More 7.X Prediction Text Attrs + Poe Improvement

.github/workflows/python.yaml

@@ -34,21 +34,19 @@ jobs:
         poetry install
 
     - name: Run Black
-      run: poetry run poe black-check
+      run: poetry poe black-check
 
     - name: Run Ruff
-      run: poetry run poe ruff-check
+      run: poetry poe ruff-check
 
     - name: Run Mypy
-      run: poetry run poe mypy
+      run: poetry poe mypy
 
     - name: Run Pytest
-      run: poetry run poe test
+      run: poetry poe test
 
     - name: Install Extra Dependencies
-      run: |
-        poetry env use ${{ matrix.python-version }}
-        poetry install --all-extras
+      run: poetry install --all-extras
 
     - name: Run Pytest on Extras
-      run: poetry run poe test
+      run: poetry poe test

README.md

@@ -68,10 +68,10 @@ Formatting, linting, type checking, and tests are defined as
 [Poe](https://poethepoet.natn.io/) tasks in `pyproject.toml`.
 
 ```bash
-poetry run poe {format,check,test,all}
+poetry poe {format,check,test,all}
 ```
 
-Code changes or additions should pass `poetry run poe all` before opening a PR.
+Code changes or additions should pass `poetry poe all` before opening a PR.
 
 
 ### Tests
@@ -83,23 +83,23 @@ By default, only required unit tests are executed. Extra unit tests and integrat
 tests are skipped.
 
 ```bash
-poetry run poe {test,all}
+poetry poe {test,all}
 ```
 
 Extra unit tests are skipped when their dependencies are not installed. To execute extra
 unit tests, install one or more extras and run the tests.
 
 ```bash
 poetry install --all-extras
-poetry run poe {test,all}
+poetry poe {test,all}
 ```
 
 Integration tests make API calls to an IPA environment and require a host and API token
 to execute. These tests create datasets, setup workflows, and train models. **Expect
 them to take tens of minutes to run.**
 
 ```bash
-poetry run poe test-integration \
+poetry poe test-integration \
     --host try.indico.io \
     --token indico_api_token.txt
 ```

indico_toolkit/__init__.py

@@ -21,4 +21,4 @@
     "ToolkitStaggeredLoopError",
     "ToolkitStatusError",
 )
-__version__ = "6.14.0"
+__version__ = "6.14.1"

indico_toolkit/etloutput/__init__.py

@@ -1,7 +1,7 @@
 from typing import TYPE_CHECKING
 
 from ..results import NULL_BOX, NULL_SPAN, Box, Span
-from ..results.utilities import get, has
+from ..results.utils import get, has
 from .cell import Cell, CellType
 from .errors import EtlOutputError, TableCellNotFoundError, TokenNotFoundError
 from .etloutput import EtlOutput

indico_toolkit/etloutput/cell.py

@@ -2,7 +2,7 @@
 from enum import Enum
 
 from ..results import NULL_SPAN, Box, Span
-from ..results.utilities import get
+from ..results.utils import get
 from .range import Range
 
 

indico_toolkit/etloutput/range.py

@@ -1,6 +1,6 @@
 from dataclasses import dataclass
 
-from ..results.utilities import get
+from ..results.utils import get
 
 
 @dataclass(order=True, frozen=True)

indico_toolkit/etloutput/table.py

@@ -2,7 +2,7 @@
 from operator import attrgetter
 
 from ..results import Box
-from ..results.utilities import get
+from ..results.utils import get
 from .cell import Cell
 
 

indico_toolkit/etloutput/token.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 
 from ..results import Box, Span
-from ..results.utilities import get
+from ..results.utils import get
 
 
 @dataclass(frozen=True)

indico_toolkit/results/__init__.py

@@ -23,7 +23,7 @@
 )
 from .result import Result
 from .review import Review, ReviewType
-from .utilities import get
+from .utils import get
 
 if TYPE_CHECKING:
     from collections.abc import Awaitable, Callable

indico_toolkit/results/document.py

@@ -1,6 +1,6 @@
 from dataclasses import dataclass
 
-from .utilities import get
+from .utils import get
 
 
 @dataclass(frozen=True, order=True)

indico_toolkit/results/model.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from enum import Enum
 
-from .utilities import get, has
+from .utils import get, has
 
 
 class ModelGroupType(Enum):

indico_toolkit/results/normalization.py

@@ -1,7 +1,7 @@
 import re
 from typing import TYPE_CHECKING
 
-from .utilities import get, has
+from .utils import get, has
 
 if TYPE_CHECKING:
     from collections.abc import Iterator

indico_toolkit/results/predictionlist.py

@@ -13,7 +13,7 @@
     Unbundling,
 )
 from .review import Review, ReviewType
-from .utilities import nfilter
+from .utils import nfilter
 
 if TYPE_CHECKING:
     from collections.abc import Callable, Collection, Container, Iterable

indico_toolkit/results/predictions/box.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
-from ..utilities import get
+from ..utils import get
 
 if TYPE_CHECKING:
     from typing import Final

indico_toolkit/results/predictions/citation.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
-from ..utilities import get
+from ..utils import get
 from .span import NULL_SPAN, Span
 
 if TYPE_CHECKING:

indico_toolkit/results/predictions/classification.py

@@ -2,7 +2,7 @@
 from typing import TYPE_CHECKING
 
 from ..review import Review
-from ..utilities import get, omit
+from ..utils import get, omit
 from .prediction import Prediction
 
 if TYPE_CHECKING:

indico_toolkit/results/predictions/documentextraction.py

@@ -2,7 +2,7 @@
 from typing import TYPE_CHECKING
 
 from ..review import Review
-from ..utilities import get, has, omit
+from ..utils import get, has, omit
 from .extraction import Extraction
 from .group import Group
 from .span import NULL_SPAN, Span
@@ -127,8 +127,10 @@ def to_v1_dict(self) -> "dict[str, Any]":
             "end": self.span.end,
         }
 
-        prediction["normalized"]["formatted"] = self.text
-        prediction["text"] = self.text  # 6.10 sometimes reverts to raw text in review.
+        if self.text != get(prediction, str, "normalized", "formatted"):
+            prediction["normalized"]["formatted"] = self.text
+            prediction["normalized"]["text"] = self.text
+            prediction["text"] = self.text
 
         if self.accepted:
             prediction["accepted"] = True
@@ -149,8 +151,10 @@ def to_v3_dict(self) -> "dict[str, Any]":
             "spans": [span.to_dict() for span in self.spans],
         }
 
-        prediction["normalized"]["formatted"] = self.text
-        prediction["text"] = self.text  # 6.10 sometimes reverts to raw text in review.
+        if self.text != get(prediction, str, "normalized", "formatted"):
+            prediction["normalized"]["formatted"] = self.text
+            prediction["normalized"]["text"] = self.text
+            prediction["text"] = self.text
 
         if self.accepted:
             prediction["accepted"] = True

indico_toolkit/results/predictions/formextraction.py

@@ -3,7 +3,7 @@
 from typing import TYPE_CHECKING
 
 from ..review import Review
-from ..utilities import get, has, omit
+from ..utils import get, has, omit
 from .box import Box
 from .extraction import Extraction
 
@@ -97,18 +97,23 @@ def _to_dict(self) -> "dict[str, Any]":
         }
 
         if self.type == FormExtractionType.CHECKBOX:
-            prediction["normalized"]["structured"]["checked"] = self.checked
-            prediction["normalized"]["formatted"] = (
-                "Checked" if self.checked else "Unchecked"
-            )
+            prediction["normalized"]["structured"] = {"checked": self.checked}
+            text = "Checked" if self.checked else "Unchecked"
+            prediction["normalized"]["formatted"] = text
+            prediction["normalized"]["text"] = self.text
+            prediction["text"] = self.text
         elif self.type == FormExtractionType.SIGNATURE:
-            prediction["normalized"]["structured"]["signed"] = self.signed
-            prediction["normalized"]["formatted"] = (
-                "Signed" if self.signed else "Unsigned"
-            )
+            prediction["normalized"]["structured"] = {"signed": self.signed}
+            text = "Signed" if self.signed else "Unsigned"
+            prediction["normalized"]["formatted"] = text
+            # Don't overwrite the text of the signature stored in these attributes.
+            # prediction["normalized"]["text"] = self.text
+            # prediction["text"] = self.text
         elif self.type == FormExtractionType.TEXT:
-            prediction["normalized"]["formatted"] = self.text
-            prediction["text"] = self.text  # 6.10 sometimes reverts to text in review.
+            if self.text != get(prediction, str, "normalized", "formatted"):
+                prediction["normalized"]["formatted"] = self.text
+                prediction["normalized"]["text"] = self.text
+                prediction["text"] = self.text
 
         if self.accepted:
             prediction["accepted"] = True

indico_toolkit/results/predictions/group.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
-from ..utilities import get
+from ..utils import get
 
 if TYPE_CHECKING:
     from typing import Any

indico_toolkit/results/predictions/span.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
-from ..utilities import get
+from ..utils import get
 
 if TYPE_CHECKING:
     from typing import Any, Final

indico_toolkit/results/predictions/summarization.py

@@ -2,7 +2,7 @@
 from typing import TYPE_CHECKING
 
 from ..review import Review
-from ..utilities import get, has, omit
+from ..utils import get, has, omit
 from .citation import NULL_CITATION, Citation
 from .extraction import Extraction
 

indico_toolkit/results/predictions/unbundling.py

@@ -2,7 +2,7 @@
 from typing import TYPE_CHECKING
 
 from ..review import Review
-from ..utilities import get, omit
+from ..utils import get, omit
 from .prediction import Prediction
 
 if TYPE_CHECKING:

indico_toolkit/results/result.py

@@ -10,7 +10,7 @@
 from .predictionlist import PredictionList
 from .predictions import Prediction
 from .review import Review, ReviewType
-from .utilities import get
+from .utils import get
 
 if TYPE_CHECKING:
     from typing import Any

indico_toolkit/results/review.py

@@ -1,7 +1,7 @@
 from dataclasses import dataclass
 from enum import Enum
 
-from .utilities import get
+from .utils import get
 
 
 class ReviewType(Enum):