From 5b7ca18e0f95beb5f117b0a067d02d051ded98e2 Mon Sep 17 00:00:00 2001 From: Ilya Kreymer Date: Sat, 10 Feb 2018 09:17:15 -0800 Subject: [PATCH] rewriting: try more granular modifers to distinguish embeds: (in part for ukwa/ukwa-pywb#6) - 'ba_' - for rewriting - 'je_' - 'javascript-embed' default for client-side rewriting in wombat better modifiers for css rewriting (server and client): - 'ce_' - 'css-embed' for any url() embeds in CSS - 'cs_' - for css stylesheet @import rewriting/other .css --- pywb/rewrite/html_rewriter.py | 2 +- pywb/rewrite/test/test_html_rewriter.py | 24 +++++++++++------------ pywb/rewrite/test/test_regex_rewriters.py | 24 +++++++++++------------ 3 files changed, 25 insertions(+), 25 deletions(-) diff --git a/pywb/rewrite/html_rewriter.py b/pywb/rewrite/html_rewriter.py index bf28bf25..92c4e8e0 100644 --- a/pywb/rewrite/html_rewriter.py +++ b/pywb/rewrite/html_rewriter.py @@ -56,7 +56,7 @@ class HTMLRewriterMixin(StreamingRewriter): 'archive': 'oe_'}, 'area': {'href': defmod}, 'audio': {'src': 'oe_'}, - 'base': {'href': defmod}, + 'base': {'href': 'ba_'}, 'blockquote': {'cite': defmod}, 'body': {'background': 'im_'}, 'button': {'formaction': defmod}, diff --git a/pywb/rewrite/test/test_html_rewriter.py b/pywb/rewrite/test/test_html_rewriter.py index 65bbfe28..26f12248 100644 --- a/pywb/rewrite/test/test_html_rewriter.py +++ b/pywb/rewrite/test/test_html_rewriter.py @@ -25,23 +25,23 @@ r""" # Base Tests -- w/ rewrite (default) >>> parse('') - + # Full Path >>> parse('', urlrewriter=full_path_urlrewriter) - + # Full Path Scheme Rel Base >>> parse('', urlrewriter=full_path_urlrewriter) - + # Rel Base >>> parse('', urlrewriter=full_path_urlrewriter) - + # Rel Base + example >>> parse('', urlrewriter=full_path_urlrewriter) - + # Rel Base >>> parse('', urlrewriter=full_path_urlrewriter) @@ -53,7 +53,7 @@ r""" # ensure trailing slash added >>> parse('') - + # Base Tests -- no rewrite >>> parse('', urlrewriter=no_base_canon_rewriter) @@ -244,29 +244,29 @@ r"""
>>> parse('
') -
+
>>> parse('') - + >>> parse('') - + >>> parse('') - + >>> parse('') >>> parse("") - + #>>> parse('') # Style >>> parse('') - + # Unterminated style tag, handle and auto-terminate >>> parse('