feishu-wiki-tools/scripts/md_to_blocks.py

#!/usr/bin/env python3
"""Markdown to Feishu Docx Block JSON converter.
Usage: python3 md_to_blocks.py < input.md > output.json
       python3 md_to_blocks.py file.md

Supports: headings, lists, dividers, inline formatting, and markdown tables.
Table blocks (31) are output as nested structures with cell blocks (32).
"""

import re, json, sys

TABLE_BLOCK = 31
CELL_BLOCK = 32
TEXT_BLOCK = 2
CODE_BLOCK = 14
PREFIX = 'ecc_'

LANG_CODES = {
    '': 1, 'text': 1, 'plain': 1,
    'bash': 7, 'sh': 7, 'shell': 7,
    'python': 11, 'py': 11,
    'go': 5, 'golang': 5,
    'js': 12, 'javascript': 12, 'json': 14,
    'yaml': 33, 'yml': 33,
    'sql': 25,
}

def lang_code(lang):
    """Map markdown code fence language to Feishu code block language id."""
    return LANG_CODES.get(lang.lower(), 1)

def parse_inline(text):
    """Parse a line of inline markdown into text_run elements."""
    elements = []
    pos = 0
    while pos < len(text):
        m = re.match(r'\*\*(.+?)\*\*|__(.+?)__', text[pos:])
        if m:
            elements.append({'text_run': {'content': m.group(1), 'text_element_style': {'bold': True}}})
            pos += len(m.group(0))
            continue
        m = re.match(r'\[(.+?)\]\((.+?)\)', text[pos:])
        if m:
            elements.append({'text_run': {'content': m.group(1), 'text_element_style': {'link': {'url': m.group(2)}}}})
            pos += len(m.group(0))
            continue
        m = re.match(r'`(.+?)`', text[pos:])
        if m:
            elements.append({'text_run': {'content': m.group(1), 'text_element_style': {'inline_code': True}}})
            pos += len(m.group(0))
            continue
        m = re.match(r'\*(.+?)\*', text[pos:])
        if m:
            elements.append({'text_run': {'content': m.group(1), 'text_element_style': {'italic': True}}})
            pos += len(m.group(0))
            continue
        nxt = re.search(r'[\*\[`]', text[pos:])
        if nxt:
            end = pos + nxt.start()
            if end > pos:
                elements.append({'text_run': {'content': text[pos:end], 'text_element_style': {}}})
            elif end == pos:
                elements.append({'text_run': {'content': text[pos:pos+1], 'text_element_style': {}}})
                pos += 1
                continue
            pos = end
        else:
            elements.append({'text_run': {'content': text[pos:], 'text_element_style': {}}})
            break
    return elements

def is_sep_line(line):
    """Check if a line is a markdown table separator, e.g. |---|:---:|---|"""
    s = line.strip()
    if not s.startswith('|') or not s.endswith('|'):
        return False
    parts = s[1:-1].split('|')
    return all(re.match(r'^[\s\-:]+$', p) for p in parts)

def is_table_row(line):
    """Check if a line looks like a markdown table row."""
    s = line.strip()
    return s.startswith('|') and s.endswith('|') and '|' in s[1:-1]

def split_row(line):
    return [c.strip() for c in line.strip()[1:-1].split('|')]

def parse_table(lines, start_idx):
    """Parse a markdown table. Returns (blocks, end_idx) or (None, start_idx)."""
    i = start_idx
    headers = []
    has_header = False

    # Look ahead: need at least 2 lines (header + separator) or 1 plain row
    if i >= len(lines) or not is_table_row(lines[i]):
        return None, start_idx

    # First line: potential header
    first_cells = split_row(lines[i])
    if not first_cells:
        return None, start_idx

    i += 1
    # Check for separator
    if i < len(lines) and is_sep_line(lines[i]):
        headers = first_cells
        has_header = True
        i += 1

    # Collect data rows
    data_rows = []
    while i < len(lines) and is_table_row(lines[i]):
        row = split_row(lines[i])
        if row:
            data_rows.append(row)
        i += 1

    # No header case: first line was a data row
    if not has_header:
        data_rows.insert(0, first_cells)

    if not data_rows:
        return None, start_idx

    num_rows = len(data_rows)
    num_cols = max(len(r) for r in data_rows)

    # Build nested blocks
    blocks = []
    table_id = f'{PREFIX}t0'
    cell_ids = []

    # Table container
    table_block = {
        'block_id': table_id,
        'block_type': TABLE_BLOCK,
        'table': {
            'property': {
                'row_size': num_rows,
                'column_size': num_cols,
                'header_row': has_header
            }
        },
        'children': [],
        '__table': True,
        '__rows': num_rows,
        '__cols': num_cols
    }

    for row_idx, row in enumerate(data_rows):
        for col_idx in range(num_cols):
            cell_text = row[col_idx] if col_idx < len(row) else ''
            cell_id = f'{PREFIX}t0r{row_idx}c{col_idx}'
            text_id = f'{PREFIX}t0r{row_idx}c{col_idx}t'
            cell_ids.append(cell_id)

            is_header_cell = has_header and row_idx == 0
            elements = parse_inline(cell_text)
            if not elements:
                elements = [{'text_run': {'content': cell_text, 'text_element_style': {}}}]
            if is_header_cell:
                for el in elements:
                    if 'text_run' in el:
                        el['text_run']['text_element_style']['bold'] = True

            text_block = {
                'block_id': text_id,
                'block_type': TEXT_BLOCK,
                'text': {'elements': elements, 'style': {}},
                'children': []
            }
            cell_block = {
                'block_id': cell_id,
                'block_type': CELL_BLOCK,
                'table_cell': {},
                'children': [text_id]
            }

            table_block['children'].append(cell_id)
            blocks.append(cell_block)
            blocks.append(text_block)

    blocks.insert(0, table_block)
    return blocks, i

def md_to_blocks(md_text):
    """Convert Markdown text to Feishu Block JSON array."""
    lines = md_text.strip().split('\n')
    blocks = []
    i = 0
    while i < len(lines):
        line = lines[i]

        # Fenced code block: ```lang ... ```
        fence = re.match(r'^```(\w*)\s*$', line.strip())
        if fence:
            lang = fence.group(1)
            code_lines = []
            i += 1
            while i < len(lines) and not lines[i].strip().startswith('```'):
                code_lines.append(lines[i])
                i += 1
            i += 1  # skip closing fence
            code_text = '\n'.join(code_lines)
            blocks.append({
                'block_type': CODE_BLOCK,
                'code': {
                    'elements': [{'text_run': {'content': code_text, 'text_element_style': {}}}],
                    'style': {'language': lang_code(lang)}
                }
            })
            continue

        # Empty line
        if not line.strip():
            if i + 1 < len(lines) and lines[i + 1].strip() and not lines[i + 1].strip().startswith(('#', '-', '*', '`', '---', '|')):
                blocks.append({'block_type': 2, 'text': {'elements': [{'text_run': {'content': '', 'text_element_style': {}}}], 'style': {}}})
            i += 1
            continue

        # Divider
        if line.strip() in ('---', '***'):
            blocks.append({'block_type': 22, 'divider': {}})
            i += 1
            continue

        # Table detection
        if '|' in line:
            tbl, ni = parse_table(lines, i)
            if tbl is not None:
                blocks.extend(tbl)
                i = ni
                continue

        # Headings
        h = re.match(r'^(#{1,3})\s+(.+)$', line)
        if h:
            level = len(h.group(1))
            bt = 2 + level
            blocks.append({
                'block_type': bt,
                f'heading{level}': {
                    'elements': parse_inline(h.group(2)),
                    'style': {}
                }
            })
            i += 1
            continue

        # Quote
        quote = re.match(r'^>\s?(.+)$', line)
        if quote:
            blocks.append({
                'block_type': 15,
                'quote': {
                    'elements': parse_inline(quote.group(1)),
                    'style': {}
                }
            })
            i += 1
            continue

        # Bullet list
        bullet = re.match(r'^[\-\*]\s+(.+)$', line)
        if bullet:
            blocks.append({
                'block_type': 12,
                'bullet': {
                    'elements': parse_inline(bullet.group(1)),
                    'style': {}
                }
            })
            i += 1
            continue

        # Numbered list
        numbered = re.match(r'^\d+\.\s+(.+)$', line)
        if numbered:
            blocks.append({
                'block_type': 13,
                'ordered': {
                    'elements': parse_inline(numbered.group(1)),
                    'style': {}
                }
            })
            i += 1
            continue

        # Regular text
        elements = parse_inline(line)
        blocks.append({
            'block_type': 2,
            'text': {
                'elements': elements if elements else [{'text_run': {'content': line, 'text_element_style': {}}}],
                'style': {}
            }
        })
        i += 1

    return blocks

if __name__ == '__main__':
    if len(sys.argv) > 1:
        with open(sys.argv[1]) as f:
            text = f.read()
    else:
        text = sys.stdin.read()

    blocks = md_to_blocks(text)
    print(json.dumps(blocks, indent=2, ensure_ascii=False))