Python: Regexp: Handle repetions {n} (with no ,)

yoff · yoff · commit b56545b236f5 · 2020-05-18T14:44:11.000+02:00
diff --git a/python/ql/src/semmle/python/regex.qll b/python/ql/src/semmle/python/regex.qll
@@ -472,8 +472,12 @@ abstract class RegexString extends Expr {
             this.getChar(endin) = "}" and
             end > start and
             exists(string multiples | multiples = this.getText().substring(start + 1, endin) |
+                multiples.regexpMatch("0+") and maybe_empty = true
+                or
                 multiples.regexpMatch("0*,[0-9]*") and maybe_empty = true
                 or
+                multiples.regexpMatch("0*[1-9][0-9]*") and maybe_empty = false
+                or
                 multiples.regexpMatch("0*[1-9][0-9]*,[0-9]*") and maybe_empty = false
             ) and
             not exists(int mid |
diff --git a/python/ql/test/query-tests/Expressions/Regex/DuplicateCharacterInSet.expected b/python/ql/test/query-tests/Expressions/Regex/DuplicateCharacterInSet.expected
@@ -1,3 +1,3 @@
-| test.py:41:12:41:18 | Str | This regular expression includes duplicate character 'A' in a set of characters. |
-| test.py:42:12:42:19 | Str | This regular expression includes duplicate character '0' in a set of characters. |
-| test.py:43:12:43:21 | Str | This regular expression includes duplicate character '-' in a set of characters. |
+| test.py:44:12:44:18 | Str | This regular expression includes duplicate character 'A' in a set of characters. |
+| test.py:45:12:45:19 | Str | This regular expression includes duplicate character '0' in a set of characters. |
+| test.py:46:12:46:21 | Str | This regular expression includes duplicate character '-' in a set of characters. |
diff --git a/python/ql/test/query-tests/Expressions/Regex/UnmatchableCaret.expected b/python/ql/test/query-tests/Expressions/Regex/UnmatchableCaret.expected
@@ -1,4 +1,4 @@
 | test.py:4:12:4:19 | Str | This regular expression includes an unmatchable caret at offset 1. |
 | test.py:5:12:5:23 | Str | This regular expression includes an unmatchable caret at offset 5. |
 | test.py:6:12:6:21 | Str | This regular expression includes an unmatchable caret at offset 2. |
-| test.py:74:12:74:27 | Str | This regular expression includes an unmatchable caret at offset 8. |
+| test.py:77:12:77:27 | Str | This regular expression includes an unmatchable caret at offset 8. |
diff --git a/python/ql/test/query-tests/Expressions/Regex/UnmatchableDollar.expected b/python/ql/test/query-tests/Expressions/Regex/UnmatchableDollar.expected
@@ -1,4 +1,4 @@
 | test.py:29:12:29:19 | Str | This regular expression includes an unmatchable dollar at offset 3. |
 | test.py:30:12:30:23 | Str | This regular expression includes an unmatchable dollar at offset 3. |
 | test.py:31:12:31:20 | Str | This regular expression includes an unmatchable dollar at offset 2. |
-| test.py:75:12:75:26 | Str | This regular expression includes an unmatchable dollar at offset 3. |
+| test.py:78:12:78:26 | Str | This regular expression includes an unmatchable dollar at offset 3. |
diff --git a/python/ql/test/query-tests/Expressions/Regex/test.py b/python/ql/test/query-tests/Expressions/Regex/test.py
@@ -35,6 +35,9 @@
 re.compile(b"\$  ")
 re.compile(b"abc$(?m)")
 re.compile(b"abc$()")
+re.compile(b"((a$)|b)*")
+re.compile(b"((a$)|b){4}")
+re.compile(b"((a$).*)")
 
 
 #Duplicate character in set
