[pre-commit.ci] pre-commit suggestions (#270)

* [pre-commit.ci] pre-commit suggestions

updates:
- [github.com/pre-commit/pre-commit-hooks: v4.3.0 → v5.0.0](pre-commit/pre-commit-hooks@v4.3.0...v5.0.0)
- [github.com/PyCQA/flake8: 7.1.1 → 7.2.0](PyCQA/flake8@7.1.1...7.2.0)
- [github.com/PyCQA/isort: 5.12.0 → 6.0.1](PyCQA/isort@5.12.0...6.0.1)
- [github.com/psf/black: 19.10b0 → 25.1.0](psf/black@19.10b0...25.1.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: pre-commit-ci[bot]

.pre-commit-config.yaml

@@ -22,30 +22,30 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v5.0.0
     hooks:
       - id: check-yaml
       - id: check-case-conflict
       - id: detect-private-key
       - id: requirements-txt-fixer
 
   - repo: https://github.com/PyCQA/flake8
-    rev: 7.1.1
+    rev: 7.2.0
     hooks:
     -   id: flake8
         args:
         - --select=W605
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 6.0.1
     hooks:
       - id: isort
         name: Format imports
         args: [ --multi-line=3, --trailing-comma, --force-grid-wrap=0, --use-parentheses, --line-width=119, -rc, -ws ]
         exclude: docs/
 
   - repo: https://github.com/psf/black
-    rev: 19.10b0
+    rev: 25.1.0
     hooks:
       - id: black
         name: Format code

nemo_text_processing/fst_alignment/alignment.py

@@ -96,7 +96,7 @@ def parse_args():
 
 
 EPS = "<eps>"
-WHITE_SPACE = "\u23B5"
+WHITE_SPACE = "\u23b5"
 ITN_MODE = "itn"
 TN_MODE = "tn"
 tn_item_special_chars = ["$", "\\", ":", "+", "-", "="]

nemo_text_processing/hybrid/utils.py

@@ -482,7 +482,7 @@ def remove_punctuation(text: str, remove_spaces=True, do_lower=True, lang="en",
 
     text = re.sub(r" +", " ", text)
     if remove_spaces:
-        text = text.replace(" ", "").replace("\u00A0", "").strip()
+        text = text.replace(" ", "").replace("\u00a0", "").strip()
 
     if do_lower:
         text = text.lower()
@@ -515,7 +515,11 @@ def _relax_diff(text):
     return acceptable
 
 
-def get_labels(targets: List[str], norm_texts_weights: List[Tuple[str, str]], lang="en",) -> List[List[str]]:
+def get_labels(
+    targets: List[str],
+    norm_texts_weights: List[Tuple[str, str]],
+    lang="en",
+) -> List[List[str]]:
     """
     Assign labels to generated normalization options (1 - for ground truth, 0 - other options)
     Args:
@@ -605,7 +609,14 @@ def print_df(df):
     prints data frame
     """
     with pd.option_context(
-        "display.max_rows", None, "display.max_columns", None, "display.width", 1000, "display.max_colwidth", 400,
+        "display.max_rows",
+        None,
+        "display.max_columns",
+        None,
+        "display.width",
+        1000,
+        "display.max_colwidth",
+        400,
     ):
         print(df)
 

nemo_text_processing/inverse_text_normalization/ar/taggers/cardinal.py

@@ -33,7 +33,9 @@ def __init__(self, tn_cardinal):
         self.graph = pynini.invert(tn_cardinal.cardinal_numbers).optimize()
 
         optional_minus_graph = pynini.closure(
-            pynutil.insert("negative: ") + pynini.cross("سالب", '"-"') + NEMO_SPACE, 0, 1,
+            pynutil.insert("negative: ") + pynini.cross("سالب", '"-"') + NEMO_SPACE,
+            0,
+            1,
         )
 
         final_graph = optional_minus_graph + pynutil.insert('integer: "') + self.graph + pynutil.insert('"')

nemo_text_processing/inverse_text_normalization/ar/taggers/decimal.py

@@ -36,7 +36,9 @@ def __init__(self, tn_decimal):
         super().__init__(name="decimal", kind="classify")
 
         optional_graph_negative = pynini.closure(
-            pynutil.insert("negative: ") + pynini.cross("سالب", '"true"') + delete_extra_space, 0, 1,
+            pynutil.insert("negative: ") + pynini.cross("سالب", '"true"') + delete_extra_space,
+            0,
+            1,
         )
 
         graph_fractional_part = pynini.invert(tn_decimal.graph_fractional).optimize()

nemo_text_processing/inverse_text_normalization/ar/verbalizers/word.py

@@ -27,6 +27,6 @@ def __init__(self):
         super().__init__(name="word", kind="verbalize")
         chars = pynini.closure(NEMO_CHAR - " ", 1)
         char = pynutil.delete("name:") + delete_space + pynutil.delete("\"") + chars + pynutil.delete("\"")
-        graph = char @ pynini.cdrewrite(pynini.cross(u"\u00A0", " "), "", "", NEMO_SIGMA)
+        graph = char @ pynini.cdrewrite(pynini.cross(u"\u00a0", " "), "", "", NEMO_SIGMA)
 
         self.fst = graph.optimize()

nemo_text_processing/inverse_text_normalization/en/taggers/cardinal.py

@@ -207,7 +207,10 @@ def __init__(self, input_case: str = INPUT_LOWER_CASED):
             + graph_in_thousands
         )
 
-        graph = pynini.union((graph_int | graph_ind) + delete_space + graph_hundreds, graph_zero,)
+        graph = pynini.union(
+            (graph_int | graph_ind) + delete_space + graph_hundreds,
+            graph_zero,
+        )
 
         graph = graph @ pynini.union(
             pynutil.delete(pynini.closure("0")) + pynini.difference(NEMO_DIGIT, "0") + pynini.closure(NEMO_DIGIT), "0"

nemo_text_processing/inverse_text_normalization/en/taggers/date.py

@@ -165,7 +165,11 @@ def __init__(self, ordinal: GraphFst, input_case: str):
             + pynutil.add_weight(year_graph, -YEAR_WEIGHT)
             + pynutil.insert("\"")
         )
-        optional_graph_year = pynini.closure(graph_year, 0, 1,)
+        optional_graph_year = pynini.closure(
+            graph_year,
+            0,
+            1,
+        )
         graph_mdy = month_graph + (
             (delete_extra_space + day_graph) | graph_year | (delete_extra_space + day_graph + graph_year)
         )

nemo_text_processing/inverse_text_normalization/en/taggers/decimal.py

@@ -97,7 +97,9 @@ def __init__(self, cardinal: GraphFst, input_case: str = INPUT_LOWER_CASED):
         point = pynutil.delete("point")
 
         optional_graph_negative = pynini.closure(
-            pynutil.insert("negative: ") + pynini.cross(MINUS, "\"true\"") + delete_extra_space, 0, 1,
+            pynutil.insert("negative: ") + pynini.cross(MINUS, "\"true\"") + delete_extra_space,
+            0,
+            1,
         )
 
         graph_fractional = pynutil.insert("fractional_part: \"") + graph_decimal + pynutil.insert("\"")

nemo_text_processing/inverse_text_normalization/en/taggers/electronic.py

@@ -106,7 +106,13 @@ def __init__(self, input_case: str = INPUT_LOWER_CASED):
             delete_extra_space
             + url_symbols
             + delete_extra_space
-            + (domain | pynini.closure(accepted_username + delete_extra_space,) + accepted_username)
+            + (
+                domain
+                | pynini.closure(
+                    accepted_username + delete_extra_space,
+                )
+                + accepted_username
+            )
         )
 
         protocol_default = (