Merge pull request #16 from NoPlagiarism/domain_constant

NoPlagiarism · Dec 10, 2023 · 44963b2 · 44963b2
2 parents 405cc57 + 01d73ad
commit 44963b2
Show file tree

Hide file tree

Showing 4 changed files with 111 additions and 77 deletions.
diff --git a/.github/workflows/parse.yml b/.github/workflows/parse.yml
@@ -27,7 +27,7 @@ jobs:
     - name: Set up Python 3.9
       uses: actions/setup-python@v3
       with:
-        python-version: "3.9"
+        python-version: "3.12"
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

diff --git a/parser/consts.py b/parser/consts.py
@@ -31,6 +31,20 @@ class Retries:
     trace_errors = get_bool_from_env("FIL_TRACE_ERRORS", True)
 
 
+class Regex:
+    # https://stackoverflow.com/questions/7930751/regexp-for-subdomain
+    # TODO: Bug found. Failed on wgl.frail.duckdns.org
+    DOMAIN_BASE_REGEX = r"(?:[a-zA-Z0-9](?:[-a-zA-Z0-9]{0,61}[a-zA-Z0-9])?\.)?(?:[a-zA-Z0-9]{1,2}(?:[-a-zA-Z0-9]{0,252}[a-zA-Z0-9])?)"
+    # (?:[a-zA-Z0-9](?:[-a-zA-Z0-9]{0,61}[a-zA-Z0-9])?\.)?(?:[a-zA-Z0-9]{1,2}(?:[-a-zA-Z0-9]{0,252}[a-zA-Z0-9])?)\.(?:[a-zA-Z]{2,63})
+    DOMAIN = DOMAIN_BASE_REGEX + r"\.(?:[a-zA-Z]{2,63})"
+    # (?:[a-zA-Z0-9](?:[-a-zA-Z0-9]{0,61}[a-zA-Z0-9])?\.)?(?:[a-zA-Z0-9]{1,2}(?:[-a-zA-Z0-9]{0,252}[a-zA-Z0-9])?)\.onion
+    DOMAIN_ONION = DOMAIN_BASE_REGEX + r"\.onion"
+    # (?:[a-zA-Z0-9](?:[-a-zA-Z0-9]{0,61}[a-zA-Z0-9])?\.)?(?:[a-zA-Z0-9]{1,2}(?:[-a-zA-Z0-9]{0,252}[a-zA-Z0-9])?)\.i2p
+    DOMAIN_I2P = DOMAIN_BASE_REGEX + r"\.i2p"
+    # (?:[a-zA-Z0-9](?:[-a-zA-Z0-9]{0,61}[a-zA-Z0-9])?\.)?(?:[a-zA-Z0-9]{1,2}(?:[-a-zA-Z0-9]{0,252}[a-zA-Z0-9])?)\.loki
+    DOMAIN_LOKI = DOMAIN_BASE_REGEX + r"\.loki"
+
+
 INST_FOLDER = "instances"
 
 LOG_DOMAIN_FROM_HEADERS = get_bool_from_env("FIL_LOG_DOMAIN_FROM_HEADERS", True)