explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-30 10:00:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Move to displacy

Browse Source
This commit is contained in:
richardpaulhudson 2023-01-31 20:51:53 +01:00
parent 5943fd161f
commit 953c511395
7 changed files with 733 additions and 736 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
spacy/displacy/__init__.py
View File

@ -8,6 +8,7 @@ from typing import Union, Iterable, Optional, Dict, Any, Callable
import warnings import warnings
from .render import DependencyRenderer, EntityRenderer, SpanRenderer from .render import DependencyRenderer, EntityRenderer, SpanRenderer
from .pprint import render_document
from ..tokens import Doc, Span from ..tokens import Doc, Span
from ..errors import Errors, Warnings from ..errors import Errors, Warnings
from ..util import is_in_jupyter from ..util import is_in_jupyter
@ -273,3 +274,41 @@ def get_doc_settings(doc: Doc) -> Dict[str, Any]:
"lang": doc.lang_, "lang": doc.lang_,
"direction": doc.vocab.writing_system.get("direction", "ltr"), "direction": doc.vocab.writing_system.get("direction", "ltr"),
} }
def pprint(
doc: Doc,
search_attr_name: Optional[str] = None,
search_attr_value: Optional[str] = None,
*,
start_i: int = 0,
length: Optional[int] = None,
):
"""Prints a tabular representation of a document or of part of a document.
If part of the document is specified using any of the four optional
parameters, the sentences surrounding that part of the document are rendered;
if none of the four optional parameters are specified, the whole document is
rendered.
doc: the document.
search_attr_name: the name of an attribute to search for in order to
determine where to start rendering, e.g. "lemma_",
or *None* if no search is to be carried out. If either
of *search_attr_name* and *search_attr_value* is *None*,
the behaviour is as if both were *None*.
search_attr_value: the value of an attribute to search for in order to
determine where to start rendering, e.g. "be",
or *None* if no search is to be carried out. If either
of *search_attr_name* and *search_attr_value* is *None*,
the behaviour is as if both were *None*.
start_i: the token index at which to start searching, or at
whose sentence to start rendering. Default: 0.
length: the number of tokens after *start_i* at whose sentence
to stop rendering. If *None*, the rest of the
document is rendered.
"""
print(
render_document(
doc, search_attr_name, search_attr_value, start_i=start_i, length=length
)
)

0
spacy/visualization.py → spacy/displacy/pprint.py
View File

669
spacy/tests/test_displacy.py
View File

@ -1,11 +1,17 @@
import numpy import numpy
import pytest import pytest
from wasabi.util import supports_ansi
from spacy import displacy from spacy import displacy
from spacy.displacy.render import DependencyRenderer, EntityRenderer from spacy.displacy.render import DependencyRenderer, EntityRenderer
from spacy.displacy.pprint import AttributeFormat, render_dep_tree, render_table
from spacy.lang.en import English from spacy.lang.en import English
from spacy.lang.fa import Persian from spacy.lang.fa import Persian
from spacy.tokens import Span, Doc from spacy.tokens import Span, Doc, Token
SUPPORTS_ANSI = supports_ansi()
@pytest.mark.issue(2361) @pytest.mark.issue(2361)
@ -363,3 +369,664 @@ def test_displacy_manual_sorted_entities():
html = displacy.render(doc, style="ent", manual=True) html = displacy.render(doc, style="ent", manual=True)
assert html.find("FIRST") < html.find("SECOND") assert html.find("FIRST") < html.find("SECOND")
@pytest.fixture
def horse_doc(en_vocab):
return Doc(
en_vocab,
words=[
"I",
"saw",
"a",
"horse",
"yesterday",
"that",
"was",
"injured",
".",
],
heads=[1, None, 3, 1, 1, 7, 7, 3, 1],
deps=["dep"] * 9,
)
def test_viz_dep_tree_basic(en_vocab):
"""Test basic dependency tree display."""
doc = Doc(
en_vocab,
words=[
"The",
"big",
"dog",
"chased",
"the",
"frightened",
"cat",
"mercilessly",
".",
],
heads=[2, 2, 3, None, 6, 6, 3, 3, 3],
deps=["dep"] * 9,
)
dep_tree = render_dep_tree(doc[0 : len(doc)], True)
assert dep_tree == [
"<╗ ",
"<╣ ",
"═╝<╗",
"═══╣",
"<╗ ║",
"<╣ ║",
"═╝<╣",
"<══╣",
"<══╝",
]
dep_tree = render_dep_tree(doc[0 : len(doc)], False)
assert dep_tree == [
" ╔>",
" ╠>",
"╔>╚═",
"╠═══",
"║ ╔>",
"║ ╠>",
"╠>╚═",
"╠══>",
"╚══>",
]
def test_viz_dep_tree_non_initial_sent(en_vocab):
"""Test basic dependency tree display."""
doc = Doc(
en_vocab,
words=[
"Something",
"happened",
".",
"The",
"big",
"dog",
"chased",
"the",
"frightened",
"cat",
"mercilessly",
".",
],
heads=[0, None, 0, 5, 5, 6, None, 9, 9, 6, 6, 6],
deps=["dep"] * 12,
)
dep_tree = render_dep_tree(doc[3 : len(doc)], True)
assert dep_tree == [
"<╗ ",
"<╣ ",
"═╝<╗",
"═══╣",
"<╗ ║",
"<╣ ║",
"═╝<╣",
"<══╣",
"<══╝",
]
dep_tree = render_dep_tree(doc[3 : len(doc)], False)
assert dep_tree == [
" ╔>",
" ╠>",
"╔>╚═",
"╠═══",
"║ ╔>",
"║ ╠>",
"╠>╚═",
"╠══>",
"╚══>",
]
def test_viz_dep_tree_non_projective(horse_doc):
"""Test dependency tree display with a non-projective dependency."""
dep_tree = render_dep_tree(horse_doc[0 : len(horse_doc)], True)
assert dep_tree == [
"<╗ ",
"═╩═══╗",
"<╗ ║",
"═╩═╗<╣",
"<══║═╣",
"<╗ ║ ║",
"<╣ ║ ║",
"═╝<╝ ║",
"<════╝",
]
dep_tree = render_dep_tree(horse_doc[0 : len(horse_doc)], False)
assert dep_tree == [
" ╔>",
"╔═══╩═",
"║ ╔>",
"╠>╔═╩═",
"╠═║══>",
"║ ║ ╔>",
"║ ║ ╠>",
"║ ╚>╚═",
"╚════>",
]
def test_viz_dep_tree_highly_nonprojective(pl_vocab):
"""Test a highly non-projective tree (colloquial Polish)."""
doc = Doc(
pl_vocab,
words=[
"Owczarki",
"przecież",
"niemieckie",
"zawsze",
"wierne",
"są",
"bardzo",
".",
],
heads=[5, 5, 0, 5, 5, None, 4, 5],
deps=["dep"] * 8,
)
dep_tree = render_dep_tree(doc[0 : len(doc)], True)
assert dep_tree == [
"═╗<╗",
" ║<╣",
"<╝ ║",
"<══╣",
"═╗<╣",
"═══╣",
"<╝ ║",
"<══╝",
]
dep_tree = render_dep_tree(doc[0 : len(doc)], False)
assert dep_tree == [
"╔>╔═",
"╠>║ ",
"║ ╚>",
"╠══>",
"╠>╔═",
"╠═══",
"║ ╚>",
"╚══>",
]
def test_viz_dep_tree_input_not_span(horse_doc):
"""Test dependency tree display behaviour when the input is not a Span."""
with pytest.raises(ValueError):
render_dep_tree(horse_doc[1:3], True)
def test_viz_render_native_attributes(horse_doc):
assert AttributeFormat("head.i").render(horse_doc[2]) == "3"
assert AttributeFormat("head.i").render(horse_doc[2], right_pad_to_len=3) == "3 "
assert AttributeFormat("dep_").render(horse_doc[2]) == "dep"
with pytest.raises(AttributeError):
AttributeFormat("depp").render(horse_doc[2])
with pytest.raises(AttributeError):
AttributeFormat("tree_left").render(horse_doc[2])
with pytest.raises(AttributeError):
AttributeFormat("tree_right").render(horse_doc[2])
def test_viz_render_colors(horse_doc):
assert (
AttributeFormat(
"dep_",
value_dep_fg_colors={"dep": 2},
value_dep_bg_colors={"dep": 11},
).render(horse_doc[2])
== "\x1b[38;5;2;48;5;11mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
# foreground only
assert (
AttributeFormat(
"dep_",
value_dep_fg_colors={"dep": 2},
).render(horse_doc[2])
== "\x1b[38;5;2mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
# background only
assert (
AttributeFormat(
"dep_",
value_dep_bg_colors={"dep": 11},
).render(horse_doc[2])
== "\x1b[48;5;11mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
def test_viz_render_custom_attributes(horse_doc):
Token.set_extension("test", default="tested1", force=True)
assert AttributeFormat("_.test").render(horse_doc[2]) == "tested1"
class Test:
def __init__(self):
self.inner_test = "tested2"
Token.set_extension("test", default=Test(), force=True)
assert AttributeFormat("_.test.inner_test").render(horse_doc[2]) == "tested2"
with pytest.raises(AttributeError):
AttributeFormat("._depp").render(horse_doc[2])
def test_viz_minimal_render_table_one_sentence(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_minimal_render_table_empty_text(
en_vocab,
):
# no headers
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert render_table(Doc(en_vocab), formats, spacing=3).strip() == ""
# headers
formats = [
AttributeFormat("tree_left", name="tree"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_", name="ent"),
]
assert render_table(Doc(en_vocab), formats, spacing=3).strip() == ""
def test_viz_minimal_render_table_spacing(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=1).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_minimal_render_table_two_sentences(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
╔> nsubj She she PRON PRP Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs
╠═ ROOT loved love VERB VBD Tense=Past|VerbForm=Fin
╠> dobj it it PRON PRP Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs
╚> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_rich_render_table_one_sentence(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3)
== "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma pos tag morph ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- ----- --- --------------- ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's PART POS Poss=yes \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister NOUN NN Number=sing \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly VERB VBD Tense=past|Verb \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to ADP IN \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via ADP IN \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . PUNCT . PunctType=peri \n\n"
)
# trigger value for value_dep shorter than maximum length in column
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat(
"text",
name="text",
fg_color=196,
value_dep_fg_colors={"'s": 50},
value_dep_bg_colors={"'s": 12},
),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3)
== "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index \x1b[38;5;196mtext \x1b[0m lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- \x1b[38;5;196m-------\x1b[0m ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 \x1b[38;5;196mSarah \x1b[0m sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 \x1b[38;5;196m\x1b[38;5;50;48;5;12m's\x1b[0m \x1b[0m 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 \x1b[38;5;196msister \x1b[0m sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 \x1b[38;5;196mflew \x1b[0m fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 \x1b[38;5;196mto \x1b[0m to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 \x1b[38;5;196mSilicon\x1b[0m silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 \x1b[38;5;196mValley \x1b[0m valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 \x1b[38;5;196mvia \x1b[0m via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 \x1b[38;5;196mLondon \x1b[0m london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 \x1b[38;5;196m. \x1b[0m . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \n\n"
if SUPPORTS_ANSI
else "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma pos tag \x1b[38;5;100mmorph \x1b[0m ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- ----- --- \x1b[38;5;100m-------------------------\x1b[0m ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's PART POS \x1b[38;5;100mPoss=yes \x1b[0m \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister NOUN NN \x1b[38;5;100mNumber=sing \x1b[0m \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly VERB VBD \x1b[38;5;100mTense=past|VerbForm=fin \x1b[0m \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to ADP IN \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via ADP IN \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . PUNCT . \x1b[38;5;100mPunctType=peri \x1b[0m \n\n"
)
def test_viz_rich_render_table_two_sentences(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
print(render_table(fully_featured_doc_two_sentences, formats, spacing=3))
print(repr(render_table(fully_featured_doc_two_sentences, formats, spacing=3)))
target = (
"\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n\n\x1b[38;5;2mtree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment\x1b[0m\n\x1b[38;5;2m----\x1b[0m \x1b[38;5;2m-----\x1b[0m ----- ----- ----- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m---\x1b[0m\n\x1b[38;5;2m ╔>\x1b[0m \x1b[38;5;2mnsubj\x1b[0m 10 She she \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Nom|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠═\x1b[0m \x1b[38;5;2mROOT \x1b[0m 11 loved love \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=Past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠>\x1b[0m \x1b[38;5;2mdobj \x1b[0m 12 it it \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Acc|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╚>\x1b[0m \x1b[38;5;2mpunct\x1b[0m 13 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n tree dep index text lemma pos tag morph ent \n------ -------- ----- ------- ------- ----- --- --------------- ------\n ╔>╔═ poss 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n ║ ╚> case 1 's 's PART POS Poss=yes \n╔>╚═══ nsubj 2 sister sister NOUN NN Number=sing \n╠═════ ROOT 3 flew fly VERB VBD Tense=past|Verb \n╠>╔═══ prep 4 to to ADP IN \n║ ║ ╔> compound 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n║ ╚>╚═ pobj 6 Valley valley PROPN NNP NounType=prop|N GPE \n╠══>╔═ prep 7 via via ADP IN \n║ ╚> pobj 8 London london PROPN NNP NounType=prop|N GPE \n╚════> punct 9 . . PUNCT . PunctType=peri \n\n\ntree dep index text lemma pos tag morph ent\n---- ----- ----- ----- ----- ----- --- --------------- ---\n ╔> nsubj 10 She she PRON PRP Case=Nom|Gender \n ╠═ ROOT 11 loved love VERB VBD Tense=Past|Verb \n ╠> dobj 12 it it PRON PRP Case=Acc|Gender \n ╚> punct 13 . . PUNCT . PunctType=peri \n\n"
)
assert render_table(fully_featured_doc_two_sentences, formats, spacing=3) == target
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=3, length=300
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=3, length=9
)
== target
)
def test_viz_rich_render_table_start(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
print(
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=11)
)
print(
repr(
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=11
)
)
)
target = (
"\n\x1b[38;5;2mtree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment\x1b[0m\n\x1b[38;5;2m----\x1b[0m \x1b[38;5;2m-----\x1b[0m ----- ----- ----- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m---\x1b[0m\n\x1b[38;5;2m ╔>\x1b[0m \x1b[38;5;2mnsubj\x1b[0m 10 She she \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Nom|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠═\x1b[0m \x1b[38;5;2mROOT \x1b[0m 11 loved love \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=Past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠>\x1b[0m \x1b[38;5;2mdobj \x1b[0m 12 it it \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Acc|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╚>\x1b[0m \x1b[38;5;2mpunct\x1b[0m 13 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\ntree dep index text lemma pos tag morph ent\n---- ----- ----- ----- ----- ----- --- --------------- ---\n ╔> nsubj 10 She she PRON PRP Case=Nom|Gender \n ╠═ ROOT 11 loved love VERB VBD Tense=Past|Verb \n ╠> dobj 12 it it PRON PRP Case=Acc|Gender \n ╚> punct 13 . . PUNCT . PunctType=peri \n\n"
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=11)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=11,
search_attr_name="pos",
search_attr_value="VERB",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=2,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=2,
length=3,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma_",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma",
search_attr_value="lovef",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma_",
search_attr_value="lovef",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemmaa",
search_attr_value="love",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=50,
search_attr_name="lemma",
search_attr_value="love",
)
== ""
)
def test_viz_rich_render_table_end(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
target = (
"\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n tree dep index text lemma pos tag morph ent \n------ -------- ----- ------- ------- ----- --- --------------- ------\n ╔>╔═ poss 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n ║ ╚> case 1 's 's PART POS Poss=yes \n╔>╚═══ nsubj 2 sister sister NOUN NN Number=sing \n╠═════ ROOT 3 flew fly VERB VBD Tense=past|Verb \n╠>╔═══ prep 4 to to ADP IN \n║ ║ ╔> compound 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n║ ╚>╚═ pobj 6 Valley valley PROPN NNP NounType=prop|N GPE \n╠══>╔═ prep 7 via via ADP IN \n║ ╚> pobj 8 London london PROPN NNP NounType=prop|N GPE \n╚════> punct 9 . . PUNCT . PunctType=peri \n\n"
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=2)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=2, length=3
)
== target
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, length=3)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="pos",
search_attr_value="VERB",
)
== target
)

668
spacy/tests/test_visualization.py
View File

@ -1,668 +0,0 @@
import pytest
from wasabi.util import supports_ansi
from spacy.visualization import AttributeFormat, render_dep_tree, render_table
from spacy.tokens import Span, Doc, Token
SUPPORTS_ANSI = supports_ansi()
@pytest.fixture
def horse_doc(en_vocab):
return Doc(
en_vocab,
words=[
"I",
"saw",
"a",
"horse",
"yesterday",
"that",
"was",
"injured",
".",
],
heads=[1, None, 3, 1, 1, 7, 7, 3, 1],
deps=["dep"] * 9,
)
def test_viz_dep_tree_basic(en_vocab):
"""Test basic dependency tree display."""
doc = Doc(
en_vocab,
words=[
"The",
"big",
"dog",
"chased",
"the",
"frightened",
"cat",
"mercilessly",
".",
],
heads=[2, 2, 3, None, 6, 6, 3, 3, 3],
deps=["dep"] * 9,
)
dep_tree = render_dep_tree(doc[0 : len(doc)], True)
assert dep_tree == [
"<╗ ",
"<╣ ",
"═╝<╗",
"═══╣",
"<╗ ║",
"<╣ ║",
"═╝<╣",
"<══╣",
"<══╝",
]
dep_tree = render_dep_tree(doc[0 : len(doc)], False)
assert dep_tree == [
" ╔>",
" ╠>",
"╔>╚═",
"╠═══",
"║ ╔>",
"║ ╠>",
"╠>╚═",
"╠══>",
"╚══>",
]
def test_viz_dep_tree_non_initial_sent(en_vocab):
"""Test basic dependency tree display."""
doc = Doc(
en_vocab,
words=[
"Something",
"happened",
".",
"The",
"big",
"dog",
"chased",
"the",
"frightened",
"cat",
"mercilessly",
".",
],
heads=[0, None, 0, 5, 5, 6, None, 9, 9, 6, 6, 6],
deps=["dep"] * 12,
)
dep_tree = render_dep_tree(doc[3 : len(doc)], True)
assert dep_tree == [
"<╗ ",
"<╣ ",
"═╝<╗",
"═══╣",
"<╗ ║",
"<╣ ║",
"═╝<╣",
"<══╣",
"<══╝",
]
dep_tree = render_dep_tree(doc[3 : len(doc)], False)
assert dep_tree == [
" ╔>",
" ╠>",
"╔>╚═",
"╠═══",
"║ ╔>",
"║ ╠>",
"╠>╚═",
"╠══>",
"╚══>",
]
def test_viz_dep_tree_non_projective(horse_doc):
"""Test dependency tree display with a non-projective dependency."""
dep_tree = render_dep_tree(horse_doc[0 : len(horse_doc)], True)
assert dep_tree == [
"<╗ ",
"═╩═══╗",
"<╗ ║",
"═╩═╗<╣",
"<══║═╣",
"<╗ ║ ║",
"<╣ ║ ║",
"═╝<╝ ║",
"<════╝",
]
dep_tree = render_dep_tree(horse_doc[0 : len(horse_doc)], False)
assert dep_tree == [
" ╔>",
"╔═══╩═",
"║ ╔>",
"╠>╔═╩═",
"╠═║══>",
"║ ║ ╔>",
"║ ║ ╠>",
"║ ╚>╚═",
"╚════>",
]
def test_viz_dep_tree_highly_nonprojective(pl_vocab):
"""Test a highly non-projective tree (colloquial Polish)."""
doc = Doc(
pl_vocab,
words=[
"Owczarki",
"przecież",
"niemieckie",
"zawsze",
"wierne",
"są",
"bardzo",
".",
],
heads=[5, 5, 0, 5, 5, None, 4, 5],
deps=["dep"] * 8,
)
dep_tree = render_dep_tree(doc[0 : len(doc)], True)
assert dep_tree == [
"═╗<╗",
" ║<╣",
"<╝ ║",
"<══╣",
"═╗<╣",
"═══╣",
"<╝ ║",
"<══╝",
]
dep_tree = render_dep_tree(doc[0 : len(doc)], False)
assert dep_tree == [
"╔>╔═",
"╠>║ ",
"║ ╚>",
"╠══>",
"╠>╔═",
"╠═══",
"║ ╚>",
"╚══>",
]
def test_viz_dep_tree_input_not_span(horse_doc):
"""Test dependency tree display behaviour when the input is not a Span."""
with pytest.raises(ValueError):
render_dep_tree(horse_doc[1:3], True)
def test_viz_render_native_attributes(horse_doc):
assert AttributeFormat("head.i").render(horse_doc[2]) == "3"
assert AttributeFormat("head.i").render(horse_doc[2], right_pad_to_len=3) == "3 "
assert AttributeFormat("dep_").render(horse_doc[2]) == "dep"
with pytest.raises(AttributeError):
AttributeFormat("depp").render(horse_doc[2])
with pytest.raises(AttributeError):
AttributeFormat("tree_left").render(horse_doc[2])
with pytest.raises(AttributeError):
AttributeFormat("tree_right").render(horse_doc[2])
def test_viz_render_colors(horse_doc):
assert (
AttributeFormat(
"dep_",
value_dep_fg_colors={"dep": 2},
value_dep_bg_colors={"dep": 11},
).render(horse_doc[2])
== "\x1b[38;5;2;48;5;11mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
# foreground only
assert (
AttributeFormat(
"dep_",
value_dep_fg_colors={"dep": 2},
).render(horse_doc[2])
== "\x1b[38;5;2mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
# background only
assert (
AttributeFormat(
"dep_",
value_dep_bg_colors={"dep": 11},
).render(horse_doc[2])
== "\x1b[48;5;11mdep\x1b[0m"
if SUPPORTS_ANSI
else "dep"
)
def test_viz_render_custom_attributes(horse_doc):
Token.set_extension("test", default="tested1", force=True)
assert AttributeFormat("_.test").render(horse_doc[2]) == "tested1"
class Test:
def __init__(self):
self.inner_test = "tested2"
Token.set_extension("test", default=Test(), force=True)
assert AttributeFormat("_.test.inner_test").render(horse_doc[2]) == "tested2"
with pytest.raises(AttributeError):
AttributeFormat("._depp").render(horse_doc[2])
def test_viz_minimal_render_table_one_sentence(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_minimal_render_table_empty_text(
en_vocab,
):
# no headers
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert render_table(Doc(en_vocab), formats, spacing=3).strip() == ""
# headers
formats = [
AttributeFormat("tree_left", name="tree"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_", name="ent"),
]
assert render_table(Doc(en_vocab), formats, spacing=3).strip() == ""
def test_viz_minimal_render_table_spacing(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=1).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_minimal_render_table_two_sentences(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left"),
AttributeFormat("dep_"),
AttributeFormat("text"),
AttributeFormat("lemma_"),
AttributeFormat("pos_"),
AttributeFormat("tag_"),
AttributeFormat("morph"),
AttributeFormat("ent_type_"),
]
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3).strip()
== """
╔>╔═ poss Sarah sarah PROPN NNP NounType=prop|Number=sing PERSON
║ ╚> case 's 's PART POS Poss=yes
╔>╚═══ nsubj sister sister NOUN NN Number=sing
╠═════ ROOT flew fly VERB VBD Tense=past|VerbForm=fin
╠>╔═══ prep to to ADP IN
║ ║ ╔> compound Silicon silicon PROPN NNP NounType=prop|Number=sing GPE
║ ╚>╚═ pobj Valley valley PROPN NNP NounType=prop|Number=sing GPE
╠══>╔═ prep via via ADP IN
║ ╚> pobj London london PROPN NNP NounType=prop|Number=sing GPE
╚════> punct . . PUNCT . PunctType=peri
╔> nsubj She she PRON PRP Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs
╠═ ROOT loved love VERB VBD Tense=Past|VerbForm=Fin
╠> dobj it it PRON PRP Case=Acc|Gender=Neut|Number=Sing|Person=3|PronType=Prs
╚> punct . . PUNCT . PunctType=peri
""".strip()
)
def test_viz_rich_render_table_one_sentence(
fully_featured_doc_one_sentence,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3)
== "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma pos tag morph ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- ----- --- --------------- ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's PART POS Poss=yes \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister NOUN NN Number=sing \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly VERB VBD Tense=past|Verb \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to ADP IN \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via ADP IN \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london PROPN NNP NounType=prop|N GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . PUNCT . PunctType=peri \n\n"
)
# trigger value for value_dep shorter than maximum length in column
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat(
"text",
name="text",
fg_color=196,
value_dep_fg_colors={"'s": 50},
value_dep_bg_colors={"'s": 12},
),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
),
]
assert (
render_table(fully_featured_doc_one_sentence, formats, spacing=3)
== "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index \x1b[38;5;196mtext \x1b[0m lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- \x1b[38;5;196m-------\x1b[0m ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 \x1b[38;5;196mSarah \x1b[0m sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 \x1b[38;5;196m\x1b[38;5;50;48;5;12m's\x1b[0m \x1b[0m 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 \x1b[38;5;196msister \x1b[0m sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 \x1b[38;5;196mflew \x1b[0m fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 \x1b[38;5;196mto \x1b[0m to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 \x1b[38;5;196mSilicon\x1b[0m silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 \x1b[38;5;196mValley \x1b[0m valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 \x1b[38;5;196mvia \x1b[0m via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 \x1b[38;5;196mLondon \x1b[0m london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 \x1b[38;5;196m. \x1b[0m . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \n\n"
if SUPPORTS_ANSI
else "\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma pos tag \x1b[38;5;100mmorph \x1b[0m ent \n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- ----- --- \x1b[38;5;100m-------------------------\x1b[0m ------\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m PERSON\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's PART POS \x1b[38;5;100mPoss=yes \x1b[0m \n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister NOUN NN \x1b[38;5;100mNumber=sing \x1b[0m \n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly VERB VBD \x1b[38;5;100mTense=past|VerbForm=fin \x1b[0m \n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to ADP IN \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via ADP IN \x1b[38;5;100m \x1b[0m \n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london PROPN NNP \x1b[38;5;100mNounType=prop|Number=sing\x1b[0m GPE \n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . PUNCT . \x1b[38;5;100mPunctType=peri \x1b[0m \n\n"
)
def test_viz_rich_render_table_two_sentences(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
print(render_table(fully_featured_doc_two_sentences, formats, spacing=3))
print(repr(render_table(fully_featured_doc_two_sentences, formats, spacing=3)))
target = (
"\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n\n\x1b[38;5;2mtree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment\x1b[0m\n\x1b[38;5;2m----\x1b[0m \x1b[38;5;2m-----\x1b[0m ----- ----- ----- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m---\x1b[0m\n\x1b[38;5;2m ╔>\x1b[0m \x1b[38;5;2mnsubj\x1b[0m 10 She she \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Nom|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠═\x1b[0m \x1b[38;5;2mROOT \x1b[0m 11 loved love \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=Past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠>\x1b[0m \x1b[38;5;2mdobj \x1b[0m 12 it it \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Acc|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╚>\x1b[0m \x1b[38;5;2mpunct\x1b[0m 13 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n tree dep index text lemma pos tag morph ent \n------ -------- ----- ------- ------- ----- --- --------------- ------\n ╔>╔═ poss 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n ║ ╚> case 1 's 's PART POS Poss=yes \n╔>╚═══ nsubj 2 sister sister NOUN NN Number=sing \n╠═════ ROOT 3 flew fly VERB VBD Tense=past|Verb \n╠>╔═══ prep 4 to to ADP IN \n║ ║ ╔> compound 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n║ ╚>╚═ pobj 6 Valley valley PROPN NNP NounType=prop|N GPE \n╠══>╔═ prep 7 via via ADP IN \n║ ╚> pobj 8 London london PROPN NNP NounType=prop|N GPE \n╚════> punct 9 . . PUNCT . PunctType=peri \n\n\ntree dep index text lemma pos tag morph ent\n---- ----- ----- ----- ----- ----- --- --------------- ---\n ╔> nsubj 10 She she PRON PRP Case=Nom|Gender \n ╠═ ROOT 11 loved love VERB VBD Tense=Past|Verb \n ╠> dobj 12 it it PRON PRP Case=Acc|Gender \n ╚> punct 13 . . PUNCT . PunctType=peri \n\n"
)
assert render_table(fully_featured_doc_two_sentences, formats, spacing=3) == target
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=3, length=300
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=3, length=9
)
== target
)
def test_viz_rich_render_table_start(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
print(
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=11)
)
print(
repr(
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=11
)
)
)
target = (
"\n\x1b[38;5;2mtree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment\x1b[0m\n\x1b[38;5;2m----\x1b[0m \x1b[38;5;2m-----\x1b[0m ----- ----- ----- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m---\x1b[0m\n\x1b[38;5;2m ╔>\x1b[0m \x1b[38;5;2mnsubj\x1b[0m 10 She she \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Nom|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠═\x1b[0m \x1b[38;5;2mROOT \x1b[0m 11 loved love \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=Past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╠>\x1b[0m \x1b[38;5;2mdobj \x1b[0m 12 it it \x1b[38;5;100mPRON \x1b[0m \x1b[38;5;100mPRP\x1b[0m \x1b[38;5;100mCase=Acc|Gender\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m ╚>\x1b[0m \x1b[38;5;2mpunct\x1b[0m 13 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\ntree dep index text lemma pos tag morph ent\n---- ----- ----- ----- ----- ----- --- --------------- ---\n ╔> nsubj 10 She she PRON PRP Case=Nom|Gender \n ╠═ ROOT 11 loved love VERB VBD Tense=Past|Verb \n ╠> dobj 12 it it PRON PRP Case=Acc|Gender \n ╚> punct 13 . . PUNCT . PunctType=peri \n\n"
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=11)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=11,
search_attr_name="pos",
search_attr_value="VERB",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=2,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=2,
length=3,
search_attr_name="lemma",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma_",
search_attr_value="love",
)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma",
search_attr_value="lovef",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemma_",
search_attr_value="lovef",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="lemmaa",
search_attr_value="love",
)
== ""
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
start_i=50,
search_attr_name="lemma",
search_attr_value="love",
)
== ""
)
def test_viz_rich_render_table_end(
fully_featured_doc_two_sentences,
):
formats = [
AttributeFormat("tree_left", name="tree", aligns="r", fg_color=2),
AttributeFormat("dep_", name="dep", fg_color=2),
AttributeFormat("i", name="index", aligns="r"),
AttributeFormat("text", name="text"),
AttributeFormat("lemma_", name="lemma"),
AttributeFormat("pos_", name="pos", fg_color=100),
AttributeFormat("tag_", name="tag", fg_color=100),
AttributeFormat("morph", name="morph", fg_color=100, max_width=15),
AttributeFormat(
"ent_type_",
name="ent",
fg_color=196,
value_dep_fg_colors={"PERSON": 50},
value_dep_bg_colors={"PERSON": 12},
),
]
target = (
"\n\x1b[38;5;2m tree\x1b[0m \x1b[38;5;2mdep \x1b[0m index text lemma \x1b[38;5;100mpos \x1b[0m \x1b[38;5;100mtag\x1b[0m \x1b[38;5;100mmorph \x1b[0m \x1b[38;5;196ment \x1b[0m\n\x1b[38;5;2m------\x1b[0m \x1b[38;5;2m--------\x1b[0m ----- ------- ------- \x1b[38;5;100m-----\x1b[0m \x1b[38;5;100m---\x1b[0m \x1b[38;5;100m---------------\x1b[0m \x1b[38;5;196m------\x1b[0m\n\x1b[38;5;2m ╔>╔═\x1b[0m \x1b[38;5;2mposs \x1b[0m 0 Sarah sarah \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196m\x1b[38;5;50;48;5;12mPERSON\x1b[0m\x1b[0m\n\x1b[38;5;2m ║ ╚>\x1b[0m \x1b[38;5;2mcase \x1b[0m 1 's 's \x1b[38;5;100mPART \x1b[0m \x1b[38;5;100mPOS\x1b[0m \x1b[38;5;100mPoss=yes \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╔>╚═══\x1b[0m \x1b[38;5;2mnsubj \x1b[0m 2 sister sister \x1b[38;5;100mNOUN \x1b[0m \x1b[38;5;100mNN \x1b[0m \x1b[38;5;100mNumber=sing \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠═════\x1b[0m \x1b[38;5;2mROOT \x1b[0m 3 flew fly \x1b[38;5;100mVERB \x1b[0m \x1b[38;5;100mVBD\x1b[0m \x1b[38;5;100mTense=past|Verb\x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m╠>╔═══\x1b[0m \x1b[38;5;2mprep \x1b[0m 4 to to \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ║ ╔>\x1b[0m \x1b[38;5;2mcompound\x1b[0m 5 Silicon silicon \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m║ ╚>╚═\x1b[0m \x1b[38;5;2mpobj \x1b[0m 6 Valley valley \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╠══>╔═\x1b[0m \x1b[38;5;2mprep \x1b[0m 7 via via \x1b[38;5;100mADP \x1b[0m \x1b[38;5;100mIN \x1b[0m \x1b[38;5;100m \x1b[0m \x1b[38;5;196m \x1b[0m\n\x1b[38;5;2m║ ╚>\x1b[0m \x1b[38;5;2mpobj \x1b[0m 8 London london \x1b[38;5;100mPROPN\x1b[0m \x1b[38;5;100mNNP\x1b[0m \x1b[38;5;100mNounType=prop|N\x1b[0m \x1b[38;5;196mGPE \x1b[0m\n\x1b[38;5;2m╚════>\x1b[0m \x1b[38;5;2mpunct \x1b[0m 9 . . \x1b[38;5;100mPUNCT\x1b[0m \x1b[38;5;100m. \x1b[0m \x1b[38;5;100mPunctType=peri \x1b[0m \x1b[38;5;196m \x1b[0m\n\n"
if SUPPORTS_ANSI
else "\n tree dep index text lemma pos tag morph ent \n------ -------- ----- ------- ------- ----- --- --------------- ------\n ╔>╔═ poss 0 Sarah sarah PROPN NNP NounType=prop|N PERSON\n ║ ╚> case 1 's 's PART POS Poss=yes \n╔>╚═══ nsubj 2 sister sister NOUN NN Number=sing \n╠═════ ROOT 3 flew fly VERB VBD Tense=past|Verb \n╠>╔═══ prep 4 to to ADP IN \n║ ║ ╔> compound 5 Silicon silicon PROPN NNP NounType=prop|N GPE \n║ ╚>╚═ pobj 6 Valley valley PROPN NNP NounType=prop|N GPE \n╠══>╔═ prep 7 via via ADP IN \n║ ╚> pobj 8 London london PROPN NNP NounType=prop|N GPE \n╚════> punct 9 . . PUNCT . PunctType=peri \n\n"
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, start_i=2)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences, formats, spacing=3, start_i=2, length=3
)
== target
)
assert (
render_table(fully_featured_doc_two_sentences, formats, spacing=3, length=3)
== target
)
assert (
render_table(
fully_featured_doc_two_sentences,
formats,
spacing=3,
search_attr_name="pos",
search_attr_value="VERB",
)
== target
)

40
spacy/tokens/doc.pyx
View File

@ -38,7 +38,6 @@ from .underscore import Underscore, get_ext_args
from ._retokenize import Retokenizer from ._retokenize import Retokenizer
from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
from ..util import get_words_and_spaces from ..util import get_words_and_spaces
from ..visualization import render_document
DEF PADDING = 5 DEF PADDING = 5
@ -1752,45 +1751,6 @@ cdef class Doc:
attrs.extend(intify_attr(x) for x in DOCBIN_ALL_ATTRS) attrs.extend(intify_attr(x) for x in DOCBIN_ALL_ATTRS)
return tuple(attrs) return tuple(attrs)
def inspect(
self,
search_attr_name=None,
search_attr_value=None,
*,
start_i=0,
length=None
):
"""Prints a tabular representation of the document or part of the document.
If part of the document is specified using any of the four optional
parameters, the sentences surrounding that part of the document are rendered;
if none of the four optional parameters are specified, the whole document is
rendered.
search_attr_name: the name of an attribute to search for in order to
determine where to start rendering, e.g. "lemma_",
or *None* if no search is to be carried out. If either
of *search_attr_name* and *search_attr_value* is *None*,
the behaviour is as if both were *None*.
search_attr_value: the value of an attribute to search for in order to
determine where to start rendering, e.g. "be",
or *None* if no search is to be carried out. If either
of *search_attr_name* and *search_attr_value* is *None*,
the behaviour is as if both were *None*.
start_i: the token index at which to start searching, or at
whose sentence to start rendering. Default: 0.
length: the number of tokens after *start_i* at whose sentence
to stop rendering. If *None*, the rest of the
document is rendered.
"""
print(
render_document(
self,
search_attr_name,
search_attr_value,
start_i=start_i,
length=length
)
)
cdef int token_by_start(const TokenC* tokens, int length, int start_char) except -2: cdef int token_by_start(const TokenC* tokens, int length, int start_char) except -2:
cdef int i = token_by_char(tokens, length, start_char) cdef int i = token_by_char(tokens, length, start_char)

27
website/docs/api/doc.mdx
View File

@ -520,33 +520,6 @@ JSON data as generated by [`Doc.to_json()`](/api/doc#to_json).
| `validate` | Whether to validate the JSON input against the expected schema for detailed debugging. Defaults to `False`. ~~bool~~ | | `validate` | Whether to validate the JSON input against the expected schema for detailed debugging. Defaults to `False`. ~~bool~~ |
| **RETURNS** | A `Doc` corresponding to the provided JSON. ~~Doc~~ | | **RETURNS** | A `Doc` corresponding to the provided JSON. ~~Doc~~ |
## Doc.inspect {id="inspect",tag="method"}
Outputs to the console a human-readable, tabular representation of all or part
of the document. If any of the first three optional parameters are specified,
the first sentence in the document that corresponds to the specification is
displayed, although a larger portion can be specified with the `length`
parameter; if none of the optional parameters is specified, the whole document
is displayed.
> #### Example
>
> ```python
> doc = nlp("All we have to decide is what to do with the time that is given us. Nobody knows how much time that is.")
> doc.inspect()
> doc.inspect("lemma_", "give")
> doc.inspect("text", "time", start_i=18)
> doc.inspect("text", "time", length=20)
> ```
| Name | Description |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `search_attr_name` | The name of an attribute to search for in order to determine the sentence to render, e.g. `lemma_`. A value only has an effect in conjunction with a value for `search_attr_value`. ~~Optional[str]~~ |
| `search_attr_value` | The value of an attribute to search for in order to determine the sentence to render, e.g. `give`. A value only has an effect in conjunction with a value for `search_attr_name`. ~~Optional[str]~~ |
| _keyword-only_ | |
| `start_i` | The index at which to begin searching or whose containing sentence to render. ~~Optional[int]~~ |
| `length` | The number of tokens to display with their containing sentences. Can be used in isolation to display a portion at the beginning of a document, or in conjunction with the other parameters to display more than one sentence. ~~Optional[int]~~ |
## Doc.retokenize {id="retokenize",tag="contextmanager",version="2.1"} ## Doc.retokenize {id="retokenize",tag="contextmanager",version="2.1"}
Context manager to handle retokenization of the `Doc`. Modifications to the Context manager to handle retokenization of the `Doc`. Modifications to the

26
website/docs/usage/visualizers.mdx
View File

@ -268,6 +268,32 @@ html = displacy.render(doc, style="dep")
display(HTML(html)) display(HTML(html))
``` ```
## Pretty printing directly to the console {id="pprint"}
The `displacy.pprint()` method outputs to the Python console a human-readable,
tabular representation of all or part of a document. If any of the first three
optional arguments are specified, the first sentence in the document that
corresponds to the specification is displayed, although a larger portion can be
specified with the `length` argument; if none of the optional arguments is
specified, the whole document is displayed.
```python {title="pprint() example"}
doc = nlp("All we have to decide is what to do with the time that is given us. Nobody knows how much time that is.")
displacy.pprint(doc)
displacy.pprint(doc, "lemma_", "give")
displacy.pprint(doc, "text", "time", start_i=18)
displacy.pprint(doc, "text", "time", length=20)
```
| Argument | Description |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `doc` | The document to render. ~~Doc~~ |
| `search_attr_name` | The name of an attribute to search for in order to determine the sentence to render, e.g. `lemma_`. A value only has an effect in conjunction with a value for `search_attr_value`. ~~Optional[str]~~ |
| `search_attr_value` | The value of an attribute to search for in order to determine the sentence to render, e.g. `give`. A value only has an effect in conjunction with a value for `search_attr_name`. ~~Optional[str]~~ |
| _keyword-only_ | |
| `start_i` | The index at which to begin searching or whose containing sentence to render. ~~Optional[int]~~ |
| `length` | The number of tokens to display with their containing sentences. Can be used in isolation to display a portion at the beginning of a document, or in conjunction with the other parameters to display more than one sentence. ~~Optional[int]~~ |
## Rendering HTML {id="html"} ## Rendering HTML {id="html"}
If you don't need the web server and just want to generate the markup – for If you don't need the web server and just want to generate the markup – for