raw_io module: Add text_input and text_output

recipe_modules/raw_io/api.py

Index: recipe_modules/raw_io/api.py
diff --git a/recipe_modules/raw_io/api.py b/recipe_modules/raw_io/api.py
index f788a5f2491b8df9d60f662c703e0cf971c63e21..a6af03d688d4bfcaaf0c786f1b13b9d3b7dadc7e 100644
--- a/recipe_modules/raw_io/api.py
+++ b/recipe_modules/raw_io/api.py
@@ -1,3 +1,4 @@
+# -*- encoding: utf-8 -*-
 # Copyright 2014 The LUCI Authors. All rights reserved.
 # Use of this source code is governed under the Apache License, Version 2.0
 # that can be found in the LICENSE file.
@@ -30,7 +31,8 @@ class InputDataPlaceholder(recipe_util.InputPlaceholder):
       self._backing_file = self.data
     else:  # pragma: no cover
       input_fd, self._backing_file = tempfile.mkstemp(suffix=self.suffix)
-      os.write(input_fd, self.data.encode('utf-8'))
+
+      os.write(input_fd, self.encode_data(self.data))
       os.close(input_fd)
     return [self._backing_file]
 
@@ -43,6 +45,18 @@ class InputDataPlaceholder(recipe_util.InputPlaceholder):
         pass
     self._backing_file = None
 
+  def encode_data(self, data):
+    return data
+
+class InputTextPlaceholder(InputDataPlaceholder):
+  def encode_data(self, data):
+    # Sometimes users give us invalid utf-8 data. They shouldn't, but it does
+    # happen every once and a while. Just ignore it, and replace with �.
+    # We're assuming users only want to write text data out.
+    decoded = self.data.decode('utf-8', 'replace')
+    return decoded.encode('utf-8')
+
+
 
 class OutputDataPlaceholder(recipe_util.OutputPlaceholder):
   def __init__(self, suffix, leak_to, name=None):
@@ -81,6 +95,12 @@ class OutputDataPlaceholder(recipe_util.OutputPlaceholder):
           os.unlink(self._backing_file)
         self._backing_file = None
 
+  def decode(self, result):
+    return result
+
+class OutputTextPlaceholder(OutputDataPlaceholder):
+  def decode(self, result):
+    return result.decode('utf-8', 'replace')
 
 class OutputDataDirPlaceholder(recipe_util.OutputPlaceholder):
   def __init__(self, suffix, leak_to, name=None):
@@ -138,6 +158,14 @@ class RawIOApi(recipe_api.RecipeApi):
 
   @recipe_util.returns_placeholder
   @staticmethod
+  def input_text(data, suffix=''):

[iannucci, 2017/02/02 02:23:30]

docstring (and for input above)

+    return InputTextPlaceholder(data, suffix)
+
+  # TODO(martiniss): Remove this once downstream callers are using text_input
+  # input = text_input
+
+  @recipe_util.returns_placeholder
+  @staticmethod
   def output(suffix='', leak_to=None, name=None):
     """Returns a Placeholder for use as a step argument, or for std{out,err}.
 
@@ -152,6 +180,22 @@ class RawIOApi(recipe_api.RecipeApi):
 
   @recipe_util.returns_placeholder
   @staticmethod
+  def output_text(suffix='', leak_to=None, name=None):
+    """Returns a Placeholder for use as a step argument, or for std{out,err}.

[iannucci, 2017/02/02 02:23:30]

document encoding difference here and text_input.

+
+    If 'leak_to' is None, the placeholder is backed by a temporary file with
+    a suffix 'suffix'. The file is deleted when the step finishes.
+
+    If 'leak_to' is not None, then it should be a Path and placeholder
+    redirects IO to a file at that path. Once step finishes, the file is
+    NOT deleted (i.e. it's 'leaking'). 'suffix' is ignored in that case.
+    """
+    return OutputTextPlaceholder(suffix, leak_to, name=name)
+
+  #output = output_text
+
+  @recipe_util.returns_placeholder
+  @staticmethod
   def output_dir(suffix='', leak_to=None, name=None):
     """Returns a directory Placeholder for use as a step argument.