1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
|
from markdown_it import MarkdownIt
from markdown_it.tree import SyntaxTreeNode
EXAMPLE_MARKDOWN = """
## Heading here
Some paragraph text and **emphasis here** and more text here.
"""
def test_tree_to_tokens_conversion():
tokens = MarkdownIt().parse(EXAMPLE_MARKDOWN)
tokens_after_roundtrip = SyntaxTreeNode(tokens).to_tokens()
assert tokens == tokens_after_roundtrip
def test_property_passthrough():
tokens = MarkdownIt().parse(EXAMPLE_MARKDOWN)
heading_open = tokens[0]
tree = SyntaxTreeNode(tokens)
heading_node = tree.children[0]
assert heading_open.tag == heading_node.tag
assert tuple(heading_open.map) == heading_node.map
assert heading_open.level == heading_node.level
assert heading_open.content == heading_node.content
assert heading_open.markup == heading_node.markup
assert heading_open.info == heading_node.info
assert heading_open.meta == heading_node.meta
assert heading_open.block == heading_node.block
assert heading_open.hidden == heading_node.hidden
def test_type():
tokens = MarkdownIt().parse(EXAMPLE_MARKDOWN)
tree = SyntaxTreeNode(tokens)
# Root type is "root"
assert tree.type == "root"
# "_open" suffix must be stripped from nested token type
assert tree.children[0].type == "heading"
assert tree[0].type == "heading"
# For unnested tokens, node type must remain same as token type
assert tree.children[0].children[0].type == "inline"
def test_sibling_traverse():
tokens = MarkdownIt().parse(EXAMPLE_MARKDOWN)
tree = SyntaxTreeNode(tokens)
paragraph_inline_node = tree.children[1].children[0]
text_node = paragraph_inline_node.children[0]
assert text_node.type == "text"
strong_node = text_node.next_sibling
assert strong_node.type == "strong"
another_text_node = strong_node.next_sibling
assert another_text_node.type == "text"
assert another_text_node.next_sibling is None
assert another_text_node.previous_sibling.previous_sibling == text_node
assert text_node.previous_sibling is None
def test_pretty(file_regression):
md = MarkdownIt("commonmark")
tokens = md.parse(
"""
# Header
Here's some text and an image 
1. a **list**
> a *quote*
"""
)
node = SyntaxTreeNode(tokens)
file_regression.check(node.pretty(indent=2, show_text=True), extension=".xml")
def test_walk():
tokens = MarkdownIt().parse(EXAMPLE_MARKDOWN)
tree = SyntaxTreeNode(tokens)
expected_node_types = (
"root",
"heading",
"inline",
"text",
"paragraph",
"inline",
"text",
"strong",
"text",
"text",
)
for node, expected_type in zip(tree.walk(), expected_node_types):
assert node.type == expected_type
|
