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
94
95
96
97
98
99
100
101
102
103
104
105
106
|
import typing
import htmlgenerator
from lxml import etree, html
from gemini_to_web import parser
def first_header_title_extractor(parsed: list[parser.GemElement]):
heading_lines = [element for element in parsed if isinstance(element, parser.HeadingLine)]
if heading_lines:
return heading_lines[0].heading_text
def to_html(parsed: list[parser.GemElement], title_extractor=first_header_title_extractor):
body = []
building_element = None
building_content = None
def close(body, building_element, building_content):
if building_element and building_content:
body.append(building_element(*building_content))
return (body, None, None)
head = []
if title_extractor:
head.append(htmlgenerator.TITLE(title_extractor(parsed)))
for item in parsed:
match item:
case parser.HeadingLine(level, heading_text):
if building_element:
body, building_element, building_content = close(body, building_element, building_content)
headers = [htmlgenerator.H1, htmlgenerator.H2, htmlgenerator.H3]
body.append(headers[level-1](heading_text))
case parser.QuoteLine(text):
# https://geminiprotocol.net/docs/gemtext.gmi#blockquotes says:
#
# > The quoted content is written as a single long line [...]
if building_element:
body, building_element, building_content = close(body, building_element, building_content)
body.append(htmlgenerator.BLOCKQUOTE(text))
case parser.PreformattingToggleLine(alt_text):
if building_element == htmlgenerator.PRE:
assert not alt_text, f"Closing preformatting toggle line with alt text {alt_text}"
body, building_element, building_content = close(body, building_element, building_content)
else:
body, building_element, building_content = close(body, building_element, building_content)
building_element = htmlgenerator.PRE
building_content = ""
case parser.PreformattedTextLine(text):
assert building_element == htmlgenerator.PRE
building_content += text
building_content += "\n"
case parser.TextLine(""):
if building_element:
body, building_element, building_content = close(body, building_element, building_content)
case parser.TextLine(text):
if building_element == htmlgenerator.P:
building_content += [htmlgenerator.BR(), text]
continue
elif building_element is not None and building_element != htmlgenerator.P:
body, building_element, building_content = close(body, building_element, building_content)
building_element = htmlgenerator.P
building_content = [text]
case parser.LinkLine(url, link_name):
if building_element == htmlgenerator.P:
building_content += [htmlgenerator.BR(), htmlgenerator.A(link_name, href=url)]
continue
elif building_element is not None and building_element != htmlgenerator.P:
body, building_element, building_content = close(body, building_element, building_content)
building_element = htmlgenerator.P
building_content = [htmlgenerator.A(link_name, href=url)]
case parser.ListItem(text):
if building_element == htmlgenerator.UL:
building_content.append(htmlgenerator.LI(text))
continue
elif building_element is not None and building_element != htmlgenerator.UL:
body, building_element, building_content = close(body, building_element, building_content)
building_element = htmlgenerator.UL
building_content = [htmlgenerator.LI(text)]
case _:
assert False, f"unknown element {item}"
close(body, building_element, building_content)
html = htmlgenerator.HTML(
htmlgenerator.HEAD(*head),
htmlgenerator.BODY(*body),
)
return html
def pretty(s):
return etree.tostring(html.fromstring(s), pretty_print=True).decode("utf8")
def cli_to_html():
import sys
input_ = sys.stdin.read()
gemtext = parser.parse(input_)
gemtext = list(gemtext)
html = to_html(gemtext)
rendered = htmlgenerator.render(html, {})
rendered = pretty(rendered)
print(rendered)
|
