From ca284b3fc9f701c1f2d60098709c75a37f605291 Mon Sep 17 00:00:00 2001
From: Jakub Kadlcik <frostyx@email.cz>
Date: Sep 12 2022 10:29:07 +0000
Subject: [PATCH 1/2] backend: decode special characters from URLs


Otherwise we will flood the database with values like
%40spacewalkproject. Also, ignore double encoded special characters.

---

diff --git a/backend/copr_backend/hitcounter.py b/backend/copr_backend/hitcounter.py
index 2a2e032..0222462 100644
--- a/backend/copr_backend/hitcounter.py
+++ b/backend/copr_backend/hitcounter.py
@@ -5,6 +5,7 @@ Shared logic for hitcounter scripts
 import os
 import re
 from datetime import datetime
+from requests.utils import unquote
 from copr_common.request import SafeRequest
 from copr_backend.helpers import BackendConfigReader
 
@@ -118,6 +119,21 @@ def get_hit_data(accesses, log):
                       url, bot.group(1))
             continue
 
+        # Convert encoded characters from their %40 values back to @.
+        url = unquote(url)
+
+        # I don't know how or why but occasionally there is an URL that is
+        # encoded twice (%2540oamg -> %40oamg - > @oamg), and yet its status
+        # code is 200. AFAIK these appear only for EPEL-7 chroots and their
+        # User-Agent is something like urlgrabber/3.10%20yum/3.4.3
+        # I wasn't able to reproduce such accesses, and we decided to not count
+        # them
+        if url != unquote(url):
+            log.warning("Skipping: %s (double encoded URL, user-agent: '%s', "
+                        "status: %s)", access["cs-uri-stem"],
+                        access["cs(User-Agent)"], access["sc-status"])
+            continue
+
         # We don't want to count every accessed URL, only those pointing to
         # RPM files and repo file
         key_strings = url_to_key_strings(url)

From 79e69073a5789470ca2aa0bc17a94dd60936b04c Mon Sep 17 00:00:00 2001
From: Jakub Kadlcik <frostyx@email.cz>
Date: Sep 12 2022 10:29:14 +0000
Subject: [PATCH 2/2] backend: ignore downloaded SRPM files


Otherwise we count each SRPM that DistGit downloads from backend, and
that inflates the stats of project RPMs downloaded.

We could specify User-Agent on DistGit and ignore it in the hitcounter
script but we agreed that we can ignore SRPM downloads altogether.

---

diff --git a/backend/copr_backend/hitcounter.py b/backend/copr_backend/hitcounter.py
index 0222462..bfe9341 100644
--- a/backend/copr_backend/hitcounter.py
+++ b/backend/copr_backend/hitcounter.py
@@ -141,6 +141,12 @@ def get_hit_data(accesses, log):
             log.debug("Skipping: %s", url)
             continue
 
+        if any(x for x in key_strings
+               if x.startswith("chroot_rpms_dl_stat|")
+               and x.endswith("|srpm-builds")):
+            log.debug("Skipping %s (SRPM build)", url)
+            continue
+
         log.debug("Processing: %s", url)
 
         # When counting RPM access, we want to iterate both project hits and