From 7a9e5d8164014abaf1485f5b90f0e99a0f159d06 Mon Sep 17 00:00:00 2001
From: Erwan Rouchet <rouchet@teklia.com>
Date: Tue, 24 Nov 2020 16:49:38 +0100
Subject: [PATCH] Deprecate TranscriptionType
---
arkindex_worker/reporting.py | 36 +++++++----
arkindex_worker/worker.py | 52 +++++++++++----
tests/test_elements_worker.py | 117 ++++++++++------------------------
tests/test_reporting.py | 68 ++++++++++++++------
4 files changed, 143 insertions(+), 130 deletions(-)
diff --git a/arkindex_worker/reporting.py b/arkindex_worker/reporting.py
index 1f0736f1..caa80aaf 100644
--- a/arkindex_worker/reporting.py
+++ b/arkindex_worker/reporting.py
@@ -1,6 +1,7 @@
# -*- coding: utf-8 -*-
import json
import traceback
+import warnings
from collections import Counter
from datetime import datetime
@@ -30,8 +31,8 @@ class Reporter(object):
"started": datetime.utcnow().isoformat(),
# Created element counts, by type slug
"elements": {},
- # Created transcription counts, by type
- "transcriptions": {},
+ # Created transcriptions count
+ "transcriptions": 0,
# Created classification counts, by class
"classifications": {},
# Created entities ({"id": "", "type": "", "name": ""}) from this element
@@ -80,26 +81,35 @@ class Reporter(object):
)
element["classifications"] = dict(counter)
- def add_transcription(self, element_id, type, type_count=1):
+ def add_transcription(self, element_id, type=None, type_count=None):
"""
Report creating a transcription on an element.
- Multiple transcriptions with the same type and parent can be declared with the type_count parameter.
+ Multiple transcriptions with the same parent can be declared with the type_count parameter.
"""
- transcriptions = self._get_element(element_id)["transcriptions"]
- transcriptions.setdefault(type, 0)
- transcriptions[type] += type_count
+ if type_count is None:
+ if isinstance(type, int):
+ type_count, type = type, None
+ else:
+ type_count = 1
+
+ if type is not None:
+ warnings.warn(
+ "Transcription types have been deprecated and will be removed in the next release.",
+ FutureWarning,
+ )
+
+ self._get_element(element_id)["transcriptions"] += type_count
def add_transcriptions(self, element_id, transcriptions):
"""
Report one or more transcriptions at once.
"""
assert isinstance(transcriptions, list), "A list is required for transcriptions"
- element = self._get_element(element_id)
- # Retrieve the previous existing transcription counts, if any
- counter = Counter(**element["transcriptions"])
- # Add the new ones
- counter.update([transcription["type"] for transcription in transcriptions])
- element["transcriptions"] = dict(counter)
+ warnings.warn(
+ "Reporter.add_transcriptions is deprecated due to transcription types being removed. Please use Reporter.add_transcription(element_id, count) instead.",
+ FutureWarning,
+ )
+ self.add_transcription(element_id, len(transcriptions))
def add_entity(self, element_id, entity_id, type, name):
"""
diff --git a/arkindex_worker/worker.py b/arkindex_worker/worker.py
index 7e7dfb37..6a089f1c 100644
--- a/arkindex_worker/worker.py
+++ b/arkindex_worker/worker.py
@@ -5,6 +5,7 @@ import logging
import os
import sys
import uuid
+import warnings
from enum import Enum
from pathlib import Path
@@ -366,22 +367,36 @@ class ElementsWorker(BaseWorker):
return sub_element["id"]
- def create_transcription(self, element, text, type, score):
+ def create_transcription(self, element, text, type=None, score=None):
"""
- Create a transcription on the given element through API
+ Create a transcription on the given element through the API.
+
+ Transcription types are deprecated; please call this method using
+ `create_transcription(element, text, score)` instead of
+ `create_transcription(element, text, type, score)`.
"""
assert element and isinstance(
element, Element
), "element shouldn't be null and should be of type Element"
- assert type and isinstance(
- type, TranscriptionType
- ), "type shouldn't be null and should be of type TranscriptionType"
assert text and isinstance(
text, str
), "text shouldn't be null and should be of type str"
+
+ # When score is not set and type is not a transcription type, grab the score from `type`.
+ # Allows create_transcription(element, text, score) and (element, text, type, score)
+ # for forwards compatibility after transcription types get deleted.
+ if score is None and not isinstance(type, TranscriptionType):
+ score, type = type, None
+ elif isinstance(type, TranscriptionType):
+ warnings.warn(
+ "Transcription types are deprecated and will be removed in the next release.",
+ FutureWarning,
+ )
+
assert (
isinstance(score, float) and 0 <= score <= 1
), "score shouldn't be null and should be a float in [0..1] range"
+
if self.is_read_only:
logger.warning(
"Cannot create transcription as this worker is in read-only mode"
@@ -393,12 +408,11 @@ class ElementsWorker(BaseWorker):
id=element.id,
body={
"text": text,
- "type": type.value,
"worker_version": self.worker_version_id,
"score": score,
},
)
- self.report.add_transcription(element.id, type.value)
+ self.report.add_transcription(element.id)
def create_classification(
self, element, ml_class, confidence, high_confidence=False
@@ -495,10 +509,14 @@ class ElementsWorker(BaseWorker):
return entity["id"]
def create_element_transcriptions(
- self, element, sub_element_type, transcription_type, transcriptions
+ self, element, sub_element_type, transcription_type=None, transcriptions=None
):
"""
Create multiple sub elements with their transcriptions on the given element through API
+
+ Transcription types are deprecated; please call this method using
+ `create_element_transcriptions(element, sub_element_type, transcriptions)` instead of
+ `create_element_transcriptions(element, sub_element_type, transcription_type, transcriptions)`.
"""
assert element and isinstance(
element, Element
@@ -506,9 +524,20 @@ class ElementsWorker(BaseWorker):
assert sub_element_type and isinstance(
sub_element_type, str
), "sub_element_type shouldn't be null and should be of type str"
- assert transcription_type and isinstance(
+
+ # When transcriptions are not set and transcription_type is not a valid transcription type,
+ # take transcriptions from `transcription_type`.
+ # Allows for forwards compatibility after transcription types get deleted.
+ if transcriptions is None and not isinstance(
transcription_type, TranscriptionType
- ), "transcription_type shouldn't be null and should be of type TranscriptionType"
+ ):
+ transcriptions, transcription_type = transcription_type, None
+ elif isinstance(transcription_type, TranscriptionType):
+ warnings.warn(
+ "Transcription types are deprecated and will be removed in the next release.",
+ FutureWarning,
+ )
+
assert transcriptions and isinstance(
transcriptions, list
), "transcriptions shouldn't be null and should be of type list"
@@ -548,7 +577,6 @@ class ElementsWorker(BaseWorker):
id=element.id,
body={
"element_type": sub_element_type,
- "transcription_type": transcription_type.value,
"worker_version": self.worker_version_id,
"transcriptions": transcriptions,
"return_elements": True,
@@ -560,7 +588,7 @@ class ElementsWorker(BaseWorker):
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"], transcription_type.value)
+ self.report.add_transcription(annotation["id"])
return annotations
diff --git a/tests/test_elements_worker.py b/tests/test_elements_worker.py
index e0b7dd49..1eea89a4 100644
--- a/tests/test_elements_worker.py
+++ b/tests/test_elements_worker.py
@@ -649,7 +649,6 @@ def test_create_transcription_wrong_element(mock_elements_worker):
mock_elements_worker.create_transcription(
element=None,
text="i am a line",
- type=TranscriptionType.Line,
score=0.42,
)
assert str(e.value) == "element shouldn't be null and should be of type Element"
@@ -658,47 +657,37 @@ def test_create_transcription_wrong_element(mock_elements_worker):
mock_elements_worker.create_transcription(
element="not element type",
text="i am a line",
- type=TranscriptionType.Line,
score=0.42,
)
assert str(e.value) == "element shouldn't be null and should be of type Element"
-def test_create_transcription_wrong_type(mock_elements_worker):
+def test_create_transcription_type_warning(responses, mock_elements_worker):
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
-
- with pytest.raises(AssertionError) as e:
- mock_elements_worker.create_transcription(
- element=elt,
- text="i am a line",
- type=None,
- score=0.42,
- )
- assert (
- str(e.value) == "type shouldn't be null and should be of type TranscriptionType"
+ responses.add(
+ responses.POST,
+ f"http://testserver/api/v1/element/{elt.id}/transcription/",
+ status=200,
)
- with pytest.raises(AssertionError) as e:
+ with pytest.warns(FutureWarning) as w:
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=1234,
+ type=TranscriptionType.Word,
score=0.42,
)
+ assert len(w) == 1
assert (
- str(e.value) == "type shouldn't be null and should be of type TranscriptionType"
+ w[0].message.args[0]
+ == "Transcription types are deprecated and will be removed in the next release."
)
- with pytest.raises(AssertionError) as e:
- mock_elements_worker.create_transcription(
- element=elt,
- text="i am a line",
- type="not_a_transcription_type",
- score=0.42,
- )
- assert (
- str(e.value) == "type shouldn't be null and should be of type TranscriptionType"
- )
+ assert len(responses.calls) == 2
+ assert [call.request.url for call in responses.calls] == [
+ "http://testserver/api/v1/workers/versions/12341234-1234-1234-1234-123412341234/",
+ f"http://testserver/api/v1/element/{elt.id}/transcription/",
+ ]
def test_create_transcription_wrong_text(mock_elements_worker):
@@ -730,7 +719,6 @@ def test_create_transcription_wrong_score(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score=None,
)
assert (
@@ -741,7 +729,6 @@ def test_create_transcription_wrong_score(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score="wrong score",
)
assert (
@@ -752,7 +739,6 @@ def test_create_transcription_wrong_score(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score=0,
)
assert (
@@ -763,7 +749,6 @@ def test_create_transcription_wrong_score(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score=2.00,
)
assert (
@@ -783,7 +768,6 @@ def test_create_transcription_api_error(responses, mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score=0.42,
)
@@ -805,7 +789,6 @@ def test_create_transcription(responses, mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text="i am a line",
- type=TranscriptionType.Line,
score=0.42,
)
@@ -817,7 +800,6 @@ def test_create_transcription(responses, mock_elements_worker):
assert json.loads(responses.calls[1].request.body) == {
"text": "i am a line",
- "type": "line",
"worker_version": "12341234-1234-1234-1234-123412341234",
"score": 0.42,
}
@@ -1313,7 +1295,6 @@ def test_create_element_transcriptions_wrong_element(mock_elements_worker):
mock_elements_worker.create_element_transcriptions(
element=None,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
assert str(e.value) == "element shouldn't be null and should be of type Element"
@@ -1322,7 +1303,6 @@ def test_create_element_transcriptions_wrong_element(mock_elements_worker):
mock_elements_worker.create_element_transcriptions(
element="not element type",
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
assert str(e.value) == "element shouldn't be null and should be of type Element"
@@ -1335,7 +1315,6 @@ def test_create_element_transcriptions_wrong_sub_element_type(mock_elements_work
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type=None,
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
assert (
@@ -1346,7 +1325,6 @@ def test_create_element_transcriptions_wrong_sub_element_type(mock_elements_work
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type=1234,
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
assert (
@@ -1354,43 +1332,32 @@ def test_create_element_transcriptions_wrong_sub_element_type(mock_elements_work
)
-def test_create_element_transcriptions_wrong_transcription_type(mock_elements_worker):
+def test_create_element_transcriptions_transcription_type_warning(
+ responses, mock_elements_worker
+):
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
-
- with pytest.raises(AssertionError) as e:
- mock_elements_worker.create_element_transcriptions(
- element=elt,
- sub_element_type="page",
- transcription_type=None,
- transcriptions=TRANSCRIPTIONS_SAMPLE,
- )
- assert (
- str(e.value)
- == "transcription_type shouldn't be null and should be of type TranscriptionType"
- )
-
- with pytest.raises(AssertionError) as e:
- mock_elements_worker.create_element_transcriptions(
- element=elt,
- sub_element_type="page",
- transcription_type=1234,
- transcriptions=TRANSCRIPTIONS_SAMPLE,
- )
- assert (
- str(e.value)
- == "transcription_type shouldn't be null and should be of type TranscriptionType"
+ responses.add(
+ responses.POST,
+ f"http://testserver/api/v1/element/{elt.id}/transcriptions/bulk/",
+ status=200,
+ json=[
+ {"id": "word1_1_1", "created": False},
+ {"id": "word1_1_2", "created": False},
+ {"id": "word1_1_3", "created": False},
+ ],
)
- with pytest.raises(AssertionError) as e:
+ with pytest.warns(FutureWarning) as w:
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type="not_a_transcription_type",
+ transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
+ assert len(w) == 1
assert (
- str(e.value)
- == "transcription_type shouldn't be null and should be of type TranscriptionType"
+ w[0].message.args[0]
+ == "Transcription types are deprecated and will be removed in the next release."
)
@@ -1401,7 +1368,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=None,
)
assert str(e.value) == "transcriptions shouldn't be null and should be of type list"
@@ -1410,7 +1376,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=1234,
)
assert str(e.value) == "transcriptions shouldn't be null and should be of type list"
@@ -1419,7 +1384,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1441,7 +1405,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1464,7 +1427,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1487,7 +1449,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1509,7 +1470,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1532,7 +1492,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1555,7 +1514,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1578,7 +1536,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1601,7 +1558,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1620,7 +1576,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1639,7 +1594,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1658,7 +1612,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1677,7 +1630,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1700,7 +1652,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1719,7 +1670,6 @@ def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=[
{
"polygon": [[0, 0], [2000, 0], [2000, 3000], [0, 3000]],
@@ -1751,7 +1701,6 @@ def test_create_element_transcriptions_api_error(responses, mock_elements_worker
mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
@@ -1778,7 +1727,6 @@ def test_create_element_transcriptions(responses, mock_elements_worker):
annotations = mock_elements_worker.create_element_transcriptions(
element=elt,
sub_element_type="page",
- transcription_type=TranscriptionType.Word,
transcriptions=TRANSCRIPTIONS_SAMPLE,
)
@@ -1790,7 +1738,6 @@ def test_create_element_transcriptions(responses, mock_elements_worker):
assert json.loads(responses.calls[1].request.body) == {
"element_type": "page",
- "transcription_type": "word",
"worker_version": "12341234-1234-1234-1234-123412341234",
"transcriptions": TRANSCRIPTIONS_SAMPLE,
"return_elements": True,
diff --git a/tests/test_reporting.py b/tests/test_reporting.py
index 7f1c1cb2..c88ea6bf 100644
--- a/tests/test_reporting.py
+++ b/tests/test_reporting.py
@@ -21,7 +21,7 @@ def test_process():
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {},
"entities": [],
"errors": [],
@@ -36,7 +36,7 @@ def test_add_element():
del element_data["started"]
assert element_data == {
"elements": {"text_line": 1},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {},
"entities": [],
"errors": [],
@@ -54,7 +54,7 @@ def test_add_element_count():
del element_data["started"]
assert element_data == {
"elements": {"text_line": 42},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {},
"entities": [],
"errors": [],
@@ -69,7 +69,7 @@ def test_add_classification():
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {"three": 1},
"entities": [],
"errors": [],
@@ -98,7 +98,7 @@ def test_add_classifications():
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {"three": 3, "two": 2},
"entities": [],
"errors": [],
@@ -107,13 +107,36 @@ def test_add_classifications():
def test_add_transcription():
reporter = Reporter("worker")
- reporter.add_transcription("myelement", "word")
+ reporter.add_transcription("myelement")
assert "myelement" in reporter.report_data["elements"]
element_data = reporter.report_data["elements"]["myelement"]
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {"word": 1},
+ "transcriptions": 1,
+ "classifications": {},
+ "entities": [],
+ "errors": [],
+ }
+
+
+def test_add_transcription_warning():
+ reporter = Reporter("worker")
+
+ with pytest.warns(FutureWarning) as w:
+ reporter.add_transcription("myelement", "word")
+ assert len(w) == 1
+ assert (
+ w[0].message.args[0]
+ == "Transcription types have been deprecated and will be removed in the next release."
+ )
+
+ assert "myelement" in reporter.report_data["elements"]
+ element_data = reporter.report_data["elements"]["myelement"]
+ del element_data["started"]
+ assert element_data == {
+ "elements": {},
+ "transcriptions": 1,
"classifications": {},
"entities": [],
"errors": [],
@@ -125,13 +148,13 @@ def test_add_transcription_count():
Report multiple transcriptions with the same element and type
"""
reporter = Reporter("worker")
- reporter.add_transcription("myelement", "word", type_count=1337)
+ reporter.add_transcription("myelement", type_count=1337)
assert "myelement" in reporter.report_data["elements"]
element_data = reporter.report_data["elements"]["myelement"]
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {"word": 1337},
+ "transcriptions": 1337,
"classifications": {},
"entities": [],
"errors": [],
@@ -143,22 +166,27 @@ def test_add_transcriptions():
with pytest.raises(AssertionError):
reporter.add_transcriptions("myelement", {"not": "a list"})
- reporter.add_transcriptions("myelement", [{"type": "word"}, {"type": "line"}])
- reporter.add_transcriptions(
- "myelement",
- [
- {"type": "word"},
- {"type": "line", "text": "something"},
- {"type": "word", "confidence": 0.42},
- ],
- )
+ with pytest.warns(FutureWarning) as w:
+ reporter.add_transcriptions("myelement", [{"type": "word"}, {"type": "line"}])
+ reporter.add_transcriptions(
+ "myelement",
+ [
+ {"type": "word"},
+ {"type": "line", "text": "something"},
+ {"type": "word", "confidence": 0.42},
+ ],
+ )
+ assert len(w) == 2
+ assert set(warning.message.args[0] for warning in w) == {
+ "Reporter.add_transcriptions is deprecated due to transcription types being removed. Please use Reporter.add_transcription(element_id, count) instead."
+ }
assert "myelement" in reporter.report_data["elements"]
element_data = reporter.report_data["elements"]["myelement"]
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {"word": 3, "line": 2},
+ "transcriptions": 5,
"classifications": {},
"entities": [],
"errors": [],
@@ -175,7 +203,7 @@ def test_add_entity():
del element_data["started"]
assert element_data == {
"elements": {},
- "transcriptions": {},
+ "transcriptions": 0,
"classifications": {},
"entities": [
{
--
GitLab