Add ability to read .bz2 files (#1059)

CHANGELOG.md

@@ -17,6 +17,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
   cells.
 - `dt.__git_version__` variable containing the commit hash from which the
   package was built.
+- ability to read .bz2 compressed files with fread.
+
 
 #### Fixed
 - Ensure that fread only emits messages to Python from the master thread.

datatable/fread.py

@@ -374,6 +374,13 @@ def _resolve_archive(self, filename, subpath=None):
                 self.logger.debug("Extracting %s into memory" % filename)
             self._text = zf.read()
 
+        elif ext == ".bz2":
+            import bz2
+            zf = bz2.open(filename, mode="rb")
+            if self._verbose:
+                self.logger.debug("Extracting %s into memory" % filename)
+            self._text = zf.read()
+
         elif ext == ".xz":
             import lzma
             zf = lzma.open(filename, mode="rb")

tests/fread/test_fread_api.py

@@ -210,6 +210,21 @@ def test_fread_gz_file(tempfile, capsys):
     os.unlink(gzfile)
 
 
+def test_fread_bz2_file(tempfile, capsys):
+    import bz2
+    bzfile = tempfile + ".bz2"
+    with bz2.open(bzfile, "wb") as f:
+        f.write(b"A\n11\n22\n33\n")
+    try:
+        d0 = dt.fread(bzfile, verbose=True)
+        out, err = capsys.readouterr()
+        assert d0.internal.check()
+        assert d0.topython() == [[11, 22, 33]]
+        assert ("Extracting %s into memory" % bzfile) in out
+    finally:
+        os.remove(bzfile)
+
+
 def test_fread_zip_file_1(tempfile, capsys):
     import zipfile
     zfname = tempfile + ".zip"