seirdy.one/scripts/xhtmlize-single-file.sh

#!/bin/sh
# copies an .html file to an equivalent .xhtml file, but replaces
# the meta charset with an XML declaration for compatibility with some
# XML tooling.
# Expects polygot XHTML(5) markup.
# Formats both the .html and .xhtml file.
# this means that every index.html file has an equivalent index.xhtml file.
# content negotiation allows an agent to pick html or xhtml.

# use xmllint to do the formatting.
# xmllint ruins inline CSS so delete the inline CSS and re-insert it.
# xmllint also adds extra whitespace around <pre><code> which we remove
# with "sd". I chose sd since it handles newlines well.

set -e -u

export html_file="$1"
export tmp_file="$html_file.tmp"
export xhtml_file=${html_file%*.html}.xhtml

cleanup() {
	rm -f "$tmp_file"
}
trap cleanup EXIT

trap cleanup EXIT
sed 7d "$html_file" | xmllint --format --encode UTF-8 --noent - -o "$tmp_file"
{
	head -n7 "$tmp_file"
	cat tmp.css
	tail -n +8 "$tmp_file" \
		| sd '<pre(?: tabindex="0")?>\n\t*<code ' '<pre tabindex="0"><code ' \
		| sd '(?:\n)?</code>\n(?:[\t\s]*)?</pre>' '</code></pre>' \
		| sd '</span>.span itemprop="familyName"' '</span> <span itemprop="familyName"'
} >>"$xhtml_file"

 # replace the html file with the formatted xhtml5 file, excluding the xml declaration
tail -n +2 "$xhtml_file" > "$html_file"

# remove the redundant charset declaration from the xhtml file. It's the
# first thing in the <head>
sed -i 5d "$xhtml_file" # busybox sed supports "-i"
xhtmlize: switch back to using xmllint Switch back to using xmllint, but now extract + replace the CSS to address the escaping. 2022-06-02 05:11:40 +00:00			`#!/bin/sh`
			`# copies an .html file to an equivalent .xhtml file, but replaces`
			`# the meta charset with an XML declaration for compatibility with some`
			`# XML tooling.`
			`# Expects polygot XHTML(5) markup.`
			`# Formats both the .html and .xhtml file.`
			`# this means that every index.html file has an equivalent index.xhtml file.`
			`# content negotiation allows an agent to pick html or xhtml.`

			`# use xmllint to do the formatting.`
			`# xmllint ruins inline CSS so delete the inline CSS and re-insert it.`
			`# xmllint also adds extra whitespace around <pre><code> which we remove`
			`# with "sd". I chose sd since it handles newlines well.`

			`set -e -u`

			`export html_file="$1"`
Internal: improve scripts - I forgot to compress xhtml files. fix that. - Stylistic change: remove unnecessary brace expansions - Don't repeatedly append to a file; run commands in a different scope and write all at once. Move Nu HTML validator filtering into a shell script: - Return a bad exit code if validation errors are found after filtering - Remove null-ish values from the JSON output; the final output should be an empty string, since nothing should be reported. 2022-06-03 00:18:13 +00:00			`export tmp_file="$html_file.tmp"`
xhtmlize: switch back to using xmllint Switch back to using xmllint, but now extract + replace the CSS to address the escaping. 2022-06-02 05:11:40 +00:00			`export xhtml_file=${html_file%*.html}.xhtml`

			`cleanup() {`
			`rm -f "$tmp_file"`
			`}`
			`trap cleanup EXIT`

			`trap cleanup EXIT`
			`sed 7d "$html_file" \| xmllint --format --encode UTF-8 --noent - -o "$tmp_file"`
Internal: improve scripts - I forgot to compress xhtml files. fix that. - Stylistic change: remove unnecessary brace expansions - Don't repeatedly append to a file; run commands in a different scope and write all at once. Move Nu HTML validator filtering into a shell script: - Return a bad exit code if validation errors are found after filtering - Remove null-ish values from the JSON output; the final output should be an empty string, since nothing should be reported. 2022-06-03 00:18:13 +00:00			`{`
			`head -n7 "$tmp_file"`
			`cat tmp.css`
			`tail -n +8 "$tmp_file" \`
			`\| sd '<pre(?: tabindex="0")?>\n\t*<code ' '<pre tabindex="0"><code ' \`
Whitespace fixes 2022-06-03 03:01:50 +00:00			`\| sd '(?:\n)?</code>\n(?:[\t\s]*)?</pre>' '</code></pre>' \`
			`\| sd '</span>.span itemprop="familyName"' '</span> <span itemprop="familyName"'`
Internal: improve scripts - I forgot to compress xhtml files. fix that. - Stylistic change: remove unnecessary brace expansions - Don't repeatedly append to a file; run commands in a different scope and write all at once. Move Nu HTML validator filtering into a shell script: - Return a bad exit code if validation errors are found after filtering - Remove null-ish values from the JSON output; the final output should be an empty string, since nothing should be reported. 2022-06-03 00:18:13 +00:00			`} >>"$xhtml_file"`

			`# replace the html file with the formatted xhtml5 file, excluding the xml declaration`
xhtmlize: switch back to using xmllint Switch back to using xmllint, but now extract + replace the CSS to address the escaping. 2022-06-02 05:11:40 +00:00			`tail -n +2 "$xhtml_file" > "$html_file"`

Internal: improve scripts - I forgot to compress xhtml files. fix that. - Stylistic change: remove unnecessary brace expansions - Don't repeatedly append to a file; run commands in a different scope and write all at once. Move Nu HTML validator filtering into a shell script: - Return a bad exit code if validation errors are found after filtering - Remove null-ish values from the JSON output; the final output should be an empty string, since nothing should be reported. 2022-06-03 00:18:13 +00:00			`# remove the redundant charset declaration from the xhtml file. It's the`
			`# first thing in the <head>`
			`sed -i 5d "$xhtml_file" # busybox sed supports "-i"`