Issue number 65

pyproject.toml

@@ -110,7 +110,6 @@ ignore = [
     "ANN101",  # Missing type annotation for self in method
     "ANN102",  # Missing type annotation for cls in classmethod
     "PLR0913", # Too many arguments to function call (> 5)
-    "E501",    # Line too long
     "C901",    # Function is too complex
     "PLR0912", # Too many branches (>= 12)
     ]

sec_parser/processing_engine/core.py

@@ -13,19 +13,19 @@
     HighlightedTextClassifier,
 )
 from sec_parser.processing_steps.image_classifier import ImageClassifier
-from sec_parser.processing_steps.individual_semantic_element_extractor.individual_semantic_element_extractor import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.individual_semantic_element_extractor import (  # noqa: E501
     IndividualSemanticElementExtractor,
 )
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.image_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.image_check import (  # noqa: E501
     ImageCheck,
 )
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.table_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.table_check import (  # noqa: E501
     TableCheck,
 )
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.top_section_title_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.top_section_title_check import (  # noqa: E501
     TopSectionTitleCheck,
 )
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.xbrl_tag_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.xbrl_tag_check import (  # noqa: E501
     XbrlTagCheck,
 )
 from sec_parser.processing_steps.introductory_section_classifier import (
@@ -62,7 +62,7 @@
     from sec_parser.processing_steps.abstract_classes.abstract_processing_step import (
         AbstractProcessingStep,
     )
-    from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+    from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
         AbstractSingleElementCheck,
     )
     from sec_parser.semantic_elements.abstract_semantic_element import (

sec_parser/processing_engine/html_tag.py

@@ -297,7 +297,9 @@ def get_approx_table_metrics(self) -> ApproxTableMetrics | None:
             self._approx_table_metrics,
             ApproxTableMetrics,
         ):
-            msg = f"Invalid type for _approx_table_metrics: {type(self._approx_table_metrics).__name__}"
+            msg = (f"Invalid type for _approx_table_metrics: "
+                   f"{type(self._approx_table_metrics).__name__}"
+                   )
             raise ValueError(msg)
 
         return self._approx_table_metrics

sec_parser/processing_steps/__init__.py

@@ -5,15 +5,15 @@
 section identification, title parsing, and text extraction, etc.
 """
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
 )
 from sec_parser.processing_steps.abstract_classes.abstract_processing_step import (
     AbstractProcessingStep,
 )
 from sec_parser.processing_steps.empty_element_classifier import EmptyElementClassifier
 from sec_parser.processing_steps.image_classifier import ImageClassifier
-from sec_parser.processing_steps.individual_semantic_element_extractor.individual_semantic_element_extractor import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.individual_semantic_element_extractor import (  # noqa: E501
     IndividualSemanticElementExtractor,
 )
 from sec_parser.processing_steps.supplementary_text_classifier import (

sec_parser/processing_steps/empty_element_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/highlighted_text_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/image_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/individual_semantic_element_extractor/individual_semantic_element_extractor.py

@@ -3,7 +3,7 @@
 from typing import TYPE_CHECKING, Callable
 
 from sec_parser.exceptions import SecParserValueError
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )
@@ -13,7 +13,7 @@
 from sec_parser.semantic_elements.semantic_elements import NotYetClassifiedElement
 
 if TYPE_CHECKING:  # pragma: no cover
-    from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+    from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
         AbstractSingleElementCheck,
     )
     from sec_parser.semantic_elements.abstract_semantic_element import (

sec_parser/processing_steps/individual_semantic_element_extractor/single_element_checks/abstract_single_element_check.py

@@ -14,10 +14,13 @@ class AbstractSingleElementCheck(ABC):
     def contains_single_element(self, element: AbstractSemanticElement) -> bool | None:
         """
         Designed to work as series of subsequent checks.
-        - Returning None means that the check is inconclusive, and the next check should be performed.
-        - Returning True means that no further checks are necessary, and the HTML element will be
+        - Returning None means that the check is inconclusive, and the next check should
+          be performed.
+        - Returning True means that no further checks are necessary, and the HTML
+          element will be
         later be able to be converted into a semantic element without any splits.
-        - Returning False means that the HTML element will be split into multiple semantic elements
+        - Returning False means that the HTML element will be split into multiple
+          semantic elements
         of type NotYetClassifiedElement.
         """
         raise NotImplementedError  # pragma: no cover

sec_parser/processing_steps/individual_semantic_element_extractor/single_element_checks/image_check.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
     AbstractSingleElementCheck,
 )
 

sec_parser/processing_steps/individual_semantic_element_extractor/single_element_checks/table_check.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
     AbstractSingleElementCheck,
 )
 

sec_parser/processing_steps/individual_semantic_element_extractor/single_element_checks/top_section_title_check.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
     AbstractSingleElementCheck,
 )
 from sec_parser.processing_steps.top_section_manager_for_10q import (

sec_parser/processing_steps/individual_semantic_element_extractor/single_element_checks/xbrl_tag_check.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (
+from sec_parser.processing_steps.individual_semantic_element_extractor.single_element_checks.abstract_single_element_check import (  # noqa: E501
     AbstractSingleElementCheck,
 )
 

sec_parser/processing_steps/introductory_section_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/page_header_classifier.py

@@ -4,7 +4,7 @@
 from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/page_number_classifier.py

@@ -5,7 +5,7 @@
 from enum import Enum, auto
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )
@@ -95,7 +95,10 @@ def _classify_elements(
             return element
 
         element.processing_log.add_item(
-            message=f"Matches the most common (x{self._most_common_candidate_count}) candidate: {candidate}",
+            message = (f"Matches the most common (x"
+                       f"{self._most_common_candidate_count})"
+                       f"candidate: {candidate}"
+                       ),
             log_origin=self.__class__.__name__,
         )
         return PageNumberElement.create_from_element(

sec_parser/processing_steps/supplementary_text_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/table_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/table_of_contents_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )
@@ -18,7 +18,8 @@
 
 class TableOfContentsClassifier(AbstractElementwiseProcessingStep):
     """
-    TableOfContentsClassifier class for converting elements into TableOfContentsElement instances.
+    TableOfContentsClassifier class for converting elements into TableOfContentsElement
+    instances.
 
     This step scans through a list of semantic elements and changes it,
     primarily by replacing suitable candidates with TableOfContentsElement instances.

sec_parser/processing_steps/text_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )

sec_parser/processing_steps/text_element_merger.py

@@ -4,7 +4,7 @@
 from typing import TYPE_CHECKING, cast
 
 from sec_parser.processing_engine.html_tag import HtmlTag
-from sec_parser.processing_steps.abstract_classes.abstract_element_batch_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_element_batch_processing_step import (  # noqa: E501
     AbstractElementBatchProcessingStep,
 )
 from sec_parser.semantic_elements.abstract_semantic_element import (
@@ -28,9 +28,14 @@ class TextElementMerger(AbstractElementBatchProcessingStep):
     into a single TextElement(<span></span><span></span>).
 
     Intended to fix weird formatting artifacts, such as:
-        <ix:nonnumeric contextref="c-1" name="us-gaap:PropertyPlantAndEquipmentTextBlock" id="f-989" escape="true">
-            <span style="background-color:#ffffff;color:#000000;font-family:'Arial',sans-serif;font-size:10pt;font-weight:400;line-height:120%">Property and equipment, net, co</span>
-            <span style="color:#000000;font-family:'Arial',sans-serif;font-size:10pt;font-weight:400;line-height:120%">nsisted of the following (in millions):</span>
+        <ix:nonnumeric contextref="c-1"
+        name="us-gaap:PropertyPlantAndEquipmentTextBlock" id="f-989" escape="true">
+            <span style="background-color:#ffffff;color:#000000;font-family:'Arial',
+            sans-serif;font-size:10pt;font-weight:400;line-height:120%">Property and
+            equipment, net, co</span>
+            <span style="color:#000000;font-family:'Arial',sans-serif;font-size:10pt;
+            font-weight:400;line-height:120%">nsisted of the following (in millions):
+            </span>
         </ix:nonnumeric>
     Notice, how text is split into two spans, even though it's a single sentence.
     Source: https://www.sec.gov/Archives/edgar/data/1652044/000165204423000094/goog-20230930.htm
@@ -77,13 +82,16 @@ def _merge(
             [e.html_tag for e in elements],
         )
         merged_processing_log = elements[0].processing_log.copy()
-        # After merging, we retain the processing log of the first element and drop the logs of the others.
-        # This is because the merged text element now represents a single entity, and we want to avoid
-        # log duplication or confusion about which part of the merged text the logs refer to.
+        # After merging, we retain the processing log of the first element and drop the
+        # logs of the others. This is because the merged text element now represents a
+        # single entity, and we want to avoid log duplication or confusion about which
+        # part of the merged text the logs refer to.
         dropped_logs = [e.processing_log for e in elements[1:]]
         if any(dropped_logs):
             merged_processing_log.add_item(
-                message="Merged multiple TextElements. Processing logs from subsequent elements are dropped.",
+                message = ("Merged multiple TextElements. "
+                           "Processing logs from subsequent elements are dropped."
+                           ),
                 log_origin=cls.__name__,
             )
         return TextElement(

sec_parser/processing_steps/title_classifier.py

@@ -2,7 +2,7 @@
 
 from typing import TYPE_CHECKING
 
-from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (
+from sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step import (  # noqa: E501
     AbstractElementwiseProcessingStep,
     ElementProcessingContext,
 )