From 581eeed98b7a5a4565ea8286ef78bfce01667535 Mon Sep 17 00:00:00 2001
From: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Date: Wed, 1 Jan 2020 13:16:48 +0100
Subject: [PATCH] Warning goldparse (#4851)

* label in span not writable anymore

* Revert "label in span not writable anymore"

This reverts commit ab442338c8c4ddd7dfbc15348f999b74f4928090.

* provide more friendly error msg for parsing file
---
 spacy/errors.py |  1 +
 spacy/gold.pyx  | 24 ++++++++++++++++--------
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/spacy/errors.py b/spacy/errors.py
index 3aa4bedea..7393ddc07 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -534,6 +534,7 @@ class Errors(object):
             "make sure the gold EL data refers to valid results of the "
             "named entity recognizer in the `nlp` pipeline.")
     # TODO: fix numbering after merging develop into master
+    E996 = ("Could not parse {file}: {msg}")
     E997 = ("Tokenizer special cases are not allowed to modify the text. "
             "This would map '{chunk}' to '{orth}' given token attributes "
             "'{token_attrs}'.")
diff --git a/spacy/gold.pyx b/spacy/gold.pyx
index 1d3d8e034..10b8bf0cf 100644
--- a/spacy/gold.pyx
+++ b/spacy/gold.pyx
@@ -194,9 +194,10 @@ class GoldCorpus(object):
         i = 0
         for loc in locs:
             loc = util.ensure_path(loc)
-            if loc.parts[-1].endswith("json"):
+            file_name = loc.parts[-1]
+            if file_name.endswith("json"):
                 examples = read_json_file(loc)
-            elif loc.parts[-1].endswith("jsonl"):
+            elif file_name.endswith("jsonl"):
                 gold_tuples = srsly.read_jsonl(loc)
                 first_gold_tuple = next(gold_tuples)
                 gold_tuples = itertools.chain([first_gold_tuple], gold_tuples)
@@ -212,17 +213,24 @@ class GoldCorpus(object):
                                 doc = ex_dict.get("text", None)
                             examples.append(Example.from_dict(ex_dict, doc=doc))
 
-            elif loc.parts[-1].endswith("msg"):
+            elif file_name.endswith("msg"):
                 text, ex_dict = srsly.read_msgpack(loc)
                 examples = [Example.from_dict(ex_dict, doc=text)]
             else:
                 supported = ("json", "jsonl", "msg")
                 raise ValueError(Errors.E124.format(path=loc, formats=supported))
-            for example in examples:
-                yield example
-                i += 1
-                if limit and i >= limit:
-                    return
+            try:
+                for example in examples:
+                    yield example
+                    i += 1
+                    if limit and i >= limit:
+                        return
+            except KeyError as e:
+                msg = "Missing key {}".format(e)
+                raise KeyError(Errors.E996.format(file=file_name, msg=msg))
+            except UnboundLocalError as e:
+                msg = "Unexpected document structure"
+                raise ValueError(Errors.E996.format(file=file_name, msg=msg))
 
     @property
     def dev_examples(self):