-
Notifications
You must be signed in to change notification settings - Fork 338
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Compare the html built by AsciiDoc and Asciidoctor as part of the self-test. Like all good tests, it doesn't pass at first. I've temporarily ignored all of the failures and have added them to the main asciidoctor issue or filed them as their own issue.
- Loading branch information
Showing
4 changed files
with
109 additions
and
5 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,81 @@ | ||
| #!/usr/bin/env python3 | ||
|
|
||
| # Script to compare two html files, ignoring differences that we consider | ||
| # to be unimportant. The output is a unified diff of formatted html meant | ||
| # to be readable and precise at identifying differences. | ||
| # | ||
| # This script is designed to be run in the container managed by the | ||
| # Dockerfile at the root of this repository. | ||
|
|
||
|
|
||
| from bs4 import BeautifulSoup, NavigableString | ||
| import difflib | ||
| import re | ||
|
|
||
|
|
||
| def normalize_html(html): | ||
| """Normalizes html to remove expected differences between AsciiDoc's | ||
| output and Asciidoctor's output. | ||
| """ | ||
| # Replace many whitespace characters with a single space in some elements | ||
| # kind of like a browser does. | ||
| soup = BeautifulSoup(html, 'lxml') | ||
| for e in soup.select(':not(script,pre,code,style)'): | ||
| for part in e: | ||
| if isinstance(part, NavigableString): | ||
| crunched = NavigableString(re.sub(r'\s+', ' ', part)) | ||
| if crunched != part: | ||
| part.replace_with(crunched) | ||
| # Format the html with indentation so we can *see* things | ||
| html = soup.prettify() | ||
| # Remove the zero width space that asciidoctor adds after each horizontal | ||
| # ellipsis. They don't hurt anything but asciidoc doesn't make them | ||
| html = html.replace('\u2026\u200b', '\u2026') | ||
| # Temporary workaround for known issues | ||
| html = html.replace('class="edit_me" href="/./', 'class="edit_me" href="') | ||
| html = re.sub( | ||
| r'(?m)^\s+<div class="console_widget" data-snippet="[^"]+">' | ||
| r'\s+</div>\n', '', html) | ||
| html = html.replace('\\<1>', '<1>') | ||
| return html | ||
|
|
||
|
|
||
| def html_diff(lhs_name, lhs, rhs_name, rhs): | ||
| """Compare two html blobs, ignoring expected differences between AsciiDoc | ||
| and Asciidoctor. The result is a generator for lines in the diff report. | ||
| If it is entirely empty then there is no diff. | ||
| """ | ||
| lhs_lines = normalize_html(lhs).splitlines() | ||
| rhs_lines = normalize_html(rhs).splitlines() | ||
| return difflib.unified_diff( | ||
| lhs_lines, | ||
| rhs_lines, | ||
| fromfile=lhs_name, | ||
| tofile=rhs_name, | ||
| lineterm='') | ||
|
|
||
|
|
||
| def html_file_diff(lhs, rhs): | ||
| """Compare two html files, ignoring expected differences between AsciiDoc | ||
| and Asciidoctor. The result is a generator for lines in the diff report. | ||
| If it is entirely empty then there is no diff. | ||
| """ | ||
| with open(lhs, encoding='utf-8') as lhs_file: | ||
| lhs_text = lhs_file.read() | ||
| with open(rhs, encoding='utf-8') as rhs_file: | ||
| rhs_text = rhs_file.read() | ||
| return html_diff(lhs, lhs_text, rhs, rhs_text) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| import sys | ||
| if len(sys.argv) != 3: | ||
| print("Expected exactly 2 arguments but got %s" % sys.argv[1:]) | ||
| exit(1) | ||
| had_diff = False | ||
| for line in html_file_diff(sys.argv[1], sys.argv[2]): | ||
| had_diff = True | ||
| # print doesn't like to print utf-8 in all cases but buffer.write is ok | ||
| sys.stderr.buffer.write(line.encode('utf-8')) | ||
| sys.stderr.buffer.write("\n".encode('utf-8')) | ||
| exit(1 if had_diff else 0) |