Use "raise ... from" in custom errors for better tracebacks

spacy/cli/train.py

@@ -211,7 +211,7 @@ def create_evaluation_callback(
         except KeyError as e:
             keys = list(scores.keys())
             err = Errors.E983.format(dict="score_weights", key=str(e), keys=keys)
-            raise KeyError(err)
+            raise KeyError(err) from None
         return weighted_score, scores
 
     return evaluate
@@ -369,7 +369,7 @@ def setup_printer(
                 Errors.E983.format(
                     dict="scores (losses)", key=str(e), keys=list(info["losses"].keys())
                 )
-            )
+            ) from None
 
         try:
             scores = [
@@ -382,7 +382,7 @@ def setup_printer(
                     key=str(e),
                     keys=list(info["other_scores"].keys()),
                 )
-            )
+            ) from None
         data = (
             [info["epoch"], info["step"]]
             + losses

spacy/gold/example.pyx

@@ -139,7 +139,7 @@ cdef class Example:
 
     def get_aligned_spans_y2x(self, y_spans):
         return self._get_aligned_spans(self.x, y_spans, self.alignment.y2x)
-    
+
     def _get_aligned_spans(self, doc, spans, align):
         seen = set()
         output = []
@@ -207,7 +207,7 @@ cdef class Example:
         sent_starts and return a list of the new Examples"""
         if not self.reference.is_sentenced:
             return [self]
-        
+
         align = self.alignment.y2x
         seen_indices = set()
         output = []
@@ -267,7 +267,7 @@ def _annot2array(vocab, tok_annot, doc_annot):
                 values.append([vocab.strings.add(v) for v in value])
             except TypeError:
                 types= set([type(v) for v in value])
-                raise TypeError(Errors.E969.format(field=key, types=types))
+                raise TypeError(Errors.E969.format(field=key, types=types)) from None
 
     array = numpy.asarray(values, dtype="uint64")
     return attrs, array.T

spacy/lang/ja/__init__.py

@@ -200,7 +200,7 @@ def try_sudachi_import(split_mode="A"):
             "(https://github.com/WorksApplications/SudachiPy). "
             "Install with `pip install sudachipy sudachidict_core` or "
             "install spaCy with `pip install spacy[ja]`."
-        )
+        ) from None
 
 
 def resolve_pos(orth, tag, next_tag):
@@ -263,7 +263,7 @@ def get_dtokens_and_spaces(dtokens, text, gap_tag="空白"):
         try:
             word_start = text[text_pos:].index(word)
         except ValueError:
-            raise ValueError(Errors.E194.format(text=text, words=words))
+            raise ValueError(Errors.E194.format(text=text, words=words)) from None
 
         # space token
         if word_start > 0:

spacy/lang/ko/__init__.py

@@ -85,7 +85,7 @@ def try_mecab_import() -> None:
             "Korean support requires [mecab-ko](https://bitbucket.org/eunjeon/mecab-ko/src/master/README.md), "
             "[mecab-ko-dic](https://bitbucket.org/eunjeon/mecab-ko-dic), "
             "and [natto-py](https://github.com/buruzaemon/natto-py)"
-        )
+        ) from None
 
 
 def check_spaces(text, tokens):

spacy/lang/ru/lemmatizer.py

@@ -21,7 +21,7 @@ class RussianLemmatizer(Lemmatizer):
                 'try to fix it with "pip install pymorphy2==0.8" '
                 'or "pip install git+https://github.com/kmike/pymorphy2.git pymorphy2-dicts-uk"'
                 "if you need Ukrainian too"
-            )
+            ) from None
         if RussianLemmatizer._morph is None:
             RussianLemmatizer._morph = MorphAnalyzer()
 

spacy/lang/th/__init__.py

@@ -31,7 +31,7 @@ class ThaiTokenizer(DummyTokenizer):
             raise ImportError(
                 "The Thai tokenizer requires the PyThaiNLP library: "
                 "https://github.com/PyThaiNLP/pythainlp"
-            )
+            ) from None
         self.word_tokenize = word_tokenize
         self.vocab = nlp.vocab
 

spacy/lang/uk/lemmatizer.py

@@ -23,7 +23,7 @@ class UkrainianLemmatizer(Lemmatizer):
                 "The Ukrainian lemmatizer requires the pymorphy2 library and "
                 'dictionaries: try to fix it with "pip uninstall pymorphy2" and'
                 '"pip install git+https://github.com/kmike/pymorphy2.git pymorphy2-dicts-uk"'
-            )
+            ) from None
 
     def __call__(
         self, string: str, univ_pos: str, morphology: Optional[dict] = None

spacy/lang/vi/__init__.py

@@ -38,7 +38,7 @@ class VietnameseTokenizer(DummyTokenizer):
                     "Pyvi not installed. Either set use_pyvi = False, "
                     "or install it https://pypi.python.org/pypi/pyvi"
                 )
-                raise ImportError(msg)
+                raise ImportError(msg) from None
 
     def __call__(self, text: str) -> Doc:
         if self.use_pyvi:

spacy/lang/zh/__init__.py

@@ -129,7 +129,7 @@ class ChineseTokenizer(DummyTokenizer):
                         "pkuseg not installed: unable to reset pkuseg "
                         "user dict. Please " + _PKUSEG_INSTALL_MSG
                     )
-                    raise ImportError(msg)
+                    raise ImportError(msg) from None
             for word in words:
                 self.pkuseg_seg.preprocesser.insert(word.strip(), "")
         else:
@@ -208,7 +208,7 @@ class ChineseTokenizer(DummyTokenizer):
                     raise ImportError(
                         "pkuseg not installed. To use this model, "
                         + _PKUSEG_INSTALL_MSG
-                    )
+                    ) from None
                 self.pkuseg_seg = pkuseg.pkuseg(str(tempdir))
             if pkuseg_data["processors_data"]:
                 processors_data = pkuseg_data["processors_data"]
@@ -258,7 +258,7 @@ class ChineseTokenizer(DummyTokenizer):
                     raise ImportError(
                         "pkuseg not installed. To use this model, "
                         + _PKUSEG_INSTALL_MSG
-                    )
+                    ) from None
             if path.exists():
                 self.pkuseg_seg = pkuseg.pkuseg(path)
 
@@ -267,7 +267,7 @@ class ChineseTokenizer(DummyTokenizer):
                 import pkuseg
             except ImportError:
                 if self.segmenter == Segmenter.pkuseg:
-                    raise ImportError(self._pkuseg_install_msg)
+                    raise ImportError(self._pkuseg_install_msg) from None
             if self.segmenter == Segmenter.pkuseg:
                 data = srsly.read_msgpack(path)
                 (user_dict, do_process, common_words, other_words) = data
@@ -311,7 +311,7 @@ def try_jieba_import(segmenter: str) -> None:
                 "Jieba not installed. To use jieba, install it with `pip "
                 " install jieba` or from https://github.com/fxsjy/jieba"
             )
-            raise ImportError(msg)
+            raise ImportError(msg) from None
 
 
 def try_pkuseg_import(segmenter: str, pkuseg_model: str, pkuseg_user_dict: str) -> None:
@@ -332,11 +332,11 @@ def try_pkuseg_import(segmenter: str, pkuseg_model: str, pkuseg_user_dict: str)
     except ImportError:
         if segmenter == Segmenter.pkuseg:
             msg = "pkuseg not installed. To use pkuseg, " + _PKUSEG_INSTALL_MSG
-            raise ImportError(msg)
+            raise ImportError(msg) from None
     except FileNotFoundError:
         if segmenter == Segmenter.pkuseg:
             msg = "Unable to load pkuseg model from: " + pkuseg_model
-            raise FileNotFoundError(msg)
+            raise FileNotFoundError(msg) from None
 
 
 def _get_pkuseg_trie_data(node, path=""):

spacy/language.py

@@ -869,7 +869,7 @@ class Language:
             try:
                 doc = proc(doc, **component_cfg.get(name, {}))
             except KeyError:
-                raise ValueError(Errors.E109.format(name=name))
+                raise ValueError(Errors.E109.format(name=name)) from None
             if doc is None:
                 raise ValueError(Errors.E005.format(name=name))
         return doc

spacy/matcher/matcher.pyx

@@ -131,7 +131,7 @@ cdef class Matcher:
                     for attr, _ in spec[1]:
                         self._seen_attrs.add(attr)
             except OverflowError, AttributeError:
-                raise ValueError(Errors.E154.format())
+                raise ValueError(Errors.E154.format()) from None
         self._patterns.setdefault(key, [])
         self._callbacks[key] = on_match
         self._filter[key] = greedy

spacy/pipeline/attributeruler.py

@@ -85,7 +85,7 @@ class AttributeRuler(Pipe):
                         span=[t.text for t in span],
                         index=index,
                     )
-                )
+                ) from None
             set_token_attrs(token, attrs)
         return doc
 

spacy/pipeline/entity_linker.py

@@ -195,7 +195,7 @@ class EntityLinker(Pipe):
             types = set([type(eg) for eg in examples])
             raise TypeError(
                 Errors.E978.format(name="EntityLinker", method="update", types=types)
-            )
+            ) from None
         if set_annotations:
             # This seems simpler than other ways to get that exact output -- but
             # it does run the model twice :(
@@ -213,7 +213,7 @@ class EntityLinker(Pipe):
                         sent_index = sentences.index(ent.sent)
                     except AttributeError:
                         # Catch the exception when ent.sent is None and provide a user-friendly warning
-                        raise RuntimeError(Errors.E030)
+                        raise RuntimeError(Errors.E030) from None
                     # get n previous sentences, if there are any
                     start_sentence = max(0, sent_index - self.n_sents)
                     # get n posterior sentences, or as many < n as there are
@@ -439,7 +439,7 @@ class EntityLinker(Pipe):
             try:
                 self.model.from_bytes(p.open("rb").read())
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         def load_kb(p):
             self.kb = KnowledgeBase(entity_vector_length=self.cfg["entity_width"])

spacy/pipeline/morphologizer.pyx

@@ -262,7 +262,7 @@ class Morphologizer(Tagger):
             try:
                 self.model.from_bytes(b)
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         deserialize = {
             "vocab": lambda b: self.vocab.from_bytes(b),
@@ -301,7 +301,7 @@ class Morphologizer(Tagger):
                 try:
                     self.model.from_bytes(file_.read())
                 except AttributeError:
-                    raise ValueError(Errors.E149)
+                    raise ValueError(Errors.E149) from None
 
         deserialize = {
             "vocab": lambda p: self.vocab.from_disk(p),

spacy/pipeline/multitask.pyx

@@ -211,7 +211,7 @@ class ClozeMultitask(Pipe):
             predictions, bp_predictions = self.model.begin_update([eg.predicted for eg in examples])
         except AttributeError:
             types = set([type(eg) for eg in examples])
-            raise TypeError(Errors.E978.format(name="ClozeMultitask", method="rehearse", types=types))
+            raise TypeError(Errors.E978.format(name="ClozeMultitask", method="rehearse", types=types)) from None
         loss, d_predictions = self.get_loss(examples, self.vocab.vectors.data, predictions)
         bp_predictions(d_predictions)
         if sgd is not None:

spacy/pipeline/pipe.pyx

@@ -204,7 +204,7 @@ cdef class Pipe:
             try:
                 self.model.from_bytes(b)
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         deserialize = {}
         if hasattr(self, "vocab"):
@@ -242,7 +242,7 @@ cdef class Pipe:
             try:
                 self.model.from_bytes(p.open("rb").read())
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         deserialize = {}
         deserialize["vocab"] = lambda p: self.vocab.from_disk(p)

spacy/pipeline/senter.pyx

@@ -183,7 +183,7 @@ class SentenceRecognizer(Tagger):
             try:
                 self.model.from_bytes(b)
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         deserialize = {
             "vocab": lambda b: self.vocab.from_bytes(b),
@@ -222,7 +222,7 @@ class SentenceRecognizer(Tagger):
                 try:
                     self.model.from_bytes(file_.read())
                 except AttributeError:
-                    raise ValueError(Errors.E149)
+                    raise ValueError(Errors.E149) from None
 
         deserialize = {
             "vocab": lambda p: self.vocab.from_disk(p),

spacy/pipeline/tagger.pyx

@@ -195,7 +195,7 @@ class Tagger(Pipe):
                 return
         except AttributeError:
             types = set([type(eg) for eg in examples])
-            raise TypeError(Errors.E978.format(name="Tagger", method="update", types=types))
+            raise TypeError(Errors.E978.format(name="Tagger", method="update", types=types)) from None
         set_dropout_rate(self.model, drop)
         tag_scores, bp_tag_scores = self.model.begin_update(
             [eg.predicted for eg in examples])
@@ -232,7 +232,7 @@ class Tagger(Pipe):
             docs = [eg.predicted for eg in examples]
         except AttributeError:
             types = set([type(eg) for eg in examples])
-            raise TypeError(Errors.E978.format(name="Tagger", method="rehearse", types=types))
+            raise TypeError(Errors.E978.format(name="Tagger", method="rehearse", types=types)) from None
         if self._rehearsal_model is None:
             return
         if not any(len(doc) for doc in docs):
@@ -292,7 +292,7 @@ class Tagger(Pipe):
             try:
                 y = example.y
             except AttributeError:
-                raise TypeError(Errors.E978.format(name="Tagger", method="begin_training", types=type(example)))
+                raise TypeError(Errors.E978.format(name="Tagger", method="begin_training", types=type(example))) from None
             for token in y:
                 tag = token.tag_
                 if tag in orig_tag_map:
@@ -400,7 +400,7 @@ class Tagger(Pipe):
             try:
                 self.model.from_bytes(b)
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
 
         def load_tag_map(b):
             tag_map = srsly.msgpack_loads(b)
@@ -456,7 +456,7 @@ class Tagger(Pipe):
                 try:
                     self.model.from_bytes(file_.read())
                 except AttributeError:
-                    raise ValueError(Errors.E149)
+                    raise ValueError(Errors.E149) from None
 
         def load_tag_map(p):
             tag_map = srsly.read_msgpack(p)

spacy/pipeline/textcat.py

@@ -203,7 +203,7 @@ class TextCategorizer(Pipe):
             types = set([type(eg) for eg in examples])
             raise TypeError(
                 Errors.E978.format(name="TextCategorizer", method="update", types=types)
-            )
+            ) from None
         set_dropout_rate(self.model, drop)
         scores, bp_scores = self.model.begin_update([eg.predicted for eg in examples])
         loss, d_scores = self.get_loss(examples, scores)
@@ -250,7 +250,7 @@ class TextCategorizer(Pipe):
             err = Errors.E978.format(
                 name="TextCategorizer", method="rehearse", types=types
             )
-            raise TypeError(err)
+            raise TypeError(err) from None
         if not any(len(doc) for doc in docs):
             # Handle cases where there are no tokens in any docs.
             return losses
@@ -351,7 +351,7 @@ class TextCategorizer(Pipe):
                 err = Errors.E978.format(
                     name="TextCategorizer", method="update", types=type(example)
                 )
-                raise TypeError(err)
+                raise TypeError(err) from None
             for cat in y.cats:
                 self.add_label(cat)
         self.require_labels()

spacy/pipeline/transition_parser.pyx

@@ -473,7 +473,7 @@ cdef class Parser(Pipe):
                 self._resize()
                 self.model.from_bytes(bytes_data)
             except AttributeError:
-                raise ValueError(Errors.E149)
+                raise ValueError(Errors.E149) from None
         return self
 
     def to_bytes(self, exclude=tuple()):
@@ -498,7 +498,7 @@ cdef class Parser(Pipe):
                 try:
                     self.model.from_bytes(msg['model'])
                 except AttributeError:
-                    raise ValueError(Errors.E149)
+                    raise ValueError(Errors.E149) from None
         return self
 
     def _init_gold_batch(self, examples, min_length=5, max_length=500):

spacy/tokens/doc.pyx

@@ -699,7 +699,7 @@ cdef class Doc:
                        for id_ in py_attr_ids]
         except KeyError as msg:
             keys = [k for k in IDS.keys() if not k.startswith("FLAG")]
-            raise KeyError(Errors.E983.format(dict="IDS", key=msg, keys=keys))
+            raise KeyError(Errors.E983.format(dict="IDS", key=msg, keys=keys)) from None
         # Make an array from the attributes --- otherwise our inner loop is
         # Python dict iteration.
         cdef np.ndarray attr_ids = numpy.asarray(py_attr_ids, dtype="i")

spacy/util.py

@@ -138,7 +138,7 @@ def get_lang_class(lang: str) -> "Language":
         try:
             module = importlib.import_module(f".lang.{lang}", "spacy")
         except ImportError as err:
-            raise ImportError(Errors.E048.format(lang=lang, err=err))
+            raise ImportError(Errors.E048.format(lang=lang, err=err)) from err
         set_lang_class(lang, getattr(module, module.__all__[0]))
     return registry.languages.get(lang)
 
@@ -502,7 +502,7 @@ def run_command(command: Union[str, List[str]]) -> None:
     except FileNotFoundError:
         raise FileNotFoundError(
             Errors.E970.format(str_command=" ".join(command), tool=command[0])
-        )
+        ) from None
     if status != 0:
         sys.exit(status)
 
@@ -891,7 +891,7 @@ def get_words_and_spaces(
         try:
             word_start = text[text_pos:].index(word)
         except ValueError:
-            raise ValueError(Errors.E194.format(text=text, words=words))
+            raise ValueError(Errors.E194.format(text=text, words=words)) from None
         if word_start > 0:
             text_words.append(text[text_pos : text_pos + word_start])
             text_spaces.append(False)
@@ -918,7 +918,7 @@ def copy_config(config: Union[Dict[str, Any], Config]) -> Config:
     try:
         return Config(config).copy()
     except ValueError:
-        raise ValueError(Errors.E961.format(config=config))
+        raise ValueError(Errors.E961.format(config=config)) from None
 
 
 def deep_merge_configs(
@@ -1002,7 +1002,7 @@ def dot_to_object(config: Config, section: str):
         try:
             component = component[item]
         except (KeyError, TypeError):
-            raise KeyError(Errors.E952.format(name=section))
+            raise KeyError(Errors.E952.format(name=section)) from None
     return component