chg: apply ruff checks.

Author: AlbertWeichselbraun

docs/conf.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # inscriptis documentation build configuration file, created by
 # sphinx-quickstart on Sat Dec 14 06:42:31 2019.
@@ -23,8 +22,7 @@
 sys.path.insert(0, os.path.abspath("."))
 sys.path.insert(0, os.path.abspath("./../src"))
 
-from inscriptis.metadata import __copyright__, __author__, __version__
-
+from inscriptis.metadata import __author__, __copyright__, __version__
 
 # -- General configuration ------------------------------------------------
 

examples/custom-html-handling.py

@@ -10,16 +10,15 @@
     "Welcome to <b>Chur</b>" is rendered as "Welcome to **Chur**".
 """
 
-from typing import Dict
+from lxml.html import fromstring
 
 from inscriptis import ParserConfig
 from inscriptis.html_engine import Inscriptis
 from inscriptis.model.html_document_state import HtmlDocumentState
 from inscriptis.model.tag import CustomHtmlTagHandlerMapping
-from lxml.html import fromstring
 
 
-def my_handle_start_b(state: HtmlDocumentState, _: Dict) -> None:
+def my_handle_start_b(state: HtmlDocumentState, _: dict) -> None:
     """Handle the opening <b> tag."""
     state.tags[-1].write("**")
 
@@ -38,7 +37,5 @@ def my_handle_end_b(state: HtmlDocumentState) -> None:
 HTML = "Welcome to <b>Chur</b>"
 
 html_tree = fromstring(HTML)
-inscriptis = Inscriptis(
-    html_tree, ParserConfig(custom_html_tag_handler_mapping=MY_MAPPING)
-)
+inscriptis = Inscriptis(html_tree, ParserConfig(custom_html_tag_handler_mapping=MY_MAPPING))
 print(inscriptis.get_text())

pyproject.toml

@@ -66,11 +66,26 @@ sources = ["src"]
 
 # code formatting with ruff
 [tool.ruff]
-line-length = 88
+line-length = 120
 target-version = "py311"  # adjust as needed
 extend-exclude = ["*.html", "*.json", "*.txt", "/a", "/b"]
 src = ["src", "tests", "benchmarking", "examples"]
 
 [tool.ruff.format]
 quote-style = "double"
 
+[tool.ruff.lint]
+select = [
+    # pycodestyle
+    "E",
+    # Pyflakes
+    "F",
+    # pyupgrade
+    "UP",
+    # flake8-bugbear
+    "B",
+    # flake8-simplify
+    "SIM",
+    # isort
+    "I",
+]

src/inscriptis/__init__.py

@@ -60,18 +60,18 @@
 """
 
 import re
-from typing import Dict, Optional, Any
-from inscriptis.model.config import ParserConfig
+from typing import Any
 
 from lxml.etree import ParserError
-from lxml.html import fromstring, HtmlElement
+from lxml.html import HtmlElement, fromstring
 
+from inscriptis.model.config import ParserConfig
 from inscriptis.html_engine import Inscriptis
 
 RE_STRIP_XML_DECLARATION = re.compile(r"^<\?xml [^>]+?\?>")
 
 
-def _get_html_tree(html_content: str) -> Optional[HtmlElement]:
+def _get_html_tree(html_content: str) -> HtmlElement | None:
     """Obtain the HTML parse tree for the given HTML content.
 
     Args:
@@ -108,9 +108,7 @@ def get_text(html_content: str, config: ParserConfig = None) -> str:
     return Inscriptis(html_tree, config).get_text() if html_tree is not None else ""
 
 
-def get_annotated_text(
-    html_content: str, config: ParserConfig = None
-) -> Dict[str, Any]:
+def get_annotated_text(html_content: str, config: ParserConfig = None) -> dict[str, Any]:
     """Return a dictionary of the extracted text and annotations.
 
     Notes:

src/inscriptis/annotation/__init__.py

@@ -1,6 +1,5 @@
 """The model used for saving annotations."""
 
-from typing import List
 from typing import NamedTuple
 
 from inscriptis.html_properties import HorizontalAlignment
@@ -30,12 +29,12 @@ class Annotation(NamedTuple):
 
 
 def horizontal_shift(
-    annotations: List[Annotation],
+    annotations: list[Annotation],
     content_width: int,
     line_width: int,
     align: HorizontalAlignment,
     shift: int = 0,
-) -> List[Annotation]:
+) -> list[Annotation]:
     r"""Shift annotations based on the given line's formatting.
 
     Adjusts the start and end indices of annotations based on the line's
@@ -60,6 +59,4 @@ def horizontal_shift(
     else:
         h_align = shift + (line_width - content_width) // 2
 
-    return [
-        Annotation(a.start + h_align, a.end + h_align, a.metadata) for a in annotations
-    ]
+    return [Annotation(a.start + h_align, a.end + h_align, a.metadata) for a in annotations]

src/inscriptis/annotation/output/__init__.py

@@ -26,13 +26,13 @@
 
 """
 
-from typing import Dict, Any
+from typing import Any
 
 
 class AnnotationProcessor:
     """An AnnotationProcessor is called for formatting annotations."""
 
-    def __call__(self, annotated_text: Dict[str, str]) -> Any:
+    def __call__(self, annotated_text: dict[str, str]) -> Any:
         """Format the given text and annotations.
 
         Args:

src/inscriptis/annotation/output/html.py

@@ -2,7 +2,7 @@
 
 from collections import defaultdict
 from itertools import cycle
-from typing import Dict, Any, List
+from typing import Any
 
 from inscriptis.annotation.output import AnnotationProcessor
 
@@ -18,13 +18,11 @@ class HtmlExtractor(AnnotationProcessor):
 
     verbatim = True
 
-    def __call__(self, annotated_text: Dict[str, Any]) -> str:
+    def __call__(self, annotated_text: dict[str, Any]) -> str:
         tag_dict = defaultdict(list)
 
         for start, end, label in reversed(annotated_text["label"]):
-            tag_dict[start].append(
-                f'<span class="{label}-label">{label}</span><span class="{label}">'
-            )
+            tag_dict[start].append(f'<span class="{label}-label">{label}</span><span class="{label}">')
             tag_dict[end].insert(0, "</span>")
 
         tagged_content = [
@@ -43,7 +41,7 @@ def __call__(self, annotated_text: Dict[str, Any]) -> str:
         return "".join(tagged_content) + "</pre></body></html>"
 
     @staticmethod
-    def _get_label_colors(labels: List[str]) -> Dict[str, str]:
+    def _get_label_colors(labels: list[str]) -> dict[str, str]:
         """Compute the mapping between annotation labels and colors.
 
         The used color schema is available in the global variable COLOR_SCHEMA.
@@ -57,7 +55,7 @@ def _get_label_colors(labels: List[str]) -> Dict[str, str]:
         """
         return dict(zip({a[2] for a in sorted(labels)}, cycle(COLOR_SCHEMA)))
 
-    def _get_css(self, labels: List[str]) -> str:
+    def _get_css(self, labels: list[str]) -> str:
         """Compute the CSS to be included into the HTML output.
 
         Args:
@@ -71,18 +69,18 @@ def _get_css(self, labels: List[str]) -> str:
         css = []
         for label, color in sorted(self._get_label_colors(labels).items()):
             css.append(
-                "pre{{"
+                "pre{"
                 "  position: relative;\n"
-                "}}\n"
-                ".{label} {{\n"
-                "  background-color: {color};\n"
+                "}\n"
+                f".{label} {{\n"
+                f"  background-color: {color};\n"
                 "  border-radius: 0.4em;\n"
-                "}}\n"
-                ".{label}-label {{\n"
+                "}\n"
+                f".{label}-label {{\n"
                 "  top: -1.0em;\n"
-                '  content: "{label}";\n'
+                f'  content: "{label}";\n'
                 "  position: absolute;\n"
-                "  background-color: {color};\n"
-                "  font-size: 75%; }}\n".format(label=label, color=color)
+                f"  background-color: {color};\n"
+                "  font-size: 75%; }\n"
             )
         return "\n".join(css)

src/inscriptis/annotation/output/surface.py

@@ -1,6 +1,6 @@
 """Surface Form Annotation Processor."""
 
-from typing import Dict, Any
+from typing import Any
 
 from inscriptis.annotation.output import AnnotationProcessor
 
@@ -10,7 +10,7 @@ class SurfaceExtractor(AnnotationProcessor):
 
     verbatim = False
 
-    def __call__(self, annotated_text: Dict[str, Any]) -> Dict[str, Any]:
+    def __call__(self, annotated_text: dict[str, Any]) -> dict[str, Any]:
         """
         Add information on the surface forms to the annotated_text dictionary.
 
@@ -22,9 +22,6 @@ def __call__(self, annotated_text: Dict[str, Any]) -> Dict[str, Any]:
             An extended dictionary which contains the extracted surface-forms
             of the annotations under the key 'surface'.
         """
-        surface_forms = [
-            (label, annotated_text["text"][start:end])
-            for start, end, label in annotated_text["label"]
-        ]
+        surface_forms = [(label, annotated_text["text"][start:end]) for start, end, label in annotated_text["label"]]
         annotated_text["surface"] = surface_forms
         return annotated_text

src/inscriptis/annotation/output/xml.py

@@ -1,7 +1,7 @@
 """XML Annotation processor."""
 
 from collections import defaultdict
-from typing import Dict, Any
+from typing import Any
 
 from inscriptis.annotation.output import AnnotationProcessor
 
@@ -11,7 +11,7 @@ class XmlExtractor(AnnotationProcessor):
 
     verbatim = True
 
-    def __call__(self, annotated_text: Dict[str, Any], root_element="content"):
+    def __call__(self, annotated_text: dict[str, Any], root_element="content"):
         tag_dict = defaultdict(list)
         for start, end, tag in reversed(annotated_text["label"]):
             tag_dict[start].append(f"<{tag}>")

src/inscriptis/annotation/parser.py

@@ -19,9 +19,8 @@
 
 from collections import defaultdict
 from copy import copy
-from typing import Dict, Tuple, List
 
-from inscriptis.model.html_element import HtmlElement, DEFAULT_HTML_ELEMENT
+from inscriptis.model.html_element import DEFAULT_HTML_ELEMENT, HtmlElement
 
 
 class ApplyAnnotation:
@@ -87,7 +86,7 @@ def __init__(self, css_profile, model: dict):
         self.css = css_profile
 
     @staticmethod
-    def _parse(model: dict) -> Tuple[Dict, List]:
+    def _parse(model: dict) -> tuple[dict, list]:
         """Compute the AnnotationModel from a model dictionary.
 
         Returns: