438 lines
16 KiB
Python
438 lines
16 KiB
Python
"""
|
||
Word 文档导出模块
|
||
"""
|
||
import os
|
||
import re
|
||
import sqlite3
|
||
import logging
|
||
from datetime import datetime
|
||
from docx import Document
|
||
from docx.shared import Pt, Cm, RGBColor
|
||
from docx.enum.text import WD_ALIGN_PARAGRAPH
|
||
from docx.oxml import OxmlElement
|
||
from docx.oxml.ns import qn
|
||
|
||
import config
|
||
from utils.outline_numbering import format_heading_display
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
LEVEL_STYLES = {
|
||
1: ('Heading 1', 16, True),
|
||
2: ('Heading 2', 14, True),
|
||
3: ('Heading 3', 13, False),
|
||
4: ('Heading 4', 12, False),
|
||
}
|
||
|
||
|
||
def export_to_word(db_path: str, project_id: int) -> str:
|
||
"""
|
||
生成 Word 文档并保存到 data/exports/，返回文件名。
|
||
"""
|
||
conn = sqlite3.connect(db_path)
|
||
try:
|
||
# 获取项目信息
|
||
cur = conn.cursor()
|
||
cur.execute("SELECT name FROM projects WHERE id=?", (project_id,))
|
||
project = cur.fetchone()
|
||
if not project:
|
||
raise ValueError(f'项目 {project_id} 不存在')
|
||
project_name = project[0]
|
||
|
||
# 获取标书大纲文本（用于标题页）
|
||
cur.execute("SELECT outline FROM tender_data WHERE project_id=?", (project_id,))
|
||
td = cur.fetchone()
|
||
bid_title = project_name + '技术标书'
|
||
if td and td[0]:
|
||
first_line = td[0].strip().split('\n')[0].strip()
|
||
if first_line:
|
||
bid_title = first_line
|
||
|
||
# 获取所有章节（按顺序）
|
||
cur.execute('''
|
||
SELECT section_number, section_title, level, is_leaf, content, intro_content
|
||
FROM bid_sections
|
||
WHERE project_id=?
|
||
ORDER BY order_index
|
||
''', (project_id,))
|
||
sections = cur.fetchall()
|
||
|
||
doc = _build_document(bid_title, sections)
|
||
|
||
# 保存文件
|
||
os.makedirs(config.EXPORT_DIR, exist_ok=True)
|
||
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
|
||
safe_name = ''.join(c for c in project_name if c.isalnum() or c in '._- \u4e00-\u9fff')
|
||
filename = f'{safe_name}_{timestamp}.docx'
|
||
filepath = os.path.join(config.EXPORT_DIR, filename)
|
||
doc.save(filepath)
|
||
logger.info(f'导出完成: {filepath}')
|
||
return filename
|
||
|
||
finally:
|
||
conn.close()
|
||
|
||
|
||
DISCLAIMER_TEXT = """\
|
||
免责声明
|
||
|
||
本工具仅供学习交流免费使用，所生成的技术方案不可直接用于投标，请务必人工核对。本工具不会通过任何平台进行销售，请用户注意辨别真伪。在您开始使用本AI标书制作服务之前，请认真阅读并同意以下关键条款。一旦您继续使用，即表示您已充分理解并认可本提示的全部内容。
|
||
|
||
服务定位
|
||
本工具为单机使用的AI标书辅助工具，旨在帮助您生成标书的参考素材。您需对最终自己编写的标书文件承担全部责任，包括审核、修改内容，确保其符合相关法律法规及项目要求。
|
||
|
||
准确性免责
|
||
本人不对AI生成内容的完全准确性与完整性作任何保证。您有义务自行核实所有关键信息，并自行承担因使用本工具所引发的一切后果。
|
||
|
||
标书风险
|
||
本工具所生成的素材文件仅作参考。若您使用（包括引用、修改或二次创作），需自行承担由此可能导致的废标、侵权等全部风险与责任，本人不承担任何相关责任。
|
||
|
||
责任限制
|
||
任何情形下，本人均不对因使用本服务而造成的任何直接、间接或衍生损失（例如利润损失、业务中断、数据丢失等）承担法律责任。
|
||
|
||
其他事项
|
||
本人保留随时修改或终止本服务的权利。本提示的解释及争议解决，均适用中华人民共和国法律。\
|
||
"""
|
||
|
||
|
||
def _add_disclaimer_page(doc: Document) -> None:
|
||
"""在文档开头插入免责声明页"""
|
||
# 标题
|
||
title_para = doc.add_paragraph()
|
||
title_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
title_run = title_para.add_run('免责声明')
|
||
title_run.font.size = Pt(16)
|
||
title_run.font.bold = True
|
||
title_run.font.name = '黑体'
|
||
title_run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
|
||
|
||
doc.add_paragraph()
|
||
|
||
# 正文各段（跳过第一行标题，已单独渲染）
|
||
body_lines = DISCLAIMER_TEXT.split('\n')[2:] # 跳过"免责声明"和空行
|
||
for line in body_lines:
|
||
p = doc.add_paragraph()
|
||
stripped = line.strip()
|
||
# 小标题行（非空且后面没有缩进，即段落标题）
|
||
is_section_title = bool(stripped) and not line.startswith(' ') and not line.startswith('\u3000')
|
||
run = p.add_run(stripped if stripped else '')
|
||
if is_section_title and stripped:
|
||
run.font.bold = True
|
||
run.font.size = Pt(11)
|
||
else:
|
||
run.font.size = Pt(10.5)
|
||
run.font.name = 'Times New Roman'
|
||
run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
|
||
p.paragraph_format.space_after = Pt(4)
|
||
_set_line_spacing_15(p)
|
||
|
||
doc.add_page_break()
|
||
|
||
|
||
def _add_toc_tree_page(doc: Document, sections: list) -> None:
|
||
"""标题页之后插入树状目录（按 level 缩进；静态文本，不含 Word 目录域）。"""
|
||
toc_heading = doc.add_paragraph()
|
||
toc_heading.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
tr = toc_heading.add_run('目录')
|
||
tr.font.size = Pt(16)
|
||
tr.font.bold = True
|
||
tr.font.name = '黑体'
|
||
tr._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
|
||
doc.add_paragraph()
|
||
|
||
for row in sections:
|
||
section_number, title, level, _, _, _ = row
|
||
level = min(int(level), 4)
|
||
text = format_heading_display(level, str(section_number or ''), str(title or ''))
|
||
p = doc.add_paragraph()
|
||
p.paragraph_format.left_indent = Cm(0.75 * max(0, level - 1))
|
||
p.paragraph_format.space_after = Pt(3)
|
||
run = p.add_run(text)
|
||
run.font.size = Pt(12)
|
||
run.font.name = '宋体'
|
||
run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
|
||
|
||
doc.add_page_break()
|
||
|
||
|
||
def _build_document(bid_title: str, sections) -> Document:
|
||
doc = Document()
|
||
|
||
# ── 页面设置 ─────────────────────────────────────────────────────────
|
||
section_obj = doc.sections[0]
|
||
section_obj.page_width = Cm(21)
|
||
section_obj.page_height = Cm(29.7)
|
||
section_obj.left_margin = Cm(3)
|
||
section_obj.right_margin = Cm(2.5)
|
||
section_obj.top_margin = Cm(2.5)
|
||
section_obj.bottom_margin = Cm(2.5)
|
||
|
||
# ── 免责声明页（第一页）─────────────────────────────────────────────
|
||
_add_disclaimer_page(doc)
|
||
|
||
# ── 标题页 ──────────────────────────────────────────────────────────
|
||
title_para = doc.add_paragraph()
|
||
title_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
title_run = title_para.add_run(bid_title)
|
||
title_run.font.size = Pt(22)
|
||
title_run.font.bold = True
|
||
title_run.font.color.rgb = RGBColor(0x1a, 0x56, 0xdb)
|
||
title_run.font.name = '黑体'
|
||
title_run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
|
||
|
||
doc.add_paragraph()
|
||
|
||
date_para = doc.add_paragraph()
|
||
date_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
date_run = date_para.add_run(datetime.now().strftime('%Y年%m月'))
|
||
date_run.font.size = Pt(14)
|
||
date_run.font.name = '宋体'
|
||
date_run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
|
||
|
||
doc.add_page_break()
|
||
|
||
# ── 树状目录页（标题页后、正文前）──────────────────────────────────
|
||
_add_toc_tree_page(doc, sections)
|
||
|
||
# ── 章节内容 ─────────────────────────────────────────────────────────
|
||
for row in sections:
|
||
section_number, title, level, is_leaf, content, intro = row
|
||
level = min(int(level), 4)
|
||
|
||
# 添加标题（带完整目录号）
|
||
heading_text = format_heading_display(level, str(section_number or ''), str(title or ''))
|
||
heading = doc.add_heading(level=level)
|
||
heading.clear()
|
||
run = heading.add_run(heading_text)
|
||
_, font_size, bold = LEVEL_STYLES.get(level, ('Heading 4', 12, False))
|
||
run.font.size = Pt(font_size)
|
||
run.font.bold = bold
|
||
run.font.name = '黑体' if level <= 2 else '宋体'
|
||
run._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体' if level <= 2 else '宋体')
|
||
|
||
# 章节引言（非叶节点）
|
||
if intro and intro.strip():
|
||
_add_body_paragraphs(doc, intro)
|
||
|
||
# 正文内容（叶节点）
|
||
if content and content.strip():
|
||
_add_body_paragraphs(doc, content)
|
||
|
||
return doc
|
||
|
||
|
||
def _set_line_spacing_15(paragraph):
|
||
"""将段落设为 1.5 倍行距（Word 中的 WD_LINE_SPACING.MULTIPLE × 1.5）"""
|
||
from docx.oxml.ns import qn as _qn
|
||
pPr = paragraph._element.get_or_add_pPr()
|
||
spacing = pPr.find(_qn('w:spacing'))
|
||
if spacing is None:
|
||
spacing = OxmlElement('w:spacing')
|
||
pPr.append(spacing)
|
||
spacing.set(_qn('w:line'), '360') # 240 × 1.5 = 360 twips
|
||
spacing.set(_qn('w:lineRule'), 'auto')
|
||
|
||
|
||
# ── 图/表标记解析 ─────────────────────────────────────────────────────────
|
||
|
||
_BLOCK_PATTERN = re.compile(
|
||
r'\[FIGURE:([^\]]+)\](.*?)\[/FIGURE\]'
|
||
r'|\[TABLE:([^\]]+)\](.*?)\[/TABLE\]',
|
||
re.DOTALL
|
||
)
|
||
|
||
|
||
def _split_content_blocks(text: str) -> list:
|
||
"""
|
||
将章节正文拆分为有序内容块列表：
|
||
{'type': 'text', 'content': '...'}
|
||
{'type': 'figure', 'title': '...', 'content': '...'}
|
||
{'type': 'table', 'title': '...', 'content': '...'}
|
||
"""
|
||
blocks = []
|
||
last = 0
|
||
for m in _BLOCK_PATTERN.finditer(text):
|
||
if m.start() > last:
|
||
blocks.append({'type': 'text', 'content': text[last:m.start()]})
|
||
if m.group(1) is not None:
|
||
blocks.append({'type': 'figure',
|
||
'title': m.group(1).strip(),
|
||
'content': m.group(2).strip()})
|
||
else:
|
||
blocks.append({'type': 'table',
|
||
'title': m.group(3).strip(),
|
||
'content': m.group(4).strip()})
|
||
last = m.end()
|
||
if last < len(text):
|
||
blocks.append({'type': 'text', 'content': text[last:]})
|
||
return blocks
|
||
|
||
|
||
def _set_para_shading(para, hex_fill: str):
|
||
"""为段落设置背景填充色"""
|
||
pPr = para._element.get_or_add_pPr()
|
||
shd = OxmlElement('w:shd')
|
||
shd.set(qn('w:val'), 'clear')
|
||
shd.set(qn('w:color'), 'auto')
|
||
shd.set(qn('w:fill'), hex_fill)
|
||
pPr.append(shd)
|
||
|
||
|
||
def _set_cell_bg(cell, hex_fill: str):
|
||
"""为表格单元格设置背景色"""
|
||
tc = cell._tc
|
||
tcPr = tc.get_or_add_tcPr()
|
||
shd = OxmlElement('w:shd')
|
||
shd.set(qn('w:val'), 'clear')
|
||
shd.set(qn('w:color'), 'auto')
|
||
shd.set(qn('w:fill'), hex_fill)
|
||
tcPr.append(shd)
|
||
|
||
|
||
def _set_cell_padding(cell, pt_value: float):
|
||
"""设置表格单元格四侧内边距（单位：磅）"""
|
||
tc = cell._tc
|
||
tcPr = tc.get_or_add_tcPr()
|
||
tcMar = OxmlElement('w:tcMar')
|
||
val = str(int(pt_value * 20)) # pt → twips（1pt = 20 twips）
|
||
for side in ('top', 'left', 'bottom', 'right'):
|
||
node = OxmlElement(f'w:{side}')
|
||
node.set(qn('w:w'), val)
|
||
node.set(qn('w:type'), 'dxa')
|
||
tcMar.append(node)
|
||
tcPr.append(tcMar)
|
||
|
||
|
||
def _safe_set_eastasia(run, font_name: str):
|
||
"""安全设置东亚字体，确保 rPr 已存在"""
|
||
_ = run.font.size # 触发 rPr 创建
|
||
try:
|
||
run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
|
||
except Exception:
|
||
pass
|
||
|
||
|
||
def _add_block_caption(doc: Document, prefix: str, title: str):
|
||
"""添加图/表居中加粗标题行"""
|
||
cap = doc.add_paragraph()
|
||
cap.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||
cap.paragraph_format.space_before = Pt(8)
|
||
cap.paragraph_format.space_after = Pt(3)
|
||
run = cap.add_run(f'{prefix}：{title}')
|
||
run.font.bold = True
|
||
run.font.size = Pt(11)
|
||
run.font.name = 'Times New Roman'
|
||
_safe_set_eastasia(run, '黑体')
|
||
|
||
|
||
def _add_figure_block(doc: Document, title: str, content: str):
|
||
"""
|
||
将图示内容渲染为带边框 + 背景色的文字图示框。
|
||
使用单格表格（Table Grid 样式）实现四周边框，比纯段落背景更专业。
|
||
"""
|
||
_add_block_caption(doc, '图', title)
|
||
|
||
lines = content.split('\n')
|
||
|
||
# 单格表格：四周边框 + 淡蓝灰背景
|
||
tbl = doc.add_table(rows=1, cols=1)
|
||
tbl.style = 'Table Grid'
|
||
cell = tbl.cell(0, 0)
|
||
_set_cell_bg(cell, 'EFF3FB') # 淡蓝灰背景
|
||
_set_cell_padding(cell, 5) # 内边距 5pt
|
||
|
||
for i, line in enumerate(lines):
|
||
if i == 0:
|
||
para = cell.paragraphs[0]
|
||
para.clear()
|
||
else:
|
||
para = cell.add_paragraph()
|
||
para.paragraph_format.space_before = Pt(0)
|
||
para.paragraph_format.space_after = Pt(1)
|
||
run = para.add_run(line if line else ' ')
|
||
run.font.size = Pt(9.5)
|
||
run.font.name = 'Courier New'
|
||
_safe_set_eastasia(run, '宋体')
|
||
|
||
# 图示后空行
|
||
sp = doc.add_paragraph()
|
||
sp.paragraph_format.space_after = Pt(8)
|
||
|
||
|
||
def _add_word_table(doc: Document, title: str, content: str):
|
||
"""将 Markdown 表格解析并渲染为 Word 表格"""
|
||
# 解析 markdown 行，过滤掉分隔行（|---|）
|
||
raw_rows = []
|
||
for line in content.strip().split('\n'):
|
||
line = line.strip()
|
||
if not line:
|
||
continue
|
||
if re.match(r'^\|[\s\-:| ]+\|$', line):
|
||
continue # 分隔行
|
||
if line.startswith('|') and line.endswith('|'):
|
||
cells = [c.strip() for c in line[1:-1].split('|')]
|
||
raw_rows.append(cells)
|
||
|
||
if not raw_rows:
|
||
# 没有解析到有效行时，降级为普通文本
|
||
_add_block_caption(doc, '表', title)
|
||
_add_plain_text(doc, content)
|
||
return
|
||
|
||
col_count = max(len(r) for r in raw_rows)
|
||
rows = [r + [''] * (col_count - len(r)) for r in raw_rows]
|
||
|
||
_add_block_caption(doc, '表', title)
|
||
|
||
table = doc.add_table(rows=len(rows), cols=col_count)
|
||
table.style = 'Table Grid'
|
||
|
||
for i, row_data in enumerate(rows):
|
||
for j, cell_text in enumerate(row_data):
|
||
cell = table.cell(i, j)
|
||
para = cell.paragraphs[0]
|
||
para.clear()
|
||
para.alignment = WD_ALIGN_PARAGRAPH.CENTER if i == 0 else WD_ALIGN_PARAGRAPH.LEFT
|
||
run = para.add_run(cell_text)
|
||
run.font.size = Pt(10)
|
||
run.font.bold = (i == 0)
|
||
run.font.name = 'Times New Roman'
|
||
_safe_set_eastasia(run, '宋体')
|
||
if i == 0:
|
||
_set_cell_bg(cell, 'D6E4F7') # 浅蓝表头
|
||
|
||
# 表格后空行
|
||
sp = doc.add_paragraph()
|
||
sp.paragraph_format.space_after = Pt(6)
|
||
|
||
|
||
def _add_plain_text(doc: Document, text: str):
|
||
"""添加普通文本段落（内部辅助）"""
|
||
for line in text.split('\n'):
|
||
line = line.strip()
|
||
if not line:
|
||
continue
|
||
p = doc.add_paragraph()
|
||
p.paragraph_format.first_line_indent = Pt(24)
|
||
p.paragraph_format.space_after = Pt(6)
|
||
_set_line_spacing_15(p)
|
||
run = p.add_run(line)
|
||
run.font.size = Pt(12)
|
||
run.font.name = 'Times New Roman'
|
||
_safe_set_eastasia(run, '宋体')
|
||
|
||
|
||
def _add_body_paragraphs(doc: Document, text: str):
|
||
"""
|
||
将正文文本分段渲染，自动识别并处理图示 [FIGURE:...] 和表格 [TABLE:...] 标记。
|
||
"""
|
||
for block in _split_content_blocks(text):
|
||
if block['type'] == 'figure':
|
||
_add_figure_block(doc, block['title'], block['content'])
|
||
elif block['type'] == 'table':
|
||
_add_word_table(doc, block['title'], block['content'])
|
||
else:
|
||
_add_plain_text(doc, block['content'])
|
||
|
||
|