]*>[\s\S]*?<\/a>)/g,m=>{_a_stash.push(m);return `\x00A${_a_stash.length-1}\x00`;});
- s=s.replace(/\[([^\]]+)\]\((https?:\/\/[^\)]+)\)/g,(_,label,url)=>`${esc(label)}`);
+ s=s.replace(/\[([^\]]+)\]\(((?:https?|file):\/\/[^\)]+)\)/g,(_,label,url)=>`${esc(label)}`);
s=s.replace(/\x00A(\d+)\x00/g,(_,i)=>_a_stash[+i]);
// Restore raw only after markdown rewrites so literal preformatted
// content stays placeholder-protected, then let the sanitizer normalize tags.
@@ -2865,6 +2865,18 @@ function renderMd(raw){
function _safeAttrValue(v){
return String(v||'').replace(/"/g,'"').replace(/'/g,"'").replace(/&/g,'&').trim();
}
+ function _markdownHref(raw){
+ const href=String(raw||'').replace(/"/g,'%22');
+ if(/^file:\/\//i.test(href)){
+ try{
+ const path=decodeURIComponent(href.replace(/^file:\/\//i,''));
+ return 'api/media?path='+encodeURIComponent(path)+'&inline=1';
+ }catch(_){
+ return 'api/media?path='+encodeURIComponent(href.replace(/^file:\/\//i,''))+'&inline=1';
+ }
+ }
+ return href;
+ }
function _isSafeUrl(v, img){
const raw=_safeAttrValue(v);
const compact=raw.replace(/[\u0000-\u001f\u007f\s]+/g,'').toLowerCase();
diff --git a/tests/test_issue470.py b/tests/test_issue470.py
index b6f156d7..78893075 100644
--- a/tests/test_issue470.py
+++ b/tests/test_issue470.py
@@ -33,6 +33,12 @@ def _make_link(url, label):
return f'{esc(label)}'
+def markdown_href(url):
+ if url.lower().startswith("file://"):
+ return "api/media?path=" + __import__("urllib.parse").parse.quote(url[7:], safe="") + "&inline=1"
+ return url
+
+
# Minimal Python mirror of the FIXED renderMd() — enough to test link behaviour.
# Mirrors the stash-based approach introduced by the fix.
@@ -48,9 +54,9 @@ def render_links_only(text):
link_stash = []
def stash_link(m):
label, url = m.group(1), m.group(2)
- link_stash.append(f'{esc(label)}')
+ link_stash.append(f'{esc(label)}')
return f'\x00L{len(link_stash)-1}\x00'
- s = re.sub(r'\[([^\]]+)\]\((https?://[^\)]+)\)', stash_link, s)
+ s = re.sub(r'\[([^\]]+)\]\(((?:https?|file)://[^\)]+)\)', stash_link, s)
# Autolink bare URLs (should NOT match inside already-stashed placeholders)
def autolink(m):
@@ -83,9 +89,9 @@ def render_table_with_links(md):
stash = []
def stash_fn(m):
lb, u = m.group(1), m.group(2)
- stash.append(f'{esc(lb)}')
+ stash.append(f'{esc(lb)}')
return f'\x00L{len(stash)-1}\x00'
- t = re.sub(r'\[([^\]]+)\]\((https?://[^\)]+)\)', stash_fn, t)
+ t = re.sub(r'\[([^\]]+)\]\(((?:https?|file)://[^\)]+)\)', stash_fn, t)
# autolink remaining bare URLs
def autolink(m):
url = m.group(1)
@@ -170,6 +176,17 @@ def test_labeled_link_renders_as_single_anchor():
assert f']({url})' not in result
+def test_labeled_file_link_renders_as_single_anchor():
+ """A labeled local file link must survive the settled render path."""
+ url = 'file:///Users/agent/Documents/Obsidian/Meal-Prep/halal-cart.html'
+ md = f'[Halal Cart Chicken]({url})'
+ result = render_links_only(md)
+ assert result.count(' tag, got: {result}"
+ assert 'href="api/media?path=%2FUsers%2Fagent%2FDocuments%2FObsidian%2FMeal-Prep%2Fhalal-cart.html&inline=1"' in result
+ assert 'Halal Cart Chicken' in result
+ assert '[Halal Cart Chicken]' not in result
+
+
def test_href_not_html_escaped():
"""URLs with & must appear as literal & in href, not &."""
url = 'https://example.com/search?q=foo&bar=baz'
@@ -261,6 +278,13 @@ def test_js_source_sanitizes_quotes_in_href():
"URL placed in href should have double-quotes percent-encoded via .replace to %22"
)
+
+def test_js_source_rewrites_file_links_to_media_endpoint():
+ """Browser pages cannot reliably navigate to file://, so renderMd must use /api/media."""
+ assert "function _markdownHref" in UI_JS
+ assert "api/media?path=" in UI_JS
+ assert "file:\\/\\/" in UI_JS
+
# ── Code-inside-bold tests (pre-existing bug, fixed in same PR) ───────────────
def test_js_inlinemd_stashes_code_before_bold():
diff --git a/tests/test_streaming_markdown.py b/tests/test_streaming_markdown.py
index 777e0428..4506c32e 100644
--- a/tests/test_streaming_markdown.py
+++ b/tests/test_streaming_markdown.py
@@ -554,7 +554,8 @@ class TestSmdUrlSchemeSanitization:
def test_sanitize_uses_scheme_allowlist(self):
# The allowlist regex must permit the safe schemes that the legacy
# renderMd path emitted (http/https + relative/anchor paths + mailto/tel)
- # and reject everything else — including javascript:, data:, vbscript:, file:.
+ # and reject dangerous executable schemes. file:// anchors are rewritten
+ # to api/media before click time rather than allowed through raw.
assert "_SMD_SAFE_URL_RE" in MESSAGES_JS, (
"Expected a _SMD_SAFE_URL_RE regex defining the safe-scheme allowlist"
)
@@ -565,11 +566,17 @@ class TestSmdUrlSchemeSanitization:
pattern = m.group(1)
# Must mention https? and must NOT mention javascript/vbscript/data
assert "https?" in pattern, "allowlist must permit https?:"
+ assert "file:" not in pattern, "raw file: anchors must be rewritten, not allowed through"
+ assert "api" in MESSAGES_JS, "allowlist must permit rewritten api/media anchors"
for bad in ("javascript", "vbscript", "data:"):
assert bad not in pattern, (
f"allowlist must NOT mention {bad!r} — schemes are denied by default"
)
+ def test_file_anchor_rewrite_helper_exists(self):
+ assert "_smdFileHref" in MESSAGES_JS
+ assert "api/media?path=" in MESSAGES_JS
+
def test_sanitize_called_after_smd_write(self):
# _smdWrite must invoke _sanitizeSmdLinks on assistantBody after feeding the parser,
# so anchors/images created mid-stream get their javascript:/data:/vbscript: