#15546: Fix {GzipFile,LZMAFile}.read1()'s handling of pathological input data.

Lib/gzip.py

@@ -385,6 +385,9 @@ class GzipFile(io.BufferedIOBase):
             return b''
 
         try:
+            # For certain input data, a single call to _read() may not return
+            # any data. In this case, retry until we get some data or reach EOF.
+            while self.extrasize <= 0:
                 self._read()
         except EOFError:
             pass

Lib/lzma.py

@@ -204,6 +204,9 @@ class LZMAFile(io.BufferedIOBase):
 
     # Fill the readahead buffer if it is empty. Returns False on EOF.
     def _fill_buffer(self):
+        # Depending on the input data, our call to the decompressor may not
+        # return any data. In this case, try again after reading another block.
+        while True:
             if self._buffer:
                 return True
 
@@ -226,7 +229,6 @@ class LZMAFile(io.BufferedIOBase):
                 self._decompressor = LZMADecompressor(**self._init_args)
 
             self._buffer = self._decompressor.decompress(rawblock)
-        return True
 
     # Read data until EOF.
     # If return_data is false, consume the data without returning it.
@@ -284,11 +286,14 @@ class LZMAFile(io.BufferedIOBase):
             return self._read_block(size)
 
     def read1(self, size=-1):
-        """Read up to size uncompressed bytes with at most one read
-        from the underlying stream.
+        """Read up to size uncompressed bytes, while trying to avoid
+        making multiple reads from the underlying stream.
 
         Returns b"" if the file is at EOF.
         """
+        # Usually, read1() calls _fp.read() at most once. However, sometimes
+        # this does not give enough data for the decompressor to make progress.
+        # In this case we make multiple reads, to avoid returning b"".
         self._check_can_read()
         if (size == 0 or self._mode == _MODE_READ_EOF or
             not self._fill_buffer()):

Misc/NEWS

@@ -77,6 +77,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #15546: Fix handling of pathological input data in the read1() method of
+  the BZ2File, GzipFile and LZMAFile classes.
+
 - Issue #13052: Fix IDLE crashing when replace string in Search/Replace dialog
   ended with '\'. Patch by Roger Serwy.