Merge pull request #76 from singer-contrib/fix-tests

Fix reading binary files/streams by adjusting encoding to match mode
ets · Jan 6, 2024 · f538266 · f538266
2 parents 1c9a462 + 4072661
commit f538266
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/.gitignore b/.gitignore
@@ -82,6 +82,7 @@ celerybeat-schedule
 .env
 
 # virtualenv
+.venv/
 venv/
 ENV/
 

diff --git a/tap_spreadsheets_anywhere/format_handler.py b/tap_spreadsheets_anywhere/format_handler.py
@@ -32,6 +32,11 @@ def get_streamreader(uri, universal_newlines=True, newline='', open_mode='r', en
     SCHEME_SEP = "://"
     kwargs = kwarg_dispatch.get(uri.split(SCHEME_SEP, 1)[0], lambda: {})()
 
+    # When reading in binary mode, undefine `encoding`.
+    # Otherwise, `smart_open` will return a `TextIOWrapper` in `"r"` mode.
+    # However, reading binary streams needs a `BufferedReader`.
+    if "b" in open_mode:
+        encoding = None
     streamreader = smart_open.open(uri, open_mode, newline=newline, errors='surrogateescape', encoding=encoding, **kwargs)
 
     if not universal_newlines and isinstance(streamreader, StreamReader):
-Original file line number
+Diff line change
@@ Expand Up / @@ -82,6 +82,7 @@ celerybeat-schedule @@
     .env
     # virtualenv
+    .venv/
     venv/
     ENV/
@@ Expand Down @@