From 28b16a8106bcd5313a04c85b5df34bb191d6904d Mon Sep 17 00:00:00 2001
From: Saul Pwanson <code@saul.pw>
Date: Thu, 16 May 2024 14:13:27 -0700
Subject: [PATCH] [path-] fix undercounted progress for multibyte chars #2323

Co-authored-by: @midichef
---
 visidata/path.py    | 10 +++++-----
 visidata/threads.py | 10 ++++++++--
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/visidata/path.py b/visidata/path.py
index 1d44a8662..44d136048 100644
--- a/visidata/path.py
+++ b/visidata/path.py
@@ -134,13 +134,13 @@ def read(self, size=-1):
         r = self.fp_orig_read(size)
         if self.prog:
             if r:
-                self.prog.addProgress(len(r))
+                self.prog.addProgress(r)
         return r
 
     def readline(self, size=-1):
         r = self.fp_orig_readline(size)
         if self.prog:
-            self.prog.addProgress(len(r))
+            self.prog.addProgress(r)
         return r
 
     def __getattr__(self, k):
@@ -152,7 +152,7 @@ def __enter__(self):
 
     def __next__(self):
         r = next(self.fp)
-        self.prog.addProgress(len(r))
+        self.prog.addProgress(r)
         return r
 
     def __iter__(self):
@@ -160,7 +160,7 @@ def __iter__(self):
             yield from self.fp
         else:
             for line in self.fp:
-                self.prog.addProgress(len(line))
+                self.prog.addProgress(line)
                 yield line
 
     def __exit__(self, type, value, tb):
@@ -332,7 +332,7 @@ def __iter__(self):
         with Progress(total=filesize(self)) as prog:
             with self.open(encoding=vd.options.encoding) as fd:
                 for i, line in enumerate(fd):
-                    prog.addProgress(len(line))
+                    prog.addProgress(line)
                     yield line.rstrip('\n')
 
     def open_bytes(self, mode='rb'):
diff --git a/visidata/threads.py b/visidata/threads.py
index 54e9a369f..c7391fc89 100644
--- a/visidata/threads.py
+++ b/visidata/threads.py
@@ -62,8 +62,10 @@ def __enter__(self):
             self.sheet.progresses.insert(0, self)
         return self
 
-    def addProgress(self, n):
+    def addProgress(self, n:'int|str|bytes'):
         'Increase the progress count by *n*.'
+        if isinstance(n, (str, bytes)):
+            n = len(n)
         self.made += n
         return True
 
@@ -83,9 +85,13 @@ def __init__(self, encoding='utf-8', **kwargs):
         super().__init__(**kwargs)
         self.est_sample = ''
         self.est_charbytes = 1
+        self.encoding = encoding
 
-    def addProgress(self, n:int):
+    def addProgress(self, n:'int|str|bytes'):
         if self.made < self.total:
+            if isinstance(n, (str, bytes)):
+                self.addSample(n)
+                n = len(n)
             return super().addProgress(n * self.est_charbytes)
 
     def addSample(self, s:str):