Fix the prefix spaces and punctuations; upgrade to version 0.9 (#49)

k2-fsa · Aug 8, 2023 · 98ffea2 · 98ffea2
1 parent 63b18db
commit 98ffea2
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 2 deletions.
diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.12 FATAL_ERROR)
 project(textsearch)
 
-set(TS_VERSION "0.8")
+set(TS_VERSION "0.9")
 
 set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/lib")
 set(CMAKE_LIBRARY_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/lib")

diff --git a/pyproject.toml b/pyproject.toml
@@ -10,7 +10,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fasttextsearch"
-version = "0.8"
+version = "0.9"
 authors = [
   { name="Next-gen Kaldi development team", email="[email protected]" },
 ]

diff --git a/textsearch/python/textsearch/match.py b/textsearch/python/textsearch/match.py
@@ -1091,6 +1091,10 @@ def _split_into_segments(
 
     for seg in segments:
         begin_pos = aligns[seg[0]]["ref_pos"]
+        # trim the prefix space
+        while chr(target_source.binary_text[begin_pos]) == " ":
+            begin_pos += 1
+
         while begin_pos >= 1:
             current_token = chr(target_source.binary_text[begin_pos - 1])
             if current_token in PUCTUATIONS["left"]:
@@ -1132,6 +1136,9 @@ def _split_into_segments(
             end_time = aligns[succeeding_index]["hyp_time"]
 
         hyp_begin_pos = aligns[seg[0]]["hyp_pos"]
+        while chr(query_source.binary_text[hyp_begin_pos]) == " ":
+            hyp_begin_pos += 1
+
         hyp_end_pos = aligns[seg[1]]["hyp_pos"]
         hyp = "".join(
             [