Fix HTTPX package crash for some values of "article" parameter in the interface (#7389)

Author: YuryYakhno

.changeset/eight-candies-stick.md

@@ -0,0 +1,5 @@
+---
+"gradio": patch
+---
+
+fix:Fix HTTPX package crash for some values of "article" parameter in the interface

gradio/interface.py

@@ -134,7 +134,7 @@ def __init__(
             live: Whether the interface should automatically rerun if any of the inputs change.
             title: A title for the interface; if provided, appears above the input and output components in large font. Also used as the tab title when opened in a browser window.
             description: A description for the interface; if provided, appears above the input and output components and beneath the title in regular font. Accepts Markdown and HTML content.
-            article: An expanded article explaining the interface; if provided, appears below the input and output components in regular font. Accepts Markdown and HTML content.
+            article: An expanded article explaining the interface; if provided, appears below the input and output components in regular font. Accepts Markdown and HTML content. If it is an HTTP(S) link to a downloadable remote file, the content of this file is displayed.
             thumbnail: String path or url to image to use as display image when the web demo is shared on social media.
             theme: A Theme object or a string representing a theme. If a string, will look for a built-in theme with that name (e.g. "soft" or "default"), or will attempt to load a theme from the Hugging Face Hub (e.g. "gradio/monochrome"). If None, will use the Default theme.
             css: Custom css as a string or path to a css file. This css will be included in the demo webpage.
@@ -295,7 +295,7 @@ def __init__(
         self.simple_description = utils.remove_html_tags(description)
         self.description = description
         if article is not None:
-            article = utils.readme_to_html(article)
+            article = utils.download_if_url(article)
         self.article = article
 
         self.thumbnail = thumbnail

gradio/utils.py

@@ -286,13 +286,24 @@ def is_zero_gpu_space() -> bool:
     return os.getenv("SPACES_ZERO_GPU") == "true"
 
 
-def readme_to_html(article: str) -> str:
+def download_if_url(article: str) -> str:
+    try:
+        result = urllib.parse.urlparse(article)
+        is_url = all([result.scheme, result.netloc, result.path])
+        is_url = is_url and result.scheme in ["http", "https"]
+    except ValueError:
+        is_url = False
+
+    if not is_url:
+        return article
+
     try:
         response = httpx.get(article, timeout=3)
         if response.status_code == httpx.codes.OK:  # pylint: disable=no-member
             article = response.text
     except (httpx.InvalidURL, httpx.RequestError):
         pass
+
     return article
 
 

test/test_utils.py

@@ -27,7 +27,7 @@
     is_in_or_equal,
     is_special_typed_parameter,
     kaggle_check,
-    readme_to_html,
+    download_if_url,
     sagemaker_check,
     sanitize_list_for_csv,
     sanitize_value_for_csv,
@@ -54,13 +54,34 @@ def test_ipython_check_no_ipython(self, mock_get_ipython):
         mock_get_ipython.return_value = None
         assert ipython_check() is False
 
-    @patch("httpx.get")
-    def test_readme_to_html_doesnt_crash_on_connection_error(self, mock_get):
-        mock_get.side_effect = httpx.ConnectError("Connection error")
-        readme_to_html("placeholder")
-
-    def test_readme_to_html_correct_parse(self):
-        readme_to_html("https://github.com/gradio-app/gradio/blob/master/README.md")
+    def test_download_if_url_doesnt_crash_on_connection_error(self):
+        in_article = "placeholder"
+        out_article = download_if_url(in_article)
+        assert out_article == in_article
+
+        # non-printable characters are not allowed in URL address
+        in_article = "text\twith\rnon-printable\nASCII\x00characters"
+        out_article = download_if_url(in_article)
+        assert out_article == in_article
+
+        # only files with HTTP(S) URL can be downloaded
+        in_article = "ftp://localhost/tmp/index.html"
+        out_article = download_if_url(in_article)
+        assert out_article == in_article
+
+        in_article = "file:///C:/tmp/index.html"
+        out_article = download_if_url(in_article)
+        assert out_article == in_article
+
+        # this address will raise ValueError during parsing
+        in_article = "https://[unmatched_bracket#?:@/index.html"
+        out_article = download_if_url(in_article)
+        assert out_article == in_article
+
+    def test_download_if_url_correct_parse(self):
+        in_article = "https://github.com/gradio-app/gradio/blob/master/README.md"
+        out_article = download_if_url(in_article)
+        assert out_article != in_article
 
     def test_sagemaker_check_false(self):
         assert not sagemaker_check()