From 46f4eb5db30bbbdff6d48c80067fe50aca4ddd3a Mon Sep 17 00:00:00 2001
From: svlandeg <sofie.vanlandeghem@gmail.com>
Date: Fri, 22 Mar 2019 16:55:05 +0100
Subject: [PATCH] error and warning messages

---
 spacy/errors.py |  7 +++++++
 spacy/kb.pyx    | 18 ++++++++----------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/spacy/errors.py b/spacy/errors.py
index 955567787..5f964114e 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -80,6 +80,8 @@ class Warnings(object):
             "the v2.x models cannot release the global interpreter lock. "
             "Future versions may introduce a `n_process` argument for "
             "parallel inference via multiprocessing.")
+    W017 = ("Alias '{alias}' already exists in the Knowledge base.")
+    W018 = ("Entity '{entity}' already exists in the Knowledge base.")
 
 
 @add_codes
@@ -376,6 +378,11 @@ class Errors(object):
             "Instead, create a new Span object and specify the `kb_id` keyword argument, "
             "for example:\nfrom spacy.tokens import Span\n"
             "span = Span(doc, start={start}, end={end}, label='{label}', kb_id='{kb_id}')")
+    E132 = ("The vectors for entities and probabilities for alias '{alias}' should have equal length, "
+            "but found {entities_length} and {probabilities_length} respectively.")
+    E133 = ("The sum of prior probabilities for alias '{alias}' should not exceed 1, "
+            "but found {sum}.")
+    E134 = ("Alias '{alias}' defined for unknown entity '{entity}'.")
 
 
 @add_codes
diff --git a/spacy/kb.pyx b/spacy/kb.pyx
index 912f51afd..a6a8ca9ba 100644
--- a/spacy/kb.pyx
+++ b/spacy/kb.pyx
@@ -1,6 +1,6 @@
 # cython: profile=True
 # coding: utf8
-from spacy.errors import user_warning
+from spacy.errors import Errors, Warnings, user_warning
 
 
 cdef class Candidate:
@@ -77,7 +77,7 @@ cdef class KnowledgeBase:
 
         # Return if this entity was added before
         if id_hash in self._entry_index:
-            user_warning("Entity " + entity_id + " already exists in the KB")
+            user_warning(Warnings.W018.format(entity=entity_id))
             return
 
         cdef int32_t dummy_value = 342
@@ -96,22 +96,20 @@ cdef class KnowledgeBase:
 
         # Throw an error if the length of entities and probabilities are not the same
         if not len(entities) == len(probabilities):
-            raise ValueError("The vectors for entities and probabilities for alias '" + alias
-                             + "' should have equal length, but found "
-                             + str(len(entities)) + " and " + str(len(probabilities)) + "respectively.")
-
+            raise ValueError(Errors.E132.format(alias=alias,
+                                                entities_length=len(entities),
+                                                probabilities_length=len(probabilities)))
 
         # Throw an error if the probabilities sum up to more than 1
         prob_sum = sum(probabilities)
         if prob_sum > 1:
-            raise ValueError("The sum of prior probabilities for alias '" + alias + "' should not exceed 1, "
-                             + "but found " + str(prob_sum))
+            raise ValueError(Errors.E133.format(alias=alias, sum=prob_sum))
 
         cdef hash_t alias_hash = self.vocab.strings.add(alias)
 
         # Return if this alias was added before
         if alias_hash in self._alias_index:
-            user_warning("Alias " + alias + " already exists in the KB")
+            user_warning(Warnings.W017.format(alias=alias))
             return
 
         cdef hash_t entity_hash
@@ -122,7 +120,7 @@ cdef class KnowledgeBase:
         for entity, prob in zip(entities, probabilities):
             entity_id_hash = self.vocab.strings[entity]
             if not entity_id_hash in self._entry_index:
-                raise ValueError("Alias '" + alias + "' defined for unknown entity '" + entity + "'")
+                raise ValueError(Errors.E134.format(alias=alias, entity=entity))
 
             entry_index = <int64_t>self._entry_index.get(entity_id_hash)
             entry_indices.push_back(int(entry_index))