feat: 添加文档转PDF转换功能
- 后端添加 PDF 转换服务，支持 Word(docx)、Excel(xlsx)、文本(txt)、Markdown(md) 格式转换为 PDF - 使用 reportlab 库，支持中文字体（simhei.ttf） - 添加 FastAPI 接口：POST /api/v1/pdf/convert 单文件转换，POST /api/v1/pdf/convert/batch 批量转换 - 前端添加 PdfConverter 页面，支持拖拽上传、转换进度显示、批量下载 - 转换流程：所有格式先转为 Markdown，再通过 Markdown 转 PDF，保证输出一致性 - DOCX 解析使用 zipfile 直接读取 XML，避免 python-docx 的兼容性问题的
This commit is contained in:
@@ -15,6 +15,7 @@ from app.api.endpoints import (
|
||||
health,
|
||||
instruction, # 智能指令
|
||||
conversation, # 对话历史
|
||||
pdf_converter, # PDF转换
|
||||
)
|
||||
|
||||
# 创建主路由
|
||||
@@ -33,3 +34,4 @@ api_router.include_router(visualization.router) # 可视化
|
||||
api_router.include_router(analysis_charts.router) # 分析图表
|
||||
api_router.include_router(instruction.router) # 智能指令
|
||||
api_router.include_router(conversation.router) # 对话历史
|
||||
api_router.include_router(pdf_converter.router) # PDF转换
|
||||
|
||||
208
backend/app/api/endpoints/pdf_converter.py
Normal file
208
backend/app/api/endpoints/pdf_converter.py
Normal file
@@ -0,0 +1,208 @@
|
||||
"""
|
||||
PDF 转换 API 接口
|
||||
|
||||
提供将 Word、Excel、Txt、Markdown 转换为 PDF 的功能
|
||||
"""
|
||||
import logging
|
||||
import uuid
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, UploadFile, File, Form, HTTPException
|
||||
from fastapi.responses import StreamingResponse
|
||||
|
||||
from app.services.pdf_converter_service import pdf_converter_service
|
||||
from app.services.file_service import file_service
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/pdf", tags=["PDF转换"])
|
||||
|
||||
# 临时存储转换后的 PDF（key: download_id, value: (pdf_content, original_filename)）
|
||||
_pdf_cache: dict = {}
|
||||
|
||||
|
||||
# ==================== 请求/响应模型 ====================
|
||||
|
||||
class ConvertResponse:
|
||||
"""转换响应"""
|
||||
def __init__(self, success: bool, message: str = "", filename: str = ""):
|
||||
self.success = success
|
||||
self.message = message
|
||||
self.filename = filename
|
||||
|
||||
|
||||
# ==================== 接口 ====================
|
||||
|
||||
@router.post("/convert")
|
||||
async def convert_to_pdf(
|
||||
file: UploadFile = File(...),
|
||||
):
|
||||
"""
|
||||
将上传的文件转换为 PDF
|
||||
|
||||
支持格式: docx, xlsx, txt, md
|
||||
|
||||
Args:
|
||||
file: 上传的文件
|
||||
|
||||
Returns:
|
||||
PDF 文件流
|
||||
"""
|
||||
try:
|
||||
# 检查文件格式
|
||||
filename = file.filename or "document"
|
||||
file_ext = filename.rsplit('.', 1)[-1].lower() if '.' in filename else ''
|
||||
|
||||
if file_ext not in pdf_converter_service.supported_formats:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"不支持的格式: {file_ext}，支持的格式: {', '.join(pdf_converter_service.supported_formats)}"
|
||||
)
|
||||
|
||||
# 读取文件内容
|
||||
content = await file.read()
|
||||
if not content:
|
||||
raise HTTPException(status_code=400, detail="文件内容为空")
|
||||
|
||||
logger.info(f"开始转换文件: {filename} ({file_ext})")
|
||||
|
||||
# 转换为 PDF
|
||||
pdf_content, error = await pdf_converter_service.convert_to_pdf(
|
||||
file_content=content,
|
||||
source_format=file_ext,
|
||||
filename=filename.rsplit('.', 1)[0] if '.' in filename else filename
|
||||
)
|
||||
|
||||
if error:
|
||||
raise HTTPException(status_code=500, detail=error)
|
||||
|
||||
# 直接返回 PDF 文件流
|
||||
return StreamingResponse(
|
||||
iter([pdf_content]),
|
||||
media_type="application/pdf",
|
||||
headers={
|
||||
"Content-Disposition": f"attachment; filename*=UTF-8''converted.pdf"
|
||||
}
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"PDF转换失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"转换失败: {str(e)}")
|
||||
|
||||
|
||||
@router.get("/download/{download_id}")
|
||||
async def download_pdf(download_id: str):
|
||||
"""
|
||||
通过下载 ID 下载 PDF（支持 IDM 拦截）
|
||||
"""
|
||||
if download_id not in _pdf_cache:
|
||||
raise HTTPException(status_code=404, detail="下载链接已过期或不存在")
|
||||
|
||||
pdf_content, filename = _pdf_cache.pop(download_id) # 下载后删除
|
||||
|
||||
# 使用 RFC 5987 编码支持中文文件名
|
||||
from starlette.responses import StreamingResponse
|
||||
import urllib.parse
|
||||
|
||||
# URL 编码中文文件名
|
||||
encoded_filename = urllib.parse.quote(f"{filename}.pdf")
|
||||
|
||||
return StreamingResponse(
|
||||
iter([pdf_content]),
|
||||
media_type="application/pdf",
|
||||
headers={
|
||||
"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@router.get("/formats")
|
||||
async def get_supported_formats():
|
||||
"""
|
||||
获取支持的源文件格式
|
||||
|
||||
Returns:
|
||||
支持的格式列表
|
||||
"""
|
||||
return {
|
||||
"success": True,
|
||||
"formats": pdf_converter_service.get_supported_formats()
|
||||
}
|
||||
|
||||
|
||||
@router.post("/convert/batch")
|
||||
async def batch_convert_to_pdf(
|
||||
files: list[UploadFile] = File(...),
|
||||
):
|
||||
"""
|
||||
批量将多个文件转换为 PDF
|
||||
|
||||
注意: 批量转换会返回多个 PDF 文件打包的 zip
|
||||
|
||||
Args:
|
||||
files: 上传的文件列表
|
||||
|
||||
Returns:
|
||||
ZIP 压缩包（包含所有PDF）
|
||||
"""
|
||||
try:
|
||||
import io
|
||||
import zipfile
|
||||
|
||||
results = []
|
||||
errors = []
|
||||
|
||||
for file in files:
|
||||
try:
|
||||
filename = file.filename or "document"
|
||||
file_ext = filename.rsplit('.', 1)[-1].lower() if '.' in filename else ''
|
||||
|
||||
if file_ext not in pdf_converter_service.supported_formats:
|
||||
errors.append(f"{filename}: 不支持的格式")
|
||||
continue
|
||||
|
||||
content = await file.read()
|
||||
pdf_content, error = await pdf_converter_service.convert_to_pdf(
|
||||
file_content=content,
|
||||
source_format=file_ext,
|
||||
filename=filename.rsplit('.', 1)[0] if '.' in filename else filename
|
||||
)
|
||||
|
||||
if error:
|
||||
errors.append(f"{filename}: {error}")
|
||||
else:
|
||||
results.append((filename, pdf_content))
|
||||
|
||||
except Exception as e:
|
||||
errors.append(f"{file.filename}: {str(e)}")
|
||||
|
||||
if not results:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"没有可转换的文件。错误: {'; '.join(errors)}"
|
||||
)
|
||||
|
||||
# 创建 ZIP 包
|
||||
zip_buffer = io.BytesIO()
|
||||
with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file:
|
||||
for original_name, pdf_content in results:
|
||||
pdf_name = f"{original_name.rsplit('.', 1)[0] if '.' in original_name else original_name}.pdf"
|
||||
zip_file.writestr(pdf_name, pdf_content)
|
||||
|
||||
zip_buffer.seek(0)
|
||||
|
||||
return StreamingResponse(
|
||||
iter([zip_buffer.getvalue()]),
|
||||
media_type="application/zip",
|
||||
headers={
|
||||
"Content-Disposition": "attachment; filename*=UTF-8''converted_pdfs.zip"
|
||||
}
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"批量PDF转换失败: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"批量转换失败: {str(e)}")
|
||||
403
backend/app/services/pdf_converter_service.py
Normal file
403
backend/app/services/pdf_converter_service.py
Normal file
@@ -0,0 +1,403 @@
|
||||
"""
|
||||
PDF 转换服务
|
||||
|
||||
支持将 Word(docx)、Excel(xlsx)、Txt、Markdown(md) 格式转换为 PDF
|
||||
策略：所有格式先转为 Markdown，再通过 Markdown 转 PDF
|
||||
"""
|
||||
import io
|
||||
import logging
|
||||
import platform
|
||||
from pathlib import Path
|
||||
from typing import List, Tuple
|
||||
|
||||
from reportlab.lib.pagesizes import A4
|
||||
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
|
||||
from reportlab.lib.enums import TA_LEFT, TA_CENTER, TA_JUSTIFY
|
||||
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle
|
||||
from reportlab.pdfbase import pdfmetrics
|
||||
from reportlab.pdfbase.ttfonts import TTFont
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class PDFConverterService:
|
||||
"""PDF 转换服务"""
|
||||
|
||||
def __init__(self):
|
||||
self.supported_formats = ["docx", "xlsx", "txt", "md"]
|
||||
self._font_name = None
|
||||
self._styles = None
|
||||
self._page_width = None
|
||||
self._page_height = None
|
||||
self._setup_fonts()
|
||||
|
||||
def _setup_fonts(self):
|
||||
"""设置字体"""
|
||||
try:
|
||||
self._page_width, self._page_height = A4
|
||||
|
||||
# 查找中文字体
|
||||
font_path = self._find_chinese_font()
|
||||
if font_path:
|
||||
try:
|
||||
font = TTFont('ChineseFont', font_path)
|
||||
pdfmetrics.registerFont(font)
|
||||
from reportlab.pdfbase.pdfmetrics import registerFontFamily
|
||||
registerFontFamily('ChineseFont', normal='ChineseFont')
|
||||
self._font_name = 'ChineseFont'
|
||||
logger.info(f"成功注册中文字体: {font_path}")
|
||||
except Exception as e:
|
||||
logger.warning(f"字体注册失败: {e}, 使用Helvetica")
|
||||
self._font_name = 'Helvetica'
|
||||
else:
|
||||
self._font_name = 'Helvetica'
|
||||
logger.warning("未找到中文字体，使用 Helvetica（不支持中文）")
|
||||
|
||||
# 创建样式
|
||||
styles = getSampleStyleSheet()
|
||||
|
||||
styles.add(ParagraphStyle(
|
||||
name='ChineseTitle',
|
||||
fontName=self._font_name,
|
||||
fontSize=16,
|
||||
leading=22,
|
||||
alignment=TA_CENTER,
|
||||
spaceAfter=12,
|
||||
))
|
||||
|
||||
styles.add(ParagraphStyle(
|
||||
name='ChineseHeading',
|
||||
fontName=self._font_name,
|
||||
fontSize=14,
|
||||
leading=20,
|
||||
spaceBefore=10,
|
||||
spaceAfter=8,
|
||||
))
|
||||
|
||||
styles.add(ParagraphStyle(
|
||||
name='ChineseBody',
|
||||
fontName=self._font_name,
|
||||
fontSize=10,
|
||||
leading=14,
|
||||
alignment=TA_JUSTIFY,
|
||||
spaceAfter=6,
|
||||
))
|
||||
|
||||
styles.add(ParagraphStyle(
|
||||
name='ChineseCode',
|
||||
fontName='Courier',
|
||||
fontSize=9,
|
||||
leading=12,
|
||||
))
|
||||
|
||||
self._styles = styles
|
||||
logger.info("PDF服务初始化完成")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"PDF服务初始化失败: {e}")
|
||||
raise
|
||||
|
||||
def _find_chinese_font(self) -> str:
|
||||
"""查找中文字体"""
|
||||
system = platform.system()
|
||||
|
||||
if system == "Windows":
|
||||
fonts = [
|
||||
"C:/Windows/Fonts/simhei.ttf",
|
||||
"C:/Windows/Fonts/simsun.ttc",
|
||||
"C:/Windows/Fonts/msyh.ttc",
|
||||
"C:/Windows/Fonts/simsun.ttf",
|
||||
]
|
||||
elif system == "Darwin":
|
||||
fonts = [
|
||||
"/System/Library/Fonts/STHeiti Light.ttc",
|
||||
"/System/Library/Fonts/PingFang.ttc",
|
||||
"/Library/Fonts/Arial Unicode.ttf",
|
||||
]
|
||||
else:
|
||||
fonts = [
|
||||
"/usr/share/fonts/truetype/wqy/wqy-microhei.ttc",
|
||||
"/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc",
|
||||
]
|
||||
|
||||
for font in fonts:
|
||||
if Path(font).exists():
|
||||
return font
|
||||
return None
|
||||
|
||||
def _sanitize_text(self, text: str) -> str:
|
||||
"""清理文本"""
|
||||
if not text:
|
||||
return ""
|
||||
return text.replace('\x00', '')
|
||||
|
||||
async def convert_to_pdf(
|
||||
self,
|
||||
file_content: bytes,
|
||||
source_format: str,
|
||||
filename: str = "document"
|
||||
) -> Tuple[bytes, str]:
|
||||
"""将文档转换为 PDF"""
|
||||
try:
|
||||
if source_format.lower() not in self.supported_formats:
|
||||
return b"", f"不支持的格式: {source_format}"
|
||||
|
||||
# 第一步：转换为 Markdown
|
||||
markdown_content, error = await self._convert_to_markdown(file_content, source_format, filename)
|
||||
if error:
|
||||
return b"", error
|
||||
|
||||
# 第二步：Markdown 转 PDF
|
||||
return await self._convert_markdown_to_pdf(markdown_content, filename)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"PDF转换失败: {e}")
|
||||
import traceback
|
||||
logger.error(f"详细错误: {traceback.format_exc()}")
|
||||
return b"", f"转换失败: {str(e)}"
|
||||
|
||||
async def _convert_to_markdown(
|
||||
self,
|
||||
file_content: bytes,
|
||||
source_format: str,
|
||||
filename: str
|
||||
) -> Tuple[str, str]:
|
||||
"""将各种格式转换为 Markdown"""
|
||||
converters = {
|
||||
"docx": self._convert_docx_to_markdown,
|
||||
"xlsx": self._convert_xlsx_to_markdown,
|
||||
"txt": self._convert_txt_to_markdown,
|
||||
"md": self._convert_md_to_markdown,
|
||||
}
|
||||
return await converters[source_format.lower()](file_content, filename)
|
||||
|
||||
async def _convert_txt_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
|
||||
"""Txt 转 Markdown"""
|
||||
try:
|
||||
text = self._decode_content(file_content)
|
||||
text = self._sanitize_text(text)
|
||||
return f"# {filename}\n\n{text}", ""
|
||||
except Exception as e:
|
||||
logger.error(f"Txt转Markdown失败: {e}")
|
||||
return "", f"文本文件处理失败: {str(e)}"
|
||||
|
||||
async def _convert_md_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
|
||||
"""Markdown 原样返回"""
|
||||
try:
|
||||
content = self._decode_content(file_content)
|
||||
content = self._sanitize_text(content)
|
||||
return f"# {filename}\n\n{content}", ""
|
||||
except Exception as e:
|
||||
logger.error(f"Markdown处理失败: {e}")
|
||||
return "", f"Markdown处理失败: {str(e)}"
|
||||
|
||||
async def _convert_docx_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
|
||||
"""Word 转 Markdown - 使用 zipfile 直接解析，更加健壮"""
|
||||
try:
|
||||
import zipfile
|
||||
import re
|
||||
|
||||
lines = [f"# {filename}", ""]
|
||||
|
||||
# 直接使用 zipfile 解析 DOCX，避免 python-docx 的严格验证
|
||||
try:
|
||||
with zipfile.ZipFile(io.BytesIO(file_content), 'r') as zf:
|
||||
# 读取主文档内容
|
||||
xml_content = zf.read('word/document.xml').decode('utf-8')
|
||||
except zipfile.BadZipFile:
|
||||
return "", "文件不是有效的 DOCX 格式"
|
||||
except KeyError:
|
||||
return "", "DOCX 文件损坏：找不到 document.xml"
|
||||
|
||||
# 简单的 XML 解析 - 提取文本段落
|
||||
# 移除 XML 标签，提取纯文本
|
||||
xml_content = re.sub(r'<w:br[^>]*>', '\n', xml_content)
|
||||
xml_content = re.sub(r'</w:p>', '\n', xml_content)
|
||||
xml_content = re.sub(r'<[^>]+>', '', xml_content)
|
||||
xml_content = re.sub(r'\n\s*\n', '\n\n', xml_content)
|
||||
|
||||
# 解码 HTML 实体
|
||||
xml_content = xml_content.replace('&', '&')
|
||||
xml_content = xml_content.replace('<', '<')
|
||||
xml_content = xml_content.replace('>', '>')
|
||||
xml_content = xml_content.replace('"', '"')
|
||||
xml_content = xml_content.replace(''', "'")
|
||||
|
||||
# 清理空白
|
||||
lines_text = [line.strip() for line in xml_content.split('\n') if line.strip()]
|
||||
|
||||
# 生成 Markdown
|
||||
for text in lines_text[:500]: # 限制最多500行
|
||||
if text:
|
||||
lines.append(text)
|
||||
|
||||
return '\n'.join(lines), ""
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Word转Markdown失败: {e}")
|
||||
import traceback
|
||||
logger.error(traceback.format_exc())
|
||||
return "", f"Word文档处理失败: {str(e)}"
|
||||
for table in doc.tables:
|
||||
lines.append("")
|
||||
for row in table.rows:
|
||||
row_data = [cell.text.strip() for cell in row.cells]
|
||||
lines.append("| " + " | ".join(row_data) + " |")
|
||||
# 表头分隔符
|
||||
if table.rows:
|
||||
lines.append("| " + " | ".join(["---"] * len(table.rows[0].cells)) + " |")
|
||||
|
||||
return "\n".join(lines), ""
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Word转Markdown失败: {e}")
|
||||
return "", f"Word文档处理失败: {str(e)}"
|
||||
|
||||
async def _convert_xlsx_to_markdown(self, file_content: bytes, filename: str) -> Tuple[str, str]:
|
||||
"""Excel 转 Markdown"""
|
||||
try:
|
||||
import openpyxl
|
||||
|
||||
wb = openpyxl.load_workbook(io.BytesIO(file_content))
|
||||
lines = [f"# {filename} - Excel数据", ""]
|
||||
|
||||
for sheet_name in wb.sheetnames[:10]:
|
||||
ws = wb[sheet_name]
|
||||
lines.append(f"## 工作表: {sheet_name}")
|
||||
lines.append("")
|
||||
|
||||
for row_idx, row in enumerate(ws.iter_rows(max_row=50, values_only=True)):
|
||||
row_data = [str(cell) if cell is not None else "" for cell in row]
|
||||
if not any(row_data):
|
||||
continue
|
||||
lines.append("| " + " | ".join(row_data) + " |")
|
||||
if row_idx == 0:
|
||||
lines.append("| " + " | ".join(["---"] * len(row_data)) + " |")
|
||||
|
||||
lines.append("")
|
||||
|
||||
return "\n".join(lines), ""
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Excel转Markdown失败: {e}")
|
||||
return "", f"Excel处理失败: {str(e)}"
|
||||
|
||||
async def _convert_markdown_to_pdf(self, markdown_content: str, filename: str) -> Tuple[bytes, str]:
|
||||
"""Markdown 转 PDF"""
|
||||
try:
|
||||
logger.info(f"Markdown转PDF开始 - filename={filename}, 字体={self._font_name}")
|
||||
logger.info(f"styles['ChineseTitle'].fontName={self._styles['ChineseTitle'].fontName}")
|
||||
|
||||
buffer = io.BytesIO()
|
||||
story = []
|
||||
|
||||
safe_filename = self._sanitize_text(filename)
|
||||
logger.info(f"safe_filename={repr(safe_filename[:50])}")
|
||||
|
||||
story.append(Paragraph(text=safe_filename, style=self._styles['ChineseTitle']))
|
||||
story.append(Spacer(1, 12))
|
||||
|
||||
in_code = False
|
||||
for line in markdown_content.split('\n'):
|
||||
line = line.strip()
|
||||
|
||||
if line.startswith('```'):
|
||||
in_code = not in_code
|
||||
story.append(Spacer(1, 6))
|
||||
continue
|
||||
|
||||
if in_code:
|
||||
story.append(Paragraph(text=self._sanitize_text(line), style=self._styles['ChineseCode']))
|
||||
continue
|
||||
|
||||
if not line:
|
||||
story.append(Spacer(1, 6))
|
||||
continue
|
||||
|
||||
# 标题处理
|
||||
if line.startswith('# '):
|
||||
story.append(Paragraph(text=self._sanitize_text(line[2:]), style=self._styles['ChineseHeading']))
|
||||
elif line.startswith('## '):
|
||||
story.append(Paragraph(text=self._sanitize_text(line[3:]), style=self._styles['ChineseHeading']))
|
||||
elif line.startswith('### '):
|
||||
story.append(Paragraph(text=self._sanitize_text(line[4:]), style=self._styles['ChineseHeading']))
|
||||
elif line.startswith('#### '):
|
||||
story.append(Paragraph(text=self._sanitize_text(line[5:]), style=self._styles['ChineseHeading']))
|
||||
elif line.startswith('- ') or line.startswith('* '):
|
||||
story.append(Paragraph(text="• " + self._sanitize_text(line[2:]), style=self._styles['ChineseBody']))
|
||||
# 表格处理
|
||||
elif line.startswith('|'):
|
||||
# 跳过 markdown 表格分隔符
|
||||
if set(line.replace('|', '').replace('-', '').replace(':', '').replace(' ', '')) == set():
|
||||
continue
|
||||
# 解析并创建表格
|
||||
table_lines = []
|
||||
for _ in range(50): # 最多50行
|
||||
if line.startswith('|'):
|
||||
row = [cell.strip() for cell in line.split('|')[1:-1]]
|
||||
if not any(row) or set(''.join(row).replace('-', '').replace(':', '').replace(' ', '')) == set():
|
||||
break
|
||||
table_lines.append(row)
|
||||
try:
|
||||
line = next(markdown_content.split('\n').__iter__()).strip()
|
||||
except StopIteration:
|
||||
break
|
||||
else:
|
||||
break
|
||||
|
||||
if table_lines:
|
||||
# 创建表格
|
||||
t = Table(table_lines, colWidths=[100] * len(table_lines[0]))
|
||||
t.setStyle(TableStyle([
|
||||
('FONTNAME', (0, 0), (-1, -1), self._font_name),
|
||||
('FONTSIZE', (0, 0), (-1, -1), 9),
|
||||
('GRID', (0, 0), (-1, -1), 0.5, '#999999'),
|
||||
('BACKGROUND', (0, 0), (-1, 0), '#4472C4'),
|
||||
('TEXTCOLOR', (0, 0), (-1, 0), '#FFFFFF'),
|
||||
]))
|
||||
story.append(t)
|
||||
story.append(Spacer(1, 6))
|
||||
else:
|
||||
story.append(Paragraph(text=self._sanitize_text(line), style=self._styles['ChineseBody']))
|
||||
|
||||
logger.info(f"准备构建PDF，story长度={len(story)}")
|
||||
|
||||
pdf_doc = SimpleDocTemplate(
|
||||
buffer,
|
||||
pagesize=(self._page_width, self._page_height),
|
||||
rightMargin=72,
|
||||
leftMargin=72,
|
||||
topMargin=72,
|
||||
bottomMargin=72
|
||||
)
|
||||
logger.info("调用pdf_doc.build()")
|
||||
pdf_doc.build(story)
|
||||
logger.info("pdf_doc.build()完成")
|
||||
|
||||
result = buffer.getvalue()
|
||||
buffer.close()
|
||||
return result, ""
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Markdown转PDF失败: {e}")
|
||||
import traceback
|
||||
logger.error(f"详细错误: {traceback.format_exc()}")
|
||||
return b"", f"Markdown转PDF失败: {str(e)}"
|
||||
|
||||
def _decode_content(self, file_content: bytes) -> str:
|
||||
"""解码文件内容"""
|
||||
encodings = ['utf-8', 'gbk', 'gb2312', 'gb18030', 'latin-1']
|
||||
for enc in encodings:
|
||||
try:
|
||||
return file_content.decode(enc)
|
||||
except (UnicodeDecodeError, LookupError):
|
||||
continue
|
||||
return file_content.decode('utf-8', errors='replace')
|
||||
|
||||
def get_supported_formats(self) -> List[str]:
|
||||
"""获取支持的格式"""
|
||||
return self.supported_formats
|
||||
|
||||
|
||||
# 全局单例
|
||||
pdf_converter_service = PDFConverterService()
|
||||
Reference in New Issue
Block a user