ultralytics-actions 0.0.45__py3-none-any.whl → 0.0.47__py3-none-any.whl

actions/__init__.py

@@ -22,4 +22,4 @@
 #     ├── test_summarize_pr.py
 #     └── ...
 
-__version__ = "0.0.45"
+__version__ = "0.0.47"

actions/utils/common_utils.py

@@ -23,22 +23,8 @@ REQUESTS_HEADERS = {
     "Origin": "https://www.google.com/",
 }
 
-
-def remove_html_comments(body: str) -> str:
-    """Removes HTML comments from a string using regex pattern matching."""
-    return re.sub(r"<!--.*?-->", "", body, flags=re.DOTALL).strip()
-
-
-def clean_url(url):
-    """Remove extra characters from URL strings."""
-    for _ in range(3):
-        url = str(url).strip('"').strip("'").rstrip(".,:;!?`\\").replace(".git@main", "").replace("git+", "")
-    return url
-
-
-def is_url(url, session=None, check=True, max_attempts=3, timeout=2):
-    """Check if string is URL and optionally verify it exists."""
-    allow_list = (
+URL_IGNORE_LIST = frozenset(
+    {
         "localhost",
         "127.0.0",
         ":5000",
@@ -56,10 +42,39 @@ def is_url(url, session=None, check=True, max_attempts=3, timeout=2):
         "twitter.com",
         "x.com",
         "storage.googleapis.com",  # private GCS buckets
-    )
+    }
+)
+
+URL_PATTERN = re.compile(
+    r"\[([^]]+)]\(([^)]+)\)"  # Matches Markdown links [text](url)
+    r"|"
+    r"("  # Start capturing group for plaintext URLs
+    r"(?:https?://)?"  # Optional http:// or https://
+    r"(?:www\.)?"  # Optional www.
+    r"(?:[\w.-]+)?"  # Optional domain name and subdomains
+    r"\.[a-zA-Z]{2,}"  # TLD
+    r"(?:/[^\s\"')\]]*)?"  # Optional path
+    r")"
+)
+
+
+def remove_html_comments(body: str) -> str:
+    """Removes HTML comments from a string using regex pattern matching."""
+    return re.sub(r"<!--.*?-->", "", body, flags=re.DOTALL).strip()
+
+
+def clean_url(url):
+    """Remove extra characters from URL strings."""
+    for _ in range(3):
+        url = str(url).strip('"').strip("'").rstrip(".,:;!?`\\").replace(".git@main", "").replace("git+", "")
+    return url
+
+
+def is_url(url, session=None, check=True, max_attempts=3, timeout=2):
+    """Check if string is URL and optionally verify it exists."""
     try:
         # Check allow list
-        if any(x in url for x in allow_list):
+        if any(x in url for x in URL_IGNORE_LIST):
             return True
 
         # Check structure
@@ -69,7 +84,7 @@ def is_url(url, session=None, check=True, max_attempts=3, timeout=2):
             return False
 
         if check:
-            requester = session if session else requests
+            requester = session or requests
             bad_codes = {404, 410, 500, 502, 503, 504}
             kwargs = {"timeout": timeout, "allow_redirects": True}
             if not session:
@@ -94,26 +109,13 @@ def is_url(url, session=None, check=True, max_attempts=3, timeout=2):
 
 def check_links_in_string(text, verbose=True, return_bad=False):
     """Process a given text, find unique URLs within it, and check for any 404 errors."""
-    pattern = (
-        r"\[([^\]]+)\]\(([^)]+)\)"  # Matches Markdown links [text](url)
-        r"|"
-        r"("  # Start capturing group for plaintext URLs
-        r"(?:https?://)?"  # Optional http:// or https://
-        r"(?:www\.)?"  # Optional www.
-        r"(?:[\w.-]+)?"  # Optional domain name and subdomains
-        r"\.[a-zA-Z]{2,}"  # TLD
-        r"(?:/[^\s\"')\]]*)?"  # Optional path
-        r")"
-    )
-    # all_urls.extend([url for url in match if url and parse.urlparse(url).scheme])
     all_urls = []
-    for md_text, md_url, plain_url in re.findall(pattern, text):
+    for md_text, md_url, plain_url in URL_PATTERN.findall(text):
         url = md_url or plain_url
         if url and parse.urlparse(url).scheme:
             all_urls.append(url)
 
     urls = set(map(clean_url, all_urls))  # remove extra characters and make unique
-    # bad_urls = [x for x in urls if not is_url(x, check=True)]  # single-thread
     with requests.Session() as session, ThreadPoolExecutor(max_workers=16) as executor:
         session.headers.update(REQUESTS_HEADERS)
         bad_urls = [url for url, valid in zip(urls, executor.map(lambda x: not is_url(x, session), urls)) if valid]
@@ -126,4 +128,8 @@ def check_links_in_string(text, verbose=True, return_bad=False):
 
 
 if __name__ == "__main__":
-    print(is_url("https://ultralytics.com/images/bus.jpg"))
+    url = "https://ultralytics.com/images/bus.jpg"
+    string = f"This is a string with a [Markdown link]({url}) inside it."
+
+    print(f"is_url(): {is_url(url)}")
+    print(f"check_links_in_string(): {check_links_in_string(string)}")

{ultralytics_actions-0.0.45.dist-info → ultralytics_actions-0.0.47.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics-actions
-Version: 0.0.45
+Version: 0.0.47
 Summary: Ultralytics Actions for GitHub automation and PR management.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{ultralytics_actions-0.0.45.dist-info → ultralytics_actions-0.0.47.dist-info}/RECORD

@@ -1,15 +1,15 @@
-actions/__init__.py,sha256=t0J0QOMCfEFOvtGGcdegXhIj1oEh6uO71pH7Wmr1_XE,742
+actions/__init__.py,sha256=A3KLreATd7sSdPwF5hJy-yAjrcE0rtjVdaXz_g0_Yg0,742
 actions/first_interaction.py,sha256=Oosw3GlXObF4RxYJG8haIjKXSV4MAx_uPXfMdRKY5qA,17851
 actions/summarize_pr.py,sha256=Pfcm6ArfZfcMme48FcCGNmMwrFFlsG0czifhXHDKAlY,11166
 actions/summarize_release.py,sha256=2D1IIeS4xrQNEJER3HItm5u9XvTL8hwGX_jWD2S8q1Y,8455
 actions/update_markdown_code_blocks.py,sha256=DN6rrDw2VHXUTetrrg1SHlYDco9iaGOfQBKFORqbCBI,6362
 actions/utils/__init__.py,sha256=WStdEAYROVnF0nubEOmrFLrejkRiMXIefA5O1ckfcFs,476
-actions/utils/common_utils.py,sha256=eqrRyN1zMY66vADwKsKE0RHY7v_d_Spq5FHKchDl0h4,4836
+actions/utils/common_utils.py,sha256=8Au56sY6toCv76WJ-8jbmW94BgE_2VXevQbt3XKDyVc,4826
 actions/utils/github_utils.py,sha256=0h0Hz2tgUta61Ymn9YggRXBZ7aZdF5krKnX7Tj9jqRU,7068
 actions/utils/openai_utils.py,sha256=U7DjxTdFGdhmWSE4_KIg1yPQdtrfG4GkbNZCgMw4_1Q,1822
-ultralytics_actions-0.0.45.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-ultralytics_actions-0.0.45.dist-info/METADATA,sha256=hNeerqNDFs7VnlPCK1kffEFz3MP0enS4uToxwRLIsqc,10561
-ultralytics_actions-0.0.45.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ultralytics_actions-0.0.45.dist-info/entry_points.txt,sha256=GowvOFplj0C7JmsjbKcbpgLpdf2r921pcaOQkAHWZRA,378
-ultralytics_actions-0.0.45.dist-info/top_level.txt,sha256=5apM5x80QlJcGbACn1v3fkmIuL1-XQCKcItJre7w7Tw,8
-ultralytics_actions-0.0.45.dist-info/RECORD,,
+ultralytics_actions-0.0.47.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+ultralytics_actions-0.0.47.dist-info/METADATA,sha256=xcYxNklkUgrpYsvP5HkQRl21H_vIiQsQWmLW_YxRjeo,10561
+ultralytics_actions-0.0.47.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ultralytics_actions-0.0.47.dist-info/entry_points.txt,sha256=GowvOFplj0C7JmsjbKcbpgLpdf2r921pcaOQkAHWZRA,378
+ultralytics_actions-0.0.47.dist-info/top_level.txt,sha256=5apM5x80QlJcGbACn1v3fkmIuL1-XQCKcItJre7w7Tw,8
+ultralytics_actions-0.0.47.dist-info/RECORD,,