type.GetMethod("Search", [System.String])
search_result = search_method.Invoke(index_instance, ["invoice"])

# Process search results
result_count = search_result.Count
print(f"Found {result_count} documents")

for i in range(result_count):
    document_info = search_result[i]
    file_name = document_info.DocumentInfo.FileName
    print(f"Document: {file_name}")

# Advanced search with custom options
def advanced_search_example():
    # Get SearchOptions type
    search_options_type = Type.GetType("GroupDocs.Search.Options.SearchOptions, GroupDocs.Search")
    search_options = Activator.CreateInstance(search_options_type)
    
    # Configure search options
    fuzzy_search_type = Type.GetType("GroupDocs.Search.Options.FuzzySearch, GroupDocs.Search")
    fuzzy_search = Activator.CreateInstance(fuzzy_search_type)
    fuzzy_search.Enabled = True
    fuzzy_search.SimilarityLevel = 0.8
    
    # Set fuzzy search in options
    set_fuzzy_method = search_options_type.GetMethod("set_FuzzySearch")
    set_fuzzy_method.Invoke(search_options, [fuzzy_search])
    
    # Perform advanced search
    search_method = index_type.GetMethod("Search", [System.String, search_options_type])
    results = search_method.Invoke(index_instance, ["confidential", search_options])
    
    return results

# Create Python 3.11 virtual environment
py -3.11 -m venv venv311

# Activate virtual environment (Windows)
venv311\Scripts\activate

# Verify Python version
python --version

# Upgrade pip and essential tools
python -m ensurepip --upgrade
python -m pip install --upgrade pip setuptools wheel

# Install pythonnet 3.0.5
python -m pip install pythonnet==3.0.5

# Install project requirements
pip install -r requirements.txt

# Navigate to wrapper directory
cd wrapper

# Build and publish the wrapper
dotnet publish -c Release -r win-x64 --self-contained false -o ./../dlls

# Return to root directory
cd ..

# Activate virtual environment (if not already active)
.venv\Scripts\activate

# Run wrapper-based approach
python run_search_wrapper.py

# Run manual type resolution approach
python run_search_manual.py