Revert #769, fix mergedirs instead (#770)

* Revert #769, solve the dependencies name collision problem in mergedirs(),

Author: tetron

cwltool/pathmapper.py

@@ -72,12 +72,7 @@ def addLocation(d):
             d["location"] = urllib.parse.urlunparse((parse.scheme, parse.netloc, path, parse.params, parse.query, parse.fragment))
 
         if "basename" not in d:
-            if parse.scheme and parse.scheme != "file":
-                d["basename"] = urllib.parse.quote(parse.netloc + parse.path, safe="")
-                if parse.query:
-                    d["basename"] += urllib.parse.quote("?"+parse.query, safe="")
-            else:
-                d["basename"] = os.path.basename(urllib.request.url2pathname(path))
+            d["basename"] = os.path.basename(urllib.request.url2pathname(path))
 
         if d["class"] == "File":
             d["nameroot"], d["nameext"] = os.path.splitext(d["basename"])

cwltool/process.py

@@ -822,6 +822,7 @@ def mergedirs(listing):
     # type: (List[Dict[Text, Any]]) -> List[Dict[Text, Any]]
     r = []  # type: List[Dict[Text, Any]]
     ents = {}  # type: Dict[Text, Any]
+    collided = set()  # type: Set[Text]
     for e in listing:
         if e["basename"] not in ents:
             ents[e["basename"]] = e
@@ -830,6 +831,23 @@ def mergedirs(listing):
                 ents[e["basename"]].setdefault("listing", []).extend(e["listing"])
             if ents[e["basename"]]["location"].startswith("_:"):
                 ents[e["basename"]]["location"] = e["location"]
+        elif e["location"] != ents[e["basename"]]["location"]:
+            # same basename, different location, collision,
+            # rename both.
+            collided.add(e["basename"])
+            e2 = ents[e["basename"]]
+
+            e["basename"] = urllib.parse.quote(e["location"], safe="")
+            e2["basename"] = urllib.parse.quote(e2["location"], safe="")
+
+            e["nameroot"], e["nameext"] = os.path.splitext(e["basename"])
+            e2["nameroot"], e2["nameext"] = os.path.splitext(e2["basename"])
+
+            ents[e["basename"]] = e
+            ents[e2["basename"]] = e2
+    for c in collided:
+        print(ents)
+        del ents[c]
     for e in six.itervalues(ents):
         if e["class"] == "Directory" and "listing" in e:
             e["listing"] = mergedirs(e["listing"])
@@ -859,6 +877,8 @@ def scandeps(base, doc, reffields, urlfields, loadref, urljoin=urllib.parse.urlj
                     "class": doc["class"],
                     "location": urljoin(base, u)
                 }
+                if "basename" in doc:
+                    deps["basename"] = doc["basename"]
                 if doc["class"] == "Directory" and "listing" in doc:
                     deps["listing"] = doc["listing"]
                 if doc["class"] == "File" and "secondaryFiles" in doc:

tests/test_pathmapper.py

@@ -54,3 +54,42 @@ def test_basename_field_generation(self):
             normalizeFilesDirs(file)
             self.assertEqual(file, expected)
 
+    def test_normalizeFilesDirs(self):
+        n = {
+            "class": "File",
+            "location": "file1.txt"
+        }
+        normalizeFilesDirs(n)
+        self.assertEqual(n, {
+            "class": "File",
+            "location": "file1.txt",
+            'basename': 'file1.txt',
+            'nameext': '.txt',
+            'nameroot': 'file1'
+        })
+
+        n = {
+            "class": "File",
+            "location": "file:///foo/file1.txt"
+        }
+        normalizeFilesDirs(n)
+        self.assertEqual(n, {
+            "class": "File",
+            "location": "file:///foo/file1.txt",
+            'basename': 'file1.txt',
+            'nameext': '.txt',
+            'nameroot': 'file1'
+        })
+
+        n = {
+            "class": "File",
+            "location": "http://example.com/file1.txt"
+        }
+        normalizeFilesDirs(n)
+        self.assertEqual(n, {
+            "class": "File",
+            "location": "http://example.com/file1.txt",
+            'basename': 'file1.txt',
+            'nameext': '.txt',
+            'nameroot': 'file1'
+        })