handle character in the category 'nonspacing mark'

Those characters are ignored, because they decorate
the previous character.

scribble.py

@@ -1,4 +1,37 @@
 # extract icons from dll on windows
 # https://mail.python.org/pipermail/python-win32/2009-April/009078.html
+import re
+import time
 
-print(min(2290538861, 2342622222))
+from highlighted_range import HighlightedRange
+from line import Line
+
+result = []
+
+byte_offset = 123
+text = "2021-09-21 08:40:38,187 [catalina-exec-37] INFO  c.r.c.s.l.SearchAdapter - Fetched 0 fields, 1 folders, 0 content requests for 1 documents; took 763ms (including 0ms to fetch field names). [project=axcelerate.lds_5m_review2, session=37891bc0-a67e-4c43-90c0-c20da567f491, user=r-162] [kttsjx2h.48z.9ls] 2021-09-21 08:47:16,529 [BravaJobHandler-12] INFO  c.r.b.c.f.i.DoneNotifierRunnable - CORE job for 'complete document request with output format xdl (source n.pdf)' complete. Notifying Brava server about completion for numId=LDS_001:00095883.. Extracting and moving XDL and SVG/Thumbs took 31ms (from remote stream from 172.28.60.208:51048,com.recommind.rmi.ssl.SslRmiExporter$CheckedSslRmiClientSocketFactory). Notifying with URL https://localhost:8889/BravaServer/done/xc_E4E99FE32A313D2FBA8D29F846C0EF439E8AE2BE159164D04B2AFD862F714BED_ (context switch time 0ms) [project=axcelerate.lds_5m_review2, session=500380b9-94c5-4740-b30a-81e9f6cd071d, user=r-377] [kttsjx2h.8ys.kai]"
+
+start = time.time()
+line = Line(byte_offset=byte_offset, byte_end=byte_offset + len(text.encode("utf8")), line=text)
+regex = re.compile(r"\w", flags=re.IGNORECASE)
+match_iter = re.finditer(regex, line.line())
+for match in match_iter:
+    start_char = match.start(0)
+    end_char = match.end(0)
+
+    start_column = line.char_to_column(start_char)
+    end_column = line.char_to_column(end_char)
+
+    result.append(HighlightedRange(start_column, end_column - start_column, highlight_full_line=True, brush=None,
+                                   brush_full_line=None))
+
+end = time.time()
+print("duration: %.3f" % ((end - start) * 1000))
+
+result = []
+start = time.time()
+for i in range(0, 10000):
+    result.append(i)
+
+end = time.time()
+print("duration: %.3f" % ((end - start) * 1000))