From 91477f0a125d7b48ca60149c83d8d25cef7403d7 Mon Sep 17 00:00:00 2001
From: Daniel Hahler <git@thequod.de>
Date: Thu, 8 Nov 2018 00:22:27 +0100
Subject: [PATCH] collection: cleanup/centralize keepduplicates handling

---
 src/_pytest/main.py        | 24 ++++++++++++------------
 src/_pytest/python.py      | 11 +----------
 testing/test_collection.py |  8 ++++++++
 3 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/src/_pytest/main.py b/src/_pytest/main.py
index 1de5f656fd0..9f629548609 100644
--- a/src/_pytest/main.py
+++ b/src/_pytest/main.py
@@ -474,8 +474,18 @@ def collect(self):
             arg = "::".join(map(str, initialpart))
             self.trace("processing argument", arg)
             self.trace.root.indent += 1
+
+            keepduplicates = self.config.getoption("keepduplicates")
+            if not keepduplicates:
+                duplicate_paths = self.config.pluginmanager._duplicatepaths
+
             try:
                 for x in self._collect(arg):
+                    if not keepduplicates:
+                        dupe_key = (type(x), x.fspath)
+                        if dupe_key in duplicate_paths:
+                            continue
+                        duplicate_paths.add(dupe_key)
                     yield x
             except NoMatch:
                 # we are inside a make_report hook so
@@ -503,7 +513,7 @@ def _collect(self, arg):
                     pkginit = parent.join("__init__.py")
                     if pkginit.isfile():
                         if pkginit not in self._node_cache:
-                            col = self._collectfile(pkginit, handle_dupes=False)
+                            col = self._collectfile(pkginit)
                             if col:
                                 if isinstance(col[0], Package):
                                     self._pkg_roots[parent] = col[0]
@@ -572,21 +582,11 @@ def filter_(f):
             for y in m:
                 yield y
 
-    def _collectfile(self, path, handle_dupes=True):
+    def _collectfile(self, path):
         ihook = self.gethookproxy(path)
         if not self.isinitpath(path):
             if ihook.pytest_ignore_collect(path=path, config=self.config):
                 return ()
-
-        if handle_dupes:
-            keepduplicates = self.config.getoption("keepduplicates")
-            if not keepduplicates:
-                duplicate_paths = self.config.pluginmanager._duplicatepaths
-                if path in duplicate_paths:
-                    return ()
-                else:
-                    duplicate_paths.add(path)
-
         return ihook.pytest_collect_file(path=path, parent=self)
 
     def _recurse(self, dirpath):
diff --git a/src/_pytest/python.py b/src/_pytest/python.py
index d360e2c8f3e..1d80bfa05f6 100644
--- a/src/_pytest/python.py
+++ b/src/_pytest/python.py
@@ -545,21 +545,12 @@ def gethookproxy(self, fspath):
             proxy = self.config.hook
         return proxy
 
-    def _collectfile(self, path, handle_dupes=True):
+    def _collectfile(self, path):
         ihook = self.gethookproxy(path)
         if not self.isinitpath(path):
             if ihook.pytest_ignore_collect(path=path, config=self.config):
                 return ()
 
-        if handle_dupes:
-            keepduplicates = self.config.getoption("keepduplicates")
-            if not keepduplicates:
-                duplicate_paths = self.config.pluginmanager._duplicatepaths
-                if path in duplicate_paths:
-                    return ()
-                else:
-                    duplicate_paths.add(path)
-
         if self.fspath == path:  # __init__.py
             return [self]
 
diff --git a/testing/test_collection.py b/testing/test_collection.py
index 18033b9c006..659d39c8112 100644
--- a/testing/test_collection.py
+++ b/testing/test_collection.py
@@ -98,6 +98,14 @@ def pytest_collect_file(path, parent):
         node = testdir.getpathnode(hello)
         assert isinstance(node, pytest.File)
         assert node.name == "hello.xxx"
+
+        # HACK: unset _duplicatepaths, which appears to be necessary for this
+        #       specific test setup?!
+        assert node.session.config.pluginmanager._duplicatepaths == {
+            (type(node), hello)
+        }
+        node.session.config.pluginmanager._duplicatepaths = set()
+
         nodes = node.session.perform_collect([node.nodeid], genitems=False)
         assert len(nodes) == 1
         assert isinstance(nodes[0], pytest.File)