From f8e167d4359f1b2734f3b0033040f2023139a9cf Mon Sep 17 00:00:00 2001
From: Eva Bardou <ebardou@teklia.com>
Date: Tue, 23 Mar 2021 17:40:28 +0100
Subject: [PATCH] Fix existing tests
---
arkindex_worker/worker.py | 87 ++++++++++++++++++---------------
tests/data/cache/lines.sqlite | Bin 12288 -> 20480 bytes
tests/data/cache/tables.sqlite | Bin 12288 -> 20480 bytes
tests/test_cache.py | 39 ++++++++++++++-
4 files changed, 85 insertions(+), 41 deletions(-)
diff --git a/arkindex_worker/worker.py b/arkindex_worker/worker.py
index 655464cf..e386f40f 100644
--- a/arkindex_worker/worker.py
+++ b/arkindex_worker/worker.py
@@ -512,20 +512,25 @@ class ElementsWorker(BaseWorker):
self.report.add_transcription(element.id)
- # Store transcription in local cache
- try:
- to_insert = [
- CachedTranscription(
- id=convert_str_uuid_to_hex(created["id"]),
- element_id=convert_str_uuid_to_hex(element.id),
- text=created["text"],
- confidence=created["confidence"],
- worker_version_id=convert_str_uuid_to_hex(self.worker_version_id),
+ if self.cache:
+ # Store transcription in local cache
+ try:
+ to_insert = [
+ CachedTranscription(
+ id=convert_str_uuid_to_hex(created["id"]),
+ element_id=convert_str_uuid_to_hex(element.id),
+ text=created["text"],
+ confidence=created["confidence"],
+ worker_version_id=convert_str_uuid_to_hex(
+ self.worker_version_id
+ ),
+ )
+ ]
+ self.cache.insert("transcriptions", to_insert)
+ except sqlite3.IntegrityError as e:
+ logger.warning(
+ f"Couldn't save created transcription in local cache: {e}"
)
- ]
- self.cache.insert("transcriptions", to_insert)
- except sqlite3.IntegrityError as e:
- logger.warning(f"Couldn't save created transcription in local cache: {e}")
def create_classification(
self, element, ml_class, confidence, high_confidence=False
@@ -676,27 +681,30 @@ class ElementsWorker(BaseWorker):
},
)
- created_ids = []
- elements_to_insert = []
- transcriptions_to_insert = []
- parent_id_hex = convert_str_uuid_to_hex(element.id)
- worker_version_id_hex = convert_str_uuid_to_hex(self.worker_version_id)
- for index, annotation in enumerate(annotations):
- transcription = transcriptions[index]
- element_id_hex = convert_str_uuid_to_hex(annotation["id"])
+ for annotation in annotations:
if annotation["created"]:
logger.debug(
f"A sub_element of {element.id} with type {sub_element_type} was created during transcriptions bulk creation"
)
self.report.add_element(element.id, sub_element_type)
+ self.report.add_transcription(annotation["id"])
- if annotation["id"] not in created_ids:
+ if self.cache:
+ # Store transcriptions and their associated element (if created) in local cache
+ created_ids = []
+ elements_to_insert = []
+ transcriptions_to_insert = []
+ parent_id_hex = convert_str_uuid_to_hex(element.id)
+ worker_version_id_hex = convert_str_uuid_to_hex(self.worker_version_id)
+ for index, annotation in enumerate(annotations):
+ transcription = transcriptions[index]
+ element_id_hex = convert_str_uuid_to_hex(annotation["id"])
+ if annotation["created"] and annotation["id"] not in created_ids:
# TODO: Retrieve real element_name through API
elements_to_insert.append(
CachedElement(
id=element_id_hex,
parent_id=parent_id_hex,
- name="test",
type=sub_element_type,
polygon=json.dumps(transcription["polygon"]),
worker_version_id=worker_version_id_hex,
@@ -704,25 +712,24 @@ class ElementsWorker(BaseWorker):
)
created_ids.append(annotation["id"])
- self.report.add_transcription(annotation["id"])
-
- transcriptions_to_insert.append(
- CachedTranscription(
- # TODO: Retrieve real transcription_id through API
- id=convert_str_uuid_to_hex(uuid.uuid4()),
- element_id=element_id_hex,
- text=transcription["text"],
- confidence=transcription["score"],
- worker_version_id=worker_version_id_hex,
+ transcriptions_to_insert.append(
+ CachedTranscription(
+ # TODO: Retrieve real transcription_id through API
+ id=convert_str_uuid_to_hex(uuid.uuid4()),
+ element_id=element_id_hex,
+ text=transcription["text"],
+ confidence=transcription["score"],
+ worker_version_id=worker_version_id_hex,
+ )
)
- )
- # Store transcriptions and their associated element (if created) in local cache
- try:
- self.cache.insert("elements", elements_to_insert)
- self.cache.insert("transcriptions", transcriptions_to_insert)
- except sqlite3.IntegrityError as e:
- logger.warning(f"Couldn't save created transcriptions in local cache: {e}")
+ try:
+ self.cache.insert("elements", elements_to_insert)
+ self.cache.insert("transcriptions", transcriptions_to_insert)
+ except sqlite3.IntegrityError as e:
+ logger.warning(
+ f"Couldn't save created transcriptions in local cache: {e}"
+ )
return annotations
diff --git a/tests/data/cache/lines.sqlite b/tests/data/cache/lines.sqlite
index ea881e4f1bb2143f560ca81ac6435842494c95f5..d7c476d4c629e98913b2c1f4edf4f66cf3f70fe5 100644
GIT binary patch
delta 446
zcmZojXjs5FL0XW7fq{V)h+%+fqK>gB3xl5hO<w*V3@p4g41D+bkMq{>E!tSf!Rywf
z%*-yXsma*FSdy5OlUh=gm{*)!lvz-cnV(mT%42a3a&-)GRS0o(@^Mu_k((^cui=xL
zlbV~FR}!C@q7dd7<m}-Xq+x8Nso>`yqTm<m<D<i+00bqe6(tHGt`R^n6!GNzytK@e
z)V$<W1)wcHlV|elxS=U=^AB?MboW#6c8%0P*rf?n@8%lh>gVhltN;}**2qlJ<kGZe
zVH5Y)oP3sFLLSAn#qoxyeAdnP`4km-c!6QY#LvgT-^I_jSx|wApQDP2&DU3z-FNaq
zeW}S8^tq8RtB6N_xk6%5szPOcslENJhwke{svb@bl$V+OL7s)9gb}Dy5~%Z`zWn45
V`T`)#Z|ISllasHAu6U7x006wphu8oB
delta 56
zcmZozz}S#5L0XWBfq{V;h+%+nqK+|8P|yA*FaHk)CcgU&eE0c}Zx$5D=i7XrPf-y7
D9GnaW
diff --git a/tests/data/cache/tables.sqlite b/tests/data/cache/tables.sqlite
index efc107cd7506757f92df1ee011b670738228b8b2..f8027fdfbd148d0240047ea2facab93bb2ced474 100644
GIT binary patch
delta 325
zcmZojXjs5FL0XWBfq{V)h+%+fqK>gB6N8@pO<w*V3@p4g41D+bkMq{>E!tSf!Rywf
z%*-yXsma*FSdy5OlUh=gm{*)!lvz-cnV(mT%42a3a&-)GRS0o(@^Mu_k((^cui=xL
zlbV~FR}!C@q7dd7<m}-Xq+x8Nso>`yqTm<m<D<i+00bqe6(tHGt`R^n6!GNzytK@e
z)V$<W1)wcHlV|elxS=U=^AB?MboW#6c8%0P*rf?n@8%lh>gVhltN;}**2qlJ<kGZe
fVH5Y)oP3sFLLSAn#qoxyeAdnP`4klw2`B&n<g#Fh
delta 56
zcmZozz}S#5L0XWJfq{V;h+%+nqK+|8P|yA*FaHk)CcgU&eE0c}Zx$5D=i7XrPf-y7
D98nAe
diff --git a/tests/test_cache.py b/tests/test_cache.py
index fb3c28a1..c71f9332 100644
--- a/tests/test_cache.py
+++ b/tests/test_cache.py
@@ -6,7 +6,7 @@ from pathlib import Path
import pytest
-from arkindex_worker.cache import CachedElement, LocalDB
+from arkindex_worker.cache import CachedElement, CachedTranscription, LocalDB
from arkindex_worker.utils import convert_str_uuid_to_hex
FIXTURES = Path(__file__).absolute().parent / "data/cache"
@@ -30,6 +30,26 @@ ELEMENTS_TO_INSERT = [
),
),
]
+TRANSCRIPTIONS_TO_INSERT = [
+ CachedTranscription(
+ id=convert_str_uuid_to_hex("11111111-1111-1111-1111-111111111111"),
+ element_id=convert_str_uuid_to_hex("11111111-1111-1111-1111-111111111111"),
+ text="Hello!",
+ confidence=0.42,
+ worker_version_id=convert_str_uuid_to_hex(
+ "56785678-5678-5678-5678-567856785678"
+ ),
+ ),
+ CachedTranscription(
+ id=convert_str_uuid_to_hex("22222222-2222-2222-2222-222222222222"),
+ element_id=convert_str_uuid_to_hex("22222222-2222-2222-2222-222222222222"),
+ text="How are you?",
+ confidence=0.42,
+ worker_version_id=convert_str_uuid_to_hex(
+ "56785678-5678-5678-5678-567856785678"
+ ),
+ ),
+]
def test_init_non_existent_path():
@@ -108,6 +128,10 @@ def test_insert_existing_lines():
cache.insert("elements", ELEMENTS_TO_INSERT)
assert str(e.value) == "UNIQUE constraint failed: elements.id"
+ with pytest.raises(sqlite3.IntegrityError) as e:
+ cache.insert("transcriptions", TRANSCRIPTIONS_TO_INSERT)
+ assert str(e.value) == "UNIQUE constraint failed: transcriptions.id"
+
with open(db_path, "rb") as after_file:
after = after_file.read()
@@ -128,3 +152,16 @@ def test_insert():
)
assert [CachedElement(**dict(row)) for row in generated_rows] == ELEMENTS_TO_INSERT
+
+ cache.insert("transcriptions", TRANSCRIPTIONS_TO_INSERT)
+ generated_rows = cache.cursor.execute("SELECT * FROM transcriptions").fetchall()
+
+ expected_cache = LocalDB(f"{FIXTURES}/lines.sqlite")
+ assert (
+ generated_rows
+ == expected_cache.cursor.execute("SELECT * FROM transcriptions").fetchall()
+ )
+
+ assert [
+ CachedTranscription(**dict(row)) for row in generated_rows
+ ] == TRANSCRIPTIONS_TO_INSERT
--
GitLab