facilitate larger training files (#4827)

* add warning for large file and change start var to long

* type for file_length

spacy/errors.py

@@ -105,6 +105,10 @@ class Warnings(object):
  W025 = ("'{name}' requires '{attr}' to be assigned, but none of the "
  "previous components in the pipeline declare that they assign it.")
  W026 = ("Unable to set all sentence boundaries from dependency parses.")
+ W027 = ("Found a large training file of {size} bytes. Note that it may "
+ "be more efficient to split your training data into multiple "
+ "smaller JSON files instead.")
+
 
 
 @add_codes

spacy/gold.pyx

@@ -13,7 +13,7 @@ import srsly
 
 from .syntax import nonproj
 from .tokens import Doc, Span
-from .errors import Errors, AlignmentError
+from .errors import Errors, AlignmentError, user_warning, Warnings
 from .compat import path2str
 from . import util
 from .util import minibatch, itershuffle
@@ -557,20 +557,24 @@ def _json_iterate(loc):
  loc = util.ensure_path(loc)
  with loc.open("rb") as file_:
  py_raw = file_.read()
+ cdef long file_length = len(py_raw)
+ if file_length > 2 ** 30:
+ user_warning(Warnings.W027.format(size=file_length))
+
  raw = <char*>py_raw
  cdef int square_depth = 0
  cdef int curly_depth = 0
  cdef int inside_string = 0
  cdef int escape = 0
- cdef int start = -1
+ cdef long start = -1
  cdef char c
  cdef char quote = ord('"')
  cdef char backslash = ord("\\")
  cdef char open_square = ord("[")
  cdef char close_square = ord("]")
  cdef char open_curly = ord("{")
  cdef char close_curly = ord("}")
- for i in range(len(py_raw)):
+ for i in range(file_length):
  c = raw[i]
  if escape:
  escape = False