diff --git a/arkindex_worker/reporting.py b/arkindex_worker/reporting.py
index 80259de398f4089a3616ab268689441dd0034023..e69b283f21c28887deb011a18a3297be28c9ec57 100644
--- a/arkindex_worker/reporting.py
+++ b/arkindex_worker/reporting.py
@@ -1,7 +1,6 @@
# -*- coding: utf-8 -*-
import json
import traceback
-import warnings
from collections import Counter
from datetime import datetime
@@ -83,35 +82,12 @@ class Reporter(object):
)
element["classifications"] = dict(counter)
- def add_transcription(self, element_id, type=None, type_count=None):
+ def add_transcription(self, element_id, count=1):
"""
Report creating a transcription on an element.
Multiple transcriptions with the same parent can be declared with the type_count parameter.
"""
- 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"
- 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))
+ self._get_element(element_id)["transcriptions"] += count
def add_entity(self, element_id, entity_id, type, name):
"""
diff --git a/arkindex_worker/worker.py b/arkindex_worker/worker.py
index 541cc2869d05bf9b208c7daa3c202342d25c3142..00a3f5507f5340ef784d5be52d714e2413928a81 100644
--- a/arkindex_worker/worker.py
+++ b/arkindex_worker/worker.py
@@ -6,7 +6,6 @@ import os
import sqlite3
import sys
import uuid
-import warnings
from enum import Enum
from pathlib import Path
@@ -183,14 +182,6 @@ class BaseWorker(object):
"""Override this method to implement your own process"""
-class TranscriptionType(Enum):
- Page = "page"
- Paragraph = "paragraph"
- Line = "line"
- Word = "word"
- Character = "character"
-
-
class EntityType(Enum):
Person = "person"
Location = "location"
@@ -488,13 +479,9 @@ class ElementsWorker(BaseWorker):
return created_ids
- def create_transcription(self, element, text, type=None, score=None):
+ def create_transcription(self, element, text, score):
"""
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
@@ -503,17 +490,6 @@ class ElementsWorker(BaseWorker):
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"
@@ -629,15 +605,9 @@ class ElementsWorker(BaseWorker):
return entity["id"]
- def create_element_transcriptions(
- self, element, sub_element_type, transcription_type=None, transcriptions=None
- ):
+ def create_element_transcriptions(self, element, sub_element_type, transcriptions):
"""
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
@@ -645,20 +615,6 @@ 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"
-
- # 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
- ):
- 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"
diff --git a/tests/test_elements_worker/test_transcriptions.py b/tests/test_elements_worker/test_transcriptions.py
index 466ee2ae84fc356df6e8abf743a6e8953bd2130b..3d603fcb7f6e548f6398ee9330a47e75194ff2a7 100644
--- a/tests/test_elements_worker/test_transcriptions.py
+++ b/tests/test_elements_worker/test_transcriptions.py
@@ -5,7 +5,6 @@ import pytest
from apistar.exceptions import ErrorResponse
from arkindex_worker.models import Element
-from arkindex_worker.worker import TranscriptionType
TRANSCRIPTIONS_SAMPLE = [
{
@@ -44,35 +43,6 @@ def test_create_transcription_wrong_element(mock_elements_worker):
assert str(e.value) == "element shouldn't be null and should be of type Element"
-def test_create_transcription_type_warning(responses, mock_elements_worker):
- elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
- responses.add(
- responses.POST,
- f"http://testserver/api/v1/element/{elt.id}/transcription/",
- status=200,
- )
-
- with pytest.warns(FutureWarning) as w:
- mock_elements_worker.create_transcription(
- element=elt,
- text="i am a line",
- type=TranscriptionType.Word,
- score=0.42,
- )
- assert len(w) == 1
- assert (
- w[0].message.args[0]
- == "Transcription types are deprecated and will be removed in the next release."
- )
-
- assert len(responses.calls) == 3
- assert [call.request.url for call in responses.calls] == [
- "http://testserver/api/v1/user/",
- "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):
elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
@@ -80,7 +50,6 @@ def test_create_transcription_wrong_text(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text=None,
- type=TranscriptionType.Line,
score=0.42,
)
assert str(e.value) == "text shouldn't be null and should be of type str"
@@ -89,7 +58,6 @@ def test_create_transcription_wrong_text(mock_elements_worker):
mock_elements_worker.create_transcription(
element=elt,
text=1234,
- type=TranscriptionType.Line,
score=0.42,
)
assert str(e.value) == "text shouldn't be null and should be of type str"
@@ -232,35 +200,6 @@ def test_create_element_transcriptions_wrong_sub_element_type(mock_elements_work
)
-def test_create_element_transcriptions_transcription_type_warning(
- responses, mock_elements_worker
-):
- elt = Element({"id": "12341234-1234-1234-1234-123412341234"})
- 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.warns(FutureWarning) as w:
- mock_elements_worker.create_element_transcriptions(
- element=elt,
- sub_element_type="page",
- transcription_type=TranscriptionType.Word,
- transcriptions=TRANSCRIPTIONS_SAMPLE,
- )
- assert len(w) == 1
- assert (
- w[0].message.args[0]
- == "Transcription types are deprecated and will be removed in the next release."
- )
-
-
def test_create_element_transcriptions_wrong_transcriptions(mock_elements_worker):
elt = Element({"zone": None})
diff --git a/tests/test_reporting.py b/tests/test_reporting.py
index af19dd1e6d374aaa7caee5afba893f33451492a2..3332702e1962c98132bb74effa54a813a7195438 100644
--- a/tests/test_reporting.py
+++ b/tests/test_reporting.py
@@ -126,36 +126,12 @@ def test_add_transcription():
}
-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": [],
- "metadata": [],
- "errors": [],
- }
-
-
def test_add_transcription_count():
"""
Report multiple transcriptions with the same element and type
"""
reporter = Reporter("worker")
- reporter.add_transcription("myelement", type_count=1337)
+ reporter.add_transcription("myelement", 1337)
assert "myelement" in reporter.report_data["elements"]
element_data = reporter.report_data["elements"]["myelement"]
del element_data["started"]
@@ -169,39 +145,6 @@ def test_add_transcription_count():
}
-def test_add_transcriptions():
- reporter = Reporter("worker")
- with pytest.raises(AssertionError):
- reporter.add_transcriptions("myelement", {"not": "a list"})
-
- 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": 5,
- "classifications": {},
- "entities": [],
- "metadata": [],
- "errors": [],
- }
-
-
def test_add_entity():
reporter = Reporter("worker")
reporter.add_entity(