Merge pull request github#8812 from RasmusWL/stdlib-FileSystemAccess-improvement

Python: Minor Stdlib file system access improvement

Author: RasmusWL

python/ql/lib/semmle/python/frameworks/Stdlib.qll

@@ -959,13 +959,18 @@ private module StdlibPrivate {
     }
   }
 
-  /** A call to `os.path.samefile` will raise an exception if an `os.stat()` call on either pathname fails. */
+  /**
+   * A call to `os.path.samefile` will raise an exception if an `os.stat()` call on either pathname fails.
+   *
+   * See https://docs.python.org/3.10/library/os.path.html#os.path.samefile
+   */
   private class OsPathSamefileCall extends FileSystemAccess::Range, DataFlow::CallCfgNode {
     OsPathSamefileCall() { this = OS::path().getMember("samefile").getACall() }
 
     override DataFlow::Node getAPathArgument() {
       result in [
-          this.getArg(0), this.getArgByName("path1"), this.getArg(1), this.getArgByName("path2")
+          // note that the f1/f2 names doesn't match the documentation, but is what actually works (tested on 3.8.10)
+          this.getArg(0), this.getArgByName("f1"), this.getArg(1), this.getArgByName("f2")
         ]
     }
   }
@@ -2534,6 +2539,56 @@ private module StdlibPrivate {
     PathLibOpenCall() { attrbuteName = "open" }
   }
 
+  /**
+   * A call to the `link_to`, `hardlink_to`, or `symlink_to` method on a `pathlib.Path` instance.
+   *
+   * See
+   * - https://docs.python.org/3/library/pathlib.html#pathlib.Path.link_to
+   * - https://docs.python.org/3/library/pathlib.html#pathlib.Path.hardlink_to
+   * - https://docs.python.org/3/library/pathlib.html#pathlib.Path.symlink_to
+   */
+  private class PathLibLinkToCall extends PathlibFileAccess, API::CallNode {
+    PathLibLinkToCall() { attrbuteName in ["link_to", "hardlink_to", "symlink_to"] }
+
+    override DataFlow::Node getAPathArgument() {
+      result = super.getAPathArgument()
+      or
+      result = this.getParameter(0, "target").getARhs()
+    }
+  }
+
+  /**
+   * A call to the `replace` or `rename` method on a `pathlib.Path` instance.
+   *
+   * See
+   * - https://docs.python.org/3/library/pathlib.html#pathlib.Path.replace
+   * - https://docs.python.org/3/library/pathlib.html#pathlib.Path.rename
+   */
+  private class PathLibReplaceCall extends PathlibFileAccess, API::CallNode {
+    PathLibReplaceCall() { attrbuteName in ["replace", "rename"] }
+
+    override DataFlow::Node getAPathArgument() {
+      result = super.getAPathArgument()
+      or
+      result = this.getParameter(0, "target").getARhs()
+    }
+  }
+
+  /**
+   * A call to the `samefile` method on a `pathlib.Path` instance.
+   *
+   * See https://docs.python.org/3/library/pathlib.html#pathlib.Path.samefile
+   */
+  private class PathLibSameFileCall extends PathlibFileAccess, API::CallNode {
+    PathLibSameFileCall() { attrbuteName = "samefile" }
+
+    override DataFlow::Node getAPathArgument() {
+      result = super.getAPathArgument()
+      or
+      result = this.getParameter(0, "other_path").getARhs()
+    }
+  }
+
   /** An additional taint steps for objects of type `pathlib.Path` */
   private class PathlibPathTaintStep extends TaintTracking::AdditionalTaintStep {
     override predicate step(DataFlow::Node nodeFrom, DataFlow::Node nodeTo) {

python/ql/test/library-tests/frameworks/stdlib-py3/FileSystemAccess.py

@@ -21,3 +21,15 @@
 
 wb = p.write_bytes
 wb(b"hello")  # $ getAPathArgument=p fileWriteData=b"hello"
+
+p.link_to("target") # $ getAPathArgument=p getAPathArgument="target"
+p.link_to(target="target") # $ getAPathArgument=p getAPathArgument="target"
+
+p.samefile("other_path") # $ getAPathArgument=p getAPathArgument="other_path"
+p.samefile(other_path="other_path") # $ getAPathArgument=p getAPathArgument="other_path"
+
+p.rename("target") # $ getAPathArgument=p getAPathArgument="target"
+p.rename(target="target") # $ getAPathArgument=p getAPathArgument="target"
+
+p.replace("target") # $ getAPathArgument=p getAPathArgument="target"
+p.replace(target="target") # $ getAPathArgument=p getAPathArgument="target"

python/ql/test/library-tests/frameworks/stdlib/FileSystemAccess.py

@@ -48,6 +48,9 @@ def through_function(open_file):
 os.path.ismount("path")  # $ getAPathArgument="path"
 os.path.ismount(path="path")  # $ getAPathArgument="path"
 
+os.path.samefile("f1", "f2")  # $ getAPathArgument="f1" getAPathArgument="f2"
+os.path.samefile(f1="f1", f2="f2")  # $ getAPathArgument="f1" getAPathArgument="f2"
+
 # actual os.path implementations
 import posixpath
 import ntpath
@@ -269,4 +272,4 @@ def test_fspath():
 shutil.copystat(src="src", dst="dst") # $ getAPathArgument="src" getAPathArgument="dst"
 
 shutil.disk_usage("path") # $ getAPathArgument="path"
-shutil.disk_usage(path="path") # $ getAPathArgument="path"
+shutil.disk_usage(path="path") # $ getAPathArgument="path"