From fe38c428c2612bfea4e9d99891b82dca23125ca6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Petr=20=C5=A0pl=C3=ADchal?= <psplicha@redhat.com>
Date: Tue, 23 Jan 2024 16:19:47 +0100
Subject: [PATCH] Support escaping `|` and `&` in `utils.filter()`

Add support for escaping boolean operators using the back slash
character `\` to allow for example regular expression grouping.
---
 fmf/utils.py             | 17 ++++++++++++++---
 tests/unit/test_utils.py | 27 +++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/fmf/utils.py b/fmf/utils.py
index 5e269aef..078bc38e 100644
--- a/fmf/utils.py
+++ b/fmf/utils.py
@@ -222,6 +222,13 @@ def filter(filter, data, sensitive=True, regexp=False, name=None):
         tag: Tier1 | tag: Tier2 | tag: Tier3
         category: Sanity, Security & tag: -destructive
 
+    Use the back slash character ``\\`` to escape the boolean
+    operators if you need to specify them as part of the filter
+    expressions::
+
+        tag: Tier(1\\|2)
+        text: Q\\&A
+
     Note that multiple comma-separated values can be used as a syntactic
     sugar to shorten the filter notation::
 
@@ -322,7 +329,10 @@ def check_clause(clause):
         # E.g. clause = 'tag: A, B & tag: C & tag: -D'
         # Split into individual literals by dimension
         literals = dict()
-        for literal in re.split(r"\s*&\s*", clause):
+
+        for literal in re.split(r"\s*(?<!\\)&\s*", clause):
+            # Remove the possible escaping
+            literal = re.sub(r"\\&", "&", literal)
             # E.g. literal = 'tag: A, B'
             # Check whether the literal matches dimension:value format
             matched = re.match(r"^([^:]*)\s*:\s*(.*)$", literal)
@@ -364,8 +374,9 @@ def check_clause(clause):
         data = lowered
 
     # At least one clause must be true
-    return any([check_clause(clause)
-                for clause in re.split(r"\s*\|\s*", filter)])
+    return any([
+        check_clause(re.sub(r"\\\|", "|", clause))
+        for clause in re.split(r"\s*(?<!\\)\|\s*", filter)])
 
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #  Logging
diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py
index 4a8fc866..049295b8 100644
--- a/tests/unit/test_utils.py
+++ b/tests/unit/test_utils.py
@@ -1,5 +1,6 @@
 import os
 import queue
+import re
 import shutil
 import threading
 import time
@@ -118,6 +119,32 @@ def test_unicode(self):
         assert filter("tag: ťip", {"tag": ["ťip"]}) is True
         assert filter("tag: -ťop", {"tag": ["ťip"]}) is True
 
+    def test_escape_or(self):
+        """ Escaping the | operator """
+
+        # Escaped
+        assert filter(r"category: (Sanity\|Security)", self.data, regexp=True) is True
+        assert filter(r"tag: Tier(1\|2)", self.data, regexp=True) is True
+
+        # Unescaped
+        with pytest.raises(re.error):
+            assert filter(r"category: (Sanity|Security)", self.data, regexp=True) is True
+        with pytest.raises(re.error):
+            assert filter(r"tag: Tier(1|2)", self.data, regexp=True) is True
+
+    def test_escape_and(self):
+        """ Escaping the & operator """
+        self.data["text"] = "Q&A"
+
+        # Escaped
+        assert filter(r"text: Q\&A", self.data) is True
+        assert filter(r"text: Q\&A", self.data) is True
+
+        # Unescaped
+        assert filter(r"text: Q&A", self.data, name="foo") is False
+        with pytest.raises(utils.FilterError):
+            filter(r"text: foo & bar", self.data)
+
 
 class TestPluralize:
     """ Function pluralize() """