md2pdf技能支持Markdown表格渲染

This commit is contained in:
2026-09-04 15:59:23 +08:00
parent e150e9c6c9
commit e3972fb25a
2 changed files with 72 additions and 5 deletions
+3 -2
View File
@@ -18,10 +18,11 @@ output_schema:
## 功能说明
- 该技能使用 `reportlab` 将 Markdown 转换为 PDF。
- 支持标题、加粗、斜体、列表、引用、分隔线、图片等常用 Markdown 语法
- 支持标题、加粗、斜体、列表、引用、分隔线、图片、表格等常用 Markdown 语法
- 图片:`![alt](src)` 独立成行时嵌入 PDF(居中,超宽时等比缩到版心宽);
相对路径按 **Markdown 文件所在目录** 解析(如任务目录里的图表),也支持绝对路径与 http(s) 图片;
图片加载失败退回 alt 文本占位,不会静默丢失;表格语法暂不支持
图片加载失败退回 alt 文本占位,不会静默丢失
- 表格:`| a | b |` 管道表格(含对齐分隔行)自动识别为表格,表头加底纹、隔行斑马纹、居中显示
- 自动处理中文字体
## 调用方式
+69 -3
View File
@@ -13,13 +13,15 @@ from pathlib import Path
from reportlab.lib.pagesizes import A4
from reportlab.lib.units import mm
from reportlab.lib import colors
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib.enums import TA_LEFT
from reportlab.lib.utils import ImageReader
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.platypus import (
SimpleDocTemplate, Paragraph, Spacer, ListFlowable, ListItem, HRFlowable, Image
SimpleDocTemplate, Paragraph, Spacer, ListFlowable, ListItem, HRFlowable, Image,
Table, TableStyle
)
# ---------- 字体注册 ----------
@@ -194,6 +196,58 @@ def image_flowable(src, md_dir, max_width):
img.hAlign = 'CENTER'
return img
# ---------- 表格 ----------
# 数据/表头行:| a | b |;分隔行:| --- | :---: | ---: | --- |
TABLE_ROW_RE = re.compile(r'^\|.*\|\s*$')
TABLE_SEP_RE = re.compile(r'^\|?\s*:?-{3,}:?\s*(?:\|\s*:?-{3,}:?\s*)+\|?\s*$')
def split_row(line):
"""按未转义的竖线拆分表格行,保留 `\|` 转义出来的字面竖线"""
line = line.strip()
cells = re.split(r'(?<!\\)\|', line)
cells = [c.replace('\\|', '|').strip() for c in cells]
# 首尾的空单元格(来自行首/行尾的 |)去掉;全空则删掉
if cells and cells[0] == '': cells = cells[1:]
if cells and cells[-1] == '': cells = cells[:-1]
return cells
def table_flowable(rows, max_width, styles):
"""表格行 → platypus Table(首行为表头加底纹,超宽时分列撑满版心)"""
ncols = max(len(r) for r in rows)
colw = max_width / ncols
cell_style = ParagraphStyle(
name='TableCell',
fontName=styles['body'].fontName,
fontSize=8.5, leading=12,
leftIndent=3, rightIndent=3,
alignment=TA_LEFT,
)
header_style = ParagraphStyle(
name='TableHeader', parent=cell_style,
fontName=styles['h3'].fontName, # 粗体
textColor=colors.white,
)
data = []
for ri, row in enumerate(rows):
row = row + [''] * (ncols - len(row))
data.append([
Paragraph(render_inline(c), header_style if ri == 0 else cell_style)
for c in row
])
t = Table(data, colWidths=[colw] * ncols)
t.setStyle(TableStyle([
('GRID', (0, 0), (-1, -1), 0.5, colors.HexColor('#c9d4e4')),
('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#2c3e50')),
('ROWBACKGROUNDS', (0, 1), (-1, -1), [colors.white, colors.HexColor('#f4f7fb')]),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('LEFTPADDING', (0, 0), (-1, -1), 4),
('RIGHTPADDING', (0, 0), (-1, -1), 4),
('TOPPADDING', (0, 0), (-1, -1), 3),
('BOTTOMPADDING', (0, 0), (-1, -1), 3),
]))
t.hAlign = 'CENTER'
return t
# ---------- Markdown 解析主函数 ----------
def parse_markdown(md_text, styles, md_dir=None, max_width=170 * mm):
"""解析 Markdown 文本,返回 platypus 故事列表"""
@@ -218,8 +272,11 @@ def parse_markdown(md_text, styles, md_dir=None, max_width=170 * mm):
current_list = []
current_list_type = None
for raw_line in lines:
line = raw_line.strip()
i = 0
n = len(lines)
while i < n:
line = lines[i].strip()
i += 1
if not line:
flush_list()
continue
@@ -276,6 +333,15 @@ def parse_markdown(md_text, styles, md_dir=None, max_width=170 * mm):
elif line.startswith('> '):
flush_list()
story.append(Paragraph(render_inline(line[2:]), styles["quote"]))
# 表格:当前行是表头行,且下一行是分隔行 → 收拢成整张表
elif TABLE_ROW_RE.match(line) and i < n and TABLE_SEP_RE.match(lines[i].strip()):
flush_list()
i += 1 # 跳过分隔行
rows = [split_row(line)]
while i < n and TABLE_ROW_RE.match(lines[i].strip()):
rows.append(split_row(lines[i].strip()))
i += 1
story.append(table_flowable(rows, max_width, styles))
# 普通段落
else:
flush_list()