spaCy/spacy/matcher.pyx

# cython: profile=True
# cython: infer_types=True
# coding: utf8
from __future__ import unicode_literals

import ujson

from .typedefs cimport attr_t
from .typedefs cimport hash_t
from .attrs cimport attr_id_t
from .structs cimport TokenC

from cymem.cymem cimport Pool
from preshed.maps cimport PreshMap
from libcpp.vector cimport vector
from libcpp.pair cimport pair
from murmurhash.mrmr cimport hash64
from libc.stdint cimport int32_t

from .attrs cimport ID, ENT_TYPE
from . import attrs
from .tokens.doc cimport get_token_attr
from .tokens.doc cimport Doc
from .vocab cimport Vocab

from .attrs import FLAG61 as U_ENT

from .attrs import FLAG60 as B2_ENT
from .attrs import FLAG59 as B3_ENT
from .attrs import FLAG58 as B4_ENT
from .attrs import FLAG57 as B5_ENT
from .attrs import FLAG56 as B6_ENT
from .attrs import FLAG55 as B7_ENT
from .attrs import FLAG54 as B8_ENT
from .attrs import FLAG53 as B9_ENT
from .attrs import FLAG52 as B10_ENT

from .attrs import FLAG51 as I3_ENT
from .attrs import FLAG50 as I4_ENT
from .attrs import FLAG49 as I5_ENT
from .attrs import FLAG48 as I6_ENT
from .attrs import FLAG47 as I7_ENT
from .attrs import FLAG46 as I8_ENT
from .attrs import FLAG45 as I9_ENT
from .attrs import FLAG44 as I10_ENT

from .attrs import FLAG43 as L2_ENT
from .attrs import FLAG42 as L3_ENT
from .attrs import FLAG41 as L4_ENT
from .attrs import FLAG40 as L5_ENT
from .attrs import FLAG39 as L6_ENT
from .attrs import FLAG38 as L7_ENT
from .attrs import FLAG37 as L8_ENT
from .attrs import FLAG36 as L9_ENT
from .attrs import FLAG35 as L10_ENT


cpdef enum quantifier_t:
    _META
    ONE
    ZERO
    ZERO_ONE
    ZERO_PLUS


cdef enum action_t:
    REJECT
    ADVANCE
    REPEAT
    ACCEPT
    ADVANCE_ZERO
    PANIC


cdef struct AttrValueC:
    attr_id_t attr
    attr_t value


cdef struct TokenPatternC:
    AttrValueC* attrs
    int32_t nr_attr
    quantifier_t quantifier


ctypedef TokenPatternC* TokenPatternC_ptr
ctypedef pair[int, TokenPatternC_ptr] StateC


cdef TokenPatternC* init_pattern(Pool mem, attr_t entity_id,
                                 object token_specs) except NULL:
    pattern = <TokenPatternC*>mem.alloc(len(token_specs) + 1, sizeof(TokenPatternC))
    cdef int i
    for i, (quantifier, spec) in enumerate(token_specs):
        pattern[i].quantifier = quantifier
        pattern[i].attrs = <AttrValueC*>mem.alloc(len(spec), sizeof(AttrValueC))
        pattern[i].nr_attr = len(spec)
        for j, (attr, value) in enumerate(spec):
            pattern[i].attrs[j].attr = attr
            pattern[i].attrs[j].value = value
    i = len(token_specs)
    pattern[i].attrs = <AttrValueC*>mem.alloc(2, sizeof(AttrValueC))
    pattern[i].attrs[0].attr = ID
    pattern[i].attrs[0].value = entity_id
    pattern[i].nr_attr = 0
    return pattern


cdef attr_t get_pattern_key(const TokenPatternC* pattern) except 0:
    while pattern.nr_attr != 0:
        pattern += 1
    id_attr = pattern[0].attrs[0]
    assert id_attr.attr == ID
    return id_attr.value


cdef int get_action(const TokenPatternC* pattern, const TokenC* token) nogil:
    for attr in pattern.attrs[:pattern.nr_attr]:
        if get_token_attr(token, attr.attr) != attr.value:
            if pattern.quantifier == ONE:
                return REJECT
            elif pattern.quantifier == ZERO:
                return ACCEPT if (pattern+1).nr_attr == 0 else ADVANCE
            elif pattern.quantifier in (ZERO_ONE, ZERO_PLUS):
                return ACCEPT if (pattern+1).nr_attr == 0 else ADVANCE_ZERO
            else:
                return PANIC
    if pattern.quantifier == ZERO:
        return REJECT
    elif pattern.quantifier in (ONE, ZERO_ONE):
        return ACCEPT if (pattern+1).nr_attr == 0 else ADVANCE
    elif pattern.quantifier == ZERO_PLUS:
        return REPEAT
    else:
        return PANIC


def _convert_strings(token_specs, string_store):
    # Support 'syntactic sugar' operator '+', as combination of ONE, ZERO_PLUS
    operators = {'!': (ZERO,), '*': (ZERO_PLUS,), '+': (ONE, ZERO_PLUS),
            '?': (ZERO_ONE,), '1': (ONE,)}
    tokens = []
    op = ONE
    for spec in token_specs:
        token = []
        ops = (ONE,)
        for attr, value in spec.items():
            if isinstance(attr, basestring) and attr.upper() == 'OP':
                if value in operators:
                    ops = operators[value]
                else:
                    raise KeyError(
                        "Unknown operator '%s'. Options: %s" % (value, ', '.join(operators.keys())))
            if isinstance(attr, basestring):
                attr = attrs.IDS.get(attr.upper())
            if isinstance(value, basestring):
                value = string_store.add(value)
            if isinstance(value, bool):
                value = int(value)
            if attr is not None:
                token.append((attr, value))
        for op in ops:
            tokens.append((op, token))
    return tokens


def merge_phrase(matcher, doc, i, matches):
    """Callback to merge a phrase on match."""
    ent_id, label, start, end = matches[i]
    span = doc[start : end]
    span.merge(ent_type=label, ent_id=ent_id)


cdef class Matcher:
    """Match sequences of tokens, based on pattern rules."""
    cdef Pool mem
    cdef vector[TokenPatternC*] patterns
    cdef readonly Vocab vocab
    cdef public object _patterns
    cdef public object _entities
    cdef public object _callbacks
    cdef public object _acceptors

    def __init__(self, vocab):
        """Create the Matcher.

        vocab (Vocab): The vocabulary object, which must be shared with the
            documents the matcher will operate on.
        RETURNS (Matcher): The newly constructed object.
        """
        self._patterns = {}
        self._entities = {}
        self._acceptors = {}
        self._callbacks = {}
        self.vocab = vocab
        self.mem = Pool()

    def __reduce__(self):
        return (self.__class__, (self.vocab, self._patterns), None, None)

    def __len__(self):
        """Get the number of rules added to the matcher. Note that this only
        returns the number of rules (identical with the number of IDs), not the
        number of individual patterns.

        RETURNS (int): The number of rules.
        """
        return len(self._patterns)

    def __contains__(self, key):
        """Check whether the matcher contains rules for a match ID.

        key (unicode): The match ID.
        RETURNS (bool): Whether the matcher contains rules for this match ID.
        """
        return len(self._patterns)

    def add(self, key, on_match, *patterns):
        """Add a match-rule to the matcher.
        A match-rule consists of: an ID key, an on_match callback, and one or
        more patterns. If the key exists, the patterns are appended to the
        previous ones, and the previous on_match callback is replaced. The
        `on_match` callback will receive the arguments `(matcher, doc, i,
        matches)`. You can also set `on_match` to `None` to not perform any
        actions. A pattern consists of one or more `token_specs`, where a
        `token_spec` is a dictionary mapping attribute IDs to values. Token
        descriptors can also include quantifiers. There are currently important
        known problems with the quantifiers – see the docs.
        """
        for pattern in patterns:
            if len(pattern) == 0:
                msg = ("Cannot add pattern for zero tokens to matcher.\n"
                       "key: {key}\n")
                raise ValueError(msg.format(key=key))
        key = self._normalize_key(key)
        self._patterns.setdefault(key, [])
        self._callbacks[key] = on_match

        for pattern in patterns:
            specs = _convert_strings(pattern, self.vocab.strings)
            self.patterns.push_back(init_pattern(self.mem, key, specs))
            self._patterns[key].append(specs)

    def remove(self, key):
        """Remove a rule from the matcher. A KeyError is raised if the key does
        not exist.

        key (unicode): The ID of the match rule.
        """
        key = self._normalize_key(key)
        self._patterns.pop(key)
        self._callbacks.pop(key)
        cdef int i = 0
        while i < self.patterns.size():
            pattern_key = get_pattern_key(self.patterns.at(i))
            if pattern_key == key:
                self.patterns.erase(self.patterns.begin()+i)
            else:
                i += 1

    def has_key(self, key):
        """Check whether the matcher has a rule with a given key.

        key (string or int): The key to check.
        RETURNS (bool): Whether the matcher has the rule.
        """
        key = self._normalize_key(key)
        return key in self._patterns

    def get(self, key, default=None):
        """Retrieve the pattern stored for a key.

        key (unicode or int): The key to retrieve.
        RETURNS (tuple): The rule, as an (on_match, patterns) tuple.
        """
        key = self._normalize_key(key)
        if key not in self._patterns:
            return default
        return (self._callbacks[key], self._patterns[key])

    def pipe(self, docs, batch_size=1000, n_threads=2):
        """Match a stream of documents, yielding them in turn.

        docs (iterable): A stream of documents.
        batch_size (int): The number of documents to accumulate into a working set.
        n_threads (int): The number of threads with which to work on the buffer
            in parallel, if the `Matcher` implementation supports multi-threading.
        YIELDS (Doc): Documents, in order.
        """
        for doc in docs:
            self(doc)
            yield doc

    def __call__(self, Doc doc):
        """Find all token sequences matching the supplied patterns on the `Doc`.

        doc (Doc): The document to match over.
        RETURNS (list): A list of `(key, label_id, start, end)` tuples,
            describing the matches. A match tuple describes a span
            `doc[start:end]`. The `label_id` and `key` are both integers.
        """
        cdef vector[StateC] partials
        cdef int n_partials = 0
        cdef int q = 0
        cdef int i, token_i
        cdef const TokenC* token
        cdef StateC state
        matches = []
        for token_i in range(doc.length):
            token = &doc.c[token_i]
            q = 0
            # Go over the open matches, extending or finalizing if able. Otherwise,
            # we over-write them (q doesn't advance)
            for state in partials:
                action = get_action(state.second, token)
                if action == PANIC:
                    raise Exception("Error selecting action in matcher")
                while action == ADVANCE_ZERO:
                    state.second += 1
                    action = get_action(state.second, token)
                if action == REPEAT:
                    # Leave the state in the queue, and advance to next slot
                    # (i.e. we don't overwrite -- we want to greedily match more
                    # pattern.
                    q += 1
                elif action == REJECT:
                    pass
                elif action == ADVANCE:
                    partials[q] = state
                    partials[q].second += 1
                    q += 1
                elif action == ACCEPT:
                    # TODO: What to do about patterns starting with ZERO? Need to
                    # adjust the start position.
                    start = state.first
                    end = token_i+1
                    ent_id = state.second[1].attrs[0].value
                    label = state.second[1].attrs[1].value
                    matches.append((ent_id, start, end))
            partials.resize(q)
            # Check whether we open any new patterns on this token
            for pattern in self.patterns:
                action = get_action(pattern, token)
                if action == PANIC:
                    raise Exception("Error selecting action in matcher")
                while action == ADVANCE_ZERO:
                    pattern += 1
                    action = get_action(pattern, token)
                if action == REPEAT:
                    state.first = token_i
                    state.second = pattern
                    partials.push_back(state)
                elif action == ADVANCE:
                    # TODO: What to do about patterns starting with ZERO? Need to
                    # adjust the start position.
                    state.first = token_i
                    state.second = pattern + 1
                    partials.push_back(state)
                elif action == ACCEPT:
                    start = token_i
                    end = token_i+1
                    ent_id = pattern[1].attrs[0].value
                    label = pattern[1].attrs[1].value
                    matches.append((ent_id, start, end))
        # Look for open patterns that are actually satisfied
        for state in partials:
            while state.second.quantifier in (ZERO, ZERO_PLUS):
                state.second += 1
                if state.second.nr_attr == 0:
                    start = state.first
                    end = len(doc)
                    ent_id = state.second.attrs[0].value
                    label = state.second.attrs[0].value
                    matches.append((ent_id, start, end))
        for i, (ent_id, start, end) in enumerate(matches):
            on_match = self._callbacks.get(ent_id)
            if on_match is not None:
                on_match(self, doc, i, matches)
        # TODO: only return (match_id, start, end)
        return matches

    def _normalize_key(self, key):
        if isinstance(key, basestring):
            return self.vocab.strings.add(key)
        else:
            return key


def get_bilou(length):
    if length == 1:
        return [U_ENT]
    elif length == 2:
        return [B2_ENT, L2_ENT]
    elif length == 3:
        return [B3_ENT, I3_ENT, L3_ENT]
    elif length == 4:
        return [B4_ENT, I4_ENT, I4_ENT, L4_ENT]
    elif length == 5:
        return [B5_ENT, I5_ENT, I5_ENT, I5_ENT, L5_ENT]
    elif length == 6:
        return [B6_ENT, I6_ENT, I6_ENT, I6_ENT, I6_ENT, L6_ENT]
    elif length == 7:
        return [B7_ENT, I7_ENT, I7_ENT, I7_ENT, I7_ENT, I7_ENT, L7_ENT]
    elif length == 8:
        return [B8_ENT, I8_ENT, I8_ENT, I8_ENT, I8_ENT, I8_ENT, I8_ENT, L8_ENT]
    elif length == 9:
        return [B9_ENT, I9_ENT, I9_ENT, I9_ENT, I9_ENT, I9_ENT, I9_ENT, I9_ENT, L9_ENT]
    elif length == 10:
        return [B10_ENT, I10_ENT, I10_ENT, I10_ENT, I10_ENT, I10_ENT, I10_ENT,
                I10_ENT, I10_ENT, L10_ENT]
    else:
        raise ValueError("Max length currently 10 for phrase matching")


cdef class PhraseMatcher:
    cdef Pool mem
    cdef Vocab vocab
    cdef Matcher matcher
    cdef PreshMap phrase_ids

    cdef int max_length
    cdef attr_t* _phrase_key

    def __init__(self, Vocab vocab, phrases, max_length=10):
        self.mem = Pool()
        self._phrase_key = <attr_t*>self.mem.alloc(max_length, sizeof(attr_t))
        self.max_length = max_length
        self.vocab = vocab
        self.matcher = Matcher(self.vocab, {})
        self.phrase_ids = PreshMap()
        for phrase in phrases:
            if len(phrase) < max_length:
                self.add(phrase)

        abstract_patterns = []
        for length in range(1, max_length):
            abstract_patterns.append([{tag: True} for tag in get_bilou(length)])
        self.matcher.add('Candidate', 'MWE', {}, abstract_patterns, acceptor=self.accept_match)

    def add(self, Doc tokens):
        cdef int length = tokens.length
        assert length < self.max_length
        tags = get_bilou(length)
        assert len(tags) == length, length

        cdef int i
        for i in range(self.max_length):
            self._phrase_key[i] = 0
        for i, tag in enumerate(tags):
            lexeme = self.vocab[tokens.c[i].lex.orth]
            lexeme.set_flag(tag, True)
            self._phrase_key[i] = lexeme.orth
        cdef hash_t key = hash64(self._phrase_key, self.max_length * sizeof(attr_t), 0)
        self.phrase_ids[key] = True

    def __call__(self, Doc doc):
        matches = []
        for ent_id, label, start, end in self.matcher(doc):
            cand = doc[start : end]
            start = cand[0].idx
            end = cand[-1].idx + len(cand[-1])
            matches.append((start, end, cand.root.tag_, cand.text, 'MWE'))
        for match in matches:
            doc.merge(*match)
        return matches

    def pipe(self, stream, batch_size=1000, n_threads=2):
        for doc in stream:
            self(doc)
            yield doc

    def accept_match(self, Doc doc, attr_t ent_id, attr_t label, int start, int end):
        assert (end - start) < self.max_length
        cdef int i, j
        for i in range(self.max_length):
            self._phrase_key[i] = 0
        for i, j in enumerate(range(start, end)):
            self._phrase_key[i] = doc.c[j].lex.orth
        cdef hash_t key = hash64(self._phrase_key, self.max_length * sizeof(attr_t), 0)
        if self.phrase_ids.get(key):
            return (ent_id, label, start, end)
        else:
            return False