Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add missing docstrings

This commit is contained in:
ines 2017-10-25 12:10:16 +02:00
parent 1262aa0bf9
commit 4d97efc3b5
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
spacy/matcher.pyx
View File

@ -255,6 +255,10 @@ cdef class Matcher:
and '*' patterns in a row and their matches overlap, the first and '*' patterns in a row and their matches overlap, the first
operator will behave non-greedily. This quirk in the semantics operator will behave non-greedily. This quirk in the semantics
makes the matcher more efficient, by avoiding the need for back-tracking. makes the matcher more efficient, by avoiding the need for back-tracking.
key (unicode): The match ID.
on_match (callable): Callback executed on match.
*patterns (list): List of token descritions.
""" """
for pattern in patterns: for pattern in patterns:
if len(pattern) == 0: if len(pattern) == 0:
@ -492,6 +496,13 @@ cdef class PhraseMatcher:
return (self.__class__, (self.vocab,), None, None) return (self.__class__, (self.vocab,), None, None)
def add(self, key, on_match, *docs): def add(self, key, on_match, *docs):
"""Add a match-rule to the matcher. A match-rule consists of: an ID key,
an on_match callback, and one or more patterns.
key (unicode): The match ID.
on_match (callable): Callback executed on match.
*docs (Doc): `Doc` objects representing match patterns.
"""
cdef Doc doc cdef Doc doc
for doc in docs: for doc in docs:
if len(doc) >= self.max_length: if len(doc) >= self.max_length:
@ -520,6 +531,13 @@ cdef class PhraseMatcher:
self.phrase_ids.set(phrase_hash, <void*>ent_id) self.phrase_ids.set(phrase_hash, <void*>ent_id)
def __call__(self, Doc doc): def __call__(self, Doc doc):
"""Find all sequences matching the supplied patterns on the `Doc`.
doc (Doc): The document to match over.
RETURNS (list): A list of `(key, start, end)` tuples,
describing the matches. A match tuple describes a span
`doc[start:end]`. The `label_id` and `key` are both integers.
"""
matches = [] matches = []
for _, start, end in self.matcher(doc): for _, start, end in self.matcher(doc):
ent_id = self.accept_match(doc, start, end) ent_id = self.accept_match(doc, start, end)
@ -532,6 +550,14 @@ cdef class PhraseMatcher:
return matches return matches
def pipe(self, stream, batch_size=1000, n_threads=2): def pipe(self, stream, 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 stream: for doc in stream:
self(doc) self(doc)
yield doc yield doc