Fix Ruff issues: remove unnecessary map(), list() calls, use dict comprehensions, remove unused import, fix default parameter, and remove trailing whitespace

Co-authored-by: bact <128572+bact@users.noreply.github.com>

Author: Copilot

pythainlp/benchmarks/word_tokenization.py

@@ -257,5 +257,5 @@ def _find_words_correctly_tokenised(
     """
     ref_b = dict(zip(ref_boundaries, [1] * len(ref_boundaries)))
 
-    labels = tuple(map(lambda x: ref_b.get(x, 0), predicted_boundaries))
+    labels = tuple(ref_b.get(x, 0) for x in predicted_boundaries)
     return labels

pythainlp/cli/benchmark.py

@@ -13,7 +13,7 @@
 
 def _read_file(path):
     with open(path, encoding="utf-8") as f:
-        lines = map(lambda r: r.strip(), f.readlines())
+        lines = (r.strip() for r in f.readlines())
     return list(lines)
 
 

pythainlp/corpus/common.py

@@ -372,7 +372,7 @@ def find_synonyms(word: str) -> list[str]:
             list_synonym.extend(synonyms["synonym"][idx])
             list_synonym.append(synonyms["word"][idx])
 
-    list_synonym = sorted(list(set(list_synonym)))
+    list_synonym = sorted(set(list_synonym))
 
     if word in list_synonym:  # remove same word
         list_synonym.remove(word)

pythainlp/morpheme/word_formation.py

@@ -35,7 +35,7 @@ def nighit(w1: str, w2: str) -> str:
         raise NotImplementedError(f"The function doesn't support {w1}.")
     list_w1 = list(w1)
     list_w2 = list(w2)
-    newword = list()
+    newword = []
     newword.append(list_w1[0])
     newword.append("ั")
     consonant_start = [i for i in list_w2 if i in set(thai_consonants)][0]

pythainlp/tag/blackboard.py

@@ -5,7 +5,7 @@
 
 # defined strings for special characters
 CHAR_TO_ESCAPE = {" ": "_"}
-ESCAPE_TO_CHAR = dict((v, k) for k, v in CHAR_TO_ESCAPE.items())
+ESCAPE_TO_CHAR = {v: k for k, v in CHAR_TO_ESCAPE.items()}
 
 
 # map from Blackboard treebank POS tag to Universal POS tag

pythainlp/tag/orchid.py

@@ -33,7 +33,7 @@
     ";": "<semi_colon>",
     "/": "<slash>",
 }
-ESCAPE_TO_CHAR = dict((v, k) for k, v in CHAR_TO_ESCAPE.items())
+ESCAPE_TO_CHAR = {v: k for k, v in CHAR_TO_ESCAPE.items()}
 
 # map from ORCHID POS tag to Universal POS tag
 # from Korakot Chaovavanich

pythainlp/tokenize/core.py

@@ -6,7 +6,6 @@
 
 from __future__ import annotations
 
-import copy
 import re
 from collections import deque
 from collections.abc import Iterable

pythainlp/tokenize/crfcut.py

@@ -140,7 +140,7 @@ def extract_features(
     """
     if not doc:
         return []
-    
+
     doc_features = []
     # Pad the document with "xxpad" tokens efficiently
     padded_doc = ["xxpad"] * window

pythainlp/tokenize/thaisumcut.py

@@ -31,7 +31,7 @@ def list_to_string(list: list[str]) -> str:
 def middle_cut(sentences: list[str]) -> list[str]:
     if not sentences:
         return []
-    
+
     result_parts = []
     for sentence in sentences:
         sentence_size = len(word_tokenize(sentence, keep_whitespace=False))

pythainlp/transliterate/thai2rom_onnx.py

@@ -127,9 +127,9 @@ def run(self, source_seq, source_seq_len):
 
         outputs = np.zeros((max_len, batch_size, self.target_vocab_size))
 
-        expected_encoder_outputs = list(
-            map(lambda output: output.name, self.encoder.get_outputs())
-        )
+        expected_encoder_outputs = [
+            output.name for output in self.encoder.get_outputs()
+        ]
         encoder_outputs, encoder_hidden, _ = self.encoder.run(
             input_feed={
                 "input_tensor": source_seq,