spaCy/spacy/errors.py

import warnings
from typing import Literal

from . import about


class ErrorsWithCodes(type):
    def __getattribute__(self, code):
        msg = super().__getattribute__(code)
        if code.startswith("__"):  # python system attributes like __class__
            return msg
        else:
            return "[{code}] {msg}".format(code=code, msg=msg)


def setup_default_warnings():
    # ignore certain numpy warnings
    filter_warning("ignore", error_msg="numpy.dtype size changed")  # noqa
    filter_warning("ignore", error_msg="numpy.ufunc size changed")  # noqa

    # warn about entity_ruler, span_ruler & matcher having no patterns only once
    for pipe in ["matcher", "entity_ruler", "span_ruler"]:
        filter_warning("once", error_msg=Warnings.W036.format(name=pipe))

    # warn once about lemmatizer without required POS
    filter_warning("once", error_msg=Warnings.W108)

    # floret vector table cannot be modified
    filter_warning("once", error_msg="[W114]")


def filter_warning(
    action: Literal["default", "error", "ignore", "always", "module", "once"],
    error_msg: str,
):
    """Customize how spaCy should handle a certain warning.

    error_msg (str): e.g. "W006", or a full error message
    action (str): "default", "error", "ignore", "always", "module" or "once"
    """
    warnings.filterwarnings(action, message=_escape_warning_msg(error_msg))


def _escape_warning_msg(msg):
    """To filter with warnings.filterwarnings, the [] brackets need to be escaped"""
    return msg.replace("[", "\\[").replace("]", "\\]")


# fmt: off

class Warnings(metaclass=ErrorsWithCodes):
    W005 = ("Doc object not parsed. This means displaCy won't be able to "
            "generate a dependency visualization for it. Make sure the Doc "
            "was processed with a model that supports dependency parsing, and "
            "not just a language class like `English()`. For more info, see "
            "the docs:\nhttps://spacy.io/usage/models")
    W006 = ("No entities to visualize found in Doc object. If this is "
            "surprising to you, make sure the Doc was processed using a model "
            "that supports named entity recognition, and check the `doc.ents` "
            "property manually if necessary.")
    W007 = ("The model you're using has no word vectors loaded, so the result "
            "of the {obj}.similarity method will be based on the tagger, "
            "parser and NER, which may not give useful similarity judgements. "
            "This may happen if you're using one of the small models, e.g. "
            "`en_core_web_sm`, which don't ship with word vectors and only "
            "use context-sensitive tensors. You can always add your own word "
            "vectors, or use one of the larger models instead if available.")
    W008 = ("Evaluating {obj}.similarity based on empty vectors.")
    W011 = ("It looks like you're calling displacy.serve from within a "
            "Jupyter notebook or a similar environment. This likely means "
            "you're already running a local web server, so there's no need to "
            "make displaCy start another one. Instead, you should be able to "
            "replace displacy.serve with displacy.render to show the "
            "visualization.")
    W012 = ("A Doc object you're adding to the PhraseMatcher for pattern "
            "'{key}' is parsed and/or tagged, but to match on '{attr}', you "
            "don't actually need this information. This means that creating "
            "the patterns is potentially much slower, because all pipeline "
            "components are applied. To only create tokenized Doc objects, "
            "try using `nlp.make_doc(text)` or process all texts as a stream "
            "using `list(nlp.tokenizer.pipe(all_texts))`.")
    W017 = ("Alias '{alias}' already exists in the Knowledge Base.")
    W018 = ("Entity '{entity}' already exists in the Knowledge Base - "
            "ignoring the duplicate entry.")
    W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be "
            "incorrect. Modify PhraseMatcher._terminal_hash to fix.")
    W024 = ("Entity '{entity}' - alias '{alias}' combination already exists in "
            "the Knowledge Base.")
    W026 = ("Unable to set all sentence boundaries from dependency parses. If "
            "you are constructing a parse tree incrementally by setting "
            "token.head values, you can probably ignore this warning. Consider "
            "using Doc(words, ..., heads=heads, deps=deps) instead.")
    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.")
    W028 = ("Doc.from_array was called with a vector of type '{type}', "
            "but is expecting one of type uint64 instead. This may result "
            "in problems with the vocab further on in the pipeline.")
    W030 = ("Some entities could not be aligned in the text \"{text}\" with "
            "entities \"{entities}\". Use "
            "`spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)`"
            " to check the alignment. Misaligned entities ('-') will be "
            "ignored during training.")
    W033 = ("Training a new {model} using a model with no lexeme normalization "
            "table. This may degrade the performance of the model to some "
            "degree. If this is intentional or the language you're using "
            "doesn't have a normalization table, please ignore this warning. "
            "If this is surprising, make sure you are loading the table in "
            "your config. The languages with lexeme normalization tables are "
            "currently: {langs}\n\nAn example of how to load a table in "
            "your config :\n\n"
            "[initialize.lookups]\n"
            "@misc = \"spacy.LookupsDataLoaderFromURL.v1\"\n"
            "lang = ${{nlp.lang}}\n"
             f'url = "{about.__lookups_url__}"\n'
            "tables = [\"lexeme_norm\"]\n")
    W035 = ("Discarding subpattern '{pattern}' due to an unrecognized "
            "attribute or operator.")
    W036 = ("The component '{name}' does not have any patterns defined.")

    # New warnings added in v3.x
    W086 = ("Component '{listener}' will be (re)trained, but it needs the component "
            "'{name}' which is frozen. If you want to prevent retraining '{name}' "
            "but want to train '{listener}' on top of it, you should add '{name}' to the "
            "list of 'annotating_components' in the 'training' block in the config. "
            "See the documentation for details: "
            "https://spacy.io/usage/training#annotating-components")
    W087 = ("Component '{name}' will be (re)trained, but the component '{listener}' "
            "depends on it via a listener and is frozen. This means that the "
            "performance of '{listener}' will be degraded. You can either freeze "
            "both, or neither of the two. If you're sourcing the component from "
            "an existing pipeline, you can use the `replace_listeners` setting in "
            "the config block to replace its token-to-vector listener with a copy "
            "and make it independent. For example, `replace_listeners = "
            "[\"model.tok2vec\"]` See the documentation for details: "
            "https://spacy.io/usage/training#config-components-listeners")
    W090 = ("Could not locate any {format} files in path '{path}'.")
    W091 = ("Could not clean/remove the temp directory at {dir}: {msg}.")
    W092 = ("Ignoring annotations for sentence starts, as dependency heads are set.")
    W093 = ("Could not find any data to train the {name} on. Is your "
            "input data correctly formatted?")
    W094 = ("Model '{model}' ({model_version}) specifies an under-constrained "
            "spaCy version requirement: {version}. This can lead to compatibility "
            "problems with older versions, or as new spaCy versions are "
            "released, because the model may say it's compatible when it's "
            'not. Consider changing the "spacy_version" in your meta.json to a '
            "version range, with a lower and upper pin. For example: {example}")
    W095 = ("Model '{model}' ({model_version}) was trained with spaCy "
            "{version} and may not be 100% compatible with the current version "
            "({current}). If you see errors or degraded performance, download "
            "a newer compatible model or retrain your custom model with the "
            "current spaCy version. For more details and available updates, "
            "run: python -m spacy validate")
    W096 = ("The method `nlp.disable_pipes` is now deprecated - use "
            "`nlp.select_pipes` instead.")
    W100 = ("Skipping unsupported morphological feature(s): '{feature}'. "
            "Provide features as a dict {{\"Field1\": \"Value1,Value2\"}} or "
            "string \"Field1=Value1,Value2|Field2=Value3\".")
    W101 = ("Skipping Doc custom extension '{name}' while merging docs.")
    W102 = ("Skipping unsupported user data '{key}: {value}' while merging docs.")
    W103 = ("Unknown {lang} word segmenter '{segmenter}'. Supported "
            "word segmenters: {supported}. Defaulting to {default}.")
    W104 = ("Skipping modifications for '{target}' segmenter. The current "
            "segmenter is '{current}'.")
    W105 = ("As of spaCy v3.0, the `{matcher}.pipe` method is deprecated. If you "
            "need to match on a stream of documents, you can use `nlp.pipe` and "
            "call the {matcher} on each Doc object.")
    W107 = ("The property `Doc.{prop}` is deprecated. Use "
            "`Doc.has_annotation(\"{attr}\")` instead.")
    W108 = ("The rule-based lemmatizer did not find POS annotation for one or "
            "more tokens. Check that your pipeline includes components that "
            "assign token.pos, typically 'tagger'+'attribute_ruler' or "
            "'morphologizer'.")
    W109 = ("Unable to save user hooks while serializing the doc. Re-add any "
            "required user hooks to the doc after processing.")
    W110 = ("The DependencyMatcher token pattern {pattern} matched a span "
            "{tokens} that is 2+ tokens long. Only the first token in the span "
            "will be included in the results. For better results, token "
            "patterns should return matches that are each exactly one token "
            "long.")
    W111 = ("Jupyter notebook detected: if using `prefer_gpu()` or "
            "`require_gpu()`, include it in the same cell right before "
            "`spacy.load()` to ensure that the model is loaded on the correct "
            "device. More information: "
            "http://spacy.io/usage/v3#jupyter-notebook-gpu")
    W112 = ("The model specified to use for initial vectors ({name}) has no "
            "vectors. This is almost certainly a mistake.")
    W113 = ("Sourced component '{name}' may not work as expected: source "
            "vectors are not identical to current pipeline vectors.")
    W114 = ("Using multiprocessing with GPU models is not recommended and may "
            "lead to errors.")
    W115 = ("Skipping {method}: the floret vector table cannot be modified. "
            "Vectors are calculated from character ngrams.")
    W116 = ("Unable to clean attribute '{attr}'.")
    W117 = ("No spans to visualize found in Doc object with spans_key: '{spans_key}'. If this is "
            "surprising to you, make sure the Doc was processed using a model "
            "that supports span categorization, and check the `doc.spans[spans_key]` "
            "property manually if necessary.\n\nAvailable keys: {keys}")
    W118 = ("Term '{term}' not found in glossary. It may however be explained in documentation "
            "for the corpora used to train the language. Please check "
            "`nlp.meta[\"sources\"]` for any relevant links.")
    W119 = ("Overriding pipe name in `config` is not supported. Ignoring override '{name_in_config}'.")
    W120 = ("Unable to load all spans in Doc.spans: more than one span group "
            "with the name '{group_name}' was found in the saved spans data. "
            "Only the last span group will be loaded under "
            "Doc.spans['{group_name}']. Skipping span group with values: "
            "{group_values}")
    W121 = ("Attempting to trace non-existent method '{method}' in pipe '{pipe}'")
    W122 = ("Couldn't trace method '{method}' in pipe '{pipe}'. This can happen if the pipe class "
            "is a Cython extension type.")
    W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option "
            "`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.")
    W124 = ("{host}:{port} is already in use, using the nearest available port {serve_port} as an alternative.")
    W125 = ("The StaticVectors key_attr is no longer used. To set a custom "
            "key attribute for vectors, configure it through Vectors(attr=) or "
            "'spacy init vectors --attr'")
    W126 = ("These keys are unsupported: {unsupported}")
    W127 = ("Not all `Language.pipe` worker processes completed successfully")

    # v4 warning strings
    W401 = ("`incl_prior is True`, but the selected knowledge base type {kb_type} doesn't support prior probability "
            "lookups so this setting will be ignored. If your KB does support prior probability lookups, make sure "
            "to return `True` in `.supports_prior_probs`.")


class Errors(metaclass=ErrorsWithCodes):
    E001 = ("No component '{name}' found in pipeline. Available names: {opts}")
    E002 = ("Can't find factory for '{name}' for language {lang} ({lang_code}). "
            "This usually happens when spaCy calls `nlp.{method}` with a custom "
            "component name that's not registered on the current language class. "
            "If you're using a custom component, make sure you've added the "
            "decorator `@Language.component` (for function components) or "
            "`@Language.factory` (for class components).\n\nAvailable "
            "factories: {opts}")
    E003 = ("Not a valid pipeline component. Expected callable, but "
            "got {component} (name: '{name}'). If you're using a custom "
            "component factory, double-check that it correctly returns your "
            "initialized component.")
    E004 = ("Can't set up pipeline component: a factory for '{name}' already "
            "exists. Existing factory: {func}. New factory: {new_func}")
    E005 = ("Pipeline component '{name}' returned {returned_type} instead of a "
            "Doc. If you're using a custom component, maybe you forgot to "
            "return the processed Doc?")
    E006 = ("Invalid constraints for adding pipeline component. You can only "
            "set one of the following: before (component name or index), "
            "after (component name or index), first (True) or last (True). "
            "Invalid configuration: {args}. Existing components: {opts}")
    E007 = ("'{name}' already exists in pipeline. Existing names: {opts}")
    E008 = ("Can't restore disabled pipeline component '{name}' because it "
            "doesn't exist in the pipeline anymore. If you want to remove "
            "components from the pipeline, you should do it before calling "
            "`nlp.select_pipes` or after restoring the disabled components.")
    E010 = ("Word vectors set to length 0. This may be because you don't have "
            "a model installed or loaded, or because your model doesn't "
            "include word vectors. For more info, see the docs:\n"
            "https://spacy.io/usage/models")
    E011 = ("Unknown operator: '{op}'. Options: {opts}")
    E012 = ("Cannot add pattern for zero tokens to matcher.\nKey: {key}")
    E017 = ("Can only add 'str' inputs to StringStore. Got type: {value_type}")
    E018 = ("Can't retrieve string for hash '{hash_value}'. This usually "
            "refers to an issue with the `Vocab` or `StringStore`.")
    E019 = ("Can't create transition with unknown action ID: {action}. Action "
            "IDs are enumerated in spacy/syntax/{src}.pyx.")
    E022 = ("Could not find a transition with the name '{name}' in the NER "
            "model.")
    E024 = ("Could not find an optimal move to supervise the parser. Usually, "
            "this means that the model can't be updated in a way that's valid "
            "and satisfies the correct annotations specified in the GoldParse. "
            "For example, are all labels added to the model? If you're "
            "training a named entity recognizer, also make sure that none of "
            "your annotated entity spans have leading or trailing whitespace "
            "or punctuation. You can also use the `debug data` command to "
            "validate your JSON-formatted training data. For details, run:\n"
            "python -m spacy debug data --help")
    E025 = ("String is too long: {length} characters. Max is 2**30.")
    E026 = ("Error accessing token at position {i}: out of bounds in Doc of "
            "length {length}.")
    E027 = ("Arguments `words` and `spaces` should be sequences of the same "
            "length, or `spaces` should be left default at None. `spaces` "
            "should be a sequence of booleans, with True meaning that the "
            "word owns a ' ' character following it.")
    E028 = ("`words` expects a list of unicode strings, but got bytes instance: {value}")
    E029 = ("`noun_chunks` requires the dependency parse, which requires a "
            "statistical model to be installed and loaded. For more info, see "
            "the documentation:\nhttps://spacy.io/usage/models")
    E030 = ("Sentence boundaries unset. You can add the 'sentencizer' "
            "component to the pipeline with: `nlp.add_pipe('sentencizer')`. "
            "Alternatively, add the dependency parser or sentence recognizer, "
            "or set sentence boundaries by setting `doc[i].is_sent_start`.")
    E031 = ("Invalid token: empty string ('') at position {i}.")
    E033 = ("Cannot load into non-empty Doc of length {length}.")
    E035 = ("Error creating span with start {start} and end {end} for Doc of "
            "length {length}.")
    E036 = ("Error calculating span: Can't find a token starting at character "
            "offset {start}.")
    E037 = ("Error calculating span: Can't find a token ending at character "
            "offset {end}.")
    E039 = ("Array bounds exceeded while searching for root word. This likely "
            "means the parse tree is in an invalid state. Please report this "
            "issue here: http://github.com/explosion/spaCy/issues")
    E040 = ("Attempt to access token at {i}, max length {max_length}.")
    E041 = ("Invalid comparison operator: {op}. Likely a Cython bug?")
    E042 = ("Error accessing `doc[{i}].nbor({j})`, for doc of length {length}.")
    E043 = ("Refusing to write to token.sent_start if its document is parsed, "
            "because this may cause inconsistent state.")
    E044 = ("Invalid value for token.sent_start: {value}. Must be one of: "
            "None, True, False")
    E045 = ("Possibly infinite loop encountered while looking for {attr}.")
    E046 = ("Can't retrieve unregistered extension attribute '{name}'. Did "
            "you forget to call the `set_extension` method?")
    E047 = ("Can't assign a value to unregistered extension attribute "
            "'{name}'. Did you forget to call the `set_extension` method?")
    E048 = ("Can't import language {lang} or any matching language from spacy.lang: {err}")
    E050 = ("Can't find model '{name}'. It doesn't seem to be a Python "
            "package or a valid path to a data directory.")
    E052 = ("Can't find model directory: {path}")
    E053 = ("Could not read {name} from {path}")
    E054 = ("No valid '{setting}' setting found in model meta.json.")
    E055 = ("Invalid ORTH value in exception:\nKey: {key}\nOrths: {orths}")
    E056 = ("Invalid tokenizer exception: ORTH values combined don't match "
            "original string.\nKey: {key}\nOrths: {orths}")
    E057 = ("Stepped slices not supported in Span objects. Try: "
            "`list(tokens)[start:stop:step]` instead.")
    E058 = ("Could not retrieve vector for key {key}.")
    E059 = ("One (and only one) keyword arg must be set. Got: {kwargs}")
    E060 = ("Cannot add new key to vectors: the table is full. Current shape: "
            "({rows}, {cols}).")
    E062 = ("Cannot find empty bit for new lexical flag. All bits between 0 "
            "and 63 are occupied. You can replace one by specifying the "
            "`flag_id` explicitly, e.g. "
            "`nlp.vocab.add_flag(your_func, flag_id=IS_ALPHA`.")
    E063 = ("Invalid value for `flag_id`: {value}. Flag IDs must be between 1 "
            "and 63 (inclusive).")
    E064 = ("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: {string}\nOrth cached: {orth}\nOrth ID: {orth_id}")
    E065 = ("Only one of the vector table's width and shape can be specified. "
            "Got width {width} and shape {shape}.")
    E067 = ("Invalid BILUO tag sequence: Got a tag starting with {start} "
            "without a preceding 'B' (beginning of an entity). "
            "Tag sequence:\n{tags}")
    E068 = ("Invalid BILUO tag: '{tag}'.")
    E071 = ("Error creating lexeme: specified orth ID ({orth}) does not "
            "match the one in the vocab ({vocab_orth}).")
    E073 = ("Cannot assign vector of length {new_length}. Existing vectors "
            "are of length {length}. You can use `vocab.reset_vectors` to "
            "clear the existing vectors and resize the table.")
    E074 = ("Error interpreting compiled match pattern: patterns are expected "
            "to end with the attribute {attr}. Got: {bad_attr}.")
    E079 = ("Error computing states in beam: number of predicted beams "
            "({pbeams}) does not equal number of gold beams ({gbeams}).")
    E080 = ("Duplicate state found in beam: {key}.")
    E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
            "does not equal number of losses ({losses}).")
    E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
            "projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
            "match.")
    E083 = ("Error setting extension: only one of `default`, `method`, or "
            "`getter` (plus optional `setter`) is allowed. Got: {nr_defined}")
    E084 = ("Error assigning label ID {label} to span: not in StringStore.")
    E085 = ("Can't create lexeme for string '{string}'.")
    E087 = ("Unknown displaCy style: {style}.")
    E088 = ("Text of length {length} exceeds maximum of {max_length}. The "
            "parser and NER models require roughly 1GB of temporary "
            "memory per 100,000 characters in the input. This means long "
            "texts may cause memory allocation errors. If you're not using "
            "the parser or NER, it's probably safe to increase the "
            "`nlp.max_length` limit. The limit is in number of characters, so "
            "you can check whether your inputs are too long by checking "
            "`len(text)`.")
    E089 = ("Extensions can't have a setter argument without a getter "
            "argument. Check the keyword arguments on `set_extension`.")
    E090 = ("Extension '{name}' already exists on {obj}. To overwrite the "
            "existing extension, set `force=True` on `{obj}.set_extension`.")
    E091 = ("Invalid extension attribute {name}: expected callable or None, "
            "but got: {value}")
    E093 = ("token.ent_iob values make invalid sequence: I without B\n{seq}")
    E094 = ("Error reading line {line_num} in vectors file {loc}.")
    E095 = ("Can't write to frozen dictionary. This is likely an internal "
            "error. Are you writing to a default function argument?")
    E096 = ("Invalid object passed to displaCy: Can only visualize `Doc` or "
            "Span objects, or dicts if set to `manual=True`.")
    E097 = ("Invalid pattern: expected token pattern (list of dicts) or "
            "phrase pattern (string) but got:\n{pattern}")
    E098 = ("Invalid pattern: expected both RIGHT_ID and RIGHT_ATTRS.")
    E099 = ("Invalid pattern: the first node of pattern should be an anchor "
            "node. The node should only contain RIGHT_ID and RIGHT_ATTRS.")
    E100 = ("Nodes other than the anchor node should all contain {required}, "
            "but these are missing: {missing}")
    E101 = ("RIGHT_ID should be a new node and LEFT_ID should already have "
            "have been declared in previous edges.")
    E102 = ("Can't merge non-disjoint spans. '{token}' is already part of "
            "tokens to merge. If you want to find the longest non-overlapping "
            "spans, you can use the util.filter_spans helper:\n"
            "https://spacy.io/api/top-level#util.filter_spans")
    E103 = ("Trying to set conflicting doc.ents: '{span1}' and '{span2}'. A "
            "token can only be part of one entity, so make sure the entities "
            "you're setting don't overlap. To work with overlapping entities, "
            "consider using doc.spans instead.")
    E106 = ("Can't find `doc._.{attr}` attribute specified in the underscore "
            "settings: {opts}")
    E107 = ("Value of custom attribute `{attr}` is not JSON-serializable: {value}")
    E109 = ("Component '{name}' could not be run. Did you forget to "
            "call `initialize()`?")
    E110 = ("Invalid displaCy render wrapper. Expected callable, got: {obj}")
    E111 = ("Pickling a token is not supported, because tokens are only views "
            "of the parent Doc and can't exist on their own. A pickled token "
            "would always have to include its Doc and Vocab, which has "
            "practically no advantage over pickling the parent Doc directly. "
            "So instead of pickling the token, pickle the Doc it belongs to.")
    E112 = ("Pickling a span is not supported, because spans are only views "
            "of the parent Doc and can't exist on their own. A pickled span "
            "would always have to include its Doc and Vocab, which has "
            "practically no advantage over pickling the parent Doc directly. "
            "So instead of pickling the span, pickle the Doc it belongs to or "
            "use Span.as_doc to convert the span to a standalone Doc object.")
    E115 = ("All subtokens must have associated heads.")
    E117 = ("The newly split tokens must match the text of the original token. "
            "New orths: {new}. Old text: {old}.")
    E118 = ("The custom extension attribute '{attr}' is not registered on the "
            "`Token` object so it can't be set during retokenization. To "
            "register an attribute, use the `Token.set_extension` classmethod.")
    E119 = ("Can't set custom extension attribute '{attr}' during "
            "retokenization because it's not writable. This usually means it "
            "was registered with a getter function (and no setter) or as a "
            "method extension, so the value is computed dynamically. To "
            "overwrite a custom attribute manually, it should be registered "
            "with a default value or with a getter AND setter.")
    E120 = ("Can't set custom extension attributes during retokenization. "
            "Expected dict mapping attribute names to values, but got: {value}")
    E121 = ("Can't bulk merge spans. Attribute length {attr_len} should be "
            "equal to span length ({span_len}).")
    E122 = ("Cannot find token to be split. Did it get merged?")
    E123 = ("Cannot find head of token to be split. Did it get merged?")
    E125 = ("Unexpected value: {value}")
    E126 = ("Unexpected matcher predicate: '{bad}'. Expected one of: {good}. "
            "This is likely a bug in spaCy, so feel free to open an issue.")
    E130 = ("You are running a narrow unicode build, which is incompatible "
            "with spacy >= 2.1.0. To fix this, reinstall Python and use a wide "
            "unicode build instead. You can also rebuild Python and set the "
            "`--enable-unicode=ucs4 flag`.")
    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 = ("Entity '{entity}' is not defined in the Knowledge Base.")
    E139 = ("Knowledge base for component '{name}' is empty.")
    E140 = ("The list of entities, prior probabilities and entity vectors "
            "should be of equal length.")
    E141 = ("Entity vectors should be of length {required} instead of the "
            "provided {found}.")
    E143 = ("Labels for component '{name}' not initialized. This can be fixed "
            "by calling add_label, or by providing a representative batch of "
            "examples to the component's `initialize` method.")
    E145 = ("Error reading `{param}` from input file.")
    E146 = ("Could not access {path}.")
    E147 = ("Unexpected error in the {method} functionality of the "
            "EntityLinker: {msg}. This is likely a bug in spaCy, so feel free "
            "to open an issue: https://github.com/explosion/spaCy/issues")
    E148 = ("Expected {ents} KB identifiers but got {ids}. Make sure that "
            "each entity in `doc.ents` is assigned to a KB identifier.")
    E149 = ("Error deserializing model. Check that the config used to create "
            "the component matches the model being loaded.")
    E150 = ("The language of the `nlp` object and the `vocab` should be the "
            "same, but found '{nlp}' and '{vocab}' respectively.")
    E152 = ("The attribute {attr} is not supported for token patterns. "
            "Please use the option `validate=True` with the Matcher, PhraseMatcher, "
            "SpanRuler or AttributeRuler for more details.")
    E153 = ("The value type {vtype} is not supported for token patterns. "
            "Please use the option validate=True with Matcher, PhraseMatcher, "
            "SpanRuler or AttributeRuler for more details.")
    E154 = ("One of the attributes or values is not supported for token "
            "patterns. Please use the option `validate=True` with the Matcher, "
            "PhraseMatcher, or SpanRuler for more details.")
    E155 = ("The pipeline needs to include a {pipe} in order to use "
            "Matcher or PhraseMatcher with the attribute {attr}. "
            "Try using `nlp()` instead of `nlp.make_doc()` or `list(nlp.pipe())` "
            "instead of `list(nlp.tokenizer.pipe())`.")
    E157 = ("Can't render negative values for dependency arc start or end. "
            "Make sure that you're passing in absolute token indices, not "
            "relative token offsets.\nstart: {start}, end: {end}, label: "
            "{label}, direction: {dir}")
    E158 = ("Can't add table '{name}' to lookups because it already exists.")
    E159 = ("Can't find table '{name}' in lookups. Available tables: {tables}")
    E160 = ("Can't find language data file: {path}")
    E161 = ("Found an internal inconsistency when predicting entity links. "
            "This is likely a bug in spaCy, so feel free to open an issue: "
            "https://github.com/explosion/spaCy/issues")
    E163 = ("cumsum was found to be unstable: its last element does not "
            "correspond to sum")
    E164 = ("x is neither increasing nor decreasing: {x}.")
    E165 = ("Only one class present in the gold labels: {label}. "
            "ROC AUC score is not defined in that case.")
    E166 = ("Can only merge DocBins with the same value for '{param}'.\n"
            "Current DocBin: {current}\nOther DocBin: {other}")
    E169 = ("Can't find module: {module}")
    E170 = ("Cannot apply transition {name}: invalid for the current state.")
    E171 = ("{name}.add received invalid 'on_match' callback argument: expected "
            "callable or None, but got: {arg_type}")
    E175 = ("Can't remove rule for unknown match pattern ID: {key}")
    E176 = ("Alias '{alias}' is not defined in the Knowledge Base.")
    E177 = ("Ill-formed IOB input detected: {tag}")
    E178 = ("Each pattern should be a list of dicts, but got: {pat}. Maybe you "
            "accidentally passed a single pattern to Matcher.add instead of a "
            "list of patterns? If you only want to add one pattern, make sure "
            "to wrap it in a list. For example: `matcher.add('{key}', [pattern])`")
    E179 = ("Invalid pattern. Expected a list of Doc objects but got a single "
            "Doc. If you only want to add one pattern, make sure to wrap it "
            "in a list. For example: `matcher.add('{key}', [doc])`")
    E180 = ("Span attributes can't be declared as required or assigned by "
            "components, since spans are only views of the Doc. Use Doc and "
            "Token attributes (or custom extension attributes) only and remove "
            "the following: {attrs}")
    E181 = ("Received invalid attributes for unknown object {obj}: {attrs}. "
            "Only Doc and Token attributes are supported.")
    E182 = ("Received invalid attribute declaration: {attr}\nDid you forget "
            "to define the attribute? For example: `{attr}.???`")
    E183 = ("Received invalid attribute declaration: {attr}\nOnly top-level "
            "attributes are supported, for example: {solution}")
    E184 = ("Only attributes without underscores are supported in component "
            "attribute declarations (because underscore and non-underscore "
            "attributes are connected anyways): {attr} -> {solution}")
    E185 = ("Received invalid attribute in component attribute declaration: "
            "`{obj}.{attr}`\nAttribute '{attr}' does not exist on {obj}.")
    E187 = ("Only unicode strings are supported as labels.")
    E189 = ("Each argument to `Doc.__init__` should be of equal length.")
    E190 = ("Token head out of range in `Doc.from_array()` for token index "
            "'{index}' with value '{value}' (equivalent to relative head "
            "index: '{rel_head_index}'). The head indices should be relative "
            "to the current token index rather than absolute indices in the "
            "array.")
    E191 = ("Invalid head: the head token must be from the same doc as the "
            "token itself.")
    E192 = ("Unable to resize vectors in place with cupy.")
    E193 = ("Unable to resize vectors in place if the resized vector dimension "
            "({new_dim}) is not the same as the current vector dimension "
            "({curr_dim}).")
    E194 = ("Unable to aligned mismatched text '{text}' and words '{words}'.")
    E195 = ("Matcher can be called on {good} only, got {got}.")
    E196 = ("Refusing to write to `token.is_sent_end`. Sentence boundaries can "
            "only be fixed with `token.is_sent_start`.")
    E197 = ("Row out of bounds, unable to add row {row} for key {key}.")
    E198 = ("Unable to return {n} most similar vectors for the current vectors "
            "table, which contains {n_rows} vectors.")
    E199 = ("Unable to merge 0-length span at `doc[{start}:{end}]`.")
    E200 = ("Can't set {attr} from Span.")
    E202 = ("Unsupported {name} mode '{mode}'. Supported modes: {modes}.")
    E203 = ("If the {name} embedding layer is not updated "
            "during training, make sure to include it in 'annotating components'")

    # New errors added in v3.x
    E849 = ("The vocab only supports {method} for vectors of type "
            "spacy.vectors.Vectors, not {vectors_type}.")
    E850 = ("The PretrainVectors objective currently only supports default or "
            "floret vectors, not {mode} vectors.")
    E851 = ("The 'textcat' component labels should only have values of 0 or 1, "
            "but found value of '{val}'.")
    E853 = ("Unsupported component factory name '{name}'. The character '.' is "
            "not permitted in factory names.")
    E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "
            "permit overlapping spans.")
    E855 = ("Invalid {obj}: {obj} is not from the same doc.")
    E856 = ("Error accessing span at position {i}: out of bounds in span group "
            "of length {length}.")
    E857 = ("Entry '{name}' not found in edit tree lemmatizer labels.")
    E858 = ("The {mode} vector table does not support this operation. "
            "{alternative}")
    E859 = ("The floret vector table cannot be modified.")
    E860 = ("Can't truncate floret vectors.")
    E861 = ("No 'keys' should be provided when initializing floret vectors "
            "with 'minn' and 'maxn'.")
    E862 = ("'hash_count' must be between 1-4 for floret vectors.")
    E863 = ("'maxn' must be greater than or equal to 'minn'.")
    E864 = ("The complete vector table 'data' is required to initialize floret "
            "vectors.")
    E865 = ("A SpanGroup is not functional after the corresponding Doc has "
            "been garbage collected. To keep using the spans, make sure that "
            "the corresponding Doc object is still available in the scope of "
            "your function.")
    E866 = ("Expected a string or 'Doc' as input, but got: {type}.")
    E867 = ("The 'textcat' component requires at least two labels because it "
            "uses mutually exclusive classes where exactly one label is True "
            "for each doc. For binary classification tasks, you can use two "
            "labels with 'textcat' (LABEL / NOT_LABEL) or alternatively, you "
            "can use the 'textcat_multilabel' component with one label.")
    E868 = ("Found a conflicting gold annotation in a reference document, "
            "with the following char-based span occurring both in the gold ents "
            "as well as in the negative spans: {span}.")
    E869 = ("The notation '{label}' is not supported anymore. To annotate "
            "negative NER samples, use `doc.spans[key]` instead, and "
            "specify the key as 'incorrect_spans_key' when constructing "
            "the NER component.")
    E870 = ("Could not serialize the DocBin because it is too large. Consider "
            "splitting up your documents into several doc bins and serializing "
            "each separately. spacy.Corpus.v1 will search recursively for all "
            "*.spacy files if you provide a directory instead of a filename as "
            "the 'path'.")
    E871 = ("Error encountered in nlp.pipe with multiprocessing:\n\n{error}")
    E872 = ("Unable to copy tokenizer from base model due to different "
            'tokenizer settings: current tokenizer config "{curr_config}" '
            'vs. base model "{base_config}"')
    E873 = ("Unable to merge a span from doc.spans with key '{key}' and text "
            "'{text}'. This is likely a bug in spaCy, so feel free to open an "
            "issue: https://github.com/explosion/spaCy/issues")
    E874 = ("Could not initialize the tok2vec model from component "
            "'{component}' and layer '{layer}'.")
    E875 = ("To use the PretrainVectors objective, make sure that static vectors are loaded. "
            "In the config, these are defined by the initialize.vectors setting.")
    E879 = ("Unexpected type for 'spans' data. Provide a dictionary mapping keys to "
            "a list of spans, with each span represented by a tuple (start_char, end_char). "
            "The tuple can be optionally extended with a label and a KB ID.")
    E884 = ("The pipeline could not be initialized because the vectors "
            "could not be found at '{vectors}'. If your pipeline was already "
            "initialized/trained before, call 'resume_training' instead of 'initialize', "
            "or initialize only the components that are new.")
    E885 = ("entity_linker.set_kb received an invalid 'kb_loader' argument: expected "
            "a callable function, but got: {arg_type}")
    E886 = ("Can't replace {name} -> {tok2vec} listeners: path '{path}' not "
            "found in config for component '{name}'.")
    E887 = ("Can't replace {name} -> {tok2vec} listeners: the paths to replace "
            "({paths}) don't match the available listeners in the model ({n_listeners}).")
    E888 = ("Can't replace listeners for '{name}' ({pipe}): invalid upstream "
            "component that doesn't seem to support listeners. Expected Tok2Vec "
            "or Transformer component. If you didn't call nlp.replace_listeners "
            "manually, this is likely a bug in spaCy.")
    E889 = ("Can't replace '{tok2vec}' listeners of component '{name}' because "
            "'{unknown}' is not in the pipeline. Available components: {opts}. "
            "If you didn't call nlp.replace_listeners manually, this is likely "
            "a bug in spaCy.")
    E890 = ("Cannot add the alias '{alias}' to the Knowledge base. "
            "Each alias should be a meaningful string.")
    E891 = ("Alias '{alias}' could not be added to the Knowledge base. "
            "This is likely a bug in spaCy.")
    E892 = ("Unknown function registry: '{name}'.\n\nAvailable names: {available}")
    E893 = ("Could not find function '{name}' in function registry '{reg_name}'. "
            "If you're using a custom function, make sure the code is available. "
            "If the function is provided by a third-party package, e.g. "
            "spacy-transformers, make sure the package is installed in your "
            "environment.\n\nAvailable names: {available}")
    E894 = ("The 'noun_chunks' syntax iterator is not implemented for language "
            "'{lang}'.")
    E895 = ("The 'textcat' component received gold-standard annotations with "
            "multiple labels per document. In spaCy 3 you should use the "
            "'textcat_multilabel' component for this instead. "
            "Example of an offending annotation: {value}")
    E896 = ("There was an error using the static vectors. Ensure that the vectors "
            "of the vocab are properly initialized, or set 'include_static_vectors' "
            "to False.")
    E897 = ("Field '{field}' should be a dot-notation string referring to the "
            "relevant section in the config, but found type {type} instead.")
    E898 = ("Can't serialize trainable pipe '{name}': the `model` attribute "
            "is not set or None. If you've implemented a custom component, make "
            "sure to store the component model as `self.model` in your "
            "component's __init__ method.")
    E899 = ("Can't serialize trainable pipe '{name}': the `vocab` attribute "
            "is not set or None. If you've implemented a custom component, make "
            "sure to store the current `nlp` object's vocab as `self.vocab` in "
            "your component's __init__ method.")
    E900 = ("Could not run the full pipeline for evaluation. If you specified "
            "frozen components, make sure they were already initialized and "
            "trained. Full pipeline: {pipeline}")
    E901 = ("Failed to remove existing output directory: {path}. If your "
            "config and the components you train change between runs, a "
            "non-empty output directory can lead to stale pipeline data. To "
            "solve this, remove the existing directories in the output directory.")
    E902 = ("The sentence-per-line IOB/IOB2 file is not formatted correctly. "
            "Try checking whitespace and delimiters. See "
            "https://spacy.io/api/cli#convert")
    E903 = ("The token-per-line NER file is not formatted correctly. Try checking "
            "whitespace and delimiters. See https://spacy.io/api/cli#convert")
    E904 = ("Cannot initialize StaticVectors layer: nO dimension unset. This "
            "dimension refers to the output width, after the linear projection "
            "has been applied.")
    E905 = ("Cannot initialize StaticVectors layer: nM dimension unset. This "
            "dimension refers to the width of the vectors table.")
    E906 = ("Unexpected `loss` value in pretraining objective: '{found}'. Supported values "
            "are: {supported}")
    E908 = ("Can't set `spaces` without `words` in `Doc.__init__`.")
    E909 = ("Expected {name} in parser internals. This is likely a bug in spaCy.")
    E910 = ("Encountered NaN value when computing loss for component '{name}'.")
    E911 = ("Invalid feature: {feat}. Must be a token attribute.")
    E912 = ("Failed to initialize lemmatizer. Missing lemmatizer table(s) found "
            "for mode '{mode}'. Required tables: {tables}. Found: {found}.")
    E913 = ("Corpus path can't be None. Maybe you forgot to define it in your "
            ".cfg file or override it on the CLI?")
    E914 = ("Executing {name} callback failed. Expected the function to "
            "return the nlp object but got: {value}. Maybe you forgot to return "
            "the modified object in your function?")
    E915 = ("Can't use score '{name}' to calculate final weighted score. Expected "
            "float or int but got: {score_type}. To exclude the score from the "
            "final score, set its weight to null in the [training.score_weights] "
            "section of your training config.")
    E916 = ("Can't log score for '{name}' in table: not a valid score ({score_type})")
    E917 = ("Received invalid value {value} for `state_type` in "
            "TransitionBasedParser: only 'parser' or 'ner' are valid options.")
    E918 = ("Received invalid value for vocab: {vocab} ({vocab_type}). Valid "
            "values are an instance of `spacy.vocab.Vocab` or True to create one"
            " (default).")
    E919 = ("A textcat `positive_label` '{pos_label}' was provided for training "
            "data that does not appear to be a binary classification problem "
            "with two labels. Labels found: {labels}")
    E920 = ("The textcat's `positive_label` setting '{pos_label}' "
            "does not match any label in the training data or provided during "
            "initialization. Available labels: {labels}")
    E921 = ("The method `set_output` can only be called on components that have "
            "a Model with a `resize_output` attribute. Otherwise, the output "
            "layer can not be dynamically changed.")
    E922 = ("Component '{name}' has been initialized with an output dimension of "
            "{nO} - cannot add any more labels.")
    E923 = ("It looks like there is no proper sample data to initialize the "
            "Model of component '{name}'. To check your input data paths and "
            "annotation, run: python -m spacy debug data config.cfg "
            "and include the same config override values you would specify "
            "for the 'spacy train' command.")
    E924 = ("The '{name}' component does not seem to be initialized properly. "
            "This is likely a bug in spaCy, so feel free to open an issue: "
            "https://github.com/explosion/spaCy/issues")
    E925 = ("Invalid color values for displaCy visualizer: expected dictionary "
            "mapping label names to colors but got: {obj}")
    E926 = ("It looks like you're trying to modify `nlp.{attr}` directly. This "
            "doesn't work because it's an immutable computed property. If you "
            "need to modify the pipeline, use the built-in methods like "
            "`nlp.add_pipe`, `nlp.remove_pipe`, `nlp.disable_pipe` or "
            "`nlp.enable_pipe` instead.")
    E927 = ("Can't write to frozen list. Maybe you're trying to modify a computed "
            "property or default function argument?")
    E928 = ("An InMemoryLookupKB can only be serialized to/from from a directory, "
            "but the provided argument {loc} points to a file.")
    E929 = ("Couldn't read InMemoryLookupKB from {loc}. The path does not seem to exist.")
    E930 = ("Received invalid get_examples callback in `{method}`. "
            "Expected function that returns an iterable of Example objects but "
            "got: {obj}")
    E931 = ("Encountered {parent} subclass without `{parent}.{method}` "
            "method in component '{name}'. If you want to use this "
            "method, make sure it's overwritten on the subclass.")
    E940 = ("Found NaN values in scores.")
    E942 = ("Executing `after_{name}` callback failed. Expected the function to "
            "return an initialized nlp object but got: {value}. Maybe "
            "you forgot to return the modified object in your function?")
    E943 = ("Executing `before_creation` callback failed. Expected the function to "
            "return an uninitialized Language subclass but got: {value}. Maybe "
            "you forgot to return the modified object in your function or "
            "returned the initialized nlp object instead?")
    E944 = ("Can't copy pipeline component '{name}' from source '{model}': "
            "not found in pipeline. Available components: {opts}")
    E945 = ("Can't copy pipeline component '{name}' from source. Expected "
            "loaded nlp object, but got: {source}")
    E947 = ("`Matcher.add` received invalid `greedy` argument: expected "
            "a string value from {expected} but got: '{arg}'")
    E948 = ("`{name}.add` received invalid 'patterns' argument: expected "
            "a list, but got: {arg_type}")
    E949 = ("Unable to align tokens for the predicted and reference docs. It "
            "is only possible to align the docs when both texts are the same "
            "except for whitespace and capitalization. The predicted tokens "
            "start with: {x}. The reference tokens start with: {y}.")
    E952 = ("The section '{name}' is not a valid section in the provided config.")
    E953 = ("Mismatched IDs received by the Tok2Vec listener: {id1} vs. {id2}")
    E954 = ("The Tok2Vec listener did not receive any valid input from an upstream "
            "component.")
    E955 = ("Can't find table(s) {table} for language '{lang}' in "
            "spacy-lookups-data. Make sure you have the package installed or "
            "provide your own lookup tables if no default lookups are available "
            "for your language.")
    E956 = ("Can't find component '{name}' in [components] block in the config. "
            "Available components: {opts}")
    E957 = ("Writing directly to `Language.factories` isn't needed anymore in "
            "spaCy v3. Instead, you can use the `@Language.factory` decorator "
            "to register your custom component factory or `@Language.component` "
            "to register a simple stateless function component that just takes "
            "a Doc and returns it.")
    E958 = ("Language code defined in config ({bad_lang_code}) does not match "
            "language code of current Language subclass {lang} ({lang_code}). "
            "If you want to create an nlp object from a config, make sure to "
            "use the matching subclass with the language-specific settings and "
            "data.")
    E959 = ("Can't insert component {dir} index {idx}. Existing components: {opts}")
    E960 = ("No config data found for component '{name}'. This is likely a bug "
            "in spaCy.")
    E961 = ("Found non-serializable Python object in config. Configs should "
            "only include values that can be serialized to JSON. If you need "
            "to pass models or other objects to your component, use a reference "
            "to a registered function or initialize the object in your "
            "component.\n\n{config}")
    E962 = ("Received incorrect {style} for pipe '{name}'. Expected dict, "
            "got: {cfg_type}.")
    E963 = ("Can't read component info from `@Language.{decorator}` decorator. "
            "Maybe you forgot to call it? Make sure you're using "
            "`@Language.{decorator}()` instead of `@Language.{decorator}`.")
    E964 = ("The pipeline component factory for '{name}' needs to have the "
            "following named arguments, which are passed in by spaCy:\n- nlp: "
            "receives the current nlp object and lets you access the vocab\n- "
            "name: the name of the component instance, can be used to identify "
            "the component, output losses etc.")
    E965 = ("It looks like you're using the `@Language.component` decorator to "
            "register '{name}' on a class instead of a function component. If "
            "you need to register a class or function that *returns* a component "
            "function, use the `@Language.factory` decorator instead.")
    E966 = ("`nlp.add_pipe` now takes the string name of the registered component "
            "factory, not a callable component. Expected string, but got "
            "{component} (name: '{name}').\n\n- If you created your component "
            "with `nlp.create_pipe('name')`: remove nlp.create_pipe and call "
            "`nlp.add_pipe('name')` instead.\n\n- If you passed in a component "
            "like `TextCategorizer()`: call `nlp.add_pipe` with the string name "
            "instead, e.g. `nlp.add_pipe('textcat')`.\n\n- If you're using a custom "
            "component: Add the decorator `@Language.component` (for function "
            "components) or `@Language.factory` (for class components / factories) "
            "to your custom component and assign it a name, e.g. "
            "`@Language.component('your_name')`. You can then run "
            "`nlp.add_pipe('your_name')` to add it to the pipeline.")
    E967 = ("No {meta} meta information found for '{name}'. This is likely a bug in spaCy.")
    E968 = ("`nlp.replace_pipe` now takes the string name of the registered component "
            "factory, not a callable component. Expected string, but got "
            "{component}.\n\n- If you created your component with"
            "with `nlp.create_pipe('name')`: remove `nlp.create_pipe` and call "
            "`nlp.replace_pipe('{name}', 'name')` instead.\n\n- If you passed in a "
            "component like `TextCategorizer()`: call `nlp.replace_pipe` with the "
            "string name instead, e.g. `nlp.replace_pipe('{name}', 'textcat')`.\n\n"
            "- If you're using a custom component: Add the decorator "
            "`@Language.component` (for function components) or `@Language.factory` "
            "(for class components / factories) to your custom component and "
            "assign it a name, e.g. `@Language.component('your_name')`. You can "
            "then run `nlp.replace_pipe('{name}', 'your_name')`.")
    E969 = ("Expected string values for field '{field}', but received {types} instead. ")
    E970 = ("Can not execute command '{str_command}'. Do you have '{tool}' installed?")
    E971 = ("Found incompatible lengths in `Doc.from_array`: {array_length} for the "
            "array and {doc_length} for the Doc itself.")
    E972 = ("`Example.__init__` got None for '{arg}'. Requires Doc.")
    E973 = ("Unexpected type for NER data")
    E974 = ("Unknown {obj} attribute: {key}")
    E976 = ("The method `Example.from_dict` expects a {type} as {n} argument, "
            "but received None.")
    E977 = ("Can not compare a MorphAnalysis with a string object. "
            "This is likely a bug in spaCy, so feel free to open an issue: "
            "https://github.com/explosion/spaCy/issues")
    E978 = ("The {name} method takes a list of Example objects, but got: {types}")
    E980 = ("Each link annotation should refer to a dictionary with at most one "
            "identifier mapping to 1.0, and all others to 0.0.")
    E981 = ("The offsets of the annotations for `links` could not be aligned "
            "to token boundaries.")
    E982 = ("The `Token.ent_iob` attribute should be an integer indexing "
            "into {values}, but found {value}.")
    E983 = ("Invalid key(s) for '{dict}': {key}. Available keys: "
            "{keys}")
    E984 = ("Invalid component config for '{name}': component block needs either "
            "a key `factory` specifying the registered function used to "
            "initialize the component, or a key `source` key specifying a "
            "spaCy model to copy the component from. For example, `factory = "
            "\"ner\"` will use the 'ner' factory and all other settings in the "
            "block will be passed to it as arguments. Alternatively, `source = "
            "\"en_core_web_sm\"` will copy the component from that model.\n\n{config}")
    E985 = ("Can't load model from config file: no [nlp] section found.\n\n{config}")
    E986 = ("Could not create any training batches: check your input. "
            "Are the train and dev paths defined? Is `discard_oversize` set appropriately? ")
    E989 = ("`nlp.update()` was called with two positional arguments. This "
            "may be due to a backwards-incompatible change to the format "
            "of the training data in spaCy 3.0 onwards. The 'update' "
            "function should now be called with a batch of Example "
            "objects, instead of `(text, annotation)` tuples. ")
    E991 = ("The function `nlp.select_pipes` should be called with either a "
            "`disable` argument to list the names of the pipe components "
            "that should be disabled, or with an 'enable' argument that "
            "specifies which pipes should not be disabled.")
    E992 = ("The function `select_pipes` was called with `enable`={enable} "
            "and `disable`={disable} but that information is conflicting "
            "for the `nlp` pipeline with components {names}.")
    E993 = ("The config for the nlp object needs to include a key `lang` specifying "
            "the code of the language to initialize it with (for example "
            "'en' for English) - this can't be None.\n\n{config}")
    E997 = ("Tokenizer special cases are not allowed to modify the text. "
            "This would map '{chunk}' to '{orth}' given token attributes "
            "'{token_attrs}'.")
    E999 = ("Unable to merge the Doc objects because they do not all share "
            "the same `Vocab`.")
    E1000 = ("The Chinese word segmenter is pkuseg but no pkuseg model was "
             "loaded. Provide the name of a pretrained model or the path to "
             "a model and initialize the pipeline:\n\n"
             'nlp.tokenizer.initialize(pkuseg_model="default")')
    E1001 = ("Target token outside of matched span for match with tokens "
             "'{span}' and offset '{index}' matched by patterns '{patterns}'.")
    E1002 = ("Span index out of range.")
    E1003 = ("Unsupported lemmatizer mode '{mode}'.")
    E1004 = ("Missing lemmatizer table(s) found for lemmatizer mode '{mode}'. "
             "Required tables: {tables}. Found: {found}. Maybe you forgot to "
             "call `nlp.initialize()` to load in the data?")
    E1005 = ("Unable to set attribute '{attr}' in tokenizer exception for "
             "'{chunk}'. Tokenizer exceptions are only allowed to specify "
             "ORTH and NORM.")
    E1007 = ("Unsupported DependencyMatcher operator '{op}'.")
    E1008 = ("Invalid pattern: each pattern should be a list of dicts. Check "
             "that you are providing a list of patterns as `List[List[dict]]`.")
    E1010 = ("Unable to set entity information for token {i} which is included "
             "in more than one span in entities, blocked, missing or outside.")
    E1011 = ("Unsupported default '{default}' in `doc.set_ents`. Available "
             "options: {modes}")
    E1012 = ("Entity spans and blocked/missing/outside spans should be "
             "provided to `doc.set_ents` as lists of Span objects.")
    E1013 = ("Invalid morph: the MorphAnalysis must have the same vocab as the "
             "token itself. To set the morph from this MorphAnalysis, set from "
             "the string value with: `token.set_morph(str(other_morph))`.")
    E1014 = ("Error loading DocBin data. It doesn't look like the data is in "
             "DocBin (.spacy) format. If your data is in spaCy v2's JSON "
             "training format, convert it using `python -m spacy convert "
             "file.json .`.")
    E1015 = ("Can't initialize model from config: no {value} found. For more "
             "information, run: python -m spacy debug config config.cfg")
    E1016 = ("The operators 'OP': '?', '*', and '+' are not supported in "
             "DependencyMatcher token patterns. The token pattern in "
             "RIGHT_ATTR should return matches that are each exactly one token "
             "long. Invalid pattern:\n{node}")
    E1017 = ("A Doc object requires both 'deps' and 'heads' for dependency "
             "parses. If no dependency labels are available, provide "
             "placeholder deps such as `deps=[\"dep\"]*len(heads)`.")
    E1018 = ("Knowledge base for component '{name}' is not set. "
             "Make sure either `nel.initialize` or `nel.set_kb` "
             "is called with a `kb_loader` function.")
    E1019 = ("`noun_chunks` requires the pos tagging, which requires a "
             "statistical model to be installed and loaded. For more info, see "
             "the documentation:\nhttps://spacy.io/usage/models")
    E1020 = ("No `epoch_resume` value specified and could not infer one from "
             "filename. Specify an epoch to resume from.")
    E1021 = ("`pos` value \"{pp}\" is not a valid Universal Dependencies tag. "
             "Non-UD tags should use the `tag` property.")
    E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
    E1024 = ("A pattern with {attr_type} '{label}' is not present in "
             "'{component}' patterns.")
    E1025 = ("Cannot intify the value '{value}' as an IOB string. The only "
             "supported values are: 'I', 'O', 'B' and ''")
    E1026 = ("Edit tree has an invalid format:\n{errors}")
    E1027 = ("AlignmentArray only supports slicing with a step of 1.")
    E1028 = ("AlignmentArray only supports indexing using an int or a slice.")
    E1029 = ("Edit tree cannot be applied to form.")
    E1030 = ("Edit tree identifier out of range.")
    E1031 = ("Could not find gold transition - see logs above.")
    E1032 = ("Span {var} {value} is out of bounds for {obj} with length {length}.")
    E1033 = ("Dimension {name} invalid -- only nO, nF, nP")
    E1034 = ("Node index {i} out of bounds ({length})")
    E1035 = ("Token index {i} out of bounds ({length})")
    E1036 = ("Cannot index into NoneNode")
    E1037 = ("Invalid attribute value '{attr}'.")
    E1038 = ("Invalid JSON input: {message}")
    E1039 = ("The {obj} start or end annotations (start: {start}, end: {end}) "
             "could not be aligned to token boundaries.")
    E1040 = ("Doc.from_json requires all tokens to have the same attributes. "
             "Some tokens do not contain annotation for: {partial_attrs}")
    E1041 = ("Expected a string, Doc, or bytes as input, but got: {type}")
    E1042 = ("`enable={enable}` and `disable={disable}` are inconsistent with each other.\nIf you only passed "
             "one of `enable` or `disable`, the other argument is specified in your pipeline's configuration.\nIn that "
             "case pass an empty list for the previously not specified argument to avoid this error.")
    E1043 = ("Expected None or a value in range [{range_start}, {range_end}] for entity linker threshold, but got "
             "{value}.")
    E1045 = ("Encountered {parent} subclass without `{parent}.{method}` "
             "method in '{name}'. If you want to use this method, make "
             "sure it's overwritten on the subclass.")
    E1046 = ("{cls_name} is an abstract class and cannot be instantiated. If you are looking for spaCy's default "
             "knowledge base, use `InMemoryLookupKB`.")
    E1047 = ("`find_threshold()` only supports components with a `scorer` attribute.")
    E1048 = ("Got '{unexpected}' as console progress bar type, but expected one of the following: {expected}")
    E1049 = ("No available port found for displaCy on host {host}. Please specify an available port "
             "with `displacy.serve(doc, port=port)`")
    E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
             "or use `auto_select_port=True` to pick an available port automatically.")
    E1051 = ("'allow_overlap' can only be False when max_positive is 1, but found 'max_positive': {max_positive}.")
    E1052 = ("Unable to copy spans: the character offsets for the span at "
             "index {i} in the span group do not align with the tokenization "
             "in the target doc.")
    E1053 = ("Both 'min_length' and 'max_length' should be larger than 0, but found"
             " 'min_length': {min_length}, 'max_length': {max_length}")
    E1054 = ("The text, including whitespace, must match between reference and "
             "predicted docs when training {component}.")
    E1055 = ("The 'replace_listener' callback expects {num_params} parameters, "
             "but only callbacks with one or three parameters are supported")
    E1056 = ("The `TextCatBOW` architecture expects a length of at least 1, was {length}.")
    E1057 = ("The `TextCatReduce` architecture must be used with at least one "
             "reduction. Please enable one of `use_reduce_first`, "
             "`use_reduce_last`, `use_reduce_max` or `use_reduce_mean`.")

    # v4 error strings
    E4000 = ("Expected a Doc as input, but got: '{type}'")
    E4001 = ("Expected input to be one of the following types: ({expected_types}), "
             "but got '{received_type}'")
    E4002 = ("Pipe '{name}' requires a teacher pipe for distillation.")
    E4003 = ("Training examples for distillation must have the exact same tokens in the "
             "reference and predicted docs.")
    E4004 = ("Backprop is not supported when is_train is not set.")
    E4005 = ("EntityLinker_v1 is not supported in spaCy v4. Update your configuration.")
    E4006 = ("Expected `entity_id` to be of type {exp_type}, but is of type {found_type}.")
    E4007 = ("Span {var} {value} must be {op} Span {existing_var} "
             "{existing_value}.")
    E4008 = ("Span {pos}_char {value} does not correspond to a token {pos}.")
    E4009 = ("The '{attr}' parameter should be 'None' or 'True', but found '{value}'.")
    E4010 = ("Required lemmatizer table(s) {missing_tables} not found in "
             "[initialize] or in registered lookups (spacy-lookups-data). An "
             "example for how to load lemmatizer tables in [initialize]:\n\n"
             "[initialize.components]\n\n"
             "[initialize.components.{pipe_name}]\n\n"
             "[initialize.components.{pipe_name}.lookups]\n"
             '@misc = "spacy.LookupsDataLoaderFromURL.v1"\n'
             "lang = ${{nlp.lang}}\n"
             f'url = "{about.__lookups_url__}"\n'
             "tables = {tables}\n"
             "# or required tables only: tables = {required_tables}\n")
    E4011 = ("Server error ({status_code}), couldn't fetch {url}")


RENAMED_LANGUAGE_CODES = {"xx": "mul", "is": "isl"}

# fmt: on


class MatchPatternError(ValueError):
    def __init__(self, key, errors):
        """Custom error for validating match patterns.

        key (str): The name of the matcher rule.
        errors (dict): Validation errors (sequence of strings) mapped to pattern
            ID, i.e. the index of the added pattern.
        """
        msg = f"Invalid token patterns for matcher rule '{key}'\n"
        for pattern_idx, error_msgs in errors.items():
            pattern_errors = "\n".join([f"- {e}" for e in error_msgs])
            msg += f"\nPattern {pattern_idx}:\n{pattern_errors}\n"
        ValueError.__init__(self, msg)