解析 YAML，返回行号

Question

我正在用 YAML 数据制作一个文档生成器，它将指定每个项目是从 YAML 文件的哪一行生成的。做这个的最好方式是什么？所以如果 YAML 文件是这样的：

- key1: item 1
  key2: item 2
- key1: another item 1
  key2: another item 2

我想要这样的东西：

[
     {'__line__': 1, 'key1': 'item 1', 'key2': 'item 2'},
     {'__line__': 3, 'key1': 'another item 1', 'key2': 'another item 2'},
]

我目前正在使用 PyYAML，但如果我可以从 Python 中使用它，任何其他库都可以。

Answer 1

以下代码是基于以前的好答案，如果有人还需要定位叶子属性的行号，以下代码可能会有所帮助：

from yaml.composer import Composer
from yaml.constructor import Constructor
from yaml.nodes import ScalarNode
from yaml.resolver import BaseResolver
from yaml.loader import Loader


class LineLoader(Loader):
    def __init__(self, stream):
        super(LineLoader, self).__init__(stream)

    def compose_node(self, parent, index):
        # the line number where the previous token has ended (plus empty lines)
        line = self.line
        node = Composer.compose_node(self, parent, index)
        node.__line__ = line + 1
        return node

    def construct_mapping(self, node, deep=False):
        node_pair_lst = node.value
        node_pair_lst_for_appending = []

        for key_node, value_node in node_pair_lst:
            shadow_key_node = ScalarNode(tag=BaseResolver.DEFAULT_SCALAR_TAG, value='__line__' + key_node.value)
            shadow_value_node = ScalarNode(tag=BaseResolver.DEFAULT_SCALAR_TAG, value=key_node.__line__)
            node_pair_lst_for_appending.append((shadow_key_node, shadow_value_node))

        node.value = node_pair_lst + node_pair_lst_for_appending
        mapping = Constructor.construct_mapping(self, node, deep=deep)
        return mapping


if __name__ == '__main__':
    stream = """             # The first line
    key1:                    # This is the second line
      key1_1: item1
      key1_2: item1_2
      key1_3:
        - item1_3_1
        - item1_3_2
    key2: item 2
    key3: another item 1
    """
    loader = LineLoader(stream)
    data = loader.get_single_data()

    from pprint import pprint

    pprint(data)

输出如下，另外一个key前缀为“__line__”，比如同级的“__line__key”。

PS：对于列表项，我还不能显示行。

{'__line__key1': 2,
 '__line__key2': 8,
 '__line__key3': 9,
 'key1': {'__line__key1_1': 3,
          '__line__key1_2': 4,
          '__line__key1_3': 5,
          'key1_1': 'item1',
          'key1_2': 'item1_2',
          'key1_3': ['item1_3_1', 'item1_3_2']},
 'key2': 'item 2',
 'key3': 'another item 1'}

Answer 2

这是puzzlet's answer的改进版：

import yaml
from yaml.loader import SafeLoader

class SafeLineLoader(SafeLoader):
    def construct_mapping(self, node, deep=False):
        mapping = super(SafeLineLoader, self).construct_mapping(node, deep=deep)
        # Add 1 so line numbering starts at 1
        mapping['__line__'] = node.start_mark.line + 1
        return mapping

你可以这样使用它：

data = yaml.load(whatever, Loader=SafeLineLoader)

Answer 3

如果您使用ruamel.yaml >= 0.9（我是作者），并使用RoundTripLoader，您可以访问集合项上的属性lc，以获取它们在源 YAML：

def test_item_04(self):
    data = load("""
     # testing line and column based on SO
     # http://stackoverflow.com/questions/13319067/
     - key1: item 1
       key2: item 2
     - key3: another item 1
       key4: another item 2
        """)
    assert data[0].lc.line == 2
    assert data[0].lc.col == 2
    assert data[1].lc.line == 4
    assert data[1].lc.col == 2

（行和列从 0 开始计数）。

This answer 显示如何在加载过程中将lc 属性添加到字符串类型。

Answer 4

我通过向Composer.compose_node 和Constructor.construct_mapping 添加钩子来实现它：

import yaml
from yaml.composer import Composer
from yaml.constructor import Constructor

def main():
    loader = yaml.Loader(open('data.yml').read())
    def compose_node(parent, index):
        # the line number where the previous token has ended (plus empty lines)
        line = loader.line
        node = Composer.compose_node(loader, parent, index)
        node.__line__ = line + 1
        return node
    def construct_mapping(node, deep=False):
        mapping = Constructor.construct_mapping(loader, node, deep=deep)
        mapping['__line__'] = node.__line__
        return mapping
    loader.compose_node = compose_node
    loader.construct_mapping = construct_mapping
    data = loader.get_single_data()
    print(data)