Updated Python and schema to work with new multi-file format.

Ichoran · Ichoran · commit daf1eaafd03b · 2017-06-12T14:41:53.000-07:00
diff --git a/src/Python/wcon/wcon_parser.py b/src/Python/wcon/wcon_parser.py
@@ -643,6 +643,9 @@ def load_from_file(cls, JSON_path,
         # CASE 1: NO "files" OBJECT, hence no multiple files.  We are done.
         if w_current.files is None:
             return w_current
+        elif ('next' not in w_current.files) and ('prev' not in w.current.files):
+            # CASE 2: "files" object exists but no prev/next, assume nothing is there
+            return w_current
         else:
             # The merge operations below will blast away the .files attribute
             # so we need to save a local copy
@@ -651,20 +654,20 @@ def load_from_file(cls, JSON_path,
         # OTHERWISE, CASE 2: MULTIPLE FILES
 
         # The schema guarantees that if "files" is present,
-        # "this", "prev" and "next" will exist.  Also, that "this" is not
+        # "current", will exist.  Also, that "current" is not
         # null and whose corresponding value is a string at least one
         # character in length.
-        cur_ext = current_files['this']
+        cur_ext = current_files['current']
 
         # e.g. cur_filename = 'filename_2.wcon'
         # cur_ext = '_2', prefix = 'filename', suffix = '.wcon'
         cur_filename = JSON_path
-        if cur_filename.find(cur_ext) == -1:
-            raise AssertionError('Cannot find the current extension "' +
-                                 cur_ext + '" within the current filename "' +
+        name_offset = cur_filename.find(cur_ext)
+        if name_offset == -1:
+            raise AssertionError('Mismatch between the filename given in the file "' +
+                                 cur_ext + '" and the file we loaded from "' +
                                  cur_filename + '".')
-        prefix = cur_filename[:cur_filename.find(cur_ext)]
-        suffix = cur_filename[cur_filename.find(cur_ext) + len(cur_ext):]
+        path_string = cur_filename[:name_offset]
 
         load_chunks = {'prev': load_prev_chunks,
                        'next': load_next_chunks}
@@ -675,12 +678,13 @@ def load_from_file(cls, JSON_path,
             # Same with the "next" chunks
             if (load_chunks[direction] and
                     current_files is not None and
-                    current_files[direction] is not None):
+                    current_files[direction] is not None and
+                    len(current_files[direction]) > 0):
                 cur_load_prev_chunks = (direction == 'prev')
                 cur_load_next_chunks = (direction == 'next')
 
-                new_file_name = (prefix + current_files[direction][0] +
-                                 suffix)
+                new_file_name = path_string + current_files[direction][0]
+
                 w_new = cls.load_from_file(new_file_name,
                                            cur_load_prev_chunks,
                                            cur_load_next_chunks,
diff --git a/src/scala/README.md b/src/scala/README.md
@@ -7,7 +7,7 @@ the behavior of the Scala implementation should be presumed to be authoritative.
 
 ## Requirements
 
-This project requires Java 8 and [Scala 2.11](http://scala-lang.org).  You do
+This project requires Java 8 and [Scala 2.12](http://scala-lang.org).  You do
 not need to install Scala explicitly, as the build process is managed by
 [SBT](http://www.scala-sbt.org/).  SBT must be installed to build the project,
 and it will take care of downloading Scala and any needed libraries.
@@ -39,32 +39,6 @@ there (the `Right` case), and prints the error and throws an exception if
 not.  (If you don't care about error-handling, replace the `match` and following
 statements with `.right.get`.)
 
-The Scala reader/writer does its best to preserve the underlying structure
-of the data file.  However, this may not be the most convenient form in which
-to browse the data.  The `DataSet` class can extract and merge all the data
-by ID, using the `combined()` method.  This method can take a map of functions
-that are used to merge data from custom tags, and these functions may fail,
-so the entire operation may fail.  Thus, the function returns an `Either`, from
-which you can extract your data:
-
-```scala
-val data = worms.combined() match {
-  case Right(ds) => ds
-  case Left(err) => println(err); throw new Exception
-}
-```
-
-You should see something like so (except formatted on a single line):
-
-```
-res0: Array[org.openworm.trackercommons.Data] =
-  Array({ "id": 1, "ox": [0.6, 0.9], "oy": [0, -0.04], "t": [0, 1],
-      "x": [ [-0.6, -0.3, 0, 0.3, 0.6], [-0.6, -0.3, 0, 0.3, 0.6] ],
-      "y": [ [0, -0.2, 0, 0.2, 0], [-0.16, 0.04, 0.24, 0.04, -0.16] ] },
-    { "id": 2, "ox": [0], "oy": [1.5], "t": [1], "x": [ [0, 0.2, 0, -0.2, 0] ],
-      "y": [ [-0.5, -0.25, 0, 0.25, 0.5] ] })
-```
-
 ## Using the reference implementation to create data
 
 The Scala implementation also contains routines to create data suitable for writing in WCON format.  In particular, it helps populate the standard data structures and ensure that minimal requirements are met.
diff --git a/tests/minimax.wcon b/tests/minimax.wcon
@@ -5,14 +5,13 @@
         "timestamp":"2012-04-23T18:25:43.511Z",
         "temperature":22,
         "humidity":40.2,
-        "dish":{ "type":"petri", "size":35, "units":"mm" },
+        "dish":{ "style":"petri", "size":35, "units":"mm" },
         "food":"none",
         "media":"agarose",
         "sex":"hermaphrodite",
         "stage":"adult",
         "age":18.511,
         "strain":"CB4856",
-        "image_orientation":"imaged onto agar",
         "protocol":"text description of protocol",
         "software":{
             "tracker":{ "name":"Software Name", "version":"1.3.0"},
diff --git a/tests/multiworm.wcon b/tests/multiworm.wcon
@@ -5,14 +5,13 @@
         "timestamp":"2012-04-23T18:25:43.511Z",
         "temperature":22,
         "humidity":40.2,
-        "dish":{ "type":"petri", "size":35, "units":"mm" },
+        "dish":{ "style":"petri", "size":35, "units":"mm" },
         "food":"none",
         "media":"agarose",
         "sex":"hermaphrodite",
         "stage":"adult",
         "age":18.511,
         "strain":"CB4856",
-        "image_orientation":"imaged onto agar",
         "protocol":"text description of protocol",
         "software":{
             "tracker":{ "name":"Software Name", "version":"1.3.0"},
diff --git a/wcon_schema.json b/wcon_schema.json
@@ -16,20 +16,20 @@
             "type": "object",
             "description": "For very long tracking experiments, it may be convenient to split a single experiment across multiple WCON files. To make it easier to reconstruct tracks across files, we support a 'files' object.",
             "properties": {
-                "this": {"type":"string", "minLength":1},
+                "current": {"type":"string"},
                 "prev": {"oneOf": [
                     {"type": "null"},
                     {"type":"string"},
-                    {"type": "array", "minItems":1, "items": {"type":"string", "minLength":1}}
+                    {"type": "array", "items": {"type":"string", "minLength":1}}
                 ]},
                 "next": {"oneOf": [
                     {"type": "null"},
                     {"type":"string"},
-                    {"type": "array", "minItems":1, "items": {"type":"string", "minLength":1}}
+                    {"type": "array", "items": {"type":"string", "minLength":1}}
                 ]}
             },
             "additionalProperties": false,
-            "required": ["this"]
+            "required": ["current"]
         },
         "units": {
             "type": "object",
@@ -48,6 +48,7 @@
             "type": "object",
             "description": "Information about experimental conditions and software versions; critical for reproducibility across labs.",
             "properties": {
+                "id": {"type": "string"},
                 "lab": {"type": "object"},
                 "who": { "$ref": "#/definitions/string_or_array_of_strings" },
                 "timestamp": {"type": "string", "format":"date-time"},
@@ -56,7 +57,7 @@
                 "arena": {
                     "type": "object",
                     "properties":{
-                        "type": {"type": "string", "default":"petri"},
+                        "style": {"type": "string", "default":"petri"},
                         "size": {"oneOf":[ {"type": "number"}, {"type": "array", "minItems":2, "items": {"type":"string"} }] },
                         "orientation": {"type": "string"}
                     }
@@ -67,7 +68,6 @@
                 "stage": {"type": "string", "enum": ["L1", "L2", "L3", "L4", "adult", "dauer"]},
                 "age": {"type": "number"},
                 "strain": {"type": "string"},
-                "image_orientation": {"type": "string", "enum": ["imaged onto agar", "imaged through agar"]},
                 "protocol": { "$ref": "#/definitions/string_or_array_of_strings" },
                 "interpolate": {"oneOf":[
                     { "$ref": "#/definitions/interpolate_metadata" },
