From d3210741db1272b29555a58164ba828439c15d5c Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Thu, 5 Feb 2026 14:07:46 +0000 Subject: [PATCH 1/2] Initial plan From 4847bb7c1f5186f4ac7330a8c6c067a8533a3dd6 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Thu, 5 Feb 2026 14:11:26 +0000 Subject: [PATCH 2/2] Fix type annotation in _find_word_boundaries docstring Co-authored-by: bact <128572+bact@users.noreply.github.com> --- pythainlp/benchmarks/word_tokenization.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pythainlp/benchmarks/word_tokenization.py b/pythainlp/benchmarks/word_tokenization.py index 356717cdf..3afaeaa13 100644 --- a/pythainlp/benchmarks/word_tokenization.py +++ b/pythainlp/benchmarks/word_tokenization.py @@ -246,7 +246,7 @@ def _binary_representation(txt: str, verbose: bool = False) -> "np.ndarray": def _find_word_boundaries(bin_reps: "np.ndarray") -> list[tuple[int, int]]: """Find the starting and ending location of each word. - :param str bin_reps: binary representation of a text + :param numpy.ndarray bin_reps: binary representation of a text :return: list of tuples (start, end) :rtype: list[tuple[int, int]]