💾 Archived View for l-3.space › gmi2html.py captured on 2021-12-03 at 14:04:38.
-=-=-=-=-=-=-
#!/usr/bin/env python3
# Convert gemtext to HTML, accepting HTML header and footer files
# Copyright 2021 hunterb
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, version 3 of the License.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see https://www.gnu.org/licenses/.
# Original code found at:
# https://github.com/huntingb/gemtext-html-converter
# Modified by tslil clingman, April 2021 in the following ways
# - added HTML escaping of all non-pre lines
# - added header and footer file input
# - added generation of <ul> ... </ul> for list items
# - fixed stripping of lines, no longer occurs in pre blocks, and
# otherwise is rstrip only
# - fixed handling of links without titles
# - replace := syntax with something my version of python3 accepts
# - modified description below
"""
HUNTER'S SIMPLE GEMTEXT TO HTML CONVERTER
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
A simple script that converts gemtext to HTML.
Takes four arguments from stdin. The first two arguments are the names
of files which will be used as a header and footer for the generated
output, in that order.
The next argument is the name of of a gemtext file, and the last
argument is the name of the desired output file.
The output file consists of, in order: the header; the lines of
gemtext in the input file converted to their HTML equivalents: <h1>,
<h2>, <h3>, <p>, <a>, <blockquote>, <li>, and <pre> tags; the footer.
"""
# importing required libraries
import sys
import re
import html
# A dictionary that maps regex to match at the beginning of gmi lines
# to their corresponding HTML tag names. Used by
# convert_single_line().
tags_dict = {
r"^# (.*)": "h1",
r"^## (.*)": "h2",
r"^### (.*)": "h3",
r"^\* (.*)": "li",
r"^> (.*)": "blockquote",
r"^=>\s*(\S+)(\s+.*)?": "a"
}
# This function takes a string of gemtext as input and returns a
# string of HTML
def convert_single_line(gmi_line):
for pattern in tags_dict.keys():
match = re.match(pattern, gmi_line)
if match:
tag = tags_dict[pattern]
groups = match.groups()
if tag == "a":
href = re.sub("^gemini://", "https://", groups[0])
href = re.sub(r"\.gmi$", ".html", href)
if len(groups) > 1 and groups[1] is not None:
inner_text = groups[1].strip()
else:
inner_text = href
return f"<p><{tag} href='{href}'>{inner_text}</{tag}></p>"
else:
inner_text = html.escape(groups[0].strip())
return f"<{tag}>{inner_text}</{tag}>"
gmi_line = html.escape(gmi_line)
return f"<p>{gmi_line}</p>"
# Reads the contents of the input file line by line and outputs HTML.
# Renders text in preformat blocks (toggled by ```) as multiline <pre>
# tags.
def main(args):
with open(args[3]) as gmi, open(args[4], "w") as output:
# Write header
header = open(args[1])
output.write(header.read())
header.close()
# Parse gmitext
pre = False
listing = False
for line in gmi:
if line.startswith("```"):
pre = not pre
if pre:
line = line.rstrip()
if len(line) > 3:
line = html.escape(line[3:])
output.write(f"<pre title=\"{line}\">\n")
else:
output.write("<pre>\n")
else:
output.write("</pre>\n")
elif pre:
output.write(html.escape(line))
else:
line = line.rstrip()
if line.startswith("*") and not listing:
listing = True
output.write("<ul>\n")
if not line.startswith("*") and listing:
listing = False
output.write("</ul>\n")
output_line = convert_single_line(line)
output.write(output_line+"\n")
# Write footer
footer = open(args[2])
output.write(footer.read())
footer.close()
# Main guard
if __name__ == "__main__":
main(sys.argv)