skills/musicXML-ocr/scripts/homr_to_musescore.py

#!/usr/bin/env python3
"""
homr_to_musescore.py

完整的 homr → MusicXML → MuseScore 可用格式 流水线。

功能：
1. 调用 homr 识别五线谱图片
2. 删除 <print> 元素（修复错误分行）
3. 添加花括号分组（钢琴谱 grand staff）

Usage:
    python homr_to_musescore.py image.png [output.musicxml]

Dependencies:
    - homr (pip install homr)
    - Python 3.8+ (标准库 xml.etree.ElementTree)

Environment:
    依赖 base conda 环境（已包含 homr）：
    conda activate base
"""

import sys
import os
import tempfile
import shutil
import xml.etree.ElementTree as ET

# homr 依赖检查
try:
    from homr.main import process_image, ProcessingConfig, XmlGeneratorArguments
    HAS_HOMR = True
except ImportError:
    HAS_HOMR = False


def step1_homr(image_path: str) -> str:
    """Step 1: 用 homr 识别图片，输出 MusicXML 路径。"""
    print(f"[Step 1] Running homr OCR on: {image_path}")

    if not HAS_HOMR:
        print("Error: homr not installed. Run: pip install homr")
        sys.exit(1)

    # homr 不支持中文路径，用临时文件
    tmp_dir = tempfile.mkdtemp(prefix='homr_')
    tmp_image = os.path.join(tmp_dir, os.path.basename(image_path))
    shutil.copy(image_path, tmp_image)

    try:
        config = ProcessingConfig(False, False, False, False, -1)
        xml_args = XmlGeneratorArguments(False, None, None)
        result = process_image(tmp_image, config, xml_args)
        musicxml_path = result
        print(f"[Step 1] Done: {musicxml_path}")
        return musicxml_path
    finally:
        shutil.rmtree(tmp_dir, ignore_errors=True)


def step2_remove_print(input_path: str, output_path: str) -> None:
    """Step 2: 删除所有 <print> 元素。"""
    print(f"[Step 2] Removing <print> elements from: {input_path}")

    ET.register_namespace('m', 'http://www.musescore.org/ns/mscore')
    ET.register_namespace('xlink', 'http://www.w3.org/1999/xlink')

    tree = ET.parse(input_path)
    root = tree.getroot()
    removed_count = 0

    for elem in root.iter():
        to_remove = [c for c in list(elem) if c.tag == 'print']
        for c in to_remove:
            elem.remove(c)
            removed_count += 1

    try:
        ET.indent(root)
    except AttributeError:
        pass

    tree.write(output_path, encoding='UTF-8', xml_declaration=True)
    print(f"[Step 2] Removed {removed_count} <print> element(s)")


def step3_add_brace(input_path: str, output_path: str) -> None:
    """Step 3: 添加花括号分组。"""
    print(f"[Step 3] Adding brace grouping to: {input_path}")

    ET.register_namespace('m', 'http://www.musescore.org/ns/mscore')
    ET.register_namespace('xlink', 'http://www.w3.org/1999/xlink')

    tree = ET.parse(input_path)
    root = tree.getroot()
    part_list = root.find('part-list')

    if part_list is None:
        print("[Step 3] Warning: no <part-list> found, skipping brace")
        shutil.copy(input_path, output_path)
        return

    group_start = ET.Element('part-group')
    group_start.set('number', '1')
    group_start.set('type', 'start')
    ET.SubElement(group_start, 'group-symbol').text = 'brace'
    ET.SubElement(group_start, 'group-barline').text = 'bracket'
    ET.SubElement(group_start, 'group-time')
    part_list.insert(0, group_start)

    for sp in part_list.findall('score-part'):
        g = ET.SubElement(sp, 'group')
        g.text = '1'

    part_list.append(ET.Element('part-group', number='1', type='stop'))

    try:
        ET.indent(root)
    except AttributeError:
        pass

    tree.write(output_path, encoding='UTF-8', xml_declaration=True)
    print(f"[Step 3] Done")


def main():
    if len(sys.argv) < 2:
        print(__doc__)
        sys.exit(1)

    image_path = sys.argv[1]
    if not os.path.exists(image_path):
        print(f"Error: file not found: {image_path}")
        sys.exit(1)

    # 确定输出文件名
    if len(sys.argv) > 2:
        output_path = sys.argv[2]
    else:
        base = os.path.splitext(os.path.basename(image_path))[0]
        output_path = os.path.join(os.path.dirname(image_path), f"{base}_final.musicxml")

    # 创建临时目录存放中间文件
    tmp_dir = tempfile.mkdtemp(prefix='homr_pipeline_')

    try:
        # Step 1: homr 识别
        raw_xml = os.path.join(tmp_dir, 'raw.musicxml')
        step1_homr(image_path)

        # homr 会在图片同目录生成 .musicxml 文件
        expected = image_path.replace(os.path.splitext(image_path)[1], '.musicxml')
        if os.path.exists(expected):
            raw_xml = expected
        else:
            # 尝试从 tmp_dir 找
            candidates = [f for f in os.listdir(tmp_dir) if f.endswith('.musicxml')]
            if candidates:
                raw_xml = os.path.join(tmp_dir, candidates[0])

        if not os.path.exists(raw_xml):
            print(f"Error: homr did not produce output file")
            sys.exit(1)

        # Step 2: 删除 print
        no_print_xml = os.path.join(tmp_dir, 'no_print.musicxml')
        step2_remove_print(raw_xml, no_print_xml)

        # Step 3: 添加花括号
        step3_add_brace(no_print_xml, output_path)

        print()
        print(f"Pipeline complete!")
        print(f"Final output: {output_path}")
        print(f"Open in MuseScore to verify: 5 measures per line, brace on grand staff")

    finally:
        shutil.rmtree(tmp_dir, ignore_errors=True)


if __name__ == '__main__':
    main()