feat(docker): improve dockerfile build (#220)

* refactor(docker): remove unnecessary root user

The USER root directive isn't needed directly after FROM

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* fix(docker): use generic nobody nogroup default instead of uid gid

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* fix(docker): build app from source locally instead of installing package

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* fix(docker): use correct files in dockerignore

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* chore(docker): dont install recommended packages with git

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* fix(docker): run apt as non-interactive

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>

* Update Dockerfile to new package structure, and fix streaming bugs.

---------

Signed-off-by: Sebastian Yaghoubi <sebastianyaghoubi@gmail.com>
Co-authored-by: afourney <adamfo@microsoft.com>

packages/markitdown/src/markitdown/_markitdown.py

@@ -327,6 +327,17 @@ class MarkItDown:
         elif base_guess.extension is not None:
             placeholder_filename = "placeholder" + base_guess.extension
 
+        # Check if we have a seekable stream. If not, load the entire stream into memory.
+        if not stream.seekable():
+            buffer = io.BytesIO()
+            while True:
+                chunk = stream.read(4096)
+                if not chunk:
+                    break
+                buffer.write(chunk)
+            buffer.seek(0)
+            stream = buffer
+
         # Add guesses based on stream content
         for guess in _guess_stream_info_from_stream(
             file_stream=stream, filename_hint=placeholder_filename

packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py

@@ -7,6 +7,7 @@ from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
 # Try loading optional (but in this case, required) dependencies
 # Save reporting of any exceptions for later
 _dependency_exc_info = None
+olefile = None
 try:
     import olefile
 except ImportError:
@@ -48,7 +49,7 @@ class OutlookMsgConverter(DocumentConverter):
         # Brute force, check if we have an OLE file
         cur_pos = file_stream.tell()
         try:
-            if not olefile.isOleFile(file_stream):
+            if olefile and not olefile.isOleFile(file_stream):
                 return False
         finally:
             file_stream.seek(cur_pos)