from spire.doc import Document, FileFormat

def convert_odt_to_docx(input_path, output_path):
    doc = Document()
    doc.LoadFromFile(input_path)  # 加載ODT文件
    doc.SaveToFile(output_path, FileFormat.Docx)  # 保存為DOCX
    print(f"轉(zhuǎn)換成功：{output_path}")

# 使用示例
convert_odt_to_docx("report.odt", "report.docx")

import os
from spire.doc import Document, FileFormat

def batch_convert(input_folder, output_folder):
    # 創(chuàng)建輸出目錄（若不存在）
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    
    # 遍歷輸入目錄
    for filename in os.listdir(input_folder):
        if filename.lower().endswith(".odt"):
            input_path = os.path.join(input_folder, filename)
            output_path = os.path.join(output_folder, 
                                      os.path.splitext(filename)[0] + ".docx")
            try:
                doc = Document()
                doc.LoadFromFile(input_path)
                doc.SaveToFile(output_path, FileFormat.Docx)
                print(f"? {filename} 轉(zhuǎn)換完成")
            except Exception as e:
                print(f"? {filename} 轉(zhuǎn)換失敗: {str(e)}")

# 使用示例
batch_convert("input_odt", "output_docx")

import aspose.words as aw

def precise_conversion(input_path, output_path):
    doc = aw.Document(input_path)
    # 保留原始頁眉頁腳
    doc.first_section.headers_footers.link_to_previous(False)
    # 設(shè)置兼容性選項
    opts = aw.saving.DocxSaveOptions()
    opts.export_headers_footers_mode = aw.saving.ExportHeadersFootersMode.PER_SECTION
    doc.save(output_path, opts)

precise_conversion("complex.odt", "complex_precise.docx")

import pdfplumber

def extract_text(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        full_text = []
        for page in pdf.pages:
            text = page.extract_text()
            if text:  # 跳過空白頁
                full_text.append(text)
        return "\n".join(full_text)

# 使用示例
content = extract_text("annual_report.pdf")
print(content[:500])  # 打印前500字符

import camelot

def extract_tables(pdf_path):
    tables = camelot.read_pdf(pdf_path, flavor="lattice")
    for i, table in enumerate(tables):
        # 自動識別表頭
        header = table.parsing_report["header"]
        # 導(dǎo)出為Excel
        table.to_excel(f"table_{i}.xlsx")
        print(f"提取表格{i+1}: {len(table.df)}行×{len(table.df.columns)}列")

extract_tables("financial_report.pdf")

from pdf2image import convert_from_path
import pytesseract

def ocr_pdf(pdf_path, lang='chi_sim+eng'):
    images = convert_from_path(pdf_path, dpi=300)
    full_text = []
    for i, image in enumerate(images):
        text = pytesseract.image_to_string(image, lang=lang)
        full_text.append(text)
    return "\n".join(full_text)

# 使用示例（需安裝中文語言包）
chinese_content = ocr_pdf("scanned_contract.pdf")

def document_pipeline(odt_path):
    # 第一步：格式統(tǒng)一
    docx_path = odt_path.replace(".odt", ".docx")
    convert_odt_to_docx(odt_path, docx_path)
    
    # 第二步：生成PDF（使用ReportLab確保格式可控）
    from reportlab.lib.pagesizes import letter
    from reportlab.pdfgen import canvas
    doc = Document(docx_path)  # 重新加載DOCX（此處簡化，實際需解析DOCX內(nèi)容）
    pdf_path = odt_path.replace(".odt", ".pdf")
    c = canvas.Canvas(pdf_path, pagesize=letter)
    # 實際項目中需實現(xiàn)DOCX內(nèi)容到PDF的映射邏輯
    c.drawString(100, 750, "Document Conversion Pipeline")
    c.save()
    
    # 第三步：結(jié)構(gòu)化提取
    if is_text_pdf(pdf_path):  # 判斷PDF類型
        content = extract_text(pdf_path)
        return {"text": content, "tables": []}
    else:
        return {"text": ocr_pdf(pdf_path), "tables": []}

# 簡化示例，實際需完善各環(huán)節(jié)邏輯

from concurrent.futures import ProcessPoolExecutor

def parallel_conversion(input_paths, output_dir, workers=4):
    def process_file(input_path):
        output_path = os.path.join(output_dir, 
                                  os.path.basename(input_path).replace(".odt", ".docx"))
        convert_odt_to_docx(input_path, output_path)
        return output_path
    
    with ProcessPoolExecutor(max_workers=workers) as executor:
        results = list(executor.map(process_file, input_paths))
    return results

import hashlib

def safe_conversion(input_path, output_path):
    try:
        # 文件校驗
        if not input_path.lower().endswith(".odt"):
            raise ValueError("非ODT文件")
        
        # 計算輸入文件哈希
        with open(input_path, "rb") as f:
            input_hash = hashlib.md5(f.read()).hexdigest()
        
        # 執(zhí)行轉(zhuǎn)換
        convert_odt_to_docx(input_path, output_path)
        
        # 驗證輸出
        with open(output_path, "rb") as f:
            output_hash = hashlib.md5(f.read()).hexdigest()
        
        if not output_hash:
            raise RuntimeError("輸出文件為空")
            
        return {"status": "success", "input_hash": input_hash, "output_hash": output_hash}
    
    except Exception as e:
        return {"status": "error", "message": str(e)}