Merge branch 'extension-autocomplete'

docs/changelog.rst

@@ -32,6 +32,7 @@ latest changes in development for next release
 
   * avoid unicode decode error with html parser (`#147`_ by `@suned`_)
 
+  * enabling autocomplete and improving error handling (`#149`_)
 
 1.5.0
 -----
@@ -335,3 +336,4 @@ latest changes in development for next release
 .. _#146: https://github.com/deanmalmgren/textract/issues/146
 .. _#147: https://github.com/deanmalmgren/textract/issues/147
 .. _#148: https://github.com/deanmalmgren/textract/issues/148
+.. _#149: https://github.com/deanmalmgren/textract/issues/149

textract/cli.py

@@ -8,11 +8,13 @@
 import pkgutil
 import sys
 import six
+import re
+import glob
 
 import argcomplete
 
 from . import VERSION
-from .parsers import DEFAULT_ENCODING
+from .parsers import DEFAULT_ENCODING, _get_available_extensions
 
 
 class AddToNamespaceAction(argparse.Action):
@@ -62,10 +64,8 @@ def get_parser():
     )
     parser.add_argument(
         '--extension', type=str, default=None,
-        choices=_get_available_encodings(),
-        help='Specify the extension of the file (e.g., docx or pdf). '
-             'Extension can be also passed with the '
-             'leading . (e.g., .docx or .pdf).',
+        choices=_get_available_extensions(),
+        help='Specify the extension of the file.',
     )
     parser.add_argument(
         '-m', '--method', default='',

textract/exceptions.py

@@ -16,11 +16,19 @@ class ExtensionNotSupported(CommandLineError):
     def __init__(self, ext):
         self.ext = ext
 
+        from .parsers import _get_available_extensions
+        available_extensions = []
+        for e in _get_available_extensions():
+            if e.startswith('.'):
+                available_extensions.append(e)
+        self.available_extensions_str = ', '.join(available_extensions)
+
     def __str__(self):
         return self.render((
             'The filename extension %(ext)s is not yet supported by\n'
             'textract. Please suggest this filename extension here:\n\n'
-            '    https://github.com/deanmalmgren/textract/issues\n'
+            '    https://github.com/deanmalmgren/textract/issues\n\n'
+            'Available extensions include: %(available_extensions_str)s\n'
         ))
 
 

textract/parsers/__init__.py

@@ -4,6 +4,8 @@
 
 import os
 import importlib
+import glob
+import re
 
 from .. import exceptions
 
@@ -22,6 +24,9 @@
 # the command line interface
 DEFAULT_ENCODING = 'utf_8'
 
+# filename format
+_FILENAME_SUFFIX = '_parser'
+
 
 def process(filename, encoding=DEFAULT_ENCODING, extension=None, **kwargs):
     """This is the core function used for extracting text. It routes the
@@ -55,17 +60,43 @@ def process(filename, encoding=DEFAULT_ENCODING, extension=None, **kwargs):
     # to avoid conflicts with packages that are installed globally
     # (e.g. python's json module), all extension parser modules have
     # the _parser extension
-    rel_module = ext + '_parser'
+    rel_module = ext + _FILENAME_SUFFIX
 
     # If we can't import the module, the file extension isn't currently
     # supported
     try:
         filetype_module = importlib.import_module(
-            rel_module, 'textract.parsers')
+            rel_module, 'textract.parsers'
+        )
     except ImportError:
         raise exceptions.ExtensionNotSupported(ext)
 
     # do the extraction
 
     parser = filetype_module.Parser()
     return parser.process(filename, encoding, **kwargs)
+
+
+def _get_available_extensions():
+    """Get a list of available file extensions to make it easy for
+    tab-completion and exception handling.
+    """
+    extensions = []
+
+    # from filenames
+    parsers_dir = os.path.join(os.path.dirname(__file__))
+    glob_filename = os.path.join(parsers_dir, "*" + _FILENAME_SUFFIX + ".py")
+    ext_re = re.compile(glob_filename.replace('*', "(?P<ext>\w+)"))
+    for filename in glob.glob(glob_filename):
+        ext_match = ext_re.match(filename)
+        ext = ext_match.groups()[0]
+        extensions.append(ext)
+        extensions.append('.' + ext)
+
+    # from relevant synonyms (don't use the '' synonym)
+    for ext in EXTENSION_SYNONYMS.keys():
+        if ext:
+            extensions.append(ext)
+            extensions.append(ext.replace('.', '', 1))
+    extensions.sort()
+    return extensions