Add extract_raw_text function

1 files changed, 16 insertions, 1 deletions

diff --git a/mammoth/__init__.py b/mammoth/__init__.py
index 59e349f..05e2167 100644
--- a/mammoth/__init__.py
+++ b/mammoth/__init__.py
@@ -1,5 +1,5 @@
 from .results import Result
-from . import docx, conversion, options
+from . import docx, conversion, options, documents
 
 
 def convert_to_html(fileobj, transform_document=None, **kwargs):
@@ -11,3 +11,18 @@ def convert_to_html(fileobj, transform_document=None, **kwargs):
             **options.read_options(kwargs)
         )
     )
+
+
+def extract_raw_text(fileobj):
+    return docx.read(fileobj).map(extract_raw_text_from_element)
+
+
+def extract_raw_text_from_element(element):
+    if isinstance(element, documents.Text):
+        return element.value
+    else:
+        text = "".join(map(extract_raw_text_from_element, element.children))
+        if isinstance(element, documents.Paragraph):
+            return text + "\n\n"
+        else:
+            return text