explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-09 16:10:33 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add output options return_matches and as_tuples to Matcher

Browse Source
This commit is contained in:
Matthew Honnibal 2018-02-18 14:00:45 +01:00
parent dd9b0945af
commit 1cf774bdc1
1 changed files with 22 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
spacy/matcher.pyx
View File

@ -548,18 +548,36 @@ cdef class PhraseMatcher:
on_match(self, doc, i, matches) on_match(self, doc, i, matches)
return matches return matches
def pipe(self, stream, batch_size=1000, n_threads=2): def pipe(self, stream, batch_size=1000, n_threads=2, return_matches=False,
as_tuples=False):
"""Match a stream of documents, yielding them in turn. """Match a stream of documents, yielding them in turn.
docs (iterable): A stream of documents. docs (iterable): A stream of documents.
batch_size (int): Number of documents to accumulate into a working set. batch_size (int): Number of documents to accumulate into a working set.
n_threads (int): The number of threads with which to work on the buffer n_threads (int): The number of threads with which to work on the buffer
in parallel, if the implementation supports multi-threading. in parallel, if the implementation supports multi-threading.
return_matches (bool): Yield the match lists along with the docs, making
results (doc, matches) tuples.
as_tuples (bool): Interpret the input stream as (doc, context) tuples,
and yield (result, context) tuples out.
If both return_matches and as_tuples are True, the output will
be a sequence of ((doc, matches), context) tuples.
YIELDS (Doc): Documents, in order. YIELDS (Doc): Documents, in order.
""" """
for doc in stream: if as_tuples:
self(doc) for doc, context in stream:
yield doc matches = self(doc)
if return_matches:
yield ((doc, matches), context)
else:
yield (doc, context)
else:
for doc in stream:
matches = self(doc)
if return_matches:
yield (doc, matches)
else:
yield doc
def accept_match(self, Doc doc, int start, int end): def accept_match(self, Doc doc, int start, int end):
assert (end - start) < self.max_length assert (end - start) < self.max_length