From 3d9f41c2c94d097bcbf8d2056a3c5f5c075472a0 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Tue, 6 Oct 2015 10:34:59 +1100
Subject: [PATCH] * Add LookupError for better error reporting in Vocab

---
 spacy/vocab.pyx | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/spacy/vocab.pyx b/spacy/vocab.pyx
index 0e35cdd6d..2cc9094eb 100644
--- a/spacy/vocab.pyx
+++ b/spacy/vocab.pyx
@@ -96,7 +96,9 @@ cdef class Vocab:
         lex = <LexemeC*>self._by_hash.get(key)
         cdef size_t addr
         if lex != NULL:
-            assert lex.orth == self.strings[string]
+            if lex.orth != self.strings[string]:
+                raise LookupError.mismatched_strings(
+                    lex.orth, self.strings[lex.orth], string)
             return lex
         else:
             return self._new_lexeme(mem, string)
@@ -352,6 +354,21 @@ def write_binary_vectors(in_loc, out_loc):
             out_file.write_from(vec, vec_len, sizeof(float))
 
 
+class LookupError(Exception):
+    @classmethod
+    def mismatched_strings(cls, id_, id_string, original_string):
+        return cls(
+            "Error fetching a Lexeme from the Vocab. When looking up a string, "
+            "the lexeme returned had an orth ID that did not match the query string. "
+            "This means that the cached lexeme structs are mismatched to the "
+            "string encoding table. The mismatched:\n"
+            "Query string: {query}\n"
+            "Orth cached: {orth_str}\n"
+            "ID of orth: {orth_id}".format(
+                query=original_string, orth_str=id_string, orth_id=id_)
+        )
+
+
 class VectorReadError(Exception):
     @classmethod
     def mismatched_sizes(cls, loc, line_num, prev_size, curr_size):